Refining search results

• US 8,498,974 B1
• Filed: 08/31/2009
• Issued: 07/30/2013
• Est. Priority Date: 08/31/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Grushetskyy, Oleksandr, Lopatenko, Andrei, Kim, Hyung-Jin
• Primary Examiner(s): Wu, Yicun
• Application Number:
  US12/551,052
• Time in Patent Office: 1,429 Days
• Field of Search: 707/706, 707/748, 707/772
• US Class Current: 707/706
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A computer-implemented method for processing query information includes receiving data representative of a search query from a user search session. The method also includes identifying a plurality of search results based upon the search query. Each search result is associated with a plurality of user characteristics and data that represents requestor behavior relative to previously submitted queries associated with the respective search result. The method also includes ordering the plurality of user characteristics based upon the data that represents requestor behavior relative to previously submitted queries and the respective search result. The method also includes adjusting the ordered plurality of user characteristics based upon at least one predefined compatibility associated with the user characteristics. The method also includes ranking the search results based upon the adjusted plurality of user characteristics.

Claims

1. A computer-implemented method comprising:

obtaining a plurality of search results responsive to a search query submitted by a user, wherein each search result refers to a respective document that is associated with a respective plurality of click measures, each click measure relating to a different respective natural language and representing, at least, a measure of behavior of users associated with the respective language in regards to the document when the document was referred to in a search result previously provided in response to the search query;

for each of a first plurality of the search results, reducing the click measure associated with the document referred to by the search result, wherein the click measure relates to a respective natural language that is incompatible with a natural language of the user;

calculating a respective scoring factor for each of the first plurality of search results based on the respective click measures associated with the document referred to by the first search result; and

ranking the search results based upon, at least, the calculated scoring factors.

2. The method of claim 1 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents the user'"'"'s ability to understand the document.

3. The method of claim 1 wherein the users are located in a same country as the user.

4. The method of claim 1 wherein a plurality of the users are located in a different country than the user.

5. The method of claim 4 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents a measure of the user'"'"'s ability to understand the document based on the country of the user and a country of the document.

6. The method of claim 1 wherein calculating the scoring factor further comprises summing the respective click measures for the document.

7. The method of claim 1 wherein calculating the scoring factor further comprises calculating a ratio of a sum of the respective click measures for the document and a sum of click counts for the query.

8. The method of claim 1 wherein the respective click measure is a ratio of a number of instances that the document was selected for the respective natural language and a number of instances that document was selected for all of the respective natural languages.

9. The method of claim 1 wherein reducing the respective click measure comprises eliminating the click measure.

10. The method of claim 1, further comprising determining that the respective natural language is incompatible with the natural language of the user based on, at least, analysis of search queries submitted by users in different countries.

11. A system comprising:

one or more processors programmed operable to perform operations comprising;

obtaining a plurality of search results responsive to a search query submitted by a user, wherein each search result refers to a respective document that is associated with a respective plurality of click measures, each click measure relating to a different respective natural language and representing, at least, a measure of behavior of users associated with the respective language in regards to the document when the document was referred to in a search result previously provided in response to the search query;

for each of a first plurality of the search results, reducing the click measure associated with the document referred to by the search result, wherein the click measure relates to a respective natural language that is incompatible with a natural language of the user;

calculating a respective scoring factor for each of the first plurality of search results based on the respective click measures associated with the document referred to by the first search result; and

ranking the search results based upon, at least, the calculated scoring factors.

12. The system of claim 11 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents the user'"'"'s ability to understand the document.

13. The system of claim 11 wherein the users are located in a same country as the user.

14. The system of claim 11 wherein a plurality of the users are located in a different country than the user.

15. The system of claim 14 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents a measure of the user'"'"'s ability to understand the document based on the country of the user and a country of the document.

16. The system of claim 11 wherein calculating the scoring factor further comprises summing the respective click measures for the document.

17. The system of claim 11 wherein calculating the scoring factor further comprises calculating a ratio of a sum of the respective click measures for the document and a sum of click counts for the query.

18. The system of claim 11 wherein the respective click measure is a ratio of a number of instances that the document was selected for the respective natural language and a number of instances that document was selected for all of the respective natural languages.

19. The system of claim 11 wherein reducing the respective click measure comprises eliminating the click measure.

20. The system of claim 11 wherein the operations further comprise determining that the respective natural language is incompatible with the natural language of the user based on, at least, analysis of search queries submitted by users in different countries.

21. A computer readable medium having instructions stored thereon that, when executed by one or more processors, causes the one or more processors to perform operations comprising:

obtaining a plurality of search results responsive to a search query submitted by a user, wherein each search result refers to a respective document that is associated with a respective plurality of click measures, each click measure relating to a different respective natural language and representing, at least, a measure of behavior of users associated with the respective language in regards to the document when the document was referred to in a search result previously provided in response to the search query;

for each of a first plurality of the search results, reducing the click measure associated with the document referred to by the search result, wherein the click measure relates to a respective natural language that is incompatible with a natural language of the user;

calculating a respective scoring factor for each of the first plurality of search results based on the respective click measures associated with the document referred to by the first search result; and

ranking the search results based upon, at least, the calculated scoring factors.

22. The computer readable medium of claim 21 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents the user'"'"'s ability to understand the document.

23. The computer readable medium of claim 21 wherein the users are located in a same country as the user.

24. The computer readable medium of claim 21 wherein a plurality of the users are located in a different country than the user.

25. The computer readable medium of claim 24 wherein calculating the scoring factor further comprises weighting a combination of the respective click measures for the document by a weight that represents a measure of the user'"'"'s ability to understand the document based on the country of the user and a country of the document.

26. The computer readable medium of claim 21 wherein calculating the scoring factor further comprises summing the respective click measures for the document.

27. The computer readable medium of claim 21 wherein calculating the scoring factor further comprises calculating a ratio of a sum of the respective click measures for the document and a sum of click counts for the query.

28. The computer readable medium of claim 21 wherein the respective click measure is a ratio of a number of instances that the document was selected for the respective natural language and a number of instances that document was selected for all of the respective natural languages.

29. The computer readable medium of claim 21 wherein reducing the respective click measure comprises eliminating the click measure.

30. The computer readable medium of claim 21 wherein the operations further comprise determining that the respective natural language is incompatible with the natural language of the user based on, at least, analysis of search queries submitted by users in different countries.