US20100070510A1 - System and method for rating electronic documents - Google Patents

System and method for rating electronic documents Download PDF

Info

Publication number
US20100070510A1
US20100070510A1 US12/406,865 US40686509A US2010070510A1 US 20100070510 A1 US20100070510 A1 US 20100070510A1 US 40686509 A US40686509 A US 40686509A US 2010070510 A1 US2010070510 A1 US 2010070510A1
Authority
US
United States
Prior art keywords
rating
document
information
content
documents
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US12/406,865
Inventor
Sumit Agarwal
Gokul Rajaram
Leora Ruth Wiseman
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Google LLC
Original Assignee
Google LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Google LLC filed Critical Google LLC
Priority to US12/406,865 priority Critical patent/US20100070510A1/en
Assigned to GOOGLE INC. reassignment GOOGLE INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: WISEMAN, LEORA RUTH, AGARWAL, SUMIT, RAJARAM, GOKUL
Publication of US20100070510A1 publication Critical patent/US20100070510A1/en
Assigned to GOOGLE LLC reassignment GOOGLE LLC CHANGE OF NAME (SEE DOCUMENT FOR DETAILS). Assignors: GOOGLE INC.
Abandoned legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0257User requested
    • G06Q30/0258Registration
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99932Access augmentation or optimizing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99935Query augmenting and refining, e.g. inexact access
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99937Sorting

