arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16551cs.DB
收藏

利用大语言模型自动化提取科学文献中的机械本构模型:应用于文化遗产保护

Automated Extraction of Mechanical Constitutive Models from Scientific Literature using Large Language Models: Applications in Cultural Heritage Conservation

Shanghai University(上海大学)

Rui Hu, Yue Wu, Tianhao Su, Yin Wang, Shunbo Hu, Jizhong Huang

AI总结:

本研究利用大语言模型自动化提取科学文献中的机械本构模型,应用于文化遗产保护,构建了结构化数据库并提高了数据处理效率。

摘要:

文化遗产的保护正日益转向数据驱动的预测维护和'数字孪生'建设。然而,高保真模拟所需的机械本构模型仍分散在数十年的非结构化科学文献中,形成一个阻碍保护工程的'数据孤岛'。为此,我们提出一个自动化、分两阶段的代理框架,利用大语言模型(LLMs)从PDF文档中提取机械本构方程、校准参数和元数据。该流程采用资源高效的'守门人'代理进行相关性过滤,以及高能力的'分析师'代理进行细粒度提取,引入一种新颖的上下文感知符号 grounding 机制以解决数学歧义。应用于超过2000篇研究论文的语料库,系统成功隔离了113个核心文档,并构建了一个包含185个本构模型实例和超过450个校准参数的结构化数据库。提取精度达到80.4%,建立了一个高度高效的'人机协同'工作流程,将手动数据整理时间减少了约90%。我们通过一个基于网页的知识检索平台展示了系统的实用性,该平台能够快速发现计算建模所需的参数。本工作将分散的文献转化为可查询的数字资产,为'数字材料孪生'的建筑遗产奠定了数据基础。

英文摘要:

The preservation of cultural heritage is increasingly transitioning towards data-driven predictive maintenance and "Digital Twin" construction. However, the mechanical constitutive models required for high-fidelity simulations remain fragmented across decades of unstructured scientific literature, creating a "Data Silo" that hinders conservation engineering. To address this, we present an automated, two-stage agentic framework leveraging Large Language Models (LLMs) to extract mechanical constitutive equations, calibrated parameters, and metadata from PDF documents. The workflow employs a resource-efficient "Gatekeeper" agent for relevance filtering and a high-capability "Analyst" agent for fine-grained extraction, featuring a novel Context-Aware Symbolic Grounding mechanism to resolve mathematical ambiguities. Applied to a corpus of over 2,000 research papers, the system successfully isolated 113 core documents and constructed a structured database containing 185 constitutive model instances and over 450 calibrated parameters. The extraction precision reached 80.4\%, establishing a highly efficient "Human-in-the-loop" workflow that reduces manual data curation time by approximately 90\%. We demonstrate the system's utility through a web-based Knowledge Retrieval Platform, which enables rapid parameter discovery for computational modeling. This work transforms scattered literature into a queryable digital asset, laying the data foundation for the "Digital Material Twin" of built heritage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