Serving advertisements using user request information and user information

• US 20120095837A1
• Filed: 06/02/2003
• Published: 04/19/2012
• Est. Priority Date: 06/02/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bharat, Krishna, Lawrence, Steve, Sahami, Mehran, Singhal, Amit
• Granted Patent: US 8,352,499 B2
• Time in Patent Office: Days
• US Class Current: 705/14.54
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search

Abstract

Ads are scored using, at least, user information and information associated with a user request, such as a search query or a document request. The scores may be used in determining whether to serve ads, how to serve ads, to order ads, to filter ads, etc. Items of user information, request-associated information, and/or ad information can be weighted based on previous uses of such information in the serving of ads and the performance of those served ads.

Claims

1. A method comprising:

a) accepting information associated with a user request;

b) accepting information about the user that submitted the user request; and

c) determining a score for at least one advertisement using both the accepted information associated with a user request and the accepted information about the user.

2. The method of claim 1 wherein the user request is a search query.

3. The method of claim 1 wherein the user request is a document request.

4. The method of claim 1 wherein the act of determining a score includes determining a similarity between

information associated with the at least one advertisement, and

the accepted information associated with a user request and the accepted information about the user.

5. The method of claim 4 wherein the information related to the at least one advertisement is represented as a first feature vector,

wherein the accepted information associated with a user request and the accepted information about the user is represented as a second feature vector, and

wherein the similarity is determined using at least a cosine distance between the first feature vector and the second feature vector.

6. The method of claim 5 wherein each of at least some items of information of at least one of the first and second feature vectors have an associated importance weight, and

wherein the similarity is determined using at least a cosine distance between at least a part of the first feature vector and at least a part of the second feature vector.

7. The method of claim 6 wherein the at least a part of the at least one of the first and second feature vectors includes items of information with the highest importance weights among the items of information of the first feature vector.

8. The method of claim 5 wherein each of at least some items of information of the first feature vector have an associated importance weight,

wherein at least some of the items of information of the first feature vector are ordered in accordance with their importance weight,

wherein each of at least some items of information of the second feature vector have an associated importance weight, and

wherein at least some of the items of information of the second feature vector are ordered in accordance with their importance weight.

9. The method of claim 4 wherein the information associated with the at least one advertisement includes terms and term frequencies,

wherein the accepted information associated with a user request and the accepted information about the user includes terms and term frequencies, and

wherein the similarity is determined using at least a term frequency-inverse document frequency measure.

10. The method of claim 4 wherein the information associated with the at least one advertisement includes a first set of items of information,

wherein the accepted information associated with a user request and the accepted information about the user includes a second set of items of information, and

wherein each of the first and second items of information have associated importance weights, the associated importance weights being determined using at least a feature selection procedure selected from a group of feature selection procedures consisting of (A) mutual information, (B) chi-square fit, (C) correlation, and (D) manual selection.

11. The method of claim 4 wherein the information associated with the at least one advertisement includes a first set of items of information,

wherein the accepted information associated with a user request and the accepted information about the user includes a second set of items of information, and

wherein each of the first and second items of information have associated importance weights, the associated importance weights being determined using at least a performance of an advertisement served in the past, wherein the advertisement included a score that was determined using at least some of the first and second items of information.

12. The method of claim 1 further comprising:

d) ordering at least two of advertisements using their determined scores.

13. The method of claim 12 further comprising:

e) determining a final set of at least one advertisement using the ordering of the at least two advertisements.

14. The method of claim 1 further comprising:

d) filtering a first set of advertisements, using their determined scores, to generate a second set of advertisements.

15. The method of claim 1 wherein the user request is a search query and wherein the information associated with the user request includes at least one keyword from the search query.

16. The method of claim 1 wherein the user request is a document request and wherein the information associated with the user request includes document information.

17. The method of claim 1 wherein the user request is a search query and wherein the information associated with the user request includes document information of a search result page responsive to the search query.

18. The method of claim 1 wherein the information about the user includes at least one of (a) user profile information and (b) user behavior information.

20. The method of claim 1 wherein the information about the user includes demographic information which includes at least one information item selected from a group of information items consisting of (A) age, (B) age range, (C) age category, (D) sex, (E) income, (F) income range, (G) income category, (H) marital status, (I) education level, and (J) parental status.

21. The method of claim 1 wherein the information about the user includes geographic information.

22. The method of claim 1 wherein the information about the user includes psychographic information.

24. The method of claim 1 wherein the information about the user includes user behavior information which includes at least one information item selected from a group of information items consisting of (A) information related to previous search queries submitted by the user, (B) information related to previous search queries submitted to a particular search engine by the user, (C) information related to previous advertisements served for rendering to the user, (D) information related to previous advertisements served for rendering by the user and selected, (E) document information of a document viewed by the user, (F) document information about a document edited by the user, (G) previous purchases by the user, and (H) previous on-line purchases by the user.

