Method for dialog management
View Patent ↗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.
1. A method of communicating with a user via a spoken dialog system, the method comprising:
selecting a dialog motivator from a plurality of dialog motivators based at least in part on user input, the plurality of dialog motivators including an assumption dialog motivator and a confirmation dialog motivator; and
when the spoken dialog system requests further user input and invokes the confirmation dialog motivator to confirm the further user input, the method comprises:
receiving the further user input; and
if 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 method of claim 1 , wherein the plurality of dialog motivators comprises at least an a-priori assumption dialog motivator.
3. The method of claim 1 , wherein the plurality of dialog motivators further comprises an a-posteriori assumption dialog motivator.
4. The method of claim 1 , wherein the method is processed by a dialog manager module within the spoken dialog system.
5. The method of claim 2 , wherein the a-priori assumption dialog motivator is governed by predefined rules governing call flow.
6. The method of claim 5 , wherein an a-priori assumption by the assumption dialog motivator requires the system to transfer the user to a main menu of an interactive voice response system if the system cannot classify the user as wanting a concrete call type.
7. The method of claim 5 , wherein an a-priori assumption by the a-priori assumption dialog motivator requires the system to transfer the user to a customer service representative if the system cannot classify the user as wanting a concrete call type.
8. The method of claim 5 , wherein an a-priori assumption by the a-priori assumption dialog motivator requires the system to transfer the user to an interactive voice response system if the call type is a vague call.
9. The method of claim 6 , wherein before the spoken dialog system transfers the user to the main menu, the spoken dialog system requests the user's telephone number.
10. The method of claim 7 , wherein before the spoken dialog system transfers the user to the customer service representative: the spoken dialog system requests the user's telephone number.
11. The method of claim 8 , wherein before the spoken dialog system transfers the user to the interactive voice response system the spoken dialog system requests the user's telephone number.
12. A computer readable medium storing instructions for controlling a computing device for communicating with a user via a spoken dialog, wherein the instructions comprise:
selecting a dialog motivator from a plurality of dialog motivators based at least in part on user input, the plurality of motivators including an assumption dialog motivator and a confirmation dialog motivator; and
when the computing device requests further user input and invokes the confirmation dialog motivator to confirm the further use: input, the instructions further comprise:
receiving the further user input; and
if 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 computer readable medium of claim 12 , wherein the plurality of dialog motivators comprises at least an a-priori assumption dialog motivator.
14. The computer readable medium of claim 12 , wherein the plurality of dialog motivators further comprises an a-posteriori assumption dialog motivator.
15. The computer readable medium of claim 13 , wherein the a-priori assumption dialog motivator is governed by predefined rules governing call flow.
16. The computer readable medium of claim 15 , wherein an a-priori assumption by the assumption dialog motivator requires the system to transfer the user to a main menu of an interactive voice response system if the system cannot classify the user as wanting a concrete call type.
17. The computer readable medium of claim 15 , wherein an a-priori assumption by the a-priori assumption dialog motivator require the system to transfer the user to a consumer service representative if the system cannot classify the user as wanting a concrete call type.
18. The computer readable medium of claim 15 , wherein an a-priori assumption by the a-priori assumption dialog motivator requires the system to transfer the user to an interactive voice response system if the call type is a vague call.
19. The computer readable medium of claim 16 , wherein before the computing device transfers the user to the main menu, the computing device requests the user's telephone number.