Modern digitalization processes involve the use of intelligent systems at key stages of information processing. Given that the data available for intelligent analysis in organizational systems are often fuzzy, there is a problem of comparing the corresponding units of information with each other. There are several known methods for such a comparison. In particular, for random fuzzy variables with known distribution laws, the degree of coincidence of these distribution laws can be used as a criterion for the correspondence of one random variable to another. However, this approach does not have the necessary flexibility required to solve practical problems. The approach we propose allows you to compare fuzzy, fuzzy and clear, as well as clear and clear data. The paper will provide an example illustrating this approach. The material presented in the study was initially focused on managing organizational systems in education. However, its results can be extended to other organizational systems.

Keywords: fuzzy data, weakly structured problems, comparison criteria, hierarchy analysis method, systems analysis, fuzzy benchmarking

The purpose of the article is a software implementation of a module for analyzing the activity of site users based on a heat map of clicks, compatible with domestic web services, for example, combining the functionality of correlation and regression analysis and visualization in the form of dashboards before and after making changes to site elements. All functionality is carried out directly in the web analytics service. Based on the data obtained on the analyzed site element, a decision is made to adjust the design and/or content to increase the click rate. Thus, the proposed solution allows us to expand the functionality of the web analytics service and reduce labor costs. The software module has been successfully tested. As a result of the analysis and making the necessary adjustments to the site, the click rate increased

Keywords: user activity, correlation and regression analysis, dashboard, program module, trend line, coefficient of determination

There is often a need to analyze unstructured data when assessing the risk of emergency situations. Traditional analysis methods may not take into account the ambiguity of information, which makes them insufficiently effective for risk assessment. The article proposes the use of a modified hierarchy process analysis method using fuzzy logic, which allows for more effective consideration of uncertainties and subjective assessments in the process of analyzing emergency risks. In addition, such methods allow for consideration of not only quantitative indicators, but also qualitative ones. This, in turn, can lead to more informed decisions in the field of risk management and increased preparedness for various situations. The integration of technologies for working with unstructured data in the process of assessing emergency risks not only increases the accuracy of forecasting, but also allows for adapting management strategies to changing conditions.

Keywords: artificial intelligent systems, unstructured data, risk assessment, classical hierarchy analysis method, modified hierarchy analysis method, fuzzy logical inference system

This paper explores methods for using large language models (LLM) to detect provocative comments on social media during mass protests. We analyze existing approaches to text data processing and develop a methodology for using LLama3 8B, Mistral 7B, and Gemma 7B models. The effectiveness of the models is evaluated using comments related to the protests in Mongolia in December 2022. The results demonstrate that the Mistral 7B model has the highest accuracy and efficiency in classifying provocative comments. The findings confirm that the use of large language models significantly improves the accuracy and speed of content analysis on social media, which is important for public opinion management and conflict prevention.

Keywords: large language model, social network, provocative comment, mass protest, text analysis, natural language processing, LLama3 8B, Mistral 7B, Gemma 7B, classification, accuracy, recall, F1-score, political instability, public opinion management

The paper considers the task of collection and preparation of data coming from several information systems on the example of automation of registrar's reporting. The languages OWL, XML, XBRL and semantic networks can be used to describe the subject area. A set of criteria for analysing and selecting the most appropriate knowledge representation language for the purpose of data collection on the example of financial statements is prepared. The results of service development are described and the application of XBRL format is shown. The multi-agent approach to modelling and design of information systems was used in the development of the service.

Keywords: data mining, subject area model, data formats, XBRL, business process, service, data integration

The article is devoted to the solution of the problem of forming mechanisms for ensuring sustainable functioning of natural and man-made risks management processes in territorially distributed organizational systems determined by both the spatio-temporal structure of the enclosing natural landscapes and the characteristics of man-made impact. The article presents and substantiates the position that regional geographic information systems and geoportals should play a key role in the risk management system. The example of the regional GIS "Mordovia" and the geoportals "Metageosystems of Mordovia. Spatial data of the region" and "Natural and cultural heritage of the Republic of Mordovia. Traveling with the Russian Geographical Society" shows the possibility of using an analytical approach to the analysis of geosystems of various hierarchical levels to solve the problem of risk analysis in territorially distributed organizational systems.

