Ad placement

• US 10,229,428 B2
• Filed: 09/15/2012
• Issued: 03/12/2019
• Est. Priority Date: 11/08/1999
• Status: Expired due to Term

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Ferber, John B., Ferber, Scott, Kretsinger, Stein E., Luenberger, Robert, Luenberger, David
• Primary Examiner(s): Munson, Patricia H
• Application Number:
  US13/620,899
• Publication Number:
  US 20130046630A1
• Time in Patent Office: 2,369 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

This invention concerns optimal ad selection for Web pages by selecting and updating an attribute set, obtaining and updating an ad-attribute profile, and optimally choosing the next ad. The present invention associates a set of attributes with each customer. The attributes reflect the customers'"'"' interests and they incorporate the characteristics that impact ad selection. Similarly, the present invention associates with each ad an ad-attribute profile in order to calculate a customer'"'"'s estimated ad selection probability and measure the uncertainty in that estimate. An ad selection algorithm optimally selects which ad to show based on the click probability estimates and the uncertainties regarding these estimates.

Claims

1. A method comprising:

detecting, by at least one server, one or more interests of a user based at least in part upon actions of the user on one or more network-based mediums over a period of time;

identifying, by the at least one server, one or more advertisements to serve to the user that relate to the one or more interests;

detecting that the user is currently using the one or more network-based mediums to search for a type of product or service;

identifying, by the at least one server, one or more additional advertisements to serve to the user that relate to the type of product or service for which the user is currently searching by searching advertisements relating to the type of product or service for which the user is currently searching that provide a high probability of being selected by the user, wherein identifying the one or more additional advertisements improves the speed of searching for the one or more additional advertisements and serving advertisements to a client device associated with the user;

determining, by the at least one server, if serving the one or more additional advertisements related to the type of product or service to the user would exceed a pre-set tolerance comprising a target number of times the one or more additional advertisements are to be served to the user;

if serving the one or more additional advertisements related to the type of product or service to the user would not exceed the pre-set tolerance, serving, by the at least one server over a network to the client device associated with the user, the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search for in place of serving the one or more advertisements related to the one or more interests while the user is currently searching for the type of product or service; and

if serving the one or more additional advertisements related to the type of product or service to the user would exceed the pre-set tolerance, serving, by the at least one server over the network to the client device associated with the user, the one or more advertisements related to the one or more interests rather than the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search.

2. The method as recited in claim 1, further comprising serving the one or more additional advertisements to the client device associated with the user over a communications network associated with the one or more network-based mediums with which the user is searching.

3. The method as recited in claim 2, further comprising serving the one or more additional advertisements over the communications network to a mobile device associated with the user.

4. The method as recited in claim 3, wherein detecting one or more interests of the user comprises detecting one or more activities of the user on a medium of the one or more network-based mediums on the mobile device.

5. The method as recited in claim 4, further comprising serving the one or more additional advertisements via a second the medium of the one or more network-based mediums on the mobile device.

6. The method as recited in claim 1, wherein the one or more network-based mediums comprise a webpage provided to the client device associated with the user.

7. The method as recited in claim 1, wherein the one or more network-based mediums comprise a software program implemented on the client device associated with the user.

8. The method as recited in claim 2, further comprising serving the one or more additional advertisements to a webpage provided to the client device associated with the user.

9. The method as recited in claim 2, further comprising serving the one or more advertisements to the client device associated with the user over the communications network after serving the one or more additional advertisements to the client device associated with the user.

10. The method as recited in claim 2, wherein the communications network comprises the Internet.

11. The method as recited in claim 1, wherein the detecting that the user is currently searching for a type of product or service comprises identifying that the user is browsing a previously identified website.

12. The method as recited in claim 11, wherein the previously identified website is a website that compares products.

13. The method as recited in claim 1, wherein detecting one or more interests of a user based at least in part upon actions of the user on a medium of the one or more network-based mediums over a period of time comprises detecting one or more websites browsed by the user.

