数据与计算发展前沿 ›› 2026, Vol. 8 ›› Issue (4): 214-221.

CSTR: 32002.14.jfdc.CN10-1649/TP.2026.04.016

doi: 10.11871/jfdc.issn.2096-742X.2026.04.016

• • 上一篇    下一篇

基于大模型和RAG技术的能源产业链知识问答系统设计与实现

郝文玉1,2(),刘伟1,高思远3,梁凌3,游博4,*()   

  1. 1 中国神华能源股份有限公司， 北京 100011
    2 国家能源投资集团有限责任公司， 北京 100011
    3 国家能源集团新能源技术研究院有限公司， 北京 102209
    4 中国科学院自动化研究所， 北京 100190
  • 收稿日期:2025-10-21 出版日期:2026-08-20 发布日期:2026-08-21
  • 通讯作者: 游博（E-mail: youbo2019@ia.ac.cn）
  • 作者简介:郝文玉，国家能源投资集团有限责任公司，高级经济师，研究方向为生产运营智能化研究。
    本文主要承担工作为方法的提出和实现。
    HAO Wenyu is a senior economist of China Energy Investment Corporation Co., Ltd. His research interests include intelligent production and operation.
    In this paper, he is mainly responsible for proposing and implementing the method.
    E-mail: 11615000@ceic.com|游博，中国科学院自动化研究所，工程师，研究方向为计算机视觉、智能体等。
    本文中负责写作指导以及论文最终审定。
    YOU Bo is currently an engineer at the Institute of Automation, Chinese Academy of Sciences. Her research interests include computer vision and intelligent agents.
    In this paper, she is mainly responsible for paper writing instruction and manuscript reviewing.
    E-mail: youbo2019@ia.ac.cn
  • 基金资助:
    国家能源集团科技创新项目资助(GJNY-23-176)

Design and Implementation of an Energy Industry Knowledge Question-Answering System Based on Large Models and RAG Technology

HAO Wenyu1,2(),LIU Wei1,GAO Siyuan3,LIANG Ling3,YOU Bo4,*()   

  1. 1 China Shenhua Energy Company Limited, Ltd, Beijing 100011, China
    2 China Energy Investment Corporation Co., Ltd, Beijing 100011, China
    3 CHN Energy New Energy Technology Research Institute Co., Ltd, Beijing 102209, China
    4 Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
  • Received:2025-10-21 Online:2026-08-20 Published:2026-08-21

RichHTML

9

PDF

44

摘要：

【目的】 构建基于检索增强生成（Retrieval-Augmented Generation，RAG）技术的本地化智能问答系统，解决能源产业复杂规章制度体系下员工信息获取难题，为企业提供高效、准确的制度知识查询工具。【方法】 融合DeepSeek语言模型与LangChain框架，设计语义索引构建与生成式问答子系统，通过检索增强生成（RAG）技术提升制度知识的检索效率与准确性，支持企业数据安全保护与动态更新。【结果】 系统在企业法规问答任务中表现优异，BLEU-1和ROUGE-1评分分别达到0.2651和0.3020，较无RAG基线显著提升，验证了模型的有效性与鲁棒性。【结论】 本研究开发的智能问答系统有效解决了能源行业制度知识获取难题，支持新员工培训与企业管理需求，为行业数字化转型提供了可复用的技术框架。

关键词: 大语言模型, RAG技术, 能源产业, 智能问答系统

Abstract:

[Purpose] This study aims to build a localized intelligent question-answering system based on Retrieval-Augmented Generation (RAG) technology to address the challenges employees face in accessing information within the complex regulatory framework of the energy industry, and to provide enterprises with an efficient and accurate tool for querying institutional knowledge. [Methods] By integrating the DeepSeek language model with the LangChain framework, this study designs a semantic indexing and generative question-answering subsystem. Through RAG technology, we enhanced the efficiency and accuracy of institutional knowledge retrieval, while supporting enterprise data security protection and dynamic updates. [Results] The system performs well in enterprise regulatory question-answering tasks, with BLEU-1 and ROUGE-1 scores of 0.2651 and 0.3020, respectively, significantly outperforming the baseline without RAG, validating the effectiveness and robustness of the system. [Conclusions] The intelligent question-answering system developed in this study effectively addresses the challenges of accessing institutional knowledge in the energy industry, supports new employee training and enterprise management needs, and provides a reusable technical framework for industry digital transformation.

Key words: large language models, RAG technology, energy industry, intelligent question-answering system