# US 10,871,879 B2 · Systems and methods for providing feed page updates in a social networking system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,871,879 B2 - Document ID: US10871879B2 - Status: Granted - Kind: B2 - Application number: 15/283,025 - Filed: 2016-09-30 - Published: 2018-04-05 - Granted: 2020-12-22 - Earliest claimed: 2016-09-30 - Assignees: Facebook, Inc. - Applicants: Facebook, Inc. - Inventors: Daniel Dinu; Lingjuan Peng; Niting Qi; Ashish Kumar Yadav; Neal Suresh Vora; Andre Nader - Web page: https://patentgrep.com/patent/US10871879B2 ## CPC - G06N 20/00: Machine learning - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06Q 10/40: Business processes related to social networking or social networking services - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION 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 ## Abstract Systems, methods, and non-transitory computer readable media can determine one or more user-related metrics relating to each page of a plurality of pages associated with an administrator based on a first machine learning model. One or more recommendations relating to each page of the plurality of pages can be determined based on a second machine learning model. One or more pages of the plurality of pages for which to display cards including page updates in a feed of the administrator can be determined, based on the determined user-related metrics and the determined recommendations. ## Claims ### Claim 1 A computer-implemented method comprising: determining, by a computing system, one or more user-related metrics related to a plurality of pages associated with an administrator based at least in part on a likelihood of the administrator selecting the one or more user-related metrics, wherein the likelihood of the administrator selecting the one or more user-related metrics is determined by a first machine learning model and the first machine learning model is trained based at least in part on tracked information about user-related metrics and pages with which page administrators have engaged; determining, by the computing system, one or more recommendations related to the plurality of pages based at least in part on a likelihood of the administrator selecting the one or more recommendations and a number of determined user-related metrics, wherein the likelihood of the administrator selecting the one or more recommendations is determined by a second machine learning model and the second machine learning model is trained based at least in part on the tracked information about user-related metrics and page recommendations selected by the page administrators; and determining, by the computing system, one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator, based at least in part on the determined user-related metrics and the determined recommendations; and providing, by the computing system, a content item that includes the one or more cards, wherein the one or more cards include the determined user-related metrics and the determined recommendations for the one or more pages corresponding to the one or more cards and wherein a selection of at least one of: the one or more cards, the determined user-related metrics, or the determined recommendations is included in new training data for further training at least one of: the first machine learning model or the second machine learning model. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising providing the content item in a feed associated with the administrator. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the one or more cards include page updates associated with the one or more pages corresponding to the one or more cards. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the one or more cards further include at least one of: page information relating to the one or more pages corresponding to the one or more cards, user-related metrics relating to the one or more pages corresponding to the one or more cards, or recommendations relating to the one or more pages corresponding to the one or more cards. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, further comprising obtaining feedback associated with at least one of: the one or more cards, the determined user-related metrics, or the determined recommendations. ### Claim 6 (depends on 3) The computer-implemented method of claim 3, wherein the content item includes an additional card that provides a list including at least one page not included in the one or more pages and a number of unread items associated with the at least one page. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the new training data further include slots within the one or more cards in which the determined user-related metrics are provided. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the new training data further include feedback obtained from the administrator regarding whether the administrator prefers to see more or less of certain types of information included in the content item. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the determining one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator is based on a third machine learning model. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein the determined user-related metrics satisfy eligibility criteria. ### Claim 11 A system comprising: at least one hardware processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to perform: determining one or more user-related metrics related to of a plurality of pages associated with an administrator based at least in part on a likelihood of the administrator selecting the one or more user-related metrics, wherein the likelihood of the administrator selecting the one or more user-related metrics is determined by a first machine learning model and the first machine learning model is trained based at least in part on tracked information about user-related metrics and pages with which page administrators have engaged; determining one or more recommendations related to the plurality of pages based at least in part on a likelihood of the administrator selecting the one or more recommendations and a number of determined user-related metrics, wherein the likelihood of the administrator selecting the one or more recommendations is determined by a second machine learning model and the second machine learning model is trained based at least in part on the tracked information about user-related metrics and page recommendations selected by the page administrators; and determining one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator, based at least in part on the determined user-related metrics and the determined recommendations; and providing a content item that includes the one or more cards, wherein the one or more cards include the determined user-related metrics and the determined recommendations for the one or more pages corresponding to the one or more cards and wherein a selection of at least one of: the one or more cards, the determined user-related metrics, or the determined recommendations is included in new training data for further training at least one of: the first machine learning model or the second machine learning model. ### Claim 12 (depends on 11) The system of claim 11, wherein the instructions further cause the system to perform providing the content item in a feed associated with the administrator. ### Claim 13 (depends on 12) The system of claim 12, wherein the one or more cards include page updates associated with the one or more pages corresponding to the one or more cards. ### Claim 14 (depends on 13) The system of claim 13, wherein the one or more cards further include at least one of: page information relating to the one or more pages corresponding to the one or more cards, user-related metrics relating to the one or more pages corresponding to the one or more cards, or recommendations relating to the one or more pages corresponding to the one or more cards. ### Claim 15 (depends on 11) The system of claim 11, wherein the determining one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator is based on a third machine learning model. ### Claim 16 A non-transitory computer readable medium including instructions that, when executed by at least one hardware processor of a computing system, cause the computing system to perform a method comprising: determining one or more user-related metrics related to a plurality of pages associated with an administrator based at least in part on a likelihood of the administrator selecting the one or more user-related metrics, wherein the likelihood of the administrator selecting the one or more user-related metrics is determined by a first machine learning model and the first machine learning model is trained based at least in part on tracked information about user-related metrics and pages with which page administrators have engaged; determining one or more recommendations related to the plurality of pages based at least in part on a likelihood of the administrator selecting the one or more recommendations and a number of determined user-related metrics, wherein the likelihood of the administrator selecting the one or more recommendations is determined by a second machine learning model and the second machine learning model is trained based at least in part on the tracked information about user-related metrics and page recommendations selected by the page administrators; and determining one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator, based at least in part on the determined user-related metrics and the determined recommendations; and providing a content item that includes the one or more cards, wherein the one or more cards include the determined user-related metrics and the determined recommendations for the one or more pages corresponding to the one or more cards and wherein a selection of at least one of: the one or more cards, the determined user-related metrics, or the determined recommendations is included in new training data for further training at least one of: the first machine learning model or the second machine learning model. ### Claim 17 (depends on 16) The non-transitory computer readable medium of claim 16, wherein the method further comprises providing the content item in a feed associated with the administrator. ### Claim 18 (depends on 17) The non-transitory computer readable medium of claim 17, wherein the one or more cards include page updates associated with the one or more pages corresponding to the one or more cards. ### Claim 19 (depends on 18) The non-transitory computer readable medium of claim 18, wherein the one or more cards further include at least one of: page information relating to the one or more pages corresponding to the one or more cards, user-related metrics relating to the one or more pages corresponding to the one or more cards, or recommendations relating to the one or more pages corresponding to the one or more cards. ### Claim 20 (depends on 16) The non-transitory computer readable medium of claim 16, wherein the determining one or more pages of the plurality of pages for which to provide one or more cards of page updates for the administrator is based on a third machine learning model.