MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641083190 A) filed by Sasi Institute Of Technology & Engineering on July 06, 2026, for Deep Learning–based Context-Aware Intelligent System For Real-Time Prediction, Latency Data Processing, Real-Time Analytics, And Autonomous Decision Making.
Inventors include Mr. Naresh Konduri, Associate Professor, Department Of Iot & Cs Including Block Chain Technology, Sasi Institute Of; Peesapati V Sunneetha, Assistant Professor In Department Cse Ai&ds, Satya Institute Of Engineering Technology And; Seepana Ratna Kumari, Assistant Professor In Department Cse Ai&ds, Satya Institute Of Engineering Technology And; Saiprasanna Panthina, Assistant Professor In Department Cse; Mrs. Sai Lavanya Akella, Assistant Professor In Department Cse; and Mr. Adari Aditya, Assistant Professor In Department Cse Ai&ds, Satya Institute Of Engineering Technology And Management, Gajularega, Vizianagaram Andhra Pradesh,..
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention discloses a Deep Learning–Based Context-Aware Intelligent System for Real-Time Prediction, Low-Latency Data Processing, Real-Time Analytics, and Autonomous Decision Making designed to process heterogeneous real-time data and generate intelligent predictions with minimal computational latency. The framework integrates Artificial Intelligence (AI), deep learning, Internet of Things (IoT), edge computing, cloud computing, and context-aware computing technologies to support adaptive and autonomous decision-making. Real-time data are acquired from IoT sensors, wearable devices, industrial equipment, surveillance systems, mobile devices, and environmental monitoring stations. The acquired data undergo preprocessing operations including cleaning, normalization, feature extraction, contextual data fusion, dimensionality reduction, and noise filtering. Advanced deep learning architectures including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Transformer models, and hybrid deep learning frameworks are employed to analyze contextual information and predict future events, anomalies, system performance, and resource requirements. The framework incorporates edge computing for low-latency inference and cloud computing for scalable model training and centralized management. Real-time analytics continuously monitor streaming data, detect patterns, and generate intelligent insights. An autonomous decision engine automatically performs resource optimization, event response, alert generation, and operational control without continuous human intervention. The proposed invention significantly improves prediction accuracy, reduces response time, enhances computational efficiency, and enables intelligent decision-making across healthcare, smart manufacturing, cybersecurity, autonomous transportation, industrial automation, smart agriculture, and next-generation smart city environments. It provides a scalable, adaptive, and reliable platform for future intelligent computing systems.
Disclaimer: Curated by HT Syndication.
