KMSBOT: Enhancing Educational Institutions with an AI-Powered Semantic Search Engine and Graph Database

Abstract

Abstract In the rapidly evolving field of education, the need for a semantic search engine to efficiently retrieve graph-based data is crucial. Universities and colleges generate vast amounts of educational content research articles, and having a semantic search engine can enhance the accuracy of search results, ensuring that students and staff can access the right information effectively. It's imperative to develop an AI-based smart recommendation system equipped with semantic search capabilities to optimize information retrieval and provide accurate mapping for students or scholars. Such a system can revolutionize how educational content is accessed, offering personalized recommendations that align with the individual learning objectives of students and scholars, thus improving their educational experience. KMSBOT is an innovative academic recommendation system designed to enhance the efficiency of existing models. It effectively summarizes academic data and provides tailored information for students, research scholars, and educational faculty. The system employs a three-module approach, utilizing data structuring, NLP processing, and semantic search engine integration. By leveraging Neo4j, NLTK, and BERT in Python, this proposed work ensures optimal performance metrics such as time, accuracy, and loss value. The proposed solution addresses the limitations of traditional recommendation systems and contributes to improving user satisfaction and engagement in academic environments.