Definitions

  • the present invention relates to a system and method for rating a document by aggregating a plurality of ratings from partner evaluators.
  • ads and other content are often targeted to specific audiences that may have an interest in the content. For instance, ads directed to males may be displayed during nationally televised football events because they draw large numbers of male viewers. Similarly, an ad for an airline may be displayed at an Internet search engine site when a user submits a query including the word “plane.”
  • One method of matching appropriate content to an audience is to manually review the content before distributing it to the audience.
  • manual review there are problems associated with manual review.
  • one significant drawback of manual rating systems and methods is the time and expense involved in reviewing the content.
  • various embodiments of the present inventions may be directed to a system and a method for rating documents such as advertisements.
  • a system and method for rating an electronic document such as an advertisement is provided. Rating information is received from one or more evaluators. A signal relevant to one or more criteria is received and a determination is made whether to deliver the document in response to the signal based on the criteria and the rating information from the one or more evaluators.
  • a method and system of determining an aggregate rating for a document involve receiving rating information for an electronic document from a plurality of evaluators, wherein at least one evaluator is associated with a trust score, and determining an aggregate content rating for the electronic document by aggregating the rating information from at least two of the plurality of evaluators, wherein the rating information for at least one evaluator is considered in association with the trust score for that evaluator.
  • a method and system for transmitting a signal that receives a rated document involves transmitting a signal to a server, the server interpreting the signal as being associated with one or more criteria for a document and determining whether a document is to be delivered based in part on rating information received from a plurality of evaluators for one or more documents and whether the one or more documents relate to the criteria. Any identified documents are then received in response to the signal.
  • a method and system for receiving documents and rating them involves receiving one or more documents from a server system and providing rating information to the server system for use by the server system in determining whether to deliver the one or more documents in response to requests for the one or more documents based on the rating provided.
  • FIG. 1 depicts a system for rating an electronic document according to an embodiment of the invention.
  • FIG. 2 depicts a networked environment for operation of a system for rating a document according to an embodiment of the invention.
  • FIG. 3 depicts a flow chart illustrating an exemplary method for rating an electronic document according to an embodiment of the invention.
  • FIG. 4 depicts an exemplary electronic document according to an embodiment of the invention.
  • FIG. 5 depicts an exemplary content rating request according to an embodiment of the invention.
  • FIG. 6 depicts an exemplary content rating according to an embodiment of the invention.
  • Embodiments described herein solve many problems with existing systems and methods.
  • One problem facing internet content providers is evaluating a large number of documents (such as advertisements presented through its services) to determine whether each is appropriate for a wide variety of different users.
  • Embodiments described herein overcome these and other problems by dividing the labor to evaluate a large number of documents among a number of different evaluator entities. Each evaluator may review a small number of documents for example, although certain evaluators may review a large number as well. Collectively, a plurality of ratings may be collected and a reliable, aggregate rating may be determined for each document.
  • Embodiments described herein overcome these problems by determining a generally applicable, aggregate content rating for each electronic document. Instead of re-evaluating a document each time it may be provided to a user, the content provider may only review or process the document's aggregate content rating in order to match appropriate content with a user or provider. Each time the document is distributed, the suitability of the document to a particular audience may be efficiently determined with reference to the content rating and audience suitability data.
  • content providers may, in some circumstances, be held to a higher duty (e.g., legal duty) of appropriate content distribution when the content provider is aware of offensive content.
  • the content provider relies on rating(s) by others and thus may not incur a higher duty.
  • the server at least partially delegates the review of its content to evaluators (e.g., third parties, such as partner advertisers or others). Because the content provider takes active steps to ensure that content is appropriate for end users, the content provider may be deemed to have satisfied general duties of care in preventing the improper distribution of offensive content.
  • document may encompass one or more advertisements, content pages (e.g., web pages), search results, emails, applications, IM messages, audio content or files, video content or files, other files, other data or applications that may reside on one or several (e.g., a network) of computer systems, or other definable concepts or content.
  • one or more document sources 12 provide one or more documents to a server 2 .
  • Server 2 may select one or more documents (such as an advertisement) and one or more evaluators 4 to rate the document.
  • Server 2 may pass the one or more documents to one:or more selected evaluators 4 , or may otherwise make the document available to the one or more evaluators 4 for rating.
  • Evaluators 4 rate the document(s) according to one or more criteria, such as sexual content and violent content. Evaluators 4 pass their rating to server 2 .
  • Server 2 may determine an aggregate rating for the document by processing all or a subset (one or more) of the document's associated evaluator ratings. For example, if a document is evaluated by ten evaluators, the aggregate rating may be based on any one of one through ten of the evaluators' ratings. For example, the aggregate rating may be based on the middle six, or some other combinations of evaluations.
  • One or more documents may be requested from server 2 .
  • a provider 8 and/or end user 10 may request the document.
  • the request may come in the form of a signal that the server interprets as a request for the document, even though the signal does not specifically indicate that a document is being requested.
  • an end user may transmit a signal to a server that requests a web page, and that signal may be interpreted as a request for an advertisement document as well.
  • the server 2 may determine whether any documents are available to respond to the signal based on one or more potential documents' rating and/or one or more criteria (e.g., whether the document meets or is related to content associated with the signal).
  • Server 2 may pass one or more documents to a recipient, such as the requesting entity.
  • the server 2 may identify other criteria associated with the signal (and/or the recipient of the document, if different from the requester). While the criteria may be based on the content of the signal or request for a document (e.g., a search request for a keyword or the like), the criteria may also be based on preferences associated with the recipient. For instance, the server 2 may identify sensitivity information and/or suitability information associated with the requestor or recipient. If the recipient is identified with a preference against violent content, the server 2 may determine whether any available documents have a rating indicating low violent content.
  • FIG. 1 depicts a system 100 for rating an electronic document according to an embodiment of the invention.
  • the system comprises a server 2 , one or more evaluators 4 , one or more providers 8 , one or more document sources 12 , one or more end users 10 , and one or more databases 6 operatively connected to server 2 .
  • System 100 enables server 2 to request, receive, and/or process content ratings of electronic documents.
  • Document sources 12 , evaluators 4 , providers 8 , and end users 10 may communicate with one or more servers 2 via electronic communication, including Internet communications.
  • Document sources 12 , evaluators 4 , providers 8 , and end users 10 may include or have access to one or more servers 2 for providing functionality associated with electronic documents.
  • Information that may be communicated between and among server 2 , evaluators 4 , providers 8 , document sources 12 , and end users 10 may include one or more of the following: document information, content rating information, sensitivity rating information, suitability standard information, trust score information, and/or evaluator or provider information.
  • the document information may include one or more of the following: the document itself, any language(s) used in the document, length information, file type information (e.g., html, doc, zip, etc.), type of document (advertisement, educational document), summary information, audio-visual content (e.g., pictures of faces, song lyrics, etc.), pornographic content, other offensiveness content (e.g., use of potentially offensive words), age-related content, the identity of the document owner and/or the document creator, information about the document's intended audience (such as geographic area, age range, gender, race, national origin, religion, other demographic information), and any other information related to a document or to the server 2 , evaluators 4 , providers 8 , or document sources 12 .
  • file type information e.g., html, doc, zip, etc.
  • type of document e.g., educational document
  • summary information e.g., audio-visual content (e.g., pictures of faces, song lyrics, etc.), pornographic
  • Document sources 12 may provide documents to server 2 or server 2 may “pull” or retrieve documents from document sources 12 .
  • the document source 12 may provide an advertisement to server 2 so that the server 2 may then provide the advertisement to one or more content providers 8 that may provide the ad to one or more end users 10 (or server 2 may provide the ad directly to the end user 10 ).
  • Document sources 12 may include any content creator or content provider 8 , such as an advertisement listings provider or server.
  • Providers 8 may provide documents to one or more end-users, 10 a through 10 n.
  • Providers 8 and evaluators 4 may include a content provider, search engine or other entity that makes available information, services, and/or products over an electronic network, such as the Internet.
  • a provider 8 may include one or more of the following, for example: an advertisement listings provider, an electronic document provider, a website host, a server, any other entity that provides electronic documents to users or other entities, or any other provider of content.
  • a provider 8 may be an evaluator 4 or a document provider 12 .
  • an evaluator 4 may be a provider 8 and/or a document provider 12 .
  • An evaluator 4 may be one or more persons or groups. The evaluators 4 and providers 8 may be partners of an entity associated with operating server 2 .
  • An end user 10 may be one or more persons, computers, computer networks, or other entity on a network. An end user 10 may request and receive content from a provider 8 and/or server 2 . Additional participants may be included based on various applications.
  • the server 2 may comprise any server, hub, central processor, provider, search engine, or other entity in a network.
  • a database 6 coupled to the server 2 may include one or more databases 40 - 54 .
  • databases 40 - 54 may comprise portions of a single database 6 . It should be appreciated that the databases 40 - 54 may or may not be physically distinct.
  • the server 2 and its modules 20 - 36 may store and access information stored in the database(s) 6 , 40 - 54 .
  • a content database 40 may store documents.
  • the documents may be rated and/or unrated.
  • the documents may be received from document sources 12 , evaluators 4 , and providers 8 , or they may be otherwise stored by the server 2 .
  • the content database 40 may identify documents of a certain type and/or group or otherwise associate documents together. For instance, documents may be identified and/or associated with other documents according to one or more of the following features: subject matter, content rating, aggregate content rating, sensitivity score, content type, language, geographic origin (e.g., country or city of origin), geographic area of target audience, document source 12 , owner of content, creator of content, target demographic, or other criteria.
  • the documents may be identified or grouped according to their offensiveness content, pornographic or other prurient content, adult content, children's content, or target age, gender, race, national origin, or religion. Other factors related to matching content to an appropriate audience can be considered.
  • a content rating database 42 may store content ratings received from evaluators 4 and any other information that may be relevant to rating a document.
  • the content rating database 42 may store information relating to number of clicks on a document, information relating to complaint letters filed for a document, verification information (such as a content creator vouching for the appropriateness of a particular document), and third party determinations relevant to the content of a document.
  • Each stored content rating may be associated with a particular evaluator 4 and a particular electronic document.
  • Each content rating may comprise one or more subject ratings (see FIG. 5 ).
  • a content rating may include a rating for violent content and a separate rating for sexual content. These separate ratings need not be combined into a single score.
  • a trust score database 44 may store trust scores associated with one or more evaluators 4 .
  • a single evaluator 4 may have one or more trust scores associated with it.
  • the single evaluator 4 may have a different score for different types of content rating subject areas. For instance, an evaluator 4 may have a high trust score with respect to age appropriateness ratings, but low trust scores with respect to violence ratings.
  • An evaluator may also have different trust scores according to any of the following criteria: time (e.g., time of day, day of year), geographic location of evaluator, document recipient profile, size of evaluator entity, business area or industry of evaluator, prior evaluator rating consistency or accuracy, terms of agreement between evaluator 4 and server 2 (if any), and trust ratings of the evaluator 4 a by other evaluators 4 b - 4 n. Evaluators 4 may automatically be assigned a low trust rating when evaluating their own content.
  • Trust scores may be normalized or otherwise adjusted for one or more evaluators 4 .
  • trust scores may be adjusted to reflect that an evaluator 4 a consistently provides higher or lower ratings, e.g., ratings of a particular type (violence) for content of a particular type (ads).
  • an evaluator 4 a may provide adult content ratings that are at least one standard deviation of the mean higher than the ratings of other evaluators 4 b - 4 n in 80% of the evaluator's 4 a ratings. This may indicate to the system that, on average, the evaluator's 4 a adult score ratings are likely to be higher than average in future ratings, e.g., future ratings of a particular type for content of a particular type.
  • Other information can be determined, deduced, or inferred from the rating behaviors of one or more evaluators. For instance, if evaluator A provides a higher adult content rating for document XYZ than evaluator B, and evaluator B provides a higher adult content rating for document QRS than evaluator C, then the system might assume that evaluator A provides (or will provide) higher adult content ratings than evaluator C. As a result, the system may adjust (e.g., lower) the trust score for evaluator A (or B or C) in a future rating, such as a rating that includes an adult content rating from both A and C.
  • the ratings themselves may be normalized or otherwise adjusted, e.g., as described above for trust scores. For instance, for a particular evaluator 4 a who consistently provides high violence ratings compared to similarly situated evaluators' 4 b - 4 g ratings of the same or similar content, the violence ratings of that particular evaluator 4 a for that type of content may be adjusted downward.
  • evaluations may be requested and received from hundreds (or perhaps thousands or millions) of evaluators 4 , biases and other rating behavior can be tracked and predicted for large numbers of users, content types, rating categories, and other criteria. Normalization and other statistical and/or data processing techniques can be used to process the data, as will occur to those skilled in the art. The processed data can be used to adjust ratings, trust scores, aggregate ratings, and other calculations and information.
  • a sensitivity database 46 may store sensitivity information for evaluators 4 , providers 8 , end users 10 , document sources 12 , the server 2 , a specific document, or other sensitivity information.
  • a sensitivity score may indicate the level of conservatism by which to aggregate content ratings. For instance, a high sensitivity score (e.g., 95%) may indicate that the aggregate rating should be aggregated very conservatively. A conservative aggregation might mean that if one evaluator 4 a rated a document as inappropriate for children, then the aggregate rating will also indicate that the document is inappropriate for children, even if the “average” rating would indicate that the content is appropriate for all ages.
  • a sensitivity score may be specified by a provider 8 and/or end user 10 , or any other entity.
  • a provider 8 may specify a very high sensitivity to violent content and to sexual content and a low sensitivity to age-related content.
  • the server 2 might select a document where none (or very few) of the document's evaluators 4 found any sexual or violent content, where the document may have content directed towards an audience of any age.
  • the sensitivity database 46 may comprise a record indicating that Provider A (or a particular end user 10 a ) has a sensitivity score of 55% for sexual content and a sensitivity score of 20% for age-related content.
  • An aggregate rating database 48 may store aggregate ratings. Each aggregate rating may be associated with the rated document as well as the evaluators 4 used to determine the aggregate rating. The aggregate rating may also be associated with one or more sensitivity ratings and trust scores. Each aggregate rating may include content ratings across a variety of criteria. The content of an aggregate rating is described further below with respect to the rating aggregation module 30 .
  • An evaluator database 50 may store evaluator information. For instance, the evaluator database 50 may store information related to the trust score of a particular evaluator 4 .
  • the evaluator database 50 may store such evaluator 4 information as the evaluator name, address, country of origin, company size, prior content rating information, industry field, company reputation information, prior trust scores, and other information that may be related to an evaluator's trust score.
  • a suitability database 52 stores information about providers 8 and end users 10 who may request documents. For instance, the suitability database 52 may identify the gender, age, name, country of origin, and other personal information about an end user 10 or other content requester. This profile would be different from another end user 10 who was a 62-yr-old male from Spain. Each user 10 and/or provider 8 might have a set of suitability standards associated with them and stored in the suitability database 52 .
  • Other database(s) 54 may store other information relating to the evaluators 4 , providers 8 , end users 10 , document sources 12 , server 2 , content ratings, aggregate ratings, trust scores, suitability scores, and sensitivity scores.
  • the server 2 may comprise one or more modules to process content, ratings, and other data.
  • a document selection module 20 may select documents to be rated.
  • the module may select the documents stored in the document database 40 .
  • the document selection module may select the documents randomly, or it may select documents with particular features.
  • the document selection module 20 may select documents provided by a particular document source 12 , documents rated by a particular evaluator 4 , documents of a particular length or type (e.g., short advertisements).
  • Documents may be selected according to subject matter, financial data, performance data, geographic origin, identity of owner, identity of creator, and/or other information associated with the document. For instance, an advertisement with a high click-through-rate (CTR) may be selected for rating before an advertisement with a low click-through rate.
  • a web page from an alcohol distributor may be selected prior to an advertisement from a utensil manufacturer.
  • An evaluator selection module 22 may select evaluators 4 a - 4 n for evaluating one or more electronic documents. Evaluators 4 and associated documents may be selected randomly or by other methods. For instance, evaluators 4 may be selected randomly from a group of evaluators of a specific type, such as a group of partner advertisers or advertising listing partners. Evaluators 4 may be selected according to any criteria, such as the trust score of the evaluator.
  • Unrated documents may be selected for rating prior to (or after) rated documents. Some evaluators 4 may submit some of the rate-able documents to the server 2 . These evaluators 4 may or may not be selected to review the documents. In one embodiment, entities that provide rate-able content to the server 2 rate the content before providing it to the server 2 .
  • a trust score module 24 determines trust scores for evaluators 4 .
  • a trust score of an evaluator 4 is a measure of the extent to which the evaluator's 4 content rating will be considered in determining an aggregate rating. For instance, the content rating of a highly trusted evaluator 4 may be given greater weight in the calculation of an aggregate rating than a less trusted evaluator 4 .
  • Trust scores may be determined according to any of the following factors related to an evaluator 4 : evaluator name, company, size of company, location (and national origin) of evaluator, language of evaluator, reputation of evaluator, company industry, prior content ratings, number of prior content ratings, and a comparison between prior content ratings and an associated aggregate rating or associated content ratings by other evaluators.
  • a sensitivity module 26 may determine sensitivity scores for a Provider 8 , an end user 10 , an evaluator 4 , and/or the server 2 . These scores may be based on information collected regarding those entities, such as prior rating data and any information stored in any of the databases 6 .
  • a high sensitivity might indicate a higher degree of conservatism in determining an aggregate rating. For instance, if a provider 8 has complained of receiving inappropriately violent content in the past, the sensitivity module 26 may associate a high violence sensitivity score with that provider.
  • a content rating module 28 may create content rating requests and pass them to evaluators 4 .
  • An exemplary content rating request is shown in FIG. 5 .
  • the content rating request may comprise a list of information requested for a document to be rated. The information requested may be different (or the same) for each document.
  • the content rating request may be different for each document. For instance, a request to rate a beer advertisement may request detailed information about the way that alcohol is portrayed, while a request to rate a power tool merchant's website might not.
