Model for generating user profiles in a behavioral targeting system

• US 20070239518A1
• Filed: 03/29/2006
• Published: 10/11/2007
• Est. Priority Date: 03/29/2006
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Yin, Hongfeng, Lin, Long-Ji, Koran, Joshua, Chung, Christina
• Granted Patent: US 7,809,740 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A behavioral targeting system determines user profiles from online activity. The system includes a plurality of models that define parameters for determining a user profile score. Event information, which comprises on-line activity of the user, is received at an entity. To generate a user profile score, a model is selected. The model comprises recency, intensity and frequency dimension parameters. The behavioral targeting system generates a user profile score for a target objective, such as brand advertising or direct response advertising. The parameters from the model are applied to generate the user profile score in a category. The behavioral targeting system has application for use in ad serving to on-line users.

Claims

1. A method for determining user profiles from online activity, said method comprising:

storing a plurality of weight parameters at an entity, wherein said weight parameters at least partially define a model to generate a user profile score;

receiving, at said entity, event information from at least one event, wherein said event comprises on-line activity between said user and said entity;

selecting at least one weight parameter; and

generating at least one user profile score by applying said weight parameter to said user event information.

2. The method as set forth in claim 1, wherein selecting at least one weight parameter to generate a user profile score comprises selecting at least one weight parameter based on a topic of said event information.

3. The method as set forth in claim 1, wherein selecting at least one weight parameter to generate a user profile score comprises selecting at least one weight parameter based on a type of said event.

4. The method as set forth in claim 1, wherein selecting at least one weight parameter to generate a user score comprises selecting at least one recency weight parameter that provides input to said user profile score based on how recent said user event information occurred.

5. The method as set forth in claim 1, wherein selecting at least one weight parameter comprises selecting intensity dimension parameters that provides input to said user profile score based on effectiveness of said user event information to predict user interest in said category.

6. The method as set forth in claim 1, wherein selecting at least one weight parameter comprises selecting frequency dimension parameters that provide input to said user profile score based on frequency of occurrence of said user event information.

7. The method as set forth in claim 1, further comprising serving an advertisement to said user based on said user profile score.

8. A system for determining user profiles from online activity, said system comprising:

storage for storing a plurality of weight parameters at an entity, wherein said weight parameters at least partially define a model to generate a user profile score; and

at least one server, coupled to said storage, for receiving event information for at least one event, wherein said event comprises on-line activity between said user and said entity, and for generating at least one user profile score by applying at least one weight parameter to said user event information.

9. The system as set forth in claim 8, wherein said weight parameter comprises a weight parameter based on a topic of said event information.

10. The system as set forth in claim 8, wherein said weight parameter comprises a weight parameter based on a type of said event.

11. The system as set forth in claim 8, wherein said weight parameter comprises a recency weight parameter that provides input to said user profile score based on how recent said user event information occurred.

12. The system as set forth in claim 8, wherein said weight parameter comprises an intensity dimension parameter that provides input to said user profile score based on effectiveness of said user event information to predict user interest in said category.

13. The system as set forth in claim 8, wherein said weight parameter comprises a frequency dimension parameters that provide input to said user profile score based on frequency of occurrence of said user event information.

14. A computer readable medium comprising a set of instructions which, when executed by a computer, cause the computer to determine user profiles from online activity, said instructions for:

storing a plurality of weight parameters at an entity, wherein said weight parameters at least partially define a model to generate a user profile score;

receiving, at said entity, event information from at least one event, wherein said event comprises on-line activity between said user and said entity;

selecting at least one weight parameter; and

generating at least one user profile score by applying said weight parameter to said user event information.

15. The computer readable medium as set forth in claim 14, wherein selecting at least one weight parameter to generate a user profile score comprises selecting at least one weight parameter based on a topic of said event information.

16. The computer readable medium as set forth in claim 14, wherein selecting at least one weight parameter to generate a user profile score comprises selecting at least one weight parameter based on a type of said event.

17. The computer readable medium as set forth in claim 14, wherein selecting at least one weight parameter to generate a user score comprises selecting at least one recency weight parameter that provides input to said user profile score based on how recent said user event information occurred.

18. The computer readable medium as set forth in claim 14, wherein selecting at least one weight parameter comprises selecting intensity dimension parameters that provides input to said user profile score based on effectiveness of said user event information to predict user interest in said category.

19. The computer readable medium as set forth in claim 14, wherein selecting at least one weight parameter comprises selecting frequency dimension parameters that provide input to said user profile score based on frequency of occurrence of said user event information.

20. The computer readable medium as set forth in claim 14, further comprising serving an advertisement to said user based on said user profile score.