The article describes the possibilities, advantages and differences of machine learning systems without a teacher from template learning. The definition of clustering is also given, indicating the main methods and tasks solved by this machine learning algorithm. The algorithm for recognizing data from documents using OCR technology is described in detail, the goals and objectives of using OCR technology in the business processes of IT companies are formed. The following are tools for solving the problem of recognizing and clustering data from PDF document scans using the Nanonets and Tesseract machine learning libraries. In conclusion, this article describes the advantages and disadvantages of using these libraries in solving the problem of recognizing and clustering data from document scans.

Keywords: machine learning, clustering, data recognition, library Nanonets, library Tesseract

The algorithm and code listing of the developed self-learning chatbot are presented. Able to maintain a conversation with the user, switch to training mode in the absence of the necessary information, analyze the context of the conversation for "forbidden" words. The Trim function is used, which removes extraneous characters represented in the tr property. And also an additional option "Solve arithmetic problems" is implemented in case of a request from the user. When implementing the latter option, a recursive descent algorithm based on three nested recursive functions was used, while the binary tree is filled in. A function has been developed to divide the incoming string into tokens. The chatbot code is developed in C++/C# based on the principles of object-oriented programming with the development of classes.

Keywords: artificial intelligence, machine learning, voice assistant chatbot, learning mode, tokens, recursive descent, binary tree

The paper considers the process of repair and maintenance of server equipment used for the formation of departmental information infrastructure. The process of performing repair work on multiple servers is described using the theory of queuing. The problem of optimal reliability management of server equipment is formulated, taking into account the limitations on the resources used. The necessary optimality conditions for the problem in the form of the Pontryagin maximum principle are obtained. The boundary value problem of the maximum principle is given. In order to obtain an algorithm for constructing an approximate solution by gradient methods, the problem is reduced to a discrete optimal control problem, for which a wide range of numerical methods is available.

Keywords: information infrastructure, server equipment, reliability, optimal management, necessary conditions of optimality, the principle of maximum

The technological instructions of most converter steel casting shops of modern metallurgical enterprises contain instructions for cutting slabs into to length using a fixed length increase factor that is directly dependent on shrinkage. This does not take into account the chemical composition of steel and the temperature of cutting slabs into exact lengths. At the same time, experience shows that for steels of different grades there is a discrepancy between the planned and actual values of the slab length. This problem required the creation of a mathematical model that makes it possible to determine the values of the linear shrinkage of the slab from cutting to complete cooling. On the basis of this model, a method for calculating the coefficient of increase in the measured length (cutting coefficient) of a slab during cooling from a cutting temperature to 30°C was developed. With the help of the proposed technique, the reduction in the length of slabs of grades 09G2S, 08PS, 22GU was studied. The paper also shows that the dependence of the cutting coefficient on the carbon concentration and temperature before cutting is linear. It was found that the effect of carbon concentration on shrinkage is significantly manifested only at high cutting temperatures (1000-1100°C). On the basis of the dependence obtained, a technical solution is proposed for automating the workplace of the operator of a gas cutting machine (CCT) of the shop for casting converter steel of a modern metallurgical enterprise.

Keywords: shrinkage, slab, mathematical model, cutting coefficient, cutting, thermophysical properties

Background. The solution of design problems in the field of territorial systems management is based on the need for automated analysis of large arrays of geospatial data, including space imagery materials. The purpose of the article is to study and develop effective methods for the semantic segmentation of images containing geospatial data. Methods and materials. The paper studies and uses methods and algorithms for increasing the accuracy and speed of the neural network of the U-Net architecture. Results. Comprehensive studies have been carried out on configuring the U-Net convolutional neural network, in particular, image restoration by nearest neighbor interpolation, adding thinning layers to the architecture. Conclusions. The presented approaches for configuring the U-Net neural network made it possible to increase the accuracy of recognition by the Jaccard metric by 2-3% and increase the speed by 2 times.

