System and method for user behavior modeling

• US 8,639,636 B2
• Filed: 08/15/2008
• Issued: 01/28/2014
• Est. Priority Date: 08/15/2008
• Status: Active Grant

• Current Assignee: AT&T Labs Incorporated (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gibbon, David C., Basso, Andrea, Spatscheck, Oliver
• Primary Examiner(s): Rivas, Omar Fernandez
• Assistant Examiner(s): MOLL, NITHYA JANAKIRAMAN
• Application Number:
  US12/192,748
• Publication Number:
  US 20100042387A1
• Time in Patent Office: 1,992 Days
• Field of Search: 703/6
• US Class Current: 706/6
• 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 comprising:

tracking user behavior across multiple modalities for interacting with a device;

storing representations of the user behavior in a log as descriptors, each descriptor associated with a modality, the descriptors comprising a first descriptor associated with a first modality and a second descriptor associated with a second modality, wherein the first modality and the second modality are distinct modalities;

normalizing the descriptors, wherein the first descriptor and the second descriptor are normalized based on;

(1) the first modality, (2) the second modality, (3) the device, and (4) a format associated with the device, to yield normalized descriptors;

merging the normalized descriptors into a unified click stream;

generating a behavioral model by analyzing the unified click stream; and

upon receiving user input associated with modifying a presentation of search results associated with a search, dynamically modifying the presentation by using the behavioral model to generate the search results.

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

3. The method of claim 1, wherein the log is stored in one of a local storage device, a network, and in a combination of both the local storage device and the network.

4. The method of claim 1, wherein the representations of the user behavior comprises one of video content, audio content, buttons pressed on a remote control, buttons pressed on a 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 the user behavior is filtered according to relevance.

6. The method of claim 1, further comprising:

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

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

8. The method of claim 1, wherein modifying the presentation further comprises one of adding new content, editing existing content, and preventing certain content from being displayed.

9. The method of claim 1, wherein the presentation further comprises a web page modified to provide user-dependent links based on the behavioral model.

10. The method of claim 1, further comprising receiving a user selection indicating which portion of the behavioral model to incorporate into the search.

11. The method of claim 1, further comprising receiving a user selection indicating a weight to assign the behavioral model in a search algorithm.

12. The method of claim 1, further comprising receiving a user selection indicating alteration of one of the descriptors and the click stream to generate a new behavioral model.

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

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

15. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, perform operations comprising;

tracking user behavior across multiple modalities for interacting with a device;

storing representations of the user behavior in a log as descriptors, each descriptor associated with a modality, the descriptors comprising a first descriptor associated with a first modality and a second descriptor associated with a second modality, wherein the first modality and the second modality are distinct modalities;

normalizing the descriptors, wherein the first descriptor and the second descriptor are normalized based on;

(1) the first modality, (2) the second modality, (3) the device, and (4) a format associated with the device, to yield normalized descriptors;

merging the normalized descriptors into a unified click stream;

generating a behavioral model by analyzing the unified click stream; and

upon receiving user input associated with modifying a presentation of search results associated with a search, dynamically modifying the presentation by using the behavioral model to generate the search results.

16. The system of claim 15, wherein normalizing the descriptors comprises abstracting a high-level behavioral concept away from details of a device.

17. The system of claim 15, wherein the log is stored in one of a local storage device, a network, and in a combination of both the local storage device and the network.

18. The system of claim 15, wherein the representations of the user behavior comprises one of video content, audio content, buttons pressed on a remote control, buttons pressed on a 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.

19. The system of claim 15, wherein the user behavior is filtered according to relevance.

20. The system of claim 15, the computer-readable storage medium having additional instructions stored which result in the operations further comprising:

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

21. The system of claim 15, wherein the user behavior is in a synthetic environment.

22. The system of claim 15, wherein modifying the presentation further comprises one of adding new content, editing existing content, and preventing certain content from being displayed.

23. The system of claim 15, wherein the presentation further comprises a web page modified to provide user-dependent links based on the behavioral model.

24. The system of claim 15, the computer-readable storage medium having additional instructions stored which result in the operations further comprising receiving a user selection indicating which portion of the behavioral model to incorporate into the search.

25. The system of claim 15, the computer-readable storage medium having additional instructions stored which result in the operations further comprising receiving a user selection indicating a weight to assign the behavioral model in a search algorithm.

26. The system of claim 15, the computer-readable storage medium having additional instructions stored which result in the operations further comprising receiving a user selection indicating alteration of one of the descriptors and the click stream to generate a new behavioral model.

27. The system of claim 15, wherein multiple users'"'"' behavior is tracked as a group.

28. The system of claim 15, wherein the behavioral model is updated by pruning unneeded descriptors.

29. A computer-readable storage device having instructions stored which, when executed on a computing device, cause the computing device to perform operations comprising:

tracking user behavior across multiple modalities for interacting with a device;

storing representations of the user behavior in a log as descriptors, each descriptor associated with a modality, the descriptors comprising a first descriptor associated with a first modality and a second descriptor associated with a second modality, wherein the first modality and the second modality are distinct modalities;

normalizing the descriptors, wherein the first descriptor and the second descriptor are normalized based on;

(1) the first modality, (2) the second modality, (3) the device, and (4) a format associated with the device, to yield normalized descriptors;

merging the normalized descriptors into a unified click stream;

generating a behavioral model by analyzing the unified click stream; and

upon receiving user input associated with modifying a presentation of search results associated with a search, dynamically modifying the presentation by using the behavioral model to generate the search results.

30. The computer-readable storage device of claim 29, wherein normalizing the descriptors comprises abstracting a high-level behavioral concept away from details of a device.

31. The computer-readable storage device of claim 29, wherein the log is stored in one of a local storage device, a network, and in a combination of both the local storage device and the network.

32. The computer-readable storage device of claim 29, wherein representations of user behavior comprises one of video content, audio content, buttons pressed on a remote control, buttons pressed on a 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.

33. The computer-readable storage device of claim 29, wherein user behavior is filtered according to relevance.

34. The computer-readable storage device of claim 29, the computer-readable storage device having additional instructions stored which result in the operations further comprising:

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

35. The computer-readable storage device of claim 29, wherein the user behavior is in a synthetic environment.

36. The computer-readable storage device of claim 29, wherein modifying the presentation further comprises one of adding new content, editing existing content, and preventing certain content from being displayed.

37. The computer-readable storage device of claim 29, wherein the presentation further comprises a web page modified to provide user-dependent links based on the behavioral model.

38. The computer-readable storage device of claim 29, the computer-readable storage device having additional instructions stored which result in the operations further comprising receiving a user selection indicating which portion of the behavioral model to incorporate into the search.

39. The computer-readable storage device of claim 29, the computer-readable storage device having additional instructions stored which result in the operations further comprising receiving a user selection indicating a weight to assign the behavioral model in a search algorithm.

40. The computer-readable storage device of claim 29, the computer-readable storage device having additional instructions stored which result in the operations further comprising receiving a user selection indicating alteration of one of the descriptors the click stream to generate a new behavioral model.

41. The computer-readable storage device of claim 29, wherein multiple users'"'"' behavior is tracked as a group.

42. The computer-readable storage device of claim 29, wherein the behavioral model is updated by pruning unneeded descriptors.