DETAILED ACTION
Status of Claims
This Action is in response to App. 19/101,520 filed 02/05/2025. Claims 1-20 are currently pending and have been examined.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites the steps of determining recommendation objects, generating features representing the objects or users to receive the objects, and determining a diversity metric.
The limitation of determining objects, generating features, and determining diversity metric, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “processor,” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “processor” language, “determining” in the context of this claim encompasses a person identifying content objects which are published on a platform (such as looking at a database of videos). Similarly, the generating state features, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the “processor” language, “generating” in the context of this claim encompasses the person reviewing the content to identify characteristics of the content (such recognizing a dog video is recommended to a pet owner). Furthermore, but for the “processor” language, “determining a diversity metric” in the context of the claim encompasses the person performing calculations to assign a number to represent the diversity of the content objects (such as assigning a higher number to the content objects which includes both exotic animal content and dog content for a dog owner). If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recite the additional elements of using a processor to perform the steps. The processor is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of identifying information and features/characteristics of the information, and assigning a number based on calculations) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
The dependent claims are further directed towards the judicial exception without significantly more. The dependent claims provide limitations on further defining additional abstract steps and information including additional determinations, calculations, and manipulation of information (such as claims 2-10). These are still directed towards the judicial exception as these further define the abstract elements such as further defining the information, relationship between the information, and the manipulation of information. They are not significantly more as they do not further integrate the judicial exception into a practical application and the additional element amounts to no more than mere instructions to apply the exception using a generic computer component. The dependent claims is not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-4, 9-14, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Nickerson et al. (US 20170124593 A1) (hereafter Nickerson), in view of Quercia et al. (US 20160092576 A1) (hereafter Quercia).
As per claim 1:
A method of recommendation diversity evaluation, comprising:
determining a plurality of objects to be recommended in a recommendation system at a first time and a plurality of users to which one or more objects of the plurality of objects is to be recommended at the first time, an object comprising a content item or a content creator; (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining recommendation objects, wherein the objects include content and creator.)
generating state features of the recommendation system at the first time, the state features comprising at least one of respective content features of the plurality of objects or respective user features of the plurality of users; and (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining features of the content and users matched for recommendation.)
determining a diversity metric of the recommendation system at the first time based on the state features, the diversity metric indicating a diversity of the recommendation system in user preferences and content creation. (See Nickerson ¶0116, “FIG. 6 depicts a screen providing content analysis results for a library of content items. As shown, the content analysis may provide metrics based on assessment of each content item according various criteria including, length/quality of the item's title, length, grammar, emotional content, paragraph density (e.g., number of sentences per paragraph), number/quality of links. The metrics may be presented as a percentage of content items in the library that satisfy a pre-defined threshold for each of the noted criteria.” Nickerson discloses the concept of determining metrics for the content based on features of the objects.)
Although Nickerson discloses the above-enclosed invention, Nickerson fails to explicitly disclose determining diversity metric representing the diversity of content and user preference.
However Quercia as shown, which talks about association and perspective based content recommendation, teaches the concept of utilizing a metric to represent diversity of content and preference.
(See Quercia ¶0067, “As a fourth variation of this second aspect, the user 112 may be evaluated to determine the openness and/or interest of the user 112 in receiving recommendations of content items 422 exhibiting individual perspective 506 that present varying degrees of difference from the user perspective 510 of the user 112. For example, some users 112 may be receptive to highly differing individual perspectives 506, while others may be only interested in modest differences. Conversely, some users 112 may be interested in content items 422 that are modestly different from the user perspective 510 of the user 112 (e.g., those that add subtlety, nuance, or qualifications to the user perspective 510 of the user 112), while other users 112 may not be interested in content items 422 that exhibit individual perspectives 506 that are too similar to the user perspective 510 of the user 112 (e.g., users 112 who are eager to avoid the “echo chamber” effect). Accordingly, in one such variation, the user 112 is associated with a diversity score, and the perspective difference score between the individual perspective 506 of the respective content items 422 and the user perspective 510 of the user 112 about the topic 504 may be calculated, and compared with the diversity score in order to select content items 422 for recommendation to the user 112.” Quercia teaches the concept of determining diversity value representing user preference and content source.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia with the invention of Nickerson. As shown, Nickerson discloses the concept of optimizing the recommendation of content to users to distribute relevant content to the appropriate audiences through the analysis and quantizing of recommendations. Quercia further teaches the concept of quantizing a diversity metric. Quercia teaches this concept to provide diversified content while still accounting for user interest to avoid echo chambers (See Quercia ¶0001-¶0003). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia to provide diverse yet relevant content to the end-user.
