Selecting and/or scoring content-relevant advertisements

• US 8,706,546 B2
• Filed: 07/18/2005
• Issued: 04/22/2014
• Est. Priority Date: 07/18/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Anderson, Darrell, Nguyen, Giao, Shivakumar, Narayanan, Carobus, Alexander Paul
• Primary Examiner(s): Brown, Alvin L
• Application Number:
  US11/184,053
• Publication Number:
  US 20070016473A1
• Time in Patent Office: 3,200 Days
• Field of Search: 705/14
• US Class Current: 705/14
• 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 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising

Abstract

Ads eligible to be served with a document (for example, because they are relevant to the document) may each be scored using a price parameter associated with the ad and an indication of relevancy of the ad to the document. The indication of relevancy of the ad to the document may be based on an ordinal ranking of a relevancy criteria of the document used to select the ad, and/or a value of a relevancy criteria of the document used to select the ad. The eligible ads may be determined by obtaining relevancy criteria for the document and selecting ads using at least some of the obtained relevancy criteria. The ads may be selected, and perhaps filtered, in a distributed manner.

Claims

1. A computer-implemented method comprising:

a) receiving, using a computer system including at least one computer, advertisement search criteria about a document;

b) assigning a criteria weight to each advertisement search criterion based on relevancy of the advertisement search criterion to the document;

c) selecting advertisements corresponding to the advertisement search criteria;

d) associating each selected advertisement with the criteria weight of the corresponding advertisement search criterion for that selected advertisement;

e) determining, using the computer system, a score for each of the selected advertisements based on a product of a price parameter associated with the advertisement and the criteria weight associated with the advertisement, each determined score representing a value associated with a placement order of the selected advertisements;

f) identifying available spaces on the document based on information from a source, the information indicating at least one certain space of the available spaces on the document for placing an advertisement, wherein the at least one certain space is preferred over other ones of the available spaces on the document; and

g) controlling, using the computer system, placement of at least some of the selected advertisements on the document by arbitrating among the selected advertisements for the available spaces on the document based on the determined scores.

2. The computer-implemented method of claim 1, further comprising ranking the advertisement search criteria based on their relevancy to the document.

3. The computer-implemented method of claim 2, further comprising determining the criteria weight for each advertisement search criterion based on the ranking.

4. The computer-implemented method of claim 1 wherein at least one advertisement search criterion relates to the content of the document.

5. The computer-implemented method of claim 1 wherein the computer system selects an advertisement by determining if it matches any of the advertisement search criteria, and associates the selected advertisement with the highest criteria weight of all matched advertisement search criteria.

6. The computer-implemented method of claim 1, further comprising:

i) broadcasting a query including at least some of the advertisement search criteria to a plurality of advertisement determination facilities,

ii) determining, at each of the advertisement determination facilities, advertisements using at least some of the advertisement search criteria,

iii) filtering the determined advertisements to generate a reduced set of advertisements, and

iv) sending, from each of the advertisement determination facilities, the reduced set of advertisements.

7. The computer-implemented method of claim 1 wherein the price parameter associated with the advertisement is one of an offer per impression, an offer per selection, an offer per conversion, a maximum offer per impression, a maximum offer per selection and a maximum offer per conversion.

8. The computer-implemented method of claim 1 wherein the computer system determines relevancy of the advertisements to the document by:

determining concepts of the document,

determining a set of one or more advertisements with the determined concepts, and

obtaining targeting information from at least some advertisements belonging to the set of one or more advertisements.

9. The computer-implemented method of claim 8 wherein the targeting information includes one or more targeting keywords.

10. The computer-implemented method of claim 8 wherein the concepts are probabilistic hierarchical inferential learned clusters.

11. The computer-implemented method of claim 1 wherein the computer system scores each of the selected advertisements by further using a performance parameter associated with the advertisement.

12. The computer-implemented method of claim 11 wherein the performance parameter associated with each advertisement is one of a selection rate and a conversion rate.

13. The computer-implemented method of claim 11 wherein the computer system scores each of the selected advertisements based on the product of the price parameter and the criteria weight with the performance parameter associated with the advertisement.

