Method for refining a search

• US 9,015,045 B2
• Filed: 03/11/2013
• Issued: 04/21/2015
• Est. Priority Date: 03/11/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Lavallee, Jean-Francois
• Primary Examiner(s): Baker, Charlotte M
• Application Number:
  US13/792,954
• Publication Number:
  US 20140257811A1
• Time in Patent Office: 771 Days
• Field of Search: 704/244, 704/239, 704/257, 704/270
• US Class Current: 704/244
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

A method for refining a search is provided. Embodiments may include receiving a first speech signal corresponding to a first utterance and receiving a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance. Embodiments may also include identifying information associated with the first speech signal as first speech signal information and identifying information associated with the second speech signal as second speech signal information. Embodiments may also include determining a first quantity of search results based upon the first speech signal information and determining a second quantity of search results based upon the second speech signal information. Embodiments may also include comparing at least one of the first quantity of search results and the second quantity of search results with a quantity of search results from a combination of information of the first and second signals and determining an information gain from the comparison.

Claims

1. A computer-implemented method for refining a search comprising:

receiving, using one or more computing devices, a first speech signal corresponding to a first utterance;

receiving a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance;

identifying information associated with the first speech signal as first speech signal information;

identifying information associated with the second speech signal as second speech signal information;

determining a first quantity of search results based upon, at least in part, the first speech signal information;

determining a second quantity of search results based upon, at least in part, the second speech signal information;

comparing at least one of the first quantity of search results and the second quantity of search results with a quantity of search results from a combination of information of the first and second signals; and

determining an information gain from the comparison.

2. The method of claim 1, further comprising:

identifying a search expansion, based upon, at least in part, the information gain.

3. The method of claim 1, further comprising:

refining a search based upon at least in part, the information gain.

4. The method of claim 3, further comprising:

generating at least one set of search results based upon the refined search.

5. The method of claim 3, wherein refining is based upon, at least in part, one or more features vectors.

6. The method of claim 5, wherein refining includes, at least in part, calculating a score for one or more potential refinement sources.

7. The method of claim 6, further comprising:

identifying a refinement source from the one or more potential refinement sources based upon, at least in part, the score.

8. A system for refining a search comprising:

one or more computing devices configured to receive a first speech signal corresponding to a first utterance, the one or more computing devices further configured to receive a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance, the one or more computing devices further configured to identify information associated with the first speech signal as first speech signal information and to identify information associated with the second speech signal as second speech signal information, the one or more computing devices further configured to determine a first quantity of search results based upon, at least in part, the first speech signal information and to determine a second quantity of search results based upon, at least in part, the second speech signal information, the one or more processors further configured to compare at least one of the first quantity of search results and the second quantity of search results with a quantity of search results from a combination of information of the first and second signals and to determine an information gain from the comparison.

9. The system of claim 8, wherein the one or more computing devices are further configured to identify a search expansion, based upon, at least in part, the information gain.

10. The system of claim 8, wherein the one or more computing devices are further configured to refine a search based upon at least in part, the information gain.

11. The system of claim 10, wherein the one or more computing devices are further configured to generate at least one set of search results based upon the refined search.

12. The system of claim 10, wherein refining is based upon, at least in part, one or more features vectors.

13. The system of claim 12, wherein refining includes, at least in part, calculating a score for one or more potential refinement sources.

14. The system of claim 13, wherein the one or more computing devices are further configured to identify a refinement source from the one or more potential refinement sources based upon, at least in part, the score.

15. A non-transitory computer readable storage medium having stored thereon instructions that when executed by a processor perform one or more operations, the operations comprising:

receiving, using one or more computing devices, a first speech signal corresponding to a first utterance;

receiving a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance;

identifying information associated with the first speech signal as first speech signal information;

identifying information associated with the second speech signal as second speech signal information;

determining a first quantity of search results based upon, at least in part, the first speech signal information;

determining a second quantity of search results based upon, at least in part, the second speech signal information;

comparing at least one of the first quantity of search results and the second quantity of search results with a quantity of search results from a combination of information of the first and second signals; and

determining an information gain from the comparison.

16. The computer readable storage medium of claim 15, further comprising:

identifying a search expansion, based upon, at least in part, the information gain.

17. The computer readable storage medium of claim 15, further comprising:

refining a search based upon at least in part, the information gain.

18. The computer readable storage medium of claim 17, further comprising:

generating at least one set of search results based upon the refined search.

19. The computer readable storage medium of claim 17, wherein refining is based upon, at least in part, one or more features vectors.

20. The computer readable storage medium of claim 19, wherein refining includes, at least in part, calculating a score for one or more potential refinement sources.