As per claim 2:
The method of claim 1, wherein determining a diversity metric of the recommendation system at the first time based on at least one of the respective content features or the respective user features comprises:
determining a polarization metric based on a similarity between each pair of content features of the respective content features, the polarization metric indicating a degree of the recommendation system approaching a polarized recommendation state.
(See Quercia ¶0066, “As a third variation of this second aspect, the individual perspectives 506 associated with various content items 422 of a selected individual 502 may be determined in various ways in the context of determining a degree of perspective difference between the user perspective 510 of the user 112 and the individual perspective 506 of the individuals 502 in order to select a content item 422 presenting a perspective difference. In a first such variation, a perspective score may be generated that quantifies the individual perspective 506 of the individual 502 and/or the content item 422. For example, an evaluation of various sources of discussion of a topic 504, such as a political issue, may enable the identification of keywords that are correlated with various individual perspectives 506 (e.g., individuals 502 discussing the topic 504 from a first individual perspective 506 may commonly use a first set of terms, while individuals 502 discussing the topic 504 from a second individual perspective 506 may commonly use a second set of terms). The frequencies of the terms used in a content item 422 may therefore enable a calculation of a perspective score indicating the strength and/or confidence of the correlation of the content item 422 and/or the individual 502 with a particular individual perspective 506. As a further such variation, a perspective difference score may be calculated between the individual perspective 506 of the individual 502 and/or the content item 42, and the user perspective 510 of the user 112; and among a set of content items 422, a particular content item 422 may be selected that has a perspective difference score within a perspective difference score range (e.g., at least 50% different from the user perspective 510 of the user 112, but less than 80% different from the user perspective 510 of the user 112, as presenting a content item 422 from a strongly conflicting individual perspective 506 on a highly polarized topic 504 may alienate the user 112).” Quercia teaches the concept of determining metric representing opposing views on the same topic/subject matter.)
As per claim 3:
The method of claim 2, wherein the polarized recommendation state comprises at least one of:
a consensus state in which objects in the recommendation system are preferred by all users of the recommendation system, or
a bi-polarization state in which objects and users in the recommendation system are divided into two opposite groups with objects in a first group being preferred by users in the first group and objects in a second group being preferred by users in the second group. (See Quercia ¶0066, “As a third variation of this second aspect, the individual perspectives 506 associated with various content items 422 of a selected individual 502 may be determined in various ways in the context of determining a degree of perspective difference between the user perspective 510 of the user 112 and the individual perspective 506 of the individuals 502 in order to select a content item 422 presenting a perspective difference. In a first such variation, a perspective score may be generated that quantifies the individual perspective 506 of the individual 502 and/or the content item 422. For example, an evaluation of various sources of discussion of a topic 504, such as a political issue, may enable the identification of keywords that are correlated with various individual perspectives 506 (e.g., individuals 502 discussing the topic 504 from a first individual perspective 506 may commonly use a first set of terms, while individuals 502 discussing the topic 504 from a second individual perspective 506 may commonly use a second set of terms). The frequencies of the terms used in a content item 422 may therefore enable a calculation of a perspective score indicating the strength and/or confidence of the correlation of the content item 422 and/or the individual 502 with a particular individual perspective 506. As a further such variation, a perspective difference score may be calculated between the individual perspective 506 of the individual 502 and/or the content item 42, and the user perspective 510 of the user 112; and among a set of content items 422, a particular content item 422 may be selected that has a perspective difference score within a perspective difference score range (e.g., at least 50% different from the user perspective 510 of the user 112, but less than 80% different from the user perspective 510 of the user 112, as presenting a content item 422 from a strongly conflicting individual perspective 506 on a highly polarized topic 504 may alienate the user 112).” Quercia teaches the concept of determining metric representing opposing views on the same topic/subject matter.)