Keywords: geographic information system, geoportal, risk analysis, spatial data, geosystems, geographically distributed organizational system

The article examines the man-made risks in the Arctic zone of the Russian Federation, methods of working with data related to the use of intellectual analysis, and the use of information systems for forecasting risks and is designed for the widest range of readers. The conducted research demonstrates that the use of data mining methods opens up broad prospects for data integration. This process includes the adaptation of the system to specific emergency situations typical of the Arctic zone of the Russian Federation, as well as the development of appropriate interfaces for interaction with external subsystems. As a result of the conducted research, the conclusions were obtained: 1. Intelligent methods allow you to analyze large amounts of data and identify hidden patterns, which helps you make more informed decisions. The quality of decisions is improved. 2. Intelligent data processing allows you to automate routine tasks and optimize business processes. This leads to increased productivity and lower costs. The efficiency of business processes increases. 3. Intelligent systems can analyze data about past events and predict future trends. This allows you to take measures to reduce risks and ensure safety. These processes make it possible to reduce risks. 4. Intelligent algorithms can process data in real time, which allows you to quickly respond to changes in the external environment. 5. In the future, it is planned to work out the issue of introducing intelligent data analysis algorithms into man-made emergency forecasting analytics systems and the development of the data science concept, such as the GIS Atlas of Natural Hazards and Risks.

Keywords: data mining, forecasting, emergency, man-made risk, information system

In this article, we consider the system of quality management of legislation in the Russian Federation: we define its basic elements, the main tools for quality control (management) in the form of legal examinations, provide a generalized algorithm for quality assessment, propose a simple general classification of controlled factors in legal examinations, and introduce the concept of a bill readiness indicator. The most important legal examination - anti-corruption (ALE) - was chosen as an example for conducting quality control of legislation. Within the framework of general trends in automation, informatization, and digitalization, we considered the use of artificial intelligence (AI) for the purposes of conducting ALE, which, in some cases of "routine work", could provide all possible assistance to specialists in the field of legal examinations and their digitalization. In this regard, a step-by-step algorithm for pre-training AI was formulated using examples from regulatory legal acts (RLA) containing corruption factors (CF); a classification of CF was carried out; a scale of AI errors in detecting CF was developed; frequency characteristics of AI errors were determined; Preliminary conclusions were obtained on the possibility of using AI in AEC.

Keywords: artificial intelligence, corruption factor, anti-corruption expertise, normative legal act, corruption factor indicator, pre-training, algorithm, errors, frequency distribution, classification, dialogue.

The article describes the prerequisites for creating an electronic notification system for students in an educational institution. A use case diagram is provided that describes interaction with the system from the point of view of the user-employee of the educational department and the user-student. A diagram of the physical database model is presented and a description of the purpose of the tables is given. The system uses two types of client applications: an administrative client for organizing the work of educational department employees and a Telegram bot for working on the students’ side. A scheme for working with user data when processing chatbot commands is defined in the IDEF0 notation. The choice of the interlocutor program as a communication tool was made based on the popularity of this technology. The administrative client is implemented in C# using Windows Forms technology, the chatbot is implemented in Python using the “schedule” time planning library, “time” working with time and “threading” multi-threading support.

Keywords: chat bot, Telegram bot, messenger, message, mobile device, information system, database, computer program, application

The article is devoted to the design of a test automation system for the DBaaS Postgres Pro cloud database management manager. New approaches, concepts and definitions of the theory of test automation are formulated and old ones are updated. An analysis of modern tools widely used in commercial software development is carried out. The features of the system under test were studied, including the specifics of working with cloud computing and the Postgres DBMS. Based on the data obtained, an optimal technology stack was formed that is planned to be used in development, and functional requirements for the test automation system were developed. In practical terms, the use of this system on a DBaaS project will reduce labor intensity and speed up work at the testing and development stages, increase the efficiency of testing and the quality of the software product.

