METHOD AND SYSTEM FOR ELECTRONIC ADVERTISING

• US 20110054997A1
• Filed: 06/04/2010
• Published: 03/03/2011
• Est. Priority Date: 06/04/2009
• Status: Active Grant

• Current Assignee: Black CROW AI Incorporated, Hercules Capital, Inc.
• Original Assignee: Intent Media Incorporated
• Inventors: Pritchard, Adam, Hartmann, Joshua, Tassone, Damon, Feuerstein, Joshua, Taqqu, Jonathan, Rajan, Arun, Schrader, Kurt, Harris, Richard
• Granted Patent: US 8,527,341 B2
• Time in Patent Office: Days
• US Class Current: 705/14.42
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0253 During e-commerce, i.e. online transactions
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

A method of delivering advertising in an online environment includes determining an intent of a user interacting with an e-commerce website, and determining a hurdle rate that is based at least on the user intent and which identifies a threshold amount to be bid by an advertiser in order to display an advertisement to the user. The method further includes selecting, from a plurality of advertisements, an optimal advertisement having an advertiser bid that exceeds the hurdle rate, and displaying the optimal advertisement to the user in an interface of a client computer system.

Claims

1. A distributed computer system comprising:

an e-commerce component adapted to determine a context of a user operating a client computer to interact with an e-commerce website;

a translation engine operable to translate the context into one or more context targets;

a hurdle rate engine operable to determine, based on the one or more context targets, a hurdle rate that identifies a threshold amount to be bid by an advertiser in order to display an advertisement to the user;

a decision engine operable to select, from a plurality of advertisements each having a respective bid, an optimal advertisement to be displayed to the user, the optimal advertisement having a respective bid that exceeds the hurdle rate; and

a delivery component adapted to display the optimal advertisement to the user.

2. The system according to claim 1, further comprising a candidate advertisement engine operable to generate a list of candidate advertisements based on the context of the user.

3. The system according to claim 1, further comprising an optimization engine operable to determine a contribution per visitor outcome for each of one or more advertisements of the plurality of advertisements.

4. The system according to claim 3, wherein the contribution per visitor outcome is based on the hurdle rate.

5. The system according to claim 3, wherein the contribution per visitor outcome is based on an expected return to purchase value.

6. The system according to claim 3, further comprising a segmentation engine operable to identify a relationship between the user and a publisher.

7. The system according to claim 6, wherein the contribution per visitor outcome is based on the relationship between the user and the publisher.

8. The system according to claim 3, wherein the contribution per visitor outcome is a positive contribution per visitor outcome, and wherein the optimal advertisement further has a positive contribution per visitor outcome.

9. The system according to claim 1, further comprising an outcome engine operable to analyze an outcome of displaying the optimal advertisement to the user.

10. The system according to claim 1, further comprising a translation database coupled to the translation engine.

11. The system according to claim 1, further comprising a hurdle rate database coupled to the hurdle rate engine.

12. The system according to claim 2, further comprising an advertising campaign database coupled to the candidate advertisement engine.

13. The system according to claim 3, further comprising an optimization database coupled to the optimization engine.

14. The system according to claim 1, wherein the delivery component includes an advertisement interface of the client computer coupled to the decision engine.

15. The system according to claim 1, further comprising a bid component operable to receive, from an advertiser, at least one bid for one or more of the plurality of advertisements.

16. A method of delivering advertising in an online environment comprising acts of:

determining an intent of a user interacting with an e-commerce website;

determining a hurdle rate, based at least on the intent of the user, that identifies a threshold amount to be bid by an advertiser in order to display an advertisement to the user interacting with the e-commerce website;

selecting, from a plurality of advertisements, an optimal advertisement having an advertiser bid that exceeds the determined hurdle rate; and

displaying the optimal advertisement to the user in an interface of a client computer system.

17. The method according to claim 16, further comprising receiving, from a publisher of the e-commerce website, an advertisement request.

18. The method according to claim 17, wherein the advertisement request includes one or more keywords, and wherein the intent of the user is based at least in part on the one or more keywords.

19. The method according to claim 17, further comprising translating the advertisement request into one or more intent targets.

20. The method according to claim 19, wherein translating the advertisement request includes selecting each of the one or more intent targets from a plurality of normalized intent targets based on information included in the advertisement request, and wherein the plurality of normalized intent targets is stored in an intent target taxonomy database.

21. The method according to claim 19, wherein determining the hurdle rate includes adjusting the hurdle rate in relation to the one or more intent targets.

22. The method according to claim 19, wherein determining the hurdle rate includes adjusting the hurdle rate based on a historical average conversion rate of each of the one or more intent targets.

23. The method according to claim 19, wherein determining the hurdle rate includes adjusting the hurdle rate based on an average contribution margin of a completed transaction for the one or more intent targets.

24. The method according to claim 16, wherein determining the intent of the user further includes translating the advertisement request into one or more process contexts.

