Methods and apparatus for serving relevant advertisements

• US 20040059708A1
• Filed: 12/06/2002
• Published: 03/25/2004
• Est. Priority Date: 09/24/2002
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Dean, Jeffrey A., Harik, Georges R., Bucheit, Paul
• Granted Patent: US 7,716,161 B2
• Time in Patent Office: Days
• US Class Current: 707/1
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0263 based upon Internet or website rating
• CPC Class Codes: Y10S 707/944 Business related

Abstract

The relevance of advertisements to a user'"'"'s interests is improved. In one implementation, the content of a web page is analyzed to determine a list of one or more topics associated with that web page. An advertisement is considered to be relevant to that web page if it is associated with keywords belonging to the list of one or more topics. One or more of these relevant advertisements may be provided for rendering in conjunction with the web page or related web pages.

Claims

1. A method for determining if an advertisement is relevant to a target document, the method comprising:

identifying targeting information for the advertisement;

analyzing the content of the target document to identify a set of one or more topics for the target document;

comparing the targeting information to the set of one or more topics to determine if a match exists; and

determining that the advertisement is relevant to the target document if the match exists.

2. The method of claim 1, wherein the advertisement belongs to an advertiser, and wherein identifying targeting information comprises receiving a list of topics from the advertiser.

3. The method of claim 1, wherein identifying targeting information comprises generating a list of topics by analyzing content of the advertisement.

4. The method of claim 1, wherein analyzing the content comprises identifying a set of one or more topics by calculating a term vector for the target document based on text within the target document.

5. The method of claim 4, wherein terms in the term vector are assigned weights based on the frequency with which the terms appear in the text of the target document.

6. The method of claim 4, wherein terms in the term vector are assigned weights based on the infrequency with which the terms appear across a collection of documents.

7. The method of claim 4, wherein the set of one or more topics contains terms whose weight exceeds a defined threshold.

8. The method of claim 4, wherein the set of one or more topics includes a defined number of terms with the highest weights among the terms of the term vector.

9. The method of claim 1, wherein analyzing the content comprises identifying a topic based on other portions of a collection of which the target document is a part.

10. The method of claim 1, wherein analyzing the content comprises identifying a topic based on one or more queries that yield a reference to the target document.

11. The method of claim 1, wherein analyzing the content comprises:

determining at least one similar document to the target document;

supplementing content of the target document with the content of the similar documents; and

analyzing the supplemented content of the target document to identify a topic.

12. The method of claim 11, wherein determining at least one similar document comprises determining that a document is similar if it contains a reference to the target document.

13. The method of claim 11, wherein determining at least one similar document comprises determining that a document is similar if the target document contains a reference to the document.

14. The method of claim 11, wherein supplementing includes replacing at least a portion of the content of the target document with at least a portion of the content of the at least one similar document.

15. The method of claim 1, wherein analyzing the content comprises:

identifying a description of the target document used by another document that references the target document; and

analyzing the content of the description to identify a topic for the target document.

16. The method of claim 1, wherein analyzing the content comprises:

identifying a description of the target document used by another document that references the target document;

supplementing the content of the target document with the description; and

analyzing the supplemented content of the target document to identify a topic for the target document.

17. The method of claim 1, wherein analyzing the content comprises:

classifying the target document into a category; and

identifying a list of one or more topics for the target document based on the category.

18. The method of claim 17, wherein meta-information associated with the target document is used to classify the target document into a category.

19. The method of claim 18, wherein the meta-information includes information from another document that contains a reference to the target document.

20. The method of claim 18, wherein the meta-information includes information from another document to which the target document refers.

21. The method of claim 19, wherein the information from another document includes meta-information associated with the other document.

22. The method of claim 1, wherein comparing the targeting information to the topic comprises comparing the targeting information to the topic or a related topic to determine if a match exists.

23. The method of claim 14, wherein the related topic is a synonym of the topic.

24. The method of claim 14, wherein the related topic is conceptually similar to the topic.

25. The method of claim 1, wherein the target document is a target web page.

26. The method of claim 25, wherein analyzing the content comprises:

analyzing terms within the target web page and including them in the set of one or more topics if the frequency with which they appear in the target web page exceeds a threshold value.

27. The method of claim 26, further comprising:

determining terms that are related to one or more topics in the set; and

supplementing the set to include the related terms.

28. The method of claim 25, wherein analyzing the content comprises analyzing terms within a title of the target web page and including them in the set of one or more topics if the frequency with which they appear in the title exceeds a threshold value.

29. The method of claim 25, wherein analyzing the content comprises:

calculating a term vector for the target web page based on text within the target web page; and

identifying a list of one or more topics based on the term vector.

30. The method of claim 29, wherein terms in the term vector are assigned weights based on the frequency with which the terms appear in the target document.

31. The method of claim 29, wherein terms in the term vector are assigned weights based on the infrequency with which the terms appear across a collection of web pages.