14. The method as recited in claim 1, wherein identifying the one or more advertisements to serve to the client device associated with the user that relate to the one or more interests comprises:

determining a probability that each advertisement of the one or more advertisements will be selected by the user; and

selecting the advertisement with the highest probability.

15. The method as recited in claim 14, further comprising determining a projected click-thru-rate for each advertisement of the one or more advertisements.

16. The method as recited in claim 15, further comprising measuring a percentage of time the user spent browsing in one or more interest categories during the period of time.

17. The method as recited in claim 16, wherein the probability that a given advertisement will be selected by the user is a function of the projected click-thru-rate for the given advertisement and the percentage of time the user spent browsing in one or more interest categories related to the given advertisement.

18. The method as recited in claim 15, wherein the click-thru-rate for a particular advertisement comprises a ratio of a number of times the particular advertisement has been clicked over a number of times the particular advertisement has been shown;

and

the method further comprising adjusting the probability for the particular advertisement based on an uncertainty level of the click-thru-rate, wherein the uncertainty level is inversely proportional to a number of times the particular advertisement has been previously served.

19. A non-transitory computer-readable storage medium including a set of instructions that, when executed, cause at least one processor to perform steps comprising:

detecting one or more interests of a user based at least in part upon actions of the user on one or more network-based mediums over a period of time;

identifying one or more advertisements to serve to the user that relate to the one or more interests;

detecting that the user is currently using the one or more network-based mediums to search for a type of product or service;

identifying one or more additional advertisements to serve to the user that relate to the type of product or service for which the user is currently searching by searching advertisements relating to the type of product or service for which the user is currently searching that provide a high probability of being selected by the user, wherein identifying the one or more additional advertisements improves the speed of searching for the one or more additional advertisements and serving advertisements to a client device associated with the user;

determining if serving the one or more additional advertisements related to the type of product or service to the user would exceed a pre-set tolerance comprising a target number of times the one or more additional advertisements are to be served to the user;

if serving the one or more additional advertisements related to the type of product or service to the user would not exceed the pre-set tolerance, serving, over a network to the ft-client device associated with the user, the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search for in place of serving the one or more advertisements related to the one or more interests while the user is currently searching for the type of product or service; and

if serving the one or more additional advertisements related to the type of product or service to the user would exceed the pre-set tolerance, serving, over the network to the client device associated with the user, the one or more advertisements related to the one or more interests rather than the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search.

20. The computer-readable storage medium as recited in claim 19, further comprising instructions that, when executed, cause the at least one processor to serve the one or more additional advertisements to the client device associated with the user over a communications network associated with the one or more network-based mediums with which the user is searching.

21. The computer-readable storage medium as recited in claim 20, further comprising instructions that, when executed, cause the at least one processor to serve the one or more additional advertisements over the communications network to a mobile device associated with the user.

22. The computer-readable storage medium as recited in claim 21, wherein detecting one or more interests of the user comprises detecting one or more activities of the user on a medium of the one or more network-based mediums on the mobile device.

23. The computer-readable storage medium as recited in claim 22, further comprising instructions that, when executed, cause the at least one processor to serve additional advertisements via a second the medium of the one or more network-based mediums on the mobile device.

24. The computer-readable storage medium as recited in claim 19, wherein the one or more network-based mediums comprise a webpage provided to the client device associated with the user.

25. The computer-readable storage medium as recited in claim 19, wherein the one or more network-based mediums comprise a software program implemented on the client device associated with the user.

26. The computer-readable storage medium as recited in claim 20, further comprising instructions that, when executed, cause at least one processor to serve the one or more additional advertisements to a webpage provided to the client device associated with the user.

27. The computer-readable storage medium as recited in claim 20, further comprising instructions that, when executed, cause at least one processor to serve the one or more advertisements to the client device associated with the user over the communications network after serving the one or more additional advertisements to the client device associated with the user.

28. The computer-readable storage medium as recited in claim 20, wherein the communications network comprises the Internet.

29. The computer-readable storage medium as recited in claim 19, wherein the detecting that the user is currently searching for a type of product or service comprises identifying that the user is browsing a previously identified website.