25. The method of claim 1 further comprising:

d) serving at least one advertisement using, at least, the determined score.

26. The method of claim 25 further comprising:

e) accepting user behavior responsive to the at least one advertisement served; and

f) adjusting one or more importance weights associated with one or more items of user information using, at least, the accepted user behavior.

27. The method of claim 26 wherein the accepted user behavior corresponds to a measure of performance of the advertisement.

28. The method of claim 26 wherein the score is determined using only a first set of items of user information, wherein the one or more items of user information having weights adjusted belong to a second set of items of user information, and wherein the second set of items of user information is larger than the first set of items of user information.

29. The method of claim 28 wherein the second set of items of user information includes the first set of items of user information.

30. The method of claim 1 wherein at least one of the accepted information associated with the user request and the accepted information about the user includes items of information having associated importance weights, and wherein the act of determining a score for at least one advertisement using both the accepted information associated with a user request and the accepted information about the user processes items of information in an order of their importance weights.

31. The method of claim 30 wherein the act of determining a score for at least one advertisement is terminated upon the occurrence of an event regardless of whether all items of information were considered in the score determination.

32. The method of claim 31 wherein the event is a timer expiration.

77. The method of claim 1 wherein the information about the user is inferred based on at least one of (A) other features of the user, and (B) features of other similar users.

19. (canceled)

23. (canceled)

33. A method comprising:

a) accepting information associated with a user request;

b) accepting information about the user that submitted the user request;

c) determining a first set of advertisements of general relevance to the user request; and

d) for at least some of the advertisements of the first set of advertisements, determining a score using at least the, accepted information about the user.

34. The method of claim 33 wherein the user request is a search query.

35. The method of claim 33 wherein the user request is a document request.

36. The method of claim 33 wherein the information about the user includes at least one of (a) user profile information and (b) user behavior information.

37. The method of claim 33 wherein the user request is a search query.

78. The method of claim 33 wherein the user request was sourced from a client device,

wherein the act of determining a first set of advertisements of general relevance to the user request is performed on a server device, and

wherein the act of determining a score, for at least some of the advertisements of the first set of advertisements, using at least the accepted information about the user, is performed on the client device.

38. A method comprising:

a) accepting information associated with a user request;

b) accepting information about the user that submitted the user request;

c) determining a first score for each of a plurality of ad groups using at least ad group information and at least one of (i) user request information and (ii) user information;

d) selecting an ad group using the first score; and

e) selecting at least one advertisement from the selected ad group using at least the user information.

39. Apparatus comprising:

a) an input for accepting

i) information associated with a user request, and

ii) information about the user that submitted the user request; and

b) determining a score for at least one advertisement using both the accepted information associated with a user request and the accepted information about the user.

40. The apparatus of claim 39 wherein the user request is a search query.

41. The apparatus of claim 39 wherein the user request is a document request.

42. The apparatus of claim 39 wherein the act of determining a score includes determining a similarity between

information associated with the at least one advertisement, and

the accepted information associated with a user request and the accepted information about the user.

43. The apparatus of claim 42 wherein the information related to the at least one advertisement is represented as a first feature vector,

wherein the accepted information associated with a user request and the accepted information about the user is represented as a second feature vector, and

wherein the similarity is determined using at least a cosine distance between the first feature vector and the second feature vector.

44. The apparatus of claim 43 wherein each of at least some items of information of at least one of the first and second feature vectors have an associated importance weight, and

wherein the similarity is determined using at least a cosine distance between at least a part of the first feature vector and at least a part of the second feature vector.

45. The apparatus of claim 44 wherein the at least a part of the at least one of the first and second feature vectors includes items of information with the highest importance weights among the items of information of the first feature vector.

46. The apparatus of claim 43 wherein each of at least some items of information of the first feature vector have an associated importance weight, and wherein each of at least some items of information of the second feature vector have an associated importance weight, the apparatus further comprising:

c) means for ordering

i) at least some of the items of information of the first feature vector in accordance with their importance weight, and

ii) at least some of the items of information of the second feature vector in accordance with their importance weight.

47. The apparatus of claim 42 wherein the information associated with the at least one advertisement includes terms and term frequencies,

wherein the accepted information associated with a user request and the accepted information about the user includes terms and term frequencies, and

wherein the means for determining similarity uses at least a term frequency-inverse document frequency measure.

