Using an automated speech application environment to automatically provide text exchange services

• US 8,027,839 B2
• Filed: 12/19/2006
• Issued: 09/27/2011
• Est. Priority Date: 12/19/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Mandalia, Baiju D., Moore, Victor S., Nusbickel, Wendi L., Da Palma, William V.
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US11/612,996
• Publication Number:
  US 20080147395A1
• Time in Patent Office: 1,743 Days
• Field of Search: 704/270.1, 704/275
• US Class Current: 704/270.1
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

The present solution includes an automated response method. The method can receive user interactions entered through a real-time text exchange interface. These user interactions with the speech application can be dynamically and automatically converted as necessary into a format consumable by a voice server. A text input API of a voice server can be used to allow the voice server to directly accept text input. Further, automated interactions can be received from the voice server, which are dynamically and automatically converted into a format accepted by the text exchange interface. The text exchange interface can be an off-the-shelf unmodified interface. The speech application can be a VoiceXML based application that lacks an inherent text exchange capability.

Claims

1. An automated response method comprising:

receiving user interactions relating to text exchanges entered through a real-time text exchange interface;

executing an unmodified speech enabled application in an automated speech application environment;

establishing a communication session between the automated speech application environment and a text exchange client, wherein the communication session includes a text exchange channel to the text exchange interface and a server channel to a voice server in the automated speech application environment; and

during the communication session;

dynamically and automatically converting the user interactions with the speech enabled application into a format consumable by the voice server;

dynamically and automatically converting output from the voice server into output directly usable by the speech enabled application; and

converting output from the speech enabled application into a format presentable in the text exchange interface.

2. The method of claim 1, wherein the method is performed in a production environment, and wherein the voice server includes an Application Program Interface (API) for handling text input.

3. The method of claim 1, wherein the voice server uses a text input API, which permits the voice server to directly consume text input, and wherein the converting of the voice markup extracts the text content, which is directly presentable in the text exchange interface.

4. The method of claim 3, wherein the text exchange interface is an instant messaging interface, a chat interface, and/or a text messaging interface.

5. The method of claim 1, wherein the voice server is configured to concurrently handle a plurality of communication sessions, said sessions including at least one session involving the text exchange interface and at least one session involving a human using a voice interface.

6. The method of claim 1, wherein the speech application is a single modality application written in a voice markup language, and wherein the interactions sent from and received by the text exchange interface are text based interactions.

7. The method of claim 1, wherein the speech application is a VoiceXML based application.

8. The method of claim 1, wherein the text exchange interface is an off-the-shelf unmodified interface, and wherein the speech application is a standard speech enabled application that lacks an inherent text exchange capability.

9. The method of claim 1, wherein the steps of claim 1 are steps performed automatically by at least one machine in accordance with at least one computer program having a plurality of code sections that are executable by the at least one machine.

10. The method of claim 1, wherein the steps of claim 1 are performed by a service agent and/or a computing device manipulated by the service agent, the steps being performed in response to a service request.

11. A method for extending an automated speech application environment to provide text exchange services comprising:

establishing a communication session between an automated speech application environment and a text exchange client, wherein the communication session includes a server channel to the automated speech application environment, wherein the communication session includes a text exchange channel to the text exchange client, wherein the automated speech application environment is configured to execute automated speech response applications that permit users to interact in real-time over a voice channel and wherein the text exchange client is configured to interact in real-time over a text exchange channel with another text exchange device; and

dynamically and automatically converting interactions between the server channel and the text exchange channel during the communication session.

12. The method of claim 11, wherein at least one of the automated speech response applications is a VoiceXML based application, wherein a text input API of a voice server included in the speech application environment is used to accept text based input.

13. The method of claim 11, further comprising:

automatically converting voice markup containing text content received from the server channel into text messages including the text content, which are conveyed over the text exchange channel.

14. The method of claim 11, wherein the text exchange interface is an instant messaging interface, a chat interface, and/or a text messaging interface.

15. The method of claim 11, wherein the text exchange interface is an off-the-shelf unmodified interface, and wherein the speech application environment includes at least one standard speech enabled application that lacks an inherent text exchange capability.

16. The method of claim 11, wherein the method is performed automatically by at least one machine in accordance with at least one computer program having a plurality of code sections that are executable by the at least one machine.

17. A system for providing text exchange services comprising:

a text exchange client configured to send and receive real-time text exchanges over a text exchange channel;

a speech application environment configured to execute an automated speech response application that permits users to interact in real-time over a voice channel; and

a Chatbot server configured to establish a communication session involving the text exchange client and the automated speech response application, wherein the Chatbot server can dynamically convert messages between the text exchange client and the speech response application during the communication session in a manner transparent to the text exchange client and to the automated speech response application.

18. The system of claim 17, wherein speech application environment includes an Application Program Interface (API) for handling text input, which the Chatbot server conveys.

19. The system of claim 17, wherein the speech application environment supports a plurality of concurrently executing communication sessions using the automated speech response application, wherein at least one of the concurrently executing communication sessions is a text exchange communication with the text exchange client, and wherein at least one of the concurrently executing communication sessions is a voice based communication session with a user conducted over the voice channel.

20. The system of claim 17, wherein the text exchange interface is an off-the-shelf unmodified interface, and wherein the automated speech response application is a VoiceXML based application that lacks an inherent text exchange capability.