Automated technical content conversion based on user understanding level

Patent metadata

Field	Value
Publication number	US-11227230-B2
Application number	US-201715462097-A
Country	US
Kind code	B2
Filing date	Mar 17, 2017
Priority date	Mar 17, 2017
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

Mechanisms are provided for modifying response of cognitive systems to user requests based on a determined knowledge level of the user and knowledge level of the concepts referenced in the cognitive system responses. The mechanisms receive a response to a user submitted request received from a client computing system and determine a first knowledge level of the user for a domain of the user submitted request. The mechanisms determine a second knowledge level associated with concepts referenced in the response and whether the first knowledge level is different from the second knowledge level. The mechanism, in response to the first knowledge level being different than the second knowledge level, modify content of the response to include concepts associated with the first knowledge level, to thereby generate a modified response. The modified response is then output to the client computing system associated with the user.

First claim

What is claimed is:

1. A method, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to configure the processor to implement a knowledge system that operates to modify responses based on a knowledge level of a user, the method comprising:
receiving, by the knowledge system, from a cognitive computing system, a response to a user submitted request received by the cognitive computing system from a client computing system;
determining, by the knowledge system, a first knowledge level of the user for a domain of the user submitted request;
determining, by the knowledge system, a second knowledge level associated with first concepts referenced in the response;
determining, by the knowledge system, whether the first knowledge level is different from the second knowledge level;
modifying, by the knowledge system, in response to the first knowledge level being different than the second knowledge level, content of the response to include second concepts, corresponding to the first concepts, which are associated with the first knowledge level, to thereby generate a modified response; and
outputting, by the knowledge system, the modified response to the client computing system associated with the user.

2. The method of claim 1 , further comprising:
monitoring, by the knowledge system, a user reaction of the user to an output of the response to the user submitted question by the cognitive system;
analyzing, by the knowledge system, the user reaction to determine a frustration or comfort level of the user with regard to content of the response; and
modifying, by the knowledge system, the first knowledge level of the user with regard to the domain of the user submitted request based on results of the analysis of the user reaction to generate an updated first knowledge level.

3. The method of claim 2 , wherein modifying the first knowledge level of the user with regard to the domain of the user submitted request comprises shifting a first knowledge level value along a range of knowledge values by a differential amount determined based on the frustration or comfort level, and storing the shifted first knowledge level, as the updated first knowledge level, in association with an identifier of the domain of the user submitted request in a user profile associated with the user.

4. The method of claim 2 , wherein determining whether the first knowledge level is different from the second knowledge level comprises comparing the second knowledge level to the updated first knowledge level, and wherein modifying content of the response comprises modifying content of the response to include second concepts, corresponding to the first concepts, which are associated with the updated first knowledge level, to thereby generate the modified response.

5. The method of claim 2 , wherein the user reaction is a facial expression of the user, and wherein analyzing the user reaction to determine a frustration or comfort level of the user comprises identifying a facial expression of the user as being an expression of frustration or discomfort with the second knowledge level associated with the first concepts in the response.

6. The method of claim 2 , wherein the user reaction is a tone of a user audible or textual message responsive to the output of the response, and wherein analyzing the user reaction to determine a frustration or comfort level of the user comprises identifying terms or phrases used in the message responsive to the output as indicating frustration or discomfort with the second knowledge level associated with the first concepts in the response.

7. The method of claim 2 , wherein the user reaction is a follow-up or clarifying question submitted to the cognitive system within a predetermined time period of outputting the response, and wherein analyzing the user reaction to determine a frustration or comfort level of the user comprises determining whether the follow-up or clarifying question references a concept in the response.

8. The method of claim 1 , wherein the second knowledge level is a relatively more detailed knowledge level than the first knowledge level, and wherein modifying content of the response to include second concepts, corresponding to the first concepts, which are associated with the first knowledge level, to thereby generate a modified response comprises identifying, in an ontology of concepts, second concepts that are at a higher level of abstraction in the ontology than the first concepts but which are associated with the first concepts in the ontology.

9. The method of claim 1 , wherein modifying content of the response to include second concepts, corresponding to the first concepts, which are associated with the first knowledge level, to thereby generate a modified response comprises:
retrieving, from a configuration management database, information for at least one second concept of the second concepts indicating at least one business value and corresponding seasonality of the at least one second concept; and
modifying the content of the response to specify a current business value of the at least one second concept based on the at least one business value and corresponding seasonality.

10. The method of claim 1 , wherein determining a first knowledge level of the user for the domain of the user submitted request comprises:
retrieving a user profile associated with the user, wherein the user profile comprises a plurality of knowledge levels associated with different domains in a plurality of domains;
determining, based on results of analysis of the user submitted request by the cognitive computing system, the domain of the user submitted request; and
retrieving, from the user profile, the first knowledge level based on a lookup of the domain of the user submitted request in the plurality of domains.

11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
receive, from a cognitive computing system, a response to a user submitted request received by the cognitive computing system from a client computing system;
determine a first knowledge level of the user for a domain of the user submitted request;
determine a second knowledge level associated with first concepts referenced in the response;
determine whether the first knowledge level is different from the second knowledge level;
modify, in response to the first knowledge level being different than the second knowledge level, content of the response to include second concepts, corresponding to the first concepts, which are associated with the first knowledge level, to thereby generate a modified response; and
output the modified response to the client computing system associated with the user.

12. The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
monitor a user reaction of the user to an output of the response to the user submitted question by the cognitive system;
analyze the user reaction to determine a frustration or comfort level of the user with regard to content of the response; and
modify the first knowledge level of the user with regard to the domain of the user submitted request based on results of the analysis of the user reaction to generate an updated first knowledge level.

13. The computer program product of claim 12 , wherein the computer readable program further causes the computing device to modify the first knowledge level of the user with

Assignees

• IBM

Inventors

• Childress Rhonda L
• Lawless Darren L
• Moody Crystal N
• Riley Daniel S
• Spisak Michael J

Classifications

• G06Q10/10

  Office automation; Time management · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06F40/237

  Lexical tools · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06F40/30

  Semantic analysis · CPC title