Alexander A. Zuenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alexander A. Zuenko has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Olga N. Zuenko
Putilov Institute for Informatics and Mathematical Modeling of the Kola Science Centre of the Russian Academy of Sciences
7 shared publications - Aleksey V. Shestakov
Putilov Institute for Informatics and Mathematical Modeling of the Kola Science Centre of the Russian Academy of Sciences
6 shared publications - Yurii Oleynik
Putilov Institute for Informatics and Mathematical Modeling of the Kola Science Centre of the Russian Academy of Sciences
6 shared publications - Olga V. Fridman
Putilov Institute for Informatics and Mathematical Modeling of the Kola Science Centre of the Russian Academy of Sciences
5 shared publications Putilov Institute for Informatics and Mathematical Modeling of the Kola Science Centre of the Russian Academy of Sciences
5 shared publications- Roman A. Makedonov2 shared publications
Latest Publications
- 6 May 2026
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 17 (1) , 129-142
OPPORTUNITIES FOR INTELLIGENTIZATION OF THE FRC KSC RAS WEBSITE
The article presents the initial stages of developing an intelligent information retrieval system on the website of the FRC KSC RAS, based on the use of large language models, ontological and prompt-engineering, and RAG-technology. The system is aimed at increasing the relevance of responses to user queries formulated in the dialogue process in natural language and related to the website content, as well as to the electronic repository of documents of the FRC KSC RAS. The system architecture has been designed, and a prototype has been developed that implements some of the proposed features of intelligent retrieval. The use of RAG-technology allows for analysis of current context without the need to retrain a large language model, which is especially important in situations where information on a website can be added and modified ad hoc. For some query types, specialized prompts have been developed to allow you to formulate an answer that corresponds to the specific of the query. In order to prevent the transfer of confidential information to external services, it was decided to deploy the software system locally on the server of the IIMM KSC RAS. The experiments carried out demonstrated the feasibility of the proposed solutions for the considered tasks of intelligent retrieval.
- 6 May 2026
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 17 (1) , 129-142
OPPORTUNITIES FOR INTELLIGENTIZATION OF THE FRC KSC RAS WEBSITE
The article presents the initial stages of developing an intelligent information retrieval system on the website of the FRC KSC RAS, based on the use of large language models, ontological and prompt-engineering, and RAG-technology. The system is aimed at increasing the relevance of responses to user queries formulated in the dialogue process in natural language and related to the website content, as well as to the electronic repository of documents of the FRC KSC RAS. The system architecture has been designed, and a prototype has been developed that implements some of the proposed features of intelligent retrieval. The use of RAG-technology allows for analysis of current context without the need to retrain a large language model, which is especially important in situations where information on a website can be added and modified ad hoc. For some query types, specialized prompts have been developed to allow you to formulate an answer that corresponds to the specific of the query. In order to prevent the transfer of confidential information to external services, it was decided to deploy the software system locally on the server of the IIMM KSC RAS. The experiments carried out demonstrated the feasibility of the proposed solutions for the considered tasks of intelligent retrieval.
- 25 December 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 16 (3) , 56-70
APPLICATION OF RAG TECHNOLOGY FOR AUTOMATED TEST GENERATION AND KNOWLEDGE ASSESSMENT WITH NATURAL LANGUAGE DIALOGUE SUPPORT
This study explores the application of Retrieval-Augmented Generation (RAG) technology for the automated generation of tests and adaptive knowledge assessment, supported by natural language dialogue. An analysis of similar research support systems for question generation is conducted. The paper presents the overall system architecture and provides a detailed examination of its core components: the question generation subsystem and the adaptive testing engine. The implementation specifics of the test question generation module and the dynamic task selection mechanism based on user responses are described. The results of testing are presented, followed by conclusions regarding the system's practical applicability.
- 25 December 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 16 (3) , 56-70
APPLICATION OF RAG TECHNOLOGY FOR AUTOMATED TEST GENERATION AND KNOWLEDGE ASSESSMENT WITH NATURAL LANGUAGE DIALOGUE SUPPORT
This study explores the application of Retrieval-Augmented Generation (RAG) technology for the automated generation of tests and adaptive knowledge assessment, supported by natural language dialogue. An analysis of similar research support systems for question generation is conducted. The paper presents the overall system architecture and provides a detailed examination of its core components: the question generation subsystem and the adaptive testing engine. The implementation specifics of the test question generation module and the dynamic task selection mechanism based on user responses are described. The results of testing are presented, followed by conclusions regarding the system's practical applicability.
