IP Library › Granted Patent US 11,676,593
Granted Patent B2
US 11,676,593 · App. 17/107,992 · Granted Jun 13, 2023

Training an artificial intelligence of a voice response system based on non_verbal feedback

Inventors: Shikhar Kwatra (San Jose, CA); Paul N. Krystek (Highland, NY); Sushain Pandit (Austin, TX); Sarbajit K. Rakshit (Kolkata, IN)
Assignee: International Business Machines Corporation
G10L15/22G10L15/063G10L15/16G10L2015/0638G10L2015/227
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,676,593
App. No.
17/107,992
Granted
Jun 13, 2023
Kind
B2
Abstract

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.

Claims (34)

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.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2020
From: KWATRA, SHIKHAR; KRYSTEK, PAUL N.; PANDIT, SUSHAIN; RAKSHIT, SARBAJIT K.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 054498/0111 →
Continuity (1)
Related Publication 20220172714A1 · Jun 2, 2022
Cited By (2)
US 12,641,178 US 12,750,443