基于多源数据融合的氢能产业链决策服务系统设计与实现
Design and Implementation of a Hydrogen Energy Industry Chain Decision Support System Based on Multi-Source Data Fusion
DOI: 10.12677/csa.2026.166222, PDF,    科研立项经费支持
作者: 刘力鸣, 刘 超, 陈晓玲*：吉林省科技创新研究院，吉林 长春；贾 超：吉林省翰德人才咨询有限公司，吉林 长春
关键词: 多源数据；氢能产业；决策服务；系统实现；Multi-Source Data； Hydrogen Energy Industry； Decision Support Services； System Implementation
摘要: 为提升氢能产业数据价值，实现数据服务支撑氢能产业智能决策，研发了氢能产业链决策服务系统。该系统应用数据治理技术，将氢能产业政策、专利和文献等多源数据融合；采用自然语言处理算法，分析融合数据的语义特征；通过知识图谱技术，呈现氢能产业发展趋势；借助熵权TOPSIS算法，监测产业发展情况。系统应用氢能产业的数据服务、计算服务和信息服务三层架构，实现了产业链信息导航、关键技术图谱和产业技术监测功能，支撑了氢能产业科技创新发展和技术攻关前瞻研究。
Abstract: To enhance the value of data in the hydrogen energy industry and enable data-driven support for intelligent decision-making, a Decision Support System for the Hydrogen Energy Industry Chain has been developed. The system employs data governance techniques to integrate multi-source data including industrial policies, patents, and literature; utilizes natural language processing algorithms to analyze semantic features of the aggregated data; leverages knowledge graph technology to visualize development trends in the hydrogen energy sector; and applies the entropy-weighted TOPSIS algorithm to monitor industry progress. Built upon a three-tier architecture comprising data services, computing services, and information services, the system provides functions such as industry chain navigation, key technology mapping, and technological monitoring, thereby supporting scientific innovation and forward-looking research in hydrogen energy technology.
文章引用：刘力鸣, 刘超, 陈晓玲, 贾超. 基于多源数据融合的氢能产业链决策服务系统设计与实现[J]. 计算机科学与应用, 2026, 16(6): 222-231. https://doi.org/10.12677/csa.2026.166222

参考文献

[1] 中华人民共和国能源法[Z].
http://www.npc.gov.cn/npc/c2/c30834/202411/t20241108_440884.html, 2024-11-08.
[2] Popel’, O.S. and Tarasenko, A.B. (2022) Promising Directions for Hydrogen Energy Development in Russia. Applied Solar Energy, 58, 152-158. [Google Scholar] [CrossRef] 
[3] Behrendt, F. (2025) The Future of Industrial Hydrogen: Renewable Sources and Applications for the Next 15 Years. Clean Energy, 9, 3-8. [Google Scholar] [CrossRef] 
[4] Ziobrowski, Z. and Rotkegel, A. (2024) Assessment of Hydrogen Energy Industry Chain Based on Hydrogen Production Methods, Storage, and Utilization. Energies, 17, Article 1808. [Google Scholar] [CrossRef] 
[5] Dawood, F., Shafiullah, G.M. and Anda, M. (2020) A Hover View over Australia’s Hydrogen Industry in Recent History: The Necessity for a Hydrogen Industry Knowledge-Sharing Platform. International Journal of Hydrogen Energy, 45, 32916-32939. [Google Scholar] [CrossRef] 
[6] 黄晓林, 胡锡晟, 黄卉, 等. 中国氢能源产业政策量化分析及区域布局研究[J]. 科技情报研究, 2021, 3(2): 83-95.
[7] 付强, 杨洸, 金辉, 等. 中国氢能产业链技术现状及发展趋势[J]. 油气与新能源, 2024, 36(4): 19-30.
[8] 李建林, 李光辉, 郭丽军, 等. “十四五”规划下氢能应用技术现状综述及前景展望[J]. 电气应用, 2021, 40(6): 10-16.
[9] 王嘉炜, 妙丛. 基于大数据分析的加氢站智能管理系统[J]. 科技创新与应用, 2022, 12(17): 27-30.
[10] 张卫, 刘延杰. 基于大数据视角的新兴产业环境分析——以氢能产业为例[J]. 智库理论与实践, 2023, 8(4): 87-100.
[11] 付强, 陈晓玲, 李沫, 等. 基于深度整合的科技资源系统的设计与实现[J]. 吉林大学学报(信息科学版), 2022, 40(6): 924-929.
[12] Blei, D.M., Ng, A. and Jordan, M.I. (2003) Latent Dirichlet Allocation. The Journal of Machine Learning Research, 3, 993-1022.
[13] 喻啸林, 周建华. 熵权-TOPSIS法在高校网络舆情监测预警中的应用[J]. 电脑与信息技术, 2025, 33(1): 69-73.
[14] 杨航, 张啸成, 张永刚. 基于实体类别信息的数据分析与关系抽取模型构建[J]. 吉林大学学报(理学版), 2025, 63(2): 428-436.
[15] 张炯娜, 王若瑶, 何晓茜. 基于AIS算法和Lambda的医学图书馆推荐系统构建[J]. 信息技术, 2024(12): 80-85, 92.