As per claim 4:
The method of claim 2, wherein determining a diversity metric of the recommendation system at the first time based on at least one of the respective content features or the respective user features further comprises at least one of:
determining a creation diversity metric based on a difference between each pair of content features of the respective content features, the creation diversity metric indicating a degree of diversity in content creation,
determining a recommendation diversity metric based on a difference between each pair of content features recommended to a user of the plurality of users, the recommendation diversity metric indicating a degree of diversity of contents recommended to a same user, or
determining a recommendation relevance metric based on a similarity between each content feature of the respective content features and each user feature of the respective user features.
(See Quercia ¶0067, “As a fourth variation of this second aspect, the user 112 may be evaluated to determine the openness and/or interest of the user 112 in receiving recommendations of content items 422 exhibiting individual perspective 506 that present varying degrees of difference from the user perspective 510 of the user 112. For example, some users 112 may be receptive to highly differing individual perspectives 506, while others may be only interested in modest differences. Conversely, some users 112 may be interested in content items 422 that are modestly different from the user perspective 510 of the user 112 (e.g., those that add subtlety, nuance, or qualifications to the user perspective 510 of the user 112), while other users 112 may not be interested in content items 422 that exhibit individual perspectives 506 that are too similar to the user perspective 510 of the user 112 (e.g., users 112 who are eager to avoid the “echo chamber” effect). Accordingly, in one such variation, the user 112 is associated with a diversity score, and the perspective difference score between the individual perspective 506 of the respective content items 422 and the user perspective 510 of the user 112 about the topic 504 may be calculated, and compared with the diversity score in order to select content items 422 for recommendation to the user 112.” Quercia teaches the concept of the diversity score to be based on differences/opposing perspectives.)
As per claim 9:
The method of claim 1, wherein generating state features of the recommendation system at the first time comprises:
generating, for a given user of the plurality of users, a user feature of the given user based on information about the given user, to obtain the respective user features of the plurality of users, or
generating, for a given object of the plurality of objects, a content feature of the given object based on information about the given object, to obtain the respective content features of the plurality of objects.
(See Quercia ¶0048, “As a first technical effect, the identification and presentation of such content items 422 to the user 112 as content item recommendations 512 may be interesting, and possibly persuasive, to the user 112 for a variety of reasons. As a first such example, the user 112 may find interest in the fact that individuals 502 having very similar individual backgrounds 602 to the user background 604 of the user 112 hold divergent individual perspectives 506 about the topic 504 than the user perspective 510 of the user 112, and may be persuaded to reconsider individual perspectives 506 that the user 112 might have otherwise disregarded as irrelevant to the user 112. As a second such example, the user 112 may be interested in understanding the individual perspectives 506 about various topics 504 that are held by individuals 602 who are very similar to the user 112. For instance, a member of a social group, such as a member of an organization such as a student body of a university, may feel compelled to understand the tastes and opinions of other individuals 502 within the social group, e.g., in order to fit in with and/or respect the opinions of the social group, and/or to identify conversation topics with other individuals 502 within the social group. Accordingly, such selectivity may improve the engagement of users 112 with the content provider 408, e.g., by increasing the predicted interest and appeal of content item recommendations 512 that are presented to the user 112.” Quercia teaches the concept of determining user features based on groups of users.)
As per claim 10:
The method of claim 1, wherein generating state features of the recommendation system at the first time comprises:
updating, for a given user of the plurality of users, a user feature of the given user at a second time based on objects recommended to the given user at the second time, so as to obtain the respective user features of the plurality of users, the second time is previous to the first time, or
updating, for a given object of the plurality of objects, a content feature of the given object at the second time based on users to which the given object is recommended, so as to obtain the respective content features of the plurality of objects.
(See Nickerson ¶0149, “The audience segmentation service may also analyze the historic content to determine a sophistication level of the audience. In an exemplary implementation, the level of sophistication of the audience may be determined to be one of “knowledgeable”, “academic”, and “general.” As will be appreciated, the level of sophistication may be impacted by the source of the content, e.g., the platform or feed from which the content originates. For example, the audience for content on the Facebook™ platform may be determined to be of “general” sophistication for one content feed or source, while the audience for content on the Twitter™ platform may be determined to be of “knowledgeable” sophistication. However, different sophistication levels, including the opposite sophistication levels, may be determined for a different content feed or source on those platforms.” Nickerson discloses the concept of tracking and updating user information over time.)
