Methods and systems for improving search rankings using advertising data

• US 8,676,790 B1
• Filed: 12/05/2003
• Issued: 03/18/2014
• Est. Priority Date: 12/05/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Henzinger, Monika, Franz, Alexander Mark
• Primary Examiner(s): Lee, Wilson
• Application Number:
  US10/728,673
• Time in Patent Office: 3,756 Days
• Field of Search: 707/3, 707/4, 707/5, 707/6, 707/100, 707/102, 707705-708, 707722-731, 707769-771
• US Class Current: 707/723
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0256 User search

Abstract

Systems and methods for improving search rankings using advertising data are disclosed. In one embodiment, a search engine implements a method comprising receiving a search query, identifying a plurality of articles relevant the search query, determining advertising data associated with the search query, and ranking the articles based at least in part on the advertising data.

Claims

1. A method for ranking search results using a processor-based device, the method comprising:

receiving a search query;

identifying a plurality of articles relevant to the search query;

identifying advertisements associated with the search query;

determining advertising data associated with the advertisements; and

ranking the articles based at least in part on the advertising data.

2. The method of claim 1, wherein determining advertising data comprises determining information related to search advertisements associated with the search query.

3. The method of claim 1, wherein determining advertising data comprises determining information related to content advertisements associated with at least a first article from the plurality of articles.

4. The method of claim 2, wherein the advertising data comprises a selection score for each search advertisement displayed for the search query.

5. The method of claim 4, wherein the selection score is based at least in part on a number of users that selected a search advertisement when displayed for the search query.

6. The method of claim 4, wherein the selection score comprises a ratio of users that selected a search advertisement when displayed for the search query.

7. The method of claim 4, wherein ranking the articles comprises weighting the articles based at least in part on the selection scores for the search advertisements.

8. The method of claim 3, wherein the advertising data comprises content advertising visit data associated with the first article.

9. The method of claim 8, wherein the content advertising visit data is based at least in part on a number of users that visited the first article.

10. The method of claim 9, wherein ranking comprises weighting the first article based at least in part on the content advertisement visit data.

11. The method of claim 3, wherein the advertising data comprises a selection score for each content advertisement displayed on the first article.

12. The method of claim 11, wherein the selection score is based at least in part on a number of users that selected a content advertisement when the content advertisement was displayed with the first article.

13. The method of claim 11, wherein the selection score comprises a ratio of users that selected a content advertisement when the content advertisement was displayed with the first article.

14. The method of claim 11, wherein the content advertisements each comprise advertising terms, the first article comprises text, and ranking is determined at least in part by augmenting text of the first article with the advertising terms of at least a content advertisement with a highest selection score.

15. The method of claim 11, wherein the content advertisements each comprise advertising terms, the first article comprises text, and ranking is determined at least in part by augmenting the text of the first article with weighted advertising terms, wherein the weighted advertising terms are weighted based on the selection score of the content advertisement that they came from.

16. The method of claim 3, wherein the first article is a source article and comprises content terms representing the content of the first article.

17. The method of claim 16, wherein ranking is determined at least in part by augmenting text of the first article with the content terms.

18. One or more non-transitory computer-readable storage media containing program code for ranking search results, the program code comprising:

program code for receiving a search query;

program code for identifying a plurality of articles relevant to the search query;

program code for identifying advertisements associated with the search query;

program code for determining advertising data associated with the advertisements; and

program code for ranking the articles based at least in part on the advertising data.

19. The non-transitory computer-readable storage medium of claim 18, wherein determining advertising data comprises program code for determining information related to search advertisements associated with the search query.

20. The non-transitory computer-readable storage medium of claim 18, wherein determining advertising data comprises determining information related to content advertisements associated with at least a first article from the plurality of articles.

21. The non-transitory computer-readable storage medium of claim 19, wherein the advertising data comprises a selection score for each search advertisement displayed for the search query.

22. The non-transitory computer-readable storage medium of claim 21, wherein the selection score is based at least in part on a number of users that selected a search advertisement when displayed for the search query.