  • the content rating module 28 may also receive and process content ratings received from evaluators 4 .
  • the content rating requests and content ratings may be communicated via traditional mail, email, or other methods.
  • the server 2 may send to an evaluator 4 a link to a server 2 website that contains the document and associated content rating information.
  • the evaluator may then access the document and provide the content rating directly on the server 2 site.
  • the content rating module 28 may then electronically process the rating information.
  • a rating aggregation module 30 may determine an aggregate rating for a document by processing one or more content ratings of the document received from one or more evaluators 4 .
  • the rating aggregation module 30 may use any aggregation algorithm or methodology.
  • the aggregation may be a total score, a mean, a mode, a median, a step function, a 75th percentile score, or any other measure that relates to the data considered.
  • the algorithm may consider one or more of the following, for example: content ratings, sensitivity information, suitability information, trust score information, document performance data (such as click through rate and frequency of display), and other information relevant to the evaluators, document, document content, or aggregation.
  • the rating aggregation module 30 may mark a document as violent if any content ratings indicated any violence whatsoever. This may occur when a high sensitivity to violence is incorporated into the algorithm.
  • Another algorithm may determine a high violence score only if a supermajority of evaluators 4 rated the document to have strong violence. The algorithm may weight the ratings of different evaluators differently according to each evaluator's trust score (if any). For instance, a highly trusted evaluator's violence rating may count three times as much as a less trusted evaluator's violence rating. Other examples are also possible.
  • An aggregate rating may comprise one or more distinct numerical scores (e.g., for different subject areas like sexuality and violence) and/or one or more verbal scores.
  • a verbal score may be a word (e.g., essay) analysis of a feature of the document. For instance, an evaluator may provide a numerical score of 4/10 in a “sexual content” category, and the evaluator may also verbally state that the document “includes a half-clothed woman with a sexually suggestive look in her eye.” It may also comprise one or more binary scores (such as yes/no or flag/no-flag).
  • the rating aggregation module 30 may flag the document as pornographic.
  • the numerical scores may comprise one or more measures of a total rating in a particular subject area, and the numerical scores may also indicate other information about the various ratings aggregated. For instance, a score may comprise a mean in addition to a standard deviation of the mean.
  • the aggregate rating may comprise a multidimensional vector coupled with verbal responses.
  • Rating aggregation module 30 may also determine that particular documents may be subjected to additional review. For instance, if a less trusted evaluator marked a document as pornographic, the document may be marked for further review (such as by manual review by the server 2 or its agents). The rating aggregation module may update aggregate ratings (e.g., automatically) at specific times or as new ratings are input into the system.
  • a suitability standard module 32 may identify or determine suitability standards of document recipients such as providers 8 and end users 10 .
  • the suitability standards may be based on provider 8 or user 10 information, such as the information described above.
  • the suitability standards may be identified by the suitability standard module 32 . For instance, a suitability standard for a user identified to be a twenty-year old male viewing a pop musician's website might indicate that a small amount of violent and sexual content may be appropriate for the user, but that alcohol-related content is not.
  • the suitability standard may be used to select a document appropriate for that user.
  • the suitability standard module 32 may attempt to determine whether any information relating to the preferences of the provider 8 or end user 10 are stored in the suitability database 52 . If a suitability standard exists for a potential content recipient, the document provision module 34 may select a document that satisfies the suitability standards (e.g., a document that contains very little violent content). A similar, but slightly different, method of identifying appropriate content may be accomplished using sensitivity scores, as described herein.
  • a document provision module 34 may select and provide documents in response to a request from a provider 8 , end user 10 , or other entity. For instance, a children's book retailer may request an advertisement to display on their site. In response, the document provision module 34 may identify or determine sensitivity score information and suitability information associated with the children's book retailer and then select a document based on this information (such as an identified suitability standard). For instance, if the site is associated with a high sensitivity to violent content, the document provision module 34 may select content that has an aggregate rating indicating zero violent content. The document provision module 34 might also select a document that was verified by a trusted evaluator to have no objectionable violent content.
  • Document selection may be based on the aggregate rating associated with the document, as well as suitability and/or sensitivity information. For instance, the document provision module 34 may determine that the provider has a high sensitivity against prurient content and therefore select a document where no evaluator found pornographic content—or where no evaluator found sexual content of any kind. The document provision module 34 may also determine that the provider prefers documents with an aggregate rating that indicates a high value in the category of child content and therefore select a document containing substantial children's content.
  • a document By identifying a suitability and/or sensitivity score for particular providers 8 and end users 10 (or other entities that receive documents), a document may be chosen that fits a suitability profile (or standard) associated with that entity. Thus, end users may receive non-offensive content, and content providers may ensure the propriety of the content provided on their sites.
  • module(s) 36 may accomplish other functions related to rating electronic documents.
  • FIG. 2 depicts a networked environment for operation of a system for rating a document according to an embodiment of the invention.
  • evaluators 4 and providers 8 may connect over a network 14 , 15 to a server 2 (e.g., using a secure https connection) to provide documents and rating information to server 2 and to receive documents and rating request information from server 2 .
  • the server 2 may store the document and rating information in a database 6 .
  • the server 2 may distribute the documents through various forums or feeds, including direct distribution in print media, providing the documents on one or more web sites affiliated with the server 2 and through providers 8 .
  • providers may comprise syndication partners of the server 2 (e.g., connected over network 14 or 15 depending on security desired), content systems (e.g., with associated content databases) and search engine systems operated by the server 2 or provider(s) 8 .
  • the documents provided to the providers 8 may be included in pages (or other documents) displayed to end-users 10 (often called an impression).
  • Each of server 2 , evaluators 4 , providers 8 , and document sources 12 may comprise computerized systems that include one or more of the following systems: a web server, a database server, proxy server, network balancing mechanisms and systems, and various software components that enable the system to operate on the internet or other network type system.
  • networks 14 and 15 although depicted as http networks, may comprise other networks such as private lines, intranets, or any other network.
  • the connection between a document source 12 such as an advertisement provider and server 2 (and other connections such as between a provider 8 and server 2 ) may comprise secure network connections to insure that data is not subject to attack or corruption by any hacker or other third party.
  • provider 8 a may comprise any number of such systems connected to the evaluator 4 or server 2 via any type of network, including an http or https network.
  • Content provider 8 may comprise a system such as server 2 that provides functionality for enabling connection over the internet or other network protocols.
  • End users 10 may comprise any user (such as users connected to the internet) and may comprise computerized systems that enable that connection through any of various types of networks, including through internet service providers, cable companies, and any other method of accessing data on the internet.
  • Providers 8 may comprise any system that distributes content such as advertising to end-users 10 .
  • FIG. 3 is a flow chart illustrating an exemplary method for rating an electronic document according to an embodiment of the invention. The method described herein may be implemented by the systems described in FIGS. 1 and 2 .
  • one or more documents may be received.
  • the server may receive one or more advertisements from one or more partner advertisers or other content providers.
  • the server may generate one or more documents.
  • the server may select one or more documents to pass to one or more evaluators. For instance, the server may pass the document to one or more partner advertisers or content providers, in which case these entities may be evaluators. These evaluators may be the same or different entities from which a document was received in block 300 (i.e., the server may select the original provider of the document (from block 300 ) to be one of the evaluators in step 310 ).
  • the server may select the documents and evaluators randomly or based on an algorithm and/or one or more criteria.
  • the document may be selected from among a plurality of documents, and the evaluators may be selected from among a plurality of evaluators. It should be understood that while this description discloses the method of rating an electronic document, many documents can be rated using this method at the same time. For instance, as each additional document is received by the server, the documents may be automatically passed to several evaluators selected immediately by the system.
  • the selected document may be passed to the one or more evaluators.
  • the server may pass the document to one or more partner advertisers who will rate the document.
  • the server may also transmit rating instructions to the evaluators 4 that describe the various ratings requested for the document.
  • the server may request each evaluator to rate the document according to a variety of criteria such as target age range, family content, violent content, and other criteria.
  • the evaluators may generate one or more content ratings associated with the document.
  • a partner evaluator may have an one or more evaluator employees or agents review the document and rate the document in each category specified by the server.
  • the content ratings may be numerical scores (e.g., a number between 1 and 5, or another number or percentage), codes (such as “V” for violent), or verbal comments (e.g., essay responses).
  • the content ratings may be received from the evaluators.
  • the content ratings may be received by the server from the partner advertisers.
  • sensitivity ratings and evaluator trust scores may be identified.
  • the server may identify trust scores associated with one or more of the evaluators that submitted content ratings for the document. Trust scores may be determined and identified as described for the trust score module 24 of FIG. 1 , and sensitivity scores may be determined and identified as described for the sensitivity module 26 of FIG. 1 .
  • an aggregate rating may be determined.
  • the aggregate rating may be based on one or more of content ratings, sensitivity scores, and trust scores.
  • the aggregate rating may be determined by any method as described above for the rating aggregation module 30 (see FIG. 1 ).
  • a request for a document may be received.
  • the server may receive a request for a document from a provider 8 or an end user 10 .
  • a suitability standard and/or a sensitivity score may be determined.
  • a document may be selected.
  • a server that receives a request for a document from a user or provider may select a document for the user or provider. The selecting may be based on a suitability standard of the user or provider, one or more aggregate ratings of the document, and/or sensitivity scores associated with the evaluators, server, provider(s), and/or user(s).
  • one or more selected documents may be passed to the requesting entity. For instance, if a provider or user requested a document in block 370 , the server may pass the selected document to the provider or user, as the case may be.
  • the acts described may be performed by hardware, software, or a combination thereof, with or without human intervention, as may be embodied in one or more computing systems such as a server system coupled to entities such as providers, evaluators, and end users. Further, it should be appreciated that not all of the blocks must be accomplished. For instance, in one embodiment, the method may begin at block 340 and end at block 390 . Also, it is not necessary that the action(s) of each block be performed in the order shown in FIG. 3 . Any orderings may be considered.
  • the aggregate content rating may be determined after a user or content provider requests a document from the server rather than before such request. Because sensitivities, suitability standards, and evaluator trust scores may change over time, and because new ratings may be added for a particular document, the document's aggregate rating may also change. Obtaining an up-to-date rating for a document before providing it to a user or provider may maximize the likelihood that the document is appropriate for the user or provider.
  • FIG. 4 shows an exemplary document 1 according to an embodiment of the invention.
  • FIG. 4 depicts an exemplary web page 1 a search result from an internet search engine.
  • the web page 1 a itself may be a document.
  • Content on the web page 1 a may also be a document.
  • the advertisements 1 b on the search result page 1 a may also be documents.
  • Other types of documents may be considered, such as advertisements, files, programs, and other information.
  • the document may have various types of content.
  • the document may have words, images, sounds, and other information, as well as functions or programs which may produce words, images, sounds, and other information.
  • Each document may have different amounts of various types of content, such as sexual content, violent content, drug or alcohol-related content, financial content, adult-related content, child-related content, and other content.
  • the document may have a picture of a bikini-clad woman holding a glass of wine and an associated title stating “Fun in the sun with WineCo brand wine.” Another document may show a man holding a gun pointed at an icon that says “debt.” Another document may state “investments with FundCo yielded 6.25% over prime last year.” Another document may show children dancing underneath a rainbow and singing “It's a Small World After All.” Another document may have an icon which, when clicked, allows the user to virtually duck hunt by using a cursor to aim a rifle at ducks sitting in a lake, as in a video game.
  • FIG. 5 shows an exemplary content rating request 50 according to an embodiment of the invention.
  • the content rating request 50 may comprise one or more requests for specific ratings 50 a - 50 c across a range of subject matter and content types. For instance, there may be requests for ratings for violence 50 a, teenage appropriateness 50 b, country-specific suitability considerations 50 c, and other information.
  • a content rating request might ask the evaluator to provide a number (e.g., a number between 1 and 10) indicating the amount of sexual content, violent content, adult content, language- or country-specific content, or other types of content or criteria.
  • the request may also request information regarding when (time of day, week, year) the document is most suitable for viewing.
  • the request may also ask the requestor to explain reasons for the requestor's numerical ratings or provide other verbal ratings.
  • FIG. 6 shows an exemplary content rating 60 according to an embodiment of the invention.
  • the content rating 50 may comprise one or more subject area content ratings 60 a - 60 c for the document, such as ratings for violence 60 a, teenage appropriateness 60 b, and country-specific suitability considerations 60 c, and other information.
  • the content rating may include one or more responses to the content rating request (see FIG. 5 ).
  • the content rating may indicate numerical or verbal ratings across a variety of criteria, such as sexual content, violent content, adult-themed content, culture-specific content, or other content criteria.
  • the server may receive a plurality of documents from document sources. It may select one or more documents (such as five documents) and one or more evaluators to select the one or more documents. For instance, the server may receive 100 documents and select five for evaluation, and then it may select three raters to rate each of the five documents. (Also and/or alternately, it may send the five documents to a plurality of selected evaluators so that each document has three evaluators, but each of the evaluators does not have all three documents.) The server may send an evaluation request with each document.
  • the server may merely post the documents and evaluation requests (e.g., evaluation forms) in a database (e.g., on a website) and enable the evaluators to access the database and provide content ratings.
  • a database e.g., on a website
  • one content rating 60 of the document with a bikini-clad woman and glass of wine by one evaluator may show a rating of 6 out of 10 for sexual content, a 4 out of 5 for alcohol content, an indication that the document is suitable for children, and the rating may include an indication that the document is most suitable between the hours of 7 p.m. and 6 a.m.
  • a content rating from a second evaluator for the same document may indicate a rating of 7 out of 10 for sexual content, a 3 out of 5 for alcohol content, an indication that the document is suitable for children, and an indication that the document is most suitable between the hours of 4 p.m. and 6 a.m.
  • a content rating from a third evaluator for the same document may indicate an 8 out of 10 for sexual content, a 3 out of 5 for alcohol content, an indication that the ad is not suitable for children, and an indication that the document is most suitable between the hours of 11 p.m. and 6 a.m., and not on holidays.
  • the server may calculate an aggregate rating for this document based on the three ratings.
  • the server may specify a high sensitivity for children's content and a medium sensitivity for violent content.
  • the server may calculate an aggregate rating for sexual content based on a mean (or median) of the three sexual content ratings, which in this case would be 7 out of 10.
  • the server may calculate an aggregate rating for alcohol content based on a mode (most common score) of the alcohol ratings, which in this case is 3 out of 5. Also, the server may discount the first evaluator's rating of 4 out of 5 if the first evaluator has a low trust score, and a weighted average of the three ratings might be 3.1 out of 5 (which may be rounded to 3).
  • the server may select the time of day rating of the most trusted evaluator. If the evaluator who indicated that the most suitable hours were between 11 p.m. and 6 a.m., the aggregate rating may indicate that the most suitable hours are between 11 p.m. and 6 a.m. The aggregate rating may also indicate the standard deviation for each component of the aggregate rating, or it may use some other measure to indicate the variance of the different ratings from the different evaluators.
  • the rating may be marked for further review. For instance, since only one evaluator indicated that the document is not suitable for children, the server (or agent of the server or another evaluator) may review the document to determine whether the unusual rating was accurate. For instance, the server may review the evaluator's ratings and/or generate (or request) one or more additional ratings for the document. Depending on the results, the server may change the aggregate rating (e.g., by re-calculating it) and/or change the trust score of the evaluator in question for one or more criteria of content.
  • the server may change the aggregate rating (e.g., by re-calculating it) and/or change the trust score of the evaluator in question for one or more criteria of content.
  • Aggregate ratings of other documents may also be determined. For instance, the ad with children singing under a rainbow may be rated to have zero sexual content, zero alcohol content, zero violent content, and suitability for any time of day (especially 8 am-6 pm).
  • An end user or provider may then request a document at midnight. For instance, a client may click on a provider's web page, and the provider may request an advertisement to display to the client on the provider's site.
  • the server may select a document to pass to the provider according to the aggregate content ratings of the various documents.
  • the server may also identify sensitivity and suitability information of the requesting provider (or user) and consider other criteria, such as time of request. For instance, the server may identify that the provider has a high sensitivity to sexual content. (In another example, the server may identify (e. g., by using cookies or information stored in a database associated with the user's IP address) the age and gender of the user (e.g., 25 year old male).
  • the server may have assign sensitivity or suitability criteria, e.g. for the time of day. For a request at midnight, the server may assign lower sensitivities to sexual and violent content than the middle of the day, since it is far less likely that children will be browsing the internet at that time.
  • the relevant time may be from the perspective of the server, provider, or end user.
  • the server may accordingly select a document that is suitable for a provider who has a high sensitivity to sexual content and a medium sensitivity to violent content.
  • the server may consider for selection all or a portion of documents stored in a database, including the bikini/wine document, the singing children, and the duck hunting documents. For instance, the server may consider only those documents which have an aggregate rating indicating little or no sexual content and only mild (or less) violence. In the middle of the day, the server might apply a high sensitivity to violent content due to the time of day and may therefore only consider non-violent documents at that time. At midnight, however, the server might consider other documents that may not be appropriate to users at an earlier time.
  • the server may then search for a document that fits the various criteria associated with the document request and the relevant sensitivity and suitability information.
  • the children singing may have no offensive or potentially offensive content, it also may have a low click through rate and therefore not be selected.
  • documents which have little or no potentially offensive content may or may not be favored over documents which do contain potentially offensive material.
  • the duck hunting document may be selected if its aggregate rating indicates only mild violence. The selection of this document may be more likely if it is an ad with a high click through rate. Other factors of document selection may be considered.

