Open architecture for a voice user interface

• US 7,496,516 B2
• Filed: 01/27/2006
• Issued: 02/24/2009
• Est. Priority Date: 12/08/2000
• Status: Expired due to Term

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Ben Franklin Patent Holding LLC (Intellectual Ventures LLC)
• Inventors: Oshima, Mitsuru, Lange, Daniel, Ponomarenko, Eugene, Burkes, Daniel, Tessel, Marianna, Tjong, Tjoen Min
• Primary Examiner(s): McFadden; Susan
• Application Number:
  US11/340,844
• Publication Number:
  US 20060190269A1
• Time in Patent Office: 1,124 Days
• Field of Search: 704/275, 704/270, 379/88.01
• 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 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A system and method for processing voice requests from a user for accessing information on a computerized network and delivering information from a script server and an audio server in the network in audio format. A voice user interface subsystem includes: a dialog engine that is operable to interpret requests from users from the user input, communicate the requests to the script server and the audio server, and receive information from the script server and the audio server; a media telephony services (MTS) server, wherein the MTS server is operable to receive user input via a telephony system, and to transfer the user input to the dialog engine; and a broker coupled between the dialog engine and the MTS server. The broker establishes a session between the MTS server and the dialog engine and controls telephony functions with the telephony system.

Claims

1. A method of processing requests for information from a network, the method comprising:

receiving user input and information regarding a user from a communications subsystem;

recognizing a voice command in the user input;

requesting a dialog engine from a broker, wherein the broker is operable to distribute the processing load across a plurality of dialog engines;

transmitting the recognized command to the dialog engine;

retrieving information requested by the recognized command from the network via the dialog engine;

converting the information from text to speech format when the retrieved information is in text format; and

outputting the retrieved information to the user.

2. The method of claim 1, wherein receiving user input and information regarding the user includes:

receiving user input and information regarding the user via a voice communications interface.

3. The method of claim 1, wherein receiving user input and information regarding the user request includes:

receiving user input and information regarding the user request via a data communications interface.

4. The method of claim 1, further comprising:

instantiating a session object in response to the recognized command, wherein the session object creates a channel.

5. The method of claim 4, further comprising:

allocating a client for the session object.

6. The method of claim 1, wherein the retrieved information is in the form of a markup language document.

7. The method of claim 1, further comprising:

instantiating a session object in response to the recognized command, wherein the session object performs one or more functions in the group of functions including;

placing a second call;

canceling a call;

dropping one or more calls in the session;

transferring a call;

appending the prompt;

playing accumulated prompts; and

initiating voice recognition.

8. The method of claim 1, further comprising:

engaging in a dialog with the user, including;

receiving input from the user,

producing a voice markup language script in response to the user input, and

executing the voice markup language script to generate an output for provision to the user.

9. The method of claim 8, wherein executing the voice markup language script comprises:

interpreting the voice markup language script to produce an audio output.

10. The method of claim 8, wherein engaging in a dialog with the user further comprises:

receiving a second user input when an output based on the executed voice markup language script is being provided to the user;

interrupting the output being provided to the user; and

processing the second user input.

11. The method of claim 8, wherein executing the voice markup language script comprises:

transmitting a prompt to a media service provider module to play the voice markup language script; and

placing the prompt in an output queue at the media service provider module.

12. The method of claim 11, wherein executing the voice markup language script comprises:

transmitting an append prompt request to the media service provider module to add a second prompt to the output queue.

13. The method of claim 9, wherein executing the voice markup language script comprises:

identifying text requiring conversion to speech; and

placing a text-to-speech request in the output queue.

14. A computer program product comprising a computer usable storage medium including computer program logic stored therein that, when executed by a processor, causes the processor to perform a method comprising:

receiving user input and information regarding a user from a communications subsystem;

recognizing a voice command in the user input;

requesting a dialog engine from a broker, wherein the broker is operable to distribute the processing load across a plurality of dialog engines;

transmitting the recognized command to the dialog engine;

retrieving information requested by the recognized command from a network via the dialog engine;

converting the information from text to speech format when the retrieved information is in text format; and

outputting the retrieved information to the user.

15. The computer program product of claim 14, wherein

the receiving user input and information regarding the user comprises:

receiving user input and information regarding the user via a voice communications interface.

16. The computer program product of claim 14, wherein the receiving user input and information regarding the user request comprises:

receiving the user input and information regarding the user request via a data communications interface.

17. The computer program product of claim 14, wherein the method further comprises:

instantiating a session object in response to the recognized command, wherein the session object creates a channel.

18. The computer program product of claim 17, wherein the method further comprises:

allocating a client for the session object.

19. The computer program product of claim 14, wherein the retrieved information is in the form of a markup language document.

20. The computer program product of claim 14, wherein the method further comprises:

instantiating a session object in response to the recognized command, wherein the session object performs one or more functions in the group of functions including;

placing a second call;

canceling a call;

dropping one or more calls in the session;

transferring a call;

appending the prompt;

playing accumulated prompts; and

initiating voice recognition.

21. The computer program product of claim 14, wherein the method further comprises:

engaging in a dialog with the user, including;

receiving input from the user,

producing a voice markup language script in response to the input, and

executing the voice markup language script to generate an output for provision to the user.

22. The computer program product of claim 21, wherein

executing the voice markup language script comprises:

interpreting the voice markup language script to produce an audio output.

23. The computer program product of claim 21, wherein

engaging in a dialog with the user further comprises:

receiving a second user input when an output based on the executed voice markup language script is being provided to the user;

interrupting the output being provided to the user; and

processing the second user input.

24. The computer program product of claim 21, wherein executing the voice markup language script comprises:

transmitting a prompt to a media service provider module to play the voice markup language script; and

placing the prompt in an output queue at the media service provider module.

25. The computer program product of claim 21, wherein executing the voice markup language script comprises:

transmitting an append prompt request to the media service provider module to add a second prompt to the output queue.

26. The computer program product of claim 22, wherein

executing the voice markup language script comprises:

identifying text requiring conversion to speech; and

placing a text-to-speech request in the output queue.

27. A system for processing requests for information from a network, the system comprising:

a media service provider module for;

receiving user input and information regarding a user from a communications subsystem,

recognizing a voice command in the user input, and

requesting a dialog engine from a broker;

a broker for;

distributing the processing load across a plurality of dialog engines, and transmitting the recognized command to a dialog engine; and

a dialog engine for;

retrieving information requested by the recognized command from the network, and

converting the information from text to speech format when the retrieved information is in text format;

wherein the media service provider is configured to output the retrieved information to the user.

28. The system of claim 27, wherein the dialog engine is further for:

receiving user input and information regarding the user via a voice communications interface.

29. The system of claim 27, wherein the dialog engine is further for:

receiving user input and information regarding the user request via a data communications interface.

30. The system of claim 27, wherein the broker is further for:

instantiating a session object in response to the recognized command, wherein the session object creates a channel.

31. The system of claim 30, wherein the broker is further for:

allocating a client for the session object.

32. The system of claim 27, wherein the retrieved information is in the form of a markup language document.

33. The system of claim 27, wherein the dialog engine is further for:

instantiating a session object in response to the recognized command, wherein the session object performs one or more functions in the group of functions including;

placing a second call;

canceling a call;

dropping one or more calls in the session;

transferring a call;

appending the prompt;

playing accumulated prompts; and

initiating voice recognition.

34. The system of claim 27, wherein the dialog engine is further for:

engaging in a dialog with the user including;

receiving input from the user,

producing a voice markup language script in response to the input, and

executing the voice markup language script to generate an output for provision to the user.

35. The system of claim 34, wherein the dialog engine is further for:

interpreting the voice markup language script to produce an audio output.

36. The system of claim 34, wherein the dialog engine is further for:

receiving a second user input when an output based on the executed voice markup language script is being provided to the user;

interrupting the output being provided to the user; and

processing the second user input.

37. The method of claim 34, wherein the dialog engine is further for:

transmitting a prompt to a media service provider module to play the voice markup language script; and

placing the prompt in an output queue at the media service provider module.

38. The method of claim 34, wherein the dialog engine is further for:

transmitting an append prompt request to the media service provider module to add a second prompt to the output queue.

39. The method of claim 35, wherein the dialog engine is further for:

identifying text requiring conversion to speech; and

placing a text-to-speech request in the output queue.

40. A method of requesting information from a network comprising:

providing user input to a system operable to perform a set of operations comprising;

recognizing a voice command in the user input;

requesting a dialog engine from a broker operable to distribute the processing load across a plurality of dialog engines;

transmitting the recognized command to the dialog engine;

retrieving information requested by the recognized command from the network via the dialog engine; and

converting the information from text to speech format when the retrieved information is in text format; and

receiving the information from the system.

41. A system for processing requests for information from a network comprising:

media service provider means for;

receiving user input and information regarding a user from a communications subsystem,

recognizing a voice command in the user input, and

requesting a dialog engine from a broker;

a broker for;

distributing the processing load across a plurality of dialog engines, and

transmitting the recognized command to a dialog engine; and

dialog engine means for;

retrieving information requested by the recognized command from the network, and

converting the information from text to speech format when the retrieved information is in text format;

wherein the media service provider means is further for outputting the retrieved information to the user.