- 25 December 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 16 (3) , 117-130
SOLVING GENERATIVE DESIGN PROBLEMS USING CONSTRAINT SATISFACTION METHODS
The paper is devoted to the consideration of methods for solving the generative design problems. Traditionally such problems are solved using a neural network approach. In the study, it is proposed to represent the problem of generative design as a constraint satisfaction problem and solving it using constraint programming technology. The proposed approach is illustrated by the example of the problem of two-dimensional spatial scena design, taking into account the heterogeneous requirements for the relative location of objects.
- 25 December 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 16 (3) , 117-130
SOLVING GENERATIVE DESIGN PROBLEMS USING CONSTRAINT SATISFACTION METHODS
The paper is devoted to the consideration of methods for solving the generative design problems. Traditionally such problems are solved using a neural network approach. In the study, it is proposed to represent the problem of generative design as a constraint satisfaction problem and solving it using constraint programming technology. The proposed approach is illustrated by the example of the problem of two-dimensional spatial scena design, taking into account the heterogeneous requirements for the relative location of objects.
- 19 December 2025
- Published by Springer Nature
- p. 77-92
Constraint Satisfaction Methods in Mining Planning
- 19 December 2025
- Published by Springer Nature
- p. 77-92
Constraint Satisfaction Methods in Mining Planning
- Open Access
- 27 January 2025
- Published by Voronezh State University in Вестник ВГУ. Серия: Системный анализ и информационные технологии
- No. 4,p. 116-128
Применение методов удовлетворения табличных ограничений для моделирования рассуждений типа ДСМ
Статья продолжает серию работ, посвященных тематике интеллектуального анализа данных с применением методов вывода на табличных ограничениях. Ранее были представлены авторские методы кластеризации, выявления паттернов требуемого вида, поиска ассоциативных правил. Разработанные методы относятся к методам объяснимого (интерпретируемого) искусственного интеллекта. Недостатки большинства существующих методов интеллектуального анализа данных связаны, в первую очередь, с трудностями гибкого учета и анализа знаний экспертов предметной области, пользовательских ограничений. Обычно для учета каждого типа подобных ограничений требуется довольно трудоемкая модификация базовых методов обучения. В статье развивается подход на основе парадигмы программирования в ограничениях, который свободен от упомянутых недостатков и позволяет гибко организовывать учет и анализ дополнительных условий задачи интеллектуального анализа данных без принципиального изменения схемы её решения. Оригинальность авторского подхода состоит в том, что для представления обучающей выборки предложено использовать особый тип табличных ограничений — сжатые таблицы D-типа, а сами задачи интеллектуального анализа данных предложено решать как задачи удовлетворения табличных ограничений с применением оригинального способа ветвления дерева поиска и авторских правил редукции сжатых таблиц. В представленной работе на примере решения задач бинарной классификации впервые рассматриваются возможности применения авторского подхода для моделирования рассуждений типа ДСМ. В статье рассматривается случай, когда свойства объектов являются атомарными, не имеют внутренней структуры. Задачу генерации ДСМ-гипотез предлагается сводить к поиску частых замкнутых паттернов, причем каждый из паттернов не должен входить как фрагмент во множество контрпримеров. В рамках предлагаемого в статье подхода добавление в задачу дополнительных типов ограничений не только не снижает производительность методов их решения, но и способствует более глубокой редукции пространства поиска за счет применения специализированных методов логического вывода для каждого из типов ограничений.
