USING ESTIMATED AD QUALITIES FOR AD FILTERING, RANKING AND PROMOTION

• US 20110015988A1
• Filed: 09/24/2010
• Published: 01/20/2011
• Est. Priority Date: 12/30/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: WRIGHT, Daniel, TANG, Diane, PREGIBON, Daryl
• Granted Patent: US 8,429,012 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 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• 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 30/0271 Personalized advertisement

Abstract

A system obtains a first parameter (QP₁) associated with a quality of an advertisement among multiple advertisements, where the first quality parameter (QP₁) does not include a click through rate (CTR). The system functionally combines the first quality parameter (QP₁) with at least one other parameter and uses the functional combination to filter, rank or promote the advertisement among the multiple advertisements.

Claims

1. A method, implemented by one or more processors associated with one or more server devices, the method comprising:

obtaining, using one or more processors associated with the one or more server devices, a first parameter (QP₁) associated with a quality of an advertisement among a plurality of advertisements, where the first quality parameter (QP₁) comprises a probability that the advertisement is of a certain measure of quality;

functionally combining, using one or more processors associated with the one or more server devices, the first quality parameter (QP₁) with a click-through-rate (CTR) associated with the advertisement, and a cost-per-click (CPC) associated with the advertisement; and

filtering, ranking, or promoting, using one or more processors associated with the one or more server devices, the advertisement, among the plurality of advertisements, based on the functional combination of the first quality parameter (QP₁), the CTR, and the CPC.

32. The method of claim 1, where the probability that the advertisement is of a certain measure of quality comprises:

a probability that the advertisement matches measured session features associated with a user selection of the advertisement, or

a probability that the advertisement does not match measured session features associated with a user selection of the advertisement.

33. The method of claim 1, where filtering the advertisement comprises preventing the advertisement from being provided to a user.

34. The method of claim 1, where functionally combining the first quality parameter (QP₁) with the CTR and CPC comprises:

multiplying, using one or more processors associated with the one or more server devices, the first quality parameter (QP₁) with the CTR to obtain a result.

35. The method of claim 34, where filtering, using the functional combination of the first quality parameter (QP₁) with the CTR and the CPC, comprises:

comparing, using one or more processors associated with the one or more server devices, the result with a threshold value to determine whether to filter the advertisement.

36. The method of claim 34, where promoting the advertisement, using the functional combination, comprises:

comparing, using one or more processors associated with the one or more server devices, the result with a threshold value to determine whether to promote the advertisement among the plurality of advertisements.

37. The method of claim 1, where functionally combining the first quality parameter (QP₁) with the CTR and CPC comprises:

multiplying, using one or more processors associated with the one or more server devices, the first quality parameter (QP₁) by the CTR and the CPC to obtain a result.

38. The method of claim 37, where ranking the advertisement, using the functional combination, comprises:

ranking, using one or more processors associated with the one or more server devices, the advertisement, among the plurality of advertisements, using the result.

39. The method of claim 1, further comprising:

obtaining, using one or more processors associated with the one or more server devices, a second quality parameter (QP₂) that indicates a different measure of quality of the advertisement; and

functionally combining, using one or more processors associated with the one or more server devices, the second quality parameter (QP₂) with the first quality parameter (QP₁), the CTR, and the CPC.

40. The method of claim 39, where functionally combining the second quality parameter (QP₂) with the first quality parameter (QP₁) and the CTR and CPC comprises obtaining a result of:

CTR*CPC+K₁*QP₁*CTR−

K₂*QP₂*CTR, where K₁ and K₂ are constants.

41. The method of claim 40, where promoting the advertisement, using the functional combination, comprises:

comparing, using one or more processors associated with the one or more server devices, the result with a threshold value to determine whether to promote the advertisement among the plurality of advertisements.

