Intelligent Tutoring System Framework and Learning Platform Development

As a general-purpose intelligent tutoring system framework for the development of intelligent tutoring system for their subjects, any subject teachers at universities and schools at all levels developed a platform for the operation of editors and intelligent tutoring systems. The knowledge graph is used to extend the subject graph, hyper-concept graph, basic concept graph, subconcept and help-concept graph. The intelligent tutoring system is designed to emulate the teaching style of human teachers, but to provide individual teaching to each individual student. Therefore, the skills included lecture slide display, video playback, comment display, comment reading by speech synthesizer, student recognition by face recognizer, question presentation and response processing, response results processing by natural language processing, and student’s learning performance prediction et al. Hidden Markov models are known as models that can probabilistically and statistically model the learning path and history of students through time intervals, estimate learning states, and predict learning outcomes. The developed intelligent tutoring system platform estimated and predicted the learning status of the student by the Hidden Markov model and then generated the learning path using a specific algorithm. We also directly generated the learning path using the Markov decision process model. The results of the analysis of the results, using the general-purpose intelligent tutoring system development framework, were very positive, while developing the intelligent tutoring system for AI subjects and allowing students to use it.