Abstract

A system and method for rating an electronic document such as an advertisement. Rating information is received from one or more evaluators. A signal relevant to a criteria is received and a determination is made whether to deliver the document in response to the signal based on the criteria and the rating information from the one or more evaluators.

Description

  • This application is a continuation, and claims priority under 35 U.S.C. §120 to U.S. patent application Ser. No. 10/812,417, filed Mar. 30, 2004, which is incorporated herein by reference.
  • BACKGROUND
  • The present invention relates to a system and method for rating a document by aggregating a plurality of ratings from partner evaluators.
  • With the advent of the Internet, a seemingly limitless variety of content may be provided to people of varying ages, preferences, and sensibilities. Some content may be more appropriate for some individuals and groups than for others. For instance, violent or pornographic content is typically deemed inappropriate for children. Providing audience-appropriate content is desirable because it generally maximizes benefits and minimizes burdens for both the content provider and the audience. For instance, an audience-appropriate and relevant ad is more likely to generate a sale than an offensive and irrelevant one.
  • Accordingly, ads and other content are often targeted to specific audiences that may have an interest in the content. For instance, ads directed to males may be displayed during nationally televised football events because they draw large numbers of male viewers. Similarly, an ad for an airline may be displayed at an Internet search engine site when a user submits a query including the word “plane.”
  • However, providing ads and other documents based on user-related content does not ensure the propriety of that content for a particular audience. For instance, a beer advertisement may not be appropriate on a website for recovering alcoholics, even though the ad and the content of the website are related by subject matter.
  • One method of matching appropriate content to an audience is to manually review the content before distributing it to the audience. However, there are problems associated with manual review. For example, one significant drawback of manual rating systems and methods is the time and expense involved in reviewing the content.
  • These and other drawbacks exist with current systems and methods.
  • SUMMARY
  • Accordingly, various embodiments of the present inventions may be directed to a system and a method for rating documents such as advertisements. In one exemplary embodiment, a system and method for rating an electronic document such as an advertisement is provided. Rating information is received from one or more evaluators. A signal relevant to one or more criteria is received and a determination is made whether to deliver the document in response to the signal based on the criteria and the rating information from the one or more evaluators.
  • In another exemplary embodiment, a method and system of determining an aggregate rating for a document involve receiving rating information for an electronic document from a plurality of evaluators, wherein at least one evaluator is associated with a trust score, and determining an aggregate content rating for the electronic document by aggregating the rating information from at least two of the plurality of evaluators, wherein the rating information for at least one evaluator is considered in association with the trust score for that evaluator.
  • In another exemplary embodiment, a method and system for transmitting a signal that receives a rated document involves transmitting a signal to a server, the server interpreting the signal as being associated with one or more criteria for a document and determining whether a document is to be delivered based in part on rating information received from a plurality of evaluators for one or more documents and whether the one or more documents relate to the criteria. Any identified documents are then received in response to the signal.
  • In another exemplary embodiment, a method and system for receiving documents and rating them involves receiving one or more documents from a server system and providing rating information to the server system for use by the server system in determining whether to deliver the one or more documents in response to requests for the one or more documents based on the rating provided.
  • Other embodiments are also within the scope of the invention
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 depicts a system for rating an electronic document according to an embodiment of the invention.
  • FIG. 2 depicts a networked environment for operation of a system for rating a document according to an embodiment of the invention.
  • FIG. 3 depicts a flow chart illustrating an exemplary method for rating an electronic document according to an embodiment of the invention.
  • FIG. 4 depicts an exemplary electronic document according to an embodiment of the invention.
  • FIG. 5 depicts an exemplary content rating request according to an embodiment of the invention.
  • FIG. 6 depicts an exemplary content rating according to an embodiment of the invention.
  • DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS
  • The embodiments described herein solve many problems with existing systems and methods. One problem facing internet content providers is evaluating a large number of documents (such as advertisements presented through its services) to determine whether each is appropriate for a wide variety of different users. Embodiments described herein overcome these and other problems by dividing the labor to evaluate a large number of documents among a number of different evaluator entities. Each evaluator may review a small number of documents for example, although certain evaluators may review a large number as well. Collectively, a plurality of ratings may be collected and a reliable, aggregate rating may be determined for each document.
  • Another problem facing internet content providers is selecting appropriate content each time a document is requested by a different user with different sensibilities and preferences. Embodiments described herein overcome these problems by determining a generally applicable, aggregate content rating for each electronic document. Instead of re-evaluating a document each time it may be provided to a user, the content provider may only review or process the document's aggregate content rating in order to match appropriate content with a user or provider. Each time the document is distributed, the suitability of the document to a particular audience may be efficiently determined with reference to the content rating and audience suitability data.
  • Yet another problem is that content providers may, in some circumstances, be held to a higher duty (e.g., legal duty) of appropriate content distribution when the content provider is aware of offensive content. In an exemplary embodiment, the content provider relies on rating(s) by others and thus may not incur a higher duty. Rather, the server at least partially delegates the review of its content to evaluators (e.g., third parties, such as partner advertisers or others). Because the content provider takes active steps to ensure that content is appropriate for end users, the content provider may be deemed to have satisfied general duties of care in preventing the improper distribution of offensive content.
  • As used herein, the term “document” and “electronic document” may encompass one or more advertisements, content pages (e.g., web pages), search results, emails, applications, IM messages, audio content or files, video content or files, other files, other data or applications that may reside on one or several (e.g., a network) of computer systems, or other definable concepts or content.
  • Overview and System Illustration
  • According to one exemplary embodiment, one or more document sources 12 provide one or more documents to a server 2. Although a single server 2 is depicted, it should be appreciated that multiple servers 2 may be provided and that such multiple servers may share data and operational tasks to best achieve efficiency and operation of the functions described herein. Server 2 may select one or more documents (such as an advertisement) and one or more evaluators 4 to rate the document. Server 2 may pass the one or more documents to one:or more selected evaluators 4, or may otherwise make the document available to the one or more evaluators 4 for rating. Evaluators 4 rate the document(s) according to one or more criteria, such as sexual content and violent content. Evaluators 4 pass their rating to server 2. Server 2 may determine an aggregate rating for the document by processing all or a subset (one or more) of the document's associated evaluator ratings. For example, if a document is evaluated by ten evaluators, the aggregate rating may be based on any one of one through ten of the evaluators' ratings. For example, the aggregate rating may be based on the middle six, or some other combinations of evaluations.
  • One or more documents may be requested from server 2. For instance, a provider 8 and/or end user 10 may request the document. The request may come in the form of a signal that the server interprets as a request for the document, even though the signal does not specifically indicate that a document is being requested. For example, an end user may transmit a signal to a server that requests a web page, and that signal may be interpreted as a request for an advertisement document as well. The server 2 may determine whether any documents are available to respond to the signal based on one or more potential documents' rating and/or one or more criteria (e.g., whether the document meets or is related to content associated with the signal). Server 2 may pass one or more documents to a recipient, such as the requesting entity. The server 2 may identify other criteria associated with the signal (and/or the recipient of the document, if different from the requester). While the criteria may be based on the content of the signal or request for a document (e.g., a search request for a keyword or the like), the criteria may also be based on preferences associated with the recipient. For instance, the server 2 may identify sensitivity information and/or suitability information associated with the requestor or recipient. If the recipient is identified with a preference against violent content, the server 2 may determine whether any available documents have a rating indicating low violent content.
  • FIG. 1 depicts a system 100 for rating an electronic document according to an embodiment of the invention. The system comprises a server 2, one or more evaluators 4, one or more providers 8, one or more document sources 12, one or more end users 10, and one or more databases 6 operatively connected to server 2.
  • System 100 enables server 2 to request, receive, and/or process content ratings of electronic documents. Document sources 12, evaluators 4, providers 8, and end users 10 may communicate with one or more servers 2 via electronic communication, including Internet communications. Document sources 12, evaluators 4, providers 8, and end users 10 may include or have access to one or more servers 2 for providing functionality associated with electronic documents.
  • Information that may be communicated between and among server 2, evaluators 4, providers 8, document sources 12, and end users 10 may include one or more of the following: document information, content rating information, sensitivity rating information, suitability standard information, trust score information, and/or evaluator or provider information. The document information may include one or more of the following: the document itself, any language(s) used in the document, length information, file type information (e.g., html, doc, zip, etc.), type of document (advertisement, educational document), summary information, audio-visual content (e.g., pictures of faces, song lyrics, etc.), pornographic content, other offensiveness content (e.g., use of potentially offensive words), age-related content, the identity of the document owner and/or the document creator, information about the document's intended audience (such as geographic area, age range, gender, race, national origin, religion, other demographic information), and any other information related to a document or to the server 2, evaluators 4, providers 8, or document sources 12.
  • Document sources 12 may provide documents to server 2 or server 2 may “pull” or retrieve documents from document sources 12. For instance, the document source 12 may provide an advertisement to server 2 so that the server 2 may then provide the advertisement to one or more content providers 8 that may provide the ad to one or more end users 10 (or server 2 may provide the ad directly to the end user 10). Document sources 12 may include any content creator or content provider 8, such as an advertisement listings provider or server.
  • Providers 8 may provide documents to one or more end-users, 10 a through 10 n. Providers 8 and evaluators 4 may include a content provider, search engine or other entity that makes available information, services, and/or products over an electronic network, such as the Internet. A provider 8 may include one or more of the following, for example: an advertisement listings provider, an electronic document provider, a website host, a server, any other entity that provides electronic documents to users or other entities, or any other provider of content. A provider 8 may be an evaluator 4 or a document provider 12.
  • Similarly, an evaluator 4 may be a provider 8 and/or a document provider 12. An evaluator 4 may be one or more persons or groups. The evaluators 4 and providers 8 may be partners of an entity associated with operating server 2. An end user 10 may be one or more persons, computers, computer networks, or other entity on a network. An end user 10 may request and receive content from a provider 8 and/or server 2. Additional participants may be included based on various applications.
  • The server 2 may comprise any server, hub, central processor, provider, search engine, or other entity in a network. A database 6 coupled to the server 2 may include one or more databases 40-54. Also, databases 40-54 may comprise portions of a single database 6. It should be appreciated that the databases 40-54 may or may not be physically distinct. The server 2 and its modules 20-36 may store and access information stored in the database(s) 6, 40-54.
  • A content database 40 may store documents. The documents may be rated and/or unrated. The documents may be received from document sources 12, evaluators 4, and providers 8, or they may be otherwise stored by the server 2. The content database 40 may identify documents of a certain type and/or group or otherwise associate documents together. For instance, documents may be identified and/or associated with other documents according to one or more of the following features: subject matter, content rating, aggregate content rating, sensitivity score, content type, language, geographic origin (e.g., country or city of origin), geographic area of target audience, document source 12, owner of content, creator of content, target demographic, or other criteria. For instance, the documents may be identified or grouped according to their offensiveness content, pornographic or other prurient content, adult content, children's content, or target age, gender, race, national origin, or religion. Other factors related to matching content to an appropriate audience can be considered.
  • A content rating database 42 may store content ratings received from evaluators 4 and any other information that may be relevant to rating a document. For instance, the content rating database 42 may store information relating to number of clicks on a document, information relating to complaint letters filed for a document, verification information (such as a content creator vouching for the appropriateness of a particular document), and third party determinations relevant to the content of a document. Each stored content rating may be associated with a particular evaluator 4 and a particular electronic document. Each content rating may comprise one or more subject ratings (see FIG. 5). For instance, a content rating may include a rating for violent content and a separate rating for sexual content. These separate ratings need not be combined into a single score.
  • A trust score database 44 may store trust scores associated with one or more evaluators 4. A single evaluator 4 may have one or more trust scores associated with it. The single evaluator 4 may have a different score for different types of content rating subject areas. For instance, an evaluator 4 may have a high trust score with respect to age appropriateness ratings, but low trust scores with respect to violence ratings. An evaluator may also have different trust scores according to any of the following criteria: time (e.g., time of day, day of year), geographic location of evaluator, document recipient profile, size of evaluator entity, business area or industry of evaluator, prior evaluator rating consistency or accuracy, terms of agreement between evaluator 4 and server 2 (if any), and trust ratings of the evaluator 4 a by other evaluators 4 b-4 n. Evaluators 4 may automatically be assigned a low trust rating when evaluating their own content.
  • Trust scores may be normalized or otherwise adjusted for one or more evaluators 4. For instance, trust scores may be adjusted to reflect that an evaluator 4 a consistently provides higher or lower ratings, e.g., ratings of a particular type (violence) for content of a particular type (ads). For instance, an evaluator 4 a may provide adult content ratings that are at least one standard deviation of the mean higher than the ratings of other evaluators 4 b-4 n in 80% of the evaluator's 4 a ratings. This may indicate to the system that, on average, the evaluator's 4 a adult score ratings are likely to be higher than average in future ratings, e.g., future ratings of a particular type for content of a particular type.
  • Other information can be determined, deduced, or inferred from the rating behaviors of one or more evaluators. For instance, if evaluator A provides a higher adult content rating for document XYZ than evaluator B, and evaluator B provides a higher adult content rating for document QRS than evaluator C, then the system might assume that evaluator A provides (or will provide) higher adult content ratings than evaluator C. As a result, the system may adjust (e.g., lower) the trust score for evaluator A (or B or C) in a future rating, such as a rating that includes an adult content rating from both A and C.
  • Similarly, instead of (or in addition to) adjusting the trust scores of evaluators, the ratings themselves may be normalized or otherwise adjusted, e.g., as described above for trust scores. For instance, for a particular evaluator 4 a who consistently provides high violence ratings compared to similarly situated evaluators' 4 b-4 g ratings of the same or similar content, the violence ratings of that particular evaluator 4 a for that type of content may be adjusted downward.
  • It should be noted that because evaluations may be requested and received from hundreds (or perhaps thousands or millions) of evaluators 4, biases and other rating behavior can be tracked and predicted for large numbers of users, content types, rating categories, and other criteria. Normalization and other statistical and/or data processing techniques can be used to process the data, as will occur to those skilled in the art. The processed data can be used to adjust ratings, trust scores, aggregate ratings, and other calculations and information.
  • A sensitivity database 46 may store sensitivity information for evaluators 4, providers 8, end users 10, document sources 12, the server 2, a specific document, or other sensitivity information. A sensitivity score may indicate the level of conservatism by which to aggregate content ratings. For instance, a high sensitivity score (e.g., 95%) may indicate that the aggregate rating should be aggregated very conservatively. A conservative aggregation might mean that if one evaluator 4 a rated a document as inappropriate for children, then the aggregate rating will also indicate that the document is inappropriate for children, even if the “average” rating would indicate that the content is appropriate for all ages. A sensitivity score may be specified by a provider 8 and/or end user 10, or any other entity. For instance, a provider 8 may specify a very high sensitivity to violent content and to sexual content and a low sensitivity to age-related content. Thus, when the server 2 selects a document for that provider 8, the server 2 might select a document where none (or very few) of the document's evaluators 4 found any sexual or violent content, where the document may have content directed towards an audience of any age.
  • For instance, the sensitivity database 46 may comprise a record indicating that Provider A (or a particular end user 10 a) has a sensitivity score of 55% for sexual content and a sensitivity score of 20% for age-related content.
  • An aggregate rating database 48 may store aggregate ratings. Each aggregate rating may be associated with the rated document as well as the evaluators 4 used to determine the aggregate rating. The aggregate rating may also be associated with one or more sensitivity ratings and trust scores. Each aggregate rating may include content ratings across a variety of criteria. The content of an aggregate rating is described further below with respect to the rating aggregation module 30.
  • An evaluator database 50 may store evaluator information. For instance, the evaluator database 50 may store information related to the trust score of a particular evaluator 4. The evaluator database 50 may store such evaluator 4 information as the evaluator name, address, country of origin, company size, prior content rating information, industry field, company reputation information, prior trust scores, and other information that may be related to an evaluator's trust score.
  • A suitability database 52 stores information about providers 8 and end users 10 who may request documents. For instance, the suitability database 52 may identify the gender, age, name, country of origin, and other personal information about an end user 10 or other content requester. This profile would be different from another end user 10 who was a 62-yr-old male from Spain. Each user 10 and/or provider 8 might have a set of suitability standards associated with them and stored in the suitability database 52.
  • Other database(s) 54 may store other information relating to the evaluators 4, providers 8, end users 10, document sources 12, server 2, content ratings, aggregate ratings, trust scores, suitability scores, and sensitivity scores.
  • The server 2 may comprise one or more modules to process content, ratings, and other data.
  • A document selection module 20 may select documents to be rated. The module may select the documents stored in the document database 40. The document selection module may select the documents randomly, or it may select documents with particular features. For instance, the document selection module 20 may select documents provided by a particular document source 12, documents rated by a particular evaluator 4, documents of a particular length or type (e.g., short advertisements). Documents may be selected according to subject matter, financial data, performance data, geographic origin, identity of owner, identity of creator, and/or other information associated with the document. For instance, an advertisement with a high click-through-rate (CTR) may be selected for rating before an advertisement with a low click-through rate. A web page from an alcohol distributor may be selected prior to an advertisement from a utensil manufacturer.
  • An evaluator selection module 22 may select evaluators 4 a-4 n for evaluating one or more electronic documents. Evaluators 4 and associated documents may be selected randomly or by other methods. For instance, evaluators 4 may be selected randomly from a group of evaluators of a specific type, such as a group of partner advertisers or advertising listing partners. Evaluators 4 may be selected according to any criteria, such as the trust score of the evaluator.
  • Unrated documents may be selected for rating prior to (or after) rated documents. Some evaluators 4 may submit some of the rate-able documents to the server 2. These evaluators 4 may or may not be selected to review the documents. In one embodiment, entities that provide rate-able content to the server 2 rate the content before providing it to the server 2.
  • A trust score module 24 determines trust scores for evaluators 4. A trust score of an evaluator 4 is a measure of the extent to which the evaluator's 4 content rating will be considered in determining an aggregate rating. For instance, the content rating of a highly trusted evaluator 4 may be given greater weight in the calculation of an aggregate rating than a less trusted evaluator 4. Trust scores may be determined according to any of the following factors related to an evaluator 4: evaluator name, company, size of company, location (and national origin) of evaluator, language of evaluator, reputation of evaluator, company industry, prior content ratings, number of prior content ratings, and a comparison between prior content ratings and an associated aggregate rating or associated content ratings by other evaluators.
  • A sensitivity module 26 may determine sensitivity scores for a Provider 8, an end user 10, an evaluator 4, and/or the server 2. These scores may be based on information collected regarding those entities, such as prior rating data and any information stored in any of the databases 6. A high sensitivity might indicate a higher degree of conservatism in determining an aggregate rating. For instance, if a provider 8 has complained of receiving inappropriately violent content in the past, the sensitivity module 26 may associate a high violence sensitivity score with that provider.
  • A content rating module 28 may create content rating requests and pass them to evaluators 4. An exemplary content rating request is shown in FIG. 5. The content rating request may comprise a list of information requested for a document to be rated. The information requested may be different (or the same) for each document. The content rating request may be different for each document. For instance, a request to rate a beer advertisement may request detailed information about the way that alcohol is portrayed, while a request to rate a power tool merchant's website might not. The content rating module 28 may also receive and process content ratings received from evaluators 4. The content rating requests and content ratings may be communicated via traditional mail, email, or other methods. For instance, the server 2 may send to an evaluator 4 a link to a server 2 website that contains the document and associated content rating information. The evaluator may then access the document and provide the content rating directly on the server 2 site. The content rating module 28 may then electronically process the rating information.