- 27 January 2025
- Published by Voronezh State University in Вестник ВГУ. Серия: Системный анализ и информационные технологии
- No. 4,p. 116-128
Open AccessПрименение методов удовлетворения табличных ограничений для моделирования рассуждений типа ДСМ
Статья продолжает серию работ, посвященных тематике интеллектуального анализа данных с применением методов вывода на табличных ограничениях. Ранее были представлены авторские методы кластеризации, выявления паттернов требуемого вида, поиска ассоциативных правил. Разработанные методы относятся к методам объяснимого (интерпретируемого) искусственного интеллекта. Недостатки большинства существующих методов интеллектуального анализа данных связаны, в первую очередь, с трудностями гибкого учета и анализа знаний экспертов предметной области, пользовательских ограничений. Обычно для учета каждого типа подобных ограничений требуется довольно трудоемкая модификация базовых методов обучения. В статье развивается подход на основе парадигмы программирования в ограничениях, который свободен от упомянутых недостатков и позволяет гибко организовывать учет и анализ дополнительных условий задачи интеллектуального анализа данных без принципиального изменения схемы её решения. Оригинальность авторского подхода состоит в том, что для представления обучающей выборки предложено использовать особый тип табличных ограничений — сжатые таблицы D-типа, а сами задачи интеллектуального анализа данных предложено решать как задачи удовлетворения табличных ограничений с применением оригинального способа ветвления дерева поиска и авторских правил редукции сжатых таблиц. В представленной работе на примере решения задач бинарной классификации впервые рассматриваются возможности применения авторского подхода для моделирования рассуждений типа ДСМ. В статье рассматривается случай, когда свойства объектов являются атомарными, не имеют внутренней структуры. Задачу генерации ДСМ-гипотез предлагается сводить к поиску частых замкнутых паттернов, причем каждый из паттернов не должен входить как фрагмент во множество контрпримеров. В рамках предлагаемого в статье подхода добавление в задачу дополнительных типов ограничений не только не снижает производительность методов их решения, но и способствует более глубокой редукции пространства поиска за счет применения специализированных методов логического вывода для каждого из типов ограничений.
- 10 January 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 5-26
USING RAG TECHNOLOGY TO DESIGN AN INTELLIGENT INFORMATION SYSTEM FOR SUPPORT EXPLORATORY SEARCH
This paper presents the integration of a large language model (LLM) into an intelligent information and analytical system for exploratory search support within specific texts. An overview of the capabilities of modern large language models is provided. Special attention is paid to the Retrieval Augmented Generation (RAG) technology used for efficient formation and control of search contexts. The design and development of the system's business logic functions and user interface elements are detailed. Experimental results applying the developed system to texts with specific characteristics are presented. Conclusions are drawn regarding the system's applicability for automating ontology population. Conclusions are drawn regarding the system's applicability for automating the process of populating ontologies, as well as filling other knowledge repositories built using automated monitoring of open big data and intelligent data processing.
- 10 January 2025
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 5-26
USING RAG TECHNOLOGY TO DESIGN AN INTELLIGENT INFORMATION SYSTEM FOR SUPPORT EXPLORATORY SEARCH
This paper presents the integration of a large language model (LLM) into an intelligent information and analytical system for exploratory search support within specific texts. An overview of the capabilities of modern large language models is provided. Special attention is paid to the Retrieval Augmented Generation (RAG) technology used for efficient formation and control of search contexts. The design and development of the system's business logic functions and user interface elements are detailed. Experimental results applying the developed system to texts with specific characteristics are presented. Conclusions are drawn regarding the system's applicability for automating ontology population. Conclusions are drawn regarding the system's applicability for automating the process of populating ontologies, as well as filling other knowledge repositories built using automated monitoring of open big data and intelligent data processing.
- 28 December 2024
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 61-68
SOLVING VEHICLE ROUTING PROBLEMS IN THE FRAMEWORK OF THE CONSTRAINT PROGRAMMING PARADIGM
The article is devoted to an analytical survey of the possibilities of solving vehicle routing problems within the framework of the constraint programming paradigm. First, the article provides an overview of the various formulations of the vehicle routing problem. Then, to facilitate understanding, these statements are formulated in the language of integer linear programming. After that, a description of the constraint programming technology is given and typical global constraints are given that are useful in various formulations of the vehicle routing problem. It is concluded that flexibility in the formulation of constraints, the possibility of integration with other optimization methods, as well as the ability to take into account uncertainties make programming in constraints one of the most popular tools for solving vehicle routing problems.
