DETERMINING USER INTENT FROM QUERY PATTERNS

• US 20140149399A1
• Filed: 07/22/2010
• Published: 05/29/2014
• Est. Priority Date: 07/22/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kurzion, Yair
• Granted Patent: US 8,868,548 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods, systems and program products for identifying user intent from query patterns including, in one implementation, a method including identifying a current query including a query term, and obtaining search results responsive to the current query. Each search result identifying a document associated with a score indicating relevance. The method includes associating an intent with the session based on submission of a query containing a refining term, where each refining term was previously submitted with different unique queries. The method includes identifying prior sessions, where each prior session includes a query that matches the current query, and each prior session includes a query that contains the refining term. The method includes identifying a document selected more frequently in the prior sessions than by a general population and modifying the scores of the document in the search results. The method also includes ranking the search results based on the scores.

Claims

1. A computer-implemented method, comprising:

identifying a query submission in a session, the query including one or more query terms, and obtaining a plurality of search results responsive to the query, each search result identifying a respective document that is associated with a respective score indicating a relevance of the document to the query;

associating an intent with the session based on the one or more query terms including an intent refining query term, wherein the intent refining query term was previously submitted with a plurality of different queries a quantity of times that exceeds a threshold;

identifying one or more of the respective documents wherein each of the identified documents was selected by users in a plurality of sessions associated with the intent with a higher or lower frequency then when the document was selected by users in a plurality of sessions not associated with the intent;

for each of the identified documents, modifying the respective score of the document based on a confidence value wherein the confidence value is based on a quantity of the plurality of sessions associated with the intent; and

ranking the plurality of search results based on the respective scores, including the one or more modified respective scores.

3. The method of claim 1 comprising associating a different second intent with the session based on the one or more query terms including a second intent refining query term, wherein the second intent refining query term was previously submitted with a plurality of different queries a second quantity of times that is beyond a second threshold.

5. The method of claim 3 comprising:

identifying one or more second documents of the documents wherein each of the second documents was selected by users in a plurality of sessions associated with the second intent with a higher or lower frequency then when the document was selected by users in a plurality of sessions not associated with the second intent; and

for each of she second documents modifying the respective score of the second document based on a second confidence value wherein the second confidence value is based on a quantity of the plurality of sessions associated with the second intent.

6. The method of claim 1 wherein modifying the respective score of the document based on the confidence value comprises:

increasing the respective score if the document was selected by users in the plurality of sessions associated with the intent with a higher frequency then when the document was selected by users in the plurality of sessions not associated with the intent; and

decreasing the respective score if the document was selected by users in the plurality of sessions associated with the intent with a lower frequency then when the document was selected by users in the plurality of sessions not associated with the intent.

9. The method of claim 1 wherein the threshold is based a distribution of a set of queries according to a respective quantity of times that each query in the set of queries was submitted in a plurality of sessions.

10. The method of claim 1 wherein each session is defined by a period of time.

11. The method of claim 9 wherein the threshold is based on a standard deviation.

2. (canceled)

4. (canceled)

7. (canceled)

8. (canceled)

12. (canceled)

13. A computer storage device encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

identifying a query submission in a session, the query including one or more query terms, and obtaining a plurality of search results responsive to the query, each search result identifying a respective document that is associated with a respective score indicating a relevance of the document to the query;

associating an intent with the session based on the one or more query terms including an intent refining query term, wherein the intent refining query term was previously submitted with a plurality of different queries a quantity of times that exceeds a threshold;

identifying one or more of the respective documents wherein each of the identified documents was selected buy users in a plurality of sessions associated with the intent with a higher or lower frequency than when the document was selected by users in a plurality of sessions not associated with the intent;

for each of the identified documents, modifying the respective score of the documents based on a confidence value wherein the confidence value is based on a quantity of the plurality of sessions associated with the intent; and

ranking the plurality of search results based on the respective scores, including the one or more modified respective scores.

