Ranking search results based on anchors

• US 8,959,093 B1
• Filed: 03/15/2010
• Issued: 02/17/2015
• Est. Priority Date: 03/15/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Nerurkar, Ajay P.
• Primary Examiner(s): Bhatia, Ajay
• Assistant Examiner(s): SHECHTMAN, CHERYL MARIA
• Application Number:
  US12/723,973
• Time in Patent Office: 1,800 Days
• Field of Search: 707/728
• US Class Current: 707/751
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

In general, one aspect described can be embodied in a method for providing input to a document ranking process for ranking a plurality of documents, the document ranking process taking as input a quality of result statistic for a query and an individual document. The method can include, for a first document identified as a search result of a query, receiving information regarding an anchor contained within the first document, where the anchor provides a link to a second document; deriving a quality of result statistic for the second document from at least a portion of first data associated with the first document and the query, the first data being indicative of user behavior relative to the first document as a search result for the query; and providing the first quality of result statistic as input to the document ranking process for the second document and the query.

Claims

1. A computer-implemented method comprising:

obtaining, at a computer system, a plurality of search results in response to a query, the plurality of search results including a first reference to a first document and a second reference to a second document;

determining that the first document referenced in the plurality of search results includes a link to the second document referenced in the plurality of search results;

in response to determining that the first document referenced in the plurality of search results includes a link to the second document referenced in the plurality of search results, computing a quality of result statistic for the second document based on;

a first measure of previous user selections of the first document when the first document was referenced by a search result provided for the query, and

a second measure of previous user selections of the second document when the second document was referenced by a search result provided for the query; and

providing, by the computer system, the quality of result statistic for the second document as input to a document ranking process, the ranking process configured to rank the plurality of search results for the query.

2. The method of claim 1, further comprising associating at least a portion of the previous user selections of the first document as user behavior data for the second document.

3. The method of claim 1, wherein the quality of result statistic for the second document is further based on a third measure of user selections of the second document when the second document was referenced by a search result provided for a different second query.

4. The method of claim 1, further comprising;

determining that a first internet domain of a first resource location of the first document is different than a second internet domain of a second resource location of the second document,

wherein computing a quality of result statistic for the second document based on the first measure of previous user selections of the first document is based on determining that the first internet domain of the first resource location is different than the second internet domain of the second resource location.

5. The method of claim 1, further comprising determining that anchor text associated with the link is relevant to the query,

wherein computing a quality of result statistic for the second document based on the first measure of previous user selections of the first document is based on determining that the anchor text associated with the link is relevant to the query.

6. The method of claim 5, wherein determining that the anchor text associated with the link is relevant to the query comprises determining that at least a portion of the anchor text matches at least a portion of the query.

7. The method of claim 1, further comprising identifying third data that is associated with the link and the query, the third data indicating, at least, selection of the link in the first document when the first document was previously identified in search results for the query,

wherein the quality of result statistic is further based on the third data.

8. The method of claim 1, wherein computing a quality of result statistic for the second document based on the first measure of previous user selections of the first document comprises aggregating the first measure of previous user selections of the first document with the second measure of previous user selections of the second document.

9. The method of claim 1, further comprising:

in response to determining that the first document referenced in the plurality of search results includes a link to the second document referenced in the plurality of search results, reducing the first measure of previous user selections of the first document associated with the first document.

10. The method of claim 1, further comprising:

determining a degree of relevance between anchor text associated with the link and the query, where the quality of result statistic is further based on the determined degree of relevance between the anchor text associated with the link and the query.

11. A computer program product encoded on one or more non-transitory computer storage media, comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

obtaining a plurality of search results in response to a query, the plurality of search results including a first reference to a first document and a second reference to a second document;

determining that the first document referenced in the plurality of search results includes a link to a second document referenced in the plurality of search results;

in response to determining that the first document referenced in the plurality of search results includes a link to a second document referenced in the plurality of search results, computing a quality of result statistic for the second document based on;

a first measure of previous user selections of the first document when the first document was referenced by a search result provided for the query, and

a second measure of previous user selections of the second document when the second document was referenced by a search result provided for the query; and

providing the quality of result statistic for the second document as input to a ranking process, the ranking process configured to rank the plurality of search results for the query.

12. The computer program product of claim 11, wherein the operations further comprise associating at least a portion of the previous user selections of the first document as user behavior data for the second document.

13. The computer program product of claim 11, wherein the operations further comprise determining that anchor text associated with the link is relevant to the query,

wherein computing the quality of result statistic for the second document based on the first measure of previous user selections of the first document is based on determining that the anchor text associated with the link is relevant to the query.

14. The computer program product of claim 13, wherein determining that the anchor text associated with the link is relevant to the query comprises determining that at least a portion of the anchor text matches at least a portion of the query.

15. The computer program product of claim 11, wherein the operations further comprise:

in response to determining that the first document referenced in the plurality of search results includes a link to the second document referenced in the plurality of search results, reducing the first measure of previous user selections of the first document associated with the first document.

16. A system for providing input to a document ranking process for ranking a plurality of documents, the system comprising:

a computer readable medium including a program product; and

one or more processors configured to execute the program product and perform operations comprising;

obtaining a plurality of search results in response to a query, the plurality of search results including a first reference to a first document and a second reference to a second document;

determining that the first document referenced in the plurality of search results includes a link to a second document referenced in the plurality of search results;

in response to determining that the first document referenced in the plurality of search results includes a link to a second document referenced in the plurality of search results, computing a quality of result statistic for the second document based on;

a first measure of previous user selections of the first document when the first document was referenced by a search result provided for the query, and

a second measure of previous user selections of the second document when the second document was referenced by a search result provided for the query; and

providing the quality of result statistic for the second document as input to a ranking process, the ranking process configured to rank the plurality of search results for the query.

17. The system of claim 16, wherein the operations further comprise associating at least a portion of the previous user selections of the first document as user behavior data for the second document.

18. The system of claim 16, wherein the operations further comprise determining that anchor text associated with the link is relevant to the query,

wherein computing the quality of result statistic for the second document based on the first measure of previous user selections of the first document is based on determining that the anchor text associated with the link is relevant to the query.

19. The system of claim 18, wherein determining that the anchor text associated with the link is relevant to the query comprises determining that at least a portion of the anchor text matches at least a portion of the query.

20. The system of claim 16, wherein the operations further comprise:

in response to determining that the first document referenced in the plurality of search results includes a link to the second document referenced in the plurality of search results, reducing the first measure of previous user selections of the first document associated with the first document.