|
2021. No. 2 Vol. 15
|
|
7–20
|
This article presents a new approach to the development of a ‘digital twin’ of a manufacturing enterprise, using a television manufacturing plant as the case study. The feature of the proposed approach is the use of hybrid methods of agent-based modeling and discrete-event simulation in order to implement a simulation model of a complex production process for assembling final products from supplied components. The most important requirement for such a system is the integration of all key chains of a digital plant: conveyor lines, warehouses with components and final products (TVs), sorting and conveyor system, assembly unit, technical control department, packing unit, etc. The proposed simulation model is implemented in the AnyLogic system, which supports the possibility of using agent-based and discrete-event modeling methods within one model. The system also supports using the built-in genetic algorithm to optimize the main parameters of the model: the most important production characteristics (for example, assembly time of a product, the number of employees involved in assembly, quality control and packaging processes). Optimization experiments were completed with the help of the developed model at various intensities of loading conveyor lines with components, various restrictions on labor resources, etc. Three scenarios of the production system behavior are investigated: the absence of the components deficit with the possibility of significantly increasing the labor resource involved, a components deficit while demand for final products is maintained, and the presence of hard restrictions on the maximum number of employees who can be involved in the processes under conditions of components deficit.
|
|
21–33
|
Valuating the position of a controlled object using indicators which are management and control tools is widely used in many areas of the economy. Usually such indicators are based on internal data, however, as the volume of available open information grows, algorithms for valuation of the position of certain control objects and on open structured data are appearing. The disadvantage of these models is their narrow specialization and binding only to structured, and sometimes strictly official data, which, as a rule, have a rare publication frequency. This does not allow you to track the change in the position of the object at different times. The authors have proposed a concept for constructing a universal complex indicator (UCI) for express valuation of the position of a controlled object in various types of activity: banking, educational, industrial, etc. Another difference in the construction of the UCI is that the concept presented in the article assumes, as a reference point, to take into account the requirements of regulatory authorities, while in most Russian and foreign studies, indicators are built for the needs of investors. It is also proposed to use, along with structured and unstructured data, tracking the dynamics of changes in the position of the control object. To determine the UCI values on the basis of various econometric models and methods, the components that characterize the requirements of the control bodies to the control object are calculated; using them the UCI value is determined from the truth table. The concept proposed was tested to build an express valuation of the financial position of 108 banks for the period from 1 January 2018 to 1 February 2020. In accordance with the requirements of the Central Bank of the Russian Federation, the values of the three UCI components were obtained, and the value was calculated for each bank. The predictive ability of the constructed model, tested on three banks of the test sample, was confirmed by the consistency of the express valuation with their actual position in March 2020. |
|
34–46
|
The intensive development and application of artificial intelligence technologies in organizing interaction with clients is accompanied by such difficulties as: the client’s unwillingness to communicate with the robot, distrust, fear, negative experience of the clients. Such problems can be solved by adhering to ethical principles of using artificial intelligence. In scientific and practical research on this topic, there are many general recommendations that are difficult to apply in practice, or, on the contrary, that describe the methods for solving a highly specialized technical or management problem. The purpose of this article is to determine the ethical principles and methods, the observance and implementation of which would increase confidence in artificial intelligence systems among client of a particular organization. As a result of the analysis and synthesis of the scientific and practical investigations, as well as the empirical experience of Russian and foreign companies, the main areas of application of artificial intelligence technologies affecting the customer experience were identified. The ethical principles recommended to be followed by business have been formulated and systematized. The main methods have been also identified to enable implementation of these principles in practice, and so to reduce the negative effects of customer interaction with artificial intelligence and increase their confidence in the company. |
|
47–59
|
