计算机工程与应用2026，Vol.62Issue(9)：108-121,14.DOI:10.3778/j.issn.1002-8331.2507-0068
基于大模型的全球航展知识图谱构建与问答系统框架研究
Research on Framework of Global Airshow Knowledge Graph Construction and Question-Answering System Based on Large Language Models
摘要
Abstract
Against the backdrop of rapid advancement of global aerospace technology,airshows serve as a pivotal plat-form for international industry exchanges and technological demonstrations,accumulating massive heterogeneous infor-mation including airshow history,exhibit technical parameters,and social media public opinion on airshow topics.Effi-cient information acquisition and utilization through existing technologies hold significant practical value.A global air-show domain knowledge graph construction method based on large-model research is proposed.By integrating retrieval augmentation generation(RAG)technology,an airshow domain Q&A system framework is constructed on this graph through fine-tuning low-rank adaptation(LoRA)and implementing chain-of-thought design for pre-trained models,con-structing the domain knowledge graph,and introducing document parsing,semantic chunking,hybrid retrieval,and cue enhancement techniques.Dataset-based tests demonstrate that the proposed method improves the benchmark model in accuracy,precision,and F1-score metrics,and subjective and objective evaluations of the Q&A system show that the RAG framework effectively reduces model"hallucination"frequency and enhances professional Q&A capabilities in spe-cialized domains.关键词
大语言模型/知识图谱/问答系统/检索增强生成/全球航展信息Key words
large language models/knowledge graph/question-answering system/retrieval-augmented generation/global airshow information分类
信息技术与安全科学引用本文复制引用
蔡锦添,郝耀辉,陈鑫,秦渝栋..基于大模型的全球航展知识图谱构建与问答系统框架研究[J].计算机工程与应用,2026,62(9):108-121,14.基金项目
国家社会科学基金(21BXW057) （21BXW057）
河南省科技攻关项目(252102211040). （252102211040）
