http://bijournal.hse.ru en-us Copyright 2024 Tue, 26 Mar 2024 13:09:30 +0300 https://bijournal.hse.ru/en/2024--1 Vol.18/908872935.html       This article is devoted to the development of methods for creating intelligent assistants. Intelligent assistants can be used in call centers to solve customer problems, to solve technical support tasks, to help people with disabilities, to help in choosing goods, etc. We consider intelligent assistants that engage in argumentative dialogue with users, aimed at finding goods and services that maximally satisfy users’ wants and needs. The development of the intelligent assistant is based on a four-level model of the subject domain and a semantic model of the user. The system under development automates the process of search and decision justification through the reuse of domain cases: accumulated knowledge about previous dialogues with users. This gives the system we developed an advantage over existing analogues, which are incapable of reusing knowledge about previous dialogues. The paper develops a case-based approach to building an intelligent system capable of reasoning about its responses. For this purpose, an argumentation graph is constructed, methods for structuring domain cases are developed, and ontological homomorphisms are used to transform the available domain cases into a finished solution. A description of model-theoretical methods for constructing intelligent assistants is presented. The cases of goods, users and dialogues of an intelligent assistant with users are formally described in the form of partial models. The transformation of domain cases and similarity of cases are formalized using ontological homomorphisms of partial models. The purpose of the developed dialogue system is not only to select a solution according to the user’s request, but also to find out the tasks that the user is going to solve, to analyze his argumentation, and then to justify the proposed solution to the user, to show that this particular product or service will be able to meet his needs. https://bijournal.hse.ru/en/2024--1 Vol.18/908893356.html       Currently the portrayal of the procedure for developing management actions during the planning process in the scientific and professional community does not align with the practice of systematic and consistent plan creation supported by an informational analytical system. Alternatively, the non-formalized decision-making activity of the planner, which involves a situational expert approach, becomes a dependency in the planning process. This study is aimed at developing an analytical approach for implementing the plan reconciliation procedure in the process of corporate performance planning. This will increase the utilization of capabilities of the corporate performance management system and formalize the task of generating managerial actions by adjusting targeted budgeting values using mathematical methods. For this purpose, the standard planning process is enhanced by analytical support units, including the algorithm of inverse calculations of individual key performance indicators (KPI) and an advanced module for scenario modeling. The improved model of target budgeting process presented here delivers automated formation of management actions of the budgeting department and subdivision management, guided towards accomplishing strategic goals. The application of inverse calculations provides a mathematical formulation of the task of calculating indicators of planned key values, and the Sense and Respond (SaR) system allows you to supplement the mathematical formulation with weighting coefficients of key performance indicators calculated algorithmically, relying on the manager’s decisions rather than expert evaluation. The implementation of the approach we developed will improve the quality of planning by the highest priority criteria of operability, accuracy and adaptability due to the consistency and methodology of budgeting with the use of modern information technology. https://bijournal.hse.ru/en/2024--1 Vol.18/908894197.html       This paper presents a developed agent-based simulation model for the development of research-and-production clusters in Russia implemented with the use of high-tech enterprises located in four science cities (Troitsk, Obninsk, Pushchino and Protvino) as the case study. A new approach to modeling and optimization of gross metropolitan product (GMP) is proposed, taking into account the influence of the “gravity effect” on the redistribution of labor resources between developing science cities and appropriate enterprises united in single research and research-and-production clusters An important element of this approach is the formation of various scenarios for the strategic development of the research-and-production clusters being assessed and support for the possibility of choosing the most preferable scenario using an evolutionary optimization algorithm. An enlarged simulation model has been developed and implemented in AnyLogic describing the possible development trajectories of science cities with a corresponding change in the values ​​of the most important characteristics: the number of economically active population, the number of research-and-production enterprises, the volume of products produced in high-tech sectors of the economy, GMP, etc. The designed framework is intended primarily for the management of research-and-production clusters implementing the strategy of innovative development. Such a framework uses methods of system dynamics and agent-based simulation modeling supported in the AnyLogic system, genetic optimization algorithms and GIS mapping for science cities, etc. to implement the required functionality. The approbation of the framework was completed with the use of real data published in the approved strategies of the relevant science cities development. As a result of the numerical experiments carried out, some recommendations were proposed for the development of the research-and-production clusters under study considering their mutual influence and the existing base of resources. https://bijournal.hse.ru/en/2024--1 Vol.18/908895665.html       To solve the problem of comparative efficiency analysis of branch operations for a small volume of randomly observed data, a non-parametric approach is relevant, since it does not require a probabilistic model of observations. Comparing the results of the non-parametric approach with the results obtained within the traditionally used Gaussian model is also relevant. Additionally, obtaining a consistent comparison of a group (of no less than three) branches is important. Currently, the non-parametric approach and the corresponding comparison with the known results of solving the problem considered in this work obtained within the framework of the normal model are absent. In addition, insufficient attention is paid to the search for methods of obtaining consistent solutions. This work to some extent fills these gaps. This work uses non-parametric statistical methods and theory of simultaneous hypothesis testing to address these problems. This paper proposes a procedure for comparative analysis of the efficiency of several units within a network organization with a small volume of observations based on the Mann–Whitney tests. We carry out a comparison of the results obtained from the proposed non-parametric procedure with results based on extensions of Student’s t-tests. We propose a method for reducing the number of compatibility problems based on the search for an appropriate significance level. We provide an example of a fully consistent comparison of the efficiency of branch operations. https://bijournal.hse.ru/en/2024--1 Vol.18/908898714.html       The aim of this study was to examine the determinants of the continuance intention with respect to use of the Audit Tools and Linked Archives System (ATLAS) by employing survey methods. These determinants are developed from an Expectation Confirmation Model (ECM). The sample of this study is auditors who use ATLAS in public accounting firms in Indonesia. As many as 356 data points can be processed using smartPLS. This study revealed that perceived usefulness, confirmation, information quality, top management commitment and satisfaction affected the auditor’s intentions when using ATLAS. The implications of this study are (1) Public accounting firms must provide full support to auditors in using ATLAS and equip auditors through training so auditors understand that using ATLAS is very useful; (2) IAPI must pay attention to outputs that are complete, good and appropriate so that the auditor is satisfied when using ATLAS. The auditor has a tendency to continue using ATLAS if he is satisfied. https://bijournal.hse.ru/en/2024--1 Vol.18/908905484.html       This paper presents the task of recognizing product information (PI) (i.e., product names, prices, materials, etc.) mentioned in customer statements. This is one of the key components in developing artificial intelligence products to enable businesses to listen to their customers, adapt to market dynamics, continuously improve their products and services, and improve customer engagement by enhancing effectiveness of a chatbot. To this end, natural language processing (NLP) tools are commonly used to formulate the task as a traditional sequence labeling problem. However, in this paper, we bring the power of machine reading comprehension (MRC) tasks to propose another, alternative approach. In this setting, determining product information types is the same as asking “Which PI types are referenced in the statement?” For example, extracting product names (which corresponds to the label PRO_NAME) is cast as retrieving answer spans to the question “Which instances of product names are mentioned here?” We perform extensive experiments on a Vietnamese public dataset. The experimental results show the robustness of the proposed alternative method. It boosts the performance of the recognition model over the two robust baselines, giving a significant improvement. We achieved 92.87% in the F1 score on recognizing product descriptions at Level 1. At Level 2, the model yielded 93.34% in the F1 score on recognizing each product information type.