30. The computer-readable storage medium as recited in claim 29, wherein the previously identified website is a website that compares products.

31. The computer-readable storage medium as recited in claim 19, wherein detecting one or more interests of a user based at least in part upon actions of the user on a medium over a period of time comprises detecting one or more websites browsed by the user.

32. The computer-readable storage medium as recited in claim 19, wherein identifying the one or more additional advertisements to serve to the user that relate to the type of product or service comprises:

determining a probability that each advertisement of the additional advertisements will be selected by the user; and

selecting the additional advertisement with the highest probability.

33. The computer-readable storage medium as recited in claim 32, further comprising instructions that, when executed, cause at least one processor to determine a projected click-thru-rate for each additional advertisement of the one or more additional advertisements.

34. The computer-readable storage medium as recited in claim 33, further comprising instructions that, when executed, cause at least one processor to measure a percentage of time the user spent browsing for the type of product or service.

35. The computer-readable storage medium as recited in claim 34, wherein the probability that a given additional advertisement will be selected by the user is a function of the projected click-thru-rate for the given advertisement and the percentage of time the user spent browsing for the type of product or service related to the given additional advertisement.

36. The computer-readable storage medium as recited in claim 33, wherein the click-thru-rate for a particular additional advertisement comprises a ratio of a number of times the particular additional advertisement has been clicked over a number of times the particular additional advertisement has been shown;

and

further comprising instructions that, when executed, cause at least one processor to adjust the probability for the particular advertisement based on an uncertainty level of the click-thru-rate, wherein the uncertainty level is inversely proportional to a number of times the particular advertisement has been previously served.

37. A method comprising:

associating, by at least one server, long-term attributes with a user profile, the long-term attributes reflecting interests of a user as indicated at least in part by activities of the user on one or more network-based mediums over a period of time;

identifying, by the at least one server, one or more advertisements to serve to the user that relate to the long-term attributes;

identifying, by the at least one server, short-term attributes associated with a type of product or service;

detecting, by at least one server, that the user is currently using the one or more network-based mediums to search for the type of product or service;

identifying, by the at least one server, one or more additional advertisements to serve to the user that relate to the short-term attributes by searching advertisements relating to the type of product or service for which the user is currently searching that provide a high probability of being selected by the user, wherein identifying the one or more additional advertisements improves the speed of searching for the one or more additional advertisements and serving advertisements to a client device associated with the user;

determining, by the at least one server, if serving the one or more additional advertisements related to the short-term attributes to the user would exceed a pre-set tolerance comprising a target number of times the one or more additional advertisements related to the short-term attributes are to be served to the user;

if serving the one or more additional advertisements related to the short-term attributes to the user would not exceed the pre-set tolerance, serving by the at least one server over a network, the one or more additional advertisements related to the short-term attributes over a communications network to the client device associated with the user while the user is currently using the one or more network-based mediums to search for the type of product or service prior to serving the one or more advertisements related to the long-term attributes; and

if serving the one or more additional advertisements related to the short-term attributes to the user would exceed the pre-set tolerance, serving, over the communication network, the one or more advertisements related to the interests to the client device associated with the user rather than the one or more additional advertisements related to the short-term attributes for which the user is currently using the one or more network-based mediums to search.

38. The method as recited in claim 37, wherein identifying the one or more additional advertisements to serve to the user that relate to the short-term attributes comprises:

determining a probability that each advertisement of the one or more additional advertisements related to the short-term attributes will be selected by the user; and

serving the additional advertisement with a high probability while the user is currently searching for the type of product or service.

39. The method as recited in claim 38, wherein the probability that a given additional advertisement will be selected by the user is a function of a click-thru-rate for the given additional advertisement.

40. The method as recited in claim 39, wherein the click-thru-rate for a particular additional advertisement comprises a ratio of a number of times the particular additional advertisement has been clicked over a number of times the particular additional advertisement has been served.

41. The method as recited in claim 40, further comprising adjusting the probability for each additional advertisement based on an uncertainty level of the click-thru-rate.

