USPTO Machine Learning for Channel Estimate Patent Application

ChangeBridge: Patent Apps - AI & Computing (G06N)

Detected March 23rd, 2026

Summary

The USPTO has published a patent application from Lenovo (United States) Inc. related to machine learning for channel estimation. The application details methods for generating channel estimates using machine learning models configured by reference signals.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has published patent application US20260082241A1, filed by Lenovo (United States) Inc. The application, titled 'Machine Learning for Channel Estimate,' describes an apparatus that uses machine learning models, configured by reference signals, to generate channel estimates for communication channels.

This publication represents a new patent application filing and does not impose immediate compliance obligations. However, it indicates ongoing innovation in AI and telecommunications technology by a major technology firm. Companies operating in the telecommunications and AI sectors should be aware of this filing as it pertains to intellectual property in machine learning applications for channel estimation.

Source document (simplified)

← USPTO Patent Applications

MACHINE LEARNING FOR CHANNEL ESTIMATE

Application US20260082241A1 Kind: A1 Mar 19, 2026

Assignee

Lenovo (United States) Inc.

Inventors

Mahdi Barzegar Khalilsarai, Venkata Srinivas Kothapalli

Abstract

Various aspects of the present disclosure relate to machine learning for channel estimate. An apparatus, such as a user equipment (UE) and/or network equipment, receives one or more reference signals (RS) that correspond to one or more RS resources for a channel. The apparatus generates a channel estimate for the channel via a machine learning model, wherein one or more model parameters for the machine learning model are configured based at least in part on the one or more RS.