All issues

Questions of construction of expert knowledge bases for creation of applied consulting and training systems in medicine are considered. Experience of construction of such bases and systems is described. Methods of construction of knowledge bases by a group of experts are offered.

The article presents updated technologies for solving two classes of linear resource allocation problems with dynamically changing characteristics of situational management systems and awareness of experts (and/or trained robots). The search for solutions is carried out in an interactive mode of computational experiment using updatable knowledge systems about problems considered as constructive objects (in accordance with the methodology of formalization of knowledge about programmable problems created in the theory of S-symbols). The technologies are focused on implementation in the form of Internet services. The first class includes resource allocation problems solved by the method of targeted solution movement. The second is the problems of allocating a single resource in hierarchical systems, taking into account the priorities of expense items, which can be solved (depending on the specified mandatory and orienting requirements for the solution) either by the interval method of allocation (with input data and result represented by numerical segments), or by the targeted solution movement method. The problem statements are determined by requirements for solutions and specifications of their applicability, which are set by an expert based on the results of the portraits of the target and achieved situations analysis. Unlike well-known methods for solving resource allocation problems as linear programming problems, the method of targeted solution movement is insensitive to small data changes and allows to find feasible solutions when the constraint system is incompatible. In single-resource allocation technologies, the segmented representation of data and results allows a more adequate (compared to a point representation) reflection of the state of system resource space and increases the practical applicability of solutions. The technologies discussed in the article are programmatically implemented and used to solve the problems of resource basement for decisions, budget design taking into account the priorities of expense items, etc. The technology of allocating a single resource is implemented in the form of an existing online cost planning service. The methodological consistency of the technologies is confirmed by the results of comparison with known technologies for solving the problems under consideration.

This paper investigates the effectiveness of Retrieval-Augmented Generation (RAG) combined with various Large Language Models (LLMs) for document retrieval and information access in corporate information systems. We survey typical use-cases of LLMs in enterprise environments, outline the RAG architecture, and discuss the major challenges that arise when integrating LLMs into a RAG pipeline. A system architecture is proposed that couples a text-vector encoder with an LLM. The encoder builds a vector database that indexes a library of corporate documents. For every user query, relevant contextual fragments are retrieved from this library via the FAISS engine and appended to the prompt given to the LLM. The LLM then generates an answer grounded in the supplied context. The overall structure and workflow of the proposed RAG solution are described in detail. To justify the choice of the generative component, we benchmark a set of widely used LLMs — ChatGPT, GigaChat, YandexGPT, Llama, Mistral, Qwen, and others — when employed as the answer-generation module. Using an expert-annotated test set of queries, we evaluate the accuracy, completeness, linguistic quality, and conciseness of the responses. Model-specific characteristics and average response latencies are analysed; the study highlights the significant influence of available GPU memory on the throughput of local LLM deployments. An overall ranking of the models is derived from an aggregated quality metric. The results confirm that the proposed RAG architecture provides efficient document retrieval and information delivery in corporate environments. Future research directions include richer context augmentation techniques and a transition toward agent-based LLM architectures. The paper concludes with practical recommendations on selecting an optimal RAG–LLM configuration to ensure fast and precise access to enterprise knowledge assets.

This article solves the problem of constructing a neuro-fuzzy model of fuzzy rules formation and using them for objects state evaluation in conditions of uncertainty. Traditional mathematical statistics or simulation modeling methods do not allow building adequate models of objects in the specified conditions. Therefore, at present, the solution of many problems is based on the use of intelligent modeling technologies applying fuzzy logic methods. The traditional approach of fuzzy systems construction is associated with an expert attraction need to formulate fuzzy rules and specify the membership functions used in them. To eliminate this drawback, the automation of fuzzy rules formation, based on the machine learning methods and algorithms, is relevant. One of the approaches to solve this problem is to build a fuzzy neural network and train it on the data characterizing the object under study. This approach implementation required fuzzy rules type choice, taking into account the processed data specificity. In addition, it required logical inference algorithm development on the rules of the selected type. The algorithm steps determine the number and functionality of layers in the fuzzy neural network structure. The fuzzy neural network training algorithm developed. After network training the formation fuzzyproduction rules system is carried out. Based on developed mathematical tool, a software package has been implemented. On its basis, studies to assess the classifying ability of the fuzzy rules being formed have been conducted using the data analysis example from the UCI Machine Learning Repository. The research results showed that the formed fuzzy rules classifying ability is not inferior in accuracy to other classification methods. In addition, the logic inference algorithm on fuzzy rules allows successful classification in the absence of a part of the initial data. In order to test, to solve the problem of assessing oil industry water lines state fuzzy rules were generated. Based on the 303 water lines initial data, the base of 342 fuzzy rules was formed. Their practical approbation has shown high efficiency in solving the problem.

Getting a qualified medical examination can be difficult for people in remote areas because medical staff available can either be inaccessible or it might lack expert knowledge at proper level. Telemedicine technologies can help in such situations. On one hand, such technologies allow highly qualified doctors to consult remotely, thereby increasing the quality of diagnosis and plan treatment. On the other hand, computer-aided analysis of the research results, anamnesis and information on similar cases assist medical staff in their routine activities and decision-making.

Creating telemedicine system for a particular domain is a laborious process. It’s not sufficient to pick proper medical experts and to fill the knowledge base of the analytical module. It’s also necessary to organize the entire infrastructure of the system to meet the requirements in terms of reliability, fault tolerance, protection of personal data and so on. Tools with reusable infrastructure elements, which are common to such systems, are able to decrease the amount of work needed for the development of telemedicine systems.

An interactive tool for creating distributed telemedicine systems is described in the article. A list of requirements for the systems is presented; structural solutions for meeting the requirements are suggested. A composition of such elements applicable for distributed systems is described in the article. A cardiac telemedicine system is described as a foundation of the tool