INTERESTINGNESS RECOMMENDATIONS IN A COMPUTING ADVICE FACILITY

• US 20110302117A1
• Filed: 06/08/2011
• Published: 12/08/2011
• Est. Priority Date: 11/02/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Dixon, Christopher, Gattis, Matthew Ryan, Pinckney, Thomas
• Granted Patent: US 8,666,909 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The present disclosure provides a recommendation to a user through a computer-based advice facility, comprising collecting topical information, wherein the collected topical information includes an interestingness aspect; filtering the collected topical information based on the interestingness aspect; determining an interestingness rating from the collected topical information, wherein the determining is through the computer-based advice facility; and providing a user with the recommendation related to the topical information based on the interestingness rating.

Claims

1. A method of providing a recommendation to a user through a computer-based advice facility, comprising:

collecting topical information, wherein the collected topical information includes an interestingness aspect, the interestingness aspect being based on the similarity to a user'"'"'s taste profile and based on newness of the topical information;

filtering the collected topical information based on the interestingness aspect;

determining an interestingness rating from the collected topical information, wherein the determining is through the computer-based advice facility; and

providing a user with the recommendation related to the topical information based on the interestingness rating.

2. The method of claim 1, wherein the interestingness aspect is derived from social activity of another individual that indicates a recommendation for a topic.

3. The method of claim 2, wherein the other individual is a friend.

4. The method of claim 2, wherein the other individual is a famous person.

5. The method of claim 2, wherein the other individual is an authoritative person.

6. The method of claim 2, wherein the other individual has similar tastes to the user.

7. The method of claim 2, wherein the social activity is saving a recommendation.

8. The method of claim 2, wherein the social activity is at least one of commenting and discussing a recommendation actively.

9. The method of claim 2, wherein the social activity is collected from sources on the Internet.

10. The method of claim 1, wherein the interestingness aspect of the topical information is an indication that the topical information has some aspect of newness.

11. The method of claim 10, wherein the newness is an indication that the topical information is new topical information over a predetermined period of time.

12. The method of claim 10, wherein the newness is an indication that the topical information is newly popular.

13. The method of claim 12, wherein newly popular is determined from an activity level on the web.

14. The method of claim 1, wherein the interestingness aspect of the topical information is from at least one of a review, recommendation, blog entry, tweet, authoritative source, news source, and e-publication.

15. The method of claim 1, wherein the interestingness aspect is time data.

16. The method of claim 15, wherein the time data is a release date.

17. The method of claim 16, wherein the release date is a release date of a movie.

18. The method of claim 16, wherein the release date is a release date of a product.

19. The method of claim 15, wherein the time data is an event opening.

20. The method of claim 19, wherein the opening is a restaurant opening.

21. The method of claim 19, wherein the opening is a cultural event opening.

22. The method of claim 1, wherein the interestingness aspect is how frequently the topical information is referenced in online sources.

23. The method of claim 1, wherein the interestingness aspect is related to a user interaction with a computer device.

24. The method of claim 23, wherein the user interactions are interpreted by the machine learning facility as user behavior that indicates a preference level for the topical information by the user.

25. The method of claim 23, wherein the user interaction is selection of a web link.

26. The method of claim 23, wherein the user interaction is at least one of tapping, touching, and clicking on the computer device screen.

27. The method of claim 1, wherein the computer-based advice facility includes a machine-learning facility.

28. The method of claim 1, wherein the computer-based advice facility includes a recommendation facility.

29. The method of claim 1, wherein the filtering is collaborative filing.

30. The method of claim 1, wherein recommendations are sent to a user'"'"'s mobile communications facility to provide recommendations in the user'"'"'s current geographic area.

31. The method of claim 30, wherein there is a graphical user interface on the mobile communications facility that provides the user with the ability to refine provided recommendations to the user.

32. The method of claim 30, wherein the recommendations show the user at least one of items to buy, events to go to, and things to see.

33. The method of claim 30, wherein the recommendation is related to a local store.

34. The method of claim 30, wherein the recommendation is related to a local restaurant.

35. The method of claim 30, wherein the recommendation is related to a local bar.

36. The method of claim 30, wherein the recommendation is related to entertainment.

37. The method of claim 30, wherein recommendations are further filtered to the user based on interestingness specific to the geographic area.

38. The method of claim 30, wherein a recommendations feed is sent to the user for the current geographic area the user is located in.

39. The method of claim 30, wherein recommendations are only sent to the user that meet a threshold in confidence and in how much the system predicts the user will like the recommendation.

40. The method of claim 39, wherein the threshold in confidence is related to the interestingness rating.

41. The method of claim 39, wherein the threshold in confidence is determined by a machine learning facility based on past behavior of the user as related to previous recommendations provided by the system.

42. The method of claim 30, wherein the user is able to save recommendations to storage on the mobile communications facility.

43. The method of claim 30, wherein the user is able to save recommendations to storage with the computer-based advice facility.