SYSTEMS AND METHODS FOR PROVIDING MEDIA RECOMMENDATIONS

• US 20120317123A1
• Filed: 02/24/2012
• Published: 12/13/2012
• Est. Priority Date: 06/13/2011
• Status: Active Grant

• Current Assignee: UV Corporation (Adeia Inc.)
• Original Assignee: United Video Properties Incorporated (Adeia Inc.)
• Inventors: Green, Benjamin, Helsinger, Alex, Papish, Michael
• Granted Patent: US 9,235,574 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Systems and methods are described for providing content recommendations by maintaining preference values indicative of a user'"'"'s preference (e.g., degree of like or dislike) for different assets and updating these preference values based on observed events and known relationships between events and content elements. Also disclosed herein are systems and methods for providing content recommendations using polarity scores, which represent how much user preferences for certain content differ from the average user preference for that content.

Claims

1. A method for providing content recommendations, comprising:

receiving, at a processing device of a recommendation server, a plurality of preference values associated with each of a plurality of content elements, wherein each preference value is a value between a first end point and a second end point, the first end point representing a dislike of the associated content element and the second end point representing a liking for the associated content element;

determining, with the processing device, a polarity score for each of the plurality of content elements based on the associated plurality of preference values, wherein each polarity score represents an amount by which the associated plurality of preference values differ from an average value of the associated plurality of preference values;

comparing, with the processing device, the plurality of polarity scores to a polarity threshold; and

in response to determining that a polarity score of the plurality of polarity scores does not exceed the polarity threshold, transmitting, to a client device for display, a recommendation for the content element associated with that polarity score.

2. The method of claim 1, wherein the comparing and transmitting are performed in response to determining that the user has not previously accessed the recommendation server.

3. The method of claim 2, further comprising:

determining, with the processing device, whether a user associated with the client device has previously accessed the recommendation server more than a threshold number of times; and

in response to determining that the user has previously accessed the recommendation server more than the threshold number of times, increasing, with the processing device, the polarity threshold.

4. The method of claim 1, wherein the polarity threshold is a minimum polarity score of the plurality of polarity scores.

5. The method of claim 1, wherein determining a polarity score associated with a content element comprises calculating an average value of the plurality of preference values associated with that content element.

6. The method of claim 1, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

7. The method of claim 1, wherein transmitting a recommendation for a content element comprises transmitting metadata descriptive of the content element.

8. The method of claim 1, wherein transmitting a recommendation to a client device for display comprises transmitting the recommendation to a client device for display on a user device in communication with the client device.

9. The method of claim 1, wherein the plurality of preference values associated with a content element is based on user ratings of that content element.

10. A system for providing content recommendations, comprising:

a memory configured to store a plurality of preference values associated with each of content elements, wherein each preference value is a value between a first end point and a second end point, the first end point representing a dislike of the associated content element and the second end point representing a liking for the associated content element;

an output device configured to transmit a recommendation for a content element to a client device for display; and

a processing device in communication with the memory and the output device and configured to;

determine a polarity score for each of the plurality of content elements based on the associated plurality of preference values, wherein each polarity score represents an amount by which the associated plurality of preference values differ from an average value of the associated plurality of preference values;

compare the plurality of polarity scores to a polarity threshold; and

in response to determining that a polarity score of the plurality of polarity scores does not exceed the polarity threshold, transmit, to the client device for display via the output device, a recommendation for the content element associated with that polarity score.

11. The system of claim 10, wherein the comparing and transmitting are performed in response to determining that the user has not previously accessed the recommendation server.

12. The system of claim 11, wherein the processing device is further configured to:

determine whether a user associated with the client device has previously accessed the system more than a threshold number of times; and

in response to determining that the user has previously accessed the system more than the threshold number of times, increase the polarity threshold.

13. The system of claim 10, wherein the polarity threshold is a minimum polarity score of the plurality of polarity scores.

14. The system of claim 10, wherein determining a polarity score associated with a content element comprises calculating an average value of the plurality of preference values associated with that content element.

15. The system of claim 10, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

16. The system of claim 10, wherein transmitting a recommendation for a content element comprises transmitting metadata descriptive of the content element.

17. The system of claim 10, wherein transmitting a recommendation to a client device for display comprises transmitting the recommendation to a client device for display on a user device in communication with the client device.

18. The system of claim 10, wherein the plurality of preference values associated with a content element is based on user ratings of that content element.

19. A system for providing content recommendations, comprising:

means for receiving a plurality of preference values associated with each of a plurality of content elements, wherein each preference value is a value between a first end point and a second end point, the first end point representing a dislike of the associated content element and the second end point representing a liking for the associated content element;

means for determining a polarity score for each of the plurality of content elements based on the associated plurality of preference values, wherein each polarity score represents an amount by which the associated plurality of preference values differ from an average value of the associated plurality of preference values;

means for comparing the plurality of polarity scores to a polarity threshold; and

means for, in response to determining that a polarity score of the plurality of polarity scores does not exceed the polarity threshold, transmitting, to a client device for display, a recommendation for the content element associated with that polarity score.

