Methods and systems for selecting and presenting content based on user preference information extracted from an aggregate preference signature

• US 8,073,848 B2
• Filed: 06/07/2010
• Issued: 12/06/2011
• Est. Priority Date: 03/06/2006
• Status: Active Grant

• Current Assignee: Veveo, Inc. (Adeia Inc.)
• Original Assignee: Veveo, Inc. (Adeia Inc.)
• Inventors: Aravamudan, Murali, Rajasekharan, Ajit, Ramakrishnan, Kajamalai G.
• Primary Examiner(s): Breene, John E
• Assistant Examiner(s): Phillips, III, Albert
• Application Number:
  US12/795,303
• Publication Number:
  US 20100241625A1
• Time in Patent Office: 547 Days
• Field of Search: 707/722, 707/734, 707/780, 707/765, 707/766
• US Class Current: 707/734
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2462 Approximate or statistical queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/438 Presentation of query results
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/4532 : involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/466 : Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/4828 : for searching program descriptors retrieval of video data G06F16/739
• CPC Class Codes: Y10S 707/99933 : Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 : Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99937 : Sorting
• CPC Class Codes: Y10S 707/99943 : Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 : Object-oriented database structure processing

Abstract

A method of selecting and presenting content based on inferred user preferences is provided. The method includes providing a set of content items having associated descriptive terms and receiving search inputs from an input device and presenting a corresponding subset of content items. The method includes receiving selection actions of content items and analyzing the descriptive terms associated with the selected content items to learn a composite set of preferred descriptive terms of the plurality of users of the input device. The method includes inferring preferences of individual users from the composite set of preferred descriptive terms by decomposing the composite set of preferred descriptive terms into individual sets of preferred descriptive terms. The decomposition act utilizes prespecified statistical models of preferences. The method includes, in response to receiving subsequent user search input, selecting and ordering a collection of content items based on the inferred preferences of said individual user.

Claims

1. A user-interface method of presenting and selecting a collection of content items to infer preferences of a given user from a plurality of users of an input interface, the preferences of the plurality of users of the input interface being learned based on content items selected by the plurality of users, the method comprising:

providing access to a set of content items, each content item having at least one associated descriptive term to describe the content item;

receiving incremental inputs through a shared input interface;

in response to said incremental input, presenting a corresponding subset of content items;

receiving from the shared input interface selection actions of content items;

analyzing the descriptive terms associated with the selected content items to learn a composite set of preferred descriptive terms of the plurality of users of the shared input interface, wherein the shared input interface used by the plurality of users is an input interface used by each user of the plurality of users so that the composite set of preferred descriptive terms collectively describes the descriptive terms associated with content items selected by each of the users of the plurality;

for at least one of the individual users of the plurality of users of the shared input interface, creating an individual preference signature that characterizes the preferred descriptive terms that correspond with said at least one individual user based on the composite set of preferred descriptive terms and based on prespecified statistical models of preferences of a population according to demographic information; and

reporting information about at least one of (i) the preferred descriptive terms characterized by the individual preference signature and (ii) the at least one individual user corresponding to said individual preference signature.

2. The method of claim 1, wherein the information about at least one of (i) the preferred descriptive terms characterized by the individual preference signature and (ii) the at least one individual user corresponding to said individual preference signature includes at least one of an approximate number of individual preference signatures, each corresponding to one of the individual users of the plurality, an inferred gender of the at least one of the individual users, and an inferred age of the at least one of the individual users.

3. The method of claim 1, wherein the demographic information is at least one of age and gender.

4. The method of claim 1, wherein the prespecified statistical models of preferences of a population according to demographic information include television viewing preferences of a population according to at least one of age and gender of members of the population.

5. The method of claim 1, wherein the set of content items includes at least one of television program items, movie items, audio / video media items, music items, contact information items, personal schedule items, web content items, and purchasable product items.

6. The method of claim 1, wherein the set of content items includes at least one of television program items, movie items, and audio / video media items and the descriptive terms includes at least one of title, cast, director, content description, and keywords associated with the content.

