Method and system utilizing a personalized user model to develop a search request

• US 8,868,590 B1
• Filed: 11/17/2011
• Issued: 10/21/2014
• Est. Priority Date: 11/17/2011
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Donneau-Golencer, Thierry D.
• Primary Examiner(s): Wong, Leslie
• Application Number:
  US13/298,374
• Time in Patent Office: 1,069 Days
• Field of Search: 707/733, 707/748, 707/765, 707/999.005, 707/999.01
• US Class Current: 707/765
• CPC Class Codes: G06F 16/24578 using ranking
• 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 16/9032 Query formulation

Abstract

A method and system for developing a computer-executable query relating to a search request issued by a user includes determining whether a search term of the search request has a user-specific meaning, connotation, context, or association based on an analysis of electronic content associated with the user and/or an analysis of interactions of the user with electronic content that is accessible to the user through one or more computing devices. If the search term has a user-specific meaning, connotation, context, or association, the method and system can incorporate the user-specific meaning, connotation, context, or association into the search request and/or the computer-executable query.

Claims

1. A method, comprising:

maintaining, in an automated fashion, a user-specific profile comprising information relating to at least one user interaction with at least one electronic content through at least one computing device,

receiving a search request, the search request comprising at least one search term,

determining whether the at least one search term has an association with the information in the user-specific profile, and

if a search term has an association with the information in the user-specific profile;

determining user-specific semantic information relating to the search term based on the association of the search term with the information in the user-profile,

adding the user-specific semantic information to the search term,

formulating at least one computer-executable query based on the search request and based on the association of the search term with the information in the user-specific profile, the at least one computer-executable query comprising the user-specific semantic information associated with the search term,

formulating a first alternative version of the search request based on a first association of the search term with first information in the user-specific profile and formulating a second alternative version of the search request, and

executing a first computer-executable query based on the first alternative version of the search request to generate a first search result, executing a second computer-executable query based on the second alternative version of the search request to generate a second search result, and selecting one of the first and second search results.

2. The method of claim 1, comprising replacing the search term with at least one word relating to the association of the search term with the information in the user-specific profile.

3. The method of claim 1, comprising adding to the search request at least one word relating to the association of the search term with the information in the user-specific profile.

4. The method of claim 3, wherein the at least one word is added to either broaden or narrow the scope of the search request.

5. The method of claim 1, comprising conducting at least one of a natural language analysis, semantic analysis, topic analysis, heat map analysis, context analysis, and query history analysis of the at least one search term using the user-specific profile.

6. The method of claim 1, comprising formulating the second alternative version of the search request based on a second association of the search term with second information in the user-specific profile.

7. The method of claim 1, comprising outputting at least one of the alternate versions of the search request in a form that is at least one of user-perceptible, user-editable and user-selectable.

8. The method of claim 1, comprising analyzing a plurality of words in the user-specific profile, determining associations between or among the words, determining weights assigned to one or more of the words, and formulating the at least one computer-executable query based on at least one of:

a word in the user-specific profile, an association between or among words in the user-specific profile, and a weight assigned to one or more words in the user-specific profile.

9. The method of claim 1, comprising creating at least one alternate version of the search request comprising a user-specific meaning of at least one search term.

10. The method of claim 9, comprising selecting one of the alternate versions of the search request.

11. The method of claim 9, comprising outputting the at least one alternate version of the search request in a form that is at least one of user-perceptible, user-editable and user-selectable prior to the formulating of the at least one computer-executable query.

12. The method of claim 1, wherein the at least one search term comprises an acronym having a user-specific meaning, comprising determining the user-specific meaning of the acronym using the user-specific profile.

13. The method of claim 1, wherein the at least one search term comprises an abbreviation or truncated word having a user-specific meaning, comprising determining the user-specific meaning of the abbreviation or truncated word using the user-specific profile.

14. The method of claim 1, wherein the at least one search term comprises a proper noun having a user-specific meaning, comprising determining the user-specific meaning of the proper noun using the user-specific profile.

