System and method for keyword extraction and contextual advertisement generation

• US 20070288454A1
• Filed: 12/27/2006
• Published: 12/13/2007
• Est. Priority Date: 06/09/2006
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Bolivar, Alvaro, Gupta, Raghav, Sun, Ken, Reitter, Alec
• Granted Patent: US 8,001,105 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A computer-implemented system and method for keyword extraction and contextual advertisement generation are disclosed. The system in an example embodiment includes a keyword extraction service to obtain information related to user activity on a host site and to extract relevant keywords from content of a web page, the information related to user activity on the host site being used to determine relevancy of the extracted keywords, and a contextual advertiser to produce an advertisement placement on an affiliate web page, the produced advertisement placement being relevant to user activity on the host site.

Claims

1. A method comprising:

obtaining information related to user activity on a host site;

using a keyword extraction service to extract relevant keywords from content of a web page, the information related to user activity on the host site being used to determine relevancy of the extracted keywords; and

using the extracted keywords to produce an advertisement placement on an affiliate web page, the produced advertisement placement being relevant to user activity on the host site.

2. The method as claimed in claim 1 wherein the web page is identified using a uniform reference locator (URL).

3. The method as claimed in claim 1 wherein the keyword extraction service may extract relevant keywords from content of the web page using a plurality of extraction processes, the method further including determining which of a plurality of extraction processes is most efficient for the content of the web page.

4. The method as claimed in claim 1 wherein metadata tags are generated automatically based on the content of the web page.

5. The method as claimed in claim 1 wherein the keyword extraction service further identifies category information on the host site associated with the content of the web page and the associated extracted keywords.

6. The method as claimed in claim 1 wherein the produced advertisement placement includes a rich media element.

7. The method as claimed in claim 1 wherein the produced advertisement placement includes a flash element.

8. The method as claimed in claim 1 further including statistically picking an advertisement slot for display of the produced advertisement placement.

9. The method as claimed in claim 1 wherein the information related to user activity on the host site is based on information from the group:

user behavior on a web site, frequency of user queries, listings availability, post-search user activity, and catalog data.

10. The method as claimed in claim 1 further including ranking the extracted keywords.

11. The method as claimed in claim 10 wherein the ranking of the extracted keywords includes using information from the group:

relevancy information, financial information, and user feedback information.

12. An article of manufacture comprising a machine-readable medium having machine executable instructions embedded thereon, which when executed by a machine, cause the machine to:

obtain information related to user activity on a host site;

use a keyword extraction service to extract relevant keywords from content of a web page, the information related to user activity on the host site being used to determine relevancy of the extracted keywords; and

use the extracted keywords to produce an advertisement placement on an affiliate web page, the produced advertisement placement being relevant to user activity on the host site.

13. The article of manufacture as claimed in claim 12 wherein the web page is identified using a uniform reference locator (URL).

14. The article of manufacture as claimed in claim 12 wherein the keyword extraction service may extract relevant keywords from content of the web page using a plurality of extraction processes, the article of manufacture being further operable to determine which of a plurality of extraction processes is most efficient for the content of the web page.

15. The article of manufacture as claimed in claim 12 being further operable to generate metadata tags automatically based on the content of the web page.

16. The article of manufacture as claimed in claim 12 wherein the keyword extraction service being further operable to identify category information on the host site associated with the content of the web page and the associated extracted keywords.

17. The article of manufacture as claimed in claim 12 wherein the produced advertisement placement includes a rich media element.

18. The article of manufacture as claimed in claim 12 wherein the produced advertisement placement includes a flash element.

19. The article of manufacture as claimed in claim 12 being further operable to statistically pick an advertisement slot for display of the produced advertisement placement.

20. The article of manufacture as claimed in claim 12 wherein the information related to user activity on the host site is based on information from the group:

user behavior on a web site, frequency of user queries, listings availability, post-search user activity, and catalog data.

21. The article of manufacture as claimed in claim 12 being further operable to rank the extracted keywords.

22. The article of manufacture as claimed in claim 21 wherein the ranking of the extracted keywords includes using information from the group:

relevancy information, financial information, and user feedback information.

23. A system comprising:

a processor;

a memory coupled to the processor to store information related to keywords;

a keyword extraction service to obtain information related to user activity on a host site and to extract relevant keywords from content of a web page, the information related to user activity on the host site being used to determine relevancy of the extracted keywords; and

a contextual advertiser to produce an advertisement placement on an affiliate web page, the produced advertisement placement being relevant to user activity on the host site.

24. The system as claimed in claim 23 wherein the web page is identified using a uniform reference locator (URL).

25. The system as claimed in claim 23 wherein the keyword extraction service may extract relevant keywords from content of the web page using a plurality of extraction processes, the system being further operable to determine which of a plurality of extraction processes is most efficient for the content of the web page.

26. The system as claimed in claim 23 being further operable to generate metadata tags automatically based on the content of the web page.

27. The system as claimed in claim 23 wherein the keyword extraction service being further operable to identify category information on the host site associated with the content of the web page and the associated extracted keywords.

28. The system as claimed in claim 23 wherein the produced advertisement placement includes a rich media element.

29. The system as claimed in claim 23 wherein the produced advertisement placement includes a flash element.

30. The system as claimed in claim 23 wherein the contextual advertiser being further operable to statistically pick an advertisement slot for display of the produced advertisement placement.

31. The system as claimed in claim 23 wherein the information related to user activity on the host site is based on information from the group:

user behavior on a web site, frequency of user queries, listings availability, post-search user activity, and catalog data.

32. The system as claimed in claim 23 wherein the keyword extraction service being further operable to rank the extracted keywords.

33. The system as claimed in claim 32 wherein the ranking of the extracted keywords includes using information from the group:

relevancy information, financial information, and user feedback information.