System and method of cognitive risk management

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted patent US12591832B2 to Blue Yonder Group, Inc. on March 31, 2026 for a cognitive risk management visualization system. The patent covers a computer-implemented method using Bayesian optimization to model supply chain networks and display KPI risk profiles with probability-based confidence intervals.

View original document View source feed page

What changed

USPTO granted patent US12591832B2 to Blue Yonder Group, Inc. on March 31, 2026. The patent (Application No. 18921674, filed October 21, 2024) covers a system and method for cognitive risk management visualization that models supply chain networks, processes input variables through Bayesian optimization with exploration and learning phases, and displays risk profiles for key performance indicators (KPIs) indicating probability of deviation from predicted values. The patent contains 20 claims.

This is a patent grant announcement only—there are no compliance deadlines, regulatory requirements, or penalties associated with this document. Entities developing AI-based supply chain risk management systems should be aware of this intellectual property when designing similar solutions to avoid potential infringement issues.

Source document (simplified)

← USPTO Patent Grants

System and method of cognitive risk management

Grant US12591832B2 Kind: B2 Mar 31, 2026

Assignee

Blue Yonder Group, Inc.

Inventors

Devanand R, Narayan Nandeda, Tushar Shekhar, Vidhi Chugh, Manish Kumar, Deb Mohanty

Abstract

A system and method for a risk management visualization system having a computer comprising a processor and memory and configured to model a supply chain network as a supply chain planning problem, one or more key process indicators (KPIs) of the supply chain planning problem is based, at least in part, on the one or more input variables, model an impact on the one or more KPIs from each of the one or more input variables at a selected confidence interval using a Bayesian optimization process comprising an exploration phase and a learning phase, and display a visualization of the risk profile for the one or more KPIs, the visualization indicating a probability that an actual KPI value differs from a predicted KPI value.