  • A rating aggregation module 30 may determine an aggregate rating for a document by processing one or more content ratings of the document received from one or more evaluators 4. The rating aggregation module 30 may use any aggregation algorithm or methodology. For instance, the aggregation may be a total score, a mean, a mode, a median, a step function, a 75th percentile score, or any other measure that relates to the data considered. The algorithm may consider one or more of the following, for example: content ratings, sensitivity information, suitability information, trust score information, document performance data (such as click through rate and frequency of display), and other information relevant to the evaluators, document, document content, or aggregation. For example, in one specific iteration, the rating aggregation module 30 may mark a document as violent if any content ratings indicated any violence whatsoever. This may occur when a high sensitivity to violence is incorporated into the algorithm. Another algorithm may determine a high violence score only if a supermajority of evaluators 4 rated the document to have strong violence. The algorithm may weight the ratings of different evaluators differently according to each evaluator's trust score (if any). For instance, a highly trusted evaluator's violence rating may count three times as much as a less trusted evaluator's violence rating. Other examples are also possible.
  • An aggregate rating may comprise one or more distinct numerical scores (e.g., for different subject areas like sexuality and violence) and/or one or more verbal scores. A verbal score may be a word (e.g., essay) analysis of a feature of the document. For instance, an evaluator may provide a numerical score of 4/10 in a “sexual content” category, and the evaluator may also verbally state that the document “includes a half-clothed woman with a sexually suggestive look in her eye.” It may also comprise one or more binary scores (such as yes/no or flag/no-flag). For instance, if three of five evaluators flagged a document as pornographic in their content rating, the rating aggregation module 30 may flag the document as pornographic. The numerical scores may comprise one or more measures of a total rating in a particular subject area, and the numerical scores may also indicate other information about the various ratings aggregated. For instance, a score may comprise a mean in addition to a standard deviation of the mean. The aggregate rating may comprise a multidimensional vector coupled with verbal responses.
  • Rating aggregation module 30 may also determine that particular documents may be subjected to additional review. For instance, if a less trusted evaluator marked a document as pornographic, the document may be marked for further review (such as by manual review by the server 2 or its agents). The rating aggregation module may update aggregate ratings (e.g., automatically) at specific times or as new ratings are input into the system.
  • A suitability standard module 32 may identify or determine suitability standards of document recipients such as providers 8 and end users 10. The suitability standards may be based on provider 8 or user 10 information, such as the information described above. The suitability standards may be identified by the suitability standard module 32. For instance, a suitability standard for a user identified to be a twenty-year old male viewing a pop musician's website might indicate that a small amount of violent and sexual content may be appropriate for the user, but that alcohol-related content is not. The suitability standard may be used to select a document appropriate for that user.
  • When server 2 attempts to select one or more documents for potential delivery to a requesting service provider 8 or end user 10, the suitability standard module 32 may attempt to determine whether any information relating to the preferences of the provider 8 or end user 10 are stored in the suitability database 52. If a suitability standard exists for a potential content recipient, the document provision module 34 may select a document that satisfies the suitability standards (e.g., a document that contains very little violent content). A similar, but slightly different, method of identifying appropriate content may be accomplished using sensitivity scores, as described herein.
  • A document provision module 34 may select and provide documents in response to a request from a provider 8, end user 10, or other entity. For instance, a children's book retailer may request an advertisement to display on their site. In response, the document provision module 34 may identify or determine sensitivity score information and suitability information associated with the children's book retailer and then select a document based on this information (such as an identified suitability standard). For instance, if the site is associated with a high sensitivity to violent content, the document provision module 34 may select content that has an aggregate rating indicating zero violent content. The document provision module 34 might also select a document that was verified by a trusted evaluator to have no objectionable violent content.
  • Document selection may be based on the aggregate rating associated with the document, as well as suitability and/or sensitivity information. For instance, the document provision module 34 may determine that the provider has a high sensitivity against prurient content and therefore select a document where no evaluator found pornographic content—or where no evaluator found sexual content of any kind. The document provision module 34 may also determine that the provider prefers documents with an aggregate rating that indicates a high value in the category of child content and therefore select a document containing substantial children's content.
  • By identifying a suitability and/or sensitivity score for particular providers 8 and end users 10 (or other entities that receive documents), a document may be chosen that fits a suitability profile (or standard) associated with that entity. Thus, end users may receive non-offensive content, and content providers may ensure the propriety of the content provided on their sites.
  • Other module(s) 36 may accomplish other functions related to rating electronic documents.
  • Illustrative System Network Environment
  • FIG. 2 depicts a networked environment for operation of a system for rating a document according to an embodiment of the invention. In such an environment, evaluators 4 and providers 8 may connect over a network 14, 15 to a server 2 (e.g., using a secure https connection) to provide documents and rating information to server 2 and to receive documents and rating request information from server 2. The server 2 may store the document and rating information in a database 6. The server 2 may distribute the documents through various forums or feeds, including direct distribution in print media, providing the documents on one or more web sites affiliated with the server 2 and through providers 8. It should be noted that providers may comprise syndication partners of the server 2 (e.g., connected over network 14 or 15 depending on security desired), content systems (e.g., with associated content databases) and search engine systems operated by the server 2 or provider(s) 8.
  • Through these various forums, the documents provided to the providers 8 may be included in pages (or other documents) displayed to end-users 10 (often called an impression).
  • Each of server 2, evaluators 4, providers 8, and document sources 12 may comprise computerized systems that include one or more of the following systems: a web server, a database server, proxy server, network balancing mechanisms and systems, and various software components that enable the system to operate on the internet or other network type system. Additionally, networks 14 and 15, although depicted as http networks, may comprise other networks such as private lines, intranets, or any other network. In an exemplary embodiment, the connection between a document source 12 such as an advertisement provider and server 2 (and other connections such as between a provider 8 and server 2) may comprise secure network connections to insure that data is not subject to attack or corruption by any hacker or other third party. In addition, whereas two evaluators 4 and two document providers 12 are depicted, it should be appreciated that one or more evaluators 4 and one or more document providers 12 may be provided in the network. Similarly, although one database 6 is depicted, it should be appreciated that multiple databases 6 may be provided and that such databases 6 may be connected to the server 2 via any type of network connection, including a distributed database server architecture.
  • Similarly, provider 8 a may comprise any number of such systems connected to the evaluator 4 or server 2 via any type of network, including an http or https network. Content provider 8 may comprise a system such as server 2 that provides functionality for enabling connection over the internet or other network protocols. End users 10 may comprise any user (such as users connected to the internet) and may comprise computerized systems that enable that connection through any of various types of networks, including through internet service providers, cable companies, and any other method of accessing data on the internet. Providers 8 may comprise any system that distributes content such as advertising to end-users 10.
  • Illustrative Process
  • FIG. 3 is a flow chart illustrating an exemplary method for rating an electronic document according to an embodiment of the invention. The method described herein may be implemented by the systems described in FIGS. 1 and 2.
  • In block 300, one or more documents may be received. For instance, the server may receive one or more advertisements from one or more partner advertisers or other content providers. Alternately or in addition, the server may generate one or more documents.
  • In block 310, the server may select one or more documents to pass to one or more evaluators. For instance, the server may pass the document to one or more partner advertisers or content providers, in which case these entities may be evaluators. These evaluators may be the same or different entities from which a document was received in block 300 (i.e., the server may select the original provider of the document (from block 300) to be one of the evaluators in step 310).
  • The server may select the documents and evaluators randomly or based on an algorithm and/or one or more criteria. The document may be selected from among a plurality of documents, and the evaluators may be selected from among a plurality of evaluators. It should be understood that while this description discloses the method of rating an electronic document, many documents can be rated using this method at the same time. For instance, as each additional document is received by the server, the documents may be automatically passed to several evaluators selected immediately by the system.
  • In block 320, the selected document may be passed to the one or more evaluators. For instance, the server may pass the document to one or more partner advertisers who will rate the document. The server may also transmit rating instructions to the evaluators 4 that describe the various ratings requested for the document. For instance, the server may request each evaluator to rate the document according to a variety of criteria such as target age range, family content, violent content, and other criteria.
  • In block 330, the evaluators may generate one or more content ratings associated with the document. For instance, a partner evaluator may have an one or more evaluator employees or agents review the document and rate the document in each category specified by the server. The content ratings may be numerical scores (e.g., a number between 1 and 5, or another number or percentage), codes (such as “V” for violent), or verbal comments (e.g., essay responses).
  • In block 340, the content ratings may be received from the evaluators. For instance, the content ratings may be received by the server from the partner advertisers.
  • In optional block 350, sensitivity ratings and evaluator trust scores may be identified. For instance, the server may identify trust scores associated with one or more of the evaluators that submitted content ratings for the document. Trust scores may be determined and identified as described for the trust score module 24 of FIG. 1, and sensitivity scores may be determined and identified as described for the sensitivity module 26 of FIG. 1.
  • In block 360, an aggregate rating may be determined. The aggregate rating may be based on one or more of content ratings, sensitivity scores, and trust scores. The aggregate rating may be determined by any method as described above for the rating aggregation module 30 (see FIG. 1).
  • In block 370, a request for a document may be received. For instance, the server may receive a request for a document from a provider 8 or an end user 10. In block 380, a suitability standard and/or a sensitivity score may be determined.
  • In block 390, a document may be selected. For instance, a server that receives a request for a document from a user or provider may select a document for the user or provider. The selecting may be based on a suitability standard of the user or provider, one or more aggregate ratings of the document, and/or sensitivity scores associated with the evaluators, server, provider(s), and/or user(s).
  • In block 400, one or more selected documents may be passed to the requesting entity. For instance, if a provider or user requested a document in block 370, the server may pass the selected document to the provider or user, as the case may be.
  • It will be appreciated to those skilled in the art that the acts described may be performed by hardware, software, or a combination thereof, with or without human intervention, as may be embodied in one or more computing systems such as a server system coupled to entities such as providers, evaluators, and end users. Further, it should be appreciated that not all of the blocks must be accomplished. For instance, in one embodiment, the method may begin at block 340 and end at block 390. Also, it is not necessary that the action(s) of each block be performed in the order shown in FIG. 3. Any orderings may be considered.
  • It should be noted that the aggregate content rating may be determined after a user or content provider requests a document from the server rather than before such request. Because sensitivities, suitability standards, and evaluator trust scores may change over time, and because new ratings may be added for a particular document, the document's aggregate rating may also change. Obtaining an up-to-date rating for a document before providing it to a user or provider may maximize the likelihood that the document is appropriate for the user or provider.
  • Illustrative User Interface and Results
  • FIG. 4 shows an exemplary document 1 according to an embodiment of the invention. FIG. 4 depicts an exemplary web page 1 a search result from an internet search engine. The web page 1 a itself may be a document. Content on the web page 1 a may also be a document. For instance, the advertisements 1 b on the search result page 1 a may also be documents. Other types of documents may be considered, such as advertisements, files, programs, and other information.
  • The document may have various types of content. For instance, the document may have words, images, sounds, and other information, as well as functions or programs which may produce words, images, sounds, and other information. Each document may have different amounts of various types of content, such as sexual content, violent content, drug or alcohol-related content, financial content, adult-related content, child-related content, and other content.
  • For instance, the document may have a picture of a bikini-clad woman holding a glass of wine and an associated title stating “Fun in the sun with WineCo brand wine.” Another document may show a man holding a gun pointed at an icon that says “debt.” Another document may state “investments with FundCo yielded 6.25% over prime last year.” Another document may show children dancing underneath a rainbow and singing “It's a Small World After All.” Another document may have an icon which, when clicked, allows the user to virtually duck hunt by using a cursor to aim a rifle at ducks sitting in a lake, as in a video game.
  • FIG. 5 shows an exemplary content rating request 50 according to an embodiment of the invention. The content rating request 50 may comprise one or more requests for specific ratings 50 a-50 c across a range of subject matter and content types. For instance, there may be requests for ratings for violence 50 a, teenage appropriateness 50 b, country-specific suitability considerations 50 c, and other information. For instance, a content rating request might ask the evaluator to provide a number (e.g., a number between 1 and 10) indicating the amount of sexual content, violent content, adult content, language- or country-specific content, or other types of content or criteria. The request may also request information regarding when (time of day, week, year) the document is most suitable for viewing. The request may also ask the requestor to explain reasons for the requestor's numerical ratings or provide other verbal ratings.
  • FIG. 6 shows an exemplary content rating 60 according to an embodiment of the invention. The content rating 50 may comprise one or more subject area content ratings 60 a-60 c for the document, such as ratings for violence 60 a, teenage appropriateness 60 b, and country-specific suitability considerations 60 c, and other information. The content rating may include one or more responses to the content rating request (see FIG. 5). The content rating may indicate numerical or verbal ratings across a variety of criteria, such as sexual content, violent content, adult-themed content, culture-specific content, or other content criteria.
  • In practice, the server may receive a plurality of documents from document sources. It may select one or more documents (such as five documents) and one or more evaluators to select the one or more documents. For instance, the server may receive 100 documents and select five for evaluation, and then it may select three raters to rate each of the five documents. (Also and/or alternately, it may send the five documents to a plurality of selected evaluators so that each document has three evaluators, but each of the evaluators does not have all three documents.) The server may send an evaluation request with each document. Alternately, instead of passing the documents and requests to the selected evaluators, the server may merely post the documents and evaluation requests (e.g., evaluation forms) in a database (e.g., on a website) and enable the evaluators to access the database and provide content ratings.
  • For instance, one content rating 60 of the document with a bikini-clad woman and glass of wine by one evaluator may show a rating of 6 out of 10 for sexual content, a 4 out of 5 for alcohol content, an indication that the document is suitable for children, and the rating may include an indication that the document is most suitable between the hours of 7 p.m. and 6 a.m.
  • A content rating from a second evaluator for the same document may indicate a rating of 7 out of 10 for sexual content, a 3 out of 5 for alcohol content, an indication that the document is suitable for children, and an indication that the document is most suitable between the hours of 4 p.m. and 6 a.m. A content rating from a third evaluator for the same document may indicate an 8 out of 10 for sexual content, a 3 out of 5 for alcohol content, an indication that the ad is not suitable for children, and an indication that the document is most suitable between the hours of 11 p.m. and 6 a.m., and not on holidays.
  • The server may calculate an aggregate rating for this document based on the three ratings. The server may specify a high sensitivity for children's content and a medium sensitivity for violent content. The server may calculate an aggregate rating for sexual content based on a mean (or median) of the three sexual content ratings, which in this case would be 7 out of 10. The server may calculate an aggregate rating for alcohol content based on a mode (most common score) of the alcohol ratings, which in this case is 3 out of 5. Also, the server may discount the first evaluator's rating of 4 out of 5 if the first evaluator has a low trust score, and a weighted average of the three ratings might be 3.1 out of 5 (which may be rounded to 3). Because the server applies a high sensitivity to children's content, it might determine that the document is not suitable for children because one of the raters indicated that the document was not suitable for children. The server may select the time of day rating of the most trusted evaluator. If the evaluator who indicated that the most suitable hours were between 11 p.m. and 6 a.m., the aggregate rating may indicate that the most suitable hours are between 11 p.m. and 6 a.m. The aggregate rating may also indicate the standard deviation for each component of the aggregate rating, or it may use some other measure to indicate the variance of the different ratings from the different evaluators.
  • If any of the three ratings was significantly different from the aggregate rating, the rating may be marked for further review. For instance, since only one evaluator indicated that the document is not suitable for children, the server (or agent of the server or another evaluator) may review the document to determine whether the unusual rating was accurate. For instance, the server may review the evaluator's ratings and/or generate (or request) one or more additional ratings for the document. Depending on the results, the server may change the aggregate rating (e.g., by re-calculating it) and/or change the trust score of the evaluator in question for one or more criteria of content.
  • Aggregate ratings of other documents may also be determined. For instance, the ad with children singing under a rainbow may be rated to have zero sexual content, zero alcohol content, zero violent content, and suitability for any time of day (especially 8 am-6 pm).
  • An end user or provider may then request a document at midnight. For instance, a client may click on a provider's web page, and the provider may request an advertisement to display to the client on the provider's site. The server may select a document to pass to the provider according to the aggregate content ratings of the various documents. In order to select an appropriate document, the server may also identify sensitivity and suitability information of the requesting provider (or user) and consider other criteria, such as time of request. For instance, the server may identify that the provider has a high sensitivity to sexual content. (In another example, the server may identify (e. g., by using cookies or information stored in a database associated with the user's IP address) the age and gender of the user (e.g., 25 year old male). The server may have assign sensitivity or suitability criteria, e.g. for the time of day. For a request at midnight, the server may assign lower sensitivities to sexual and violent content than the middle of the day, since it is far less likely that children will be browsing the internet at that time. The relevant time may be from the perspective of the server, provider, or end user.
  • The server may accordingly select a document that is suitable for a provider who has a high sensitivity to sexual content and a medium sensitivity to violent content. The server may consider for selection all or a portion of documents stored in a database, including the bikini/wine document, the singing children, and the duck hunting documents. For instance, the server may consider only those documents which have an aggregate rating indicating little or no sexual content and only mild (or less) violence. In the middle of the day, the server might apply a high sensitivity to violent content due to the time of day and may therefore only consider non-violent documents at that time. At midnight, however, the server might consider other documents that may not be appropriate to users at an earlier time.
  • The server may then search for a document that fits the various criteria associated with the document request and the relevant sensitivity and suitability information. Although the children singing may have no offensive or potentially offensive content, it also may have a low click through rate and therefore not be selected. It should be noted that documents which have little or no potentially offensive content may or may not be favored over documents which do contain potentially offensive material. Here, the duck hunting document may be selected if its aggregate rating indicates only mild violence. The selection of this document may be more likely if it is an ad with a high click through rate. Other factors of document selection may be considered.
  • The embodiments of the present inventions are not to be limited in scope by the specific embodiments described herein. For example, although many of the embodiments disclosed herein have been described with reference to advertisements, the principles herein are equally applicable to documents and other content. Indeed, various modifications of the embodiments of the present inventions, in addition to those described herein, will be apparent to those of ordinary skill in the art from the foregoing description and accompanying drawings. Thus, such modifications are intended to fall within the scope of the following appended claims. Further, although some of the embodiments of the present invention have been described herein in the context of a particular implementation in a particular environment for a particular purpose, those of ordinary skill in the art will recognize that its usefulness is not limited thereto and that the embodiments of the present inventions can be beneficially implemented in any number of environments for any number of purposes. Accordingly, the claims set forth below should be construed in view of the full breath and spirit of the embodiments of the present inventions as disclosed herein.

