Reviewing the suitability of websites for participation in an advertising network

• US 8,762,204 B2
• Filed: 07/19/2010
• Issued: 06/24/2014
• Est. Priority Date: 06/29/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Desikan, Pavan Kumar, Ip, Lawrence, James, Timothy, Kulkarni, Sanjeev, Phukan, Prasenjit, Portnov, Dmitriy, Rajaram, Gokul
• Primary Examiner(s): Myhre, James W
• Application Number:
  US12/839,262
• Publication Number:
  US 20100287041A1
• Time in Patent Office: 1,436 Days
• Field of Search: 705/14.6
• US Class Current: 705/14.6
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0263 based upon Internet or website rating
• CPC Class Codes: G06Q 30/0265 Vehicular advertisement

Abstract

The way in which Websites are reviewed for use in an advertising network may be improved by (a) accepting a collection including one or more documents, (b) determining whether or not the collection complies with policies of an advertising network, and (c) approving the collection if it was determined that the collection complies with the policies. The collection may be added to the advertising network if the collection is approved such that (e.g., content-targeted) advertisements may be served in association with renderings of documents included in the collection. The collection may be a Website including one or more Webpages. The policy may concern (A) content of the one or more documents of the collection, (B) usability of a Website wherein the collection of one or more documents is a Website including one or more Webpages, and/or (C) a possible fraud or deception on the advertising network or participants of the advertising network by the collection.

Claims

1. A computer-implemented method comprising:

receiving, by a computer system including at least one computer, a list of collections, each of the collections including one or more documents and at least some of the collections having a violation of a given policy of an advertising network;

training, by the computer system, an expert system to classify other collections as having the given policy violation or not;

receiving, by the computer system, a first collection including one or more documents associated with a first request by a publisher to host advertisements of advertisers belonging to an advertising network;

determining, by the computer system and using the trained expert system, whether or not the first collection complies with policies of an advertising network, and wherein the policies are independent of the advertisements of the advertisers belonging to the advertising network, by generating a first quality score for the first collection, by the trained expert system, based on inclusion or exclusion of predetermined items corresponding to each policy and comparing the generated first quality score to a first threshold;

approving, by the computer system, the first collection responsive to a determination by the trained expert system that the first collection complies with the policies of the advertising network based on the generated quality score being greater than the first threshold;

processing, by the computer system, the first collection to the advertising network such that advertisements of the advertisers belonging to the advertising network may be served in association with renderings of the one or more documents included in the first collection;

determining, by the computer system, that the first quality score is greater than a second threshold, the second threshold greater than the first threshold;

providing an incentive, by the computer system, to a publisher of the first collection, responsive to the determination that the first quality score is greater than the second threshold;

receiving, by the computer system, a second collection including one or more documents associated with a second request by a publisher to host advertisements of advertisers belonging to an advertising network;

determining, by the computer system and using the trained expert system, whether or not the second collection complies with the policies, by generating a second quality score for the second collection, by the trained expert system, based on inclusion or exclusion of predetermined items corresponding to each policy and comparing the generated second quality score to the first threshold;

approving, by the computer system, the second collection responsive to a determination by the trained expert system that the second collection complies with the policies of the advertising network based on the generated second quality score being greater than the first threshold;

processing, by the computer system, the second collection to the advertising network such that advertisements of the advertisers belonging to the advertising network may be served in association with renderings of the one or more documents included in the second collection;

determining, by the computer system, that the second quality score is less than the second threshold; and

providing a disincentive, by the computer system, to a publisher of the second collection, responsive to the determination that the first quality score is less than the second threshold.

2. The computer-implemented method of claim 1 wherein the expert system is one of (A) a neural network, (B) a Bayesian network, or (C) a support vector machine.

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

scheduling a follow-up determination of whether or not the first collection complies with the policies of the advertising network.

4. The computer-implemented method of claim 1 wherein the first collection including one or more documents is a first Website including one or more Webpages, and wherein the second collection including one or more documents is a second Website including one or more Webpages.

5. The computer-implemented method of claim 1 wherein at least one of the first and second collections includes one or more documents which includes at least one of (A) audio content, or (B) video content.

