JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE) ›› 2026, Vol. 61 ›› Issue (5): 38-45.doi: 10.6040/j.issn.1671-9352.0.2025.180

Previous Articles     Next Articles

Design and implementation of a safety knowledge recommendation system for power enterprises

HUANG Ronghui1, ZHANG Zhonghao2*   

  1. 1. Southern Power Grid Digital Platform Technology(Guangdong)Co., Ltd., Shenzhen 518053, Guangdong, China;
    2. Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan 523129, Guangdong, China
  • Published:2026-05-15

PDF (PC)

8

Abstract: Addressing the issues of generalized content delivery and insufficient personalization in safety knowledge dissemination within power enterprises, a safety knowledge recommendation system tailored for the power industry is designed and implemented in this study "Learn what you do" and "Learn what you lack" are adopted as the core scenarios of the system, the system integrates scenario-driven routing and heterogeneous knowledge matching strategies to achieve precise recommendations. By constructing a standardized tagging system through knowledge graphs and employing Jaccard similarity calculations with dynamic feedback optimization algorithms, it resolves the weaknesses of traditional recommendation models, such as poor generalization capability and low real-time performance.The system supports mobile deployments, incorporating a layered data processing architecture and automated operation mechanisms. It features dynamic recommendation weight adjustment and cold-start optimization capabilities. This solution effectively meets the complex needs of power enterprises with diverse job roles and multi-level risk scenarios, significantly enhancing knowledge acquisition efficiency and safety management standards.

Key words: power safety, knowledge recommendation, scenario-driven, dynamic feedback

CLC Number: 