Claims (20)

1. A computer-implemented method, comprising:
receiving, at a server, rating information associated with contents of a document from one or more evaluators;
identifying, at the server, a trust score for each of the one or more evaluators, each trust score being a measure of an extent to which a respective evaluator's rating information is considered in determining an aggregate rating, each trust score based on factors associated with the respective evaluator;
identifying a sensitivity score, the sensitivity score indicating a level of conservatism in determining the aggregate rating;
determining the aggregate rating for the document based on the rating information, the trust scores, and the sensitivity score;
receiving a request from a recipient for one or more documents;
identifying a preferred aggregate rating to be associated with the request; and
determining whether to deliver the document in response to the request based on whether the aggregate rating satisfies the preferred aggregate rating.
2. The method of claim 1, wherein identifying a preferred aggregate rating to be associated with the request comprises:
receiving the preferred aggregate rating from the recipient.
3. The method of claim 1, wherein the preferred aggregate rating is associated with a user or is stored in a profile.
4. The method of claim 1, wherein each trust score is based on a geographical location of a respective evaluator.
5. The method of claim 1, wherein each trust score is based on one or more prior content ratings received from the respective evaluator.
6. The method of claim 1, wherein each trust score is based on an industry associated with the respective evaluator.
7. The method of claim 1, further comprising:
identifying a suitability standard associated with the recipient.
8. The method of claim 7, wherein determining the aggregate rating for the document based on the rating information, the trust scores, and the sensitivity score comprises:
determining the aggregate rating for the document based on the rating information, the trust scores, the sensitivity score, and the suitability standard.
9. The method of claim 1, wherein the aggregate rating comprises a mean of the rating information.
10. The method of claim 1, wherein the aggregate rating comprises a mode of the rating information.
11. The method of claim 1, wherein the aggregate rating comprises a median of the rating information.
12. A computer-implemented method, comprising:
associating evaluation information with documents, the evaluation information comprising trust information and rating information;
receiving a request at a server for one or more of the documents;
ranking the documents based on the evaluation information in response to the request;
providing the ranked documents; and
updating the trust information based on the ranking.
13. The method of claim 12, further comprising:
receiving the rating information from one or more evaluators.
14. The method of claim 12, wherein the trust information includes trust scores being a measure of an extent to which a respective evaluator's rating information is considered in determining an aggregate rating, each trust score based on factors associated with the respective evaluator.
15. The method of claim 14, wherein each trust score is based on one or more prior content ratings received from the respective evaluator.
16. The method of claim 14, further comprising:
identifying a sensitivity score, the sensitivity score indicating a level of conservatism in determining the aggregate rating; and
determining the aggregate rating for each document based on the rating information associated with each document, the trust scores associated with each document, and the sensitivity score.
17. The method of claim 16, further comprising:
identifying a preferred aggregate rating to be associated with the request; and
18. The method of claim 17, wherein ranking the documents based on the evaluation information in response to the request comprises:
ranking the documents based on the aggregate rating for each document and the preferred aggregate rating.
19. A computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:
receiving, at a server, rating information associated with contents of a document from one or more evaluators;
identifying, at the server, a trust score for each of the one or more evaluators, each trust score being a measure of an extent to which a respective evaluator's rating information is considered in determining an aggregate rating, each trust score based on factors associated with the respective evaluator;
identifying a sensitivity score, the sensitivity score indicating a level of conservatism in determining the aggregate rating;
determining the aggregate rating for the document based on the rating information, the trust scores, and the sensitivity score;
receiving a request from a recipient for one or more documents;
identifying a preferred aggregate rating to be associated with the request; and
determining whether to deliver the document in response to the request based on whether the aggregate rating satisfies the preferred aggregate rating.
20. A computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:
associating evaluation information with documents, the evaluation information comprising trust information and rating information;
receiving a request at a server for one or more of the documents;
ranking the documents based on the evaluation information in response to the request;
providing the ranked documents; and
updating the trust information based on the ranking.
US12/406,865 2004-03-30 2009-03-18 System and method for rating electronic documents Abandoned US20100070510A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US12/406,865 US20100070510A1 (en) 2004-03-30 2009-03-18 System and method for rating electronic documents

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US10/812,417 US7533090B2 (en) 2004-03-30 2004-03-30 System and method for rating electronic documents
US12/406,865 US20100070510A1 (en) 2004-03-30 2009-03-18 System and method for rating electronic documents

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US10/812,417 Continuation US7533090B2 (en) 2004-03-30 2004-03-30 System and method for rating electronic documents

Publications (1)

Publication Number Publication Date
US20100070510A1 true US20100070510A1 (en) 2010-03-18

Family

ID=35055616

Family Applications (2)

Application Number Title Priority Date Filing Date
US10/812,417 Expired - Fee Related US7533090B2 (en) 2004-03-30 2004-03-30 System and method for rating electronic documents
US12/406,865 Abandoned US20100070510A1 (en) 2004-03-30 2009-03-18 System and method for rating electronic documents

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US10/812,417 Expired - Fee Related US7533090B2 (en) 2004-03-30 2004-03-30 System and method for rating electronic documents

Country Status (1)

Country Link
US (2) US7533090B2 (en)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070033531A1 (en) * 2005-08-04 2007-02-08 Christopher Marsh Method and apparatus for context-specific content delivery
US20090287697A1 (en) * 2005-08-08 2009-11-19 Google Inc. Agent rank
US20090327287A1 (en) * 2005-11-01 2009-12-31 Lycos, Inc. Method and system for performing a search on a network
US7971137B2 (en) 2005-12-14 2011-06-28 Google Inc. Detecting and rejecting annoying documents
US20110307408A1 (en) * 2010-06-14 2011-12-15 Computer Associates Think, Inc. System and Method for Assigning a Business Value Rating to Documents in an Enterprise
US20120328262A1 (en) * 2011-06-24 2012-12-27 Franck Thudor Reproduction device and method for operating the same
WO2013138743A1 (en) * 2012-03-15 2013-09-19 Cobb Daniel J Digital parental controls interface
US8606792B1 (en) 2010-02-08 2013-12-10 Google Inc. Scoring authors of posts
US20140308650A1 (en) * 2013-04-12 2014-10-16 Pearson Education, Inc. Evaluation control
US9066122B1 (en) * 2013-03-08 2015-06-23 Google Inc. Serving video content segments
US9483954B2 (en) 2013-03-12 2016-11-01 Pearson Education, Inc. Educational network based intervention
US9928383B2 (en) 2014-10-30 2018-03-27 Pearson Education, Inc. Methods and systems for network-based analysis, intervention, and anonymization
US10516691B2 (en) 2013-03-12 2019-12-24 Pearson Education, Inc. Network based intervention
US10699296B2 (en) * 2015-12-30 2020-06-30 Verizon Patent And Licensing, Inc. Native video advertising with voice-based ad management and machine-to-machine ad bidding
US11403849B2 (en) 2019-09-25 2022-08-02 Charter Communications Operating, Llc Methods and apparatus for characterization of digital content
US11616992B2 (en) 2010-04-23 2023-03-28 Time Warner Cable Enterprises Llc Apparatus and methods for dynamic secondary content and data insertion and delivery
US11750887B2 (en) 2012-03-15 2023-09-05 Black Wave Adventures, Llc Digital content controller

Families Citing this family (88)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8051104B2 (en) 1999-09-22 2011-11-01 Google Inc. Editing a network of interconnected concepts
US7752072B2 (en) * 2002-07-16 2010-07-06 Google Inc. Method and system for providing advertising through content specific nodes over the internet
US8050970B2 (en) 2002-07-25 2011-11-01 Google Inc. Method and system for providing filtered and/or masked advertisements over the internet
US20040044571A1 (en) * 2002-08-27 2004-03-04 Bronnimann Eric Robert Method and system for providing advertising listing variance in distribution feeds over the internet to maximize revenue to the advertising distributor
US8311890B2 (en) 2002-11-01 2012-11-13 Google Inc. Method and system for dynamic textual ad distribution via email
DE10345065A1 (en) * 2003-09-26 2005-04-14 Boehringer Ingelheim Pharma Gmbh & Co. Kg Aerosol formulation for inhalation containing an anticholinergic
US7930206B2 (en) 2003-11-03 2011-04-19 Google Inc. System and method for enabling an advertisement to follow the user to additional web pages
US20050096980A1 (en) * 2003-11-03 2005-05-05 Ross Koningstein System and method for delivering internet advertisements that change between textual and graphical ads on demand by a user
US20050144069A1 (en) * 2003-12-23 2005-06-30 Wiseman Leora R. Method and system for providing targeted graphical advertisements
US7533090B2 (en) * 2004-03-30 2009-05-12 Google Inc. System and method for rating electronic documents
US20050222900A1 (en) * 2004-03-30 2005-10-06 Prashant Fuloria Selectively delivering advertisements based at least in part on trademark issues
US7996753B1 (en) 2004-05-10 2011-08-09 Google Inc. Method and system for automatically creating an image advertisement
US11409812B1 (en) * 2004-05-10 2022-08-09 Google Llc Method and system for mining image searches to associate images with concepts
US7801738B2 (en) * 2004-05-10 2010-09-21 Google Inc. System and method for rating documents comprising an image
US7697791B1 (en) 2004-05-10 2010-04-13 Google Inc. Method and system for providing targeted documents based on concepts automatically identified therein
US7639898B1 (en) 2004-05-10 2009-12-29 Google Inc. Method and system for approving documents based on image similarity
US8065611B1 (en) 2004-06-30 2011-11-22 Google Inc. Method and system for mining image searches to associate images with concepts
US20050267799A1 (en) * 2004-05-10 2005-12-01 Wesley Chan System and method for enabling publishers to select preferred types of electronic documents
US8762280B1 (en) 2004-12-02 2014-06-24 Google Inc. Method and system for using a network analysis system to verify content on a website
US20060130143A1 (en) * 2004-12-14 2006-06-15 Shrader Theodore J Method and system for utilizing informaiton worms to generate information channels
US20070156676A1 (en) * 2005-09-09 2007-07-05 Outland Research, Llc System, Method and Computer Program Product for Intelligent Groupwise Media Selection
US20070189544A1 (en) * 2005-01-15 2007-08-16 Outland Research, Llc Ambient sound responsive media player
US8112310B1 (en) 2005-01-21 2012-02-07 A9.Com, Inc. Internet advertising system that provides ratings-based incentives to advertisers
US7657520B2 (en) * 2005-03-03 2010-02-02 Google, Inc. Providing history and transaction volume information of a content source to users
US8087068B1 (en) 2005-03-08 2011-12-27 Google Inc. Verifying access to a network account over multiple user communication portals based on security criteria
US7757080B1 (en) 2005-03-11 2010-07-13 Google Inc. User validation using cookies and isolated backup validation
US7921028B2 (en) * 2005-04-12 2011-04-05 Hewlett-Packard Development Company, L.P. Systems and methods of partnering content creators with content partners online
US20070011050A1 (en) * 2005-05-20 2007-01-11 Steven Klopf Digital advertising system
US7744256B2 (en) * 2006-05-22 2010-06-29 Edison Price Lighting, Inc. LED array wafer lighting fixture
US20070162342A1 (en) * 2005-05-20 2007-07-12 Steven Klopf Digital advertising system
US7725502B1 (en) 2005-06-15 2010-05-25 Google Inc. Time-multiplexing documents based on preferences or relatedness
US7903099B2 (en) * 2005-06-20 2011-03-08 Google Inc. Allocating advertising space in a network of displays
US8452656B2 (en) * 2005-06-29 2013-05-28 Google Inc. Prioritizing ad review, by using expected revenue for example, in an advertising system
US20070005420A1 (en) * 2005-06-30 2007-01-04 Microsoft Corporation Adjustment of inventory estimates
US8176101B2 (en) 2006-02-07 2012-05-08 Google Inc. Collaborative rejection of media for physical establishments
US20070073696A1 (en) * 2005-09-28 2007-03-29 Google, Inc. Online data verification of listing data
US7603619B2 (en) * 2005-11-29 2009-10-13 Google Inc. Formatting a user network site based on user preferences and format performance data
US7725530B2 (en) * 2005-12-12 2010-05-25 Google Inc. Proxy server collection of data for module incorporation into a container document
US7730082B2 (en) 2005-12-12 2010-06-01 Google Inc. Remote module incorporation into a container document
US8185819B2 (en) 2005-12-12 2012-05-22 Google Inc. Module specification for a module to be incorporated into a container document
US7730109B2 (en) * 2005-12-12 2010-06-01 Google, Inc. Message catalogs for remote modules
US20070145680A1 (en) * 2005-12-15 2007-06-28 Outland Research, Llc Shake Responsive Portable Computing Device for Simulating a Randomization Object Used In a Game Of Chance
JP4870448B2 (en) * 2006-02-23 2012-02-08 株式会社日立製作所 Information processing apparatus, customer needs analysis method, and program
US20070239533A1 (en) * 2006-03-31 2007-10-11 Susan Wojcicki Allocating and monetizing advertising space in offline media through online usage and pricing model
US10289294B2 (en) 2006-06-22 2019-05-14 Rohit Chandra Content selection widget for visitors of web pages
US9292617B2 (en) 2013-03-14 2016-03-22 Rohit Chandra Method and apparatus for enabling content portion selection services for visitors to web pages
US11429685B2 (en) 2006-06-22 2022-08-30 Rohit Chandra Sharing only a part of a web page—the part selected by a user
US11763344B2 (en) 2006-06-22 2023-09-19 Rohit Chandra SaaS for content curation without a browser add-on
US10909197B2 (en) 2006-06-22 2021-02-02 Rohit Chandra Curation rank: content portion search
US11288686B2 (en) 2006-06-22 2022-03-29 Rohit Chandra Identifying micro users interests: at a finer level of granularity
US11853374B2 (en) 2006-06-22 2023-12-26 Rohit Chandra Directly, automatically embedding a content portion
US11301532B2 (en) 2006-06-22 2022-04-12 Rohit Chandra Searching for user selected portions of content
US10866713B2 (en) 2006-06-22 2020-12-15 Rohit Chandra Highlighting on a personal digital assistant, mobile handset, eBook, or handheld device
US8910060B2 (en) * 2006-06-22 2014-12-09 Rohit Chandra Method and apparatus for highlighting a portion of an internet document for collaboration and subsequent retrieval
US10884585B2 (en) 2006-06-22 2021-01-05 Rohit Chandra User widget displaying portions of content
US8661031B2 (en) * 2006-06-23 2014-02-25 Rohit Chandra Method and apparatus for determining the significance and relevance of a web page, or a portion thereof
US8352573B2 (en) * 2006-06-23 2013-01-08 Rohit Chandra Method and apparatus for automatically embedding and emailing user-generated highlights
US8023927B1 (en) 2006-06-29 2011-09-20 Google Inc. Abuse-resistant method of registering user accounts with an online service
US8407250B2 (en) 2006-08-07 2013-03-26 Google Inc. Distribution of content document to varying users with security customization and scalability
US8954861B1 (en) 2006-08-07 2015-02-10 Google Inc. Administrator configurable gadget directory for personalized start pages
US8185830B2 (en) 2006-08-07 2012-05-22 Google Inc. Configuring a content document for users and user groups
WO2008036969A2 (en) * 2006-09-22 2008-03-27 John Stannard Davis, Iii Trust network based advertising system
US20080077562A1 (en) * 2006-09-22 2008-03-27 Leonard Dylan Schleppe System and Method for Relating Ratings by Entities to Associations among the Entities
US9456250B2 (en) 2006-12-15 2016-09-27 At&T Intellectual Property I, L.P. Automatic rating optimization
US7711684B2 (en) 2006-12-28 2010-05-04 Ebay Inc. Collaborative content evaluation
US8108253B2 (en) * 2007-02-13 2012-01-31 Google Inc. Identifying advertising specialist
US8176055B1 (en) * 2007-03-27 2012-05-08 Google Inc. Content entity management
US8311883B2 (en) * 2007-09-26 2012-11-13 Redeparede.Com Inc. Method and system for sorting online advertisements
US20090106070A1 (en) 2007-10-17 2009-04-23 Google Inc. Online Advertisement Effectiveness Measurements
US9679256B2 (en) * 2010-10-06 2017-06-13 The Chancellor, Masters And Scholars Of The University Of Cambridge Automated assessment of examination scripts
US20120137316A1 (en) * 2010-11-30 2012-05-31 Kirill Elizarov Media information system and method
US20120150850A1 (en) * 2010-12-08 2012-06-14 Microsoft Corporation Search result relevance by determining query intent
US8849812B1 (en) * 2011-08-31 2014-09-30 BloomReach Inc. Generating content for topics based on user demand
WO2014030186A1 (en) * 2012-08-23 2014-02-27 富士通株式会社 Relay device, relay method, relay program and relay system
US9591052B2 (en) 2013-02-05 2017-03-07 Apple Inc. System and method for providing a content distribution network with data quality monitoring and management
EP3074935A1 (en) * 2013-11-28 2016-10-05 Faulwetter, Patrick Platform device for providing quantitative collective knowledge
CN105874486B (en) * 2013-11-28 2020-10-27 帕特里克·弗尔韦特 Platform device for providing qualitative cluster knowledge
US10089660B2 (en) * 2014-09-09 2018-10-02 Stc.Unm Online review assessment using multiple sources
US10127214B2 (en) * 2014-12-09 2018-11-13 Sansa Al Inc. Methods for generating natural language processing systems
US10102764B1 (en) * 2016-06-22 2018-10-16 AltSchool, PBC Systems and methods with image capture device and assessment computing device for learning assessment
US11514353B2 (en) * 2017-10-26 2022-11-29 Google Llc Generating, using a machine learning model, request agnostic interaction scores for electronic communications, and utilization of same
US10395169B1 (en) 2018-07-06 2019-08-27 Global Elmeast Inc. Self learning neural knowledge artifactory for autonomous decision making
US11610107B2 (en) 2018-07-06 2023-03-21 Global Elmeast Inc. Methodology to automatically incorporate feedback to enable self learning in neural learning artifactories
US10311058B1 (en) 2018-07-06 2019-06-04 Global Elmeast Inc. Techniques for processing neural queries
US20200012930A1 (en) * 2018-07-06 2020-01-09 Global Elmeast Inc. Techniques for knowledge neuron enhancements
US20210118063A1 (en) * 2019-10-18 2021-04-22 Google Llc Multi-tier scalable media analysis
US11783122B1 (en) 2022-05-22 2023-10-10 Klaviyo, Inc. Automated testing of templates of a mobile message
US11887149B1 (en) 2023-05-24 2024-01-30 Klaviyo, Inc Determining winning arms of A/B electronic communication testing for a metric using historical data and histogram-based bayesian inference

