Determining proximity to topics of advertisements

• US 8,572,114 B1
• Filed: 12/21/2011
• Issued: 10/29/2013
• Est. Priority Date: 04/17/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Hubinette, Carl F.
• Primary Examiner(s): Coby, Frantz
• Application Number:
  US13/332,999
• Time in Patent Office: 678 Days
• Field of Search: 707758-760, 707/769, 707/770, 707/771, 707/772, 707/773, 707/774, 707/775
• US Class Current: 707/769
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The present disclosure includes a system and method for determining proximity to topics of content items (e.g., an advertisement or “ad”). In some implementations, a method includes identifying search criteria associated with keywords of a content item. The keywords used in determining whether or not to embed the content item in Web pages including search results. Numerical scores for the search criteria is determined based, at least in part, on a topic of the content item, the numerical score indicative of proximity to the topic of the content item.

Claims

1. A system, comprising:

one or more data processing apparatuses; and

a data storage apparatus encoded with instructions that when executed by the one or more data processing apparatuses cause the one or more data processing apparatuses to perform operations comprising;

accessing ad keyword data specifying an ad keyword associated with an advertisement;

identifying at least one keyword cluster specifying terms related to a topic of the advertisement;

determining a first conditional probability that the ad keyword occurs in the at least one keyword cluster;

identifying one or more search keywords to which the advertisement is responsive;

determining a second conditional probability that the one or more search keywords occur in the at least one keyword cluster; and

determining a relevance of the one or more search keywords to the advertisement based at least in part on a comparison of the first conditional probability and the second conditional probability.

2. The system of claim 1, wherein at least one of the first conditional probability or the second conditional probability is determined based at least in part using a Bayesian network.

3. The system of claim 1, wherein determining a relevance comprises:

determining the relevance of the one or more search keywords to the advertisement based at least in part on a difference between the first conditional probability and the second conditional probability.

4. The system of claim 1, wherein determining a relevance comprises:

determining a relevance of the one or more search keywords to the topic of the advertisement based at least in part on the comparison of the first conditional probability and the second conditional probability.

5. A computer-implemented method comprising:

identifying one or more topic terms relevant to a topic of a content item;

identifying a search query having one or more query terms associated with keywords of the content item;

determining one or more proximity metrics for the search query based, at least in part, on a comparison of the one or more query terms to the one or more topic terms, wherein the one or more proximity metrics indicate a proximity of the one or more query terms to the topic of the content item; and

determining that the search query is relevant to the topic of the content item based on a comparison of the one or more proximity metrics to a proximity threshold, the search query being relevant to the topic when the one or more query terms are proximate to the topic.

6. The method of claim 5, wherein determining one or more proximity metrics comprises:

determining one or more conditional probabilities that the one or more query terms are relevant to the topic of the content item; and

determining a numerical value indicating the proximity to the topic based, at least in part, on the one or more conditional probabilities.

7. The method of claim 6, wherein the one or more proximity metrics are determined using a Bayesian filter.

8. The method of claim 5, further comprising:

determining that the search query is irrelevant to the topic of the content item based on a comparison of the one or more proximity metrics to the proximity threshold, the search query being irrelevant to the topic when the one or more query terms are not proximate to the topic.

9. The method of claim 5, wherein the content item is an advertisement.

10. The method of claim 9, wherein the one or more topic terms are terms in a keyword cluster related to the topic of the advertisement.

11. A computer-implemented method comprising:

accessing ad keyword data specifying ad keywords associated with an advertisement;

identifying, by one or more processors, a keyword cluster specifying terms related to a topic of the advertisement;

determining a first conditional probability that the ad keywords occur in the keyword cluster;

identifying one or more search keywords to which the advertisement is responsive;

determining a second conditional probability that the one or more search keywords occur in the keyword cluster; and

determining a topical proximity between the one or more search keywords and the topic of the advertisement based on a comparison of the first conditional probability and the second conditional probability.

12. The method of claim 11, wherein determining a topical proximity between the one or more search keywords and the topic of the advertisement comprises:

determining a relevance of the one or more search keywords to the topic based at least in part on a difference between the first conditional probability and the second conditional probability.

13. The method of claim 11, wherein at least one of the first conditional probability or the second conditional probability is determined based at least in part using a Bayesian network.

14. The method of claim 11, further comprising:

comparing the topical proximity to a proximity threshold; and

determining that the one or more search keywords are relevant to the topic in response to determining that the topical proximity exceeds the proximity threshold.

15. The method of claim 11, further comprising:

identifying the advertisement as relevant to the one or more search keywords based on the topical proximity exceeding a proximity threshold.

16. A system, comprising:

one or more data processing apparatuses; and

a data storage apparatus encoded with instructions that when executed by the one or more data processing apparatuses cause the one or more data processing apparatuses to perform operations comprising;

accessing ad keyword data specifying ad keywords associated with an advertisement;

identifying at least one keyword cluster specifying terms related to a topic of the advertisement;

determining a first conditional probability that the ad keywords occur in the at least one keyword cluster;

identifying one or more search keywords to which the advertisement is responsive;

determining a second conditional probability that the one or more search keywords occur in the at least one keyword cluster; and

determining a topical proximity between the one or more search keywords and the advertisement based on a comparison of the first conditional probability and the second conditional probability.

17. The system of claim 16, wherein the instructions, when executed by the one or more data processing apparatuses, cause the one or more data processing apparatuses to perform operations further comprising:

comparing the topical proximity to a proximity threshold; and

determining that the one or more search keywords are not relevant to the advertisement in response to determining that the topical proximity does not exceed the proximity threshold.

18. The system of claim 16, wherein the instructions, when executed by the one or more data processing apparatuses, cause the one or more data processing apparatuses to perform operations further comprising:

identifying the advertisement as relevant to the one or more search keywords based on the topical proximity exceeding a proximity threshold.

19. The system of claim 16, wherein at least one of the first conditional probability or the second conditional probability is determined based at least in part using a Bayesian network.

20. Software stored in a computer memory device accessible by one or more data processing apparatuses that upon such execution cause the one or more data processing apparatuses to perform operations comprising:

accessing ad keyword data specifying ad keywords associated with an advertisement;

identifying a keyword cluster specifying terms related to a topic of the advertisement;

determining a first conditional probability that the ad keywords occur in the keyword cluster;

identifying one or more search keywords to which the advertisement is responsive;

determining a second conditional probability that the one or more search keywords occur in the keyword cluster; and

determining a relevance of the one or more search keywords to the topic of the advertisement based at least in part on a comparison of the first conditional probability and the second conditional probability.