32. The method of claim 29, wherein the set of one or more topics includes terms whose weight exceeds a defined value.

33. The method of claim 29, wherein the set of one or more topics includes a defined number of terms with the highest weights among the terms of the term vector.

34. The method of claim 25, wherein analyzing the content comprises:

determining at least one similar web page to the target web page;

revising the content of the target web page by supplementing it with the content of the similar web page; and

analyzing the revised content of the target web page to identify a set of one or more topics.

35. The method of claim 34, wherein supplementing includes replacing at least a portion of the target web page content with at least a portion of the similar web page content.

36. The method of claim 34, wherein determining at least one similar web page comprises determining that a web page is similar if it contains a link to the target web page.

37. The method of claim 34, wherein determining at least one similar web page comprises determining that a web page is similar if the target web page contains a link to the web page.

38. The method of claim 34, the web page is contained in a host, and wherein determining at least one similar web page comprises determining that a web page is similar if it is contained within the same host as the target web page.

39. The method of claim 34, wherein the web page is contained in a host, and wherein determining at least one similar web page comprises determining that a web page is similar if it is stored within a subdirectory of related pages on the same host as the target web page.

40. The method of claim 25, wherein analyzing the content comprises:

determining anchor text corresponding to the target web page;

revising the content of the target web page by supplementing it with the anchor text; and

analyzing the revised content of the target web page to identify a set of one or more topics.

41. The method of claim 40, wherein supplementing includes replacing at least a portion of the target web page content with at least a portion of the anchor text.

42. The method of claim 40, wherein supplementing includes replacing the target web page content with at least a portion of the anchor text.

43. The method of claim 25, wherein analyzing the content comprises:

classifying the target web page into a category; and

identifying a list of one or more topics for the target web page based on the category.

44. The method of claim 43, wherein meta-information associated with the target web page is used to classify the target web page into a category.

45. The method of claim 44, wherein the meta-information includes information from another document that contains a reference to the target web page.

46. The method of claim 45, wherein the information from another document includes meta-information associated with the other document.

47. The method of claim 44, wherein the meta-information includes anchor text corresponding to the target web page.

48. The method of claim 25, wherein the advertisement belongs to an advertiser, and wherein identifying targeting information comprises receiving a set of one or more topics from the advertiser.

49. The method of claim 25, wherein identifying targeting information comprises generating a set of one or more topics based on content of the advertisement.

50. The method of claim 25, wherein identifying targeting information comprises generating a set of one or more topics for the advertisement based on text of queries on a search engine that yield a result that links to a web page on a web site to which the advertisement links.

51. A method for determining if an advertisement is relevant to a target web page, the method comprising:

identifying targeting information for the advertisement;

generating a set of one or more topics for the target web page based on the text of queries on a search engine that yield a result that links to the target web page;

comparing the targeting information to the set of one or more topics to determine if a match exists; and

determining that the advertisement is relevant to the target web page if the match exists.

52. A method for determining if an advertisement is relevant to a target web page, the method comprising:

identifying targeting information for the advertisement;

generating a set of one or more topics for the target web page based on a search query history of one or more users who visit the target web page;

comparing the targeting information to the set of one or more topics to determine if a match exists; and

determining that the advertisement is relevant to the target web page if the match exists.

53. The method of claim 52, wherein the search query history is based on users who visited the target web page within a given time period.

54. The method of claim 53 wherein the given time period is the last Y minutes, wherein Y is a predefined term.

56. The method of claim 54, wherein determining advertisements comprises determining advertisements for which keywords have been specified that correspond to a topic that appears in the set.

55. A method of serving to a target web page a relevant advertisement, the method comprising:

receiving a request for an advertisement that is relevant to the target web page;

analyzing text of the target web page to identify a set of one or more topics corresponding to the target web page;

determining advertisements that are associated with a topic that appears in the set; and

providing at least one of the identified advertisements in response to the request.

57. Apparatus for determining if an advertisement is relevant to a target web page, the apparatus comprising:

means for identifying targeting information for the advertisement;

means for analyzing content of the target web page to identify a set of one or more topics for the target web page;

means for comparing the targeting information to the set of one or more topics to determine if a match exists; and

means for determining that the advertisement is relevant to the target web page if the match exists.

58. A method for determining if an advertisement is relevant to a target web page, the method comprising:

a step for identifying targeting information for the advertisement;

a step for analyzing the content of the target web page to identify a set of one or more topics for the target web page;

a step for comparing the targeting information to the set of one or more topics to determine if a match exists; and

a step for determining that the advertisement is relevant to the target web page if the match exists.

59. Apparatus for determining if an advertisement is relevant to a target web page, comprising:

at least one memory having program instructions, and

at least one processor configured to execute the program instructions to perform operations of;

identifying targeting information for the advertisement;

analyzing content of the target web page to identify a set of one or more topics for the target web page;

comparing the targeting information to the set of one or more topics to determine if a match exists; and

determining that the advertisement is relevant to the target web page if the match exists.