Machine learning model validation with verification data

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted Patent US12591773B2 to Qualcomm Incorporated on March 31, 2026, covering methods for validating machine learning models using verification data in wireless communication networks. The patent includes processes for quantizing and compiling unvalidated ML models, obtaining verification data, and determining performance levels to satisfy validation conditions. Qualcomm receives exclusive rights to this technology for the patent term.

View original document View source feed page

What changed

USPTO granted Patent US12591773B2 to Qualcomm on March 31, 2026. The patent covers methods of validating machine learning models in wireless communication by receiving an unvalidated trained ML model, quantizing and compiling it, obtaining verification data, and validating the model to determine performance levels. The patent also covers methods for transmitting verification data between network devices and receiving performance reports.

Technology companies and legal professionals developing ML-based wireless communication systems should review this patent to assess potential licensing needs or freedom-to-operate considerations. The patent grants Qualcomm exclusive rights to the described ML model validation methods in wireless communications, with 24 claims covering both the validation process and verification data transmission protocols.

Source document (simplified)

← USPTO Patent Grants

Machine learning model validation with verification data

Grant US12591773B2 Kind: B2 Mar 31, 2026

Assignee

QUALCOMM Incorporated

Inventors

Xipeng Zhu, Taesang Yoo, Gavin Bernard Horn

Abstract

A method of wireless communication by a first network device includes receiving a machine learning model, the machine learning model being unvalidated and trained. The method also includes quantizing and compiling the machine learning model. The method further includes obtaining verification data. The method still further includes validating the machine learning model with the verification data to determine a performance level of the machine learning model. A method of wireless communication by a first network device includes transmitting machine learning model verification data to a second network device. The method also includes receiving a report, from the second network device, indicating performance of a machine learning model with the verification data. The method further includes validating the machine learning model in response to the performance satisfying a performance condition.