DETERMINING RATIONALE OF COGNITIVE SYSTEM OUTPUT

• US 20200134414A1
• Filed: 10/29/2018
• Published: 04/30/2020
• Est. Priority Date: 10/29/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chan, Yuk L., Flom, Mikhail, Jumba, Albert S., Kumar, Niraj, Luthra, Tejinder, Mallepalle, Sue, Pistoleanu, Florin-Traian, Ravindranath, Goduwin R., Sreedharan, Rekha M., Sweiss, Abraham, Taylor, Sheryl, Yarlagadda, Hemanth
• Granted Patent: US 11,037,049 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/042 Knowledge-based neural networks; Logical representations of neural networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence

Abstract

According to one or more embodiments of the present invention, a computer-implemented method includes generating, by a cognitive system, an answer for a user-provided query using an analytics algorithm. The answer is based on a set of data sources. The method further includes determining an influence weightage of each data source from the set of data sources. The method further includes generating and presenting a rationale for the answer based on the influence weightage.

Claims

1. A computer-implemented method comprising:

generating, by a cognitive system, an answer for a user-provided query using an analytics algorithm, the answer is based on a set of data sources;

determining an influence weightage of each data source from the set of data sources; and

generating and presenting a rationale for the answer based on the influence weightage.

2. The computer-implemented method of claim 1, wherein the rationale comprises a visual representation of the set of data sources and one or more operations performed to generate the answer.

3. The computer-implemented method of claim 2, wherein the rationale further comprises a summary of each data source from the set of data sources used to generate the answer.

4. The computer-implemented method of claim 1, wherein a data source from the set of data sources is one from a group of electronic data sources comprising books, articles, journal papers, social media posts, and blog posts.

5. The computer-implemented method of claim 1, wherein determining the influence weightage of each data source on the answer comprises back propagating an influence weightage of each operation performed in the analytics algorithm to obtain the answer.

6. The computer-implemented method of claim 1, wherein the answer is a first answer, the method further comprising:

adjusting, by a user, the influence weightage of a first data source from the set of data sources; and

generating, by the cognitive system, a second answer for the user-provided query using the analytics algorithm, the answer is based on the set of data sources using the adjusted influence weightage.

7. The computer-implemented method of claim 6, wherein adjusting the influence weightage can omit the first data source from being used to generate the answer.

8. A system comprising:

a user interface;

an answer generator; and

a rationale generator;

wherein, the system performs a method comprising;

generating, by the answer generator, an answer for a user-provided query using machine learning, the answer is based on a set of data sources;

determining, by the rationale generator, an influence weightage of each data source from the set of data sources, and generating a rationale for the answer based on the influence weightage; and

presenting, by the use interface, the rationale to a user.

9. The system of claim 8, wherein the rationale comprises a visual representation of the set of data sources and one or more operations performed to generate the answer.

10. The system of claim 9, wherein the rationale further comprises a summary of each data source from the set of data sources used to generate the answer.

11. The system of claim 8, wherein a data source from the set of data sources is one from a group of electronic data sources comprising books, articles, journal papers, social media posts, and blog posts.

12. The system of claim 8, wherein determining the influence weightage of each data source on the answer comprises back propagating an influence weightage of each operation performed to obtain the answer.

13. The system of claim 8, wherein the answer is a first answer, the method further comprising:

adjusting, by the user interface, the influence weightage of a first data source from the set of data sources; and

generating, by the answer generator, a second answer for the user-provided query using the machine learning, the answer is based on the set of data sources using the adjusted influence weightage.

14. The system of claim 13, wherein adjusting the influence weightage can omit the first data source from being used to generate the answer.

15. A computer program product comprising a computer readable storage medium having stored thereon program instructions executable by one or more processing devices to perform a method comprising:

generating, by a cognitive system, an answer for a user-provided query using machine learning, the answer is based on a set of data sources;

determining an influence weightage of each data source from the set of data sources; and

generating and presenting a rationale for the answer based on the influence weightage.

16. The computer program product of claim 15, wherein the rationale comprises a visual representation of the set of data sources and one or more operations performed to generate the answer.

17. The computer program product of claim 16, wherein the rationale further comprises a summary of each data source from the set of data sources used to generate the answer.

18. The computer program product of claim 15, wherein a data source from the set of data sources is one from a group of electronic data sources comprising books, articles, journal papers, social media posts, and blog posts.

19. The computer program product of claim 15, wherein determining the influence weightage of each data source on the answer comprises back propagating an influence weightage of each operation performed to obtain the answer.

20. The computer program product of claim 15, wherein the answer is a first answer, the method further comprising:

adjusting, by a user, the influence weightage of a first data source from the set of data sources; and

generating, by the cognitive system, a second answer for the user-provided query using the machine learning, the answer is based on the set of data sources using the adjusted influence weightage.