Methods and systems for improving a search ranking using population information

• US 8,090,713 B2
• Filed: 11/18/2008
• Issued: 01/03/2012
• 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
• Primary Examiner(s): Lewis, Cheryl
• Application Number:
  US12/273,449
• Publication Number:
  US 20110238643A1
• Time in Patent Office: 1,141 Days
• Field of Search: 707/723, 707/769, 709/203
• US Class Current: 707/723
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

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 population associated with the search query is determined, an article (such as a webpage) associated with the search query is determined, and a ranking score for the article based at least in part on data associated with the population is determined. Algorithms and types of data associated with a population useful in carrying out such systems and methods are described.

Claims

1. A computer-implemented method, comprising:

receiving, at a server device and from a client device, a search query entered on the client device by a user;

determining, using the server device, that the user belongs to at least a first population group;

determining, using the server device, that at least a first article is responsive to the search query;

determining, using the server device, an interest value reflecting an interest of the first population group in the first article, the interest value based on at least one selection of the first article made when the first article was previously presented to at least one member of the first population group in response to an earlier search query identical to the search query;

determining, using the server device, a first ranking score for the first article, the first ranking score based at least in part on the interest value; and

outputting a search result from the server device to the client device in response to the search query, the first article ranked in the search result according to the first ranking score.

2. The method of claim 1, wherein determining that the user belongs to the first population group comprises determining, using the server device, demographic data associated with the user.

3. The method of claim 2, wherein determining the demographic data comprises determining, using the server device, a likely geographic location for the user.

4. The method of claim 3, wherein determining the likely geographic location for the user comprises determining, using the server device, at least one of the following:

an Internet Protocol address from which the search query was sent;

an address input by the user to access a search engine; and

demographic data input by the user.

5. The method of claim 2, wherein determining the demographic data comprises determining, using the server device, a least one of the following:

age, age range, sex, race, primary language, secondary language, location, income, income range, a continent, a region, a country, a state, a county, a city, a gender, an ethnic group, a group, persons with a shared characteristic, persons with a shared interest, persons grouped by a predetermined selection, and internet service provider data.

6. The method of claim 2, wherein determining the demographic data comprises at least one of the following:

determining, using the server device, a language of the search query; and

determining, using the server device, data associated with previous senders of the search query.

7. The method of claim 1, wherein determining that the user belongs to the first population group comprises determining, using the server device, self-identification data associated with the user.

8. The method of claim 7, wherein the self-identification data is selected from at least one of the following:

user registration data, user preference data, and user selected data.

9. The method of claim 1, wherein determining that the user belongs to the first population group comprises determining, using the server device, automatic-identification data associated with the user.

10. The method of claim 9, wherein the automatic-identification data comprises at least one of the following:

an IP address, a domain, and default data obtained by an application associated with the user.

11. The method of claim 1, wherein the interest value comprises a selection score for the first article in a context of the first population group.

12. The method of claim 11, wherein the selection score for the first article in the context of the first population group comprises a number of clicks for the first article by members of the first population group for the search query.

13. The method of claim 11, wherein the interest value comprises at least the selection score divided by at least a total selection score for a set of documents provided in response to the search query, the total selection score corresponding to how many clicks users in the first population group made on any of the set of documents.

14. The method of claim 13, wherein the interest value comprises a smoothing factor associated with the clicks.

15. The method of claim 1, wherein the interest value comprises a number of members of the first population group that selected any article returned for the search query.

16. The method of claim 1, wherein the interest value comprises a number of members of the first population group that input the search query.

17. The method of claim 1, wherein the interest value comprises a total selection score.

18. The method of claim 17, wherein the total selection score comprises a total number of members of the first population group that selected the first article.

19. The method of claim 1, further comprising determining, using the server device, that the user also belongs to at least a second population group, wherein the interest value is determined so that it also reflects an interest of the second population group in the first article.

20. The method of claim 1, further comprising

determining, using the server device, that also at least a second article is responsive to the search query;

determining, using the server device, another interest value reflecting an interest of the firs population group in the second article; and

determining, using the server device, a second ranking score for the second article, the second ranking score based at least in part on the other interest value, wherein the second article is ranked in the search result according to the second ranking score.

21. The method of claim 1, wherein the interest value is based at least in part on a total selection score, a selection score based at least in part on the first population group, a smoothing factor, a number of times a query was input by members of the first population group, and a number of times a query was input.

