Fake skip evaluation of synonym rules

• US 8,909,627 B1
• Filed: 10/26/2012
• Issued: 12/09/2014
• Est. Priority Date: 11/30/2011
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Popovici, Dan, Koo, Terry Yang-Hoe
• Primary Examiner(s): Leroux, Etienne
• Application Number:
  US13/661,734
• Time in Patent Office: 774 Days
• Field of Search: 707/769, 707/723
• US Class Current: 707/723
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/3349 Reuse of stored results of previous queries

Abstract

Methods, systems, and apparatus, including computer programs are encoded on a computer storage medium, for fake skip evaluation of synonyms. In one aspect, a method includes determining, using query log data, that a particular search result selected by a user includes a query term included in an initial search query and a particular synonym that was generated for the query term using a particular synonym rule. The particular search result is selected by the user from among search results that were generated using an initial search query and one or more revised search queries that include the particular synonym. The method further includes determining, using the query log data, that a first search result is ranked above the particular search result, and includes the particular synonym for the query term. In response to these determinations, a fake skip count is incremented for the synonym rule that corresponds to the particular synonym.

Claims

1. A computer-implemented method comprising:

determining, using data associated with search queries submitted by past users of a search engine, that a particular search result selected by a particular, past user of the search engine includes a query term included in an initial search query, and a particular synonym that was generated for the query term included in the initial search query using a particular synonym rule, wherein the data associated with the search queries indicates that the particular search result was selected by the particular, past user of the search engine from among multiple search results that were generated by the search engine using the initial search query and one or more revised search queries that include the particular synonym for the query term;

determining, using the data associated with the search queries, that a different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine;

in response to determining that (i) the particular search result selected by the particular, past user of the search engine includes the query term included in the initial search query, and the particular synonym for the query term, and (ii) the different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine, incrementing a particular type of skip count for the particular synonym rule; and

determining whether to revise a subsequently received search query that includes the query term included in the initial search query, to include the particular synonym for the query term, based at least on the particular type of skip count for the particular synonym rule.

2. The method of claim 1, comprising assigning a score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule.

3. The method of claim 2, wherein assigning the score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule comprises assigning the score to the particular synonym rule based on the particular type of skip count for the particular synonym rule, a click count for the particular synonym rule, and a different type of skip count for the particular synonym rule.

4. The method of claim 3, comprising associating a first weight with the particular type of skip count for the particular synonym rule, a second weight with the different type of skip count for the particular synonym rule, and a third weight with the click count for the particular synonym rule.

5. The method of claim 2, further comprising:

determining that the score assigned to the particular synonym rule does not meet a threshold; and

removing the particular synonym rule from a set of synonym rules used to generate revised search queries based on determining that the score assigned to the particular synonym rule does not meet the threshold.

6. The method of claim 1, wherein the different search result includes the query term included in the initial search query.

7. The method of claim 1, comprising determining, using the data associated with the search queries, that the particular synonym for the query term was generated for the query term using a synonym rule associated with a particular query context, and wherein incrementing the particular type of skip count for the particular synonym rule comprises incrementing the particular type of skip count for the synonym rule associated with the particular query context.

8. The method of claim 3, wherein the score assigned to the particular synonym rule satisfies:

9. A computer-readable storage device having stored thereon instructions, which, when executed by a computer, cause the computer to perform operations comprising:

determining, using data associated with search queries submitted by past users of a search engine, that a particular search result selected by a particular, past user of the search engine includes a query term included in an initial search query, and a particular synonym that was generated for the query term included in the initial search query using a particular synonym rule, wherein the data associated with the search queries indicates that the particular search result was selected by the particular, past user of the search engine from among multiple search results that were generated by the search engine using the initial search query and one or more revised search queries that include the particular synonym for the query term;

determining, using the data associated with the search queries, that a different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine;

in response to determining that (i) the particular search result selected by the particular, past user of the search engine includes the query term included in the initial search query, and the particular synonym for the query term, and (ii) the different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine, incrementing a particular type of skip count for the particular synonym rule; and

determining whether to revise a subsequently received search query that includes the query term included in the initial search query, to include the particular synonym for the query term, based at least on the particular type of skip count for the particular synonym rule.

