Call flow object model in a speech recognition system

• US 7,359,860 B1
• Filed: 02/27/2004
• Issued: 04/15/2008
• Est. Priority Date: 02/27/2003
• Status: Active Grant

• Current Assignee: LumenVox, LLC.
• Original Assignee: LumenVox, LLC.
• Inventors: Schipper, Sidney, Bergman, Michael D., Blake, James F. II, Miller, Edward S., Danielson, Kyle N.
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US10/789,397
• Time in Patent Office: 1,509 Days
• Field of Search: 704/270, 704/275, 379/88.05, 379/88.1
• US Class Current: 704/275
• 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

Abstract

Systems and methods are provided for embodiments of a speech recognition system call flow object model. The systems and methods organize and execute, for example, multiple question directed dialogs, overview dialogs, or natural language directed dialogs. In certain embodiments, the organizing and executing of the natural language directed dialogs uses primary and secondary concepts without requiring a structured response. The systems and methods enable the call flow designers to define particular call flows without requiring the designers to perform any programming or coding.

Claims

1. A method of designing a call flow in a speech recognition system, the method comprising:

organizing and utilizing a multiple question directed dialog in the speech recognition system;

organizing and utilizing a natural language directed dialog in the speech recognition system; and

organizing and utilizing an overview dialog in the speech recognition system,

wherein the natural language directed dialog comprises a primary concept and a secondary concept.

2. A method of designing a call flow in a speech recognition system, the method comprising:

organizing and utilizing a multiple question directed dialog in the speech recognition system;

organizing and utilizing a natural language directed dialog in the speech recognition system; and

organizing and utilizing an overview dialog in the speech recognition system,

wherein the natural language directed dialog comprises a primary concept and a secondary concept without requiring a structured response.

3. A speech recognition system having a plurality of modules for implementing a call flow, the speech recognition system comprising:

at least one global module defining concepts that are available to a caller in a plurality of places in a call flow; and

at least one user-defined module that processes at least a portion of the call flow, wherein at least one user-defined module is a natural language module comprising primary and secondary responses to process natural language input from the caller.

4. The speech recognition system of claim 3, wherein the speech recognition system includes at least two user-defined modules, wherein one of the user-defined modules is a list module comprising a standard caller input module.

5. The speech recognition system of claim 3, wherein the speech recognition system includes at least two user-defined modules, wherein one of the user-defined modules is an overview module that continues after an interruption in the call flow where the interruption occurred.

6. The speech recognition system of claim 3, wherein the speech recognition system includes at least two user-defined modules, wherein one of the user-defined modules is a multilevel module that allows multiple questions to be asked by a caller in the same module.

7. The speech recognition system of claim 3, further comprising an execution chain that provides actions that are performed in response to input by the caller.

8. The speech recognition system of claim 7, wherein the execution chain is a main execution chain.

9. The speech recognition system of claim 7, wherein the execution chain is one or more of the following:

a no match execution chain, a no input execution chain, an error execution chain, a response execution chain, a confirmation execution chain.