Personalization of Web Search Results Using Term, Category, and Link-Based User Profiles

• US 20130282713A1
• Filed: 01/07/2013
• Published: 10/24/2013
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Stephen R. Lawrence
• Inventors: Lawrence, Stephen R.
• Granted Patent: US 9,298,777 B2
• Time in Patent Office: Days
• US Class Current: 707/732
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

A system and method for creating a user profile and for using the user profile to order search results returned by a search engine. The user profile is based on search queries submitted by a user, the user'"'"'s specific interaction with the documents identified by the search engine and personal information provided by the user. Terms for the user profile may be selected from the documents accessed by the user by performing paragraph sampling or context analysis. Generic scores associated with the search results are modulated by the user profile to measure their relevance to a user'"'"'s preference and interest. The search results are re-ordered accordingly so that the most relevant results appear on the top of the list. User profiles can be created and/or stored on the client side or server side of a client-server network environment.

Claims

1. A computer-implemented method, comprising:

at a system having one or more processors and memory storing programs executed by the one or more processors;

accessing a user profile for a user;

receiving a search query from the user;

obtaining search results identifying a set of search result documents responsive to the search query, each document being associated with a generic score that is user independent;

determining a personalized score for each document, of at least a subset of the set of search result documents, in accordance with the user profile;

determining a final score for each document in at least said subset of the set of search result documents as a function of the personalized score for the document, the generic score associated with the document, and a confidence score, the confidence score accounting for one or more of;

quantity of information acquired about the user, how closely the search query matches the user profile, and age of the user profile;

providing, in accordance with the final scores, results identifying at least a subset of the set of search result documents to a client system associated with the user; and

updating the user profile as a function of search queries received from the user and documents selected by the user from search results provided to the user in response to the search queries.

2. The method of claim 1, the method including:

ranking the subset of the set of search result documents according to their final scores.

3. The method of claim 1, wherein the user profile comprises information about terms, each term associated with a weight indicating importance of the term to the user.

4. The method of claim 1, wherein the user profile comprises information about categories, each category associated with a weight indicating a correlation between search preferences of the user and the category.

5. The method of claim 1, wherein the user profile comprises links, each link associated with a weight indicating relevance of the link to search preferences of the user.

6. The method of claim 1, wherein updating the user profile comprises applying context patterns to identify context for important terms in documents selected by the user.

7. The method of claim 6, wherein the context patterns comprise prefix and postfix patterns.

8. The method of claim 6, the method including associating weights with the context patterns, wherein the weights can be recalibrated.

9. A search engine system, comprising:

one or more central processing units for executing programs;

an interface for receiving information; and

a search engine module executable by the one or more central processing units, the module comprising;

instructions for accessing a user profile for a user;

instructions for receiving a search query from the user;

instructions for obtaining search results identifying a set of search result documents responsive to the search query, each document being associated with a generic score that is user independent;

instructions for determining a personalized score for each document, of at least a subset of the set of search result documents, in accordance with the user profile;

instructions for determining a final score for each document in at least said subset of the set of search result documents as a function of the personalized score for the document, the generic score associated with the document, and a confidence score, the confidence score accounting for one or more of;

quantity of information acquired about the user, how closely the search query matches the user profile, and age of the user profile;

instructions for providing, in accordance with the final scores, results identifying at least a subset of the set of search result documents to a client system associated with the user; and

instructions for updating the user profile as a function of search queries received from the user and documents selected by the user from search results provided to the user in response to the search queries.

10. The search engine system of claim 9, the search engine module including:

instructions for ranking the subset of the set of search result documents according to their final scores.

11. The search engine system of claim 9, wherein the user profile comprises information about terms, each term associated with a weight indicating importance of the term to the user.

12. The search engine system of claim 9, wherein the user profile comprises information about categories, each category associated with a weight indicating a correlation between search preferences of the user and the category.

13. The search engine system of claim 9, wherein the user profile comprises links, each link associated with a weight indicating relevance of the link to search preferences of the user.

14. The search engine system of claim 9, wherein updating the user profile comprises applying context patterns to identify context for important terms in documents selected by the user.

15. The search engine system of claim 14, wherein the context patterns comprise prefix and postfix patterns.

16. The search engine system of claim 14, the method including associating weights with the context patterns, wherein the weights can be recalibrated.

17. A non-transitory computer readable storage medium storing one or more programs for execution by one or more processors, the one or more programs comprising:

instructions for accessing a user profile for a user;

instructions for receiving a search query from the user;

instructions for obtaining search results identifying a set of search result documents responsive to the search query, each document being associated with a generic score that is user independent;

instructions for determining a personalized score for each document, of at least a subset of the set of search result documents, in accordance with the user profile;

instructions for determining a final score for each document in at least said subset of the set of search result documents as a function of the personalized score for the document, the generic score associated with the document, and a confidence score, the confidence score accounting for one or more of;

quantity of information acquired about the user, how closely the search query matches the user profile, and age of the user profile;

instructions for providing, in accordance with the final scores, results identifying at least a subset of the set of search result documents to a client system associated with the user; and

instructions for updating the user profile as a function of search queries received from the user and documents selected by the user from search results provided to the user in response to the search queries.

18. The non-transitory computer readable storage medium of claim 17, the search engine module including:

instructions for ranking the subset of the set of search result documents according to their final scores.

19. The non-transitory computer readable storage medium of claim 17, wherein the user profile comprises information about terms, each term associated with a weight indicating importance of the term to the user.

20. The non-transitory computer readable storage medium of claim 17, wherein the user profile comprises information about categories, each category associated with a weight indicating a correlation between search preferences of the user and the category.

21. The non-transitory computer readable storage medium of claim 17, wherein the user profile comprises links, each link associated with a weight indicating relevance of the link to search preferences of the user.

22. The non-transitory computer readable storage medium of claim 17, wherein updating the user profile comprises applying context patterns to identify context for important terms in documents selected by the user.

23. The non-transitory computer readable storage medium of claim 22, wherein the context patterns comprise prefix and postfix patterns.

24. The non-transitory computer readable storage medium of claim 22, the method including associating weights with the context patterns, wherein the weights can be recalibrated.