20. The system of claim 19, wherein the comparing and transmitting are performed in response to determining that the user has not previously accessed the recommendation server.

21. The system of claim 20, further comprising:

means for determining whether a user associated with the client device has previously accessed the system more than a threshold number of times; and

means for in response to determining that the user has previously accessed the system more than the threshold number of times, increasing the polarity threshold.

22. The system of claim 19, wherein the polarity threshold is a minimum polarity score of the plurality of polarity scores.

23. The system of claim 19, wherein the means for determining a polarity score associated with a content element comprises means for calculating an average value of the plurality of preference values associated with that content element.

24. The system of claim 19, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

25. The system of claim 19, wherein the means for transmitting a recommendation for a content element comprises means for transmitting metadata descriptive of the content element.

26. The method of claim 19, wherein the means for transmitting a recommendation to a client device for display comprises means for transmitting the recommendation to a client device for display on a user device in communication with the client device.

27. The system of claim 19, wherein the plurality of preference values associated with a content element is based on user ratings of that content element.

28. A method for providing content recommendations, comprising:

receiving, at a processing device of a client server, metadata descriptive of a content element, wherein;

the content element is associated with a polarity score that does not exceed a polarity score threshold,

the polarity score is based on a plurality of preference values associated with that content element,

each preference value of the plurality of preference values is a value between a first end point and a second end point, the first end point representing a dislike of the content element and the second end point representing a liking for the content element, and

each polarity score represents an amount by which the plurality of preference values differ from an average value of the plurality of preference values;

transforming, with the processing device, the metadata into a recommendation display for a user device; and

transmitting, from the processing device to the user device, the recommendation display.

29. The method of claim 28, wherein the metadata descriptive of a content element is received from a recommendation server, and the receiving occurs before the processing device has accessed the recommendation server on behalf of the user device more than a threshold number of times.

30. The method of claim 28, wherein the polarity threshold is a minimum polarity score of a plurality of polarity scores associated with a corresponding plurality of content elements.

31. The method of claim 28, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

32. The method of claim 28, wherein the plurality of preference values associated with the content element is based on user ratings of that content element.

33. A system for providing content recommendations, comprising:

a memory configured to store metadata descriptive of a content element;

an output device configured to transmit a recommendation display to a user device; and

a processing device in communication with the memory and the output device and configured to;

receive the metadata descriptive of a content element, wherein;

the content element is associated with a polarity score that does not exceed a polarity score threshold,

the polarity score is based on a plurality of preference values associated with that content element,

each preference value of the plurality of preference values is a value between a first end point and a second end point, the first end point representing a dislike of the content element and the second end point representing a liking for the content element, and

each polarity score represents an amount by which the plurality of preference values differ from an average value of the plurality of preference values;

transform the metadata into a recommendation display for a user device; and

transmit, to the user device via the output device, the recommendation display.

34. The system of claim 33, wherein the metadata descriptive of a content element is received from a recommendation server, and the receiving occurs before the system has accessed the recommendation server on behalf of the user device more than a threshold number of times.

35. The system of claim 33, wherein the polarity threshold is a minimum polarity score of a plurality of polarity scores associated with a corresponding plurality of content elements.

36. The system of claim 33, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

37. The system of claim 33, wherein the plurality of preference values associated with the content element is based on user ratings of that content element.

38. A system for providing content recommendations, comprising:

means for receiving metadata descriptive of a content element, wherein;

the content element is associated with a polarity score that does not exceed a polarity score threshold,

the polarity score is based on a plurality of preference values associated with that content element,

each preference value of the plurality of preference values is a value between a first end point and a second end point, the first end point representing a dislike of the content element and the second end point representing a liking for the content element, and

each polarity score represents an amount by which the plurality of preference values differ from an average value of the plurality of preference values;

means for transforming the metadata into a recommendation display for a user device; and

means for transmitting, to the user device, the recommendation display.

39. The method of claim 38, wherein the metadata descriptive of a content element is received from a recommendation server, and the receiving occurs before the system has accessed the recommendation server on behalf of the user device more than a threshold number of times.

40. The method of claim 38, wherein the polarity threshold is a minimum polarity score of a plurality of polarity scores associated with a corresponding plurality of content elements.

41. The method of claim 38, wherein the polarity score associated with a content element further represents a concentration of the plurality of preference values associated with that content element around two or more different values between the first and second end points.

42. The method of claim 38, wherein the plurality of preference values associated with the content element is based on user ratings of that content element.