Methods and apparatuses for detecting and localizing faults using machine learning models

ChangeBridge: Patent Grants - Networking (H04L)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted patent US12592953B2 to Telefonaktiebolaget LM Ericsson for methods of detecting and localizing network faults using machine learning models. The patent covers pre-processing procedure-level time series data across multiple network nodes for training ML anomaly detection models. The patent contains 17 claims and was filed August 1, 2022.

View original document View source feed page

What changed

USPTO granted patent US12592953B2 to Ericsson covering methods for detecting anomalies in network operations using machine learning. The technology involves obtaining procedure-level time series data from multiple network nodes and deriving feature time series to train ML models for fault detection. The patent is classified under H04L 63/1425 (network security monitoring), H04L 41/61 (network management), and G06N 3/0442 (neural network architectures).

This patent grant does not impose compliance obligations on third parties. Companies developing ML-based network monitoring or fault detection systems should review the patent claims to assess potential licensing needs or design-around considerations for their products.

Source document (simplified)

← USPTO Patent Grants

Methods and apparatuses for detecting and localizing faults using machine learning models

Grant US12592953B2 Kind: B2 Mar 31, 2026

Assignee

Telefonaktiebolaget LM Ericsson (publ)

Inventors

Tahar Zanouda, Saranya Govindaraj, Dominik Budyn, Martin Rydar

Abstract

A method of pre-processing data for use in training one or more machine learning, ML, models for use in detecting anomalies occurring during execution of one or more procedures at a plurality of network nodes in a network, includes: obtaining procedure level time series data relating to the execution of a first procedure at the plurality of network nodes; and deriving, from the procedure level time series data relating to the execution of the first procedure at the plurality of network nodes, one or more first feature time series of one or more respective first feature values, wherein the one or more first feature time series are for use in training a first ML model associated with the first procedure.