Recommending content based on intersecting user interest profiles

• US 9,680,959 B2
• Filed: 08/30/2012
• Issued: 06/13/2017
• Est. Priority Date: 08/30/2012
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kothari, Nisarg Dilipkumar, Rizzolo, Nicholas Delmonico, Gargi, Ullas
• Primary Examiner(s): SALAD, ABDULLAHI ELMI
• Application Number:
  US13/599,136
• Publication Number:
  US 20160255170A1
• Time in Patent Office: 1,748 Days
• Field of Search: 709204-205, 705 1453, 705 267, 725 46
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04L 67/306 User profiles

Abstract

This technology may generate recommendations of relevant content, based on determining intersections among one or more user interest profiles of users, who interact either synchronously or asynchronously. This technology may retrieve interest profiles for particular users, determine intersections among all user interest profiles (or among individual content recommendations), and create a group interest profile, update the particular users'"'"' interest profiles based on the group interest profile created, and generate recommendations of content that is determined to be relevant based on the group interest profile. A user may select items from these recommendations of content, add the user-selected content recommendations to a common group pool, generate a group interest profile based on the common group pool, and generate recommendations of content based on the group interest profile. Scores for the recommendations of content may be calculated and the top scoring ones may be displayed to the users in the group.

Claims

1. A computer-implemented method comprising:

retrieving, by one or more computing devices, a first user interest profile of a first user and a second user interest profile of a second user from a social network;

generating, by at least one of the one or more computing devices, a first set of recommendations of content for the first user based on the first user interest profile and a second set of recommendations of content for the second user based on the second user interest profile;

determining, by at least one of the one or more computing devices, a first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

identifying, by at least one of the one or more computing devices, a shared set of recommendations of content from the first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

generating, by at least one of the one or more computing devices, a first shared interest element for a group of the first user and the second user based on the shared set of recommendations of content;

generating, by at least one of the one or more computing devices, a group interest profile for the group of the first user and the second user based on the first shared interest element; and

generating, by at least one of the one or more computing devices, a third set of recommendations of content for the group of the first user and the second user based on the group interest profile.

2. A computer-implemented method according to claim 1, wherein the first user interest profile corresponds to the first user in the group and the second user interest profile corresponds to the second user in the group on the social network.

3. A computer-implemented method according to claim 1, further comprising:

determining a second intersection between the first user interest profile and the second user interest profile to identify a second shared interest element.

4. A computer-implemented method according to claim 3, wherein the group interest profile is based at least in part on the second intersection identifying a presence of the second shared interest element between the first user interest profile and the second user interest profile.

5. A computer-implemented method according to claim 1, further comprising:

receiving, from the first user, a selection of a first recommendation of content in the first set of recommendations of content; and

receiving, from the second user, a selection of a second recommendation of content in the second set of recommendations of content.

6. A computer-implemented method of claim 5, further comprising:

adding the first recommendation of content and the second recommendation of content to a pool of recommendations.

7. A computer-implemented method according to claim 6, wherein generating the group interest profile includes generating the group interest profile based on the pool of recommendations.

8. A computer-implemented method according to claim 1, wherein generating the third set of recommendations of content for the group further comprises:

calculating a score for the first set and the second set of recommendations of content based on a corresponding relevancy of the first set of recommendations of content to the first user interest profile and the second set of recommendations of content to the second user interest profile;

determining a statistical function of calculated scores being assigned to the first set and the second set of recommendations of content;

calculating a final score for the first set and the second set of recommendations of content based on a value of the determined statistical function of the calculated scores; and

providing for display top scoring recommendations of content to the group of users based on the final score calculated for the first set and the second set of recommendations of content.

9. A computer-implemented method according to claim 8, wherein the statistical function is one from a group of an average function, a mean function and a median function.

10. A computer-implemented method according to claim 8, further comprising:

updating the first user interest profile and the second user interest profile based on the top scoring recommendations of content.

11. A computer program product comprising a non-transitory computer useable memory including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

retrieve a first user interest profile of a first user and a second user interest profile of a second user from a social network;

generate a first set of recommendations of content for the first user based on the first user interest profile and a second set of recommendations of content for the second user based on the second user interest profile;

determine a first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

identify a shared set of recommendations of content from the first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

generate a first shared interest element for a group of the first user and the second user based on the shared set of recommendations of content;

generate a group interest profile for the group of the first user and the second user based on the first shared interest element; and

generate a third set of recommendations of content for the group of the first user and the second user based on the group interest profile.

