Content selection using performance metrics

Patent metadata

Field	Value
Publication number	US-9256892-B2
Application number	US-201414281370-A
Country	US
Kind code	B2
Filing date	May 19, 2014
Priority date	Nov 30, 2006
Publication date	Feb 9, 2016
Grant date	Feb 9, 2016

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer program product, for selecting advertisements. In one aspect, a method includes receiving publisher selections of advertisements; associating the selected advertisements with an advertisement environment in a document; generating an advertisement request code for inclusion in the document; evaluating performance metrics for the selected advertisements; and in response to determining that the selected advertisements do not meet the performance threshold, optimizing the selection of selected advertisements based on the performance metrics; substituting a selected advertisement with a candidate advertisement and causing a client device to render the candidate advertisement in the advertisement environment in the document.

First claim

What is claimed is:

1. A method comprising:
receiving publisher selections of advertisements from a plurality of advertisements;
associating the selected advertisements with an advertisement environment in a document, wherein the advertisement environment is associated with a location in the document for presenting one or more advertisements;
generating, by one or more processors, an advertisement request code for inclusion in the document, the advertisement request code configured to issue an advertisement request for selection of an advertisement from the selected advertisements for presentation in the advertisement environment;
evaluating performance metrics for the selected advertisements presented in the advertisement environment;
determining that the selected advertisements do not meet a performance threshold;
in response to determining that the selected advertisements do not meet the performance threshold, optimizing the selection of selected advertisements based on the performance metrics comprising overriding the publisher selections;
substituting a selected advertisement with a candidate advertisement of a plurality of candidate advertisements, wherein the candidate advertisements are different than the selected advertisements; and
providing the candidate advertisement instead of the selected advertisement to a client device for rendering in the advertisement environment of the document.

2. The method of claim 1 , wherein the performance metrics include a click-through rate or a conversion rate.

3. The method of claim 1 , further comprising:
estimating performance metrics for a plurality of candidate advertisements; and
identifying a candidate advertisement from the plurality of candidate advertisements with performance metrics greater than a performance threshold.

4. The method of claim 3 , comprising:
identifying a plurality of candidate advertisements based on a context of the document or advertisements related to the selected advertisements.

5. A computer program product stored on a computer storage device comprising instructions that when executed by one or more processors cause the processors to perform operations comprising:
receiving publisher selections of advertisements from a plurality of advertisements;
associating the selected advertisements with an advertisement environment in a document, wherein the advertisement environment is associated with a location in the document for presenting one or more advertisements;
generating, by one or more processors, an advertisement request code for inclusion in the document, the advertisement request code configured to issue an advertisement request for selection of an advertisement from the selected advertisements for presentation in the advertisement environment;
evaluating performance metrics for the selected advertisements presented in the advertisement environment;
determining that the selected advertisements do not meet a performance threshold;
in response to determining that the selected advertisements do not meet the performance threshold, optimizing the selection of selected advertisements based on the performance metrics comprising overriding the publisher selections;
substituting a selected advertisement with a candidate advertisement of a plurality of candidate advertisements, wherein the candidate advertisements are different than the selected advertisements; and
providing the candidate advertisement instead of the selected advertisement to a client device for rendering in the advertisement environment of the document.

6. The computer program product of claim 5 , wherein the performance metrics include a click-through rate, or a conversion rate.

7. The computer program product of claim 5 , wherein the operations further comprise:
estimating performance metrics for a plurality of candidate advertisements; and
identifying a candidate advertisement from the plurality of candidate advertisements with performance metrics greater than a performance threshold.

8. The computer program product of claim 7 , wherein the instructions comprise:
identifying a plurality of candidate advertisements based on a context of the document or advertisements related to the selected advertisements.

9. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving publisher selections of advertisements from a plurality of advertisements;

associating the selected advertisements with an advertisement environment in a document, wherein the advertisement environment is associated with a location in the document for presenting one or more advertisements;
generating, by one or more processors, an advertisement request code for inclusion in the document, the advertisement request code configured to issue an advertisement request for selection of an advertisement from the selected advertisements for presentation in the advertisement environment;
evaluating performance metrics for the selected advertisements presented in the advertisement environment;
determining that the selected advertisements do not meet a performance threshold;
in response to determining that the selected advertisements do not meet the performance threshold, optimizing the selection of selected advertisements based on the performance metrics comprising overriding the publisher selections;
substituting a selected advertisement with a candidate advertisement of a plurality of candidate advertisements, wherein the candidate advertisements are different than the selected advertisements; and
providing the candidate advertisement instead of the selected advertisement to a client device for rendering in the advertisement environment of the document.

10. The system of claim 9 , wherein the performance metrics include a click-through rate, or a conversion rate.

11. The system of claim 9 , wherein the operations further comprise:
estimating performance metrics for a plurality of candidate advertisements; and
identifying a candidate advertisement from the plurality of candidate advertisements with performance metrics greater than a performance threshold.

12. The system of claim 11 , wherein the instructions comprise:
identifying a plurality of candidate advertisements based on a context of the document or advertisements related to the selected advertisements.

Assignees

• Google Inc

Inventors

• Kniaz Rob
• Sharma Abinhay
• Chen Kai
• Drobintsev Maxim

Classifications

• G06Q30/0277 Primary

  Online advertisement · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0273

  Determination of fees for advertising · CPC title