Method and system for multi-client access to a dialog system

• US 6,377,913 B1
• Filed: 08/13/1999
• Issued: 04/23/2002
• Est. Priority Date: 08/13/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Ramaswamy, Ganesh N., Coffman, Daniel M., Neti, Chalapathy V., Kleindienst, Jan, Gopalakrishnan, Popani
• Primary Examiner(s): Lim, Krisna
• Application Number:
  US09/374,026
• Time in Patent Office: 984 Days
• Field of Search: 704/2, 704/8, 704/9, 704/257, 704/258, 709/203
• US Class Current: 704/8
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L

Abstract

In accordance with the invention, a method and system for accessing a dialog system employing a plurality of different clients, includes providing a first client device for accessing a conversational system and presenting a command to the conversational system by converting the command to a form understandable to the conversational system. The command is interpreted by employing a mediator, a dialog manager and a multi-modal history to determine the intent of the command based on a context of the command. A second client device is determined based on a predetermined device preference stored in the conversational system. An application is abstracted to perform the command, and the results of the performance of the command are set to the second client device.

Claims

1. A method for accessing a dialog system employing a plurality of different clients comprising:

providing a first client device for accessing a conversational system;

presenting a command to the conversational system by converting the command to a form understandable to the conversational system;

interpreting the command by employing a mediator, a dialog manager and a multi-modal history to determine the intent of the command based on a context of the command;

determining a second client device based on a predetermined device preference;

abstracting an application to perform the command; and

sending results of the performance of the command to the second client device.

2. The method as recited in claim 1, wherein the first client device is the same as the second client device.

3. The method as recited in claim 1, wherein the second client device is a plurality of client devices.

4. The method as recited in claim 1, wherein the first client device and the second client device include at least one of a telephone, a computer and a personal digital assistant.

5. The method as recited in claim 1, wherein the command is presented in natural speech, the method further comprising the steps of recognizing the speech and converting the speech to a formal language.

6. The method as recited in claim 5, further comprising the steps of outputting the results of the performance of the command to the second client device by speech synthesis.

7. The method as recited in claim 1, wherein the command is presented graphically, the method further comprising the steps of responding to the command by one or both of a graphical result and synthesized speech.

8. The method as recited in claim 1, further comprising the step providing a component abstraction interface to interface with applications such that the conversational system is shielded from details of execution of the application.

9. The method as recited in claim 1, further comprising the step querying a user via the first client device for one of information about the device preference and clarification of command information.

10. The method as recited in claim 1, wherein the mediator employs information about one of the first client device and the second client device to determine the context of the command.

11. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for accessing a dialog system employing a plurality of different clients, the method steps comprising:

providing a first client device for accessing a conversational system;

presenting a command to the conversational system by converting the command to a form understandable to the conversational system;

interpreting the command by employing a mediator, a dialog manager and a multi-modal history to determine the intent of the command based on a context of the command;

determining a second client device based on a predetermined device preference;

abstracting an application to perform the command; and

sending results of the performance of the command to the second client device.

12. The program storage device as recited in claim 11, wherein the first client device is the same as the second client device.

13. The program storage device as recited in claim 11, wherein the second client device is a plurality of client devices.

14. The program storage device as recited in claim 11, wherein the first client device and the second client device include at least one of a telephone, a computer and a personal digital assistant.

15. The program storage device as recited in claim 11, wherein the command is presented in natural speech, the method further comprising the steps of recognizing the speech and converting the speech to a formal language.

16. The program storage device as recited in claim 15, further comprising the steps of outputting the results of the performance of the command to the second client device by speech synthesis.

17. The program storage device as recited in claim 11, wherein the command is presented graphically, the method comprising the steps of responding to the command by one or both of a graphical result and synthesized speech.

18. The program storage device as recited in claim 11, further comprising the step providing a component abstraction interface to interface with applications such that the conversational system is shielded from details of execution of the application.

19. The program storage device as recited in claim 11, further comprising the step querying a user via the first client device for one of information about the device preference and clarification of command information.

20. The program storage device as recited in claim 11, wherein the mediator employs information about one of the first client device and the second client device to determine the context of the command.

21. A system for accessing a dialog system employing a plurality of different clients, comprising:

a device handling and abstraction system adapted to provide input and output interfacing to a plurality of different client devices, the device handling and abstraction system for receiving commands from at least one client device and converting the commands to a form acceptable to a conversational system;

the conversational system coupled to the device handling and abstraction system for receiving converted commands, the conversational system adapted to interpret the converted commands based on a context of the command to determine an appropriate application responsive to the converted command, the conversational system including a device preference to which results of executing the converted commands are sent; and

an application abstraction system coupled to the conversational system and adapted for determining which applications are appropriate for executing the converted command, the application abstraction system being adapted to interface with a plurality of applications and to shield the conversational system from communications with the applications.

22. The system as recited in claim 21, wherein the plurality of different client devices include at least one of a telephone, a computer and a personal digital assistant.

23. The system as recited in claim 21, wherein a command is input to a first client and a result is received by the first client.

24. The system as recited in claim 21, wherein the commands include graphical commands and speech commands.

25. The system as recited in claim 21, wherein the results of executing the converted commands are conveyed to a client device as one of or both of synthesized speech and graphics.

26. The system as recited in claim 21, wherein the device preference includes a plurality of client devices.

27. The system as recited in claim 21, wherein the converted commands include a formal language converted from natural speech.

28. The system as recited in claim 21, wherein the conversational system includes a dialog manager and a multimodal history to determine the intent of the converted commands based on a context of the commands.

29. The system as recited in claim 21, wherein the conversational system includes a mediator which employs information about at least one of the plurality of different client devices and a client device of the device preference to determine the context of the command.