现代信息科技2026，Vol.10Issue(3)：52-56,62,6.DOI:10.19850/j.cnki.2096-4706.2026.03.011
基于大模型检索增强生成的水利问答架构设计
Design of Water Conservancy Question and Answer Architecture Based on Large Model Retrieval-augmented Generation
摘要
Abstract
To address the challenges of knowledge hallucination,poor information timeliness and low localized deployment efficiency faced by Large Language Models(LLMs)in their applications to water conservancy and other knowledge-intensive industries,this paper proposes a Knowledge-Enhanced Retrieval-Augmented Generation(KE-RAG)system architecture that integrates vector retrieval with Knowledge Graph(KG)constraints.This architecture takes the domestically developed open-source model Qwen3-32B-AWQ as the generation core,constructs a multimodal water conservancy knowledge base containing laws and regulations,technical standards,engineering cases and expert experience,and achieves high-performance localized inference through the vectorized Large Language Model(vLLM)framework.Experimental results show that on the evaluation set,this architecture reaches a professional knowledge question and answer accuracy of 91.5%,an average end-to-end response latency of less than 500 ms and a throughput nearly four times higher than that of standard deployment,with all metrics significantly outperforming those of baseline models,which provides a reference solution for the application of Large Language Models in the water conservancy industry.关键词
大语言模型/检索增强生成/知识图谱/水利知识问答/高性能推理/本地化部署Key words
Large Language Model/retrieval-augmented generation/Knowledge Graph/water conservancy knowledge question and answer/high-performance inference/localized deployment分类
信息技术与安全科学引用本文复制引用
丁羽亮,欧阳晴雯,左君谣,胡佳,彭秀莲..基于大模型检索增强生成的水利问答架构设计[J].现代信息科技,2026,10(3):52-56,62,6.基金项目
湖南省水利科技项目(XSKJ2024064-30) （XSKJ2024064-30）