Keywords: artificial neural networks, machine learning, deep learning, convolutional neural networks, u-net, semantic segmentation, pattern recognition, geospatial data

The article confirms the need for a systematic approach to the scientific justification of the electronic document management systems security(EDMS) and the relevance of the study, presents the results of the analysis of guidance documents regarding the development of mathematical models and existing experience, summarizes the procedure for the scientific justification of EDMS security, highlights the main trends in modeling today, a new approach to the construction of EDMS security models is proposed, defines its role and place in the existing theory and practice.

Keywords: Security models of computer systems, security policy, electronic document management system, systematic approach

Despite the existing differentiation of the regions of the Russian Federation in terms of natural and climatic conditions and the level of socio-economic development, the main principle of the state cadastral valuation is aimed at the uniformity of its implementation. The study in this paper is aimed at revealing the concept of "regional features" as a factor leading to a discrepancy in the methodology for determining the cadastral value of real estate at the regional level. The article highlights the factors of regional specifics that form the features of the appraisal work to determine the cadastral value of land plots in 2022 on the territory of St. Petersburg and the Perm Territory, as well as recommendations for improving the existing unified methodology.

Keywords: state cadastral valuation, mass valuation, taxation, cadastral value, market value, differentiation of regions, regional peculiarity, real estate object, land plot

The paper is devoted to the application of the simplex optimization algorithm in the field of magnetic measurements, namely in measuring the demagnetization curve of highly coercive magnetic materials. The algorithm has found its place in the implementation of a new method based on the full-scale model approach and the Gills-Atterton hysteresis model, the essence of which is also described in the work. It is expected that the new method will make it possible to more accurately determine the demagnetization curve of permanent magnets by using voltage meters instead of classical induction sensors, which will avoid the accumulation of error. The simplex optimization algorithm makes it possible to optimize the parameters of the Gills-Atterton model in such a way that the simulated mathematical model of a highly coercive magnetic material best corresponds to the measured magnetic material. The method is tested on a multiphysical model built in the COMSOL Multiphysics software package and includes calculations of an inductor and a permanent high-coercive magnet.

Keywords: permanent magnet, neodymium magnet, highly coercive material, magnetic material, Fourier-Bessel decomposition, approximation, momentum, optimization, simplex, Nelder-Mead algorithm, mathematical model, coercive force, hysteresis

Annotation: The possibility of quality assessing of paint coatings by using the products surface conditions analysis through the use of digital technologies is shown. In the conditions of industrial enterprise, the comparative analysis of АК-1301 and Tikkurila Metallista coatings condition, exposed to aggressive environments: water, gasoline is carried out. From digital images of the surface, adhesive strength and the porosity of the coatings before-and-after the effects of the environments were assessed. It is shown that АК-1301 enamel has the highest adhesive strength and chemical resistance to water and gasoline.

Keywords: paint coating, adhesion, surface porosity, corrosive environment, digital image, pixel

The work is devoted to the development of a new method for determining the demagnetization curve of high-coercive permanent magnets, for example, magnets made of NeFeB alloy. It is expected that the new method will make it possible to more accurately determine the demagnetization curve of permanent magnets by using voltage and current meters instead of class induction sensors, which will avoid the accumulation of error that occurs when integrating a signal from induction sensors. The paper describes in detail the algorithm of the new method for determining the demagnetization curve, provides references to the methods and algorithms used in the development of the new method. The method was tested on a multiphysical model of a permanent magnet and a magnetizing installation built in the COMSOL Multiphysics software package.

Keywords: permanent magnet, neodymium magnet, highly coercive material, magnetic material, Fourier-Bessel decomposition, approximation, momentum, optimization, simplex, Nelder-Mead algorithm, mathematical model, coercive force, hysteresis

The article considers a formalized data model of a software package for automating the accounting of the activities of an animal care center, which includes two subsystems: "Subsystem of information support for the activities of a shelter for homeless animals" and "Subsystem of automation of accounting for the activities of a hotel for animals". The formalized model allows you to structure the subject area, highlight the main components, their properties and relationships between them (customers, pets, aviaries, booking requests, volunteers, tasks, etc.), which was later used for algorithmization of the solution and software implementation of complex tools on the 1C:Enterprise platform.

