Intellectual Property India Publishes Patent Application for Machine Learning-Based Responsible Ai Governance System For Personalized Learning And Automated Educational Assessment

MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641108589 A) filed by Dr. J. Naga Madhuri; Dr. Jijjavarapu Sunitha Kumari; Veeresh Biradar; Dr. R. Jeyalakshmi; Bangalore Lakshmi Roopa; Poongodi K; Radhika Ankala; Ms. G. M. Jeevapriya; Rudresh S; Dr. Agalya Vt Raj; Dr. Muthukumar Subramanian; and Dr. Pritam Chattopadhyay on September 10, 2026, for Machine Learning-Based Responsible Ai Governance System For Personalized Learning And Automated Educational Assessment.

Inventors include Dr. J. Naga Madhuri; Dr. Jijjavarapu Sunitha Kumari; Veeresh Biradar; Dr. R. Jeyalakshmi; Bangalore Lakshmi Roopa; Poongodi K; Radhika Ankala; Ms. G. M. Jeevapriya; Rudresh S; Dr. Agalya Vt Raj; Dr. Muthukumar Subramanian; and Dr. Pritam Chattopadhyay.

The application for the patent was published on October 02, 2026, under issue no. 40/2026.

Abstract: Machine Learning-Based Responsible AI Governance System for Personalized Learning and Automated Educational Assessment is the proposed invention. The proposed invention the system collects authorized learner data, including academic performance, assessment responses, learning activities, competency levels, interaction patterns, and progress history, and processes the data through preprocessing, normalization, anonymization, and feature extraction to generate a dynamic learner profile. An Agentic AI orchestration layer comprising specialized agents analyzes the learner state and generates personalized learning paths, adaptive content recommendations, assessments, automated evaluations, feedback, and intervention plans. A Policy-as-Code governance engine evaluates each AI-generated decision using machine-executable rules relating to fairness, privacy, curriculum alignment, explainability, confidence, academic integrity, and human oversight. Based on the evaluation, decisions are automatically approved, modified, blocked, or escalated for educator review. The system continuously monitors learner outcomes and feeds the resulting data back to update subsequent learner-state analysis and educational decisions. Further, AI actions, policy evaluations, explanations, confidence scores, and intervention outcomes are maintained in an auditable decision log.

Disclaimer: Curated by HT Syndication.