42. The method as recited in claim 41, wherein the uncertainty level is inversely proportional to a number of times the particular additional advertisement has been previously served.

43. The method as recited in claim 39, wherein the probability that a given additional advertisement will be selected by the user is a function of how related a given additional advertisement is to the short-term attributes.

44. The method as recited in claim 37, further comprising serving the one or more additional advertisements to a medium of the one or more network-based mediums on a mobile device.

45. The method as recited in claim 44, further comprising serving the one or more additional advertisements to a medium of the one or more network-based mediums on the mobile device.

46. The method as recited in claim 45, wherein the one or more network-based mediums comprise a webpage provided to the client device associated with the user.

47. The method as recited in claim 45, wherein the one or more network-based mediums comprise a software program implemented on the client device associated with the user.

48. The method as recited in claim 37, further comprising serving the one or more additional advertisements to a webpage provided to the client device associated with the user.

49. The method as recited in claim 37, wherein the one or more network-based mediums comprise an Internet browser implemented on the client device associated with the user.

50. A non-transitory computer-readable storage medium including a set of instructions that, when executed, cause at least one processor to perform steps comprising:

associating long-term attributes with a user profile, the long-term attributes reflecting interests of a user as indicated at least in part by activities of the user on one or more network-based mediums over a period of time;

identifying one or more advertisements to serve to the user that relate to the long-term attributes;

identifying short-term attributes associated with a type of product or service;

detecting, by at least one processor, that the user is currently using the one or more network-based mediums to search for the type of product or service;

identifying one or more additional advertisements to serve to the user that relate to the short-term attributes by searching advertisements relating to the type of product or service for which the user is currently searching that provide a high probability of being selected by the user, wherein identifying the one or more additional advertisements improves the speed of searching for the one or more additional advertisements and serving advertisements to a client device associated with the user;

determining if serving the one or more additional advertisements related to the short-term attributes to the user would exceed a pre-set tolerance comprising a target number of times the one or more additional advertisements related to the short-term attributes are to be served to the user;

if serving the one or more additional advertisements related to the short-term attributes to the user would not exceed the pre-set tolerance, serving the one or more additional advertisements related to the short-term attributes over a communications network to the client device associated with the user while the user is currently using the one or more network-based mediums to search for the type of product or service prior to serving the one or more advertisements related to the long-term attributes; and

if serving the one or more additional advertisements related to the short-term attributes to the user would exceed the pre-set tolerance, serving, over the communication network, the one or more advertisements related to the interests to the client device associated with the user rather than the one or more additional advertisements related to the short-term attributes for which the user is currently using the one or more network-based mediums to search.

51. The computer-readable storage medium as recited in claim 50, wherein identifying the one or more advertisements to serve to the user that relate to the long-term attributes comprises:

determining a probability that each advertisement of the one or more advertisements related to the long-term attributes will be selected by the user; and

selecting the advertisement with a high probability.

52. The computer-readable storage medium as recited in claim 51, wherein the probability that a given advertisement will be selected by the user is a function of a click-thru-rate for the given advertisement.

53. The computer-readable storage medium as recited in claim 52, wherein the click-thru-rate for a particular advertisement comprises a ratio of a number of times the particular advertisement has been clicked over a number of times the particular advertisement has been served.

54. The computer-readable storage medium as recited in claim 53, further comprising instructions that, when executed, cause at least one processor to adjust the probability for each advertisement based on an uncertainty level of the click-thru-rate.

55. The computer-readable storage medium as recited in claim 54, wherein the uncertainty level is inversely proportional to a number of times the particular advertisement has been previously served.

56. The computer-readable storage medium as recited in claim 52, wherein the probability that a given advertisement will be selected by the user is a function of how related a given advertisement is to the long-term attributes.

57. The computer-readable storage medium as recited in claim 50, further comprising instructions that, when executed, cause at least one processor to serve the one or more additional advertisements to a mobile device.

58. The computer-readable storage medium as recited in claim 57, further comprising instructions that, when executed, cause at least one processor to serve the one or more additional advertisements to a medium of the one or more network-based mediums on the mobile device.