  • TP391
[1] HEINRICH H W. Industrial accident prevention: a scientific approach[M]. New York: McGraw-Hill, 1951:609.
[2] 叶健辉,殷智,孟伶智,等. 基于电网运行关键指标的调度人员综合能力评价模型[J]. 中国科技信息,2015(21):140-142. YE Jianhui, YIN Zhi, MENG Lingzhi, et al. A comprehensive competency evaluation model for dispatchers based on key power grid operation indicators[J]. China Science and Technology Information, 2015(21):140-142.
[3] 阮聪,齐林海,王红. 融合知识图谱与神经张量网络的需求响应智能推荐[J]. 电网技术,2021,45(6):2131-2140. RUAN Cong, QI Linhai, WANG Hong. Intelligent recommendation for demand response integrating knowledge graph and neural tensor network[J]. Power System Technology, 2021, 45(6):2131-2140.
[4] 徐冲,汪凝,倪相生. 基于知识图谱的用户特征-关系推荐模型在电力安全教育中的应用[J]. 电力信息与通信技术,2024,22(11):60-66. XU Chong, WANG Ning, NI Xiangsheng. Application of a knowledge graph-based user feature-relation recommendation model in electric power safety education[J]. Electric Power Information and Communication Technology, 2024, 22(11):60-66.
[5] 邓淑斌,王子石,梁志飞,等. 基于知识图谱的电力交易智能推荐技术研究[J]. 粘接,2024,51(10):149-152. DENG Shubin, WANG Zishi, LIANG Zhifei, et al. Research on intelligent recommendation technology for electricity trading based on knowledge graph[J]. Adhesion, 2024, 51(10):149-152.
[6] 闫世泽,方志军. 基于用户行为融合特征与异常点检测的知识图谱推荐模型[J/OL].计算机工程[2026-01-08]. https://doi.org/10.19678/j.issn.1000-3428.0070696. Yan Shize, Fang Zhijun. Knowledge graph recommendation model based on user behavior fusion features and outlier detection[J/OL]. Computer Engineering[2026-01-08]. https://doi.org/10.19678/j.issn.1000-3428.0070696.
[7] 甘轲,朱小飞,程佳玮. 基于多视角关系增强知识图谱的推荐方法[J]. 计算机应用,2025,45(11):3519-3528. GAN Ke, ZHU Xiaofei, CHENG Jiawei. Recommendation method based on multi-view relational enhanced knowledge graph[J]. Computer Applications, 2025, 45(11):3519-3528.
[8] 刘滨,雷晓雨,刘格格,等. 融合知识图谱的多行为职位推荐[J]. 河北科技大学学报,2025,46(3):333-341. LIU Bin, LEI Xiaoyu, LIU Gege, et al. Multi-behavior job recommendation with knowledge graph integration[J]. Journal of Hebei University of Science and Technology, 2025, 46(3):333-341.
[9] 刘运通,孙晓莹,张展. 融合语义的图神经网络饰品设计知识推荐[J]. 计算机工程与设计,2024,45(12):3812-3819. LIU Yuntong, SUN Xiaoying, ZHANG Zhan. Semantic-enhanced graph neural network for jewelry design knowledge recommendation[J]. Computer Engineering and Design, 2024, 45(12):3812-3819.
[10] ZHAO Yao, WANG Ting. Knowledge base embeddings for a recommendation based on overlapping knowledge and graph learning[J/OL]. Arabian Journal for Science and Engineering[2024-06-03]. https://doi.org/10.1007/s13369-024-09573-7.
[11] 张馨月,高辉. 基于图重构的社交知识推荐[J]. 计算机应用研究,2024,41(12):3607-3613. ZHANG Xinyue, GAO Hui. Graph reconstruction-based social knowledge recommendation[J]. Application Research of Computers, 2024, 41(12):3607-3613.
[12] 杨宇亮,石嘉豪,秦高原,等. 电网运维岗位知识推荐系统设计与实现[J]. 信息通信,2020(12):161-163. YANG Yuliang, SHI Jiahao, QIN Gaoyuan, et al. Design and implementation of knowledge recommendation system for power grid operation and maintenance positions[J]. Information & Communications, 2020(12):161-163.
[13] 曲朝阳,徐鹏飞,娄建楼,等. 基于协同过滤的电力信息运维知识个性化推荐模型[J]. 东北师大学报(自然科学版),2017,49(2):84-88. QU Zhaoyang, XU Pengfei, LOU Jianlou, et al. Personalized recommendation model for electric power information operation knowledge based on collaborative filtering[J]. Journal of Northeast Normal University(Natural Science Edition), 2017, 49(2):84-88.
[14] 刘书安,蒋贵君,洪永杰. 节能知识推荐系统之建立与验证[J]. 资料分析,2025,20(1):55-71. LIU Shuan, JIANG Guijun, HONG Yongjie. Establishment and verification of an energy-saving knowledge recommendation system[J]. Journal of Data Analysis, 2025, 20(1):55-71.
[15] GAO Li, LIU Yi, CHEN Qingkui, et al. A user-knowledge vector space reconstruction model for the expert knowledge recommendation system[J]. Information Sciences, 2023, 632:358-377.
[16] 樊明山. 基于大数据技术的个性化推荐系统设计[J]. 信息与电脑,2025,37(9):31-33. FAN Mingshan. Design of personalized recommendation system based on big data technology[J]. Information and Computer, 2025, 37(9):31-33.
[17] 王海荣,王怡梦,周北京,等. 融合多模态信息的知识感知推荐方法[J]. 郑州大学学报(工学版),2025,46(6):15-22. WANG Hairong, WANG Yimeng, ZHOU Beijing, et al. Knowledge-aware recommendation method incorporating multimodal information fusion[J]. Journal of Zhengzhou University(Engineering Science), 2025, 46(6):15-22.
