Method, Apparatus and Computer Program Product for Determining Relevance and/or Ambiguity in a Search System

• US 20080270378A1
• Filed: 06/28/2007
• Published: 10/30/2008
• Est. Priority Date: 04/24/2007
• Status: Abandoned Application

• Current Assignee: Nokia Corporation
• Original Assignee: Nokia Corporation
• Inventors: Reponen, Erika, Setlur, Vidya, Gao, Jiang, Pulli, Kari, Schloter, C. Philipp
• Application Number:
  US11/769,951
• Publication Number:
  US 20080270378A1
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content

Abstract

An apparatus for a determining relevance and/or ambiguity in a search system may include a processing element configured for receiving visual media comprising a query, determining search results including a matching score for at least one candidate visual media with respect to the query based on ambiguity and relevance, utilizing a mapping function to provide a confidence level associated with the search results, and providing a visualization of the search results based on the confidence level.

Claims

1. A method comprising:

receiving visual media comprising a query;

determining search results including a matching score for at least one candidate visual media with respect to the query based on ambiguity and relevance;

utilizing a mapping function to provide a confidence level associated with the search results; and

providing a visualization of the search results based on the confidence level.

2. The method of claim 1, wherein utilizing the mapping function comprises applying a transform function trained using parameters determined from previously used data to determine the confidence level based on a plurality of extracted features of the at least one candidate visual media.

3. The method of claim 1, wherein utilizing the mapping function comprises applying a plurality of trained transform functions, each of which corresponds to a corresponding one of a plurality of features to determine a corresponding confidence level with respect to each of the plurality of features.

4. The method of claim 1, wherein utilizing the mapping function further comprises applying linkage analysis to an output of the mapping function to determine the confidence level.

5. The method of claim 4, wherein applying linkage analysis further comprises applying information defining similarity between visual media of a database from which the at least one candidate visual media is accessed to an integrated output of the mapping function.

6. The method of claim 1, wherein utilizing the mapping function further comprises applying popularity information regarding previous matching operations for the at least one candidate visual media to an output of the mapping function to determine the confidence level.

7. The method of claim 1, wherein providing the visualization comprises providing relevancy indicators to indicate the confidence level.

8. The method of claim 1, wherein providing the visualization comprises providing an indication of an exact match between the query and the candidate visual media.

9. The method of claim 1, wherein providing the visualization comprises providing a different visualization element for each of various different confidence levels.

10. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for receiving visual media comprising a query;

a second executable portion for determining search results including a matching score for at least one candidate visual media with respect to the query based on ambiguity and relevance;

a third executable portion for utilizing a mapping function to provide a confidence level associated with the search results; and

a fourth executable portion for providing a visualization of the search results based on the confidence level.

11. The computer program product of claim 10, wherein the third executable portion includes instructions for applying a transform function trained using parameters determined from previously used data to determine the confidence level based on a plurality of extracted features of the at least one candidate visual media.

12. The computer program product of claim 10, wherein the third executable portion includes instructions for applying a plurality of trained transform functions, each of which corresponds to a corresponding one of a plurality of features to determine a corresponding confidence level with respect to each of the plurality of features.

13. The computer program product of claim 10, wherein the third executable portion includes instructions for applying linkage analysis to an output of the mapping function to determine the confidence level.

14. The computer program product of claim 13, wherein the third executable portion includes instructions for applying information defining similarity between visual media of a database from which the at least one candidate visual media is accessed to an integrated output of the mapping function.

15. The computer program product of claim 10, wherein the third executable portion includes instructions for applying popularity information regarding previous matching operations for the at least one candidate visual media to an output of the mapping function to determine the confidence level.

16. The computer program product of claim 10, wherein the fourth executable portion includes instructions for providing relevancy indicators to indicate the confidence level.

17. The computer program product of claim 10, wherein the fourth executable portion includes instructions for providing an indication of an exact match between the query and the candidate visual media.

18. The computer program product of claim 10, wherein the fourth executable portion includes instructions for providing a different visualization element for each of various different confidence levels.

19. An apparatus comprising a processing element configured to:

receive visual media comprising a query;

determine search results including a matching score for at least one candidate visual media with respect to the query based on ambiguity and relevance;

utilize a mapping function to provide a confidence level associated with the search results; and

provide a visualization of the search results based on the confidence level.

20. The apparatus of claim 19, wherein the processing element is further configured to apply a transform function trained using parameters determined from previously used data to determine the confidence level based on a plurality of extracted features of the at least one candidate visual media.

21. The apparatus of claim 19, wherein u the processing element is further configured to apply a plurality of trained transform functions, each of which corresponds to a corresponding one of a plurality of features to determine a corresponding confidence level with respect to each of the plurality of features.

22. The apparatus of claim 19, wherein the processing element is further configured to apply linkage analysis to an output of the mapping function to determine the confidence level.

23. The apparatus of claim 22, wherein the processing element is further configured to apply information defining similarity between visual media of a database from which the at least one candidate visual media is accessed to an integrated output of the mapping function.

24. The apparatus of claim 19, wherein the processing element is further configured to apply popularity information regarding previous matching operations for the at least one candidate visual media to an output of the mapping function to determine the confidence level.

25. The apparatus of claim 19, wherein the processing element is further configured to provide relevancy indicators to indicate the confidence level.

26. The apparatus of claim 19, wherein the processing element is further configured to provide an indication of an exact match between the query and the candidate visual media.

27. The apparatus of claim 19, wherein the processing element is further configured to provide a different visualization element for each of various different confidence levels.

28. An apparatus comprising:

means for receiving visual media comprising a query image;

means for determining search results including a matching score for at least one candidate visual media with respect to the query based on ambiguity and relevance;

means for utilizing a mapping function to provide a confidence level associated with the search results; and

means for providing a visualization of the search results based on the confidence level.

29. The apparatus of claim 28, further comprising means for applying linkage analysis to an output of the mapping function to determine the confidence level.

30. The apparatus of claim 28, further comprising means for applying information defining similarity between visual media of a database from which the at least one candidate visual media is accessed to an integrated output of the mapping function.

31. A method comprising:

utilizing a mapping function to provide a confidence level associated with search results including a matching score for at least one candidate visual media with respect to visual media comprising a query based on ambiguity and relevance; and

providing information for use in a visualization of the search results based on the confidence level.

32. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for utilizing a mapping function to provide a confidence level associated with search results including a matching score for at least one candidate visual media with respect to visual media comprising a query based on ambiguity and relevance; and

a second executable portion for providing information for use in a visualization of the search results based on the confidence level.

33. An apparatus comprising a processing element configured to:

utilize a mapping function to provide a confidence level associated with search results including a matching score for at least one candidate visual media with respect to visual media comprising a query based on ambiguity and relevance; and

provide information for use in a visualization of the search results based on the confidence level.