Citations (57)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5636346A (en) * 1994-05-09 1997-06-03 The Electronic Address, Inc. Method and system for selectively targeting advertisements and programming
US5724521A (en) * 1994-11-03 1998-03-03 Intel Corporation Method and apparatus for providing electronic advertisements to end users in a consumer best-fit pricing manner
US5845265A (en) * 1995-04-26 1998-12-01 Mercexchange, L.L.C. Consignment nodes
US5918010A (en) * 1997-02-07 1999-06-29 General Internet, Inc. Collaborative internet data mining systems
US5920854A (en) * 1996-08-14 1999-07-06 Infoseek Corporation Real-time document collection search engine with phrase indexing
US5931901A (en) * 1996-12-09 1999-08-03 Robert L. Wolfe Programmed music on demand from the internet
US6026368A (en) * 1995-07-17 2000-02-15 24/7 Media, Inc. On-line interactive system and method for providing content and advertising information to a targeted set of viewers
US6044375A (en) * 1998-04-30 2000-03-28 Hewlett-Packard Company Automatic extraction of metadata using a neural network
US6061659A (en) * 1997-06-03 2000-05-09 Digital Marketing Communications, Inc. System and method for integrating a message into a graphical environment
US6067570A (en) * 1997-10-20 2000-05-23 The Delfin Project, Inc. Method and system for displaying and interacting with an informational message based on an information processing system event
US6078866A (en) * 1998-09-14 2000-06-20 Searchup, Inc. Internet site searching and listing service based on monetary ranking of site listings
US6223163B1 (en) * 1997-03-21 2001-04-24 Walker Digital, Llc Method and apparatus for controlling offers that are provided at a point-of-sale terminal
US6247009B1 (en) * 1997-03-10 2001-06-12 Canon Kabushiki Kaisha Image processing with searching of image data
US6253189B1 (en) * 1997-09-15 2001-06-26 At&T Corp. System and method for completing advertising time slot transactions
US6269361B1 (en) * 1999-05-28 2001-07-31 Goto.Com System and method for influencing a position on a search result list generated by a computer network search engine
US6285987B1 (en) * 1997-01-22 2001-09-04 Engage, Inc. Internet advertising system
US6298348B1 (en) * 1998-12-03 2001-10-02 Expanse Networks, Inc. Consumer profiling system
US6324519B1 (en) * 1999-03-12 2001-11-27 Expanse Networks, Inc. Advertisement auction system
US20010047297A1 (en) * 2000-02-16 2001-11-29 Albert Wen Advertisement brokering with remote ad generation system and method in a distributed computer network
US20010051911A1 (en) * 2000-05-09 2001-12-13 Marks Michael B. Bidding method for internet/wireless advertising and priority ranking in search results
US20020002525A1 (en) * 2000-06-30 2002-01-03 Masatoshi Arai Digital contents advertisement display system using auction
US20020035536A1 (en) * 2000-09-18 2002-03-21 Peter Gellman Method and system for forming a list-based value discovery network
US20020038282A1 (en) * 2000-09-27 2002-03-28 Montgomery Rob R. Buyer-side auction dynamic pricing agent, system, method and computer program product
US20020046104A1 (en) * 2000-05-09 2002-04-18 Geomicro, Inc. Method and apparatus for generating targeted impressions to internet clients
US20020077891A1 (en) * 2000-12-15 2002-06-20 Castle Daniel C. Method and apparatus to maximize advertising revenue
US6421675B1 (en) * 1998-03-16 2002-07-16 S. L. I. Systems, Inc. Search engine
US20020099605A1 (en) * 2000-10-06 2002-07-25 Searchcactus, Llc Search engine with demographic-based advertising
US20020111898A1 (en) * 2001-01-22 2002-08-15 Chisato Numaoka Advertisement space auction method, apparatus and storage medium
US20020123988A1 (en) * 2001-03-02 2002-09-05 Google, Inc. Methods and apparatus for employing usage statistics in document retrieval
US6526440B1 (en) * 2001-01-30 2003-02-25 Google, Inc. Ranking search results by reranking the results based on local inter-connectivity
US20030149618A1 (en) * 2002-02-01 2003-08-07 Microsoft Corporation Flexible dynamic advertising
US20040015397A1 (en) * 2002-07-16 2004-01-22 Barry Christopher J. Method and system for providing advertising through content specific nodes over the internet
US20040019523A1 (en) * 2002-07-25 2004-01-29 Barry Christopher J. Method and system for providing filtered and/or masked advertisements over the internet
US20040044571A1 (en) * 2002-08-27 2004-03-04 Bronnimann Eric Robert Method and system for providing advertising listing variance in distribution feeds over the internet to maximize revenue to the advertising distributor
US20040059712A1 (en) * 2002-09-24 2004-03-25 Dean Jeffrey A. Serving advertisements using information associated with e-mail
US20040059708A1 (en) * 2002-09-24 2004-03-25 Google, Inc. Methods and apparatus for serving relevant advertisements
US20040093327A1 (en) * 2002-09-24 2004-05-13 Darrell Anderson Serving advertisements based on content
US20040107363A1 (en) * 2003-08-22 2004-06-03 Emergency 24, Inc. System and method for anticipating the trustworthiness of an internet site
US20040119740A1 (en) * 2002-12-24 2004-06-24 Google, Inc., A Corporation Of The State Of California Methods and apparatus for displaying and replying to electronic messages
US20040167928A1 (en) * 2002-09-24 2004-08-26 Darrell Anderson Serving content-relevant advertisements with client-side device support
US20040249709A1 (en) * 2002-11-01 2004-12-09 Donovan Kevin Rjb Method and system for dynamic textual ad distribution via email
US20040261096A1 (en) * 2002-06-20 2004-12-23 Bellsouth Intellectual Property Corporation System and method for monitoring blocked content
US20050065806A1 (en) * 2003-06-30 2005-03-24 Harik Georges R. Generating information for online advertisements from Internet data and traditional media data
US20050071224A1 (en) * 2003-09-30 2005-03-31 Andrew Fikes System and method for automatically targeting web-based advertisements
US20050096979A1 (en) * 2003-11-03 2005-05-05 Ross Koningstein System and method for enabling an advertisement to follow the user to additional web pages
US20050131918A1 (en) * 2003-12-12 2005-06-16 W. Daniel Hillis Personalized profile for evaluating content
US20050131762A1 (en) * 2003-12-31 2005-06-16 Krishna Bharat Generating user information for use in targeted advertising
US20050131758A1 (en) * 2003-12-11 2005-06-16 Desikan Pavan K. Systems and methods detecting for providing advertisements in a communications network
US20050144069A1 (en) * 2003-12-23 2005-06-30 Wiseman Leora R. Method and system for providing targeted graphical advertisements
US20050216335A1 (en) * 2004-03-24 2005-09-29 Andrew Fikes System and method for providing on-line user-assisted Web-based advertising
US20050223002A1 (en) * 2004-03-30 2005-10-06 Sumit Agarwal System and method for rating electronic documents
US20050222900A1 (en) * 2004-03-30 2005-10-06 Prashant Fuloria Selectively delivering advertisements based at least in part on trademark issues
US20050222989A1 (en) * 2003-09-30 2005-10-06 Taher Haveliwala Results based personalization of advertisements in a search engine
US20050222903A1 (en) * 2004-03-31 2005-10-06 Paul Buchheit Rendering content-targeted ads with e-mail
US6974398B2 (en) * 2002-06-06 2005-12-13 Steven Curtis Murphy Magnum bullet darts
US7240039B2 (en) * 2003-10-29 2007-07-03 Hewlett-Packard Development Company, L.P. System and method for combining valuations of multiple evaluators
US7765206B2 (en) * 2002-12-13 2010-07-27 Metaweb Technologies, Inc. Meta-Web

Family Cites Families (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5974398A (en) 1997-04-11 1999-10-26 At&T Corp. Method and apparatus enabling valuation of user access of advertising carried by interactive information and entertainment services
US6698020B1 (en) * 1998-06-15 2004-02-24 Webtv Networks, Inc. Techniques for intelligent video ad insertion
US6230170B1 (en) * 1998-06-17 2001-05-08 Xerox Corporation Spatial morphing of text to accommodate annotations
EP1159684A1 (en) 1998-12-18 2001-12-05 Flycast Communications Corp. Optimized internet advertising using history to select sites
US11109114B2 (en) 2001-04-18 2021-08-31 Grass Valley Canada Advertisement management method, system, and computer program product
US6985882B1 (en) 1999-02-05 2006-01-10 Directrep, Llc Method and system for selling and purchasing media advertising over a distributed communication network
US7072888B1 (en) * 1999-06-16 2006-07-04 Triogo, Inc. Process for improving search engine efficiency using feedback
US6434747B1 (en) 2000-01-19 2002-08-13 Individual Network, Inc. Method and system for providing a customized media list
US8813123B2 (en) 2000-01-19 2014-08-19 Interad Technologies, Llc Content with customized advertisement
US20020026359A1 (en) 2000-02-22 2002-02-28 Long Kenneth W. Targeted advertising method and system
BR0106739A (en) 2000-05-31 2002-04-02 Ntt Docomo Inc Improvement introduced in method and apparatus for the distribution of advertising and announcements through a network
US7058516B2 (en) * 2000-06-30 2006-06-06 Bioexpertise, Inc. Computer implemented searching using search criteria comprised of ratings prepared by leading practitioners in biomedical specialties
US20020002509A1 (en) * 2000-06-30 2002-01-03 Wagorn Paul E. Custom advertising and trade facilitation system for internet or e-mail implementation
US7599851B2 (en) * 2000-09-05 2009-10-06 Renee Frengut Method for providing customized user interface and targeted marketing forum
WO2002063414A2 (en) * 2000-11-01 2002-08-15 Real Media, Inc. System and method for delivering plural advertisement information on a data network
US20020138331A1 (en) * 2001-02-05 2002-09-26 Hosea Devin F. Method and system for web page personalization
US20020194062A1 (en) 2001-04-19 2002-12-19 Leif Linde Method and system for simulating the distribution of targeted advertising
JP2002358455A (en) 2001-05-31 2002-12-13 Matsushita Electric Ind Co Ltd Advertisement information distributing apparatus and charging apparatus
US9154823B2 (en) * 2001-06-06 2015-10-06 Sony Corporation Advertisement selecting apparatus, advertisement selecting method and storage medium
US20040054589A1 (en) 2001-06-14 2004-03-18 Nicholas Frank C. Method and system for providing network based target advertising and encapsulation
JP2003006085A (en) 2001-06-20 2003-01-10 Nec Corp Contents distribution system, its method and contents distribution program
US20030009495A1 (en) * 2001-06-29 2003-01-09 Akli Adjaoute Systems and methods for filtering electronic content
US20030083937A1 (en) 2001-11-01 2003-05-01 Masayuki Hasegawa Advertisement delivery systems, advertising content and advertisement delivery apparatus, and advertisement delivery methods
WO2003050744A1 (en) 2001-12-07 2003-06-19 Sofcast, Inc. Delivering content and advertisement
US20030126267A1 (en) * 2001-12-27 2003-07-03 Koninklijke Philips Electronics N.V. Method and apparatus for preventing access to inappropriate content over a network based on audio or visual content
CN1307805C (en) 2002-02-04 2007-03-28 松下电器产业株式会社 Advertisement program providing system
US20030217056A1 (en) * 2002-03-25 2003-11-20 Today Communications, Inc. Method and computer program for collecting, rating, and making available electronic information
JP4007060B2 (en) 2002-05-20 2007-11-14 日産自動車株式会社 Advertisement distribution processing system, advertisement distribution processing apparatus and method, communication terminal, and advertisement presentation method
US6983280B2 (en) * 2002-09-13 2006-01-03 Overture Services Inc. Automated processing of appropriateness determination of content for search listings in wide area network searches
JP2004249499A (en) * 2003-02-18 2004-09-09 Canon Inc Image forming system
US20040199584A1 (en) * 2003-03-05 2004-10-07 Evan Kirshenbaum Method and system for customized configuration of an appearance of a website for a user
US7263529B2 (en) * 2003-08-29 2007-08-28 Pitney Bowes Inc. Method and system for creating and maintaining a database of user profiles and a related value rating database for information sources and for generating a list of information sources having a high estimated value
US7587488B2 (en) * 2003-09-15 2009-09-08 Blue Coat Systems, Inc. Dynamic background rater for internet content
US20050144297A1 (en) * 2003-12-30 2005-06-30 Kidsnet, Inc. Method and apparatus for providing content access controls to access the internet