23. The non-transitory computer readable storage medium of claim 21, wherein the selection score comprises a ratio of users that selected a search advertisement when displayed for the search query.

24. The non-transitory computer-readable storage medium of claim 21, wherein ranking the articles comprises program code for weighting the articles based at least in part on the selection scores for the search advertisements.

25. The non-transitory computer-readable storage medium of claim 20, wherein the advertising data comprises content advertising visit data associated with the first article.

26. The non-transitory computer-readable storage medium of claim 25, wherein the content advertising visit data is based at least in part on a number of users that visited the first article.

27. The non-transitory computer-readable storage medium of claim 26, wherein ranking comprises program code for weighting the first article based at least in part on the content advertisement visit data.

28. The non-transitory computer-readable storage medium of claim 20, wherein the advertising data comprises a selection score for each content advertisement displayed on the first article.

29. The non-transitory computer-readable storage medium of claim 28, wherein the selection score is based at least in part on a number of users that selected a content advertisement when the content advertisement was displayed with the first article.

30. The non-transitory computer-readable storage medium of claim 28, wherein the selection score comprises a ratio of users that selected a content advertisement when the content advertisement was displayed with the first article.

31. The non-transitory computer-readable storage medium of claim 28, wherein the content advertisements each comprise advertising terms, the first article comprises text, and ranking is determined at least in part by augmenting the text of the first article with the advertising terms of at least a content advertisement with a highest selection score.

32. The non-transitory computer-readable storage medium of claim 28, wherein the content advertisements each comprise advertising terms, the first article comprises text, and ranking is determined at least in part by augmenting the text of the first article with weighted advertising terms, wherein the advertising terms are weighted based on the selection score of the content advertisement that they came from.

33. The non-transitory computer-readable storage medium of claim 20, wherein the first article is a source article and comprises content terms representing the content of the first article.

34. The non-transitory computer-readable storage medium of claim 33, wherein the ranking score is determined at least in part by augmenting text of the first article with the content terms.

35. A method for ranking search results using a processor-based device, the method comprising:

receiving a search query from a user;

identifying a collection of source documents based on terms of the search query and textual contents of the source documents;

identifying one or more content advertisements displayed on the source documents in the collection;

ranking the source documents based at least in part on one or more characteristics of previous user interaction with the content advertisements; and

based on the ranking, presenting at least some of the collection of source documents in a ranked order to the user.

36. The method of claim 35, wherein the source documents are ranked based at least in part on a number of users who purchased an advertised product after clicking on a content advertisement.

37. The method of claim 35, wherein the source documents are ranked based at least in part on a text of a content advertisement.

38. The method of claim 35, wherein the source documents are ranked based at least in part on a ratio or a number of users who clicked on a content advertisement.

39. The method of claim 35, wherein identifying a set of source documents that are responsive to the search query comprises:

accessing an index of source documents indexed in accordance with terms in the source documents, and

matching terms in the search query with the indexed terms in the source documents.

40. A method for ranking search results using a processor-based device, the method comprising:

receiving terms of a search query from a user;

identifying a collection of source documents based on terms of the search query and textual contents of the source documents;

identifying one or more search advertisements based on the terms of the search query;

ranking the source documents based at least in part on one or more characteristics of previous user interaction with the search advertisements; and

based on the ranking, presenting at least some of the collection of source documents in a ranked order to the user.

41. The method of claim 40, wherein the source documents are ranked based at least in part on a number of users who purchased an advertised product after clicking on a search advertisement.

42. The method of claim 40, wherein the source documents are ranked based at least in part on a text of a search advertisement.

43. The method of claim 40, wherein the source documents are ranked based at least in part on a ratio or a number of users who clicked on a search advertisement.

44. The method of claim 40, wherein identifying a set of source documents comprises:

accessing an index of source documents indexed in accordance with terms in the source documents, and

matching the terms of search query with the indexed terms in the source documents.