Listings optimization using a plurality of data sources

• US 20050027699A1
• Filed: 01/06/2004
• Published: 02/03/2005
• Est. Priority Date: 08/01/2003
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Awadallah, Amr, Diab, Ali, Gerster, David A., Cadogan, Timothy Roy
• Granted Patent: US 7,617,203 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A system is provided for allocating combinations of search results, types of space, and/or other information from different sources (e.g., search engines) in which a type of space, search results, and/or other information from at least one source or type or from each source or type, for example, are optimized to obtain an optimum commercial value. Using the example of a search, a commercial metric and a user satisfaction metric are established for search terms and used in the optimization process. In calculating the commercial value and the user satisfaction value for a set of search results, the weight given to the commercial value and the user satisfaction value of a search result is different depending on its source. Optionally, keeping the user satisfaction value above a certain threshold is treated as a constraint while optimizing the commercial value. Alternatively, a tradeoff may be allowed between the minimum threshold for the user satisfaction and a better commercial value. For example, a commercial value may be associated with the commercial metric and quality metric so that the total commercial value may be calculated and optimized.

Claims

1. A method comprising:

receiving a query

in response to the query, constructing a composite search result that includes search result candidates from a plurality of candidate sources;

wherein the step of constructing includes determining an amount of search results of each of said search result candidates based on at least a plurality of estimated attribute values of said composite search result;

wherein each of said plurality of attribute values is a value that represents a measure of an attribute of the composite search result; and

providing said composite search result as an answer to said query.

2. The method of claim 1 further comprising:

forming a plurality of individual commercial values by at least assigning an individual commercial value to each of the plurality of attribute values; and

determining a composite commercial value from the plurality of individual commercial values;

wherein the determining of the amount of search results selected is based on at least the plurality of estimated attribute values via being based on the composite commercial value.

3. The method of claim 1, wherein the plurality of attribute values include at least a first attribute value that is a measure of commercial value and a second attribute value that is a measure of user satisfaction.

4. The method of claim 1, wherein each search result candidate is associated with a plurality of attribute values.

5. The method of claim 1, wherein one of the plurality of attribute values includes an value associated with an estimated market share, and wherein the estimated market share is an estimated amount of sponsored search result candidates received.

6. The method of claim 1, wherein the plurality of attribute values includes a value associated with name recognition.

7. The method of claim 1, wherein the plurality of attribute values includes a monetary value.

8. The method of claim 1, wherein at least one of the search result candidates is an amount space on a web page.

9. The method of claim 1, wherein the search result candidates include advertisements.

10. The method of claim 1, wherein the search result candidates include sponsored results that are sponsored by at least one of plurality of the candidate sources.

11. The method of claim 1, wherein the plurality of search result candidates include at least one search result candidate, which includes search results that were determined based on monetary payments.

12. The method of claim 1, wherein the plurality of search result candidates include at least one search result candidate that has search results that were not determined based on a monetary payment.

13. The method of claim 1, wherein at least one of the plurality attribute values is a composite commercial value, and the constructing includes at least:

calculating the commercial value by performing a weighted sum of individual commercial values that corresponds to a composite search result, wherein each of the individual commercial values is associated with search results selected from a different one of the plurality of search result candidates; and

adjusting a choice of the commercial attribute values according to an adjustment of the amount of search results that are

taken from the plurality of search result candidates and included in the composite search results.

14. The method of claim 1, wherein at least one of the attribute values is a user satisfaction value, and the constructing includes at least:

calculating a composite user satisfaction value by performing a weighted sum of individual user satisfaction values, wherein each individual user satisfaction value corresponds to search results selected from a different one of search result candidates; and

adjusting a choice of the composite user satisfaction value according to an adjustment of an amount of search results that are

selected from the plurality of search result candidates and included in the composite search results.

15. The method of claim 1, wherein the constructing includes maintaining at least one of the plurality of attribute values equal to or above a fixed threshold value.

16. The method of claim 1, wherein the constructing includes allowing tradeoffs between a first attribute value of the plurality of attribute values and a second attribute value of the plurality of attribute values;

wherein the tradeoff includes expanding a range of acceptable values of the first attribute value in exchange for a given value of the second attribute value.

17. The method of claim 1, wherein one of the plurality of attribute values is calculated using a plurality weights for forming a weighted sum of a plurality of click-thru-ratios, each of the plurality of weights and of the plurality of click-thru-ratios corresponds to search results selected from one of the plurality of search result candidates.

18. The method of claim 1, wherein step of constructing comprises:

calculating a first estimated attribute value and a second estimated attribute value for a plurality of possible composite search results; and

selecting one of the plurality of possible composite search results as the composite search result to the send to the user,

wherein the plurality of possible search results includes at least one possible composite search result having a preferred value for a first estimated attribute value;

wherein the preferred value is a value for the first estimated attribute value that is preferred over at least one other possible composite search result; and

wherein the composite search results that is selected has a second estimated attribute value that has a predetermined relationship to a threshold value, and has a first estimated attribute value that is closer to the preferred value than any of the other possible composite search results having the predetermined relationship.

19. The method of claim 18, wherein the predetermined relationship is that the second estimated attribute value is less than the threshold value.

20. The method of claim 18, wherein the predetermined relationship is that the second estimated attribute value is greater than the threshold value.

23. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 1.

24. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 2.

25. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 3.

26. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 4.

27. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 5.

28. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 6.

29. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 7.

30. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 8.

31. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 9.

32. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 10.

33. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 11.

34. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 12.

35. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 13.

36. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 14.

37. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 15.

38. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 16.

39. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 17.

40. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 18.

41. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 19.

42. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 20.

21. A method comprising:

receiving a query;

in response to the query, determining an estimated user satisfaction value for a composite search result, wherein the composite search result includes search results selected from a plurality of search result candidates from a plurality of candidate sources and the user satisfaction value is based on search results selected from at least two of the plurality of search result candidates; and

providing an answer to the query including the composite search results.

22. The method of claim 21, wherein the determining of the user satisfaction is based on search results selected from all of the plurality of search result candidates.

43. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 21.

44. A computer-readable medium carrying one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform the method recited in claim 22.