본문 바로가기
  • Home

A Technique for UML-based System Development Using Generative AI

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(12), pp.121-128
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : October 25, 2024
  • Accepted : November 28, 2024
  • Published : December 31, 2024

Eun-Sook Cho 1

1서일대학교

Accredited

ABSTRACT

Generative AI has been successfully applied across various domains such as healthcare, finance, and entertainment, offering transformative capabilities for complex tasks. In this paper, we propose a method for automating and optimizing UML-based software development using generative AI. The proposed method focuses on streamlining the development process by automating the generation of UML diagrams and improving model accuracy through AI-powered refinement. Key features include the ability to generate functional and structural UML models, such as use case, sequence, and class diagrams, directly from textual requirements with minimal manual intervention. The integration of generative AI reduces development time by 30% and error rates by 40% compared to traditional methods. Additionally, the approach supports iterative refinement, ensuring consistent and accurate models while minimizing redundant efforts. By leveraging AI for both analysis and design phases, the proposed method enhances efficiency and reliability in complex system development projects.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.