As per claim 11:
An electronic device, comprising a computer processor coupled to a computer-readable memory unit, the memory unit comprising instructions that when executed by the computer processor implements a method of recommendation diversity evaluation, the method comprising: (See Nickerson ¶0010, “According to a further aspect, there is provided a system for distributing digital content matched to web properties. The system includes at least one processor, a network interface, and a computer readable medium in communication with the at least one processor. The computer readable medium stores computer processing instructions executable by the at least one processor to provide: a content collection component for receiving a plurality of digital content items by way of the network interface; a content assessment component for determining content attributes of each of the plurality of digital content items; an audience assessment component for determining audience attributes of an audience of a web property; a matching component for matching the plurality of digital content items to the web property by assessing the content attributes and the audience attributes; and a distributing component for selectively distributing the plurality of digital content items to the web property by way of the network interface, in response to the matching.” Nickerson discloses a processor executing instructions stored on a memory.)
determining a plurality of objects to be recommended in a recommendation system at a first time and a plurality of users to which one or more objects of the plurality of objects is to be recommended at the first time, an object comprising a content item or a content creator; (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining recommendation objects, wherein the objects include content and creator.)
generating state features of the recommendation system at the first time, the state features comprising at least one of respective content features of the plurality of objects or respective user features of the plurality of users; and (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining features of the content and users matched for recommendation.)
determining a diversity metric of the recommendation system at the first time based on the state features, the diversity metric indicating a diversity of the recommendation system in user preferences and content creation. (See Nickerson ¶0116, “FIG. 6 depicts a screen providing content analysis results for a library of content items. As shown, the content analysis may provide metrics based on assessment of each content item according various criteria including, length/quality of the item's title, length, grammar, emotional content, paragraph density (e.g., number of sentences per paragraph), number/quality of links. The metrics may be presented as a percentage of content items in the library that satisfy a pre-defined threshold for each of the noted criteria.” Nickerson discloses the concept of determining metrics for the content based on features of the objects.)
Although Nickerson discloses the above-enclosed invention, Nickerson fails to explicitly disclose determining diversity metric representing the diversity of content and user preference.
However Quercia as shown, which talks about association and perspective based content recommendation, teaches the concept of utilizing a metric to represent diversity of content and preference.
(See Quercia ¶0067, “As a fourth variation of this second aspect, the user 112 may be evaluated to determine the openness and/or interest of the user 112 in receiving recommendations of content items 422 exhibiting individual perspective 506 that present varying degrees of difference from the user perspective 510 of the user 112. For example, some users 112 may be receptive to highly differing individual perspectives 506, while others may be only interested in modest differences. Conversely, some users 112 may be interested in content items 422 that are modestly different from the user perspective 510 of the user 112 (e.g., those that add subtlety, nuance, or qualifications to the user perspective 510 of the user 112), while other users 112 may not be interested in content items 422 that exhibit individual perspectives 506 that are too similar to the user perspective 510 of the user 112 (e.g., users 112 who are eager to avoid the “echo chamber” effect). Accordingly, in one such variation, the user 112 is associated with a diversity score, and the perspective difference score between the individual perspective 506 of the respective content items 422 and the user perspective 510 of the user 112 about the topic 504 may be calculated, and compared with the diversity score in order to select content items 422 for recommendation to the user 112.” Quercia teaches the concept of determining diversity value representing user preference and content source.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia with the invention of Nickerson. As shown, Nickerson discloses the concept of optimizing the recommendation of content to users to distribute relevant content to the appropriate audiences through the analysis and quantizing of recommendations. Quercia further teaches the concept of quantizing a diversity metric. Quercia teaches this concept to provide diversified content while still accounting for user interest to avoid echo chambers (See Quercia ¶0001-¶0003). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia to provide diverse yet relevant content to the end-user.
As per claim 12:
The device of claim 11, wherein determining a diversity metric of the recommendation system at the first time based on at least one of the respective content features or the respective user features comprises:
determining a polarization metric based on a similarity between each pair of content features of the respective content features, the polarization metric indicating a degree of the recommendation system approaching a polarized recommendation state.
