Machine learning platform for dynamic model selection

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted Patent US12591809B2 to Oracle International Corporation for an integrated machine learning platform that converts ML models with different schemas into shared schema formats, organizes models into groups, and performs pre-deployment evaluation. The patent covers dynamic model selection in production environments based on scoring metrics tied to business goals.

View original document View source feed page

What changed

Oracle received US Patent 12,591,809 covering a machine learning platform that converts ML models across different schemas into a common format, groups models based on configurable criteria, and evaluates models individually or as groups before deployment. The system includes a selector component that dynamically chooses optimal models from a model group in production based on context-specific scoring metrics aligned with business objectives.

This is a patent grant announcement establishing Oracle's intellectual property rights in ML model management technology. Technology companies developing competitive ML platforms should review the patent claims to assess potential infringement exposure. Oracle and licensees may explore commercialization opportunities. The patent does not impose compliance obligations but creates IP considerations for firms operating in the ML infrastructure space.

Source document (simplified)

← USPTO Patent Grants

Machine learning platform for dynamic model selection

Grant US12591809B2 Kind: B2 Mar 31, 2026

Assignee

Oracle International Corporation

Inventors

Shashi Anand Babu, Raghuram Venkatasubramanian, Neel Madhav, Herve Mazoyer, Daren Race, Arun Kumar Kalyaana Sundaram, Lasya Priya Thilagar

Abstract

The present disclosure relates generally to an integrated machine learning platform. The machine learning platform can convert machine learning models with different schemas into machine learning models that share a common schema, organize the machine learning models into model groups based on certain criteria, and perform pre-deployment evaluation of the machine learning models. The machine learning models in a model group can be evaluated or used individually or as a group. The machine learning platform can be used to deploy a model group and a selector in a production environment, and the selector may learn to dynamically select the model(s) from the model group in the production environment in different contexts or for different input data, based on a score determined using certain scoring metrics, such as certain business goals.