Multi-platform capable inference engine and universal grammar language adapter for intelligent voice application execution

• US 7,609,829 B2
• Filed: 03/17/2004
• Issued: 10/27/2009
• Est. Priority Date: 07/03/2001
• Status: Active Grant

• Current Assignee: HTC Corporation
• Original Assignee: Apptera Incorporated
• Inventors: Chiu, Leo K., Yong, Mang Kang, Luellen, Cory Andrew, Boothroyd, Margaret Ann, Appadurai, Arumugam, Wang, Sandy Chai-Jen, LaBarge, John Robert
• Primary Examiner(s): DEANE JR, WILLIAM J
• Application Number:
  US10/803,851
• Publication Number:
  US 20040225499A1
• Time in Patent Office: 2,050 Days
• Field of Search: 37920101-20103, 37926501-26514
• US Class Current: 379/201.01
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/36 Memories
• CPC Class Codes: H04M 2201/39 using speech synthesis
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/42059 Making use of the calling party identifier
• 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 voice application creation and deployment system includes a voice application server for creating and serving voice applications to clients over a communication network; at least one voice portal node having access to the communication network, the portal node for facilitating client interaction with the voice applications; and an inference engine executable from the application server. In a preferred embodiment the inference engine is called during one or more predetermined points of an ongoing voice interaction to decide whether an inference of client need can be made based on analysis of existing data related to the interaction during a pre-determined point in an active call flow of the served voice application, and if an inference is warranted, determines which inference dialog will be executed and inserted into the call flow.

Claims

1. A voice application creation and deployment system comprising:

a voice application sewer to create and serve voice applications to clients over a communication network;

at least one voice portal node coupled to the communication network, the portal node to facilitate client interaction with the voice applications; and

an inference engine executable from the voice application server, wherein

the inference engine is activated at one or more predetermined points of an ongoing voice interaction, wherein the inference engine is configured to determine whether an inference of client need can be performed, this determination being based on analysis of real-time client data related to the interaction during a pre-determined point in an active call flow of the served voice application and further based on analysis of historical data associated with client interaction, the inference engine further configured to determine which inference dialog is executed and inserted into the call flow if an inference is appropriate.

2. The system of claim 1 wherein the communications network is the Internet network.

3. The system of claim 1 wherein the communications network is a combination of an Internet and telephony network.

4. The system of claim 1 wherein the inference engine is part of the application logic maintained in the voice application server.

5. The system of claim 1 wherein the at least one voice portal is an interactive voice response system combined with a telephony server.

6. The system of claim 1 wherein the at least one voice portal is a computerized node connected to a data network having access to the Internet.

7. The system of claim 1 wherein the inference engine is called at pre-determined points in a call flow of an interaction using a voice application.

8. The system of claim 1 wherein the inference engine uses session information and historical data collected about a caller to determine if an inference should be executed.

9. The system of claim 1 further comprising a universal grammar adapter adapted to produce universal grammar script from a specialized input, the script transformable into any one of a plurality of scripting languages supported by and referred to as a specification parameter of a speech-to-text or text-to-speech engine.

10. The system of claim 1 wherein the inference dialogs are multi part composites of separate dialogs.

11. The system of claim 1 wherein the related data includes at least one of caller line identification, caller number identification, and caller history data.

12. The system of claim 1 wherein the related data is mined for statistics that are compared with an inference model to determine a particular inference.

13. The system of claim 1 further comprising an inference model, including an ontology set and a semantic index.

14. The system of claim 1 wherein the inference engine causes generation of voice dialog from a base of semantics.

15. The system of claim 1 wherein the inference engine causes an inference to occur at more than one time during the course of an interaction.