(See Quercia ¶0066, “As a third variation of this second aspect, the individual perspectives 506 associated with various content items 422 of a selected individual 502 may be determined in various ways in the context of determining a degree of perspective difference between the user perspective 510 of the user 112 and the individual perspective 506 of the individuals 502 in order to select a content item 422 presenting a perspective difference. In a first such variation, a perspective score may be generated that quantifies the individual perspective 506 of the individual 502 and/or the content item 422. For example, an evaluation of various sources of discussion of a topic 504, such as a political issue, may enable the identification of keywords that are correlated with various individual perspectives 506 (e.g., individuals 502 discussing the topic 504 from a first individual perspective 506 may commonly use a first set of terms, while individuals 502 discussing the topic 504 from a second individual perspective 506 may commonly use a second set of terms). The frequencies of the terms used in a content item 422 may therefore enable a calculation of a perspective score indicating the strength and/or confidence of the correlation of the content item 422 and/or the individual 502 with a particular individual perspective 506. As a further such variation, a perspective difference score may be calculated between the individual perspective 506 of the individual 502 and/or the content item 42, and the user perspective 510 of the user 112; and among a set of content items 422, a particular content item 422 may be selected that has a perspective difference score within a perspective difference score range (e.g., at least 50% different from the user perspective 510 of the user 112, but less than 80% different from the user perspective 510 of the user 112, as presenting a content item 422 from a strongly conflicting individual perspective 506 on a highly polarized topic 504 may alienate the user 112).” Quercia teaches the concept of determining metric representing opposing views on the same topic/subject matter.)
As per claim 13:
The device of claim 12, wherein the polarized recommendation state comprises at least one of:
a consensus state in which objects in the recommendation system are preferred by all users of the recommendation system, or
a bi-polarization state in which objects and users in the recommendation system are divided into two opposite groups with objects in a first group being preferred by users in the first group and objects in a second group being preferred by users in the second group.
(See Quercia ¶0066, “As a third variation of this second aspect, the individual perspectives 506 associated with various content items 422 of a selected individual 502 may be determined in various ways in the context of determining a degree of perspective difference between the user perspective 510 of the user 112 and the individual perspective 506 of the individuals 502 in order to select a content item 422 presenting a perspective difference. In a first such variation, a perspective score may be generated that quantifies the individual perspective 506 of the individual 502 and/or the content item 422. For example, an evaluation of various sources of discussion of a topic 504, such as a political issue, may enable the identification of keywords that are correlated with various individual perspectives 506 (e.g., individuals 502 discussing the topic 504 from a first individual perspective 506 may commonly use a first set of terms, while individuals 502 discussing the topic 504 from a second individual perspective 506 may commonly use a second set of terms). The frequencies of the terms used in a content item 422 may therefore enable a calculation of a perspective score indicating the strength and/or confidence of the correlation of the content item 422 and/or the individual 502 with a particular individual perspective 506. As a further such variation, a perspective difference score may be calculated between the individual perspective 506 of the individual 502 and/or the content item 42, and the user perspective 510 of the user 112; and among a set of content items 422, a particular content item 422 may be selected that has a perspective difference score within a perspective difference score range (e.g., at least 50% different from the user perspective 510 of the user 112, but less than 80% different from the user perspective 510 of the user 112, as presenting a content item 422 from a strongly conflicting individual perspective 506 on a highly polarized topic 504 may alienate the user 112).” Quercia teaches the concept of determining metric representing opposing views on the same topic/subject matter.)
As per claim 14:
The device of claim 12, wherein determining a diversity metric of the recommendation system at the first time based on at least one of the respective content features or the respective user features further comprises at least one of:
determining a creation diversity metric based on a difference between each pair of content features of the respective content features, the creation diversity metric indicating a degree of diversity in content creation,
determining a recommendation diversity metric based on a difference between each pair of content features recommended to a user of the plurality of users, the recommendation diversity metric indicating a degree of diversity of contents recommended to a same user, or
determining a recommendation relevance metric based on a similarity between each content feature of the respective content features and each user feature of the respective user features.
