System and method for online unique users and frequency estimation for advertisements on a video sharing website based on auction history results

• US 8,666,810 B1
• Filed: 02/17/2012
• Issued: 03/04/2014
• Est. Priority Date: 02/17/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Strobl, Reto, Dybdahl, Haakon
• Primary Examiner(s): Jarrett, Scott L
• Application Number:
  US13/399,240
• Time in Patent Office: 746 Days
• Field of Search: 705/14.45
• US Class Current: 705/14.45
• CPC Class Codes: G06Q 30/0249 based upon budgets or funds
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

Methods, systems, user interfaces, and apparatus, including computer programs encoded on a computer-readable storage medium, for providing performance estimates for a content campaign. A method includes identifying a campaign including one or more targeting criteria for targeting content items to users; identifying historical auction results; storing the historical auction results as a plurality of documents; evaluating the plurality of documents to determine an estimated number of impressions that would occur in the plurality of documents based on the targeting criteria; determining an estimated total number of impressions for the targeting criteria in the time period based at least in part on the estimated number of impressions in the plurality of documents; and determining a total number of unique targeted users including determining a frequency of impression and determining the total number of unique targeted users as the total number of impressions divided by the frequency of impression.

Claims

1. A computer implemented method comprising:

identifying a campaign including one or more targeting criteria for targeting content items to users;

determining, by one or more processors, a number of unique users that will be targeted based on the targeting criteria in a predetermined time period including;

identifying historical auction results including content served in response to content requests;

storing the historical auction results as a plurality of documents, one for each auction result, wherein storing an auction result as a document comprises storing serving criteria and a user identifier for a user that was served a content item based on the auction result;

evaluating the plurality of documents including initiating a first query on the plurality of documents to determine an estimated number of impressions that would occur in the plurality of documents based on the targeting criteria including generating a first count for occurrences in the plurality of documents that satisfy the first query including identifying a location in the plurality of documents wherein the first count satisfies a first threshold number of occurrences;

determining an estimated total number of impressions for the targeting criteria in the time period based at least in part on the estimated number of impressions in the plurality of documents; and

determining a total number of unique targeted users including initiating a second query starting at a next entry after the location in the plurality of documents including estimating the number of unique users for the targeting criteria based on the second query including determining a frequency of impression for a plurality of the users represented in the plurality of documents as a sum of a frequency of impression for a selected number of users divided by the selected number of users and determining the total number of unique targeted users as the total number of impressions divided by the frequency of impression.

2. The method of claim 1 wherein the targeting criteria for targeting content items are selected from the group comprising keywords, URLs, verticals, topics, placements, user signals, or a combination thereof.

3. The method of claim 1 wherein determining the total number of unique targeted users includes determining a total number of predicted impressions for the historical auction results and a frequency at which documents satisfy the targeting criteria in the historical auction results, and determining a number of unique users as the total number of predicted impressions divided by the frequency at which documents satisfy the targeting criteria in the historical auction results.

4. The method of claim 1 further comprising identifying a number of documents that are required to produce a first query result and wherein determining the estimated total number of impressions includes determining a number of unique users that are determined when evaluating the plurality of documents in order to satisfy the number of documents.

5. The method of claim 4, wherein determining the frequency includes determining a frequency for each of the unique users which are associated with one or more documents.

6. The method of claim 5 wherein determining the frequency includes determining an average frequency for the unique users.

7. The method of claim 1 further comprising storing the plurality of documents in a repository.

8. The method of claim 1 wherein the first query is initiated on a beginning of the plurality of documents in the repository.

9. The method of claim 1 wherein the estimated total number of impressions is determined as an extrapolation based on a number of historical auctions that are evaluated as compared to a total number of auctions that are conducted in a time period.

10. The method of claim 1 wherein the campaign is associated with a video content item, the method further comprising providing the total number of unique targeted users to a campaign sponsor.

