Search

The purpose of the study is to develop an approach for identifying and processing invalid events in critical information infrastructure (CII) based on the concepts of taxonomy and categorization. The approach aims to improve the efficiency of identifying, classifying, and managing information security (IS) incidents. The article addresses the current tasks of ensuring the required level of CII protection and minimizing the negative consequences of information security incidents resulting from invalid events. The identification of these events is associated with the complexity of detecting such events, the need to process large volumes of data, insufficient speed in detecting IS events, as well as technological limitations.The relevance of identifying and classifying invalid events in information security, especially for CII, is driven by the need for timely detection and response to incidents that could lead to negative consequences. Understanding the nature and characteristics of such events allows for effective system protection and prevention of significant damage. To enhance the effectiveness of ensuring security, it is necessary to identify the class of invalid events among the numerous information security events by considering the characteristics that define invalid events.The novelty of the proposed approach lies in solving the task of identifying the class of invalid information security events based on taxonomy methods, involving the use of event categorization tools with the attributes of invalid events.Materials and methods. The approach to identifying invalid events in CII, based on the principles of information security event taxonomy, was used to solve the task. It was shown that identifying invalid information security events is directly related to solving the problem of searching for and analyzing their attributes, which represent the characteristics or parameters used to describe and classify security incidents. Based on the key principles of taxonomy, a model of the structure of the set of invalid events was developed to determine the characteristics that can be the basis for classifying invalid events. The process of identifying invalid information security events includes a sequence of stages: taxonomy, categorization, and classification, with appropriate methods and tools implemented at each stage.Results. Approaches to identifying invalid events in CII have been analyzed. Problems related to large data volumes, the complexity of event processing, the considerable time required for their detection, and technological limitations were considered. It was shown that the concept of taxonomy and categorization allows for effective identification and classification of information security incidents, ensuring efficient processing and response. The feasibility of applying taxonomy for describing and identifying the attributes of invalid events was justified, contributing to the development of effective protection strategies and improving security levels. A generalized scheme for processing invalid events was proposed, including a set of interconnected stages of identification, categorization, impact assessment, response, documentation, and analysis. An algorithm for structured description and classification of incidents was developed, allowing for more accurate and timely responses to information security threats.Conclusion. The results obtained increase the effectiveness of solving the task of classifying information security incidents by identifying invalid events, which reduces the level of negative consequences of incidents and enhances the security of CII objects.

The purpose of the study. The article discusses the research and further development of modern cyber-physical systems of the Internet of Things (CPS IoT). Researchers in the field of psychology, logic, lin- guistics, philosophy, for the study of artificial intelligence, used many different models of this phenomenon of “man”. Currently, the search for new approaches continues. One of the interesting approaches lies in the development of the application of cognitive mechanisms that a person uses in solving everyday tasks. The application of methods of gestalt processing of states of the CPS IoT worldview is considered to solve an ever-expanding range of tasks. Hybrid or, as they are also called, combined models can be used for gestalt processing to solve various tasks of cyber-physical systems of the Internet of Things related to forecasting indexes of the functioning of socio-economic systems. To do this, you can use a long-known approach to hybrid- ization, the essence of which is to split the entire set of initial data into subsets of initial data. The main stages of gestalt processing and one of the initial stages – the formation of a need are shown. The significant moments of the organization of interaction of CPS IoT modules with the environment are presented. In the demo example, the CPS IoT of the estate museum is considered. The main elements of the formation of the need for CPS IoT in organizing and conducting excursions are described.Materials and methods of research. To solve problems within the framework of gestalt processing of CPS IoT, new methods and developments of specialists in the field of intelligent systems are re- quired. Hybrid, combined models can be used for gestalt processing for various tasks of cyber-physical systems of the Internet of Things related to forecasting indexes of the functioning of socio-economic systems. You can use a long-known approach to hybridization, the essence of which is to split the entire set of initial data into subsets of initial data. It is possible to use gestalt processing within the framework of a holistic approach when