(See Quercia ¶0067, “As a fourth variation of this second aspect, the user 112 may be evaluated to determine the openness and/or interest of the user 112 in receiving recommendations of content items 422 exhibiting individual perspective 506 that present varying degrees of difference from the user perspective 510 of the user 112. For example, some users 112 may be receptive to highly differing individual perspectives 506, while others may be only interested in modest differences. Conversely, some users 112 may be interested in content items 422 that are modestly different from the user perspective 510 of the user 112 (e.g., those that add subtlety, nuance, or qualifications to the user perspective 510 of the user 112), while other users 112 may not be interested in content items 422 that exhibit individual perspectives 506 that are too similar to the user perspective 510 of the user 112 (e.g., users 112 who are eager to avoid the “echo chamber” effect). Accordingly, in one such variation, the user 112 is associated with a diversity score, and the perspective difference score between the individual perspective 506 of the respective content items 422 and the user perspective 510 of the user 112 about the topic 504 may be calculated, and compared with the diversity score in order to select content items 422 for recommendation to the user 112.” Quercia teaches the concept of the diversity score to be based on differences/opposing perspectives.)
As per claim 19:
The device of claim 11, wherein generating state features of the recommendation system at the first time comprises:
generating, for a given user of the plurality of users, a user feature of the given user based on information about the given user, to obtain the respective user features of the plurality of users, or
generating, for a given object of the plurality of objects, a content feature of the given object based on information about the given object, to obtain the respective content features of the plurality of objects.
(See Quercia ¶0048, “As a first technical effect, the identification and presentation of such content items 422 to the user 112 as content item recommendations 512 may be interesting, and possibly persuasive, to the user 112 for a variety of reasons. As a first such example, the user 112 may find interest in the fact that individuals 502 having very similar individual backgrounds 602 to the user background 604 of the user 112 hold divergent individual perspectives 506 about the topic 504 than the user perspective 510 of the user 112, and may be persuaded to reconsider individual perspectives 506 that the user 112 might have otherwise disregarded as irrelevant to the user 112. As a second such example, the user 112 may be interested in understanding the individual perspectives 506 about various topics 504 that are held by individuals 602 who are very similar to the user 112. For instance, a member of a social group, such as a member of an organization such as a student body of a university, may feel compelled to understand the tastes and opinions of other individuals 502 within the social group, e.g., in order to fit in with and/or respect the opinions of the social group, and/or to identify conversation topics with other individuals 502 within the social group. Accordingly, such selectivity may improve the engagement of users 112 with the content provider 408, e.g., by increasing the predicted interest and appeal of content item recommendations 512 that are presented to the user 112.” Quercia teaches the concept of determining user features based on groups of users.)
As per claim 20:
A computer program product, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by an electronic device to cause the electronic device to perform a method of recommendation diversity evaluation, the method comprising: (See Nickerson ¶0010, “According to a further aspect, there is provided a system for distributing digital content matched to web properties. The system includes at least one processor, a network interface, and a computer readable medium in communication with the at least one processor. The computer readable medium stores computer processing instructions executable by the at least one processor to provide: a content collection component for receiving a plurality of digital content items by way of the network interface; a content assessment component for determining content attributes of each of the plurality of digital content items; an audience assessment component for determining audience attributes of an audience of a web property; a matching component for matching the plurality of digital content items to the web property by assessing the content attributes and the audience attributes; and a distributing component for selectively distributing the plurality of digital content items to the web property by way of the network interface, in response to the matching.” Nickerson discloses a processor executing instructions stored on a memory.)
determining a plurality of objects to be recommended in a recommendation system at a first time and a plurality of users to which one or more objects of the plurality of objects is to be recommended at the first time, an object comprising a content item or a content creator; (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining recommendation objects, wherein the objects include content and creator.)
generating state features of the recommendation system at the first time, the state features comprising at least one of respective content features of the plurality of objects or respective user features of the plurality of users; and (See Nickerson ¶0044, “In one implementation, the content distribution service (22) includes a recommendation engine (50) that automatically analyzes content requirements, across multiple web properties or networks of web properties that are associated with the platform, and analyzes content available through the content hub (20), and in real time or near real time, recommends specific content for distribution to specific web properties or networks of web properties. Such analysis may be based, for example, on the aforementioned audience parameters. The recommendation engine (50) may automatically determine the quality of match between content and pre-defined audience segments.” Nickerson discloses the concept of determining features of the content and users matched for recommendation.)
