Modifying search result ranking based on populations

• US 8,694,511 B1
• Filed: 08/20/2007
• Issued: 04/08/2014
• Est. Priority Date: 08/20/2007
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Corduneanu, Adrian Dumitru, Diligenti, Michelangelo
• Primary Examiner(s): Coby, Frantz
• Application Number:
  US11/841,313
• Time in Patent Office: 2,423 Days
• Field of Search: 707/3, 707/4, 707/5, 707/736, 707/748, 707/751, 707/754, 707/721, 707/713, 707/729, 707/725, 707/743, 707/723, 707/760, 709/223
• US Class Current: 707/748
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/438 Presentation of query results
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

The present disclosure includes, among other things, systems, methods and program products for modifying search result rankings based on populations.

Claims

1. A computer-implemented method, the method comprising:

identifying click data for a document, wherein the click data represents a plurality of selections of the document, each selection being weighted according to a respective viewing time of the document when the document was identified as a search result responsive to a query submitted by a respective user in a respective country in a respective language;

calculating first click data by aggregating the weighted selections of the document that are for a same respective country in a respective language;

calculating second click data by aggregating the weighted selections of the document that are for a same respective language;

deemphasizing the second click data relative to the first click data based on, at least, a determination that a language of the query and a language of a user interface are the same; and

calculating a quality of result statistic for the document by combining the first click data with the deemphasized second click data; and

providing the quality of result statistic as an input to a ranking for the document.

2. The method of claim 1 wherein the deemphasizing further Comprises:

determining a first click fraction based on the first click data;

determining a second click fraction based on the second click data;

determining whether the first click fraction is less than the second click fraction; and

deemphasizing the second click data based at least partially on the determination that the first click fraction is less than the second click fraction.

3. The method of claim 1 wherein the deemphasizing further comprises:

determining whether a language of the document and the language of the user interface are the same; and

deemphasizing the second click data relative to the first click data based at least partially on the determination that the language of the document and the language of the user interface are the same.

4. The method of claim 1 in which the second click data is deemphasized by applying a smoothing factor to the second click data.

5. The method of claim 4 in which the smoothing factor is based at least partially on an amount of the first click data.

6. A non-transitory computer-readable medium having a computer program product stored thereon that, when executed by data processing apparatus, causes the data processing apparatus to perform operations comprising:

identifying click data for a document, wherein the click data represents a plurality of selections of the document, each selection being weighted according to a respective viewing time of the document when the document was identified as a search result responsive to a query submitted by a respective user in a respective country in a respective language;

calculating first click data by aggregating the weighted selections of the document that are for a same respective country;

calculating second click data by aggregating the weighted selections of the document that are for a same respective language;

deemphasizing the second click data relative to the first click data based on, at least, a determination that a language of the query and a language of a user interface are the same; and

calculating a quality of result statistic for the document by combining the first click data with the deemphasized second click data; and

providing the quality of result statistic as an input to a ranking for the document.

7. The computer-readable medium of claim 6 wherein the deemphasizing further comprises:

determining a first click fraction based on the first click data;

determining a second click fraction based on the second click data;

determining whether the first click fraction is less than the second click fraction; and

deemphasizing the second click data based at least partially on the determination that the first click fraction is less than the second click fraction.

8. The computer-readable medium of claim 6 wherein the deemphasizing further comprises:

determining whether a language of the document and the language of the user interface are the same; and

deemphasizing the second click data relative to the first click data based at least partially on the determination that the language of the document and the language of the user interface are the same.

9. The computer-readable medium of claim 6 in which the second click data is deemphasized by applying a smoothing factor to the second click data.

10. The computer-readable medium of claim 9 in which the smoothing factor is based at least partially on an amount of the first click data.

11. A system comprising:

a storage device having instructions stored thereon; and

one or more computers operable to execute the instructions to perform operations comprising;

identifying click data for a document, wherein the click data represents a plurality of selections of the document, each selection being weighted according to a respective viewing time of the document when the document was identified as a search result responsive to a query submitted by a respective user in a respective country in a respective language;

calculating first click data by aggregating the weighted selections of the document that are for a same respective country;

calculating second click data by aggregating the weighted selections of the document that are for a same respective language;

deemphasizing the second click data relative to the first click data based on, at least, a determination that a language of the query and a language of a user interface are the same; and

calculating a quality of result statistic for the document by combining the first click data with the deemphasized second click data; and

providing the quality of result statistic as an input to a ranking for the document.

12. The system of claim 11 wherein the deemphasizing further comprises:

determining a first click fraction based on the first click data;

determining a second click fraction based on the second click data;

determining whether the first click fraction is less than the second click fraction; and

deemphasizing the second click data based at least partially on the determination that the first click fraction is less than the second click fraction.

13. The system of claim 11 wherein the deemphasizing further comprises:

determining whether a language of the document and the language of the user interface are the same; and

deemphasizing the second click data relative to the first click data based at least partially on the determination that the language of the document and the language of the user interface are the same.

14. The system of claim 11 in which the second click data is deemphasized by applying a smoothing factor to the second click data.

15. The system of claim 14 in which the smoothing factor is based at least partially on an amount of the first click data.

16. The system of claim 11, wherein the one or more computers comprise a server operable to interact with a user interface device through a data communication network, and the user interface device is operable to interact with the server as a client.

17. The system of claim 16, wherein the user interface device comprises a computer running a web browser.