59. The computer-readable storage medium as recited in claim 58, wherein the one or more network-based mediums comprise a webpage provided to the client device associated with the user.

60. The computer-readable storage medium as recited in claim 58, wherein the one or more network-based mediums comprise a software program implemented on the client device associated with the user.

61. The computer-readable storage medium as recited in claim 50, further comprising instructions that, when executed, cause at least one processor to serve the one or more additional advertisements to a webpage provided to the client device associated with the user.

62. The computer-readable storage medium as recited in claim 50, wherein the one or more network-based mediums comprise an Internet browser implemented on the client device associated with the user.

63. A method comprising:

detecting, by at least one server, one or more interests of a user based at least in part upon actions of the user on one or more network-based mediums on a mobile device associated with the user;

identifying, by the at least one server, one or more advertisements to serve to the user that relate to the one or more interests;

detecting that the user is currently using the one or more network-based mediums to search for a type of product or service;

identifying, by the at least one server, one or more additional advertisements to serve to the user that relate to the type of product or service for which the user is currently searching by searching advertisements relating to the type of product or service for which the user is currently searching that provide a high probability of being selected by the user, wherein identifying the one or more additional advertisements improves the speed of searching for the one or more additional advertisements and serving advertisements to a client device associated with the user;

determining, by the at least one server, if serving the one or more additional advertisements related to the type of product or service to the user would exceed a pre-set tolerance comprising a target number of times the one or more additional advertisements are to be served to the user;

if serving the one or more additional advertisements related to the type of product or service to the user would not exceed the pre-set tolerance, serving, over a network, the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search for to the mobile device associated with the user in place of serving the one or more advertisements related to the one or more interests while the user is currently searching for the type of product or service; and

if serving the one or more additional advertisements related to the type of product or service to the user would exceed the pre-set tolerance, serving, by the at least one server over a network, the one or more advertisements related to the one or more interests to the mobile device associated with the user rather than the one or more additional advertisements related to the type of product or service for which the user is currently using the one or more network-based mediums to search.

64. The method as recited in claim 63, further comprising serving the one or more additional advertisements to the mobile device over a communications network associated with the one or more network-based mediums with which the user is searching.

65. The method as recited in claim 64, further comprising serving the one or more advertisements over the communications network to the mobile device associated with the user.

66. The method as recited in claim 64, further comprising serving the one or more additional advertisements to a medium of the one or more network-based mediums on the mobile device.

67. The method as recited in claim 66, wherein the one or more network-based mediums comprise a webpage provided to the mobile device associated with the user.

68. The method as recited in claim 66, wherein the one or more network-based mediums comprise a software program implemented on the mobile device associated with the user.

69. The method as recited in claim 64, further comprising serving the one or more advertisements to the mobile device associated with the user over the communications network after serving the one or more additional advertisements to the mobile device associated with the user.

70. The method as recited in claim 64, wherein the communications network comprises the Internet.

71. The method as recited in claim 63, further comprising serving the one or more additional advertisements to a webpage provided to the mobile device associated with the user.

72. The method as recited in claim 63, wherein the detecting that the user is currently searching for a type of product or service comprises identifying that the user is browsing a previously identified website.

73. The method as recited in claim 72, wherein the previously identified website is a website that compares products.

74. The method as recited in claim 63, wherein identifying the one or more advertisements to serve to the user that relate to the one or more interests comprises:

determining a probability that each advertisement of the one or more advertisements will be selected by the user; and

selecting the advertisement with a high probability.

75. The method as recited in claim 74, further comprising determining a projected click-thru-rate for each advertisement of the one or more advertisements.

76. The method as recited in claim 75, wherein the click-thru-rate for a particular advertisement comprises a ratio of a number of times the particular advertisement has been clicked over a number of times the particular advertisement has been shown;

and

the method further comprising adjusting the probability for the particular advertisement based on an uncertainty level of the click-thru-rate, wherein the uncertainty level is inversely proportional to a number of times the particular advertisement has been previously served.