Keywords: formalized model, animal shelter, homeless animals, hotel for animals, 1C:Enterprise, automation, activity accounting, animals, software package, information system

Classification plays a big role in the modern world. Text classification is used in solving many problems, such as: recognizing the emotional coloring of content, determining thematic affiliation, content. The article discusses various methods of text classification using machine learning, their advantages and disadvantages.

Keywords: text classification, machine learning, support vector machine, Bayes method, nearest neighbors method.

The article studies the relevance of online tutoring, considers various existing systems for organizing online tutoring, identifies their strengths and weaknesses, and identifies the most relevant functions of the considered services. The design of the architecture of the developed software product is considered. The goals for further research are defined.

Keywords: online tutoring, tutor, online learning, design patterns, application architecture, information system

The main content of the diversification of production as the activity of business entities is considered. manifested in the purchase of existing enterprises, organizations of new enterprises, this article proposes a method of using GIS to optimize the sewage system of critical areas. The nearby territory of the Volgograd Arena stadium was chosen as the site of work.

Keywords: ArcGIS, Storm and Sanitary Analysis, Civil 3D, Sewage.

The specifics of web-oriented information systems are considered, the stages of the life cycle are determined taking into account their specifics. The analysis of modern cloud Internet technologies providing storage, management and distributed shared access to information resources is carried out. Examples of cloud Internet services are presented, the capabilities of which can be used at the stage of planning and managing IS, design, development of the client and server parts, testing, and also supplemented with the functionality of Internet services for time management, presentation of results, data collection, work on documents, online communication at meetups. Conclusions are drawn about the possibility of creating a flexible space for joint work of a team of distributed developers.

Keywords: web-oriented information system, life cycle, life cycle model, planning, design, design, development, testing, cloud internet service, distributed team

English is an analytical language, so in English, the word order is important for understanding sentences and phrases. Practicing construpcting noun phrases with the correct order of adjective requires constant practice with feedback. As teachers' time for verifying assignments is limited, we propose to use a tutoring system, which can generate step-by-step feedback. It will help students develop the skill of arranging adjectives in the correct order.

Keywords: tutoring system, ontological modeling, natural language processing, English, adjective order, hypernyms, automated verification of the learners' answers

This article analyzes the problems of spatial, temporal and phase synchronization in non-cooperative passive bistatic radar coordinate meters, which make it difficult to detect weak objects. The method of time and phase synchronization based on the estimation of the parameters of the direct wave signal and the method of detecting weak objects, which consists of a long coherent accumulation of signal parameters, are investigated. A universal algorithm is proposed, which consists of two stages: extraction of direct wave pulses and parameter estimation. Based on the estimation of parameters and waveform, an algorithm for detecting weak targets based on the generalized Fourier transform is given.

Keywords: non-cooperative passive bistatic radar, algorithm, synchronization, pulse, generalized Fourier transform

In the presented work, a hybrid neural network is proposed, which combines quantum and classical computing, and is intended for use in image classification. The hybrid neural network is implemented on the basis of a classical convolutional neural network using a quantum circuit. Also, within the framework of this study, a comparison was made of various configurations of a hybrid neural network in which a different number of qubits were used. The hybrid neural network configurations were trained and tested on the CIFAR10 and CIFAR100 datasets. Comparison of the performance of a hybrid neural network for multiclass classification was carried out for a different number of classes (from 2 to 10) with the corresponding number of qubits (from 2 to 4). The results obtained during the experiments confirmed the possibility of using a hybrid neural network to solve the problem of multiclass classification.

Keywords: machine learning, deep learning, quantum machine learning, quantum computing, hybrid neural network, image classification, convolutional neural network, quantum circuit

The search for orthogonal and quasi-orthogonal matrices is considered as a sequence of setting initial conditions, choosing an implementation method, filtering a set of generated sequences. It is proposed to accelerate the search for matrices by pre-fixing their structure and filtering the generated sequences using the Fourier spectrum. Fixing the structure involves using the symmetry properties of the desired matrices. Filtering allows you to exclude sequences with explicit spectrum outliers when forming blocks of symmetric matrices.

