US 12,443,963 B2
License compliance failure risk management
Ana Paula Appel, São Paulo (BR); Manuel Soares Pereira Da Rocha Junior, São Paulo (BR); Carlos Eduardo Buzeto, São Paulo (BR); and Allana Paola Paoli Neves, São Paulo (BR)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on May 15, 2023, as Appl. No. 18/317,684.
Prior Publication US 2024/0386439 A1, Nov. 21, 2024
Int. Cl. G06Q 30/018 (2023.01); G06Q 50/26 (2024.01)
CPC G06Q 30/018 (2013.01) [G06Q 50/26 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for managing licenses comprising:
receiving, by a computer, evidence required for compliance with conditions set forth in a license from a client device of a designated user via a network;
extracting, by the computer, compliance related data from the evidence using a convolutional neural network (CNN) trained on a dataset of labeled environmental compliance images to detect regulatory violations including at least one of pollutant emissions, hazardous material storage conditions, or industrial safety equipment presence, wherein the CNN outputs a confidence score for each detected regulatory violation;
applying, by the computer, optical character recognition and natural language processing to extract textual compliance information from documents within the evidence;
validating, by the computer, using a plurality of machine learning models comprising the CNN for image analysis and a set of language models for text analysis and a set of regression neural networks for sensor data analysis, the compliance related data against predefined regulatory standards stored in a knowledge graph comprising nodes representing licenses, evidence types, and evidence submission deadlines with edges indicating temporal relationships;
automatically generating, by the computer, a compliance failure risk score based on detected discrepancies between the evidence and the predefined regulatory standards, wherein the compliance failure risk score indicates a probability of license revocation;
correlating, by the computer, the validated compliance related data with a temporal evidence submission timeline generated for the license, wherein the temporal evidence submission timeline specifies evidence submission intervals over a life of the license;
recording, by the computer, the validated compliance related data and risk score in an immutable blockchain ledger as a self-executing smart contract; and
transmitting, by the computer, the validated compliance related data to a regulatory agency via a secure blockchain network to maintain the license for an entity, wherein the transmitting creates an auditable cryptographic record of compliance.