SEMANTIC CONSISTENCY OF EXPLANATIONS IN EXPLAINABLE ARTIFICIAL INTELLIGENCE APPLICATIONS

Patent №

US 11,769,080

Granted

2023-09-26

Filed 2022

Owner

KYNDRYL, INC.

Lab

AI components

5

ml · nlp · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

17865152

A computer-implemented method in accordance with one embodiment includes, in response to a submission of an input dataset to an artificially intelligent application, receiving an explanation from each module of the application. The modules are configured within the application in a serial sequence in which each module, upon receiving the input dataset and any input generated by an immediately preceding module of the serial sequence, generates output that is forwarded as input to a next module, if any, in the sequence. A determination is made that at least two of the received explanations are semantically inconsistent.

Machine learningNatural languageKnowledge representationPlanningAI hardwareG06N 5/045G06N 20/00G06F 17/16G06F 40/30G06N 3/0442G06N 3/0464G06N 3/08

AI classification

Planning1.00
Natural language1.00
Machine learning1.00
Knowledge representation1.00
AI hardware1.00
Speech0.02
Evolutionary computation0.01
Vision0.01

Ownership

KYNDRYL, INC.

assignment · 641130939

Assignors

VENKATESWARAN, SREEKRISHNAN, PADHI, DEBASISHA, ASTHANA, SHUBHI, BHAMIDIPATY, ANURADHA, KUNDU, ASHISH

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC