Wireless communication method using on-device learning-based machine learning network

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published April 7th, 2026

Detected April 8th, 2026

Summary

USPTO granted patent US12598483B2 to LG Electronics Inc. on April 7, 2026. The patent covers a wireless communication method using on-device learning-based machine learning networks that collect location samples to generate training data for updating ML models applied to terminal receivers. The technology is designed to provide adaptive wireless communication services responsive to actual communication environments.

View original document View source feed page

What changed

USPTO issued patent US12598483B2 to LG Electronics Inc. for a wireless communication method using on-device learning-based machine learning networks. The patent describes generating a learning list from location samples collected during network communication, detecting events associated with items in the learning list, obtaining training data to update ML networks applied to terminal receivers, and updating the first ML network using the training data. The invention enables wireless communication services adaptive to actual communication environments.

For technology companies developing wireless communication systems, on-device machine learning capabilities, or 5G-related services, this patent establishes prior art that may affect patent prosecution strategies. Companies in telecommunications, mobile devices, and AI-driven wireless technologies should conduct freedom-to-operate analyses before commercializing similar on-device learning approaches for wireless network optimization.

What to do next

Monitor patent portfolio for potential infringement of US12598483B2
Review product development for freedom-to-operate considerations
Evaluate licensing opportunities for the patented technology

Source document (simplified)

← USPTO Patent Grants

Wireless communication method using on-device learning-based machine learning network

Grant US12598483B2 Kind: B2 Apr 07, 2026

Assignee

LG ELECTRONICS INC.

Inventors

Jongku Lee, Ilhwan Kim, Ikjoo Jung

Abstract

Disclosed is a wireless communication method using an on-device learning-based machine learning network. A method according to one embodiment of the present specification comprises the steps of: generating a learning list on the basis of one or more location samples collected while a terminal communicates through a network; when an event associated with any one of one or more first items included in the learning list is detected, obtaining training data for updating, to a second machine learning network, a first machine learning network to be applied to a receiver of the terminal; and updating the first machine learning network by using the training data, and thereby the method provides a wireless communication service adaptive to an actual communication environment. A system including at least one processor of the present specification may be associated with an artificial intelligence module, a drone (unmanned aerial vehicle (UAV)), a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, etc.