AUTOMATED SENTENCE PLANNING IN A TASK CLASSIFICATION SYSTEM

• US 20100241420A1
• Filed: 05/28/2010
• Published: 09/23/2010
• Est. Priority Date: 03/14/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Walker, Marilyn A., Rambow, Owen Christopher, Rogati, Monica
• Granted Patent: US 8,185,401 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08

Abstract

The invention relates to a system that interacts with a user in an automated dialog system (100). The system may include a communicative goal generator (210) that generates communicative goals based on a first communication received from the user. The generated communicative goals (210) may be related to information needed to be obtained from the user. The system may further include a sentence planning unit (220) that automatically plans one or more sentences based on the communicative goals generated by the communicative goal generator (210). At least one of the planned sentences may be then output to the user (230).

Claims

1. A method of managing a dialog with a user, the method comprising:

generating communicative goals based on a communication received from the user, the communicative goals being related to further information needed from the user in addition to information in the communication;

generating a plurality of appropriate prompts to the communication from the user based on the communicative goals;

ranking the plurality of appropriate prompts independent of the user; and

outputting to the user an output prompt based on the ranking of the plurality of appropriate prompts.

2. The method of claim 1, wherein the output prompt is chosen from the plurality of appropriate prompts.

3. The method of claim 1, further comprising:

applying a set of linguistic rules to the output appropriate prompt.

4. The method of claim 1, wherein ranking the plurality of appropriate prompts is performed using a set of learned rules in a training database.

5. The method of claim 1, wherein generating the plurality of appropriate prompts is performed using interaction information in a discourse history database that comprises the interaction information, the interaction information being related to a set of interactions between the user and the automated dialog system.

6. The method of claim 1, wherein the communication comprises a nonverbal communication.

7. The method of claim 6, wherein the nonverbal communication comprises at least one of a gesture, a body movement, a head movement, a non-response, text, a keyboard entry, a keypad entry, a mouse click, a DTMF code, a pointer, a stylus, a cable set-top box entry, a graphical user interface entry, and a touchscreen entry.

8. The method of claim 1, wherein generating the communicative goals further comprises confirming information previously obtained from the user.

9. The method of claim 1, further comprising:

converting at least one of the ranked appropriate prompts from text to speech.

10. The method of claim 1, wherein the method is processed in one of a customer care system, a reservation system, a parts ordering system, a navigation system, an information gathering system, and an information retrieval system.

11. A system of managing a dialog with a user, the system comprising:

a processor;

a first module controlling the processor to generate communicative goals based on a communication received from the user, the communicative goals being related to further information needed from the user in addition to information in the communication;

a second module controlling the processor to generate a plurality of appropriate prompts to the communication from the user based on the communicative goals;

a third module controlling the processor to rank the plurality of appropriate prompts independent of the user; and

a fourth module controlling the processor to output to the user an output prompt based on the ranking of the plurality of appropriate prompts.

12. The system of claim 11, wherein the fourth module outputs the output prompt based on the plurality of appropriate prompts.

13. The system of claim 11, further comprising a fifth module controlling the processor to apply a set of linguistic rules to the output prompt.

14. The system of claim 11, wherein the third module ranks the plurality of appropriate prompts by using a set of learned rules in a training database.

15. The system of claim 11, wherein the second module generates the plurality of appropriate prompts by using interaction information in a discourse history database that comprises the interaction information, the interaction information being related to a set of interactions between the user and the automated dialog system.

16. The system of claim 11, wherein the communication comprises a nonverbal communication.

17. The system of claim 16, wherein the nonverbal communication comprises at least one of a gesture, a body movement, a head movement, a non-response, text, a keyboard entry, a keypad entry, a mouse click, a DTMF code, a pointer, a stylus, a cable set-top box entry, a graphical user interface entry, and a touchscreen entry.

18. The system of claim 11, wherein the first module further controls the processor to confirm information previously obtained from the user.

19. The system of claim 11, further comprising a fifth module controlling the processor to convert at least one of the ranked appropriate prompts from text to speech.

20. The system of claim 11, wherein the system comprises at least one of a customer care system, a reservation system, a parts ordering system, a navigation system, an information gathering system, and an information retrieval system.

21. A non-transitory computer-readable storage medium storing instructions, which causes a device to manage a dialog with a user, the instructions comprising:

generating via a processor communicative goals based on a communication received from the user, the communicative goals being related to further information needed from the user in addition to information in the communication;

generating via the processor a plurality of appropriate prompts to the communication from the user based on the communicative goals;

ranking via the processor the plurality of appropriate prompts independent of the user; and

outputting to the user via the processor an output prompt based on the ranking of the plurality of appropriate prompts.

22. The non-transitory computer-readable storage medium of claim 21, wherein the output prompt is chosen from the plurality of appropriate prompts.