# US 11,113,349 B2 · Cohort service > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,349 B2 - Document ID: US11113349B2 - Status: Granted - Kind: B2 - Application number: 16/279,779 - Filed: 2019-02-19 - Published: 2020-08-20 - Granted: 2021-09-07 - Earliest claimed: 2019-02-19 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Usha Seetharaman; Saurabh Agarwal; Saravanan Arumugam; Aastha Jain; Parag Agrawal - Web page: https://patentgrep.com/patent/US11113349B2 ## CPC - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 9/451: Execution arrangements for user interfaces - G06F 9/453: {Help systems} - G06F 16/24575: {using context} - G06F 16/24578: {using ranking} - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/00: Machine learning - H04L 67/306: User profiles - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A cohort service is configured to address the technical problem of providing recommendations to a member of an online connection network system in a manner that alleviates potentially excessive cognitive load associated with presenting recommended entities indiscriminately as a scrollable list. The cohort service is configured to visually surface recommended relevant entities already grouped as cohorts. A cohort is a grouping of entities based on one or more common attributes, such as, e.g., same school, same company, etc. The cohort service is designed to group recommendation results into cohorts at the server side, which increases the liquidity and the relevance of the recommended entities so that the already grouped recommendations can be sent to the client computer system for presentation to a viewer. ## Claims ### Claim 1 A computer implemented method comprising: in an online connection system, detecting a request for recommendations with respect to a first member represented by a first member profile, the request received from a client application executing at a client system associated with the first member; from the client application, receiving information indicating a viewing context associated with the detected request, the viewing context indicating a first attribute value of a member with whom the first member has recently established a connection via the online connection system; at a server system, fetching a first plurality of candidate member profiles for providing to the first member as connection recommendations, each candidate member profile in the first plurality of candidate member profiles having a member profile indicating the first cohort attribute value; ranking the first plurality of candidate member profiles using a machine learning model; selecting a first cohort of member profiles from the first plurality of candidate member profiles based on the ranking; and causing display of a reference one or more references to one or more member profiles in the first cohort of member profiles on a display device associated with the first member. ### Claim 2 (depends on 1) The method of claim 1, wherein the viewing context indicates a a second attribute value of the member with whom the first member recently established a connection via the online connection system. ### Claim 3 (depends on 2) The method of claim 2, further comprising: at the server system, fetching a second plurality of candidate member profiles for providing to the first member as connection recommendations, each candidate member profile in the second plurality of candidate member profiles having the second attribute value; ranking the second plurality of candidate member profiles using the machine learning model; selecting a second set of member profiles from the second plurality of candidate member profiles based on the ranking; and causing display of a reference to one or more member profiles in the second cohort of member profiles on a display device associated with the first member. ### Claim 4 (depends on 3) The method of claim 3, wherein the machine learning model is a hierarchical machine learning model and the ranking of the candidate member profiles comprises jointly ranking member profiles within the first plurality of member profiles and the second plurality of member profiles and ranking across the first plurality of member profiles and the second plurality of member profiles. ### Claim 5 (depends on 4) The method of claim 4, comprising using the hierarchical machine learning model to capture properties of the first plurality of member profiles during the ranking of the first and second plurality of member profiles and using the captured properties during the ranking. ### Claim 6 (depends on 1) The method of claim 1, wherein causing display of one or more references to one or more member profiles in the first cohort of member profiles comprises: generating a user interface that includes the one or more references to the one or more member profiles, presented as a group. ### Claim 7 (depends on 6) The method of claim 6, wherein the user interface includes selection controls to permit a user to select multiple of the one or more references and request an action with respect to a group of member profiles corresponding with the selected references. ### Claim 8 (depends on 7) The method of claim 7, wherein the action is to initiate a connection invitation from the first member with respect to member profiles corresponding to the respective selected references. ### Claim 9 (depends on 1) The method of claim 1, wherein the first attribute value is a member profile attribute value of the member with whom the first member has recently established a connection via the online connection system, the member profile attribute value indicating identification of a school or identification of a company. ### Claim 10 A system comprising: one or more processors; and non-transitory computer readable storage medium comprising instructions that where executed by the one or processors cause the one or more processors to perform operations comprising: in an online connection system detecting a request for recommendations with respect to a first member represented by a first member profile, the request received from a client application executing at a client system associated with the first member; from the client application, receiving information indicating a viewing context associated with the detected request, the viewing context indicating a first attribute value of a member with whom the first member has recently established a connection via the online connection system; at a server system, fetching a first plurality of candidate member profiles for providing to the first member as connection recommendations, each candidate member profile in the first plurality of candidate member profiles having a member profile indicating the first attribute value; ranking the first plurality of candidate entities member profiles using a machine learning model; selecting a first cohort of member profiles from the first plurality of candidate member profiles based on the ranking; and causing display of one or more references to one or more member profiles in the first cohort of member profiles on a display device associated with the first member. ### Claim 11 (depends on 10) The system of claim 10, wherein the viewing context indicates a a second attribute value of the member with whom the first member recently established a connection via the online connection system. ### Claim 12 (depends on 11) The system of claim 11, further comprising: at the server system, fetching a second plurality of candidate member profiles for providing to the first member as connection recommendations, each candidate member profile in the second plurality of candidate member profiles having the second attribute value ranking the second plurality of candidate member profiles using the machine learning model; selecting a second set of member profiles from the second plurality of candidate member profiles based on the ranking; and causing display of a reference to one or more member profiles in the second cohort of member profiles on a display device associated with the first member. ### Claim 13 (depends on 12) The system of claim 12, wherein the machine learning model is a hierarchical machine learning model and the ranking of the candidate member profiles comprises jointly ranking member profiles within the first plurality of member profiles and the second plurality of member profiles and ranking across the first plurality of member profiles and the second plurality of member profiles. ### Claim 14 (depends on 13) The system of claim 13, comprising using the hierarchical machine learning model to capture properties of the first plurality of member profiles during the ranking of the first and second plurality of member profiles and using the captured properties during the ranking. ### Claim 15 (depends on 10) The system of claim 10, wherein causing display of one or more references to one or more member profiles in the first cohort of member profiles comprises: generating a user interface that includes the one or more references to the selected one or more member profiles presented as a group. ### Claim 16 (depends on 15) The system of claim 15, wherein the user interface includes selection controls to permit a user to select of the one or more references and request an action with respect to a group of member profiles corresponding with the selected references. ### Claim 17 (depends on 16) The system of claim 16, wherein the action is to initiate a connection invitation from the first member with respect to member profiles corresponding to the respective selected references. ### Claim 18 A machine-readable non-transitory storage medium having instruction data executable by a machine to cause the machine to perform operations comprising: in an online connection system, detecting a request for recommendations with respect to a first member represented by a first member profile, the request received from a client application executing at a client system associated with the first member; from the client application, receiving information indicating a viewing context associated with the detected request, the viewing context indicating a first attribute value of a member with whom the first member has recently established a connection via the online connection system; at a server system, fetching a first plurality of candidate member profiles for providing to the first member as connection recommendations, each candidate member profile in the first plurality of candidate member profiles having a member profile indicating the first attribute value; ranking the first plurality of candidate member profiles using a machine learning model; selecting a first cohort of member profiles from the first plurality of candidate member profiles based on the ranking; and causing display of one or more references to one or more member profiles in the first cohort of member profiles on a display device associated with the first member.