基于大语言模型的灌浆工程知识服务系统  

Grouting works knowledge service system based on large language model

作　　者：张天鸿 王晓玲[1] 余红玲 王佳俊[1] 苏哲 张君[1] ZHANG Tianhong;WANG Xiaoling;YU Hongling;WANG Jiajun;SU Zhe;ZHANG jun(State Key Laboratory of Hydraulic Engineering Intelligent Construction and Operation,Tianjin University,Tianjin 300072,China;College of Water Resources and Civil Engineering,China Agricultural University,Beijing 100091,China)

机构地区：[1]天津大学水利工程智能建设与运维全国重点实验室,天津300072 [2]中国农业大学水利与土木工程学院,北京100091

出　　处：《水利学报》2025年第1期130-142,共13页Journal of Hydraulic Engineering

基　　金：国家自然科学基金项目(52379131);华能集团总部科技项目(HNKJ20-H21TB)。

摘　　要：目前灌浆工程各阶段专业知识信息获取均依赖人工对多领域文本进行分析,人力成本高、生产效率低。为解决上述问题,需要构建基于大语言模型的知识服务系统。提供大语言模型微调所需的高质量文本,以及如何应对特定工程文本所固有的时效性与信息安全风险是构建该服务系统的重点和难点。为此,本研究首先针对通用性灌浆施工规范,提出了基于混合策略的数据集构建方法,并通过引入自我检查思维链与评分策略,攻克了传统数据生成质量不高的局限,为大语言模型微调提供了所需的高质量数据;其次采用LangChain构建了灌浆工程的检索增强生成框架,利用内嵌本地知识库实现了特定灌浆文本与模型的隔离,保障了特定工程文本的信息安全;最后通过阶段更新满足了特定工程文本的时效性要求。专业性测试表明,利用上述方法进行微调的Qwen-7B-Grout模型,在灌浆专业问题的判断与填空题的问答方面准确率分别达到了100%和80%。本研究提出的基于大语言模型构建的灌浆工程知识服务系统,不仅实现了通用灌浆知识的问答,而且能够对工程文档进行高效的检索增强生成,可有效提高生产效率并降低人力成本,为灌浆设计与施工管理提供新的智能辅助手段。Professional information acquisition in grouting engineering currently relies on manual processing of diverse texts,resulting in high labor costs and low efficiency.To address these challenges,it is essential to develop a knowledge service system based on large language model.The construction of this service system hinges on providing high-quality text for fine-tuning large language model and managing the inherent timeliness and information security risks of specific engineering texts.To overcome these challenges,a hybrid strategy dataset construction method is proposed,based on universal grouting construction specifications.By incorporating self-checking chain of thought and scoring strategies,the quality limitations of traditional data generation are addressed,ensuring the provision of high-quality data necessary for fine-tuning the large language model.Additionally,LangChain is employed to build a retrieval augmented generation framework for grouting engineering.By incorporating an embedded local knowledge base,this framework ensures the isolation of specific grouting text and models,guaranteeing information security.To meet the timeliness requirements of specific engineering texts,a staged update approach is adopted.Professional tests demonstrate that the Qwen-7B-Grout model,fine-tuned using our proposed methods,achieves 100%accuracy in the judgment of grouting-specific issues and 80%accuracy in fill-in-the-blank questions.The knowledge service system based on large language model proposed in this study not only facilitates general grouting knowledge Q&A but also realizes efficient retrieval augmented generation of engineering documents.In conclusion,this system significantly improves production efficiency and reduces labor costs,offering new intelligent assistance for grouting design and construction management.

关 键 词：灌浆工程知识服务 混合策略数据生成 大语言模型 检索增强生成 灌浆工程 

分 类 号：TV52[水利工程—水利水电工程]