Method and system for predictive interactive voice recognition

• US 20060018440A1
• Filed: 07/26/2004
• Published: 01/26/2006
• Est. Priority Date: 07/26/2004
• Status: Active Grant

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors LLC (General Motors Company)
• Inventors: Watkins, Gary A., Smith, James M.
• Granted Patent: US 8,000,452 B2
• Time in Patent Office: Days
• US Class Current: 379/88.10
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/405 involving speaker-dependent recognition adaptation to speaker for speech recognition G10L15/07
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A method for a predictive interactive voice recognition system includes receiving a voice call, associating said voice call with a behavioral pattern, and invoking a service context responsive to said behavioral pattern. The system provides advantages of improved voice recognition and more efficient use of the voice user interface to obtain services.

Claims

1. A method for a predictive interactive voice recognition system comprising the steps of:

receiving a voice call;

associating said voice call with a behavioral pattern; and

invoking a service context responsive to said behavioral pattern.

2. The method of claim 1 also comprising the steps of:

receiving a caller utterance;

determining, responsive to the caller utterance, a confidence factor representative of a degree of certainty that the caller utterance matches the service context; and

exiting the service context if the utterance does not match the service criteria.

3. The method of claim 1 also comprising the steps of:

recording caller service requests;

creating a plurality of data records responsive to the caller service requests;

categorizing the caller service requests responsive to a plurality of service contexts; and

recording a caller behavioral pattern in response to the categorizing.

4. The method of claim 1, also comprising the steps of:

identifying a plurality of parameters related to the caller and the received voice call; and

categorizing the parameters into the behavioral pattern.

5. The method of claim 3, also comprising the step of retrieving stored caller information, wherein the step of categorizing is also responsive to the stored caller information.

6. The method of claim 3 also comprising the step of assigning a confidence factor responsive to said caller behavioral pattern.

7. The method of claim 1 wherein the step of invoking comprises:

generating a caller utterance confidence factor responsive to the received voice call;

generating a behavior pattern confidence factor responsive to the received voice call and stored data; and

generating a composite confidence factor responsive to the caller utterance confidence factor and the behavior pattern confidence factor, wherein the step of invoking is responsive to the composite confidence factor.

8. A method of predictive interactive voice recognition comprising the steps of:

receiving a call from a vehicle with a telematics unit to an interactive voice recognition system;

associating said call with a behavioral pattern comprising previous caller service requests; and

invoking a service context responsive to said behavioral pattern.

9. A system for predictive interactive voice recognition comprising:

means for receiving a voice call;

means for associating said voice call with a behavioral pattern; and

means for invoking a service context responsive to said behavioral pattern.

10. The system of claim 9 further comprising:

means for the determination of a confidence factor responsive to a caller utterance, wherein the means for invoking the service context is responsive to the confidence factor.

11. The system of claim 9 further comprising:

means for recording caller service requests;

means for creating a plurality of data records responsive to said caller service request; and

means for categorizing caller service requests responsive to a plurality of service contexts;

wherein the behavior pattern is responsive to the means for categorizing.