15. The computer storage device of claim 13 wherein the operations further comprise associating a different second intent with the session based on the one or more query terms including a second intent refining query term, wherein second intent refining query term was previously submitted with a plurality of different queries a second quantity of items that is beyond a second threshold.

17. The computer storage device of claim 15, wherein the operations comprising:

identifying one or more second documents of the documents wherein each of the second documents was selected by users in a plurality of sessions associated with the second intent with a higher or lower frequency than when the document was selected by users in a plurality of sessions not associated with the second intent; and

for each of the second documents, modifying the respective score of the second document based on a second confidence value wherein the second confidence value is based on a quantity of the plurality of sessions associated with the second intent.

18. The computer storage device of claim 17 wherein modifying the respective score of the document based on the confidence value comprises:

increasing the respective score if the document was selected by users in the plurality of sessions associated with the intent with a higher frequency then when the document was selected by users in the plurality of sessions not associated with the intent; and

decreasing the respective score if the document was selected by users in the plurality of sessions associated with the intent with a lower frequency then when the documents was selected by users in the plurality of sessions not associated with the intent.

21. The computer storage device of claim 13 wherein the threshold is based a distribution of a set of queries according to a respective quantity of times that each query in the set of queries was submitted in a plurality of sessions.

22. The computer storage device of claim 13 wherein each sessions is defined by a period of time.

23. The computer storage device of claim 21, wherein the threshold is based on a standard deviation.

14. (canceled)

16. (canceled)

19. (canceled)

20. (canceled)

24. (canceled)

25. A system comprising:

one or more computers; and

;

a computer-readable device coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising;

identifying a query submission in a session, the query including one or more query terms, and obtaining a plurality of search results responsive to the query, each search result identifying a respective document that is associated with a respective score indicating a relevance of the document to the query;

associating an intent with the session based on the one or more query terms including an intent refining query term, wherein the intent refining query term was previously submitted with a plurality of different queries a quantity of times that exceeds a threshold;

identify one or more of the respective documents wherein each of the identified documents was selected by users in a plurality of sessions associated with the intent with a higher or lower frequency then when the document was selected by users in a plurality of sessions not associated with the intent;

for each of the identified documents modifying the respective score of the document based on a confidence value wherein the confidence value is based on a quantity of the plurality of sessions associated with the intent; and

ranking the plurality of search results based on the respective scores, including the one or more modified respective scores.

27. The system of claim 25 wherein the operations further comprise associating a different second intent with the session based on the one or more query terms including a second intent refining query term, wherein the second intent refining query term was previously submitted with a plurality of different queries a second quantity of Times that is beyond a second threshold.

29. The system of claim 27, wherein the operations further comprise:

identifying one or more second documents of the documents wherein each of the second documents was selected by users in a plurality of sessions associated with the second intent with a higher or lower frequency then when the document was selected by users in a plurality of sessions not associated with the second intent; and

for each of the second documents, modifying the respective score of the second document based on the second confidence value wherein the second confidence value is based on a quantity of the plurality of sessions associated with the second intent.

30. The system of claim 25, wherein modifying the respective score of the document based on the confidence value comprises:

increasing the respective score if the document was selected by user in the plurality of sessions associated with the intent with a higher frequency then when the document was selected by users in the plurality of sessions not associated with the intent; and

decreasing the respective score if the document was selected by users in the plurality of Sessions associated with the intent with a lower frequency then when the document was selected by users in the plurality of sessions not associated with the intent.

33. The system of claim 25 wherein the threshold is based a distribution of a set of queries according to a respective quantity of times that each query in the set of queries was submitted in a plurality of sessions.

34. The system of claim 25 wherein each session is defined by a period of time.

35. The system of claim 33, wherein the threshold is based on a standard deviation.

26. (canceled)

28. (canceled)

31. (canceled)

32. (canceled)

36. (canceled)