22. A computer-readable medium containing program code, comprising:

first program code for receiving, at a server device and from a client device, a search query entered on the client device by a user;

second program code for determining, using the server device, that the user belongs to at least a first population group;

third program code for determining, using the server device, that at least a first article is responsive to the search query;

fourth program code for determining, using the server device, an interest value reflecting an interest of the first population group in the first article, the interest value based on at least one selection of the first article made when the first article was previously presented to at least one member of the first population group in response to an earlier search query identical to the search query;

fifth program code for determining, using the server device, a first ranking score for the first article, the first ranking score based at least in part on the interest value; and

sixth program code for outputting a search result from the server device to the client device in response to the search query, the first article ranked in the search result according to the first ranking score.

23. A system comprising:

at least one processor; and

a computer-readable medium containing program code that when executed cause the at least one processor to perform operations comprising;

receiving, at a server device and from a client device, a search query entered on the client device by a user;

determining, using the server device, that the user belongs to at least a first population group;

determining, using the server device, that at least a first article is responsive to the search query;

determining, using the server device, an interest value reflecting an interest of the first population group in the first article, the interest value based on at least one selection of the first article made when the first article was previously presented to at least one member of the first population group in response to an earlier search query identical to the search query;

determining, using the server device, a first ranking score for the first article, the first ranking score based at least in part on the interest value; and

outputting a search result from the server device to the client device in response to the search query, the first article ranked in the search result according to the first ranking score.

24. The system of claim 23, wherein the interest value comprises a selection score for the first article in a context of the first population group.

25. The system of claim 24, wherein the selection score for the first article in the context of the first population group comprises a number of clicks for the first article by members of the first population group for the search query.

26. The system of claim 24, wherein the interest value comprises at least the selection score divided by at least a total selection score for a set of documents provided in response to the search query, the total selection score corresponding to how many clicks users in the first population group made on any of the set of documents.

27. The system of claim 26, wherein the interest value comprises a smoothing factor associated with the clicks.

28. The system of claim 23, wherein the interest value comprises a number of members of the first population group that selected any article returned for the search query.

29. The system of claim 23, wherein the interest value comprises a number of members of the first population group that input the search query.

30. The system of claim 23, wherein the interest value comprises a total selection score.

31. The system of claim 30, wherein the total selection score comprises a total number of members of the first population group that selected the first article.

32. The system of claim 23, wherein determining that the user belongs to the first population group comprises determining, using the server device, demographic data associated with the user.

33. The system of claim 32, wherein determining the demographic data comprises determining, using the server device, a likely geographic location for the user.

34. The system of claim 33, wherein determining the likely geographic location for the user comprises determining, using the server device, at least one of the following:

an Internet Protocol address from which the search query was sent;

an address input by the user to access a search engine; and

demographic data input by the user.

35. The system of claim 32, wherein determining the demographic data comprises determining, using the server device, at least one of the following:

age, age range, sex, race, primary language, secondary language, location, income, income range, a continent, a region, a country, a state, a county, a city, a gender, an ethnic group, a group, persons with a shared characteristic, persons with a shared interest, persons grouped by a predetermined selection, and internet service provider data.

36. The system of claim 32, wherein determining the demographic data comprises at least one of the following:

determining, using the server device, a language of the search query; and

determining, using the server device, data associated with previous senders of the search query.

37. The system of claim 23, wherein determining that the user belongs to the first population group comprises determining, using the server device, self-identification data associated with the user.

38. The system of claim 37, wherein the self-identification data is selected from at least one of the following:

user registration data, user preference data, and user selected data.

39. The system of claim 23, wherein determining that the user belongs to the first population group comprises determining, using the server device, automatic-identification data associated with the user.

40. The system of claim 39, wherein the automatic-identification data comprises at least one of the following:

an IP address, a domain, and default data obtained by an application associated with the user.

41. The system of claim 23, further comprising determining, using the server device, that the user also belongs to at least a second population group, wherein the interest value is determined so that it also reflects an interest of the second population group in the first article.

42. The system of claim 23, further comprising

determining, using the server device, that also at least a second article is responsive to the search query;

determining, using the server device, another interest value reflecting an interest of the firs population group in the second article; and

determining, using the server device, a second ranking score for the second article, the second ranking score based at least in part on the other interest value, wherein the second article is ranked in the search result according to the second ranking score.

43. The system of claim 23, wherein the interest value is based at least in part on a total selection score, a selection score based at least in part on the first population group, a smoothing factor, a number of times a query was input by members of the first population group, and a number of times a query was input.