Intellectual Property India Publishes Patent Application for Machine Learning-Based Hrm System For Faculty Stress Prediction, Workload Optimization, And Performance Enhancement In Higher Education

MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641103939 A) filed by Murali Karri; Prof. Diwakar Chaudhary; Soundararajan Kandasamy; Dr Ranjith Kumar Varre; Dr. D. Suresh Kumar; Dr. B. Ujwala; Durgaprasad Sathamraju; Sakthivel M; Dr. Sandaboina Shivakumar; Maalini D; Ramdulari Chouhan; and S Mercy Hennah on August 28, 2026, for Machine Learning-Based Hrm System For Faculty Stress Prediction, Workload Optimization, And Performance Enhancement In Higher Education.

Inventors include Murali Karri; Prof. Diwakar Chaudhary; Soundararajan Kandasamy; Dr Ranjith Kumar Varre; Dr. D. Suresh Kumar; Dr. B. Ujwala; Durgaprasad Sathamraju; Sakthivel M; Dr. Sandaboina Shivakumar; Maalini D; Ramdulari Chouhan; and S Mercy Hennah.

The application for the patent was published on September 11, 2026, under issue no. 37/2026.

Abstract: Machine Learning-Based HRM System for Faculty Stress Prediction, Workload Optimization, and Performance Enhancement in Higher Education is the proposed invention. The proposed invention machine learning-based intelligent human resource management system for faculty stress prediction, dynamic workload optimization, and performance enhancement in higher educational institutions. The system employs a time-series foundation model, preferably a Moirai-based predictive architecture, for processing multivariate and time-dependent faculty data. Authorized institutional data comprising teaching workload, course assignments, student mentoring activities, research responsibilities, publication activities, administrative duties, examination assignments, attendance patterns, historical workload, and performance indicators are acquired and transformed into multivariate temporal sequences. The time-series prediction engine learns longitudinal and cross-variable dependencies to generate a faculty stress risk score, forecast future workload intensity, identify abnormal workload patterns, and predict faculty performance trajectories. A constraint-aware workload optimization engine evaluates alternative allocations of teaching, research, mentoring, examination, and administrative responsibilities while satisfying predefined institutional and faculty eligibility constraints. An intelligent recommendation engine generates proactive interventions for reducing predicted workload imbalance and supporting faculty performance enhancement. The system provides predictive alerts, optimized workload configurations, and decision-support information through an administrative interface.

Disclaimer: Curated by HT Syndication.