- 28 December 2024
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 61-68
SOLVING VEHICLE ROUTING PROBLEMS IN THE FRAMEWORK OF THE CONSTRAINT PROGRAMMING PARADIGM
The article is devoted to an analytical survey of the possibilities of solving vehicle routing problems within the framework of the constraint programming paradigm. First, the article provides an overview of the various formulations of the vehicle routing problem. Then, to facilitate understanding, these statements are formulated in the language of integer linear programming. After that, a description of the constraint programming technology is given and typical global constraints are given that are useful in various formulations of the vehicle routing problem. It is concluded that flexibility in the formulation of constraints, the possibility of integration with other optimization methods, as well as the ability to take into account uncertainties make programming in constraints one of the most popular tools for solving vehicle routing problems.
- 28 December 2024
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 82-96
SURVEY OF FRIEQUENT PATTERN SEARCH METHODS FOR DATA MINING
The article discusses one of the promlems of data mining, namely: the problem of searching for a special type of data dependencies - frequent patterns. Associative rules between features can be built on the basis of frequent patterns. A survey of the most popular methods for solving this problem is provided. The closely related problem of generating formal concepts based on a formal context is also considered, and one of the methods for solving it — the "close-by-one" method. The disadvantages of the considered methods include the complexity of their modification in the presence of additional (in addition to the frequency of occurrence in the training sample) requirements for the desired pattern. It is concluded that it is necessary to develop existing methods of pattern discovery, as well as the expediency of developing new approaches to solve the problems of searching for "interesting patterns", as well as searching for patterns with additional requirements for their type.
- 28 December 2024
- Published by Kola Science Centre in Transaction Kola Science Centre
- Vol. 15 (3) , 82-96
SURVEY OF FRIEQUENT PATTERN SEARCH METHODS FOR DATA MINING
The article discusses one of the promlems of data mining, namely: the problem of searching for a special type of data dependencies - frequent patterns. Associative rules between features can be built on the basis of frequent patterns. A survey of the most popular methods for solving this problem is provided. The closely related problem of generating formal concepts based on a formal context is also considered, and one of the methods for solving it — the "close-by-one" method. The disadvantages of the considered methods include the complexity of their modification in the presence of additional (in addition to the frequency of occurrence in the training sample) requirements for the desired pattern. It is concluded that it is necessary to develop existing methods of pattern discovery, as well as the expediency of developing new approaches to solve the problems of searching for "interesting patterns", as well as searching for patterns with additional requirements for their type.
- 20 December 2024
- Published by Springer Nature
- p. 196-206
Generating Hypotheses Based on the Table Constraint Satisfaction Methods in JSM-Systems
- 20 December 2024
- Published by Springer Nature
- p. 196-206
Generating Hypotheses Based on the Table Constraint Satisfaction Methods in JSM-Systems
- Open Access
- 14 November 2024
- Published by Samara National Research University in Ontology of Designing
- Vol. 14 (3)
Clustering using table constraint satisfaction methods
The research focuses on developing cluster analysis methods, specifically clustering methods with partial teacher involvement, where background knowledge from the subject area is used when assigning objects to classes. The traditional approach to this problem involves modifying existing clustering methods, most of which are local search methods. The article proposes a systematic approach to searching for optimal partitions within the constraint programming paradigm. The originality of this research lies in solving the clustering problem as a constraint satisfaction problem, utilizing specialized table constraints, known as D-type smart tables, to model basic and additional conditions. Table constraint reduction rules are employed to organize logical inference procedures on D-type smart tables. The advantages of this approach are discussed, demonstrating how analyzing one of the optimal solutions can help identify objects on the boundary of clusters and those belonging to the same cluster for any optimal partition.
- 14 November 2024
- Published by Samara National Research University in Ontology of Designing
- Vol. 14 (3)
Open AccessClustering using table constraint satisfaction methods
The research focuses on developing cluster analysis methods, specifically clustering methods with partial teacher involvement, where background knowledge from the subject area is used when assigning objects to classes. The traditional approach to this problem involves modifying existing clustering methods, most of which are local search methods. The article proposes a systematic approach to searching for optimal partitions within the constraint programming paradigm. The originality of this research lies in solving the clustering problem as a constraint satisfaction problem, utilizing specialized table constraints, known as D-type smart tables, to model basic and additional conditions. Table constraint reduction rules are employed to organize logical inference procedures on D-type smart tables. The advantages of this approach are discussed, demonstrating how analyzing one of the optimal solutions can help identify objects on the boundary of clusters and those belonging to the same cluster for any optimal partition.