System and method for applying probability distribution models to dialog systems in the troubleshooting domain

1. A method for troubleshooting based on a probability distribution model, the method comprising:

establishing a speech-based conversation with a user;

establishing at least one non-speech-based channel of interaction for obtaining behavioral information associated with a product during the speech-based conversation;

for each of a plurality of component variables, maintaining via a processor a probability distribution for a state of the product based on a state of the speech-based conversation over time and a state of the behavioral information over time; and

troubleshooting the product by responding based on the probability distribution.

2. The method of claim 1 , wherein the at least one non-speech-based channel of interaction includes automated responses from the product to troubleshoot.

3. The method of claim 1 , wherein the at least one non-speech-based channel of interaction includes observing behavior of the product to troubleshoot.

4. The method of claim 1 , wherein the at least one of speech-based conversation and the at least one non-speech-based channel of interaction are established over at least one of a telephone network, a local area network, Internet, and other communications network.

5. The method of claim 1 , wherein Bayesian Networks are used to maintain the probability distribution.

6. The method of claim 1 , wherein partially observable Markov decision processes (POMDPs) are used to select troubleshooting responses.

7. The method of claim 1 , wherein troubleshooting is performed on at least one of a DSL modem, software applications, television, video game console, digital video recorder, computer or components of a computer, cellular phone or other communications device, household appliances, and web page.

8. A system for troubleshooting based on a probability distribution model, the system comprising:

a processor;

a first module configured to control the processor to establish a speech-based conversation with the user;

a second module configured to control the processor to establish at least one non-speech-based channel of interaction for obtaining behavioral information associated with the product during the speech-based conversation;

a third module configured to control the processor to maintain a probability distribution over time for each of a plurality of component variables describing a state of the product based on a state of a conversation over time and a state of the behavioral information over time; and

a fourth module configured to control the processor to troubleshoot the product by responding based on the probability distribution.

9. The system of claim 8 , wherein the at least one non-speech-based channel of interaction includes automated responses from the product to troubleshoot.

10. The system of claim 8 , wherein the at least one non-speech-based channel of interaction includes observing behavior of the product to troubleshoot.

11. The system of claim 8 , wherein at least one of the speech-based conversation and the at least one non-speech-based channel of interaction are established over one of a telephone network, a local area network, Internet, and other communications network.

12. The system of claim 8 , wherein Bayesian Networks are used to maintain the probability distribution.

13. The system of claim 8 , wherein partially observable Markov decision processes (POMDPs) are used to select troubleshooting responses.

14. The system of claim 8 , wherein troubleshooting is performed on at least one of a DSL modem, software applications, television, video game console, digital video recorder, computer or components of a computer, cellular phone or other communications device, household appliances, and web page.

15. A non-transitory computer-readable medium storing a computer program having instructions for troubleshooting based on a probability distribution model, the instructions comprising:

establishing a speech-based conversation with a user;

establishing at least one non-speech-based channel of interaction for obtaining behavioral information associated with the product or service during the sub-based conversation;

for each of a plurality of component variables describing the current state of the product, maintaining a probability distribution over time based on a state of the sub-based conversation over time and a state of the behavioral information over time; and

troubleshooting product by responding based on the probability distribution.

16. The non-transitory computer-readable medium of claim 15 , wherein the at least one non-speech-based channel of interaction includes automated responses from the product to troubleshoot.

17. The non-transitory computer-readable medium of claim 15 , wherein the at least one non-speech-based channel of interaction includes observing behavior of the product to troubleshoot.

18. The non-transitory computer-readable medium of claim 15 , wherein at least one of the speech-based conversation and the at least one non-speech-based channel of interaction are established over one of a telephone network, a local area network, Internet, and other communications network.

19. The non-transitory computer-readable medium of claim 15 , wherein Bayesian Networks are used to maintain the probability distribution.

20. The non-transitory computer-readable medium of claim 15 , wherein partially observable Markov decision processes (POMDPs) are used to select troubleshooting actions.

21. The non-transitory computer-readable medium of claim 15 , wherein troubleshooting is performed on at least one of a DSL modem, software applications, television, video game console, digital video recorder, computer or components of a computer, cellular phone or other communications device, household appliances, and web page.