splitting into subsets of the initial data - clusters. The cognitive approach uses sensory images, concept-representations, concept-scenarios and gestalts. The CPS IoT gestalt can be considered as one of the approaches to solving modern problems within the framework of Industry 4.0 technology. The article describes intelligent cyber-physical systems using methods of gestalt processing of their states - a picture of the world. Approaches to the use of needs and one of the many approaches to the formation of the needs of cyber-physical systems of the Internet of Things are considered.Results. Within the framework of the cognitive approach, con- cepts-representations of CPS IoT for arising (emerging) needs and their fixation are proposed. After fixing the need, as the main stages of its formation, the following are highlighted: concretization of the event, collection of relevant initial data for the need; formation (folding of perceived information) of the gestalt: checking the state of the necessary elements, searching for resources in the environment; organization of contact with the environment. These stages of the formation of the need relate to CPS IoT of any nature and are fo- cused on any tasks of the Internet of Things. It is advisable to save scenarios for the formation of needs for possible reuse in the future. The demo example shows an example of the formation of a need for CPS IoT during an excursion.Conclusion. The article considers a cognitive approach related to the use and development of intelligent cyber-physical systems for the Internet of Things and the Internet of everything. The main stages of the formation of the need for CPS IoT are considered. The implementation of the proposed approach, the development and use of gestalt concepts will allow reflecting CPS IoT with new emergent properties.

Purpose of the study. The aim of the study is to create and develop modern cyber physical systems. The evolution of cyber physical systems (CPS) is associated with the development of a cognitive approach within the framework of the application of mechanisms used by humans to solve their daily tasks. In the cognitive approach to working with cyber physical systems, gestalt is considered as one of the ways of solving modern tasks within the framework of the new Industry 4.0 technology. In the cognitive approach a simple task is considered for cyber physical systems of the Internet of Things (CPS IoT) with gestalt processing. When investigating such a task for a simple cyber physical system, it will be possible to use a gestalt with a simple structure. The complication of the task and structure of gestalt can occur with the development of CPS IoT. The article examines an intelligent cyber physical system of the Internet of Things using methods of gestalt processing of their states - a picture of the world, while solving various problems of the Internet of Things.Materials and research methods. To solve tasks within the framework of a cognitive approach to the construction and development of cyber physical systems, new methods and developments of specialists in the field of intelligent systems are required. In the context of Industry 4.0 technologies, the Internet of Things the gestalt processing of CPS IoT is considered. Within the framework of the cognitive approach sensory images, concept-representations, concept-scenarios, concept-gestalts of cyber physical systems are used to interact with the real world. It is important to use concept gestalts that can reflect CPS IoT with new emergent properties. CPS IoT gestalt refers to a certain state of the cyber physical system and its habitat, which occurs when a need arises and closes after the need is satisfied. The main task of gestalt processing for a cyber physical system is to satisfy its needs. The solution to this problem includes: the organization of the collection and the direct collection of the necessary elements for the formation of the gestalt, and later for its closure; the formation of the gestalt; the closure of the gestalt. For the accumulation of experience, its use and development, it is proposed to use machine learning methods. Machine learning results can be presented in the form of concept representations, concept scenarios.Results. The concepts-gestalts of CPS IoT, gestalt processing of CPS IoT are proposed within the framework of the cognitive approach. As the main stages of gestalt processing, the article highlights: - preparation of initial data for the formation of the need for CPS IoT: - formation of an imaginative perception - a picture of the world, including the current state of CPS IoT and necessary for the closure of the gestalt; - formation of gestalt; – formation of initial data for planning the control actions necessary for closing the CPS IoT gestalt; - implementation of control actions to close the CPS IoT gestalt; - saving the gestalt processing scenario for possible reuse in the future. These stages of gestalt processing relate to IoT CPS of any nature and are focused on any tasks of the Internet of Things. The demo example shows the use of gestalt processing for CPS IoT with a simple model without training.Conclusion. The article discusses the cognitive approach that refers to the use and development of intelligent cyber physical systems for the Internet of things and the Internet of everything. A method related to the gestalt processing of CPS IoT situations is proposed, which allows recognizing a need, and forming of a gestalt. Based on the generated CPS IoT gestalt, control actions are planned to close the CPS IoT gestalt. The implementation of the proposed approach, development and use of gestalt concepts will allow to reflect CPS IoT with new emergent properties.

The purpose of the study is to improve the incident management process. The article considers the process approach to incident management in case of technical failures and its main stages: detection, response, investigation, elimination, resolution. At the stages of response and investigation of the incident, as well as its elimination, there is an urgent problem, which is the violation of the deadlines adopted in the Service Level Agreement (SLA).A comparative analysis of the indicators before and after the application of the proposed use case approach is carried out. The proposed algorithm, applying the base of use cases, allows reducing the number of incidents that are returned for revision, as well as reduce the number of incidents, the resolution period of which exceeds the limits accepted according to the SLA.The scientific novelty lies in the use of the case analysis device for incident processing in the technical support service.Materials and methods. To solve the above problem related to the violation of the deadlines for processing incidents accepted in the SLA, the article considers an approach to improving the incident management process based on the use case analysis of incidents. The use of the case analysis device is a cycle of reasoning based on use cases. By the value of the degree of similarity to the incident, a specific use case and the associated decision-making scenario are selected. The method of plausible reasoning allows us to solve the problem of multiple escalations as an integrated automation tool and, as a result, reduce the number of violations of the deadlines for resolving incidents. This approach allows you to increase the efficiency of finding similar scenarios for responding to incidents. The nearest neighbor method is used to compare and extract use cases. This method does not require large computational costs and provides the required degree of reliability (error) of the decision. The application of the nearest neighbor method is based on calculating the degree of proximity of the current situation to the use cases stored in the base of use cases.Results. The proposed approach allowed us to develop a new algorithm for classifying incidents in the information system based on the use case and statistical analysis, which reduces the response time and eliminates incidents. The analysis of statistical data is carried out; the efficiency is estimated as a result of the application of the algorithm based on the use case analysis. The assessment showed a significant reduction in unnecessary escalations of incidents to the second support line, so the application of the base of use cases in resolving incidents allowed for improving the incident management process.Conclusion. In the course of the study, the main problem in the incident management process was identified - violation of the deadlines adopted in the SLA. The basic incident management algorithm is analyzed. The application of the method of plausible reasoning and the nearest neighbor method is justified. The cycle of updating the base of use cases and the conceptual model of the incident management process are considered. Within the framework of the developed conceptual model, the base of use cases includes decisions made by experts, which use the knowledge of previous experience to get out of a particular situation. An algorithm for finding a solution in the base of use cases is implemented. A distinctive feature of the developed algorithm is the application of a use case recognition algorithm and the search for similar images contained in the base of use cases using the nearest neighbor method.