12. A computer program product according to claim 11, wherein the first user interest profile corresponds to the first user in the group and the second user interest profile corresponds to the second user in the group on the social network.

13. A computer program product according to claim 11, further causing the computer to determine a second intersection between the first user interest profile and the second user interest profile to identify a second shared interest element.

14. A computer program product according to claim 13, wherein the group interest profile is based at least in part on, the second intersection identifying a presence of the second shared interest element between the first user interest profile and the second user interest profile.

15. A computer program product according to claim 11, further causing the computer to receive, from the first user, a selection of a first recommendation of content in the first set of recommendations of content and receive, from the second user, a selection of a second recommendation of content in the second set of recommendations of content.

16. A computer program product according to claim 15, further causing the computer to add the first recommendation of content and the second recommendation of content to a pool of recommendations.

17. A computer program product according to claim 16, wherein generating the group interest profile includes generating the group interest profile based on the pool of recommendations.

18. A computer program product according to claim 11, wherein causing the computer to generate the third set of recommendations of content for the group further comprises causing the computer to calculate a score for the first set and the second set of recommendations of content based on a corresponding relevancy of the first set of recommendations of content to the first user interest profile and the second set of recommendations of content to the second user interest profile, to determine a statistical function of calculated scores being assigned to the first set and the second set of recommendations of content, to calculate a final score for the first set and the second set of recommendations of content based on a value of the determined statistical function of the calculated scores and to provide for display top scoring recommendations of content to the group of users based on the final score calculated for the first set and the second set of recommendations of content.

19. A computer program product according to claim 18, wherein the statistical function is one from a group of an average function, a mean function and a median function.

20. A computer program product according to claim 18, further causing the computer to update the first user interest profile and the second user interest profile based on the top scoring recommendations of content.

21. A system, comprising:

a processor;

a memory storing instructions, that when executed, cause the system to;

retrieve a first user interest profile of a first user and a second user interest profile of a second user from a social network;

generate a first set of recommendations of content for the first user based on the first user interest profile and a second set of recommendations of content for the second user based on the second user interest profile;

determine a first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

identify a shared set of recommendations of content from the first intersection between the first set of recommendations of content for the first user and the second set of recommendations of content for the second user;

generate a first shared interest element for a group of the first user and the second user based on the shared set of recommendations of content;

generate a group interest profile for the group of the first user and the second user based on the first shared interest element; and

generate a third set of recommendations of content for the group of the first user and the second user based on the group interest profile.

22. A system according to claim 21, wherein the first user interest profile corresponds to the first user in the group and the second user interest profile corresponds to the second user in the group on the social network.

23. A system according to claim 21, further comprising determining a second intersection between the first user interest profile and the second user interest profile to identify a second shared interest element.

24. A system according to claim 23, wherein the group interest profile is based at least in part on the second intersection identifying a presence of the second shared interest element between the first user interest profile and the second user interest profile.

25. A system according to claim 21, further comprising:

a user interface configured to receive, from the first user, a selection of a first recommendation of content in the first set of recommendations of content and receive, from the second user, a selection of a second recommendation of content in the second set of recommendations of content.

26. A system according to claim 25, further comprising:

a selection prompt module for adding the first recommendation of content and the second recommendation of content to a pool of recommendations.

27. A system according to claim 26, wherein a group interest profile module generates the group interest profile based on the pool of recommendations.

28. A system according to claim 21, wherein generating the third set of recommendations of content for the group further comprises calculating a score for the first set and the second set of recommendations of content based on a corresponding relevancy of the first set of recommendations of content to the first user interest profile and the second set of recommendations of content to the second user interest profile, determining a statistical function of calculated scores being assigned to the first set and the second set of recommendations of content, calculating a final score for the first set and the second set of recommendations of content based on a value of the determined statistical function of the calculated scores and providing for display top scoring recommendations of content to the group of users based on the final score calculated for the first set and the second set of recommendations of content.

29. A system according to claim 28, wherein the statistical function is one from a group of an average function, a mean function and a median function.

30. A system according to claim 28, further comprising updating the first user interest profile and the second user interest profile based on the top scoring recommendations of content.