Systems and methods for determining user interests

• US 20060224552A1
• Filed: 03/31/2005
• Published: 10/05/2006
• Est. Priority Date: 03/31/2005
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Greene, Daniel H., Riezler, Stefan
• Granted Patent: US 7,613,664 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation

Abstract

Techniques are provided to determine user-interest features and user-interest parameter weights for a user-interest model. The user-interest features are pre-determined and/or determined dynamically. Pre-determined user-interest features are based on user-interest profiles, prior user activities, documents listed in a resume, reading or browsing patterns and the like. Dynamically determined user-interest features include features learned from an archive of user activities using statistical analysis, machine learning and the like. User-interest parameter weights are pre-determined and/or dynamically determined. Pre-determined user-interest parameter weights include parameter weights manually entered by a user indicating the relevant importance of a user-interest feature and parameter weights previously learned from an archive of the user'"'"'s past activities. Dynamically assigned user-interest parameter weights include dynamically determined updates to user-interest parameter weights based on newly identified documents or topics of interest.

Claims

1. A computer-implemented method of determining a user-interest model comprising the steps of:

determining user-interest features;

determining parameter weights for the user-interest features; and

determining a user-interest model based on the user-interest features and the parameter weights.

2. The method of claim 1, in which the user-interest features are based on a user-interest profile.

3. The method of claim 1, in which the user-interest features are learned.

4. The method of claim 3, in which the user-interest features are learned from a corpus of documents associated with at least one prior transaction.

5. The method of claim 4, in which the at least one prior transaction is at least one of:

search history, reading history; and

browsing history.

6. The method of claim 2, in which the parameter weights are determined stochastically and relevant user-interest features are determined by automatic feature selection.

7. The method of claim 2, in which the parameter weights are set manually.

8. The method of claim 2, in which the parameter weights are learned.

9. The method of claim 1, in which the parameter weights are learned from a corpus of documents associated with at least one prior transaction.

10. The method of claim 9, in which the at least one prior transaction is at least one of:

search history, reading history; and

browsing history.

11. The method of claim 2, in which the parameter weights are set by occurrences of features in topically related documents.

12. A computer-implemented system for determining a user-interest model comprising:

an input/output circuit for retrieving documents;

a processor that determines user-interest features;

determines parameter weights for the user-interest features; and

which determines a user-interest model based on the user-interest features and the associated parameter weights.

13. The system of claim 12, in which the user-interest features are based on a user-interest profile.

14. The system of claim 12, in which the user-interest features are learned.

15. The system of claim 14, in which the user-interest features are learned from a corpus of documents associated with at least one prior transaction.

16. The system of claim 15, in which the at least one prior transaction is at least one of:

search history, reading history; and

browsing history.

17. The system of claim 13, in which the parameter weights are determined stochastically and relevant user-interest features are determined by automatic feature selection.

18. The system of claim 13, in which the parameter weights are set manually.

19. The system of claim 13, in which the parameter weights are learned.

20. The system of claim 12, in which the parameter weights are learned from a corpus of documents associated with at least one prior transaction.

21. The system of claim 20, in which the at least one prior transaction is at least one of:

search history, reading history; and

browsing history.

22. The system of claim 13, in which the parameter weights are set by occurrences of features in topically related documents.

23. Computer readable storage medium comprising:

computer readable program code embodied on the computer readable storage medium, the computer readable program code usable to program a computer for determining user interests comprising the steps of;

determining user-interest features;

determining parameter weights for the user-interest features; and

determining a user-interest model based on the user-interest features and the parameter weights.

24. A carrier wave encoded to transmit a control program, useable to program a computer for determining user interests, to a device for executing the program, the control program comprising:

instructions for determining user-interest features;

instructions for determining parameter weights for the user-interest features; and

instructions for determining a user-interest model based on the user-interest features and the parameter weights.