Systems and Methods for Providing Personalized Recommendations for Electronic Content

• US 20140164401A1
• Filed: 12/10/2012
• Published: 06/12/2014
• Est. Priority Date: 12/10/2012
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: AOL Inc. (Apollo Global Management, Inc.)
• Inventors: TIMM, Sean Christopher, ACHUTHAN, Sudhir, KYAW, Thu, SONG, Sang Chul, BARRETT, Mikhail, MAHAJAN, Vineet
• Granted Patent: US 9,721,019 B2
• Time in Patent Office: Days
• US Class Current: 707/751
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Computer-implemented systems and methods are provided for presenting content recommendations. In one implementation, a method is provided for providing content recommendations to a plurality of users. The method may include generating a first plurality of content recommendations for a first user using a first plurality of methods, each of the first plurality of methods having a weight associated therewith. The method may further include selecting a second plurality of content recommendations from the first plurality of content recommendations based on the weights associated with the first plurality of methods. The method may further include providing the second plurality of content recommendations to the first user. The method may further include updating the weights associated with the first plurality of methods based on engagement by the first user with the second plurality of content recommendations.

Claims

1. A computer-implemented method for providing content recommendations to a plurality of users, comprising:

generating a first plurality of content recommendations for a first user using a first plurality of methods, each of the first plurality of methods having a weight associated therewith;

selecting, by at least one hardware processor, a second plurality of content recommendations from the first plurality of content recommendations based on the weights associated with the first plurality of methods;

providing the second plurality of content recommendations to the first user; and

updating the weights associated with the first plurality of methods based on engagement by the first user with the second plurality of content recommendations.

2. The method of claim 1, further comprising:

generating a third plurality of content recommendations for a second user using a second plurality of methods, each of the second plurality of methods having a weight associated therewith;

selecting a fourth plurality of content recommendations from the third plurality of content recommendations based on the weights associated with the second plurality of methods;

providing the fourth plurality of content recommendations to the second user; and

updating the weights associated with the second plurality of methods based on engagement by the second user with the fourth plurality of content recommendations.

3. The method of claim 2, wherein the first plurality of methods are different from the second plurality of methods.

4. The method of claim 2, wherein the first plurality of methods are executed in parallel with the second plurality of methods.

5. The method of claim 1, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation; and

the first method generates the first recommendation by using electronic content from a social network of the first user.

6. The method of claim 1, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation;

the first method generates the first recommendation; and

the first method includes determining users similar to the first user and determining content read by the users similar to the first user.

7. The method of claim 6, wherein the users similar to the first user are determined based on content shared by the first user and the users similar to the first user.

8. The method of claim 6, wherein the users similar to the first user are determined based on demographic information of the first user and the users similar to the first user.

9. The method of claim 1, wherein the first user engages with the second plurality of content recommendations by one of clicking, sharing, and tweeting a content recommendation in the second plurality of content recommendations.

28. The method of claim 1, wherein the first plurality of content recommendations include at least one of a recommendation for an advertisement, a video file, a text file, and an audio file.

10. A system for providing content recommendations to a plurality of users, comprising:

at least one hardware processor; and

a memory storing instructions to be executed by the at least one hardware processor,

wherein the at least one hardware processor is configured by the instructions to;

generate a first plurality of content recommendations for a first user using a first plurality of methods, each of the first plurality of methods having a weight associated therewith;

select a second plurality of content recommendations from the first plurality of content recommendations based on the weights associated with the first plurality of methods;

provide the second plurality of content recommendations to the first user; and

update the weights associated with the first plurality of methods based on engagement by the first user with the second plurality of content recommendations.

11. The system of claim 10, wherein the at least one hardware processor is further configured to:

generate a third plurality of content recommendations for a second user using a second plurality of methods, each of the second plurality of methods having a weight associated therewith;

select a fourth plurality of content recommendations from the third plurality of content recommendations based on the weights associated with the second plurality of methods;

provide the fourth plurality of content recommendations to the second user; and

update the second weights based on engagement by the second user with the fourth plurality of content recommendations.

12. The system of claim 11, wherein the first plurality of methods are different from the second plurality of methods.

13. The system of claim 11, wherein the at least one hardware processor is configured to execute the first plurality of methods in parallel with the second plurality of methods.

14. The system of claim 10, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation; and

the first method generates the first recommendation by using electronic content from a social network of the first user.

15. The system of claim 10, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation;

the first method generates the first recommendation; and

the first method includes determining users similar to the first user and determining content read by the users similar to the first user.

16. The system of claim 15, wherein the users similar to the first user are determined based on content shared by the first user and the users similar to the first user.

17. The system of claim 15, wherein the users similar to the first user are determined based on demographic information of the first user and the users similar to the first user.

18. The system of claim 10, wherein the first user engages with the second plurality of content recommendations by one of clicking, sharing, and tweeting a content recommendation in the second plurality of content recommendations.

29. The system of claim 10, wherein the first plurality of content recommendations include at least one of a recommendation for an advertisement, a video file, a text file, and an audio file.

19. A non-transitory computer-readable storage medium storing instructions for enabling a processor to execute a method for providing content recommendations to a plurality of users, the method comprising:

generating a first plurality of content recommendations for a first user using a first plurality of methods, each of the first plurality of methods having a weight associated therewith;

selecting a second plurality of content recommendations from the first plurality of content recommendations based on the weights associated with the first plurality of methods;

providing the second plurality of content recommendations to the first user; and

updating the weights associated with the first plurality of methods based on engagement by the first user with the second plurality of content recommendations.

20. The non-transitory computer-readable storage medium of claim 19, wherein the method further comprises:

generating a third plurality of content recommendations for a second user using a second plurality of methods, each of the second plurality of methods having a weight associated therewith;

selecting a fourth plurality of content recommendations from the third plurality of content recommendations based on the weights associated with the second plurality of methods;

providing the fourth plurality of content recommendations to the second user; and

updating the weights associated with the second plurality of methods based on engagement by the second user with the fourth plurality of content recommendations.

21. The non-transitory computer-readable storage medium of claim 20, wherein the first plurality of methods are different from the second plurality of methods.

22. The non-transitory computer-readable storage medium of claim 20, wherein the first plurality of methods are executed in parallel with the second plurality of methods.

23. The non-transitory computer-readable storage medium of claim 19, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation; and

the first method generates the first recommendation by using electronic content from a social network of the first user.

24. The non-transitory computer-readable storage medium of claim 19, wherein:

the first plurality of methods includes a first method;

the first plurality of content recommendations includes a first recommendation;

the first method generates the first recommendation; and

the first method includes determining users similar to the first user and determining content read by the users similar to the first user.

25. The non-transitory computer-readable storage medium of claim 24, wherein the users similar to the first user are determined based on content shared by the first user and the users similar to the first user.

26. The non-transitory computer-readable storage medium of claim 24, wherein the users similar to the first user are determined based on demographic information of the first user and the users similar to the first user.

27. The non-transitory computer-readable storage medium of claim 19, wherein the first user engages with the second plurality of content recommendations by one of clicking, sharing, and tweeting a content recommendation in the second plurality of content recommendations.

30. The non-transitory computer-readable storage medium of claim 19, wherein the first plurality of content recommendations include at least one of a recommendation for an advertisement, a video file, a text file, and an audio file.