Keywords: mining of matrices, Hadamard matrices, Propus conctruction, filtering sequences

The article analyzes the influence of an air cushion vehicle as a source of dust on the general and local picture of the dust situation in an industrial premises and assesses the significance of the increase in the concentration of dust particles in the dust and gas environment. A model for measuring the dustiness of the working area of industrial premises using a special set of high-frequency bandpass filters and a PC is proposed. Determination of dust content in industrial premises is carried out by the received spectrum of the acoustic signal, which is a "frequency portrait" of the concentration of dust particles in the dust and gas environment.

Keywords: industrial premises, transport vehicle, concentration of dust particles, measuring complex, ultrasonic signal, dustiness spectrogram

The piezoelectric element is one of the most popular electronic components in use, which are used as part of many electronic devices. These devices are very effectively used in medicine, education, construction, oil and gas industry, military equipment, metrology and many others. They are part of devices that provide diagnostics of various human organs, measurement of the flow of pumped liquids and gases that utilize mechanical energy of a person and vehicles for the purpose of its subsequent conversion into electrical energy. In order to obtain a piezoelectric effect, it is necessary to indicate certain effects on the crystal. Such effects include: application of excessive pressure; compression; stretching; torsion. The criteria that affect the effectiveness of multilayer piezoelectric converters are discussed below.

Keywords: piezoelectric effect, Piezoelectric elements, Matlab, technical characteristics, operational properties

The paper discusses the problem of building a unified system for a metallurgical enterprise that integrates heterogeneous information systems of various purposes, such as Computerized Information Systems (CIS), Manufacturing Execution Systems (MES), Enterprise Resource Planning (ERP), and Process Automation Systems (PAS). Data exchange with various automated systems of the enterprise is carried out by a special Data Exchange Module with Automated Systems of the Enterprise (DEMAS), which is implemented as a web service. DEMAS aims to ensure guaranteed information exchange between information systems and store information in a single data repository.

Keywords: information system, engineering process, metallurgical company, integration, web-service

This paper considers the modern classification methods of breast cancer histopathology. The main purpose of the study is to conduct an extended test of the trained model on data that fundamentally differs from the training dataset. We chose a large Russian dataset with different types of classification as the training dataset. The dataset contains images with different resolutions and magnifications. As testing data, the same dataset was used, but the resolution, color balance, brightness, and contrast of the images were changed. The classes in the dataset were unbalanced, so we applied augmentation methods (flipping and rotation). The models ResNet 152, DenseNet 121, Inception_resnet_v2 were selected for training. The transfer learning approach was used for training. The preprocessing of images consisted of normalizing the values of all image channels in the range from 0 to 1. The models had good results with standard testing methods. The resolution change slightly reduced metrics. The change in color balance, brightness, and contrast significantly reduced all metrics. The test results show that elementary normalization is not enough for high-quality training of models resistant to changes in input data.

Keywords: neural network, model, machine learning, breast cancer, cancer classification, artificial intelligence, transfer learning, histopathology

The article considers the practical part of the implementation of the task of determining the relevance of training directions, using the example of the direction "Applied Informatics", possible professions and companies for the employment of graduates by comparing the skills obtained in the framework of training and the requirements of the labor market. The results of the practical testing of the formalized model will be used as part of the module of digital tools for remote career guidance.

Keywords: service requests, vacancies, demand for training areas, career guidance, digitalization of career guidance activities, job search services

The objective of this study is to determine the patterns of development of new information technologies in the industry and formulate the main barriers to their introduction into project activities. The study of the issue was carried out on the basis of scientific publications of domestic and foreign researchers. The main theoretical methods are used: analysis, classification, analogy and synthesis. This article makes a comparative analysis of the use of modern technologies in European countries according to the "center-periphery" scheme and shows the similarities of information processes between Russia and European countries. The success of promoting innovative developments in the construction sector depends on: the presence of major players in the construction market, government support, the introduction of new educational standards, standardization of information modeling. The main obstacles are related to the compatibility of all processes in one digital space, legal and legal norms, issues of training and education.

Keywords: building information modeling, government order, BIM standardization, construction education, innovation, international experience