TEMPORAL REPRESENTATION OF THE ESSENCES OF THE SUBJECT AREA FOR THE CONSTRUCTION OF EXPLANATIONS IN INTELLIGENT SYSTEMS

Abstract

The subject of research in the article is is the processes of constructing explanations in intelligent systems using causal relationships. The aim is to develop a representation of the entities of the subject area, taking into account the temporal aspect in order to represent the binary relations in time between the properties of the same entity. The construction of temporal relations between the properties of entities makes it possible to determine the probabilistic causal relationships between the states of these entities and use these dependencies to form explanations for the implemented decision-making process in the intelligent system, taking into account possible alternatives. Tasks: structuring the objects of the subject area, taking into account their essential properties for the decision-making process, including temporal; definition of classes of essences of subject area; determination of equivalence classes of entities of the subject area taking into account changes in the properties of these entities over time; development of a temporal model of representation of essences of subject area for construction of explanations in intellectual systems on the basis of definition of dependences in time between properties of essences. The approaches used are: set-theoretic approach, which is used to describe the classes of entities and classes of equivalence of entities of the subject area; linear temporal logic, which provides a representation of the relationship between entities in the temporal aspect. The following results were obtained. The structuring of the objects of the subject area is performed taking into account their properties, which are used in the decision-making process in the intellectual system; defined classes of entities; the classes of equivalence of entities of the subject area are defined as a kind of class of entities with the same values of key attributes, which makes it possible to take into account changes in these values over time; a temporal model of representation of the essences of the subject area is developed, which takes into account their static, dynamic properties and properties of time. Conclusions. The scientific novelty of the results is as follows. An equivalence class for entities is distinguished, which contains entities with the same key static properties and different dynamic properties considering the time of their change, which allows to reflect changes in the state of the entity in the decision-making process in the intelligent system. The temporal model of representation of essences of subject area which contains classes of equivalence of essences, and also temporal communications between properties of elements of these classes is offered. The selection of classes of equivalence of entities makes it possible to present the decision-making process in the intellectual system in the form of a sequence of temporal connections between the properties of entities of the subject area, and to form on this basis casual relationships between states of entities.