Principles of constructing mental models of a solution for external users in the task of generating explanations in an intelligent system

The subject of the research is the process of constructing user mental models in intelligent information systems. The aim is to improve the principles of building mental models of external users regarding the decisions of an intelligent information system to form explanations in accordance with both the needs of these users and the limitations on the use of solutions in a specific subject area. Objectives: improvement of existing principles of mental model construction based on structuring the description of the intelligent system's solution; development of a principle for constructing mental models of the intelligent system user, considering the limitations when using the obtained solution. The scientific novelty of the obtained results is as follows. The existing principles of human mental model construction have been adapted, considering the differences in constructing explanations for a solution in an intelligent system represented as a «black box». The adapted principles consider the correspondence between the structure of the mental model and the solution, the multiplicity of mental models regarding the solution, and the incompleteness of input data for decision-making. The principle of input data supplementation is proposed, which consists in using the values of solution properties that are irrelevant from the user's point of view to limit the set of relevant solutions. The use of this principle in constructing an explanation makes it possible to consider the negative aspects of using the obtained result and thereby simplify the user's choice and application of this solution.