10. The device of claim 9, wherein the operations comprise assigning a score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule.

11. The device of claim 10, wherein assigning the score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule comprises assigning the score to the particular synonym rule based on the particular type of skip count for the particular synonym rule, a click count for the particular synonym rule, and a different type of skip count for the particular synonym rule.

12. The device of claim 11, wherein the operations comprise associating a first weight with the particular type of skip count for the particular synonym rule, a second weight with the different type of skip count for the particular synonym rule, and a third weight with the click count for the particular synonym rule.

13. The device of claim 10, wherein the operations comprise:

determining that the score assigned to the particular synonym rule does not meet a threshold; and

removing the particular synonym rule from a set of synonym rules used to generate revised search queries based on determining that the score assigned to the particular synonym rule does not meet the threshold.

14. The device of claim 9, wherein the different search result includes the query term included in the initial search query.

15. The device of claim 9, wherein the operations comprise determining, using the data associated with the search queries, that the particular synonym for the query term was generated for the query term using a synonym rule associated with a particular query context, and wherein incrementing the particular type of skip count for the particular synonym rule comprises incrementing the particular type of skip count for the synonym rule associated with the particular query context.

16. The device of claim 11, wherein the score assigned to the particular synonym rule satisfies:

17. A system comprising:

one or more computers; and

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

determining, using data associated with search queries submitted by past users of a search engine, that a particular search result selected by a particular, past user of the search engine includes a query term included in an initial search query, and a particular synonym that was generated for the query term included in the initial search query using a particular synonym rule, wherein the data associated with the search queries indicates that the particular search result was selected by the particular, past user of the search engine from among multiple search results that were generated by the search engine using the initial search query and one or more revised search queries that include the particular synonym for the query term;

determining, using the data associated with the search queries, that a different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine;

in response to determining that (i) the particular search result selected by the particular, past user of the search engine includes the query term included in the initial search query, and the particular synonym for the query term, and (ii) the different search result that also includes the particular synonym for the query term was ranked above the particular search result and was not selected by the particular, past user of the search engine incrementing a particular type of skip count for the particular synonym rule; and

determining whether to revise a subsequently received search query that includes the query term included in the initial search query, to include the particular synonym for the query term, based at least on the particular type of skip count for the particular synonym rule.

18. The system of claim 17, wherein the operations comprise assigning a score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule.

19. The system of claim 18, wherein assigning the score to the particular synonym rule based at least in part on the particular type of skip count for the particular synonym rule comprises assigning the score to the particular synonym rule based on the particular type of skip count for the particular synonym rule, a click count for the particular synonym rule, and a different type of skip count for the particular synonym rule.

20. The system of claim 19, wherein the operations comprise associating a first weight with the particular type of skip count for the particular synonym rule, a second weight with the different type of skip count for the particular synonym rule, and a third weight with the click count for the particular synonym rule.

21. The system of claim 18, wherein the operations comprise:

determining that the score assigned to the particular synonym rule does not meet a threshold; and

removing the particular synonym rule from a set of synonym rules used to generate revised search queries based on determining that the score assigned to the particular synonym rule does not meet the threshold.

22. The system of claim 17, wherein the different search result includes the query term included in the initial search query.

23. The system of claim 17, wherein the operations comprise determining, using the data associated with the search queries, that the particular synonym for the query term was generated for the query term using a synonym rule associated with a particular query context, and wherein incrementing the particular type of skip count for the particular synonym rule comprises incrementing the particular type of skip count for the synonym rule associated with the particular query context.

24. The system of claim 19, wherein the score assigned to the particular synonym rule satisfies: