RUS  ENG
Full version
JOURNALS // Artificial Intelligence and Decision Making // Archive

Artificial Intelligence and Decision Making, 2024 Issue 1, Pages 38–51 (Mi iipr4)

Decision support systems

Method of automatic constructing training exercises for electronic tutoring systems

O. A. Sychev, M. E. Denisov

Volgograd State Technical University, Volgograd, Russia

Abstract: The paper proposes a method of constructing training exercises by teacher requests, which balances the studies concepts and levels of task complexity. The method is based on ranking training tasks according to their relevance to the request, taking into account previous tasks in the exercise and alternating tasks and studies objectives in task a series. Using the task bank, the key characteristics of the generated tasks were identified. The experimental results showed that the method met the requirements; removing any part of the method led to a deterioration in the generated tasks. The proposed method significantly reduces the labor costs of teachers when using large banks of training tasks.

Keywords: big data, generating training tasks, constructing exercises, method implementation options.

DOI: 10.14357/20718594240104



© Steklov Math. Inst. of RAS, 2024