2-31. -31. (canceled)

42. A computer-readable memory device that stores computer-executable instructions, the computer-readable memory device comprising:

instructions for obtaining a first parameter (QP₁) associated with a quality of an advertisement, among a plurality of advertisements, where the first quality parameter (QP₁) comprises a probability that the advertisement is of a certain measure of quality;

instructions for functionally combining the first quality parameter (QP₁) with a click-through-rate (CTR) and a cost-per-click (CPC) associated with the advertisement; and

instructions for filtering, ranking, or promoting the advertisement, among the plurality of advertisements, based on the functional combination of the first quality parameter (QP₁), the CTR, and the CPC.

43. The computer-readable memory device of claim 42, where the probability that the advertisement is of a certain measure of quality comprises:

a probability that the advertisement matches measured session features associated with a user selection of the advertisement, or

a probability that the advertisement does not match measured session features associated with a user selection of the advertisement.

44. The computer-readable memory device of claim 42, where filtering the advertisement comprises preventing the advertisement from being provided to a user.

45. The computer-readable memory device of claim 42, where the instructions for functionally combining the first quality parameter (QP₁) with the CTR and the CPC comprises:

instructions for multiplying the first quality parameter (QP₁) with the CTR;

QP₁*CTR.

46. The computer-readable memory device of claim 45, where the instructions for using the function combination to filter the advertisement comprises:

instructions for comparing QP₁*CTR with a threshold value to determine whether to filter the advertisement.

47. The computer-readable memory device of claim 42, where the instructions for using the functional combination to promote the advertisement among the plurality of advertisements comprises:

instructions for comparing QP₁*CTR with a threshold value to determine whether to promote the advertisement among the plurality of advertisements.

48. The computer-readable memory device of claim 42, where the instructions for functionally combining the first quality parameter (QP₁) with the CTR and CPC comprises:

instructions for multiplying the first quality parameter (QP₁) by CTR and CPC;

QP₁*CPC*CTR.

49. The computer-readable memory device of claim 48, where the instructions for using the functional combination to rank the advertisement comprises:

instructions for ranking the advertisement, among the plurality of advertisements, using QP*CPC*CTR.

50. The computer-readable memory device of claim 42, further comprising:

instructions for obtaining a second parameter (QP₂) associated with a quality of the advertisement; and

instructions for functionally combining the second quality parameter (QP₂) with the first quality parameter (QP₁) and the at least one other parameter.

51. The computer-readable memory device of claim 50, where functionally combining the second quality parameter (QP₂) with the first quality parameter (QP₁) and the CTR and CPC comprises:

CTR*CPC+K₁*QP₁*CTR−

K₂*QP₂*CTR, where K₁ and K₂ are constants.

52. The computer-readable memory device of claim 51, where the instructions for using the functional combination to promote the advertisement among the plurality of advertisements comprises:

instructions for comparing CTR*CPC+K₁*QP₁*CTR−

K₂*QP₂*CTR with a threshold to determine whether to promote the advertisement among the plurality of advertisements.

53. A method implemented by one or more processors of a computer system, comprising:

obtaining, using one or more processors of the computer system, ratings associated with a first group of advertisements, where the ratings, include a quality of the first group of advertisements;

observing, using one or more processors of the computer system, multiple different user actions associated with user selection of advertisements of the first group of advertisements;

calculating, using one or more processors of the computer system, a probability that an advertisement of a second group of advertisements is of a certain quality, as a function of multiple different types of user actions, based on the observed user actions and the obtained ratings;

estimating, by one or more processors of the computer system, quality scores, associated with the second group of advertisements, based on the calculated probabilities;

calculating, using one or more processors of the computer system, a combination of the estimated quality scores and click through rates associated with advertisements in the second group of advertisements;

filtering, using one or more processors of the computer system, the second group of advertisements based on a comparison of the combination of the estimated quality scores and click through rates to a threshold, to generate a subset of advertisements from the second group of advertisements; and

providing, to a user, the subset of advertisements from the second group of advertisements.

54. The method of claim 53, further comprising:

promoting one or more advertisements, of the subset of advertisements, based on the calculated combination of the estimated quality scores and the click through rates.

55. The method of claim 54, further comprising:

positioning the promoted one or more advertisements, of the subset of advertisements, in a prominent position on a document; and

positioning unpromoted advertisements, of the second group of advertisements, in a less prominent position on the document than the promoted one or more advertisements.