Purpose of the study. The purpose of the study is to develop proposals for the formation of a neuroeducational environment that ensures that students acquire the competencies necessary to solve the problem of introducing end-to-end digital technologies within the framework of the digital economy program. The analysis showed that improving the training of specialists in the field of neurotechnology and artificial intelligence in the digital economy is an urgent and demanded task. The paper discusses an approach to solve the problem of improving the training of specialists in the field of neurotechnologies, taking into account the requirements of the federal project “Personnel for the digital economy” by creating a technological platform for a neuroeducational environment that ensures the acquisition of the necessary competencies by students.Materials and methods of research. In the process of carrying out the research, theoretical provisions in the field of the theory of neural networks were developed, a new class of neurons and neural networks was proposed, which are close in functions to biological neural networks and are called selective. The technology of training and application of selective neural networks has been developed. The advantage of selective technologies in comparison with classical neural networks is shown. Hardware models of neural networks, which are part of the neuroeducational system, have been developed and used in the educational process. A general methodology for teaching neural network technology as one of the end-to-end technologies of the digital economy has been developed, as well as a methodology for using neural networks in solving economic problems in the context of digital transformation.Results. A technological platform for a neuroeducational environment has been developed, including software, hardware models of classical neurons and perceptrons (McCulloch-Pitts), as well as neurons and perceptrons of a new class, called selective. A software tool for teaching standard and selective neurotechnologies was developed and proposed, for which a certificate of state registration of a computer program was obtained. For the assimilation of theoretical material and the acquisition of practical skills, methodological materials, author’s practical tasks and author’s laboratory works have been developed, which are part of the technological platform. The approaches proposed in the article can be used in organizing the study of the theory of neural networks and methods of applied application of neurotechnologies in solving the problems of introducing end-to-end digital technologies within the framework of the digital economy program. The development results are confirmed by 4 patents for inventions. In order to more effectively master the theoretical provisions and features of the practical application of neurotechnologies, the main attention is paid to the physical meaning and presentation of the processes occurring during the functioning of a neural network in the form of formal descriptions that provide a more effective assimilation of the foundations of the theory of neural networks and neurotechnologies using existing standard neural network architectures, as well as architectures built on the basis of selective neural networks.Conclusion. The architecture and components of the technological platform of the neuroeducational environment based on neuroeducational complexes have been developed. A general methodological approach has been developed for teaching the basics of neurotechnology based on standard and selective neural networks and the peculiarities of their application in the framework of the digital economy program. A methodology for teaching the basics of neurotechnology based on standard and selective neural networks has been developed, which includes the mathematical theory of standard and selective neural networks, a description of the learning process for standard neural networks based on McCulloch-Pitts neurons, as well as selective neural networks based on selective neurons.

Purpose of research. The aim of the research is to form modules of organizational and technical systems (OTS) using a cognitive approach to solve problems of adaptation of cyberphysical systems. Currently, there is a rapid development of elements of the Internet of things. New tasks related to self-organization and adaptation in a rapidly changing external environment are brought to the fore. These tasks occur when new elements appear in the telecommunications computer network, they fail, change the mode, new tasks occur, etc. To work out these tasks, the possibilities of approaches to support and decision-making such as situational, cognitive, and semiotic are considered. The authors consider the cognitive approach in more detail. Within the framework of the cognitive paradigm, the article describes the use of the cognitive approach for solving problems of adaptation of cyberphysical systems. To solve this problem on the basis of an agent-based approach, the structure of a cyberphysical system with the possibility of adaptation is presented and the functions of its agents are described. The main stages of solving problems of adaptation of cyberphysical systems are presented. An adaptation algorithm using the planning mechanism is presented. The demo example shows a knowledge base for solving the problem of adapting cyberphysical systems using a cognitive planning mechanism.Materials and methods of research. New approaches and methods are required to address adaptation issues in planning. The cognitive approach is one of the developing directions in solving many problems of the Internet of things. One of these tasks is the ability to adapt OTS modules in a rapidly changing external environment based on the planning mechanism. To solve the planning problem, we use the algorithm described by Aristotle more than 2,350 years ago and implemented in the GPS program. This algorithm can be considered the first description of the cognitive mechanism that a person uses. The knowledge base uses an integrated approach to knowledge representation. When developing OTS modules, an agent-based approach was used to solve the problem of adaptation.Results. The existing and developing approaches and methods for decision support and decision-making are considered for decisionmaking in newly emerging situations in OTS modules. The main provisions of such significant approaches as situational, cognitive and semiotic are presented. A cognitive approach to the adaptation of intelligent systems is proposed. The solution of the problem of adaptation of cyberphysical systems is considered within the framework of the cognitive paradigm. The structure of a cyberphysical system capable of solving adaptation problems is shown. The functions of OTS modules based on agent-oriented technology are described. A description of the adaptation algorithm using the cognitive planning mechanism is given. The main stages of solving problems of adaptation of cyberphysical systems are presented. A demo example of solving the problem of adaptation by a cyberphysical system-a cooking robot – is shown.Conclusion. Using the modular architecture of an intelligent system allows you to solve many problems. One of these tasks is to configure elements of the Internet of things when they deviate from their main function. The planning mechanisms proposed for parametric adaptation can be repeatedly applied in OTS modules as separate agents. This approach is relevant for elements of the Internet of things. In the case of expanding the functionality of the OTS modules of Internet of things, it is advisable to apply machine learning with fixing the results in the knowledge base of planning agents.

The aim of the study is to increase the efficiency of the incident management process in an enterprise information system. The article analyzes the work on improving the incident management process. The expediency of applying a number of key metrics is substantiated, which makes it possible to assess the degree to which the process indicators achieved their target values, that is, assess the quality of the incident management: the speed of solving the incident, the degree of satisfaction of service users and the availability of channels for processing user requests. A comparative analysis of the existing model of the incidents’ management process and the proposed model is performed. The proposed model, which includes an additional support line, can significantly improve key indicators of incident handling and resolution process. The scientific novelty of the developed proposals lies in the integrated use of a combination of process, technological and service metrics, which provides the construction of a more effective model of incident management.Materials and methods. The theoretical basis of the study is the analysis of recommendations for the use of metrics in accordance with: the management methodology of the COBIT information technology, recommendations for building an incident management process based on the ITIL library of information technology infrastructure, as well as the results of scientific research by Russian and foreign scientists and publications of leading organizations in the field of management incidents in enterprise information systems. The analysis of incident management process metrics is carried out. The mathematical methods of quantitative measurement of key metrics are used. The analysis of statistical data received by the technical support service for incident management processes was carried out.Results. The use of key metrics is justified, with the help of which the task of promptly responding to incidents, their subsequent processing and resolution is solved in conditions of ensuring guaranteed access to channels for processing calls. A three-tier incidents’ management model was developed, which made it possible to more effectively solve the problem of managing their processing based on the integrated use of key metrics.Conclusion. The study revealed the shortcomings of the existing model of the incident management process. The analysis of metrics used in existing models of the incident management process is carried out. The choice of a set of relevant metrics is substantiated, the complex application of which allowed us to develop a more effective incident management model that meets both the requirements of service consumers and the requirements for the operation of an information system. The developed model provides improved quality of incident processing (speed, completeness, reliability).A distinctive feature of the developed model is the use of objective quantitative characteristics obtained on the basis of relevant metrics of the incident management process, which made it possible to substantiate proposals for improving the existing incident management model in the enterprise information system.

Purpose of the study. The aim of the study is to substantiate and develop an approach to improving the quality of training of specialists in the direction of training “Information Security”, based on improving the quality of assimilation of the educational material of the disciplines provided for by the curriculum.Materials and methods. To achieve this goal, it is proposed to use innovative teaching methods based on the use of modern interactive educational technologies.The study is based on the analysis and use of research materials in the field of the application of pedagogical technologies in the modern educational process, the requirements of the law, which are mandatory when implementing the main educational programs of higher professional education. In preparing the article, the materials obtained by the authors during the planning, preparation, conduct and analysis of laboratory studies with students studying in the direction of training “Information Security” were also used.Results. The specifics of training specialists in the direction of training “Information Security”, due to the high demands placed on them by employers, as well as the complexity and necessity of solving the problems facing the Russian Federation in the field of ensuring information security, lies in the need for them to obtain, along with fundamental knowledge in the field of information security, knowledge of modern and promising information protection technologies.An important role in improving the quality of training highly qualified specialists who are professionally in demand and capable of self-development is currently played by the application of new approaches to their training based on the use of innovative methods. The proposed approach consists in the development by students of modern and promising information protection technologies using innovative teaching methods during the organization, preparation and conduct of training sessions.One of the main, most important in practical, research aspects, forms of conducting classes in the process of training information security specialists is a laboratory workshop.The proposed approach was tested in the educational process when planning, preparing and conducting laboratory work on the topic “Creating a virtual private network in a virtual environment” in the discipline “Information Security Technology”. The main features of this lesson include the relevance, high technology and practical orientation of the topic of the lesson, as well as its interactivity.The result of applying the proposed approach was an increase in the degree of assimilation, the breadth of coverage of the studied material and, as a result, an increase in the effectiveness of the formation of students’ competencies provided for in the curriculum.Conclusion. As a result of the research, an approach to improving the quality of training of specialists in the field of training “Information Security” was substantiated and developed.The proposed approach, which consists in the application of innovative interactive teaching methods during the organization, preparation and conduct of training on relevant, high-tech topics of applied importance, was implemented in practice when students learn the discipline “Information Security Technology”, which allowed to improve the quality of assimilation educational material of the discipline and, ultimately, to improve the quality of training of specialists in the direction of training “Information Security”.

