MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641124111 A) filed by Thanga Kumaran M; Akshay Kumar Chillakuri; Dr Bhagyalakshmi Bn; Dr. Arti Bhatt; Swapna S; N Balamurugan; P. Tamilarasan; S Nagoorkani; Dr. K. Anu Radha; Mrs. Mahabooba M; Dr. Atish Baburao Mane; and Dr. O. Cyril Mathew on October 16, 2026, for Machine Learning-Based Research Gap Identification And Methodology Recommendation System For Higher Education.
Inventors include Thanga Kumaran M; Akshay Kumar Chillakuri; Dr Bhagyalakshmi Bn; Dr. Arti Bhatt; Swapna S; N Balamurugan; P. Tamilarasan; S Nagoorkani; Dr. K. Anu Radha; Mrs. Mahabooba M; Dr. Atish Baburao Mane; and Dr. O. Cyril Mathew.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention discloses a machine learning-based research gap identification and methodology recommendation system for higher education that integrates scholarly literature analysis, natural language processing, knowledge graphs and intelligent recommendation techniques. The system acquires a research topic, research question, research objective, or collection of scholarly documents and retrieves pertinent academic literature. Semantic analysis is conducted to identify research questions, goals, variables, populations, methods, results, limitations, conflicting findings, and future research needs, all of which are depicted in a research evidence knowledge graph. A research-gap intelligence system detects and categorizes knowledge, theoretical, empirical, methodological, population, contextual, temporal, and contradictory-evidence deficiencies, creating a multi-dimensional research-gap vector. A validation process assesses the strength of evidence, the recency of publications, the diversity of methodologies, semantic coherence, and confidence levels to establish if the identified gap is adequately substantiated. The established research-gap vector is converted into methodological necessities and aligned with a methodology knowledge graph that encompasses research designs, sampling techniques, data-collection methods, analytical strategies, and validation procedures. A compatibility engine assesses the suitability and feasibility of methodologies by evaluating characteristics of research gaps, research questions, discipline, available data, resources, academic level, and constraints faced by researchers. Recommendations for ranked and explainable methodologies are produced along with supporting evidence, alternative methods, and confidence levels. A feedback- learning system logs researchers' choices and the resulting research outcomes, then adjusts the recommendation models and knowledge frameworks accordingly. The invention presents a cohesive and flexible system for converting research gaps backed by evidence into practical and understandable methodology suggestions for higher education research. FIG.1
Disclaimer: Curated by HT Syndication.
