Methods and systems for improving a search ranking using related queries

• US 8,452,758 B2
• Filed: 04/03/2012
• Issued: 05/28/2013
• Est. Priority Date: 09/12/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Tong, Simon, Pearson, Mark, Brin, Sergey
• Primary Examiner(s): PARDO, THUY N
• Application Number:
  US13/438,145
• Publication Number:
  US 20120191705A1
• Time in Patent Office: 420 Days
• Field of Search: 707/721, 707/731, 707/748, 707/751
• US Class Current: 707/721
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Systems and methods that improve search rankings for a search query by using data associated with queries related to the search query are described. In one aspect, a search query is received, a related query related to the search query is determined, an article (such as a web page) associated with the search query is determined, and a ranking score for the article based at least in part on data associated with the related query is determined. Several algorithms and types of data associated with related queries useful in carrying out such systems and methods are described.

Claims

1. A computer-implemented method comprising:

determining, by a computer system, a main score for a document as a result for a search query, the main score based, at least in part, on one or more related search queries that have at least a threshold relationship to the search query, wherein determining the main score comprises;

identifying one or more other documents that have been included in search results for the search query or for the one or more related search queries;

determining first click data for the document and the search query, wherein the first click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the search query, and ii) first other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the search query;

determining second click data for the document and the one or more related search queries, wherein the second click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the one or more related search queries, and ii) second other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the one or more related search queries; and

generating at least a component of the main score based, at least in part, on the first click data and the second click data; and

providing, by the computer system, the main score for the document as a result for the search query.

2. The method of claim 1, further comprising adjusting the first other click data by a blending factor that indicates a degree to which the first other click data for the one or more other documents and the search query reliably indicates user behavior with regard to the document and the search query,

wherein the first click data is based on the adjusted first other click data.

3. The method of claim 1, further comprising adjusting the second other click data by a blending factor that indicates a degree to which the second other click data for the one or more other documents and the one or more search queries reliably indicates user behavior with regard to the document and the search query,

wherein the second click data is based on the adjusted second other click data.

4. The method of claim 1, further comprising weighting the second click data based on weights for the one or more related search queries, wherein the weights indicate how strongly the one or more related queries are related to the search query,

wherein the component of the main score is based, at least in part, on the first click data and the weighted second click data.

5. The method of claim 4, further comprising determining a combination of the weights for the one or more related search queries;

wherein the component of the main score is based, at least in part, on the first click data, the weighted second click data, and the combination of the weights for the one or more related search queries.

6. The method of claim 5, wherein the combination of the weights for the one or more related search queries comprises a sum of the weights for the one or more related search queries.

7. The method of claim 5, wherein the component of the main score is based, at least in part, on a sum of the first click data and the weighted second click data, divided by the combination of the weights for the one or more related search queries.

8. A computer program product tangibly embodied on one or more computer readable media storing instructions that, when executed by one or more computing devices, cause operation to be performed comprising:

determining a main score for a document as a result for a search query, the main score based, at least in part, on one or more related search queries that have at least a threshold relationship to the search query, wherein determining the main score comprises;

identifying one or more other documents that have been included in search results for the search query or for the one or more related search queries;

determining first click data for the document and the search query, wherein the first click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the search query, and ii) first other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the search query;

determining second click data for the document and the one or more related search queries, wherein the second click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the one or more related search queries, and ii) second other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the one or more related search queries; and

generating at least a component of the main score based, at least in part, on the first click data and the second click data; and

providing the main score for the document as a result for the search query.

9. The computer program product of claim 8, wherein:

the operations further comprise adjusting the first other click data by a blending factor that indicates a degree to which the first other click data for the one or more other documents and the search query reliably indicates user behavior with regard to the document and the search query, and

the first click data is based on the adjusted first other click data.

10. The computer program product of claim 8, wherein:

the operations further comprise adjusting the second other click data by a blending factor that indicates a degree to which the second other click data for the one or more other documents and the one or more search queries reliably indicates user behavior with regard to the document and the search query, and

the second click data is based on the adjusted second other click data.

11. The computer program product of claim 8, wherein:

the operations further comprise weighting the second click data based on weights for the one or more related search queries, wherein the weights indicate how strongly the one or more related queries are related to the search query, and

the component of the main score is based, at least in part, on the first click data and the weighted second click data.

12. The computer program product of claim 11, wherein:

the operations further comprise determining a combination of the weights for the one or more related search queries, and

the component of the main score is based, at least in part, on the first click data, the weighted second click data, and the combination of the weights for the one or more related search queries.

13. The computer program product of claim 12, wherein the combination of the weights for the one or more related search queries comprises a sum of the weights for the one or more related search queries.

14. The computer program product of claim 12, wherein the component of the main score is based, at least in part, on a sum of the first click data and the weighted second click data, divided by the combination of the weights for the one or more related search queries.

15. A system comprising:

a computer system; and

a related query processor of the computer system to determine a main score for a document as a result for a search query, the main score based, at least in part, on one or more related search queries that have at least a threshold relationship to the search query, wherein the main score is determined by performing operations comprising;

identifying one or more other documents that have been included in search results for the search query or for the one or more related search queries;

determining first click data for the document and the search query, wherein the first click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the search query, and ii) first other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the search query;

determining second click data for the document and the one or more related search queries, wherein the second click data comprises a combination of at least i) click data that indicates a level at which the document was selected when the document was presented in search results for the one or more related search queries, and ii) second other click data that indicates a level at which the one or more other documents were selected when the one or more other documents were presented in search results for the one or more related search queries; and

generating at least a component of the main score based, at least in part, on the first click data and the second click data;

wherein the related query processor is further configured to provide the main score for the document as a result for the search query to a ranking processor.

16. The system of claim 15, wherein:

the operations further comprise adjusting the first other click data by a blending factor that indicates a degree to which the first other click data for the one or more other documents and the search query reliably indicates user behavior with regard to the document and the search query, and

the first click data is based on the adjusted first other click data.

17. The system of claim 15, wherein:

the operations further comprise adjusting the second other click data by a blending factor that indicates a degree to which the second other click data for the one or more other documents and the one or more search queries reliably indicates user behavior with regard to the document and the search query, and

the second click data is based on the adjusted second other click data.

18. The system of claim 15, wherein:

the operations further comprise weighting the second click data based on weights for the one or more related search queries,

the weights indicate how strongly the one or more related queries are related to the search query, and

the component of the main score is based, at least in part, on the first click data and the weighted second click data.

19. The system of claim 18, wherein:

the operations further comprise determining a combination of the weights for the one or more related search queries, and

the component of the main score is based, at least in part on the first click data, the weighted second click data, and the combination of the weights for the one or more related search queries.

20. The system of claim 19, wherein the combination of the weights for the one or more related search queries comprises a sum of the weights for the one or more related search queries.

21. The system of claim 19, wherein the component of the main score is based, at least in part, on a sum of the first click data and the weighted second click data, divided by the combination of the weights for the one or more related search queries.