MUMBAI, India, Oct. 12 -- Intellectual Property India has published a patent application (202641118328 A) filed by Dr. G. Palanikumar; Dr. Mahesh Nandkumar Gaikwad; Dr. Nagaraja B; Dr. Pallavi Dnyanoba Mundhe; S. Jeyapriyanga; Dr. Abu Farah Hoque; Mrs. Mohanapriya T; Ms. Mahabooba M; Katta Akhila; Kanigiri Kumari; Salik Ram Dewangan; and Pradnesh Ramesh Padave on October 03, 2026, for Intelligent Machine Learning-Enabled Library Management And Easy Resource Access System For Higher Education Institutions.
Inventors include Dr. G. Palanikumar; Dr. Mahesh Nandkumar Gaikwad; Dr. Nagaraja B; Dr. Pallavi Dnyanoba Mundhe; S. Jeyapriyanga; Dr. Abu Farah Hoque; Mrs. Mohanapriya T; Ms. Mahabooba M; Katta Akhila; Kanigiri Kumari; Salik Ram Dewangan; and Pradnesh Ramesh Padave.
The application for the patent was published on October 09, 2026, under issue no. 41/2026.
Abstract: An intelligent machine learning-enabled library management and simple resource access system for higher education institutions is the subject of the current invention. An authenticated user interface, academic intent processing module, user-context modeling module, unified physical and digital resource repository, machine learning recommendation engine, availability processor, resource-location module, personalized resource-bundling module, predictive demand module, feedback processor, and administrative analytics module are all included in the system. A natural-language or structured academic requirement is fed into the system, which transforms it into a semantic academic intent representation. The representation is compared to both digital and physical library materials, along with the authorized academic context of an authenticated user. Semantic relevance, academic context, resource availability, geography, resource kind, past interaction, and demand data are all taken into account in machine learning-based ranking. The system creates coordinated resource bundles and tailored resource recommendations on the fly. Whereas digital resources are linked to verified electronic access information, physical resources are linked to location data for creating access and navigation directions. In order to determine future resource requests and any availability mismatches, a predictive demand module examines past library interactions. A feedback module modifies recommendations based on what it learns from authorized user interactions. Intelligent academic resource discovery, personalized access, physical resource navigation, adaptive recommendation, and predictive library resource management are all made possible by the invention's integrated technical architecture. FIG.1.
Disclaimer: Curated by HT Syndication.
