System and method for cross domain generalization for industrial artificial intelligence applications class

US12032929B2 · kind B2 · utility

Assignee

• TVARIT GMBH · DE

Inventors

• Aditya Srivastava · Fremont, US
• Sanjay Shekhawat · Jaipur, IN
• Rushil Gupta · Chandigarh, IN
• Sachin Kumar · Freeport, US
• Kamal Galrani · Hessen, DE
• Rahul Prajapat · Frankfurt am Main, DE
• Naga Sai Pranay Modukuru · Stuttgart, DE
• Rishabh Agrahari · Mumbai, IN
• Nihal Rajan Barde · Tondavlai, IN
• Arnab Kumar Mondal · New Delhi, IN
• Prathosh A.P · Mumbai, IN

Key dates

• Filing date: Dec 8, 2022
• Grant date: Jul 9, 2024
• Expiry date: Mar 1, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/096
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A cross domain generalization system for industrial artificial intelligence (AI) applications is disclosed. A target encoder subsystem obtains target data from a target machine product and generates lower dimensional data for obtained target data using a target artificial intelligence (AI) model. The generated lower dimensional data are corresponding to a plurality of target embeddings data. The target encoder subsystem further applies the plurality of target embeddings data into a source classifier AI model. A source classifier subsystem predicts a quality of the target machine product by generating class labels for each of the plurality of target embeddings data based on a result of the classifier AI model. The goal of the present invention is to learn features or representations such that the correlation with a label space is similar both in source and target domains while being invariant of data distributions.