OPEN PROFILE CONTENT IDENTIFICATION

• US 20080243780A1
• Filed: 03/30/2007
• Published: 10/02/2008
• Est. Priority Date: 03/30/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Datar, Mayur, Miller, Jason C., Rabii, Bahman, Tunguz-Zawislak, Tomasz J., Perez-Bergquist, Andres S., Harmsen, Jeremiah, Hochberg, Mike, Tung, Julie, Nance, Megan
• Granted Patent: US 7,730,017 B2
• Time in Patent Office: Days
• US Class Current: 707/3
• 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 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

Open profile data in a user profile, e.g., free-form fields in a user profile, are processed to identify interests and preferences of the user. The interests and preferences are utilized to identify categories associated with the user profile, and content items, e.g., advertisements, can be identified based on the categories.

Claims

1. A computer-implemented method, comprising:

identifying open profile data in one or more user profiles;

identifying categories defined by the open profile data; and

identifying one or more content items based on the identified categories.

2. The method of claim 1, wherein:

the one or more content items comprise advertisements.

3. The method of claim 2, wherein:

identifying open profile data in one or more user profiles comprises identifying open text fields in the one or more user profiles.

4. The method of claim 3, comprising:

natural language processing text stored in the open text fields to identify phrases; and

assigning weights to the phrases.

5. The method of claim 4, wherein:

identifying categories defined by the open profile data comprises identifying user interests based on the phrase weights.

6. The method of claim 4, comprising:

sentiment detecting the text stored in the open text field to identify user interests.

7. The method of claim 6, wherein:

identifying categories defined by the open profile data comprises identifying categories based on the phrase weights and the user interests.

8. The method of claim 7, wherein:

identifying categories defined by the open profile data comprises generating category clusters based on the phrase weights.

9. The method of claim 4, wherein:

identifying categories defined by the open profile data comprises discounting high frequency phrases.

10. The method of claim 4, comprising:

sentiment detecting the text stored in the open text field to identify user non-interests; and

discounting phrases associated with the user non-interests.

11. The method of claim 2, comprising:

classifying the categories according to category features; and

assigning labels to the classified categories.

12. The method of claim 1, wherein:

the user profiles comprises social network user profiles.

13. The method of claim 1, comprising:

serving the one or more identified content items to a user associated with the identified categories.

14. A computer-implemented method, comprising:

identifying free-form text data in a user profile;

extracting category indicia from the free-form text data; and

identifying one or more content items based on the identified category indicia.

15. The method of claim 14, wherein:

the one or more content items comprise advertisements.

16. The method of claim 15, wherein:

extracting category indicia from the free-form text data comprises;

natural language processing the free-form text data to identify phrases; and

assigning weights to the phrases.

17. The method of claim 16, wherein:

extracting category indicia from the free-form text data comprises identifying user interests based on the phrase weights.

18. The method of claim 16, comprising:

sentiment detecting the free-from text data to identify user interests.

19. The method of claim 18, wherein:

extracting category indicia from the free-form text data comprises identifying category indicia based on the phrase weights and the user interests.

20. A system, comprising:

a natural language processor configured to extract one or more phrases from free-from text data in a user profile and assign phrase weights to the extracted phrases;

a sentiment detection processor configured to identify user interests and non-interests from the free-from text data in the user profile; and

a category processor configured to associate labels with a user profile based on the extracted one or more phrases, assigned phrase weights, and the identified user interests and non-interests.

21. A computer-implemented method, comprising:

identifying open profile data in user profiles;

identifying categories defined by the open profile data; and

associating the identified categories with corresponding user profiles.