determining a diversity metric of the recommendation system at the first time based on the state features, the diversity metric indicating a diversity of the recommendation system in user preferences and content creation. (See Nickerson ¶0116, “FIG. 6 depicts a screen providing content analysis results for a library of content items. As shown, the content analysis may provide metrics based on assessment of each content item according various criteria including, length/quality of the item's title, length, grammar, emotional content, paragraph density (e.g., number of sentences per paragraph), number/quality of links. The metrics may be presented as a percentage of content items in the library that satisfy a pre-defined threshold for each of the noted criteria.” Nickerson discloses the concept of determining metrics for the content based on features of the objects.)
Although Nickerson discloses the above-enclosed invention, Nickerson fails to explicitly disclose determining diversity metric representing the diversity of content and user preference.
However Quercia as shown, which talks about association and perspective based content recommendation, teaches the concept of utilizing a metric to represent diversity of content and preference.
(See Quercia ¶0067, “As a fourth variation of this second aspect, the user 112 may be evaluated to determine the openness and/or interest of the user 112 in receiving recommendations of content items 422 exhibiting individual perspective 506 that present varying degrees of difference from the user perspective 510 of the user 112. For example, some users 112 may be receptive to highly differing individual perspectives 506, while others may be only interested in modest differences. Conversely, some users 112 may be interested in content items 422 that are modestly different from the user perspective 510 of the user 112 (e.g., those that add subtlety, nuance, or qualifications to the user perspective 510 of the user 112), while other users 112 may not be interested in content items 422 that exhibit individual perspectives 506 that are too similar to the user perspective 510 of the user 112 (e.g., users 112 who are eager to avoid the “echo chamber” effect). Accordingly, in one such variation, the user 112 is associated with a diversity score, and the perspective difference score between the individual perspective 506 of the respective content items 422 and the user perspective 510 of the user 112 about the topic 504 may be calculated, and compared with the diversity score in order to select content items 422 for recommendation to the user 112.” Quercia teaches the concept of determining diversity value representing user preference and content source.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia with the invention of Nickerson. As shown, Nickerson discloses the concept of optimizing the recommendation of content to users to distribute relevant content to the appropriate audiences through the analysis and quantizing of recommendations. Quercia further teaches the concept of quantizing a diversity metric. Quercia teaches this concept to provide diversified content while still accounting for user interest to avoid echo chambers (See Quercia ¶0001-¶0003). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Quercia to provide diverse yet relevant content to the end-user.
Claim(s) 5, 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Nickerson et al. (US 20170124593 A1) (hereafter Nickerson), in view of Quercia et al. (US 20160092576 A1) (hereafter Quercia), in view of Manavoglu et al. (US 20080154858 A1) (hereafter Manavoglu).
As per claim 5:
Although the combination of Nickerson and Quercia discloses the above-enclosed invention, the combination fails to explicitly disclose the concept of decreasing a number of outputs based on the outputs falling below a threshold.
However Manavoglu as shown, which talks about providing targeted content, teaches the concept of decreasing a number of outputs based on threshold.
The method of claim 1, wherein the recommendation system is configured to recommend top k objects from the plurality of objects to a user, and the method further comprises:
in accordance with a determination that the diversity metric is below a diversity threshold, decreasing a value of k or presenting an indication to decrease the value of k.
(See Manavoglu ¶0062, “After ranking the advertisements the system 100 may move to block 365. At block 365 the service provider server 240 may add the advertisements from the ranked list of available advertisements to allotted space on the search results page. The service provider server 240 may add the advertisements to the page in the order the advertisements appear in the ranked list. There may not be enough space on the search results page for all of the available advertisements. Therefore, some of the advertisements in the ranked list may not be included on the search results page. Alternatively or in addition, there may not be enough advertisements in the ranked list to fill the space allotted for advertisements on the search results page. In this case, the service provider server 240 may leave the allotted space empty or may add other advertisements to the allotted space. Once the service provider server 240 has filled the allotted advertisement space on the search results page, or the once all the advertisers on the ranked list have been added to the page, the system 100 may move to block 370. Alternatively or in addition, the service provider server 240 may not display an advertisement if the value used in ranking the advertisement is below a certain threshold.” Manavoglu teaches the concept of decreasing a number of top objects based on not meeting a threshold.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Manavoglu with the combination of Nickerson and Quercia. As shown, the combination discloses the concept of utilizing metrics associated with objects to rank objects for optimal recommendation of content. Manavoglu further teaches the concept of reducing the number of ranked content presented in response to threshold conditions not being met. Manavoglu teaches this concept to prevent content objects which do not meet content standards to be presented (See Manavoglu ¶0062). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Manavoglu to further ensure content recommendations meet a minimum standard.