The key task of the current stage of the education system development is the task of transition to new methods of organization and support of the educational process, allowing providing high-quality training of graduates with practical knowledge and skills in demand in the labor market. To solve this task is possible only with the use of innovative methods and tools for the creation of information-educational environment in the formation and processing of learning objects and software services distributed in the educational network and allowing the flexible implementation of the processes of educational and methodological support of educational activities.The aim of the research is to determine the possibilities of using the ontological approach to the construction of innovative automated education management systems, including the construction of individual learning trajectories. In this regard, the problem of modeling and algorithmization of the formation of educational programs as a chain of interrelated training modules and objects, taking into account the implementation of a competence-based model of learning in a distributed educational environment of the University, seems to be interesting.The modern education system is to be aimed primarily at adaptive generation of educational content, taking into account the needs of students and in accordance with constantly changing conditions and needs of the labor market. At present, research in this area mainly concerns issues such as the use of multimedia technologies and simulation programs, knowledge testing technologies based on the competency model, methods for measuring the degree of satisfaction with the quality of training, and management methods based on the portfolio of students. These issues and problems are considered with varying degrees of detail, for example, in [1, 2, 3, 4] and other works. The developed methodology for the formation of educational programs is based on the research results of these authors and is developing towards the use of ontologies that can integrate various concepts of professional and educational standards and create on their basis fundamentally new educational modules and objects. In our opinion, it corresponds to world trends in the development of science in this field of knowledge.It is proposed to use the methods and methodologies of knowledge engineering as engineering methods: ontological engineering methods used for semantic modeling of the information and educational environment, allowing to represent the subject area in the form of a set of interconnected ontologies; methods for constructing and visualizing ontologies; methodologies for building databases and knowledge bases and forming complex queries to databases and knowledge bases; methods for semantic analysis of metadata; graph theory.As a result of the analysis of the objects of the information and educational environment, the requirements for the meta-description of educational objects and services are identified, and a description of the concepts of basic ontologies of the informational and educational environment is presented. The article also discusses the possibilities of using modern software for the formation of an intellectual repository of ontologies. Thus, the proposed toolkit for generating educational programs, in our opinion, will allow us to formalize, simplify, and significantly accelerate the process offlexible development of materials necessary for organizing and supporting the educational process. Application of the described approach makes it possible to improve the quality of training of specialists due to the prompt creation of organizational, managerial and educational materials adapted to the requirements of the labor market, taking into account the peculiarities of forms and methods of training.

