Patent Grant for Model Management Using Containers by STRIPE, LLC

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12585982B2 to STRIPE, LLC for a method of managing machine learning models using containers. The patent describes a system for deploying machine learning models and their dependencies within containerized application instances.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12585982B2 to STRIPE, LLC, covering a novel approach to model management using containerization. The patent details a system that receives requests to deploy machine learning models, identifies dependent models, selects a container environment, and deploys the models as part of an application instance within that environment. This grant signifies a recognized innovation in the operationalization of AI and machine learning workflows.

While this is a patent grant and not a regulatory rule imposing direct compliance obligations, it is relevant for technology companies involved in AI development and deployment. Compliance officers should be aware of this patent as it may impact intellectual property strategies, licensing agreements, and potential infringement considerations related to AI model deployment technologies. No immediate actions are required, but monitoring patent landscapes in AI is advisable.

Source document (simplified)

← USPTO Patent Grants

Model management using containers

Grant US12585982B2 Kind: B2 Mar 24, 2026

Assignee

STRIPE, LLC

Inventors

Hsien-Chiao Lee, Jonathan Bender

Abstract

The subject technology receives a first request to deploy a first machine learning model, the first request including information indicating an identifier associated with the first machine learning model. The subject technology determines, based at least in part on the first machine learning model, a set of dependent machine learning models. The subject technology selects a first container environment to deploy the first machine learning model and the set of dependent machine learning models. The subject technology, based on the selected first container environment, executes an instance of an application in the selected first container environment, the first machine learning model and the set of dependent machine learning models being deployed as part of the instance of the application.