Open Profile Content Identification

• US 20100174726A1
• Filed: 03/18/2010
• Published: 07/08/2010
• 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 8,341,169 B2
• Time in Patent Office: Days
• US Class Current: 707/750
• 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 system comprising:

a natural language processor configured to identify phrases from free-form text data in a user profile, and assign weights to the phrases;

a sentiment detection processor configured to identify user interests and non-interests from the phrases; and

a category processor configured to associate one or more category labels with the user profile, each category label specifying a category, and the association being based on the phrases, the assigned weights, and the user interests and non-interests.

2. The system of claim 1, wherein:

the phrases include one or more noun phrases; and

the natural language processor is configured to identify one or more nouns and related adjectives in the one or more noun phrases.

3. The system of claim 2, wherein the natural language processor is configured to assign a weight to a noun phrase based on a number of nouns in the noun phrase.

4. The system of claim 3, wherein the natural language processor is configured to adjust the assigned weight based on a number of adjectives in the noun phrase.

5. The system of claim 1, wherein the sentiment detection processor is configured to identify one or more positive or negative verbs and related nouns in the one or more phrases.

6. The system of claim 5, wherein the sentiment detection processor is configured to identify one or more categories of interest or non-interest based on the one or more identified positive or negative verbs and related nouns.

7. The system of claim 6, wherein the category processor is configured to associate the one or more category labels based on the one or more identified categories of interest or non-interest.

8. A method performed by a data processing apparatus, comprising:

receiving profile data associated with a user account;

identifying phrases from free-form text data in the received profile data;

assigning weights to the phrases;

determining user interests and user non-interests from the phrases;

adjusting the weights based on the user interests and user non-interests; and

associating one or more category labels with the profile data based on the phrases and the adjusted weights assigned to the phrases.

9. The method of claim 8, further comprising targeting an advertisement based on the one or more associated category labels.

10. The method of claim 8, wherein identifying the phrases includes identifying psychographic information in the profile data.

11. The method of claim 8, wherein associating the one or more category labels includes associating the one or more category labels based on a phrase with a highest adjusted weight.

12. The method of claim 8, wherein assigning the weights includes assigning a value to each phrase.

13. The method of claim 12, wherein identifying the phrases includes identifying one or more nouns or adjectives in at least one identified phrase, the at least one identified phrase assigned with the value based on a number of nouns or adjectives in the at least one identified phrase.

14. The method of claim 12, wherein identifying the phrases includes identifying one or more keywords indicative of sentiments in each identified phrase.

15. The method of claim 14, wherein:

identifying the one or more keywords includes identifying interests and non-interests in relation to the one or more keywords in each identified phrase; and

associating the one or more category labels includes associating the one or more category labels based on the phrases, the adjusted weights, the interests and the non-interests.

16. The method of claim 14, wherein:

identifying the one or more keywords includes performing a polarity analysis on the one or more keywords to identify one or more positive or negative verbs and related nouns; and

assigning the value includes assigning the value based on the one or more identified positive or negative verbs and related nouns.

17. A system comprising:

a data processing apparatus; and

a memory in data communication with the data processing apparatus and storing instructions executable by the data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising;

receiving profile data associated with a user account;

identifying phrases from free-form text data in the received profile data;

assigning weights to the phrases;

determining user interests and user non-interests from the phrases;

adjusting the weights based on the user interests and user non-interests; and

associating one or more category labels with the profile data based on the phrases and the adjusted weights assigned to the phrases.

18. The system of claim 17, wherein the memory further includes instructions executable by the data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising:

receiving an advertisement based on the one or more associated categories.

19. The system of claim 17, wherein the phrases include one or more noun phrases;

and

wherein the instructions cause the data processing apparatus to identify one or more nouns and related adjectives in the one or more noun phrases.

20. The system of claim 17, wherein the instructions cause the data processing apparatus to identify one or more positive or negative verbs and related nouns in the phrases.