Patent Citations (59)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5636346A (en) * 1994-05-09 1997-06-03 The Electronic Address, Inc. Method and system for selectively targeting advertisements and programming
US5724521A (en) * 1994-11-03 1998-03-03 Intel Corporation Method and apparatus for providing electronic advertisements to end users in a consumer best-fit pricing manner
US5845265A (en) * 1995-04-26 1998-12-01 Mercexchange, L.L.C. Consignment nodes
US6026368A (en) * 1995-07-17 2000-02-15 24/7 Media, Inc. On-line interactive system and method for providing content and advertising information to a targeted set of viewers
US5920854A (en) * 1996-08-14 1999-07-06 Infoseek Corporation Real-time document collection search engine with phrase indexing
US5931901A (en) * 1996-12-09 1999-08-03 Robert L. Wolfe Programmed music on demand from the internet
US6285987B1 (en) * 1997-01-22 2001-09-04 Engage, Inc. Internet advertising system
US5918010A (en) * 1997-02-07 1999-06-29 General Internet, Inc. Collaborative internet data mining systems
US6336132B2 (en) * 1997-02-07 2002-01-01 About.Com, Inc. Internet resource location system with identified and approved human guides assigned to specific topics to provide content related to the topic
US6247009B1 (en) * 1997-03-10 2001-06-12 Canon Kabushiki Kaisha Image processing with searching of image data
US6223163B1 (en) * 1997-03-21 2001-04-24 Walker Digital, Llc Method and apparatus for controlling offers that are provided at a point-of-sale terminal
US6061659A (en) * 1997-06-03 2000-05-09 Digital Marketing Communications, Inc. System and method for integrating a message into a graphical environment
US6253189B1 (en) * 1997-09-15 2001-06-26 At&T Corp. System and method for completing advertising time slot transactions
US6067570A (en) * 1997-10-20 2000-05-23 The Delfin Project, Inc. Method and system for displaying and interacting with an informational message based on an information processing system event
US6421675B1 (en) * 1998-03-16 2002-07-16 S. L. I. Systems, Inc. Search engine
US6044375A (en) * 1998-04-30 2000-03-28 Hewlett-Packard Company Automatic extraction of metadata using a neural network
US6078866A (en) * 1998-09-14 2000-06-20 Searchup, Inc. Internet site searching and listing service based on monetary ranking of site listings
US6298348B1 (en) * 1998-12-03 2001-10-02 Expanse Networks, Inc. Consumer profiling system
US6324519B1 (en) * 1999-03-12 2001-11-27 Expanse Networks, Inc. Advertisement auction system
US6269361B1 (en) * 1999-05-28 2001-07-31 Goto.Com System and method for influencing a position on a search result list generated by a computer network search engine
US20010042064A1 (en) * 1999-05-28 2001-11-15 Goto.Com. System and method for influencing a position on a search result list generated by a computer network search engine
US20010047297A1 (en) * 2000-02-16 2001-11-29 Albert Wen Advertisement brokering with remote ad generation system and method in a distributed computer network
US20010051911A1 (en) * 2000-05-09 2001-12-13 Marks Michael B. Bidding method for internet/wireless advertising and priority ranking in search results
US20020046104A1 (en) * 2000-05-09 2002-04-18 Geomicro, Inc. Method and apparatus for generating targeted impressions to internet clients
US20020002525A1 (en) * 2000-06-30 2002-01-03 Masatoshi Arai Digital contents advertisement display system using auction
US20020035536A1 (en) * 2000-09-18 2002-03-21 Peter Gellman Method and system for forming a list-based value discovery network
US20020038282A1 (en) * 2000-09-27 2002-03-28 Montgomery Rob R. Buyer-side auction dynamic pricing agent, system, method and computer program product
US20020099605A1 (en) * 2000-10-06 2002-07-25 Searchcactus, Llc Search engine with demographic-based advertising
US20020077891A1 (en) * 2000-12-15 2002-06-20 Castle Daniel C. Method and apparatus to maximize advertising revenue
US20020111898A1 (en) * 2001-01-22 2002-08-15 Chisato Numaoka Advertisement space auction method, apparatus and storage medium
US6526440B1 (en) * 2001-01-30 2003-02-25 Google, Inc. Ranking search results by reranking the results based on local inter-connectivity
US20020123988A1 (en) * 2001-03-02 2002-09-05 Google, Inc. Methods and apparatus for employing usage statistics in document retrieval
US20030149618A1 (en) * 2002-02-01 2003-08-07 Microsoft Corporation Flexible dynamic advertising
US6974398B2 (en) * 2002-06-06 2005-12-13 Steven Curtis Murphy Magnum bullet darts
US20040261096A1 (en) * 2002-06-20 2004-12-23 Bellsouth Intellectual Property Corporation System and method for monitoring blocked content
US20040015397A1 (en) * 2002-07-16 2004-01-22 Barry Christopher J. Method and system for providing advertising through content specific nodes over the internet
US20040019523A1 (en) * 2002-07-25 2004-01-29 Barry Christopher J. Method and system for providing filtered and/or masked advertisements over the internet
US20040044571A1 (en) * 2002-08-27 2004-03-04 Bronnimann Eric Robert Method and system for providing advertising listing variance in distribution feeds over the internet to maximize revenue to the advertising distributor
US20040059708A1 (en) * 2002-09-24 2004-03-25 Google, Inc. Methods and apparatus for serving relevant advertisements
US20040093327A1 (en) * 2002-09-24 2004-05-13 Darrell Anderson Serving advertisements based on content
US20040059712A1 (en) * 2002-09-24 2004-03-25 Dean Jeffrey A. Serving advertisements using information associated with e-mail
US20040167928A1 (en) * 2002-09-24 2004-08-26 Darrell Anderson Serving content-relevant advertisements with client-side device support
US20040249709A1 (en) * 2002-11-01 2004-12-09 Donovan Kevin Rjb Method and system for dynamic textual ad distribution via email
US7765206B2 (en) * 2002-12-13 2010-07-27 Metaweb Technologies, Inc. Meta-Web
US20040119740A1 (en) * 2002-12-24 2004-06-24 Google, Inc., A Corporation Of The State Of California Methods and apparatus for displaying and replying to electronic messages
US20050065806A1 (en) * 2003-06-30 2005-03-24 Harik Georges R. Generating information for online advertisements from Internet data and traditional media data
US20040107363A1 (en) * 2003-08-22 2004-06-03 Emergency 24, Inc. System and method for anticipating the trustworthiness of an internet site
US20050071224A1 (en) * 2003-09-30 2005-03-31 Andrew Fikes System and method for automatically targeting web-based advertisements
US20050222989A1 (en) * 2003-09-30 2005-10-06 Taher Haveliwala Results based personalization of advertisements in a search engine
US7240039B2 (en) * 2003-10-29 2007-07-03 Hewlett-Packard Development Company, L.P. System and method for combining valuations of multiple evaluators
US20050096979A1 (en) * 2003-11-03 2005-05-05 Ross Koningstein System and method for enabling an advertisement to follow the user to additional web pages
US20050131758A1 (en) * 2003-12-11 2005-06-16 Desikan Pavan K. Systems and methods detecting for providing advertisements in a communications network
US20050131918A1 (en) * 2003-12-12 2005-06-16 W. Daniel Hillis Personalized profile for evaluating content
US20050144069A1 (en) * 2003-12-23 2005-06-30 Wiseman Leora R. Method and system for providing targeted graphical advertisements
US20050131762A1 (en) * 2003-12-31 2005-06-16 Krishna Bharat Generating user information for use in targeted advertising
US20050216335A1 (en) * 2004-03-24 2005-09-29 Andrew Fikes System and method for providing on-line user-assisted Web-based advertising
US20050222900A1 (en) * 2004-03-30 2005-10-06 Prashant Fuloria Selectively delivering advertisements based at least in part on trademark issues
US20050223002A1 (en) * 2004-03-30 2005-10-06 Sumit Agarwal System and method for rating electronic documents
US20050222903A1 (en) * 2004-03-31 2005-10-06 Paul Buchheit Rendering content-targeted ads with e-mail

Cited By (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10991009B2 (en) 2005-08-04 2021-04-27 Time Warner Cable Enterprises Llc Methods and apparatus for context-specific content delivery
US9286388B2 (en) * 2005-08-04 2016-03-15 Time Warner Cable Enterprises Llc Method and apparatus for context-specific content delivery
US20070033531A1 (en) * 2005-08-04 2007-02-08 Christopher Marsh Method and apparatus for context-specific content delivery
US10032190B2 (en) 2005-08-04 2018-07-24 Time Warner Cable Enterprises Llc Method and apparatus for context-specific content delivery
US10445784B2 (en) 2005-08-04 2019-10-15 Time Warner Cable Enterprises Llc Methods and apparatus for context-specific content delivery
US8296293B2 (en) * 2005-08-08 2012-10-23 Google Inc. Agent rank
US8224826B2 (en) 2005-08-08 2012-07-17 Google Inc. Agent rank
US9002856B2 (en) 2005-08-08 2015-04-07 Google Inc. Agent rank
US20110213770A1 (en) * 2005-08-08 2011-09-01 Google Inc. Agent rank
US20090287697A1 (en) * 2005-08-08 2009-11-19 Google Inc. Agent rank
US8171009B2 (en) * 2005-11-01 2012-05-01 Lycos, Inc. Method and system for performing a search on a network
US20090327287A1 (en) * 2005-11-01 2009-12-31 Lycos, Inc. Method and system for performing a search on a network
US20110219300A1 (en) * 2005-12-14 2011-09-08 Google Inc. Detecting and rejecting annoying documents
US7971137B2 (en) 2005-12-14 2011-06-28 Google Inc. Detecting and rejecting annoying documents
US9442989B1 (en) 2010-02-08 2016-09-13 Google Inc. Scoring authors of posts
US8983974B1 (en) 2010-02-08 2015-03-17 Google Inc. Scoring authors of posts
US8606792B1 (en) 2010-02-08 2013-12-10 Google Inc. Scoring authors of posts
US10949429B1 (en) 2010-02-08 2021-03-16 Google Llc Scoring authors of posts
US9846728B1 (en) 2010-02-08 2017-12-19 Google Inc. Scoring authors of posts
US11616992B2 (en) 2010-04-23 2023-03-28 Time Warner Cable Enterprises Llc Apparatus and methods for dynamic secondary content and data insertion and delivery
US20110307408A1 (en) * 2010-06-14 2011-12-15 Computer Associates Think, Inc. System and Method for Assigning a Business Value Rating to Documents in an Enterprise
US9330376B2 (en) * 2010-06-14 2016-05-03 Ca, Inc. System and method for assigning a business value rating to documents in an enterprise
US8565585B2 (en) * 2011-06-24 2013-10-22 Thomson Licensing Reproduction device and method for operating the same
US20120328262A1 (en) * 2011-06-24 2012-12-27 Franck Thudor Reproduction device and method for operating the same
US10231019B2 (en) 2012-03-15 2019-03-12 Black Wave Adventures, Llc Digital parental controls interface
US11750887B2 (en) 2012-03-15 2023-09-05 Black Wave Adventures, Llc Digital content controller
WO2013138743A1 (en) * 2012-03-15 2013-09-19 Cobb Daniel J Digital parental controls interface
US9066122B1 (en) * 2013-03-08 2015-06-23 Google Inc. Serving video content segments
US10516691B2 (en) 2013-03-12 2019-12-24 Pearson Education, Inc. Network based intervention
US9483954B2 (en) 2013-03-12 2016-11-01 Pearson Education, Inc. Educational network based intervention
US10977257B2 (en) 2013-04-12 2021-04-13 Pearson Education, Inc. Systems and methods for automated aggregated content comment generation
US10417241B2 (en) 2013-04-12 2019-09-17 Pearson Education, Inc. System and method for automated aggregated content comment provisioning
US10019527B2 (en) 2013-04-12 2018-07-10 Pearson Education, Inc. Systems and methods for automated aggregated content comment generation
US11003674B2 (en) 2013-04-12 2021-05-11 Pearson Education, Inc. Systems and methods for automated aggregated content comment generation
US20140308650A1 (en) * 2013-04-12 2014-10-16 Pearson Education, Inc. Evaluation control
US9928383B2 (en) 2014-10-30 2018-03-27 Pearson Education, Inc. Methods and systems for network-based analysis, intervention, and anonymization
US10366251B2 (en) 2014-10-30 2019-07-30 Pearson Education, Inc. Methods and systems for network-based analysis, intervention, and anonymization
US10083321B2 (en) 2014-10-30 2018-09-25 Pearson Education, Inc. Methods and systems for network-based analysis, intervention, and anonymization
US10699296B2 (en) * 2015-12-30 2020-06-30 Verizon Patent And Licensing, Inc. Native video advertising with voice-based ad management and machine-to-machine ad bidding
US11403849B2 (en) 2019-09-25 2022-08-02 Charter Communications Operating, Llc Methods and apparatus for characterization of digital content

Also Published As

Publication number Publication date
US20050223002A1 (en) 2005-10-06
US7533090B2 (en) 2009-05-12

Similar Documents

Publication Publication Date Title
US7533090B2 (en) System and method for rating electronic documents
US7801738B2 (en) System and method for rating documents comprising an image
US10146776B1 (en) Method and system for mining image searches to associate images with concepts
US8014634B1 (en) Method and system for approving documents based on image similarity
US8849070B2 (en) Method and system for providing targeted documents based on concepts automatically identified therein
US7991772B2 (en) Providing history and transaction volume information of a content source to users
CA2603042C (en) Methods and systems for member-created advertisement in a member network
US9141964B1 (en) Method and system for automatically creating an image advertisement
US20080109445A1 (en) Systems and methods of enhancing leads
US20080109294A1 (en) Systems and methods of enhancing leads
US8060405B1 (en) Methods and systems for correlating connections between users and links between articles
AU2004279071A1 (en) Determining and/or using end user local time information in an ad system
US11681761B1 (en) Method and system for mining image searches to associate images with concepts
US20170228765A1 (en) Method and system for adjusting the display of advertisements
KR20040040405A (en) Methods, systems, and software for automated growth of intelligent on-line communities

Legal Events

Date Code Title Description
AS Assignment

Owner name: GOOGLE INC.,CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:AGARWAL, SUMIT;RAJARAM, GOKUL;WISEMAN, LEORA RUTH;SIGNING DATES FROM 20040712 TO 20040713;REEL/FRAME:023962/0355

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION

AS Assignment

Owner name: GOOGLE LLC, CALIFORNIA

Free format text: CHANGE OF NAME;ASSIGNOR:GOOGLE INC.;REEL/FRAME:044142/0357

Effective date: 20170929