Keywords: software testing automation, DBaaS, cloud database, Postgres DBMS, GO programming language

The article is devoted to the development of automated information systems (AIS) for electronic document management in the educational field. Using the example of the process of accreditation monitoring of basic professional educational programs implemented in university departments, functional requirements, user algorithms and a prototype AIS (web system) for generating documents have been developed. The use of the considered AIS allows you to flexibly customize the structure of documents and data completion forms for accreditation monitoring, add and edit the required data about teachers in visual web interfaces, automatically generate documents based on information stored in the database, manage the life cycles of documents, evaluate the quality of the documents compiled. The labor intensity of working with documents is significantly simplified compared to existing business processes. The proposed approach can be applied to the development of document flow subsystems for various business processes of a university within the framework of educational, methodological, scientific and other types of activities of employees and, as a result, towards the creation of a unified AIS for electronic document management of the university, based on the integration of all subsystems. The described functionality and algorithms can be adapted to the creation of web systems for electronic document management of computer training complexes (CTC) for collecting and processing data on the progress of students, managing the life cycle of developing exercises for the CTC and performing them by trainees.

Keywords: automated information systems, electronic document management, information technologies in education, document life cycle, UML graphic notation

The problem of ensuring the safety of transportation activities is considered. The main components of the safety of transport activities in the context of management decisions are formulated. The causes of transport and environmental risks in relation to the stages of the vehicle life cycle are determined. Based on the analysis of the dynamics of traffic accidents caused by truck drivers, the theoretical dependence of the distribution of the random magnitude of accidents is determined. The influence of environmental factors on the mechanism of ensuring safety in the provision of transport services is considered. A model of the process of searching for an optimal management solution is presented, taking into account a limited number of criteria. It is recommended that the criteria include the probability of security risks depending on the source of the risk. The directions of improving the management decision-making system through the introduction of digitalization tools are formulated.

Keywords: transport process, vehicle, safety, risk, management decision, model of the process of finding the optimal management solution

The organization and management of infrastructure construction has a direct impact on the level of comfort of residents, safety in the city, and the efficiency of the functioning of the city economy. In this article, based on an integrated approach, various features of the development of road and transport infrastructure in large cities are studied under the condition of their expansion in the process of urbanization, where roads play a connecting role between individual areas of the city and neighboring settlements in the common single space of the agglomeration.

Keywords: road and transport infrastructure, sustainable development, urban space, agglomeration development, urban development

The article is devoted to the issue of making organizational and technological decisions when the stock of information for alternatives to choosing the required tasks is either very small, or they are changing drastically. Since it is not easy to make an organizational and technological business decision due to the fact that it is not clear what the result will be, it is proposed to use game theory in conditions of uncertainty. What kind of decision will be made and which of the available strategies the designer will adopt depends on what economic effect will be obtained as a result of the implementation of the organizational and technological solution being developed. Game theory is a special class of mathematical models for decision-making under specific conditions. By choosing solutions in the wake of uncertainty, game theory formalizes possible knowledge about the course of action of the participants in the game in certain conflict situations and allows you to mathematically substantiate knowledge about a rational course of action in certain conditions. When constructing construction projects in environmentally unfavorable conditions, the risk matrix is compared and the best option for the development of a construction project is determined.

Keywords: construction and technical expertise, reliability, organizational and technological solutions, diagnostic methods, efficiency.

The article analyses the current state of automated control systems for street lighting: advantages and disadvantages, problems faced by manufacturers and operators of such systems. The article describes the basic principles of automated control systems, such as the use of motion sensors, light sensors and communication technology to optimise the operation of street lighting. The article also discusses the features and problems of designing street lighting based on automated lighting control systems, and possible problems associated with their implementation and operation.

