SYSTEM AND METHOD FOR USER BEHAVIOR MODELING

• US 20100042387A1
• Filed: 08/15/2008
• Published: 02/18/2010
• Est. Priority Date: 08/15/2008
• Status: Active Grant

• Current Assignee: AT&T Labs Incorporated (AT&T, Inc.)
• Original Assignee: AT&T Labs Incorporated (AT&T, Inc.)
• Inventors: Spatscheck, Oliver, Basso, Andrea, Gibbon, David C.
• Granted Patent: US 8,639,636 B2
• Time in Patent Office: Days
• US Class Current: 703/6
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Disclosed herein are systems, methods, and computer readable-media for contextual adaptive advertising. The method for contextual adaptive advertising comprises tracking user behavior across multiple modalities or devices, storing one or more representations of user behavior in a log as descriptors, normalizing the descriptors, merging the normalized descriptors into a unified click or interactive stream, and generating a behavioral model by analyzing the click or interactive stream.

Claims

1. A method of user behavioral modeling, the method comprising:

tracking user behavior across multiple modalities or devices;

storing one or more representations of user behavior in a log as descriptors;

normalizing the descriptors;

merging the normalized descriptors into a unified click stream; and

generating a behavioral model by analyzing the click stream.

2. The method of claim 1, wherein normalizing the descriptors includes abstracting a high-level behavioral concept away from the details of a device.

3. The method of claim 1, wherein the log is stored locally, in a network, or in some combination of both.

4. The method of claim 1, wherein representations of user behavior includes at least one of video content, audio content, buttons pressed on a remote control or gamepad, clicks on a mouse, characters typed on a keyboard, IP Multimedia Subsystem traffic, meta-data, haptic input, biometric tracking, and timing, frequency, and location of inputs.

5. The method of claim 1, wherein user behavior is filtered or sorted according to relevance.

6. The method of claim 1, the method further comprising:

extrapolating a contextual most-desired next instantiation by synthesizing or suggesting media content based the behavioral model.

7. The method of claim 1, wherein the user behavior is in a synthetic or alternative environment.

8. The method of claim 1, wherein a media presentation is modified based on the behavioral model.

9. The method of claim 8, wherein modifying the media presentation is one or more of adding new content, editing existing content, or preventing certain content from being displayed.

10. The method of claim 8, wherein the media presentation is a web page which is modified to provide user-dependent links based on the behavioral model.

11. The method of claim 8, wherein the media presentation is a search engine and associated search results.

12. The method of claim 11, wherein a user selects whether or not to incorporate the behavioral model into a search.

13. The method of claim 11, wherein a user selects which portion of the behavioral model to incorporate into a search.

14. The method of claim 11, wherein a user selects a weight to assign the behavioral model in a search algorithm.

15. The method of claim 1, wherein a user alters the descriptors or click stream to generate a new behavioral model.

16. The method of claim 1, wherein multiple users'"'"' behavior is tracked as a group.

17. The method of claim 1, wherein the behavioral model is updated by pruning unneeded descriptors.

18. A system for user behavioral modeling, the system comprising:

a module configure to track user behavior across multiple modalities or devices;

a module configure to store one or more representations of user behavior in a log as descriptors;

a module configure to normalize the descriptors;

a module configure to merge the normalized descriptors into a unified click stream; and

a module configure to generate a behavioral model by analyzing the click stream.

19. The system of claim 18, wherein normalizing the descriptors includes abstracting a high-level behavioral concept away from the details of a device.

20. The system of claim 18, wherein the log is stored locally, in a network, or in some combination of both.

21. The system of claim 18, wherein representations of user behavior includes at least one of video content, audio content, buttons pressed on a remote control or gamepad, clicks on a mouse, characters typed on a keyboard, IP Multimedia Subsystem traffic, meta-data, haptic input, biometric tracking, and timing, frequency, and location of inputs.

22. The system of claim 18, wherein user behavior is filtered or sorted according to relevance.

23. The system of claim 18, the system further comprising:

a module configured to extrapolate a contextual most-desired next instantiation by synthesizing or suggesting media content based the behavioral model.

24. The system of claim 18, wherein the user behavior is in a synthetic or alternative environment.

25. The system of claim 18, wherein a media presentation is modified based on the behavioral model.

26. The system of claim 25, wherein modifying the media presentation is one or more of adding new content, editing existing content, or preventing certain content from being displayed.

27. The system of claim 25, wherein the media presentation is a web page which is modified to provide user-dependent links based on the behavioral model.

28. The system of claim 25, wherein the media presentation is a search engine and associated search results.

29. The system of claim 28, wherein a user selects whether or not to incorporate the behavioral model into a search.

30. The system of claim 28, wherein a user selects which portion of the behavioral model to incorporate into a search.

31. The system of claim 28, wherein a user selects a weight to assign the behavioral model in a search algorithm.

32. The system of claim 18, wherein a user alters the descriptors or click stream to generate a new behavioral model.

33. The system of claim 18, wherein multiple users'"'"' behavior is tracked as a group.

34. The system of claim 18, wherein the behavioral model is updated by pruning unneeded descriptors.

35. A computer-readable medium storing a computer program having instructions for user behavioral modeling, the instructions comprising:

tracking user behavior across multiple modalities or devices;

storing one or more representations of user behavior in a log as descriptors;

normalizing the descriptors;

merging the normalized descriptors into a unified click stream; and

generating a behavioral model by analyzing the click stream.

36. The computer-readable medium of claim 35, wherein normalizing the descriptors includes abstracting a high-level behavioral concept away from the details of a device.

37. The computer-readable medium of claim 35, wherein the log is stored locally, in a network, or in some combination of both.

38. The computer-readable medium of claim 35, wherein representations of user behavior includes at least one of video content, audio content, buttons pressed on a remote control or gamepad, clicks on a mouse, characters typed on a keyboard, IP Multimedia Subsystem traffic, meta-data, haptic input, biometric tracking, and timing, frequency, and location of inputs.

39. The computer-readable medium of claim 35, wherein user behavior is filtered or sorted according to relevance.

40. The computer-readable medium of claim 35, the instructions further comprising:

extrapolating a contextual most-desired next instantiation by synthesizing or suggesting media content based the behavioral model.

41. The computer-readable medium of claim 35, wherein the user behavior is in a synthetic or alternative environment.

42. The computer-readable medium of claim 35, wherein a media presentation is modified based on the behavioral model.

43. The computer-readable medium of claim 42, wherein modifying the media presentation is one or more of adding new content, editing existing content, or preventing certain content from being displayed.

44. The computer-readable medium of claim 42, wherein the media presentation is a web page which is modified to provide user-dependent links based on the behavioral model.

45. The computer-readable medium of claim 42, wherein the media presentation is a search engine and associated search results.

46. The computer-readable medium of claim 45, wherein a user selects whether or not to incorporate the behavioral model into a search.

47. The computer-readable medium of claim 45, wherein a user selects which portion of the behavioral model to incorporate into a search.

48. The computer-readable medium of claim 45, wherein a user selects a weight to assign the behavioral model in a search algorithm.

49. The computer-readable medium of claim 35, wherein a user alters the descriptors or click stream to generate a new behavioral model.

50. The computer-readable medium of claim 35, wherein multiple users'"'"' behavior is tracked as a group.

51. The computer-readable medium of claim 35, wherein the behavioral model is updated by pruning unneeded descriptors.