In the context of digitalization of the most knowledge-intensive sectors of the domestic economy, the development of an industrial training system in the field of electronic instrumentation is of great importance. The key areas of its development with the use of information and communication technologies include the development and improvement of the technological basis for training and retraining of personnel in engineering educational programs. One of the elements of this basis is the service of multi-user remote access via the internet to a high-tech experimental equipment laboratory as a service based on internet of things (IoT) systems. Within the framework of this service, an urgent problem is to increase the functional saturation of automated stands/installations, which is currently characterized by a paucity of scientific research. The purpose of the research is to expand the areas of experimental research carried out in the mode of multiuser remote access based on specialized IoT systems. As a result, a method of multidisciplinary application of specialized IoT systems was developed. This consists of the technical implementation of possibilities for additional research: research into technologies underlying both multi-user distributed measuring and control systems and IoT systems in general; research into technologies used in their end-to-end computer-aided design; research into joint interaction of several geographically distributed automated stands/installations, implemented on the basis of a four level IoT reference architecture. A methodology for the design of multi-user distributed measuring and control systems as specialized IoT systems has also been developed, focused on solving multidisciplinary research problems in an interactive dialogue mode based on single sample of experimental equipment. The methodology mobilizes organizational, technical and methodological support for the process of creating such systems with specified target characteristics. In general, the method and methodology developed open up opportunities for systematically implementing the basic principles of the “Education 4.0” concept in the preparation and retraining of engineering personnel in the field of electronic instrumentation. |
|
60–74
|
This article considers the problem of finding text documents similar in meaning in the corpus. We investigate a problem arising when developing applied intelligent information systems that is non-detection of a part of solutions by the TF-IDF algorithm: one can lose some document pairs that are similar according to human assessment, but receive a low similarity assessment from the program. A modification of the algorithm, with the replacement of the complete vocabulary with a vocabulary of specific terms is proposed. The addition of thesauri when building a corpus vector model based on a ranking function has not been previously investigated; the use of thesauri has so far been studied only to improve topic models. The purpose of this work is to improve the quality of the solution by minimizing the loss of its significant part and not adding “false similar” pairs of documents. The improvement is provided by the use of a vocabulary of specific terms extracted from the text of the analyzed documents when calculating the TF-IDF values for corpus vector representation. The experiment was carried out on two corpora of structured normative and technical documents united by a subject: state standards related to information technology and to the field of railways. The glossary of specific terms was compiled by automatic analysis of the text of the documents under consideration, and rule-based NER methods were used. It was demonstrated that the calculation of TF-IDF based on the terminology vocabulary gives more relevant results for the problem under study, which confirmed the hypothesis put forward. The proposed method is less dependent on the shortcomings of the text layer (such as recognition errors) than the calculation of the documents’ proximity using the complete vocabulary of the corpus. We determined the factors that can affect the quality of the decision: the way of compiling a terminology vocabulary, the choice of the range of n-grams for the vocabulary, the correctness of the wording of specific terms and the validity of their inclusion in the glossary of the document. The findings can be used to solve applied problems related to the search for documents that are close in meaning, such as semantic search, taking into account the subject area, corporate search in multi-user mode, detection of hidden plagiarism, identification of contradictions in a collection of documents, determination of novelty in documents when building a knowledge base. |
|
75–90
|
All organizations have been affected by the coronavirus pandemic in different ways. Small and medium-sized enterprises (SMEs) are more vulnerable to changes due to their limited resources. However, the capabilities of information technologies and processes of knowledge management can assist these enterprises to survive and respond appropriately to changes. Thus, this study aims to assess the extent to which information technology capabilities influence the responsiveness of SMEs to challenges that have emerged during the coronavirus crisis. It also investigates the degree to which knowledge management affects such a relationship in the context of Saudi Arabia. The study includes developing a survey as a data collection method. The responses from 136 SMEs were used to make an analysis and, consequently, draw a conclusion. It has been found that IT capabilities positively influence SMEs’ responsiveness to changes brought by coronavirus, through supporting work flexibility and providing a wide range of options in the supply chain, processes, and sales. It further found that knowledge management mediates the relationship between IT capabilities and SMEs’ responsiveness.
|
|
|