Intellectual Property India Publishes Patent Application for An Intelligent Multi-Model Learning System For Enhanced Data-Driven Decision Making

MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641089771 A) filed by Umashankari V; R. Parthiban; Sharmila V; Prabharani P; Mr. D. Rajapandi; K. Kanniyarasu; A. Nithya; Palanisamy K. C.; P. Pandiyarajan; and M. Devendran on July 23, 2026, for An Intelligent Multi-Model Learning System For Enhanced Data-Driven Decision Making.

Inventors include Umashankari V; R. Parthiban; Sharmila V; Prabharani P; Mr. D. Rajapandi; K. Kanniyarasu; A. Nithya; Palanisamy K. C.; P. Pandiyarajan; and M. Devendran.

The application for the patent was published on July 31, 2026, under issue no. 31/2026.

Abstract: ABSTRACT AN INTELLIGENT MULTI-MODEL LEARNING SYSTEM FOR ENHANCED DATA-DRIVEN DECISION MAKING The invention discloses an intelligent multi-model learning system for enhanced data-driven decision-making. The system integrates supervised, unsupervised, and reinforcement learning techniques within a unified modular architecture, enabling adaptability to heterogeneous datasets and dynamic environments. A preprocessing and feature engineering module standardizes and transforms raw data from structured, semi-structured, and unstructured sources, ensuring compatibility for model training. An adaptive orchestration engine dynamically selects and combines models based on task-specific requirements, while a reinforcement-based controller continuously monitors outcomes and adjusts model weights to optimize performance. The system further incorporates an explainable artificial intelligence module that provides transparency and interpretability of decision outcomes, thereby enhancing trustworthiness and regulatory compliance. A feedback and continuous learning module enables incremental updates to model parameters, ensuring resilience and long-term accuracy in evolving data contexts. Applications of the invention include healthcare diagnostics, financial forecasting, and industrial automation, where improved predictive accuracy, operational efficiency, and decision transparency are critical. The invention thus provides a robust, scalable, and transparent framework for intelligent multi-model learning and decision optimization.

Disclaimer: Curated by HT Syndication.