VOICE-BASED SEARCH PROCESSING

• US 20090006345A1
• Filed: 06/28/2007
• Published: 01/01/2009
• Est. Priority Date: 06/28/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Naam, Ramez, Flake, Gary W., Platt, John C., Gupta, Anoop, Hurst-Hiller, Oliver, Griffin, Trenholme J.
• Granted Patent: US 8,260,809 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.

Claims

1. A computer-implemented system that facilitates a search, comprising:

a voice recognition component that receives a partial query input as voice signals of a user;

a classifier that processes the partial query input and infers an intended search goal therefrom;

a query formulation component that generates a formal query based on the inferred intended search goal; and

a search engine that receives and processes the formal query to return search results.

2. The system of claim 1, wherein the search engine processes output results of the voice recognition component and preliminary search results to arrive at the search results.

3. The system of claim 1, wherein the search results are based on a confidence value output by the voice recognition component.

4. The system of claim 1, wherein the classifier infers multiple different search goals based on the partial query input and the search engine processes the multiple different search goals to return a set of search results for each different search goal.

5. The system of claim 1, further comprising a context component that generates context information related to a software environment in which the user is currently active, the context information employed by the classifier to infer the intended search goal.

6. The system of claim 1, further comprising a location component that computes geographic location data of the user and which location data the query formulation component processes to generate the formal query.

7. The system of claim 1, wherein the classifier infers the intended search goal based on the voice signals and at least one other sensed input type.

8. The system of claim 1, further comprising a machine learning and reasoning component that learns and reasons about user interaction with the formal query and ranks the search results based on the user interaction.

9. The system of claim 1, further comprising a syntactical processing component that receives recognized voice signals output from the voice recognition component and, analyzes and processes word usage in the recognized voice signals for syntax properties.

10. The system of claim 1, further comprising a natural language processing component that receives recognized voice signals output from the voice recognition component and, analyzes and processes word usage in the recognized voice signals for natural language characteristics.

11. The system of claim 1, further comprising a query database that stores query information and from which similar or matching characters sets, terms, or phrases are derived for generating the formal query.

12. A computer-implemented method of completing a search input, comprising:

receiving a partial query input from a user in a form of an utterance;

processing the utterance into voice data;

analyzing the voice data for terms and phrases;

comparing the terms and phrases with query information of a datasource;

inferring an intended goal from matching query information selected from the datasource to complete the partial query input; and

formulating a formal query based on the matching query information.

13. The method of claim 12, further comprising outputting recognition results based on processing of the utterance into the voice data, and processing the recognition results in combination with preliminary search results obtained from processing the formal query to arrive at a final set of search results.

14. The method of claim 12, further comprising:

inferring multiple intended goals based on possible interpretations to complete the partial input query;

processing the formal query to return search results; and

assigning search results to each of the possible interpretations for selection by the user.

15. The method of claim 12, further comprising processing historical information about the user and utilizing the processed historical information to generate the formal query.

16. The method of claim 12, further comprising performing a search based on the formal query, and storing ambiguities derived as part of the search for processing of a future search.

17. The method of claim 12, further comprising monitoring user interaction with the formal query and, learning and reasoning about the user interaction to refine a future partial query input.

18. The method of claim 12, further comprising:

inferring multiple different search goals based on processing of the utterance into the voice data;

outputting a confidence value associated with each of the multiple different search goals;

formulating a formal query for each of the multiple different search goals;

executing the formal queries to return search results; and

adjusting a number of the search results to be associated with each of the formal queries based on the associated confidence value.

19. The method of claim 12, further comprising processing multiple input data types to generate the partial query input, and formulating the formal query based on inferences made on corresponding sets of query information for the multiple input types.

20. A computer-executable system, comprising:

means for receiving part of a search query as an utterance;

means for processing the utterance into words-and-phrases data;

means for processing user preferences data and geolocation data;

means for inferring query information from the datasource based on the geolocation data and user preferences data;

means for formulating a final query based on the inferred query information; and

means for processing the final query to return search results, and presenting the search results based in part on recognition results from processing the utterance into the words-and-phrases data.