Method and system for predictive interactive voice recognition

• US 8,000,452 B2
• Filed: 07/26/2004
• Issued: 08/16/2011
• Est. Priority Date: 07/26/2004
• Status: Expired due to Fees

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors LLC (General Motors Company)
• Inventors: Smith, James M., Watkins, Gary A.
• Primary Examiner(s): Elahee; Md S
• Application Number:
  US10/898,857
• Publication Number:
  US 20060018440A1
• Time in Patent Office: 2,577 Days
• Field of Search: 379 8801- 8803, 379/88.23, 704/257, 704/273, 704/254, 704/246, 704/247, 704/251, 704/252, 704/E15.001, 340/905
• US Class Current: 379/88.02
• 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;

receiving an utterance from a caller;

determining one or more words from the caller'"'"'s utterance by performing speech recognition on the utterance;

accessing a behavioral pattern associated with the caller that indicates the caller'"'"'s past behavior based on multiple previous calls from the caller;

determining a desired service context based on a combination of the one or more determined words and the behavioral pattern, wherein the desired service context is determined using at least one confidence factor related to the one or more determined words, the behavioral pattern or both; and

invoking the desired service context.

2. The method of claim 1, wherein the step of determining one or more words further comprises the steps of determining in response to the utterance a caller utterance confidence factor representative of a degree of certainty that the caller utterance matches a word indicative of a service context.

3. The method of claim 2, wherein the accessing step further comprises accessing a behavior pattern confidence factor.

4. The method of claim 3, wherein the step of determining a desired service context further comprises forming a composite confidence factor from the caller utterance confidence factor and the behavior pattern confidence factor, and then using the composite confidence factor to determine the desired service context.

5. The method of claim 1, further 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 based on a plurality of service contexts; and

determining the behavioral pattern based on one or more of the categorizations.

6. The method of claim 1, further comprising the steps of:

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

determining the behavioral pattern based on the parameters.

7. The method of claim 6, further comprising the step of retrieving stored caller information, wherein the step of determining the behavioral pattern is based at least in part on the stored caller information.