Systems and methods for facilitating communication using an interactive communication system

Patent metadata

Field	Value
Publication number	US-9998597-B2
Application number	US-201514792137-A
Country	US
Kind code	B2
Filing date	Jul 6, 2015
Priority date	Jul 6, 2015
Publication date	Jun 12, 2018
Grant date	Jun 12, 2018

Abstract

An interactive communication system configured to conduct a call with a caller. The interactive communication system comprises at least one computer hardware processor configured to perform: obtaining a plurality of dialog chunks comprising information provided by the caller to the interactive communication system and information provided by the interactive communication system to the caller; generating, based on the plurality of dialog chunks, a respective plurality of feature sets, each of the plurality of feature sets comprising at least one feature generated using a respective dialog chunk of the plurality of dialog chunks; determining, based on the plurality of feature sets, a respective plurality of dialog chunk scores; determining, based at least in part on the plurality of dialog chunk scores, a likelihood that the caller is dissatisfied with the interactive communication system; and when the likelihood exceeds a threshold, performing a remedial action that alters how the call is handled.

First claim

What is claimed is:

1. A method for conducting a call between a caller and an interactive communication system, the method comprising:
using at least one computer hardware processor to perform:
obtaining a plurality of dialog chunks comprising both information provided by the caller to the interactive communication system and information provided by the interactive communication system to the caller;
generating, based on the plurality of dialog chunks including both the information provided by the caller to the interactive communication system and the information provided by the interactive communication system to the caller, a respective plurality of feature sets, each of the plurality of feature sets comprising at least one feature generated using a respective dialog chunk of the plurality of dialog chunks;
determining, based on the plurality of feature sets, a respective plurality of dialog chunk scores;
determining, based at least in part on the plurality of dialog chunk scores, a likelihood that the caller is dissatisfied with the interactive communication system; and
when the likelihood exceeds a threshold, performing a remedial action that alters a manner in which the call is handled.

2. The method of claim 1 , wherein performing the remedial action comprises transferring the call to a human operator.

3. The method of claim 1 , wherein performing the remedial action comprises changing a dialog plan according to which the interactive communication system interacts with the caller during the call.

4. The method of claim 1 , wherein the plurality of feature sets includes a first feature set generated based on a first dialog chunk in the plurality of dialog chunks, the first feature set comprising a feature selected from the group consisting of: a feature indicating how well the information provided by the caller in the first dialog chunk matches input that the interactive communication system expected the caller would provide, a feature indicating that the caller requested assistance from a human operator, a feature indicating that the caller expressed dissatisfaction, a feature indicating a confidence in results of performing automated speech recognition on input provided by the caller, and a feature indicating an internal state of the interactive communication system.

5. The method of claim 1 , wherein determining the likelihood that the caller is dissatisfied with the interactive communication system comprises:
determining, based at least in part on the plurality of feature sets, a plurality of respective weights for scores in the plurality of dialog chunk scores; and
calculating the likelihood as a weighted linear combination of dialog chunk scores in which the dialog chunk scores are weighted by weights in the plurality of weights.

6. The method of claim 5 , wherein determining the plurality of respective weights is performed using a first neural network.

7. The method of claim 6 , wherein determining the plurality of dialog chunk scores is performed using a second neural network different from the first neural network.

8. An interactive communication system configured to conduct a call with a caller, the interactive communication system comprising:
at least one computer hardware processor configured to perform:
obtaining a plurality of dialog chunks comprising both information provided by the caller to the interactive communication system and information provided by the interactive communication system to the caller;
generating, based on the plurality of dialog chunks including both the information provided by the caller to the interactive communication system and the information provided by the interactive communication system to the caller, a respective plurality of feature sets, each of the plurality of feature sets comprising at least one feature generated using a respective dialog chunk of the plurality of dialog chunks;
determining, based on the plurality of feature sets, a respective plurality of dialog chunk scores;
determining, based at least in part on the plurality of dialog chunk scores, a likelihood that the caller is dissatisfied with the interactive communication system; and
when the likelihood exceeds a threshold, performing a remedial action that alters a manner in which the call is handled.

9. The interactive communication system of claim 8 , wherein performing the remedial action comprises transferring the call to a human operator and/or changing a dialog plan according to which the interactive communication system interacts with the caller during the call.

10. The interactive communication system of claim 8 , wherein the plurality of feature sets includes a first feature set generated based on a first dialog chunk in the plurality of dialog chunks, the first feature set comprising a feature selected from the group consisting of: a feature indicating how well the information provided by the caller in the first dialog chunk matches input that the interactive communication system expected the caller would provide, a feature indicating that the caller requested assistance from a human operator, a feature indicating that the caller expressed dissatisfaction, a feature indicating a confidence in results of performing automated speech recognition on input provided by the caller, and a feature indicating an internal state of the ICS system.

11. The interactive communication system of claim 8 , wherein determining the likelihood that the caller is dissatisfied with the interactive communication system comprises:
determining, based at least in part on the plurality of feature sets, a plurality of respective weights for scores in the plurality of dialog chunk scores; and
calculating the likelihood as a weighted linear combination of dialog chunk scores in which the dialog chunk scores are weighted by weights in the plurality of weights.

12. The interactive communication system of claim 11 , wherein determining the plurality of respective weights is performed using a first neural network.

13. The interactive communication system of claim 12 , wherein determining the plurality of dialog chunk scores is performed using a second neural network different from the first neural network.

14. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method for conducting a call between a caller and an interactive communication system, the method comprising:
obtaining a plurality of dialog chunks comprising both information provided by the caller to the interactive communication system and information provided by the interactive communication system to the caller;
generating, based on the plurality of dialog chunks including both the information provided by the caller to the interactive communication system and the information provided by the interactive communication system to the caller, a respective plurality of feature sets, each of the plurality of feature sets comprising at least one feature generated using a respective dialog chunk of the plurality of dialog chunks;
determining, based on the plurality of feature sets, a respective plurality of dialog chunk scores;
determining, based at least in part on the plurality of dialog chunk scores, a likelihood that the caller is dissatisfied with the interactive communication system; and
when the likelihood exceeds a threshold, performing a remedial action that alters a manner in which the call is handled.

15. The at least one non-transitory computer readable storage mediu

Assignees

• Nuance Communications Inc

Inventors

• Havelka Jiri
• Bakis Raimo

Classifications

• H04M3/5166 Primary

  in combination with interactive voice response systems or voice portals, e.g. as front-ends · CPC title

• H04M2203/2038

  Call context notifications · CPC title

• H04M3/5175

  Call or contact centers supervision arrangements · CPC title

• G06F40/30

  Semantic analysis · CPC title

• H04M2201/40

  using speech recognition · CPC title