MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202621062466 A) filed by Ajaykumar Tanaji Aiwale; Ms. Hemlata Hanamant Mane; Shraddha Rajesh Jadhao; Veena Kiragi; Sunita Shailesh Yewale; Mr. Vaibhav R. Chavan; Vaishali Kumar; Ashwini Ashok Athawale; Smita Amit Shedbale; and Smita Yogesh Arude on May 17, 2026, for A Hybrid Machine Learning-Based System For Advanced Data Analytics In Large-Scale Data Environments.
Inventors include Ajaykumar Tanaji Aiwale; Ms. Hemlata Hanamant Mane; Shraddha Rajesh Jadhao; Veena Kiragi; Sunita Shailesh Yewale; Mr. Vaibhav R. Chavan; Vaishali Kumar; Ashwini Ashok Athawale; Smita Amit Shedbale; and Smita Yogesh Arude.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to a hybrid machine learning-based system for advanced data analytics in large-scale data environments. The invention provides an intelligent analytical framework configured to process structured, semi-structured, and unstructured datasets generated from heterogeneous sources including cloud platforms, enterprise databases, Internet of Things (IoT) devices, industrial sensors, healthcare systems, financial systems, and social media networks. The disclosed system comprises a data acquisition module, pre-processing and transformation module, hybrid machine learning engine, distributed computing framework, adaptive learning module, security management module, and decision-support interface. The pre-processing module performs data cleaning, normalization, feature extraction, dimensionality reduction, and transformation operations for generating analytically optimized datasets. The hybrid machine learning engine integrates supervised learning, unsupervised learning, deep learning, reinforcement learning, and ensemble learning models to perform predictive analysis, anomaly detection, classification, clustering, and intelligent pattern recognition. The distributed computing framework enables parallel processing, adaptive workload allocation, and scalable resource optimization for handling large-scale datasets with reduced computational latency. The invention further supports real-time analytics and continuous adaptive learning through automated model optimization mechanisms based on evolving data patterns and feedback information. Security and privacy protection are achieved using encrypted communication protocols, intelligent authentication systems, and role-based access control mechanisms. The system additionally generates predictive reports, anomaly alerts, visualization outputs, and automated recommendations for supporting intelligent decision-making. The invention thereby provides a scalable, secure, and computationally efficient platform for advanced large-scale data analytics across industrial, healthcare, financial, educational, and enterprise applications.
Disclaimer: Curated by HT Syndication.
