Training an artificial intelligence of a voice response system based on non_verbal feedback
Methods, systems, and computer program products for training an artificial intelligence (AI) of a voice response system. Aspects include receiving, by the voice response system from a user, a voice command to perform a requested action and interpreting, by an AI model, the voice command. Aspects also include performing an action based on the interpretation of the voice command and receiving non-verbal feedback from the user. Aspects further include updating the AI model based on a determination that the non-verbal feedback indicates that the user is not satisfied with the action performed.
1. A method for training an artificial intelligence (AI) of a voice response system, the method comprising:
receiving, by a microphone of the voice response system directly from a user, a voice command to perform a requested action;
interpreting, by an AI model, the voice command;
performing an action based on the interpretation of the voice command;
receiving a non-verbal feedback from the user during a threshold time after the action is performed, wherein the non-verbal feedback includes a physical reaction of the user; and
updating the AI model based on a determination that the non-verbal feedback indicates that the user is not satisfied with the action performed,
wherein determination that the non-verbal feedback indicates that the user is not satisfied with the action performed is based on the physical reaction of the user including a change in biometric data gathered from a wearable device of the user.
2. The method of claim 1 , wherein the non-verbal feedback is provided by the user in response to a request from the voice response system for the user to type the voice command.
3. The method of claim 1 , further comprising monitoring a behavior of the user within the threshold time after the action is performed.
4. The method of claim 1 , further comprising creating a correlation among a determined change in behavior of the user within a threshold time after the action is performed and the interpreted voice command to identify a portion of the voice command that is being wrongly interpreted.
5. The method of claim 4 , further comprising comparing the portion of the voice command that is being wrongly interpreted to data from other users to identify a best AI model for the user.
6. A system for training an artificial intelligence (AI) of a voice response system, the system comprising:
a memory having computer-readable instructions; and
a processor for executing the computer-readable instructions, the computer-readable instructions including instructions for:
receiving, by a microphone of the voice response system directly from a user, a voice command to perform a requested action;
interpreting, by an AI model, the voice command;
performing an action based on the interpretation of the voice command;
receiving a non-verbal feedback from the user during a threshold time after the action is performed, wherein the non-verbal feedback includes a physical reaction of the user; and
updating the AI model based on a determination that the non-verbal feedback indicates that the user is not satisfied with the action performed,
wherein determination that the non-verbal feedback indicates that the user is not satisfied with the action performed is based on the physical reaction of the user including a change in biometric data gathered from a wearable device of the user.
7. The system of claim 6 , wherein the non-verbal feedback is provided by the user in response to a request from the voice response system for the user to type the voice command.
8. The system of claim 6 , wherein the computer-readable instructions further include instructions for comprising monitoring a behavior of the user within the threshold time after the action is performed.
9. The system of claim 6 , wherein the computer-readable instructions further include instructions for creating a correlation among a determined change in behavior of the user within a threshold time after the action is performed and the interpreted voice command to identify a portion of the voice command that is being wrongly interpreted.
10. The system of claim 9 , wherein the computer-readable instructions further include instructions for comparing the portion of the voice command that is being wrongly interpreted to data from other users to identify a best AI model for the user.
11. A computer program product comprising a computer-readable storage medium having program instructions embodied therewith the program instructions executable by a computer processor to cause the computer processor to perform a method, comprising:
receiving, by a microphone of a voice response system directly from a user, a voice command to perform a requested action;
interpreting, by an AI model, the voice command;
performing an action based on the interpretation of the voice command;
receiving a non-verbal feedback from the user during a threshold time after the action is performed, wherein the non-verbal feedback includes a physical reaction of the user; and
updating the AI model based on a determination that the non-verbal feedback indicates that the user is not satisfied with the action performed,
wherein determination that the non-verbal feedback indicates that the user is not satisfied with the action performed is based on the physical reaction of the user including a change in biometric data gathered from a wearable device of the user.
12. The computer program product of claim 11 , wherein the non-verbal feedback is provided by the user in response to a request for the user to type the voice command.
13. The computer program product of claim 11 , wherein the method further comprises monitoring a behavior of the user within the threshold time after the action is performed.
14. The computer program product of claim 11 , wherein the method further comprises creating a correlation among a determined change in behavior of the user within a threshold time after the action is performed and the interpreted voice command to identify a portion of the voice command that is being wrongly interpreted.