Methods for Creating Contextual Models of Subject Areas

The aim of the study is to evaluate the methods of autonomous collection and use of local contexts for selecting an answer option by an intelligent system in the dialog interaction process. The following research methods were used: analysis of technical documentation, scientific papers, conference materials and instructional manuals. The current methods of collecting local contexts used in the most successful projects are analyzed. The methods of coding text words for processing by software are analyzed. The methods of measuring the quality of data collected in this way are analyzed. The result of the work is the presentation of the studied methods of collecting, storing and evaluating local contexts. A method for modeling subcategory contexts by a subject area is proposed in order to improve the quality of the decision-making system. A new method of graph modeling of logical connections of natural language data is proposed. A comparison of the effectiveness of various approaches to modeling local contexts is carried out and the corresponding conclusions are made.