A structural-functional model of learning in computerized learning systems

Abstract

The subject matter of the article is the development of a universal structural-functional model of computerized learning systems that integrates learner, learning, and explanation models. This model addresses the task of personalizing the learning process, considering the individual characteristics of the learner, and ensuring long-term knowledge retention. The goal of the work is to develop a universal structural-functional learning system model that combines modern adaptive algorithms, integrates psychological and cognitive aspects, and introduces new approaches to long-term knowledge retention. Special emphasis is placed on the system's flexibility, allowing the adaptation of educational content to each user's needs while considering the dynamics of their development and changes in their level of knowledge. The following tasks were solved in the article: analyzing existing learning models, identifying their limitations, and developing new approaches to building an adaptive learning process. The following methods used are – network and vector models for constructing learning trajectories, graph structures for visualizing educational content, and psychological profiling algorithms. Additionally, knowledge actualization methods were applied to reduce the forgetting rate and optimize the learning process. The following results were obtained – a universal structural-functional model of computerized learning systems was created, integrating the learner model, the learning process model, and the explanation model. This model reflects the structure of the adaptive learning process and the interconnections between its components, enabling the personalization of learning trajectories based on the learner’s knowledge level, motivation, and psychological characteristics. The proposed model represents knowledge using network and vector structures, which allows for the systematization of educational materials, visualization of relationships between concepts, and adaptive management of the learning process.The developed model can be applied to analyze students’ preparedness levels, support adaptive learning strategies, and assess progress. The integration of psychological profiling mechanisms and knowledge renewal algorithms enhances the efficiency of the educational process. Conclusions: The proposed structural-functional model demonstrates its effectiveness in addressing key challenges of personalized and adaptive learning. By integrating psychological profiles, knowledge levels, and advanced algorithms, the model enables the creation of scalable and intelligent educational systems. It facilitates personalized learning, effective assessment, and targeted feedback while ensuring long-term knowledge retention and fostering innovation in modern educational technologies.