Anatolii O. Kurotych
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Anatolii O. Kurotych has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Lesia V. Bulatetska
Lesya Ukrainka Volyn National University
2 shared publications - Oksana Onyshchuk
Lesya Ukrainka Volyn National University
1 shared publication Анатолій Куротич
Волинський національний університет імені Лесі Українки
1 shared publicationЛеся Булатецька
Волинський національний університет імені Лесі Українки
1 shared publication
Latest Publications
- Open Access
- 26 September 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (29) , 152-160
RECONSTRUCTING ENTITY RELATIONSHIPS IN DATABASE SCHEMAS WITH PLANTUML AND LLMS
The article explores the potential of using Large Language Models (LLMs) for automatically restoring relationships between tables in SQL databases with incompletely defined foreign keys. To evaluate the ability of LLMs to infer foreign keys from textual descriptions of table structures, an experimental database was created. The database schema, excluding relationships, was provided as input to two large language models: ChatGPT-4o and Claude 3.7 Sonnet. For analysis purposes, only basic information was provided to the LLMs: table names, field names, and primary keys, without any data examples. The ChatGPT-4o model successfully detected all relationships between tables but demonstrated limitations in determining the types of these relationships: all were classified as “one-to-one”, regardless of their actual structure. This indicates the model's inability to accurately interpret the type of relationships based on textual descriptions. In contrast, the Claude 3.7 Sonnet model not only correctly identified all existing relationships, but also correctly determined their types (e.g., one-to-many), demonstrating higher accuracy and a deeper understanding of the database structure within the task at hand. The description of the table structure was provided to the language models in PlantUML format, ensuring a standardized, clear and unambiguous representation of the input data. Based on the modeling results, ER diagrams were also constructed in PlantUML format. The experiment confirms the effectiveness of LLMs in reconstructing missing foreign keys and shows potential for automated analysis, documentation, and improvement of existing databases. Following consistent naming conventions during schema design significantly simplifies both the work of developers and the automated processing of database structures by intelligent systems, playing a crucial role in these processes.
- 26 September 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (29) , 152-160
Open AccessRECONSTRUCTING ENTITY RELATIONSHIPS IN DATABASE SCHEMAS WITH PLANTUML AND LLMS
The article explores the potential of using Large Language Models (LLMs) for automatically restoring relationships between tables in SQL databases with incompletely defined foreign keys. To evaluate the ability of LLMs to infer foreign keys from textual descriptions of table structures, an experimental database was created. The database schema, excluding relationships, was provided as input to two large language models: ChatGPT-4o and Claude 3.7 Sonnet. For analysis purposes, only basic information was provided to the LLMs: table names, field names, and primary keys, without any data examples. The ChatGPT-4o model successfully detected all relationships between tables but demonstrated limitations in determining the types of these relationships: all were classified as “one-to-one”, regardless of their actual structure. This indicates the model's inability to accurately interpret the type of relationships based on textual descriptions. In contrast, the Claude 3.7 Sonnet model not only correctly identified all existing relationships, but also correctly determined their types (e.g., one-to-many), demonstrating higher accuracy and a deeper understanding of the database structure within the task at hand. The description of the table structure was provided to the language models in PlantUML format, ensuring a standardized, clear and unambiguous representation of the input data. Based on the modeling results, ER diagrams were also constructed in PlantUML format. The experiment confirms the effectiveness of LLMs in reconstructing missing foreign keys and shows potential for automated analysis, documentation, and improvement of existing databases. Following consistent naming conventions during schema design significantly simplifies both the work of developers and the automated processing of database structures by intelligent systems, playing a crucial role in these processes.
- 7 February 2025
- Published by Academy of Cognitive and Natural Sciences
Optimizing the process of ER diagram creation with PlantUML
Relational databases are widely used for storing and processing structured information, while their visualization is a key phase in the architectural design of information systems. One of the most popular tools for creating ERD is PlantUML, which implements the “diagram as code” approach for generating diagrams. This research analyzes PlantUML’s capabilities for building ERD and explores tools that improve the diagrams’ quality and automate their generation process. The shortcomings of PlantUML’s basic functionality for creating ERD are described. Additional PlantUML features are described, such as improving the appearance and readability of diagrams by highlighting primary and foreign keys, removing unnecessary elements, and creating legends for user convenience. A plugin module has been developed to enhance the readability of PlantUML code (hereafter referred to as ‘PUML code’) by structuring it into functions and procedures, making diagrams easier to create and maintain. The benefits of the modular approach include standardized styles and a minimized amount of PUML code. The article also introduces the Sqlant tool, which allows PUML code to be automatically generated from a PostgreSQL relational database. The PlantUML, combined with automation tools like Sqlant and a modular approach, is an effective tool for producing high-quality ERD. It can be particularly beneficial in environments where database structures undergo frequent changes. Despite the limitations of the official documentation, PlantUML has significant potential to extend its functionality.
- 7 February 2025
- Published by Academy of Cognitive and Natural Sciences
Optimizing the process of ER diagram creation with PlantUML
Relational databases are widely used for storing and processing structured information, while their visualization is a key phase in the architectural design of information systems. One of the most popular tools for creating ERD is PlantUML, which implements the “diagram as code” approach for generating diagrams. This research analyzes PlantUML’s capabilities for building ERD and explores tools that improve the diagrams’ quality and automate their generation process. The shortcomings of PlantUML’s basic functionality for creating ERD are described. Additional PlantUML features are described, such as improving the appearance and readability of diagrams by highlighting primary and foreign keys, removing unnecessary elements, and creating legends for user convenience. A plugin module has been developed to enhance the readability of PlantUML code (hereafter referred to as ‘PUML code’) by structuring it into functions and procedures, making diagrams easier to create and maintain. The benefits of the modular approach include standardized styles and a minimized amount of PUML code. The article also introduces the Sqlant tool, which allows PUML code to be automatically generated from a PostgreSQL relational database. The PlantUML, combined with automation tools like Sqlant and a modular approach, is an effective tool for producing high-quality ERD. It can be particularly beneficial in environments where database structures undergo frequent changes. Despite the limitations of the official documentation, PlantUML has significant potential to extend its functionality.