Purpose of the research. The aim of the study is to increase the effectiveness of information security and to enhance accuracy and promptness of the classification of security events, security incidents, and threats in information security systems. To respond to this challenge, neural network technologies were suggested as a classification tool for information security systems. These technologies allow accommodating incomplete, inaccurate and unidentified raw data, as well as utilizing previously accumulated information on security issues. To address the problem more effectively, collective methods based on collective neural ensembles aligned with an advanced complex approach were implemented.Materials and methods: When solving complex classification problems, often none of the classification algorithms provides the required accuracy. In such cases, it seems reasonable to build compositions of algorithms, mutually compensating errors of individual algorithms. The study also gives an insight into the application of neural network ensemble to address security issues in the corporate information system and provides a brief review of existing approaches to the construction of neural network ensembles and methods to shape problem solving with neural networks classifiers. An advanced integrated approach is proposed to tackle problems of security event classification based on neural network ensembles (neural network committees). The approach is based on a three-step procedure. The stages of the procedure implementation are described. It is shown that the use of this approach facilitates the efficiency of solving the problem.Results: An advanced integrated approach to addressing security event classification based on neural network ensembles (neural network committees) is proposed. This approach applies adaptive reduction of neural network ensemble (selection of the best classifiers is based on the assessment of the compliance degree of the competence area of the private neural network classifier and convergence of the results of private classifiers), as well as the selection and rationale of the voting method (composition or aggregation of outputs of private classifiers). The results of numerical experiments support the effectiveness of the proposed approach.Conclusion: Collectively used artificial neural networks in the form of neural network ensembles (committees of neural networks) will provide more accurate and reliable results of security event classification in the corporate information network. Moreover, an advanced integrated approach to the construction of a neural network ensemble is proposed to facilitate effectiveness of the classification process. The approach is based on the application of the adaptive reduction procedure for the results of private classifiers and the procedure for selecting the method of aggregation of the results of private classifiers. These outcomes will enable advancement of the system control over information security incidents. Finally, the paper defines tendencies and directions of the development of collective solution methods applying neural network ensembles (committees of neural networks).

Objective. The aim of this study is to develop proposals for improving decision support system, as a subsystem of information and analytical support of the Situation Centre, allowing to increase the validity, accuracy and reliability of decisions taken in modeling semi-structured systems (large-scale economic, organizational, technical or social systems), operating in conditions of significant uncertainty of the external environment and internal factors.Materials and methods. The basis of the study is a new paradigm the need for integration and convergence of various approaches and models (situation, simulation, expertise, cognitive, semiotic etc.), Software environments and technical solutions in the construction of information-analytical systems of Situation Centres. The analysis made it possible to justify the expediency of applying poly-model complexes with formalized decision-making procedures as part of decision support systems. When solving the problem of choosing the most preferable model, the main properties of models are evaluated, such as adequacy (qualitative and quantitative), simplicity and optimality, flexibility (adaptability), universality and problem orientation of the model. The joint use of heterogeneous models in the composition of a poly-model complex makes it possible to increase the accuracy and reliability of solving the problem of choosing the most preferable model of the object of investigation.Results. The necessity of integration and convergence of various approaches and models (situation, simulation, expertise, cognitive, semiotic and others) is presented in the construction of intelligent decision-making support system for the Situation Centre. Expediency description of the object under study by a set of heterogeneous and composite models with the possibility of accounting for the structural dynamics of the modeling object (organizational-technical, socio-economic systems, etc.) is shown, as well as adaptation of the modes with changes for the research object and then comparing the results obtained. An approach based on the use of poly-model complex is proposed, consisting of information analysis system of the Situation Centre that provides the synthesis of an adequate model of the study object. For this purpose, additional elements are introduced in the composition parameters and structures (redundancy) allowing for the direct use of the model to control the quality of the model, to ensure its robustness (insensitivity to changes in composition, structure and content of the original data). The conclusion. The article discusses proposals for improving the decision support system for the Situation Center, using poly-model complexes with formalized decision-making procedures. The advantage of poly-model complex is a possibility of solving the same problems with the use of different models and then comparing the results obtained, a description of the object under study by the set of heterogeneous and composite models, the possibility of taking into account the structural dynamics of the modeling object (organizational, technical, social and economic systems, and others) as well as adaptation of the model taking into account changes in the research object. The developed proposals are aimed at increasing the accuracy and reliability of the results of modeling of weakly structured systems for the validity of management decisions. The obtained results can be used to improve the scientific and methodological support of the functioning of decision support systems as an integral part of the nformation and analytical system of the Situation Centre.