11. The method of claim 10 wherein providing the total number of unique targeted users further comprises providing the total number of unique targeted users to a campaign sponsor in response to selection or designation of the targeting criteria.

12. The method of claim 10 wherein providing the total number of unique targeted users happens in substantially real time.

13. The method of claim 10 further comprising providing to the campaign sponsor an estimate of the number of views of the video content item in the predetermined time period.

14. The method of claim 1 wherein the serving criteria include bid information indicating a winning bid amount for an auction.

15. A user interface comprising:

a set of one or more targeting criteria controls for configuring targeting criteria for targeting content items for a campaign;

a first output control configured to display an estimated total number of impressions for the targeting criteria in a predetermined time period; and

a second output control configured to display a number of unique users that will be targeted based on the targeting criteria in the predetermined time period;

wherein;

the estimated total number of impressions is determined based at least in part on a first query on historical auction results stored as a plurality of documents, wherein the first query determines an estimated number of impressions that would occur in the plurality of documents based on the targeting criteria including generating a first count for occurrences in the plurality of documents that satisfy the first query including identifying a location in the plurality of documents wherein the first count satisfies a first threshold number of occurrences; and

the total number of unique targeted users is determined by initiating a second query starting at a next entry after the location in the plurality of documents including estimating the number of unique users for the targeting criteria based on the second query including dividing the estimated total number of impressions by an estimated frequency of impression, wherein the estimated frequency of impression is a sum of a frequency of impression for a selected number of users represented in the plurality of documents divided by the selected number of users.

16. The user interface of claim 15 wherein the total number of unique targeted users is determined based at least in part by dividing a total number of predicted impressions by a frequency at which documents satisfy the targeting criteria in the historical auction results.

17. The user interface of claim 15 wherein the campaign is associated with a video content item and the second output control is configured to display the total number of unique targeted users to a campaign sponsor.

18. The user interface of claim 17 further comprising a third output control configured to display to the campaign sponsor an estimate of the number of views of the video content item in the predetermined time period.

19. A computer program product tangibly embodied in a computer-readable storage device and comprising instructions that, when executed by a processor, cause the processor to:

identify a campaign including one or more targeting criteria for targeting content items to users;

determine a number of unique users that will be targeted based on the targeting criteria in a predetermined time period including;

identifying historical auction results including content served in response to content requests;

storing the historical auction results as a plurality of documents, one for each auction result, wherein storing an auction result as a document comprises storing serving criteria and a user identifier for a user that was served a content item based on the auction result;

evaluating the plurality of documents including initiating a first query on the plurality of documents to determine an estimated number of impressions that would occur in the plurality of documents based on the targeting criteria including generating a first count for occurrences in the plurality of documents that satisfy the query including identifying a location in the plurality of documents wherein the first count satisfies a first threshold number of occurrences;

determining an estimated total number of impressions for the targeting criteria in the time period based at least in part on the estimated number of impressions in the plurality of documents; and

determining a total number of unique targeted users including initiating a second query starting at a next entry after the location in the plurality of documents including estimating the number of unique users for the targeting criteria based on the second query including determining a frequency of impression for a plurality of the users represented in the plurality of documents as a sum of a frequency of impression for a selected number of users divided by the selected number of users and determining the total number of unique targeted users as the total number of impressions divided by the frequency of impression.

20. The computer program product of claim 19 wherein determining the total number of unique targeted users includes determining a total number of predicted impressions for the historical results and a frequency at which documents satisfy the targeting criteria in the historical results, and determining a number of unique users as the total number of predicted impressions divided by the frequency at which documents satisfy the targeting criteria in the historical auction results.

21. The computer program product of claim 19 wherein the campaign is associated with a video content item and the instructions comprise instructions to provide the total number of unique targeted users to a campaign sponsor.

22. The computer program product of claim 19 further comprising instructions to provide to the campaign sponsor an estimate of the number of views of the video content item in the predetermined time period.