同济大学学报（自然科学版）2026，Vol.54Issue(1)：13-21,30,10.DOI:10.11908/j.issn.0253-374x.24303
基于协同专家系统的建筑施工大语言模型问答系统
A Construction Question and Answer System Based on a Collaborative Expert System and Large Language Model
摘要
Abstract
To address the issues of hallucinated generation and high deployment costs encountered by large language model(LLM)-based question answering systems in construction scenarios,this paper proposes a construction-oriented question answering system based on a collaborative expert mechanism.The system integrates shared experts and routing experts in a coordinated manner,which significantly improves the accuracy of answer generation and inference efficiency while preserving the model's expressive capacity and reducing computational overhead.In addition,a domain knowledge base-injected fine-tuning strategy is introduced to guide the model to deeply learn professional semantics in the construction domain during training,thereby enhancing its understanding of engineering-related texts and ensuring that the generated responses better align with practical engineering requirements.Experimental results demonstrate that,with only approximately one-third of the model parameters activated,the proposed system achieves a generation semantic similarity of 81.1％,effectively balancing efficiency and performance and providing an efficient,reliable,and construction-specific intelligent decision-support tool for construction management.关键词
建筑施工/智能建造/问答系统/大语言模型/本地知识库Key words
building construction/intelligent construction/question and answer system/large language model/local knowledge base分类
信息技术与安全科学引用本文复制引用
杨彬,肖鸿儒,高尚,雷克,陈文硕,张其林,汪丛军..基于协同专家系统的建筑施工大语言模型问答系统[J].同济大学学报（自然科学版）,2026,54(1):13-21,30,10.基金项目
国家重点研发计划(2022YFC3801702) （2022YFC3801702）