Keywords: lighting control, digital twin, automation, sensor, light sources, LED lighting fixture

This paper examines the problems and obstacles that arise during the implementation of investment projects in the field of capital construction, between the customer and the general contractor (a subsidiary of the customer). To solve the problems, it is proposed to develop specific measures to modernize the investment and construction activities of the customer company, in accordance with the economic development strategy adopted in Russia, based on digitalization. Information systems and technologies offer great opportunities for the development of various aspects of economic activity. One of them is information systems for managing investment projects. As a result of the work, the authors formulated the main directions of development and proposed solutions for modernizing the investment and construction activities of the customer company.

Keywords: investment and construction activities, investment project, industrial construction, customer, general contractor, information systems and technologies

A mathematical model for managing a commercial organization that specializes in the production and sale of asphalt and asphalt concrete is presented and analyzed in this paper. The study is based on mathematical modeling principles and management theory. An organized two-tier management system has been proposed, consisting of an asphalt manufacturer and its clients. The problem was considered numerically using various types of input data, and the company "FIRM PROFILE LLC" provided necessary information for calculations. The paper analyzes the results obtained and offers practical recommendations for improving the management of this enterprise.

Keywords: optimal management, mathematical modeling, simulation modeling, enterprise model, hierarchical system

The article considers one of the approaches to solving the problem of multi-criteria optimization with the choice of a balanced compromise option in the implementation of management activities in the territorial body of the Ministry of Internal Affairs of Russia on the basis of a comprehensive analysis of the current state of the operational situation in conditions of uncertainty and in the presence of existing restrictions and existing at the disposal of the subject of management of resource capabilities.. The emphasis is on the rational alignment of a set of mutually contradictory goals with the preferences of a person competent to make managerial decisions. It is shown how information on the relative importance of normalized values of vector estimates according to optimality criteria should be used to implement a reasonable narrowing of the achievable Pareto set and subsequent implementation of the best choice. The solution of the practical problem of vector optimization to determine the effectiveness of the use of forces and means of law enforcement agencies in detecting and suppressing crimes in public places is given.

Keywords: internal affairs bodies, law enforcement, operational environment, management decisions, management activities, multi-criteria optimization task, compromise in decision-making, Pareto set, decision support methods

The two level dynamic model is presented, representing the process of innovation implementation. The main task of this paper is conducting an analytical research of the model and different information regulations, designing solutions based on information regulations to find the best possible management of the subjects of the system. The system consists of several management entities (center, agents), the system is hierarchical. The Center manages the innovation process, agents promote innovations. But at the same time, agents have third-party income from activity that is not related to the promotion of innovations. The Pontryagin maximum principle is used for analytical research, the information regulations of the Hermeyer games G1, G2 are used. Numerical solutions are constructed, experiments are carried out, and the results are analyzed during the research.

Keywords: analytical research, Pontryagin's maximum principle, motivation, compulsion, Hermeyer games G1, G2, optimal management

The article examines methods for identifying semantic and formal management guidelines in monitoring the regulatory framework for ensuring fire safety in the Republic of Vietnam. The research includes in-depth semantic analysis, multi-level security parameters, the use of neural networks and innovative approaches to improve the effectiveness of the fire safety system at various levels. The work emphasizes the relevance of developing methods and tools for determining risk levels in the absence of clear numerical values of the accepted risk in legislation.

Keywords: in-depth semantic analysis, multi-level security parameters, neural networks, regulatory monitoring, fire safety, risk management, regulatory legislation, security innovations, fire inspectors, Republic of Vietnam

The article is devoted to the problem of optimizing the provision of resources in organizational systems, taking into account the factors of an aggressive external environment. The main task is to develop a model that will reduce costs when providing resources under various criteria and restrictions. The author proposes to use mathematical modeling to solve this problem. It examines various modeling and optimization approaches, including the use of linear and nonlinear functions, consideration of time and other parameters such as time, weather and possible risk. The article also discusses specific models of the external environment that can be used when calculating the effectiveness of the “Resource Provision - External Environment” system. In conclusion, the author suggests that the proposed approaches will help improve understanding of optimization processes and application of models in real-world settings.

