METHODOLOGY FOR MONITORING STUDENTS’ KNOWLEDGE LEVEL USING ARTIFICIAL INTELLIGENCE

Abstract

This article provides a comprehensive theoretical and practical analysis of a methodology for monitoring students’ knowledge levels based on artificial intelligence technologies. Within the scope of the study, the limitations of traditional assessment methods (tests, written examinations, and exams) are substantiated, particularly their inability to fully reflect students’ actual knowledge level, learning dynamics, and individual learning trajectories.

At the same time, a conceptual model of AI-based monitoring systems is developed, and its structural components—learner model, domain model, instructional model, and adaptation mechanism—are analyzed in an integrated manner. Within this framework, the possibilities of real-time tracking of student activities using learning analytics technologies, processing large-scale educational data (big data), and forecasting are highlighted.

The study also develops methodological foundations for forming individual learning trajectories based on adaptive learning principles, dynamic assessment of knowledge levels, and automated decision-making mechanisms. Furthermore, the potential of AI tools to improve accuracy, reliability, and objectivity in assessing students’ knowledge levels is justified through experimental results.

The findings indicate that AI-based monitoring systems not only significantly enhance the effectiveness of student assessment but also contribute to the individualization of the learning process, optimization of learning activities, and comprehensive improvement of education quality.