Year: 2025
Type: article
Abstract: The study introduces a new Machine Learning-Driven Query System (ML-QS) specifically for the school context to solve the problem of frequent simple queries. It seeks to optimize precision in disseminating information services for students, parents, and faculty. On this basis, warding off suboptimal results and achieving versatility in target interactions, the developed mechanism of the ML-QS utilizes combined structures of machine learning, specifically NLP, and administrative and organizational knowledge to provide answers consonant with the principles of institutional practice and procedural norms. It helps solve shortcomings in the currently available systems of chatbots as they adapt the answers to domain-related questions and promote increased user satisfaction and efficiency in administrative tasks. In terms of methodological underpinnings, this work uses supervised and online learning to train and optimize the ML QS. Findings confirm its utility in satisfying various user requirements and managing organizational procedures, supporting its ability to improve user satisfaction and organizational performance in learning institutions. The study gives guidelines on using ML-QS in educational institutions, the potential of encouraging user interactions, and the enhancement of information services, pointing out future research directions and prospects. Finally, the ML-QS is one of the most significant developments in machine learning for handling difficulties arising from user queries in uncertain contexts and providing the best solution for enabling effectiveness and timeliness of information delivery
Language: English
Topic: AI in Service Interactions
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: bronze
OpenAlex ID: W4409277045