Modifying search result ranking based on corpus search statistics

• US 8,756,220 B1
• Filed: 01/14/2013
• Issued: 06/17/2014
• Est. Priority Date: 05/23/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Provine, John R., Basile, Claudio, Vasserman, Alexander L.
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US13/740,415
• Time in Patent Office: 519 Days
• Field of Search: 707/748, 707/752, 707/749, 707/750, 707/727, 707/721
• US Class Current: 707/721
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

Methods, systems, and apparatus, including computer program products, for ranking search results of a search query using corpus search statistics. In one aspect, a method includes determining a first relevance of a first corpus to a search query, determining a second relevance of a second corpus to the search query, determining a measure of relative relevance of the first corpus and the second corpus to the search query, and providing the measure of relative relevance to a ranking engine for ranking of search results for a new search corresponding to the search query.

Claims

1. A computer-implemented method comprising:

determining a first measure of a first corpus for a search query as a count of times the search query was submitted to search the first corpus in view of a count of times other queries were submitted to search the first corpus;

determining a second measure of a second corpus for the search query as a count of times the search query was submitted to search the second corpus in view of a count of times other queries were submitted to search the second corpus;

determining a click measure based on a count of selections of first corpus search results for the search query relative to a count of selections of second corpus search results for the search query;

determining a measure of relative relevance of the first corpus and the second corpus for the search query based on the first measure, the second measure and the click measure; and

providing the measure of relative relevance to a ranking engine for ranking of search results for a search corresponding to the search query.

2. The method of claim 1 wherein determining the first measure of the first corpus for the search query further comprises determining the first measure by combining a plurality of relevance determinations wherein each relevance determination in the plurality is for a different time period.

3. The method of claim 1 wherein determining the first measure of the first corpus for the search query comprises determining the count of times the search query was submitted to search the first corpus in view of the count of times all queries were submitted to search the first corpus.

4. The method of claim 1 wherein determining the measure of relative relevance of the first corpus and the second corpus for the search query comprises determining the first measure of the first corpus as compared to the second measure of the second corpus.

5. The method of claim 1 wherein determining the measure of relative relevance comprises computing a weighted combination of a relative search fraction of the first measure and the second measure, and the click measure.

6. The method of claim 1 wherein the respective counts for the first and second corpora are derived from language-specific data or country-specific data, and wherein determining a relevance of a corpus for the search query further comprises selecting which of the data to use for the respective counts based on a determination that the selected data will provide a reliable statistic.

7. The method of claim 1 wherein the first corpus comprises web pages and wherein the second corpus comprises videos.

8. The method of claim 1 wherein the first corpus comprises web pages and wherein the second corpus comprises images.

9. The method of claim 1 wherein the ranking engine is configured to increase a score of a search result for the search that refers to a document in the second corpus based at least in part on the measure of relative relevance.

10. A system comprising:

a storage device having instructions stored thereon; and

data processing apparatus operable to execute the instructions to perform operations comprising;

determining a first measure of a first corpus for a search query as a count of times the search query was submitted to search the first corpus in view of a count of times other queries were submitted to search the first corpus;

determining a second measure of a second corpus for the search query as a count of times the search query was submitted to search the second corpus in view of a count of times other queries were submitted to search the second corpus;

determining a click measure based on a count of selections of first corpus search results for the search query relative to a count of selections of second corpus search results for the search query;

determining a measure of relative relevance of the first corpus and the second corpus for the search query based on the first measure, the second measure and the click measure; and

providing the measure of relative relevance to a ranking engine for ranking of search results for a search corresponding to the search query.

11. The system of claim 10 wherein determining the first measure of the first corpus for the search query further comprises determining the first measure by combining a plurality of relevance determinations wherein each relevance determination in the plurality is for a different time period.

12. The system of claim 10 wherein determining the first measure of the first corpus for the search query comprises determining the count of times the search query was submitted to search the first corpus in view of the count of times all queries were submitted to search the first corpus.

13. The system of claim 10 wherein determining the measure of relative relevance of the first corpus and the second corpus for the search query comprises determining the first measure of the first corpus as compared to the second measure of the second corpus.

14. The system of claim 10 wherein determining the measure of relative relevance comprises computing a weighted combination of a relative search fraction of the first measure and the second measure, and the click measure.

15. The system of claim 10 wherein the respective counts for the first and second corpora are derived from language-specific data or country-specific data, and wherein determining a relevance of a corpus for the search query further comprises selecting which of the data to use for the respective counts based on a determination that the selected data will provide a reliable statistic.

16. The system of claim 10 wherein the first corpus comprises web pages and wherein the second corpus comprises videos.

17. The system of claim 10 wherein the first corpus comprises web pages and wherein the second corpus comprises images.

18. The system of claim 10 wherein the ranking engine is configured to increase a score of a search result for the search that refers to a document in the second corpus based at least in part on the measure of relative relevance.

19. A storage device having instructions stored thereon that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:

determining a first measure of a first corpus for a search query as a count of times the search query was submitted to search the first corpus in view of a count of times other queries were submitted to search the first corpus;

determining a second measure of a second corpus for the search query as a count of times the search query was submitted to search the second corpus in view of a count of times other queries were submitted to search the second corpus;

determining a click measure based on a count of selections of first corpus search results for the search query relative to a count of selections of second corpus search results for the search query;

determining a measure of relative relevance of the first corpus and the second corpus for the search query based on the first measure, the second measure and the click measure; and

providing the measure of relative relevance to a ranking engine for ranking of search results for a search corresponding to the search query.

20. The storage device of claim 19 wherein determining the first measure of the first corpus for the search query further comprises determining the first measure by combining a plurality of relevance determinations wherein each relevance determination in the plurality is for a different time period.

21. The storage device of claim 19 wherein determining the first measure of the first corpus for the search query comprises determining the count of times the search query was submitted to search the first corpus in view of the count of times all queries were submitted to search the first corpus.

22. The storage device of claim 19 wherein determining the measure of relative relevance of the first corpus and the second corpus for the search query comprises determining the first measure of the first corpus as compared to the second measure of the second corpus.

23. The storage device of claim 19 wherein determining the measure of relative relevance comprises computing a weighted combination of a relative search fraction of the first measure and the second measure, and the click measure.

24. The storage device of claim 19 wherein the respective counts for the first and second corpora are derived from language-specific data or country-specific data, and wherein determining a relevance of a corpus for the search query further comprises selecting which of the data to use for the respective counts based on a determination that the selected data will provide a reliable statistic.

25. The storage device of claim 19 wherein the first corpus comprises web pages and wherein the second corpus comprises videos.

26. The storage device of claim 19 wherein the first corpus comprises web pages and wherein the second corpus comprises images.

27. The storage device of claim 19 wherein the ranking engine is configured to increase a score of a search result for the search that refers to a document in the second corpus based at least in part on the measure of relative relevance.