MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641089056 A) filed by St Peters Engineering College on July 21, 2026, for An Intelligent Distributed Machine Learning System For Scalable, Real-Time Prediction And Adaptive Decision Making Across Heterogeneous Data Environments.
Inventors include Ms. Kavya Shree S, Assistant Professor In Department Of Cse, St Peters; Mr. D. Sanjeeva Reddy, Assistant Professor In Department Of Cse, St Peters Engineering College, Opposite Ts Forest Academy, Kompally Road; Ms. Kyadasi Akhila, Assistant Professor In Department Of Cse, St Peters; Mr. Korra Uttam, Assistant Professor In Department Of Ece, St Peters; Mrs. M. Usha, Assistant Professor In Department Of Cse, St Peters; and Mrs. G. Harikeerthana, Assistant Professor In Department Of Cse, St Peters Engineering College, Opposite Ts Forest Academy Kompally Road, Dullapally, Maisammaguda, Medchal, Hyderabad, Telangana.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: The present invention relates to an Intelligent Distributed Machine Learning System for Scalable, Real-Time Prediction and Adaptive Decision Making Across Heterogeneous Data Environments. The invention introduces a unified distributed machine learning framework designed to process heterogeneous data generated from geographically dispersed sources, including Internet of Things (IoT) devices, edge computing nodes, cloud platforms, industrial systems, healthcare infrastructures, financial networks, transportation systems, and smart city applications. The proposed system integrates distributed machine learning, adaptive learning algorithms, intelligent resource management, and real-time predictive analytics to provide scalable, accurate, and low-latency decision support across dynamic computing environments. The framework includes a Data Acquisition Module for collecting structured, semi-structured, and unstructured data, followed by a Data Preprocessing Module that performs data cleaning, normalization, feature extraction, and transformation. A Distributed Machine Learning Module trains predictive models across multiple computing nodes using various machine learning and deep learning algorithms, enabling parallel processing and improved scalability. An Adaptive Learning and Model Optimization Module continuously updates model parameters based on evolving data patterns, ensuring sustained prediction accuracy under changing operational conditions. The system further incorporates a Real-Time Prediction Engine that generates immediate predictive insights and an Adaptive Decision-Making Module that recommends optimized actions for operational improvement. An Intelligent Resource Management Module dynamically distributes computational workloads across distributed nodes to reduce processing latency, improve resource utilization, and enhance system reliability. By eliminating dependence on centralized processing and enabling distributed analytics with adaptive learning capabilities, the proposed invention provides a scalable and efficient intelligent decision support platform suitable for applications in healthcare, industrial automation, finance, transportation, agriculture, cybersecurity, energy management, and smart city infrastructure. The invention significantly enhances prediction accuracy, computational efficiency, scalability, and responsiveness, making it suitable for next- generation intelligent systems operating in heterogeneous and continuously evolving data environments.
Disclaimer: Curated by HT Syndication.
