RANK-BASED ESTIMATE OF RELEVANCE VALUES

• US 20100153357A1
• Filed: 12/15/2009
• Published: 06/17/2010
• Est. Priority Date: 06/27/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Slackman, Richard O.
• Granted Patent: US 8,078,606 B2
• Time in Patent Office: Days
• US Class Current: 707/707
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99937 Sorting
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method includes submitting a query to multiple search engines. The method also includes receiving a ranked list of search results from each search engine based on the query. The method includes determining a search engine weighting value for each search engine, where each search engine weighting value indicates a degree of relevance of a category of specialization of a particular search engine to a category of the query.

Claims

1. A method, comprising:

submitting a query to multiple search engines;

receiving a ranked list of search results from each search engine based on the query; and

determining a search engine weighting value for each search engine of the multiple search engines, wherein each search engine weighting value indicates a degree of relevance of a category of specialization of a particular search engine to a category of the query.

2. The method of claim 1, further comprising determining a final relevance value for each search result.

3. The method of claim 2, wherein determining the final relevance value for each search result includes applying to each search result a particular search engine weighting value corresponding to the search engine that supplied the particular search result.

4. The method of claim 3, wherein determining the final relevance value for each search result includes applying a search result relevance value to each search result.

5. The method of claim 4, wherein the search result relevance value is based on an actual relevance value.

6. The method of claim 5, wherein the actual relevance value is received from the search engine that supplied the particular search result.

7. The method of claim 6, further comprising estimating the search result relevance value for each search result without using a corresponding actual relevance value.

8. The method of claim 7, wherein estimating the search result relevance value includes:

determining a first search result relevance value for a most relevant search result of a first ranked list;

determining a second search result relevance value for a least relevant search result of the first ranked list; and

determining other search result relevance values in the first ranked list based on the first search result relevance value for the most relevant search result of the first ranked list and the second search result relevance value for the least relevant search result of the first ranked list.

9. The method of claim 5, wherein each ranked list contains at least one actual relevance value.

10. The method of claim 2, further comprising combining the search results into a single list.

11. The method of claim 10, further comprising sorting the single list in descending order based on the final relevance values.

12. The method of claim 11, further comprising displaying at least a portion of the ordered list.

13. A system, comprising:

a processor configured to;

submitting a query to multiple search engines;

receiving a ranked list of search results from each search engine based on the query; and

determining a search engine weighting value for each search engine of the multiple search engines, wherein each search engine weighting value indicates a degree of relevance of a category of specialization of a particular search engine to a category of the query.

14. The system of claim 13, further comprising estimating a search result relevance value for each search result without using a corresponding actual relevance value.

15. The system of claim 14, further comprising normalizing the search result relevance value for each search result.

16. The system of claim 15, further comprising determining a final relevance value for each search result based on the normalized search result relevance value for each search result and the associated search engine weighting value of the search engine that supplied the search result.

17. The system of claim 16, wherein determining the final relevance value includes multiplying the normalized search result relevance value by the associated search engine weighting value.

18. A computer-readable storage medium storing instructions executable by a computer system to:

submit a query to multiple search engines;

receive a ranked list of search results from each search engine based on the query;

determine a search engine weighting value for each search engine of the multiple search engines, wherein each search engine weighting value indicates a degree of relevance of a category of specialization of a particular search engine to a category of the query; and

determining a final relevance value for each search result based on the search engine weighting value corresponding to the search engine that supplied the particular search result.

19. The computer-readable storage medium of claim 18, further comprising instructions executable by the computer system to combine the search results into a single list.

20. The computer-readable storage medium of claim 19, further comprising instructions executable by the computer system to sort the single list in descending order based on the final relevance values.