Intellectual Property India Publishes Patent Application for System And Method For Explainable Artificial Intelligence-Based Decision Support And Predictive Analytics

MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641091434 A) filed by Pragati Engineering College on July 28, 2026, for System And Method For Explainable Artificial Intelligence-Based Decision Support And Predictive Analytics.

Inventors include Mrs. P. Devi Sravanthi; Mrs. P. Ramya Krishna; Rajapudi Subhashini; Bandaru Naga Divya; and Nittala Phani Raghawendra.

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

Abstract: ABSTRACT A System and Method for Explainable Artificial Intelligence-Based Decision Support and Predictive Analytics The present disclosure relates to a system and method for decision support and predictive analytics using explainable artificial intelligence. The system comprises a multi-source intelligent data acquisition module configured to collect and validate heterogeneous data using dynamic trust evaluation, a context-aware semantic intelligence module configured to generate contextual representations, an adaptive feature evolution engine configured to optimize predictive features, a hybrid predictive intelligence orchestration module configured to dynamically select predictive models, a causal dependency discovery module configured to identify cause-and-effect relationships, a prediction confidence quantification module configured to estimate inference reliability, an explainability knowledge generation module configured to produce structured reasoning, a decision consistency verification module configured to validate generated recommendations, a secure evidence traceability module configured to generate cryptographically protected inference records, a continuous autonomous learning module configured to improve predictive performance using operational feedback, and an intelligent resource optimization module configured to optimize computational resources. The proposed architecture improves prediction accuracy, transparency, explainability, operational reliability, security, computational efficiency, traceability and adaptive decision support in heterogeneous computing environments.

Disclaimer: Curated by HT Syndication.