Recommending a group to a user of a social networking system based on affinities of the user for members of the group

Patent metadata

Field	Value
Publication number	US-10257308-B2
Application number	US-201615162577-A
Country	US
Kind code	B2
Filing date	May 23, 2016
Priority date	May 23, 2016
Publication date	Apr 9, 2019
Grant date	Apr 9, 2019

Abstract

A social networking system identifies a set of groups of which a user of the social networking system is not a member and selects a group for recommendation to the user based on a predicted affinity of the user for each identified group. The social networking system computes an affinity score of the user for each of one or more members of the selected group based at least in part on information describing a set of connections between the user and each member. Based on the scores, the social networking system selects a set of members of the group and generates a recommendation unit, wherein images associated with the selected members are arranged based on their scores and overlay at least a portion of an image associated with the group. The recommendation unit is communicated to the user to suggest that the user join the recommended group.

First claim

What is claimed is:

1. A method comprising:
maintaining information at a social networking system describing a plurality of groups, each group having a plurality of members and each member being a user of the social networking system;
identifying an opportunity to suggest, to a viewing user of the social networking system, that the viewing user join one or more of the plurality of groups;
determining a candidate set of groups from the plurality of groups, where the viewing user is not a member of any of the candidate set of groups;
predicting an affinity between the viewing user and each of one or more of the candidate set of groups;
selecting a group from the candidate set of groups, where the viewing user has at least a threshold predicted affinity for the selected group;
retrieving information associated with one or more members of the selected group;
computing an affinity score of the viewing user for each of the one or more members of the selected group based at least in part on one or more stored connections between the viewing user and the one or more members of the selected group;
ranking the one or more members of the selected group based on the computed affinity scores;
selecting a set of the one or more members of the selected group based at least in part on the ranking;
generating a recommendation for the viewing user to join the selected group, the recommendation comprising an arrangement of one or more images associated with each of the selected set of members of the selected group overlaying at least a portion of an image associated with the group, the images arranged within the recommendation based on the ranking; and
sending the recommendation for display to the viewing user.

2. The method of claim 1 , wherein the affinity score of the viewing user for each of the one or more members of the selected group is based at least in part on a measure of similarity of an attribute associated with the viewing user to an attribute associated with each of the one or more members of the selected group.

3. The method of claim 2 , further comprising:
associating weights with one or more attributes associated with the viewing user having at least a threshold measure of similarity to one or more attributes associated with each of the one or more members of the selected group; and
computing the affinity score of the viewing user for each of the one or more members of the selected group based at least in part on the weights.

4. The method of claim 1 , wherein the affinity score of the viewing user for each of the one or more members of the selected group is computed based at least in part on information stored in conjunction with the one or more stored connections between the viewing user and the one or more members of the selected group.

5. The method of claim 1 , wherein the selected set of the one or more members of the selected group are associated with at least a threshold affinity score.

6. The method of claim 1 , wherein the recommendation to join the selected group further comprises one or more selected from a group consisting of: a description of the selected group, a number of members of the selected group having stored connections to the viewing user, a number of members of the selected group, information describing one or more members of the selected group, information describing a predicted affinity of the viewing user for the selected group, an option to request to join the selected group, one or more content items associated with the selected group, and any combination thereof.

7. The method of claim 1 , wherein the recommendation to join the selected group is sent for display to the viewing user in conjunction with a feed of content items.

8. The method of claim 1 , wherein the predicted affinity of the viewing user for each of one or more of the candidate set of groups is based at least in part on one or more selected from a group consisting of: a measure of similarity between information associated with content maintained by the social networking system for which the viewing user has expressed an interest and information associated with a candidate group, a number of members of the candidate group connected to the viewing user, a threshold measure of similarity between attributes associated with members of the candidate group and attributes associated with the viewing user, a measure of similarity between one or more groups of which the viewing user is a member and the candidate group, a distance between a geographic location associated with the candidate group and a geographic location associated with the viewing user, and any combination thereof.

9. The method of claim 1 , wherein the candidate set of groups is determined from the plurality of groups subject to one or more privacy settings associated with the plurality of groups.

10. The method of claim 1 , wherein the information associated with one or more members of the selected group is retrieved subject to a privacy setting associated with the one or more members.

11. A computer program product comprising a non-transitory computer readable storage medium having instructions encoded therein that, when executed by a processor, cause the processor to:
maintain information at a social networking system describing a plurality of groups, each group having a plurality of members and each member being a user of the social networking system;
identify an opportunity to suggest, to a viewing user of the social networking system, that the viewing user join one or more of the plurality of groups;
determine a candidate set of groups from the plurality of groups, where the viewing user is not a member of any of the candidate set of groups;
predict an affinity between the viewing user and each of one or more of the candidate set of groups;
selecting a group from the candidate set of groups, where the viewing user has at least a threshold predicted affinity for the selected group;
retrieve information associated with one or more members of the selected group;
compute an affinity score of the viewing user for each of the one or more members of the selected group based at least in part on one or more stored connections between the viewing user and the one or more members of the selected group;
rank the one or more members of the selected group based on the computed affinity scores;
select a set of the one or more members of the selected group based at least in part on the ranking;
generate a recommendation for the viewing user to join the selected group, the recommendation comprising an arrangement of one or more images associated with each of the selected set of members of the selected group overlaying at least a portion of an image associated with the group, the images arranged within the recommendation based on the ranking; and
send the recommendation for display to the viewing user.

12. The computer program product of claim 11 , wherein the affinity score of the viewing user for each of the one or more members of the selected group is based at least in part on a measure of similarity of an attribute associated with the viewing user to an attribute associated with each of the one or more members of the selected group.

13. The computer program product of claim 12 , wherein the non-transitory computer readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to:
associate weights with one or more attributes associated with the viewing user having at least a threshold measure of similarity to one or more attributes associated with each of the one or more members of the selected group; and
compute the affinity score o

Assignees

• Facebook Inc

Inventors

• Li Jingxian
• Ju Li
• Ertmann Eric Carl
• Wong Felix

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• H04L67/22

  Electricity · mapped topic

• G06Q50/01

  Physics · mapped topic

• H04L67/306 Primary

  User profiles · CPC title

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title