Machine learning for management of positioning techniques and radio frequency usage

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published April 7th, 2026

Detected April 7th, 2026

Summary

USPTO granted patent US12596954B2 to Cisco Technology, Inc. on April 7, 2026. The patent covers machine learning techniques for selecting optimal positioning methods in networking environments based on environmental factors. The invention uses ML models to predict accuracy of different positioning techniques and select the most appropriate one for a given location and conditions.

View original document View source feed page

What changed

USPTO issued Patent US12596954B2 to Cisco Technology, Inc. for machine learning-based systems that manage wireless positioning techniques and radio frequency usage. The patent describes receiving indications about a mobile device's location region, determining environmental exogenous factors, and using ML models to predict accuracy of various positioning techniques before selecting the optimal method. The patent contains 20 claims and is classified under CPC G06N 20/00 (machine learning).

For technology companies and telecommunications firms, this patent establishes intellectual property rights in ML-assisted positioning that could affect product development strategies. Companies developing positioning systems, location-based services, or RF networking equipment may need to consider licensing implications or design-around strategies to avoid infringement on the disclosed techniques.

What to do next

Monitor for updates

Source document (simplified)

← USPTO Patent Grants

Machine learning for management of positioning techniques and radio frequency usage

Grant US12596954B2 Kind: B2 Apr 07, 2026

Assignee

Cisco Technology, Inc.

Inventors

Gino M. Corleto, Robert E. Barton, Jerome Henry, Malcolm M. Smith

Abstract

Techniques for improved networking are provided. An indication that a mobile device is in a first region of a physical space is received, and one or more current exogenous factors are determined for the physical space. Positioning technique accuracy is predicted for each respective positioning technique of a plurality of positioning techniques by processing the indication of the first region and the one or more current exogenous factors using a machine learning model. A first positioning technique of the plurality of positioning techniques is selected based on the predicted positioning technique accuracies.