EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-ACNC: Aerospace Requirement Texts Knowledge Graph Construction Utilizing Large Language Model

Yuhao Liu, Junjie Hou, Yuxuan Chen, Jie Jin, Wenyue Wang

Aerospace · 23.05.2025 · 12 (6) · 463

DOI: 10.3390/aerospace12060463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aerospace, online erschienen am 23.05.2025. Verfasst von Yuhao Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China State Administration of Science, Technology and Industry for National Defense.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional methods for requirement identification depend on the manual transformation of unstructured requirement texts into formal documents, a process that is both inefficient and prone to errors. Although requirement knowledge graphs offer structured representations, current named entity recognition and relation extraction techniques continue to face significant challenges in processing the specialized terminology and intricate sentence structures characteristic of the aerospace domain. To overcome these limitations, this study introduces a novel approach for constructing aerospace-specific requirement knowledge graphs using a large language model. The method first employs the GPT model for data augmentation, followed by BERTScore filtering to ensure data quality and consistency. An efficient continual learning based on token index encoding is then implemented, guiding the model to focus on key information and enhancing domain adaptability through fine-tuning of the Qwen2.5 (7B) model. Furthermore, a chain-of-thought reasoning framework is established for improved entity and relation recognition, coupled with a dynamic few-shot learning strategy that selects examples adaptively based on input characteristics. Experimental results validate the effectiveness of the proposed method, achieving F1 scores of 88.75% in NER and 89.48% in relation extraction tasks.

Förderung

  • China State Administration of Science, Technology and Industry for National Defense

Zitieren

APA

Liu, Y., Hou, J., Chen, Y., Jin, J., & Wang, W. (2025). LLM-ACNC: Aerospace Requirement Texts Knowledge Graph Construction Utilizing Large Language Model. Aerospace, 12(6), 463. https://doi.org/10.3390/aerospace12060463

Vancouver

Liu Y, Hou J, Chen Y, Jin J, Wang W. LLM-ACNC: Aerospace Requirement Texts Knowledge Graph Construction Utilizing Large Language Model. Aerospace. 2025;12(6):463. doi:10.3390/aerospace12060463

BibTeX
@article{Liu2025,
  author = {Liu, Yuhao and Hou, Junjie and Chen, Yuxuan and Jin, Jie and Wang, Wenyue},
  title = {LLM-ACNC: Aerospace Requirement Texts Knowledge Graph Construction Utilizing Large Language Model},
  journal = {Aerospace},
  year = {2025},
  volume = {12},
  number = {6},
  pages = {463},
  doi = {10.3390/aerospace12060463}
}
Kostenlos starten →