7. The method of claim 1, wherein the set of content items is contained on at least one of a cable television system, a video-on-demand system, an IPTV system, a personal video recorder, and an on-line service.

8. The method of claim 1, wherein the incremental inputs are entered by at least one of the plurality of users on an input constrained device.

9. The method of claim 8, wherein the input constrained device has a plurality of overloaded keys, each of the overloaded keys representing two or more characters.

10. The method of claim 1, wherein the incremental input is entered by at least one of the plurality of users on at least one of a telephone, a PDA, a computer, and a remote control.

11. The method of claim 1, wherein at least one of receiving incremental inputs, receiving selection actions, analyzing the descriptive terms, and creating the individual preference signature is performed on a server system remote from the user.

12. The method of claim 1, wherein at least one of receiving incremental inputs, receiving selection actions, analyzing the descriptive terms, and creating the individual preference signature is performed on a user client device.

13. The method of claim 1, further comprising:

inferring which content items were selected by one of the individual users based on the received selection actions;

analyzing the descriptive terms associated with the content items inferred to have been selected by the individual user to identify sets of actions resulting in the selection of similar content items, wherein similarity is determined by comparing the descriptive terms associated with any one of the selected content items with any of the previously selected content items; and

analyzing the date, day, and time of at least two of the individual selection actions of the sets of actions to learn periodicities of the individual user actions resulting in the selections of similar content items, wherein the periodicity corresponding to a particular set of actions for selecting similar content items indicates the amount of time between the user selection actions of the set;

wherein the reporting information about the preferred descriptive terms characterized by the individual preference signature includes reporting information about at least one of the learned periodicities of the sets of actions resulting in the selection of similar content items.

14. The method of claim 13, wherein the learned periodicity is about one day.

15. The method of claim 13, wherein the learned periodicity is about one week.

16. The method of claim 13, wherein the learned periodicity is about one month.

17. The method of claim 13, further comprising:

associating more than one descriptive term with the learned periodicity; and

weighting the descriptive terms associated with the learned periodicity according to at least one of recency of the user selections of content items and number of user selections of content items;

wherein the reporting information about the preferred descriptive terms characterized by the individual preference signature is based on the weights of the descriptive terms.

18. The method of claim 13, wherein the time of the user selection actions are represented as time slots of a specified duration.

19. The method of claim 18, wherein the specified duration is about one second.

20. The method of claim 18, wherein the specified duration is about one minute.

21. The method of claim 18, wherein the specified duration is about 30 minutes.

22. The method of claim 18, wherein the specified duration is about one hour.

23. The method of claim 18, wherein the specified duration is about one day.

24. The method of claim 18, wherein the specified duration is about one week.

25. The method of claim 18, wherein the specified duration is about one month.

26. The method of claim 13, further comprising:

associating the learned periodicities of the sets of actions resulting in the selection of similar content items with the corresponding descriptive terms associated with the similar content items that were selected; and

in response to receiving subsequent incremental input entered by the individual user, selecting and ordering a collection of content items wherein content items associated with descriptive terms similar to the subsequent incremental input and associated with descriptive terms further associated with periodicities similar to the date, day, and time of the subsequent incremental input are presented on a display device as more relevant content.

27. The method of claim 13, further comprising:

analyzing the learned periodicities of the individual user actions to detect a change in the periodicities of the selection of similar content items;

wherein the reporting information about at least one of the learned periodicities includes reporting the change in the learned periodicities.

28. The method of claim 1, further comprising:

analyzing the descriptive terms associated with the content items selected by the plurality of users to detect an increase in the frequency with which descriptive terms are associated with the content items selected by the plurality of users;

wherein the reporting information about the preferred descriptive terms characterized by the individual preference signature includes reporting the increase in the frequency with which descriptive terms are associated with the content items selected by the plurality of users.

29. The method of claim 1, further comprising:

analyzing the descriptive terms associated with the content items selected by the plurality of users to detect a change in the frequency with which descriptive terms are associated with the content items selected by the plurality of users;

wherein the reporting information about the preferred descriptive terms characterized by the individual preference signature includes reporting the change in the frequency with which descriptive terms are associated with the content items selected by the plurality of users.