As per claim 15:
Although the combination of Nickerson and Quercia discloses the above-enclosed invention, the combination fails to explicitly disclose the concept of decreasing a number of outputs based on the outputs falling below a threshold.
However Manavoglu as shown, which talks about providing targeted content, teaches the concept of decreasing a number of outputs based on threshold.
The device of claim 11, wherein the recommendation system is configured to recommend top k objects from the plurality of objects to a user, and the method further comprises:
in accordance with a determination that the diversity metric is below a diversity threshold, decreasing a value of k or presenting an indication to decrease the value of k. (See Manavoglu ¶0062, “After ranking the advertisements the system 100 may move to block 365. At block 365 the service provider server 240 may add the advertisements from the ranked list of available advertisements to allotted space on the search results page. The service provider server 240 may add the advertisements to the page in the order the advertisements appear in the ranked list. There may not be enough space on the search results page for all of the available advertisements. Therefore, some of the advertisements in the ranked list may not be included on the search results page. Alternatively or in addition, there may not be enough advertisements in the ranked list to fill the space allotted for advertisements on the search results page. In this case, the service provider server 240 may leave the allotted space empty or may add other advertisements to the allotted space. Once the service provider server 240 has filled the allotted advertisement space on the search results page, or the once all the advertisers on the ranked list have been added to the page, the system 100 may move to block 370. Alternatively or in addition, the service provider server 240 may not display an advertisement if the value used in ranking the advertisement is below a certain threshold.” Manavoglu teaches the concept of decreasing a number of top objects based on not meeting a threshold.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Manavoglu with the combination of Nickerson and Quercia. As shown, the combination discloses the concept of utilizing metrics associated with objects to rank objects for optimal recommendation of content. Manavoglu further teaches the concept of reducing the number of ranked content presented in response to threshold conditions not being met. Manavoglu teaches this concept to prevent content objects which do not meet content standards to be presented (See Manavoglu ¶0062). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Manavoglu to further ensure content recommendations meet a minimum standard.
Non-Obvious Subject Matter
Claims 6-8 and 16-18 are determined to be non-obvious. As currently claimed, claims 6-8, 16-18 are directed towards adjustments based on a diversity threshold not being met including increasing a similarity threshold, decreasing a diversity boosting factor, or adjusting dimensions of features. The Examiner further notes the following reference(s):
Trabelsi et al. (US 20170243244 A1), which teaches the concept of utilizing multiple different thresholds for content targeting.
Mani (US 20150279390 A1), which discusses the concept of summarizing media content including adjusting and normalizing weights representing content.
The Examiner notes that although the concept of utilizing multiple thresholds, adjusting thresholds, weights/factors, and normalizing information are known in the art, these references alone or in combination fail to teach/suggest the concept of responding to a first diversity threshold not being met to trigger the adjustment of other features or metrics. As such, the Examiner has determined the limitations of claims 6-8,16-18 to be non-obvious over the prior art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chakrabarti et al. (US 7542951 B1), which talks about providing recommendations from diverse sources including diversity analysis.
Ruiz et al. (US 20150006280 A1), which talks about ranking search results including utilizing a diversity score in the ranking.
Saad (US 20210304280 A1), which talks about determining diverse recommendations including calculating diversity score.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VINCENT M CAO whose telephone number is (571)270-5598. The examiner can normally be reached Monday - Friday 11-7.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, ILANA SPAR can be reached at (571) 270-7537. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/VINCENT M CAO/Primary Examiner, Art Unit 3622
Prosecution Insights