Systems and methods for providing media recommendations

Patent metadata

Field	Value
Publication number	US-9235574-B2
Application number	US-201213404294-A
Country	US
Kind code	B2
Filing date	Feb 24, 2012
Priority date	Jun 13, 2011
Publication date	Jan 12, 2016
Grant date	Jan 12, 2016

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.

First claim

What is claimed is:

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 plurality of polarity scores for 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;
receiving, at the processing device, a request from a user to access the recommendation server;
determining, with the processing device, whether the user has previously accessed the recommendation server more than a threshold number of times;
increasing, with the processing device, a polarity score threshold when the user has previously accessed the recommendation server more than the threshold number of times;
comparing, with the processing device, the plurality of polarity scores to the polarity score threshold; and
in response to determining that a polarity score of the plurality of polarity scores does not exceed the polarity score threshold, transmitting, to a client device for display, a recommendation for a content element associated with the 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 1 , wherein the polarity score threshold is a minimum polarity score of the plurality of polarity scores.

4. The method of claim 1 , wherein determining a plurality of polarity scores for the plurality of content elements comprises calculating an average value of the plurality of preference values associated with at least one of the plurality of content elements.

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

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

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

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

9. The method of claim 1 , wherein the polarity score threshold is based on a user history.

10. The method of claim 1 , wherein the polarity score is based on a number of peaks in a distribution of the plurality of preference values.

11. 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 plurality of polarity scores for 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;
receive, at the processing device, a request from a user to access the recommendation server;
determine, with the processing device, whether the user has previously accessed the recommendation server more than a threshold number of times;
increase, with the processing device, a polarity score threshold when the user has previously accessed the recommendation server more than the threshold number of times;
compare the plurality of polarity scores to the polarity score threshold; and
in response to determining that a polarity score of the plurality of polarity scores does not exceed the polarity score threshold, transmit, to the client device for display via the output device, a recommendation for a content element associated with the polarity score.

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

13. The system of claim 11 , wherein the polarity score threshold is a minimum polarity score of the plurality of polarity scores.

14. The system of claim 11 , wherein determining the plurality of polarity scores for the plurality of content elements comprises calculating an average value of the plurality of preference values associated with at least one of the plurality of content elements.

15. The system of claim 11 , wherein the polarity score associated with the content element further represents a concentration of the plurality of preference values associated with the content element around two or more different values between the first and second end points.

16. The system of claim 11 , wherein transmitting the recommendation for the content element comprises transmitting metadata descriptive of the content element.

17. The system of claim 11 , wherein transmitting the recommendation to the client device for display comprises transmitting the recommendation to the client device for display on a user device, and wherein the user device is in communication with the client device.

18. The system of claim 11 , wherein the plurality of preference values associated with the content element is based on user ratings of the content element.

19. The system of claim 11 , wherein the polarity score threshold is based on a user history.

20. The system of claim 11 , wherein the polarity score is based on a number of peaks in a distribution of the plurality of preference values.

Assignees

• Green Benjamin
• Helsinger Alex
• Papish Michael
• Rovi Guides Inc

Inventors

• Green Benjamin
• Helsinger Alex
• Papish Michael

Classifications

• G06F16/437 Primary

  Administration of user profiles, e.g. generation, initialisation, adaptation, distribution · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F17/30035 Primary

  Physics · mapped topic

• G06F17/30867

  Physics · mapped topic