48. The apparatus of claim 42 wherein the information associated with the at least one advertisement includes a first set of items of information,

wherein the accepted information associated with a user request and the accepted information about the user includes a second set of items of information, and

wherein each of the first and second items of information have associated importance weights, the apparatus further comprising:

d) means for determining the associated importance weights using at least a feature selection procedure selected from a group of feature selection procedures consisting of (A) mutual information, (B) chi-square fit, (C) correlation, and (D) manual selection.

49. The apparatus of claim 42 wherein the information associated with the at least one advertisement includes a first set of items of information,

wherein the accepted information associated with a user request and the accepted information about the user includes a second set of items of information, and

wherein each of the first and second items of information have associated importance weights, the apparatus further comprising:

c) means for determining the associated importance weights using at least a performance of an advertisement served in the past, wherein the advertisement included a score that was determined using at least some of the first and second items of information.

50. The apparatus of claim 39 further comprising:

c) means for ordering at least two of advertisements using their determined scores.

51. The apparatus of claim 50 further comprising:

d) means for determining a final set of at least one advertisement using the ordering of the at least two advertisements.

52. The apparatus of claim 39 further comprising:

c) means for filtering a first set of advertisements, using their determined scores, to generate a second set of advertisements.

53. The apparatus of claim 39 wherein the user request is a search query and wherein the information associated with the user request includes at least one keyword from the search query.

54. The apparatus of claim 39 wherein the user request is a document request and wherein the information associated with the user request includes document information.

55. The apparatus of claim 39 wherein the user request is a search query and wherein the information associated with the user request includes document information of a search result page responsive to the search query.

56. The apparatus of claim 39 wherein the information about the user includes at least one of (a) user profile information and (b) user behavior information.

58. The apparatus of claim 39 wherein the information about the user includes demographic information which includes at least one information item selected from a group of information items consisting of (A) age, (B) age range, (C) age category, (D) sex, (E) income, (F) income range, (G) income category, (H) marital status, (I) education level, and (J) parental status.

59. The apparatus of claim 39 wherein the information about the user includes geographic information.

60. The apparatus of claim 39 wherein the information about the user includes psychographic information.

62. The apparatus of claim 39 wherein the information about the user includes user behavior information which includes at least one information item selected from a group of information items consisting of (A) information related to previous search queries submitted by the user, (B) information related to previous search queries submitted to a particular search engine by the user, (C) information related to previous advertisements served for rendering to the user, (D) information related to previous advertisements served for rendering by the user and selected, (E) document information of a document viewed by the user, (F) document information about a document edited by the user, (G) previous purchases by the user, and (H) previous on-line purchases by the user.

63. The apparatus of claim 39 further comprising:

c) an ad server for serving at least one advertisement using, at least, the determined score.

64. The apparatus of claim 63 further comprising:

d) means for accepting user behavior responsive to the at least one advertisement served; and

e) means for adjusting one or more importance weights associated with one or more items of user information using, at least, the accepted user behavior.

65. The apparatus of claim 64 wherein the accepted user behavior corresponds to a measure of performance of the advertisement.

66. The apparatus of claim 64 wherein the means for determining a score uses only a first set of items of user information, wherein the one or more items of user information having weights adjusted belong to a second set of items of user information, and wherein the second set of items of user information is larger than the first set of items of user information.

67. The apparatus of claim 66 wherein the second set of items of user information includes the first set of items of user information.

68. The apparatus of claim 39 wherein at least one of the accepted information associated with the user request and the accepted information about the user includes items of information having associated importance weights, and

wherein the means for determining a score for at least one advertisement uses both the accepted information associated with a user request and the accepted information about the user processes items of information in an order of their importance weights.

69. The apparatus of claim 68 wherein the means for determining a score for at least one advertisement terminates determination processing upon the occurrence of an event regardless of whether all items of information were considered in the score determination.

70. The apparatus of claim 69 wherein the event is a timer expiration.

57. (canceled)

61. (canceled)

71. Apparatus comprising:

a) an input for accepting

i) information associated with a user request, and

ii) information about the user that submitted the user request;

b) means for determining a first set of advertisements of general relevance to the user request; and

c) means, for at least some of the advertisements of the first set of advertisements, for determining a score using at least the accepted information about the user.

72. The apparatus of claim 71 wherein the user request is a search query.

73. The apparatus of claim 71 wherein the user request is a document request.

74. The apparatus of claim 71 wherein the information about the user includes at least one of (a) user profile information and (b) user behavior information.

75. The apparatus of claim 71 wherein the user request is a search query.

76. Apparatus comprising:

a) an input for accepting

i) information associated with a user request,

ii) information about the user that submitted the user request;

b) means for determining a first score for each of a plurality of ad groups using at least ad group information and at least one of (i) user request information and (ii) user information;

c) means for selecting an ad group using the first score; and

d) means for selecting at least one advertisement from the selected ad group using at least the user information.