Keywords: providing resources, mathematical modeling, optimization, risk management, organizational systems, external environment.

With the rapid development of technology and the widespread use of video surveillance, modeling the architecture of neural networks for human recognition in video is attracting increasing attention from researchers. This article presents a study of the use of neural networks (NN) as an interdisciplinary model for classifying objects in video, including solving the problem of face search. This highlights the versatility of neural networks in integrating trained data and accurately classifying objects, which is critical for ensuring security and efficiency of video surveillance. The study uses an analysis of various neural network architectures, as well as a study of their operating algorithms. Data obtained from a literature review and experimental results allow us to evaluate the effectiveness of solving the task of classifying objects in video using various architectures, without tying the study to a specific data set. The study confirms the possibility of using modern neural network architectures for human recognition in real-time video based on the experience of experts in the field of computer vision and machine learning. The active use of neural networks as a tool for video surveillance increases the safety of infrastructure facilities and the efficiency of security services. Ultimately, this article presents an analysis of neural network architectures for facial recognition in video streams, advocating their use as a key element in the development of modern video surveillance systems and ensuring public safety.

Keywords: neural networks, neural network architectures, video surveillance systems, real-time recognition, improving security, social well-being

The article discusses issues of theoretical substantiation of examination mechanisms using expert assessment methods to analyze the vulnerability of an important government facility. The article discusses the theoretical justification of the mechanisms of development examination for two cases. The first is taking into account the interest of experts in the results of the examination, when experts strive for a minimum discrepancy between their true assessment and the resulting expert assessment of the project. In the second case, they show interest in increasing their rating. For both cases, we define the objective functions of the experts and find the conditions for the existence of a Nash equilibrium situation.

Keywords: comprehensive security, methods, models, security forces, violators, important government facilities, expert assessment methods, vulnerability analysis

The proposed work considers two types of neural network models for describing fire risks depending on the size of the population and preventive measures. Neural network models make it possible to consider fire risks integrally, taking into account the type of municipality or separately for each of the three existing types. Based on these models, a response surface for fire risks - population and prevention has been implemented, which allows you to assess the magnitude of risks based on input data to optimize decisions made. For a given value of the standard risk, the dependence of optimal prevention was obtained depending on the number of deposits in the municipality, which makes it possible to guarantee fire risks less than or equal to the standard indicators. The article analyzes and evaluates the effectiveness of preventive measures using neural networks. The input data for training the neural network includes fire data collected in Vietnam and Russia (population, number of fires, number of deaths, number of preventive measures). Based on these indicators, the effectiveness of preventive measures is predicted. Based on the forecasting results, decisions can be made to ensure fire safety in the state. The results obtained indicate the possibility of predicting the absolute value of the effectiveness of preventive work based on quantitative and categorical variables. A relatively large forecast error is associated, on the one hand, with the need to take into account a larger number of input parameters, and on the other hand, with the need to increase the size of the neural network training base. After refining the model, the results obtained allow us to evaluate the effectiveness of preventive measures for provinces and cities.

Keywords: fire safety, preventive measures, neural network, management decision support, prediction model

The article discusses the issues of identifying and ranking threats at an important government facility. The classification of threats by type is described. The article discusses the concepts of “design-based threats” and “the most dangerous variant of the violator’s actions” and their differences. An example of ranking threats and reducing their number to reduce the dimensionality of the vulnerability analysis problem is considered. An important government object is considered as an object in the example. Experts are tasked with ranking threats according to the level of potential losses for an important government facility if they are realized. In practice, the implementation of an accepted design threat may lead to lower potential losses than the most dangerous option for violators and, as a result, to lower requirements for the effectiveness of the physical protection system.

Keywords: comprehensive security, methods, models, security forces, intruders, important government facilities, clashes between security forces and attacks, ranking of threats