MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202511122305 A) filed by K. R. Mangalam University, Gurugram, Haryana, on Dec. 5, 2025, for 'system for federated learning-based predictive decision intelligence.'
Inventor(s) include Dr. Aman Jatain; and Prashant Panwar.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a system for federated learning-based predictive decision intelligence designed to enable collaborative model development, real-time inference, and privacy-preserving decision support across distributed digital ecosystems. The system includes a federated learning engine configured to perform localized training on private datasets retained at computational nodes, a secure communication layer for transmitting encrypted model updates, and a coordinating module that aggregates the updates into a unified global model. The global model is subsequently processed by a predictive decision-intelligence engine that generates actionable insights, forecasts, and domain-specific predictions. The system incorporates an orchestration module capable of managing resource allocation, training synchronization, and node dynamics across heterogeneous infrastructures. Through adaptive learning mechanisms, defense-in-depth security, explainability components, and continuous model-evolution capabilities, the system establishes a scalable and compliant framework for deriving predictive intelligence from decentralized data sources without compromising privacy, confidentiality, or operational integrity."
Disclaimer: Curated by HT Syndication.
