Support decision-making in information control systems using the temporal knowledge base

Abstract

The subject matter of the article are the processes of using temporal knowledge to support decision-making on the control of composite objects within the framework of the enterprise functioning paradigm. The goal is to develop an integrated approach to building, as well as the use of temporal knowledge bases for analyzing the current state of the enterprise as an integral object at different levels of the organizational hierarchy and decision support for control. Tasks: to develop a model of the temporal knowledge base for the presentation of context-oriented temporal dependencies on the behavior of the control object; improve the method of detecting anomalous states of the control object based on the analysis of temporal data and knowledge; to present technologies for the automated construction and use of a temporal knowledge base to support decision-making on enterprise management. The methods used are: methods of construction knowledge bases and methods of supporting management in conditions of uncertainty. The following results were obtained. The following results were obtained. A model of a temporal knowledge base has been developed for use in information management systems. The method of detecting anomalous states of the control object in information control systems based on the use of temporal dependencies has been improved. Technologies for building and using a temporal knowledge base to support management decisions under uncertainty are proposed. Conclusions. The scientific novelty of the results obtained is as follows: A model of a temporal knowledge base has been developed, containing patterns and the realization of logical facts reflecting the state of the control object, as well as the rules establishing the links between these states over time. The model makes it possible to increase the efficiency of enterprise management in conditions of uncertainty based on an analysis of its current state and the derivation of permissible sequences of actions for the transition to a target state. The method for detecting anomalous states of a control object in information control systems has been improved by taking into account the connection between actions at the control object and the context for performing these actions. The method allows to take into account the current properties of the components of the complex control object to classify the current state in conditions of uncertainty. The proposed technology for the construction and use of a temporal knowledge base in information management systems that provide for the iterative replenishment of knowledge in the operation of an enterprise and their use in the context of incomplete information about the control object.