Abstract
This study describes and evaluates the methods developed for the module for the analysis of problems of the closed subject system of answers to questions for the Kazakh language. Question analysis is one of the most important components of a quality control system to obtain the information needed to determine what is being asked and how to answer it. Therefore, we propose new methods of problem analysis in two main problems, namely rule-based and hidden Markov model based on the integration of systematic classification, focus extraction and question classifiers, both of which depend on the relationship between words in the problem. uses the ratio. It also compares these solutions with basic models. This study also manually presents the gold standard aggregated and annotated data for further research in this area.