| 注册
首页|期刊导航|同济大学学报(自然科学版)|自适应分支求解策略增强的智能建造政策类文本检索方法

自适应分支求解策略增强的智能建造政策类文本检索方法

卢昱杰 蔺梦想 杨川

同济大学学报(自然科学版)2026,Vol.54Issue(8):1186-1199,14.
✕
同济大学学报(自然科学版)2026,Vol.54Issue(8):1186-1199,14.DOI:10.11908/j.issn.0253-374x.25147

自适应分支求解策略增强的智能建造政策类文本检索方法

Intelligent Construction Policy Text Retrieval Method Enhanced with Adaptive Branch Resolution Strategy

卢昱杰 1蔺梦想 2杨川2

作者信息

  • 1. 同济大学土木工程学院,上海 200092||同济大学工程结构性能演化与控制教育部重点实验室,上海 200092||同济大学上海智能科学与技术研究院,上海 200092
  • 2. 同济大学土木工程学院,上海 200092
  • 折叠

摘要

Abstract

Accurate interpretation and application of intelligent construction policies are essential throughout the project lifecycle,as they directly affect compliance,technology selection,and project evaluation.However,policy retrieval in this domain is challenged by lengthy documents,specialized terminology,and regional variations,making conventional retrieval methods insufficient for complex reasoning tasks.Although retrieval-augmented generation(RAG)has shown promise,its direct application to intelligent construction remains limited by weak reasoning ability and difficulty in resolving semantic ambiguity.To address these limitations,this paper proposes Branch-RAG,an improved RAG framework based on an adaptive branch resolution strategy for intelligent construction policy question and answer.By integrating a policy knowledge graph as external knowledge,Branch-RAG dynamically enhances logical reasoning according to question granularity.A policy knowledge base covering 13 provinces and 24 prefecture-level cities in China was constructed,together with a dataset of 3 420 structured question-answer pairs.Experimental results show that Branch-RAG achieves an overall accuracy of 79.6%,outperforming the second-best Graph-RAG by 3.3%,while maintaining an average response time of 14.82 s.It performs particularly well on high-difficulty questions.This paper provides an efficient and accurate solution for complex policy retrieval in intelligent construction and supports the practical deployment of RAG in vertical domains.

关键词

检索增强生成/文本检索/自适应分支求解策略/知识图谱/多跳推理

Key words

retrieval-augmented generation(RAG)/text retrieval/adaptive branching solution strategy/knowledge graph/multi-hop reasoning

分类

建筑与水利

引用本文复制引用

卢昱杰,蔺梦想,杨川..自适应分支求解策略增强的智能建造政策类文本检索方法[J].同济大学学报(自然科学版),2026,54(8):1186-1199,14.

基金项目

中央高校基本科研业务费专项资金(22120250350) (22120250350)

中央高校基本科研业务费专项资金(2024-1-ZD-02) (2024-1-ZD-02)

"十四五"国家重点研发计划课题(2022YFC3801700) (2022YFC3801700)

上海市科技创新行动计划(22dz1207100) (22dz1207100)

同济大学学报(自然科学版)

0253-374X

访问量0
|
下载量0
段落导航相关论文