14. The computer-implemented method of claim 11 further comprising:

i) broadcasting a query including at least some of the advertisement search criteria to a plurality of advertisement determination facilities,

ii) determining, at each of the advertisement determination facilities, advertisements using at least some of the advertisement search criteria,

iii) filtering the determined advertisements to generate a reduced set of advertisements, and

iv) sending, from each of the advertisement determination facilities, the reduced set of advertisements.

15. The computer-implemented method of claim 14 wherein each of the advertisement determination facilities filters the determined advertisements by scoring each of the determined advertisements based on the product of the price parameter and the criteria weight with the performance parameter associated with the advertisement.

17. The computer-implemented method of claim 6 wherein each of the plurality of advertisement determination facilities is a shard.

20. The method of claim 1, further comprising determining a placement priority of a first and second advertisement from the selected advertisements, wherein the first and second advertisements have corresponding scores.

21. The method of claim 20, wherein determining the placement priority comprises determining an amount an advertiser associated with a given advertisement must pay in order for the given advertisement to appear before another advertisement on the document based on the criteria weight associated with each advertisement.

16. Apparatus comprising:

a) at least one processor; and

b) at least one storage device storing processor executable instructions which, when executed by the at least one processor, perform a method including;

i) receiving advertisement search criteria about a document;

ii) assigning a criteria weight to each advertisement search criterion based on relevancy of the advertisement search criterion to the document;

iii) selecting advertisements corresponding to the advertisement search criteria;

iv) associating each selected advertisement with the criteria weight of the corresponding advertisement search criterion for that selected advertisement;

v) determining a score for each of the selected advertisements based on a product of a price parameter associated with the advertisement and the criteria weight associated with the advertisement, each determined score representing a value associated with a placement order of the selected advertisements;

vi) identifying available spaces on the document based on information from a source, the information indicating at least one certain space of the available spaces on the document for placing an advertisement, wherein the at least one certain space is preferred over other ones of the available spaces on the document; and

vii) controlling placement of at least some of the selected advertisements on the document by arbitrating among the selected advertisements for the available spaces on the document based on the determined scores.

18. A computer-implemented method comprising:

a) receiving, using a computer system including at least one computer, advertisement search criteria about a document;

b) assigning a criteria weight to each advertisement search criterion based on relevancy of the advertisement search criterion to the document;

c) selecting advertisements corresponding to the advertisement search criteria;

d) associating each selected advertisement with the criteria weight of the corresponding advertisement search criterion for that selected advertisement;

e) determining, using the computer system, a score for each of the selected advertisements based on a product of a price parameter associated with the advertisement, a performance parameter associated with the advertisement, and the criteria weight associated with the advertisement, each determined score representing a value associated with a placement order of the selected advertisements;

f) identifying available spaces on the document based on information from a source, the information indicating at least one certain space of the available spaces on the document for placing an advertisement, wherein the at least one certain space is preferred over other ones of the available spaces on the document; and

g) controlling, using the computer system, placement of at least some of the selected advertisements on the document by arbitrating among the selected advertisements for the available spaces on the document based on the determined scores.

19. A tangible, non-transitory computer readable medium storing processor executable instructions, which, when executed by at least one processor, cause the at least one processor to perform a method including:

i) receiving advertisement search criteria about a document;

ii) assigning a criteria weight to each advertisement search criterion based on relevancy of the advertisement search criterion to the document;

iii) selecting advertisements corresponding to the advertisement search criteria;

iv) associating each selected advertisement with the criteria weight of the corresponding advertisement search criterion for that selected advertisement;

v) determining a score for each of the selected advertisements based on a product of a price parameter associated with the advertisement and the criteria weight associated with the advertisement, each determined score representing a value associated with a placement order of the selected advertisements;

vi) identifying available spaces on the document based on information from a source, the information indicating at least one certain space of the available spaces on the document for placing an advertisement, wherein the at least one certain space is preferred over other ones of the available spaces on the document; and

vii) controlling placement of at least some of the selected advertisements on the document by arbitrating among the selected advertisements for the available spaces on the document based on the determined scores.