Method and computer readable medium for search scoring

• US 7,130,819 B2
• Filed: 09/30/2003
• Issued: 10/31/2006
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Energetic Power Investment Limited
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Panchapakesan, Venkat, Acton, Brian, Wang, Xuejun
• Primary Examiner(s): Smith, Jeffrey A.
• Application Number:
  US10/675,234
• Publication Number:
  US 20050071255A1
• Time in Patent Office: 1,127 Days
• Field of Search: 705/26, 705/27, 707/3, 707/5, 707/7
• US Class Current: 705/26.1
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06Q 50/10 Services

Abstract

A method and apparatus for generating search results with higher relevancy. The present invention exploits the fact that users'"'"' choices on each given search term tend to converge to several products from several merchants, and all of the results are very relevant to the search term. In one embodiment, these results are used to decide the order of merchants for each search term. By learning the users'"'"' choices, especially from purchasing and/or clicking information, highly relevant and most popular products can be assigned a higher score or rank over text relevant only products.

Claims

1. A method for arranging search results comprising:

capturing sales information associated with a document, wherein the document was returned in a search result set formed in response to a search term;

determining relative responsiveness, compared with other members of the search result set, of the document to the search term based on the sales information and on a position of the document in an ordering of the search result set;

generating a score for association with the document reflecting the relative responsiveness of the document to the search term; and

using the score to affect a response to a subsequent search.

2. The method of claim 1, wherein the subsequent search uses the search term, and the response includes a search result set, the ordering thereof affected by use of the score.

3. The method claim 1, further comprising adjusting the score to account for a specific knowledge of the document.

4. The method claim 1, further comprising adjusting the score to account for a specific knowledge of the search term.

5. The method of claim 1, further comprising applying the score in conjunction with a text relevancy score, a paid inclusion score, or a paid sponsorship score.

6. The method of claim 5, further comprising applying a usage function to said score.

7. The method of claim 1, wherein said document includes a product page.

8. The method of claim 1, wherein said document is a catalog page.

9. The method of claim 8, wherein said catalog page represents a display page for a product that displays a plurality of merchants who are offering said product.

10. The method of claim 9, wherein said catalog page also displays pricing information for said product by said plurality of merchants.

11. The method of claim 1, wherein the relative responsiveness of the document to the search term accounts for at least one sales type.

12. The method of claim 11, wherein said at least one sales type comprises a preferred merchant sales type that represents sales made with a preferred merchant.

13. The method of claim 11, wherein said at least one sales type comprises a non-preferred merchant sales type that represents sales made with a non-preferred merchant.

14. The method of claim 11, wherein said at least one sales type comprises a related search preferred merchant sales type that represents sales made with a preferred merchant from a related search.

15. The method of claim 11, wherein said at least one sales type comprises a catalog sales type that represents sales made with a catalog page.

16. The method of claim 15, wherein said catalog page represents a display page for a product that displays a plurality of merchants who are offering said product.

17. The method of claim 11, wherein said at least one sales type comprises a related search catalog sales type that represents sales made with a catalog page from a related search.

18. The method of claim 11, wherein said at least one sales type comprises a mapped catalog sales type that represents sales of a product that is associated with a catalog page.

19. The method of claim 11, wherein said at least one sales type comprises a related search mapped catalog sales type that represents sales of a product that is associated with a catalog page from a related search.

20. The method of claim 11, further comprising computing a configuration parameter for each of said at least one sales type, wherein said score is generated in accordance with said configuration parameter and said at least one sales type.

21. The method of claim 20, wherein said score is generated in accordance with:

Hotscore_k,p=Σ

(α

_k,t,T(t)C_k,p,t)

where C_k,p,t is a number of said at least one sales type t'"'"'s occurrence for said search term k on said document p, and α

_k,t,T(t) is said configuration parameter.

22. The method of claim 1, wherein generating includes selecting a configuration for generating the score.

23. The method of claim 1, wherein the sales information comprises at least one merchant/product identification pair associated with the search term, each of the at least one merchant/product identification pertaining to a product purchased subsequent to return of the search result set.

24. The method of claim 23, further comprising categorizing the at least one merchant/product identification pair into at least one type;

and eliminating at least one merchant/product identification pair deemed to below confidence.

25. The method of claim 1, wherein generating a score comprises selecting a formula emphasizing a scoring strategy from a plurality of formulas, each of the plurality emphasizing a different scoring strategy.

26. A computer readable medium encoded with computer readable program code, the program code comprising:

instructions operable to obtain sales information associated with a document, wherein the document was returned in a search result set formed in response to a search term;

instructions operable to determine relative responsiveness, compared with other members of the search result set, of the document to the search term based on the sales information and on a position of the document in an ordering of the search result set; and

instructions operable to generate a score for association with the document reflecting the relative responsiveness of the document to the search term.

27. The computer readable medium of claim 26 wherein said score is applied to affect an ordering of the search result set in response to at least one subsequent search using the search term.

28. The computer readable medium of claim 26 further comprising:

instructions for adjusting said score to account for passage of time.

29. The computer readable medium of claim 26 further comprising:

instructions for adjusting said score to account for positioning of said document within a listing order of said search result set.

30. The computer readable medium claim 26 further comprising:

instructions for adjusting said score to account for a specific knowledge of said document.

31. The computer readable medium claim 26 further comprising:

instructions for adjusting said score to account for a specific knowledge of said search term.

32. The computer readable medium of claim 26 further comprising:

instructions for applying said score in conjunction with a text relevancy score, a paid inclusion score, or a paid sponsorship score.

33. The computer readable medium of claim 26 further comprising:

instructions for applying a usage function to said score.