Contextual justification for a virtual assistant response

Patent metadata

Field	Value
Publication number	US-11798532-B2
Application number	US-202117340379-A
Country	US
Kind code	B2
Filing date	Jun 7, 2021
Priority date	Jun 7, 2021
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

In an approach to providing contextual justification for a virtual assistant response, one or more computer processors receive a first voice command from a user. One or more computer processors determine one or more boundary conditions associated with the first voice command. Based on the one or more boundary conditions, one or more computer processors determine a first response to the first voice command and a contextual justification of the first response. One or more computer processors respond to the user with the response to the first voice command and the contextual justification of the response.

First claim

What is claimed is:

1. A computer-implemented method comprising:
tracking, by one or more computer processors, one or more activities associated with a user over time;
determining, by one or more computer processors, one or more patterns in the one or more activities associated with the user;
receiving, by one or more computer processors, a first voice command from the user;
based on the one or more patterns, predicting, by one or more computer processors, one or more boundary conditions associated with the first voice command and the one or more activities;
based on the one or more boundary conditions, determining, by one or more computer processors, a first response to the first voice command and a contextual justification of the first response, wherein the contextual justification is an explanation of a reasoning behind the first response; and
responding, by one or more computer processors, to the user with the response to the first voice command and the contextual justification of the response.

2. The computer-implemented method of claim 1 , further comprising:
receiving, by one or more computer processors, from the user, a second response associated with the first response to the voice command and the contextual justification of the first response; and
determining, by one or more computer processors, the second response includes at least one of a second voice command or an additional boundary condition.

3. The computer-implemented method of claim 1 , further comprising:
storing, by one or more computer processor, the first voice command, the one or more boundary conditions, the first response to the first voice command, and the contextual justification of the first response in a knowledge corpus.

4. The computer-implemented method of claim 1 , wherein determining the one or more boundary conditions further comprises at least one of:
extracting, by one or more computer processors, at least one of the one or more boundary conditions from the first voice command;
communicating, by one or more computer processors, with one or more data sources associated with the user; and
extracting, by one or more computer processors, data from one or more computing devices associated with the user.

5. The computer-implemented method of claim 4 , wherein the one or more data sources include at least one of: a calendar application, an email application, a social media application, and a global positioning system (GPS).

6. The computer-implemented method of claim 1 , wherein determining the one or more boundary conditions further comprises at least one of:
identifying, by one or more computer processors, one or more pending opportunities associated with the user;
identifying, by one or more computer processors, one or more pending activities of the user; and
identifying, by one or more computer processors, an activity history which indicates a preference of the user.

7. The computer-implemented method of claim 1 , further comprising:
determining, by one or more computer processors, a sentiment of the user associated with the first voice command, wherein determining the sentiment of the user is accomplished using one or more natural language processing (NLP) techniques; and
customizing, by one or more computer processors, the first response to the first voice command and the contextual justification of the first response based on the sentiment.

8. A computer program product comprising:
one or more computer readable storage devices and program instructions collectively stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to track one or more activities associated with a user over time;
program instructions to determine one or more patterns in one or more activities associated with the user;
program instructions to receive a first voice command from the user;
based on the one or more patterns, program instructions to predict one or more boundary conditions associated with the first voice command and the one or more activities;
based on the one or more boundary conditions, program instructions to determine a first response to the first voice command and a contextual justification of the first response, wherein the contextual justification is an explanation of a reasoning behind the first response; and
program instructions to respond to the user with the response to the first voice command and the contextual justification of the response.

9. The computer program product of claim 8 , the stored program instructions further comprising:
program instructions to receive, from the user, a second response associated with the first response to the voice command and the contextual justification of the first response; and
program instructions to determine the second response includes at least one of a second voice command or an additional boundary condition.

10. The computer program product of claim 8 , the stored program instructions further comprising:
program instructions to store the first voice command, the one or more boundary conditions, the first response to the first voice command, and the contextual justification of the first response in a knowledge corpus.

11. The computer program product of claim 8 , wherein the program instructions to determine the one or more boundary conditions comprise at least one of:
program instructions to extract at least one of the one or more boundary conditions from the first voice command;
program instructions to communicate with one or more data sources associated with the user; and
program instructions to extract data from one or more computing devices associated with the user.

12. The computer program product of claim 11 , wherein the one or more data sources include at least one of: a calendar application, an email application, a social media application, and a global positioning system (GPS).

13. The computer program product of claim 8 , wherein the program instructions to determine the one or more boundary conditions comprise at least one of:
program instructions to identify one or more pending opportunities associated with the user;
program instructions to identify one or more pending activities of the user; and
program instructions to identify an activity history which indicates a preference of the user.

14. The computer program product of claim 8 , the stored program instructions further comprising:
program instructions to determine a sentiment of the user associated with the first voice command, wherein determining the sentiment of the user is accomplished using one or more natural language processing (NLP) techniques; and
program instructions to customize the first response to the first voice command and the contextual justification of the first response based on the sentiment.

15. A computer system comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions collectively stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to track one or more activities associated with a user over time;
program instructions to determine one or more patterns in one or more activities associated with the user;
program instructions to receive a first voice command from the user;
based on the one or more patterns, program instructions to predict one or more boundary conditions associated with the first voice command and the one or more activities;
based on the one or more boundary conditions,

Assignees

• IBM

Inventors

• Decrop Clement
• Agrawal Tushar
• Fox Jeremy R
• Rakshit Sarbajit K
• Nagar Raghuveer Prasad
• Hulugundi Jagadesh Ramaswamy

Classifications

• G10L15/02 Primary

  Feature extraction for speech recognition; Selection of recognition unit · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G10L15/183

  using context dependencies, e.g. language models · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title