Fujitsu Limited Patent for Object Attribute Identification using Machine Learning

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted Fujitsu Limited a patent (US12586351B2) for a method of object attribute identification using machine learning. The patent describes a process for acquiring video, using a machine learning model to identify object attributes across hierarchical levels, and specifying those attributes.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12586351B2 to Fujitsu Limited. This patent covers a non-transitory computer-readable storage medium and associated process for object attribute identification using machine learning. The technology involves acquiring video, utilizing a machine learning model trained on reference data to identify object attributes within a first hierarchy, and then further identifying attributes within a second, subordinate hierarchy.

This patent grant is primarily relevant for entities involved in developing or utilizing AI-powered video analysis and object recognition systems. While it does not impose immediate compliance obligations, it establishes intellectual property rights for Fujitsu Limited in this domain. Companies operating in areas such as surveillance, autonomous systems, or content analysis should be aware of this patent and its potential implications for their own technology development and licensing strategies.

Source document (simplified)

← USPTO Patent Grants

Storage medium, specifying method, and information processing device

Grant US12586351B2 Kind: B2 Mar 24, 2026

Assignee

Fujitsu Limited

Inventors

Yuya Obinata, Yasuhiro Aoki, Takuma Yamamoto, Daisuke Uchida

Abstract

A non-transitory computer-readable storage medium storing a specifying program that causes at least one computer to execute a process, the process includes acquiring a video that includes an object; narrowing down, by inputting the acquired video to a machine learning model that refers to reference source data in which attributes of objects are associated with each of a plurality of hierarchies, attributes of the object included in the video among attributes of objects of a first hierarchy; identifying attributes of objects of a second hierarchy under the first hierarchy by using the attributes of the object obtained by the narrowing down; and specifying, by inputting the acquired video to the machine learning model, an attribute of the object included in the video among the attributes of the objects of the second hierarchy.

CPC Classifications

G06V 10/764 G06V 10/82 G06V 20/46 G06V 10/469 G06V 10/761 G06V 10/454 G06V 30/19173 G06V 40/172 G06V 10/25 G06V 10/255 G06V 10/772 G06V 10/95 G06V 10/955 G06N 3/0455 G06N 20/00 G06N 3/045 G06N 3/08 G06N 3/04 G06N 3/084 G06Q 20/20 G07G 1/0045 G06F 18/214 G06F 18/24 G06F 18/2413 G06F 18/2431 G06F 18/2415 G06F 18/211