SYSTEMS AND METHODS FOR RESPONDING TO NATURAL LANGUAGE SPEECH UTTERANCE

• US 20100286985A1
• Filed: 07/19/2010
• Published: 11/11/2010
• Est. Priority Date: 06/03/2002
• Status: Active Grant

• Current Assignee: Dialect, LLC
• Original Assignee: VoiceBox Technologies, Inc. (Microsoft Corporation)
• Inventors: Kennewick, Robert A., Locke, David, Kennewick, Richard, Freeman, Tom, Kennewick, Michael R. JR., Kennewick, Michael R. SR.
• Granted Patent: US 8,155,962 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Systems and methods for receiving natural language queries and/or commands and execute the queries and/or commands. The systems and methods overcome the deficiencies of prior art speech query and response systems through the application of a complete speech-based information query, retrieval, presentation and command environment. This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment can be created. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command.

Claims

1. A method for responding to natural language speech utterances, comprising:

receiving a natural language speech utterance at a speech unit connected to a computer device, wherein the speech unit converts the received natural language speech utterance into an electronic signal;

recognizing one or more words in the electronic signal with a speech recognition engine that operates on the computer device;

identifying a request contained in the natural language speech utterance with a parser that further operates on the computer device, wherein the parser identifies the request contained in the natural language speech utterance from the one or more recognized words;

selecting a domain agent that processes requests in a context for the identified request;

processing the request contained in the natural language speech utterance in a multi-threaded environment with the selected domain agent, wherein processing the request with the selected domain agent includes;

submitting a plurality of asynchronous queries created with the selected domain agent to a plurality of information sources, wherein the plurality of information sources include one or more local information sources and one or more network information sources;

asynchronously evaluating a plurality of results returned from the plurality of information sources to the selected domain agent in response to the plurality of asynchronous queries;

scoring the plurality of asynchronously evaluated results with the selected domain agent to determine one or more of the plurality of results that represents a best response to the request; and

presenting the best response to the request on the computer device.

2. The method of claim 1, wherein processing the request with the selected domain agent further includes the selected domain agent formatting the best response using a format template associated with the determined context, criteria identified from the natural language speech utterance, or a profile for a user that provided the natural language speech utterance.

3. The method of claim 2, wherein processing the request with the selected domain agent further includes the selected domain agent performing one or more variable substitutions and transformations using the format template to format the best response.

4. The method of claim 3, wherein processing the request with the selected domain agent further includes the selected domain agent using probabilistic or fuzzy set decision methods to vary one or more of a personality for presenting the best response, an order for presenting tokens contained in the best response, or a terminology for presenting the tokens contained in the best response.

5. The method of claim 1, wherein scoring the asynchronously evaluated results includes applying probabilistic or fuzzy scoring techniques to one or more of previously evaluated asynchronous results, the determined context, criteria identified from the natural language speech utterance, tokens associated with a desired response to the request, a dialog history relating to one or more prior natural language speech utterances, a profile for a user that provided the natural language speech utterance, or information specific to the selected domain agent.

6. A system for responding to natural language speech utterances, comprising:

a speech unit connected to a computer device, wherein the speech unit receives a natural language speech utterance and converts the received natural language speech into an electronic signal;

a speech recognition engine that operates on the computer device, wherein the speech recognition engine recognizes one or more words in the electronic signal converted from the natural language speech utterance;

a parser that further operates on the computer device, wherein the parser identifies a request contained in the natural language speech utterance from the one or more recognized words and determines a context for the identified request;

a domain agent configured to process requests in the context for the request identified in the natural language speech utterance, wherein the domain agent further operates on the computer device and causes the computer device to;

submit a plurality of asynchronous queries created with the domain agent to a plurality of information sources, wherein the plurality of information sources include one or more local information sources and one or more network information sources;

asynchronously evaluate a plurality of results returned from the plurality of information sources to the domain agent in response to the plurality of asynchronous queries;

score the plurality of asynchronously evaluated results with the domain agent to determine one or more of the plurality of results that represents a best response to the request; and

present the best response to the request on the computer device.

7. The system of claim 6, wherein to process the request with the domain agent, the domain agent further causes the computer device to format the best response using a format template associated with the context for the request contained in the natural language speech utterance, criteria identified from the natural language speech utterance, or a profile for a user that provided the natural language speech utterance.

8. The system of claim 7, wherein to process the request with the domain agent, the domain agent further causes the computer device to perform one or more variable substitutions and transformations using the format template to format the best response.

9. The system of claim 8, wherein to process the request with the domain agent, the domain agent further causes the computer device to use probabilistic or fuzzy set decision methods to vary one or more of a personality for presenting the best response, an order for presenting tokens contained in the best response, or a terminology for presenting the tokens contained in the best response.

10. The system of claim 6, wherein to score the asynchronously evaluated results, the domain agent further causes the computer device to apply probabilistic or fuzzy scoring techniques to one or more of previously evaluated asynchronous results, the determined context, criteria identified from the natural language speech utterance, tokens associated with a desired response to the request, a dialog history relating to one or more prior natural language speech utterances, a profile for a user that provided the natural language speech utterance, or information specific to the domain agent.