25. The method according to claim 24, wherein translating the advertisement request includes selecting each of the one or more process contexts from a plurality of normalized process contexts based on information included in the advertisement request, and wherein the plurality of normalized process contexts is stored in a process context taxonomy database.

26. The method according to claim 24, wherein determining the hurdle rate includes adjusting the hurdle rate based on the one or more process contexts.

27. The method according to claim 16, further comprising selecting, from the plurality of advertisements, one or more candidate advertisements, and wherein the optimal advertisement is selected from the one or more candidate advertisements.

28. The method according to claim 27, wherein each of the one or more candidate advertisements is selected based on the hurdle rate.

29. The method according to claim 27, wherein each of the one or more candidate advertisements is selected based on a relationship between the user and the publisher.

30. The method according to claim 27, further comprising determining, for each of the one or more candidate advertisements, an advertisement revenue potential, and wherein the selected optimal advertisement has an advertisement revenue potential exceeding the determined advertisement revenue potential of each of the others of the one or more candidate advertisements.

31. The method according to claim 30, wherein the advertisement revenue potential is based on a return to visit rate.

32. The method according to claim 30, wherein the advertisement revenue potential is based on an expected return to purchase value.

33. The method according to claim 30, wherein the advertisement revenue potential is based on a fully loaded expected transaction value.

34. The method according to claim 16, wherein the optimal advertisement is associated with a relevance type selected by the publisher.

35. The method according to claim 34, wherein the relevance type is one of retailer discovery, substitute discovery, and complement discovery.

36. The method according to claim 16, further comprising generating a dynamic uniform resource locator based on the intent of the user, and including the dynamic uniform resource locator within the optimal advertisement.

37. The method according to claim 16, further comprising configuring a creative content of the optimal advertisement such that the creative content targets the intent of the user.

38. The method according to claim 16, wherein the hurdle rate is based on one or more outcomes related to displaying the optimal advertisement to the user.

39. A method of delivering advertising in an online environment comprising acts of:

identifying a characteristic of a user interacting with an e-commerce website;

determining a hurdle rate for displaying an advertisement to the user at the e-commerce website based at least on the determined characteristic of the user;

determining whether to display an advertisement to the user based on the characteristic of the user, and, if so,

selecting an advertisement from a plurality of advertisements based on an intent of the user, wherein the selected advertisement is offered by an advertiser for at least the hurdle rate; and

delivering the selected advertisement to the user in an interface of a client computer system.

40. The method according to claim 39, further comprising receiving an advertisement request from a publisher.

41. The method according to claim 40, wherein the advertisement request includes the characteristic of the user.

42. The method according to claim 39, wherein the characteristic of the user is one of past purchaser and non-past purchaser.

43. The method according to claim 39, wherein the characteristic of the user is loyalty program member.

44. The method according to claim 39, wherein the characteristic of the user is based on historical data provided by the publisher.

45. The method according to claim 39, wherein the characteristic of the user is based on the intent of the user.

46. The method according to claim 39, wherein the characteristic of the user is based on at least one visitor acquisition mechanism.

47. The method according to claim 46, wherein the visitor acquisition mechanism is at least one of a paid search, a natural search, and an e-mail.

48. The method according to claim 39, wherein the characteristic of the user is based on an inter-session behavior of the user.

49. The method according to claim 39, wherein the characteristic of the user is based on an intra-session behavior of the user.

50. The method according to claim 39, wherein the characteristic of the user is collected from one of the e-commerce website and the client computer system.

51. The method according to claim 39, wherein determining the hurdle rate includes adjusting the hurdle rate based on the characteristic of the user.

52. The method according to claim 39, wherein the characteristic is one of a high value visitor and a low value visitor.

53. A computer readable medium having stored thereon sequences of instructions including instructions that will cause a processor to perform a method of delivering advertising comprising acts of:

determining an intent of a user interacting with an e-commerce website;

determining a hurdle rate, based at least on the intent of the user, that identifies a threshold amount to be bid by an advertiser in order to display an advertisement to the user interacting with the e-commerce website;

selecting, from a plurality of advertisements, an optimal advertisement having an advertiser bid that exceeds the determined hurdle rate; and

displaying the optimal advertisement to the user in an interface of a client computer system.

54. A computer readable medium having stored thereon sequences of instructions including instructions that will cause a processor to perform a method of delivering advertising comprising acts of:

identifying a characteristic of a user interacting with an e-commerce website;

determining a hurdle rate for displaying an advertisement to the user at the e-commerce website based at least on the determined characteristic of the user;

determining whether to display an advertisement to the user based on the characteristic of the user, and, if so,

selecting an advertisement from a plurality of advertisements based on an intent of the user, wherein the selected advertisement is offered by an advertiser for at least the hurdle rate; and

delivering the selected advertisement to the user in an interface of a client computer system.