MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202541016038 A) filed by Manivannan K; Dr. T. Anuprathibha; I. Nandhini; V. S. B. Engineering College, Karur; M. Kirubhasan; S. Kuberan; T. Kanishkar; and B. Jhose Rubaraj on February 24, 2025, for A Comprehensive Personalized Student Resource Recommendation System Using Dynamic Web Technologies For Academic And Career Development.
Inventors include Manivannan K; Dr. T. Anuprathibha Number; I. Nandhini; V. S. B. Engineering College, Karur; M. Kirubhasan; S. Kuberan; T. Kanishkar; and B. Jhose Rubaraj.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: The efficiency of student career growth and academic resource allocation depends on the accuracy and adaptability of recommendation systems in an evolving educational landscape. This work falls under the Web and AI-driven Recommendation Systems domain and proposes a Comprehensive Personalized Student Resource Recommendation System that curates and recommends internships, hackathons, workshops, academic materials, and job opportunities based on a student’s year of study, department, and professional interests. The system integrates real-time filtering algorithms, automated notifications, and a structured data retrieval mechanism, ensuring timely and relevant recommendations. By incorporating machine learning (ML)-based ranking mechanisms and adaptive filtering, the system continuously refines recommendations to match user preferences. Our approach improves engagement rates by 45% compared to traditional portals by reducing manual effort and redundant searches. The proposed system categorizes student profiles, updates resource databases dynamically, and ranks opportunities using personalized filtering. Evaluation of simulated datasets reflecting real-world academic and career transitions demonstrates a 35% improvement in recommendation accuracy and a 50% increase in resource accessibility over non-dynamic systems. Unlike conventional university portals and generic career platforms, our system ensures real-time updates, automated notifications, and ML-driven insights for enhanced personalization. This paper contributes to advancing intelligent recommendation models in educational technology by optimizing real-time resource allocation, reducing information overload, and significantly enhancing student engagement. The system outperforms previous solutions by integrating ML-based personalization, real-time updates, and dynamic filtering, ensuring students receive the most relevant resources at the right time for academic and career success.
Disclaimer: Curated by HT Syndication.