15. The method of claim 1, wherein the at least one search term comprises an unknown word, comprising accessing the user-specific profile to, in an automated fashion, resolve the unknown word prior to formulating the computer-executable query.

16. The method of claim 1, comprising accessing the user-specific profile to, in an automated fashion, associate at least one related word, topic, sub-topic, concept, context or connotation with the search term prior to formulating the at least one computer-executable query.

17. The method of claim 16, comprising, in an automated fashion, modifying the search request to include the at least one related word, topic, sub-topic, concept, context or connotation associated with the search term as the user is inputting the search request.

18. The method of claim 1, comprising executing the computer-executable query, evaluating the results of the executing of the query, and generating at least one alternate version of the search request based on the results of the executing of the query.

19. The method of claim 1, comprising monitoring at least one user interaction in response to the determining of whether the at least one search term has an association with the information in the user-specific profile or the formulating of the at least one computer-executable query, and updating at least one of the search request, the computer-executable query, and the user-specific profile based on the monitoring.

20. The method of claim 1, wherein the user-specific semantic information adds a user-specific meaning to the search term according to the user-specific profile, and wherein the method comprises incorporating the user-specific meaning of the search term into the at least one computer-executable query.

21. The method of claim 1, comprising, with the user-specific profile, determining a plurality of different possible user-specific semantic interpretations of the search term, selecting one of the user-specific semantic interpretations of the search term, incorporating the selected user-specific semantic interpretation of the search term into the at least one computer-executable query, and not incorporating the non-selected user-specific semantic interpretations of the search term into the at least one computer executable query.

22. At least one computer accessible medium comprising a plurality of instructions that in response to being executed, result in a computing device:

receiving a search request, the search request comprising at least one search term,

accessing a user-specific profile comprising words, associations between or among the words, and weights assigned to one or more of the words, the user-specific profile being created in an automated fashion as a result of an automated analysis of electronic content associated with a computing device user,

analyzing the at least one search term using the user-specific profile to interpret, correct, or augment the at least one search term by determining user-specific semantic information relating to the search term and associating the user-specific semantic information with the search term,

formulating a computer-executable query corresponding to the search request and based on a user-specific interpretation, correction or augmentation of the at least one search term, the computer-executable query comprising the user-specific semantic information associated with the search term,

formulating a first alternative version of the search request based on a first association of the search term with first information in the user-specific profile and formulating a second alternative version of the search request, and

executing a first computer-executable query based on the first alternative version of the search request to generate a first search result, executing a second computer-executable query based on the second alternative version of the search request to generate a second search result, and selecting one of the first and second search results.

23. The at least one computer accessible medium of claim 22, wherein the plurality of instructions results in the computing device:

receiving user input relating to at least one of the user-specific interpretation, correction or augmentation of the at least one search term, and

updating at least one of the search request, the computer-executable query, and the user-specific profile based on the user input.

24. A computing device comprising:

at least one processor, and

at least one memory device coupled to the at least one processor, the at least one memory device having stored therein a plurality of instructions that when executed by the at least one processor, cause the at least one processor to;

identify at least one search term of a search request,

access a database comprising words, associations between or among the words, and weights assigned to one or more of the words, wherein the words, associations, and weights in the database are derived from an automated analysis of electronic content and interactions associated with a computing device user,

determine at least one user-specific meaning of the at least one search term using the database,

formulate a computer-executable query corresponding to the search request and based on the user-specific meaning of the at least one search term,

formulate a first alternative version of the search request based on a first association of the search term with first information in the user-specific profile and formulate a second alternative version of the search request, and

execute a first computer-executable query based on the first alternative version of the search request to generate a first search result, execute a second computer-executable query based on the second alternative version of the search request to generate a second search result, and select one of the first and second search results.

25. The computing device of claim 24, wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

receive user input relating to the user-specific meaning, and

update at least one of the search request, the computer-executable query, and the database in response to the user input.