Machine learning model abstraction layer for runtime efficiency

US11475368B2 · kind B2 · utility

Assignee

• Zscaler, Inc. · US

Inventors

• Rex Shang · Los Altos, US
• Dianhuan Lin · Sunnyvale, US
• Changsha Ma · Campbell, US
• Douglas A. Koch · Santa Clara, US
• Shashank Gupta · Sammamish, US
• Parnit Sainion · معلمی نژاد, US
• Visvanathan Thothathri · Santa Clara, US
• Narinder Paul · Sunnyvale, US
• Howie Xu · Palo Alto, US

Key dates

• Filing date: Sep 18, 2020
• Grant date: Oct 18, 2022
• Expiry date: Feb 19, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/045
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Systems and methods include training a machine learning model with data for identifying features in monitored traffic in a network; analyzing the trained machine learning model to identify information overhead therein, wherein the information overhead is utilized in part for the training; removing the information overhead in the machine learning model; and providing the machine learning model for runtime use for identifying the features in the monitored traffic, with the removed information overhead from the machine learning model.