[18] 董锦锦,顾海瑞,陆佳炜,等. 基于本体-匹配双向扩展模型的设计知识推荐方法[J]. 机电工程,2024,41(10):1793-1805. DONG Jinjin, GU Hairui, LU Jiawei, et al. Design knowledge recommendation method based on ontology-matching bidirectional extension model[J]. Journal of Mechanical & Electrical Engineering, 2024, 41(10):1793-1805.
[19] 宋音希,何鹤,钟岳,等. 基于先进计算机技术的电力企业智慧审计系统设计分析[J]. 数字技术与应用,2024,42(5):193-195. SONG Yinxi, HE He, ZHONG Yue, et al. Design and analysis of intelligent auditing system for power enterprises based on advanced computer technology[J]. Digital Technology and Application, 2024, 42(5):193-195.
[20] 马晓亮,高洁,刘英,等. 基于意图理解驱动的客服知识推荐大模型构建[J]. 华南理工大学学报(自然科学版),2025,53(3):40-49. MA Xiaoliang, GAO Jie, LIU Ying, et al. Construction of customer service knowledge recommendation large model driven by intent understanding[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(3):40-49.
[21] JIANG Hua. Deep learning based personalized English listening learning path recommendation algorithm[J]. Systems and Soft Computing, 2025(12):200210.
[22] SHI Lin, YANG Xiaoqing. Personalized recommendation algorithm for cultural and creative products based on fuzzy decision support system[J]. International Journal of Computational Intelligence Systems, 2025, 18(1):116.
[23] ZHANG Yixuan, WANG Yanyi. A personalized recommendation algorithm for English exercises incorporating fuzzy cognitive models and multiple attention mechanisms[J]. Scientific Reports, 2025, 15(1):11531.
[24] 曹丹. 基于深度学习和知识图谱的企业信息化管理资源个性化推荐[J]. 信息系统工程,2025(2):101-104. CAO Dan. Personalized recommendation of enterprise information management resources based on deep learning and knowledge graph[J]. Information Systems Engineering, 2025(2):101-104.
[25] 杨栩,曹琼,黄贤英,等. 自注意力增强的动态个性化多行为推荐模型[J]. 计算机工程与设计,2025,46(4):1134-1140. YANG Xu, CAO Qiong, HUANG Xianying, et al. Self-attention enhanced dynamic personalized multi-behavior recommendation model[J]. Computer Engineering and Design, 2025, 46(4):1134-1140.
[26] 柳亚,毛谦昂,颜嘉麒,等. 面向用户动态偏好的科技论文推荐:一种基于注意嵌入的知识图谱方法[J]. 信息资源管理学报,2025,15(1):113-125. LIU Ya, MAO Qianang, YAN Jiaqi, et al. Scientific paper recommendation for dynamic user preferences:a knowledge graph approach based on attentive embedding[J]. Journal of Information Resources Management, 2025, 15(1):113-125.
[27] 胡晓莹,荀亚玲,李砚峰. 基于项目流行度和用户动态兴趣的纠偏推荐[J]. 计算机技术与发展,2024,34(8):135-142. HU Xiaoying, XUN Yaling, LI Yanfeng. Debiased recommendation based on item popularity and user dynamic interests[J]. Computer Technology and Development, 2024, 34(8):135-142.
[28] 沈学利,王乐,田学成. 融合双分支动态偏好的会话推荐[J]. 计算机系统应用,2024,33(3):52-62. SHEN Xueli, WANG Le, TIAN Xuecheng. Conversational recommendation with dual-branch dynamic preferences integration[J]. Computer Systems and Applications, 2024, 33(3):52-62.
[29] 周洋涛,李青山,褚华,等. 基于静态与动态学习需求感知的知识点推荐方法[J]. 软件学报,2024,35(9):4425-4447. ZHOU Yangtao, LI Qingshan, CHU Hua, et al. Knowledge point recommendation method based on static and dynamic learning requirement perception[J]. Journal of Software, 2024, 35(9):4425-4447.
[30] GAN M X, KWON O C. A knowledge-enhanced contextual bandit approach for personalized recommendation in dynamic domains[J]. Knowledge-Based Systems, 2022, 251:109158.
[31] 吕晓靥,李昆昊,纪佳琪. 基于隐语义模型的音乐推荐算法研究[J]. 河北软件职业技术学院学报,2023,25(2):34-37. LÜ Xiaoye, LI Kunhao, JI Jiaqi. Research on music recommendation algorithm based on latent semantic model[J]. Journal of Hebei Software Institute, 2023, 25(2):34-37.
[32] 郑建国,苏成卉. 基于多神经网络和改进PMF的视频推荐算法[J]. 计算机工程与设计,2021,42(1):96-105. ZHENG Jianguo, SU Chenghui. Video recommendation algorithm based on multi-neural network and improved PMF[J]. Computer Engineering and Design, 2021, 42(1):96-105.
[33] 李小强. 基于分层结构知识库和推理机技术的电网调度智能操作票系统[J]. 电气时代,2021(4):52-54. LI Xiaoqiang. Intelligent operation ticket system for power grid dispatching based on hierarchical knowledge base and inference engine technology[J]. Electrical Age, 2021(4):52-54.
[1] TANG Buzhou, HU Han. Construction of technology and application of knowledge graph in power safety [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2026, 61(5): 18-26.
[2] LUO Aike, YU Zhaojie. Methods of electric power safety entity extraction and risk prediction based on the joint learning [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2026, 61(5): 27-37.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd