Method for dialog management

• US 8,600,747 B2
• Filed: 06/17/2008
• Issued: 12/03/2013
• Est. Priority Date: 10/15/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Abella, Alicia, Gorin, Allen Louis
• Primary Examiner(s): Guerra-Erazo, Edgar
• Assistant Examiner(s): Sharma, Neeraj
• Application Number:
  US12/140,805
• Publication Number:
  US 20080247519A1
• Time in Patent Office: 1,995 Days
• Field of Search: 704/239, 704/275, 704/9, 704/251, 704/254, 704/235, 704/277, 715/811, 379/88.03, 379/88.04, 379/88.14, 718/102, 706/11, 717/100
• US Class Current: 704/239
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A spoken dialog system and method having a dialog management module are disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise an error handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input.

Claims

1. A system comprising:

a processor; and

a computer-readable storage device having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

selecting a task-specific dialog motivator from a plurality of non-domain specific dialog motivators, wherein;

the plurality of non-domain specific dialog motivators are not associated with any domain;

each non-domain specific dialog motivator in the plurality of non-domain specific dialog motivators determines what action a dialog manager needs to take in conducting a dialog with a user using rules that act on instances of task knowledge;

the plurality of non-domain specific dialog motivators comprise an assumption dialog motivator and a confirmation dialog motivator; and

the task-specific dialog motivator is selected based on a comparison of user input to characteristics of each non-domain specific dialog motivator in the plurality of non-domain specific dialog motivators; and

upon a spoken dialog system requesting further user input and invoking the confirmation dialog motivator to confirm the further user input;

receiving the further user input; and

when a confidence value associated with understanding the further user input is below a threshold value, invoking the assumption dialog motivator to present assumed further user input during a confirmation dialog.

2. The system of claim 1, wherein the plurality of non-domain specific dialog motivators further comprises a previously encoded assumption dialog motivator.

3. The system of claim 1, wherein the plurality of non-domain specific dialog motivators further comprises an acquired information assumption dialog motivator.

4. The system of claim 2, wherein the previously encoded assumption dialog motivator is governed by predefined rules governing call flow.

5. The system of claim 4, wherein an previously encoded assumption by the previously encoded assumption dialog motivator triggers a transfer of the user to a main menu of an interactive voice response system when the user is not classified as wanting a concrete call type.

6. The system of claim 4, wherein a previously encoded assumption by the previously encoded assumption dialog motivator triggers transferring the user to a customer service representative when the user is not classified as wanting a concrete call type.

7. The system of claim 4, wherein a previously encoded assumption by the previously encoded assumption dialog motivator triggers transferring the user to an interactive voice response system when the call type is classified as a vague call.

8. The system of claim 5, wherein before the spoken dialog service transfers the user to the main menu, the spoken dialog service requests the user'"'"'s telephone number.

9. The system of claim 6, the computer-readable storage device having additional instructions stored which result in the operations further comprising, before transferring the user to the customer service representative, requesting a telephone number from the user.

10. The system of claim 7, the computer-readable storage device having additional instructions stored which result in the operations further comprising, before transferring the user to the interactive voice response system, requesting a telephone number from the user.

11. The system of claim 1, wherein the spoken dialog system further comprises a dialog manager.

12. A method comprising:

selecting, using a processor, a task-specific dialog motivator from a plurality of non-domain specific dialog motivators, wherein;

the plurality of non-domain specific dialog motivators are not associated with any domain;

each non-domain specific dialog motivator in the plurality of non-domain specific dialog motivators determines what action a dialog manager needs to take in conducting a dialog with a user using rules that act on instances of task knowledge;

the plurality of non-domain specific dialog motivators comprise an assumption dialog motivator and a confirmation dialog motivator; and

the task-specific dialog motivator is selected based on a comparison of user input to characteristics of each non-domain specific dialog motivator in the plurality of non-domain specific dialog motivators; and

upon a spoken dialog system requesting further user input and invoking the confirmation dialog motivator to confirm the further user input;

receiving the further user input; and

when a confidence value associated with understanding the further user input is below a threshold value, invoking the assumption dialog motivator to present assumed further user input during a confirmation dialog.

13. The method of claim 12, wherein the plurality of non-domain specific dialog motivators further comprise a previously encoded assumption dialog motivator.

14. The method of claim 12, wherein the plurality of non-domain specific dialog motivators further comprise an acquired information assumption dialog motivator.

15. The method of claim 13, wherein the previously encoded assumption dialog motivator is governed by predefined rules governing call flow.

16. The method of claim 15, wherein a previously encoded assumption by the previously encoded assumption dialog motivator triggers a transfer of the user to a main menu of an interactive voice response system when the user is not classified as wanting a concrete call type.

17. The method of claim 16, wherein a previously encoded assumption by the previously encoded assumption dialog motivator triggers transferring the user to a customer service representative when the user is not classified as wanting a concrete call type.

18. The method of claim 16, wherein a previously encoded assumption by the previously encoded assumption dialog motivator triggers transferring the user to an interactive voice response system when the call type is classified as a vague call.

19. The method of claim 16, wherein before the spoken dialog service transfers the user to the main menu, the spoken dialog service requests the user'"'"'s telephone number.

20. The method of claim 17, the method further comprising, before transferring the user to the customer service representative, requesting a telephone number from the user.