6. The computer-implemented method of claim 1 wherein at least one of the first and second collections includes one or more documents which includes an online game.

7. The method of claim 1, wherein the advertising network, the advertisers of the advertising network and the publisher are different entities.

8. The method of claim 1, further comprising determining that the generated second quality score for the second collection is greater than the first threshold but is less than the second threshold;

and responsive to the determination, adding the second collection to a queue for review.

9. The method of claim 8, wherein adding the second collection to a queue for review further comprises determining a number of policy violations of the second collection, and adding the second collection to a queue having a priority inversely proportional to the number of policy violations.

10. The method of claim 9, wherein adding the second collection to a queue for review further comprises determining a severity of policy violations of the second collection, and adding the second collection to a queue having a priority inversely proportional to the severity of the policy violations.

11. A system, comprising a computer system including at least one computer comprising a processor, wherein the processor is configured for:

receiving a list of collections, each of the collections including one or more documents and at least some of the collections having a violation of a given policy of an advertising network;

training an expert system to classify other collections as having the given policy violation or not;

receiving a first collection including one or more documents associated with a first request by a publisher to host advertisements of advertisers belonging to an advertising network;

determining, using the trained expert system, whether or not the first collection complies with policies of an advertising network, and wherein the policies are independent of the advertisements of the advertisers belonging to the advertising network, by generating a first quality score for the first collection, by the trained expert system, based on inclusion or exclusion of predetermined items corresponding to each policy and comparing the generated first quality score to a first threshold;

approving the first collection responsive to a determination by the trained expert system that the first collection complies with the policies of the advertising network based on the generated quality score being greater than the first threshold;

processing the first collection to the advertising network such that advertisements of the advertisers belonging to the advertising network may be served in association with renderings of the one or more documents included in the first collection;

determining that the first quality score is greater than a second threshold, the second threshold greater than the first threshold;

providing an incentive to a publisher of the first collection, responsive to the determination that the first quality score is greater than the second threshold;

receiving a second collection including one or more documents associated with a second request by a publisher to host advertisements of advertisers belonging to an advertising network;

determining, using the trained expert system, whether or not the second collection complies with the policies, by generating a second quality score for the second collection, by the trained expert system, based on inclusion or exclusion of predetermined items corresponding to each policy and comparing the generated second quality score to the first threshold;

approving the second collection responsive to a determination by the trained expert system that the second collection complies with the policies of the advertising network based on the generated second quality score being greater than the first threshold;

processing the second collection to the advertising network such that advertisements of the advertisers belonging to the advertising network may be served in association with renderings of the one or more documents included in the second collection;

determining that the second quality score is less than the second threshold; and

providing a disincentive to a publisher of the second collection responsive to the determination that the first quality score is less than the second threshold.

12. The system of claim 11, wherein the expert system is one of (A) a neural network, (B) a Bayesian network, or (C) a support vector machine.

13. The system of claim 11, wherein the processor is further configured for:

scheduling a follow-up determination of whether or not the first collection complies with the policies of the advertising network.

14. The system of claim 11, wherein the first collection including one or more documents is a first Website including one or more Webpages, and wherein the second collection including one or more documents is a second Website including one or more Webpages.

15. The system of claim 11, wherein at least one of the first and second collections includes one or more documents which includes at least one of (A) audio content, or (B) video content.

16. The system of claim 11, wherein at least one of the first and second collections includes one or more documents which includes an online game.

17. The system of claim 11, wherein the advertising network, the advertisers of the advertising network and the publisher are different entities.

18. The system of claim 11, wherein the processor is further configured for determining that the generated second quality score for the second collection is greater than the first threshold but is less than the second threshold;

and responsive to the determination, adding the second collection to a queue for review.

19. The system of claim 18, wherein the processor is further configured for determining a number of policy violations of the second collection, and adding the second collection to a queue having a priority inversely proportional to the number of policy violations.

20. The system of claim 18, wherein the processor is further configured for determining a severity of policy violations of the second collection, and adding the second collection to a queue having a priority inversely proportional to the severity of the policy violations.