International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Best Practice on Automatic Toon Image Creation from JSON File of Message Sequence Diagram via Natural Language based Requirement Specifications

  • Hyuntae Kim (Dept. of Software and Communication Engineering, Hongik University) ;
  • Ji Hoon Kong (Dept. of Software and Communication Engineering, Hongik University (Toonsquare)) ;
  • Hyun Seung Son (Dept. of Computer Engineering, Mokpo National University) ;
  • R. Young Chul Kim (Dept. of Software and Communication Engineering, Hongik University)
  • Received : 2024.01.24
  • Accepted : 2024.02.08
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In AI image generation tools, most general users must use an effective prompt to craft queries or statements to elicit the desired response (image, result) from the AI model. But we are software engineers who focus on software processes. At the process's early stage, we use informal and formal requirement specifications. At this time, we adapt the natural language approach into requirement engineering and toon engineering. Most Generative AI tools do not produce the same image in the same query. The reason is that the same data asset is not used for the same query. To solve this problem, we intend to use informal requirement engineering and linguistics to create a toon. Therefore, we propose a sequence diagram and image generation mechanism by analyzing and applying key objects and attributes as an informal natural language requirement analysis. Identify morpheme and semantic roles by analyzing natural language through linguistic methods. Based on the analysis results, a sequence diagram and an image are generated through the diagram. We expect consistent image generation using the same image element asset through the proposed mechanism.

Keywords

Acknowledgement

This study was conducted with the support of the Korea Creative Content Agency (Task Name: Artificial Intelligence-based User Interactive Storytelling 3D Scene Authoring Technology Development, Task Number: RS-2023-00227917, Contribution Rate: 70%) and the Basic Research Project of the Korea Research Foundation (Task Name: Non-defective Research through automatic refactoring based on the NLP BERT Model, Task Number: No.2021R1I1A3050407, Contribution Rate: 15%) with the support of the Korea Creative Content Agency (Task Name: No.2021R1A3050407, Contribution Rate: 15%).

References

  1. Marcus, Gary, Ernest Davis, and Scott Aaronson. "A very preliminary analysis of DALL-E 2." arXiv preprint arXiv:2204.13807, 2022 DOI: https://doi.org/10.48550/arXiv.2204.13807
  2. Berkeley Neural Parser, [Internet], https://parser.kitaev.io/.
  3. Fillmore, Charles J. The case for case. Universals in Linguistic Theory. E. Bach and R. Harms. New York, Holt, Rinehart, and Winston: 1-89. 1968.
  4. B. K. Park, and R. Y. C. Kim, "Effort estimation approach through extracting use cases via informal requirement specifications," Applied Sciences, vol.10, no.9, 2020 DOI: https://doi.org/10.3390/app10093044
  5. H. T. Kim, and R. Y. C. Kim, "Extraction Practices on UML Sequence Diagram through Natural Language based Requirement Specifications," International Symposium on Advanced and Applied Convergence, AACL22, 2023
  6. J. H. Kim, and R. Y. C. Kim, "Cartoon Extraction Mechanism via UML Model based on Natural Language Requirement Specs.," 10th Annual Conf. on Computational Science & Computational Intelligence, Proceeding, 2023
  7. Fabric JS, [Internet], http://fabricjs.com/