Machine Learning Anomaly Detection in Constrained Network Systems

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted patent US12591803B2 to Steering Solutions IP Holding Corporation for machine learning-based anomaly detection methods in constrained networks. The patent covers signal anomaly detection using ML models, counter-based thresholding, and remote diagnostics integration with corrective action procedures. The patent contains 20 claims and names 8 inventors.

View original document View source feed page

What changed

The USPTO issued Patent No. US12591803B2 to Steering Solutions IP Holding Corporation on March 31, 2026, for systems and methods of applying machine learning-based anomaly detection in constrained network environments. The patent describes receiving signals, using ML anomaly detection models to determine if signal values fall within expected ranges, incrementing counters upon anomaly detection, and initiating corrective actions upon threshold exceedance. The 20-claim patent covers both apparatus and method embodiments with applications in signal processing systems.

This patent grant represents a standard intellectual property issuance with no compliance obligations for third parties. Technology companies developing ML-based anomaly detection systems or constrained network applications may wish to review the claims to assess potential freedom-to-operate considerations. No regulatory deadlines, reporting requirements, or penalties are associated with this document.

Source document (simplified)

← USPTO Patent Grants

Systems and methods for applying machine learning based anomaly detection in a constrained network

Grant US12591803B2 Kind: B2 Mar 31, 2026

Assignee

Steering Solutions IP Holding Corporation

Inventors

Bernard C. Robinson, Peter D. Schmitt, Jonathan Hirscher, Owen K. Tosh, Michael R. Story, Emilio Quaggiotto, Joachim J. Klesing, Andrew J. Frank

Abstract

A method for signal anomaly detection includes receiving at least one signal and determining, using at least one machine learning anomaly detection model, whether a value associated with the at least one signal is within a range of an expected value. The method also includes, in response to a determination that the value associated with the at least one signal is not within the range of the expected value, incrementing a counter, and, in response to a determination that a value of the counter is greater than or equal to a threshold value, identifying, based on the at least one signal, signal anomaly information. The method also includes communicating the signal anomaly information to a remote computing device, receiving, from the remote computing device, diagnostics information responsive to the signal anomaly information, and, in response to receiving the diagnostics information, initiating at least one corrective action procedure.