Research on Report Recommendation Algorithm Based on Graph Convolution Network and User Information

doi:10.12204/j.issn.1000-7229.2023.05.005

Abstract

Abstract:

Traditional reporting tools cannot recommend relevant business information to users independently. This has created many challenges in the operation and management of electric power enterprises. To address the above problems, this study proposes a graph convolutional network (GCN) report recommendation algorithm based on user information. First, the overall structure of the reporting tool based on the data center platform is introduced. Considering the marketing business as an example, the correlation between users and indicators is analyzed and a correlation feature extraction model based on a graph convolutional network is proposed. Simultaneously, the general preference characteristics of users and indicators are integrated into the model, and the depth of the graph aggregation information is further improved. Subsequently, the index score is accurately predicted, and a recommendation result is provided. Finally, the models are compared for a public dataset and marketing business dataset, and the average precision rate, recall rate, and normalized discounted cumulative gain are selected as evaluation indicators to verify the accuracy of the proposed algorithm. The results show that compared with existing algorithms, the proposed algorithm significantly improves the recommendation effect, which can empower the operation and management of electric power enterprises and help realize digital transformation.

Key words: report tool, graph convolution network, marketing business, user information

CLC Number:

TM714

YANG Zhiwei, ZHANG Fan, YANG Zhi, LI Wenjuan, LIU Wen. Research on Report Recommendation Algorithm Based on Graph Convolution Network and User Information[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(5): 43-52.

Figures/Tables 10

Fig.1 Report tool support platform architecture

Fig.2 Correlation of electricity tariff standardization indicators

Fig.3 Main idea of recommendation algorithm

Fig.4 Network architecture of recommendation algorithm

Fig.5 Basic architecture of BERT model

Table 1 Model parameters

Table 1 Performance comparison under public datasets

Fig.6 Performance comparison under marketing data set

Fig.7 Recommendation process of user 32

Table 3 Comparison experiment of super parameters

References 34

[1]	习近平. 在第七十五届联合国大会一般性辩论上的讲话[R]. 北京: 中华人民共和国国务院, 2020.
[2]	谢小荣, 贺静波, 毛航银, 等. “双高”电力系统稳定性的新问题及分类探讨[J]. 中国电机工程学报, 2021, 41(2): 461-475.
	XIE Xiaorong, HE Jingbo, MAO Hangyin, et al. New issues and classification of power system stability with high shares of renewables and power electronics[J]. Proceedings of the CSEE, 2021, 41(2): 461-475.
[3]	张智刚, 康重庆. 碳中和目标下构建新型电力系统的挑战与展望[J]. 中国电机工程学报, 2022, 42(8): 2806-2819.
	ZHANG Zhigang, KANG Chongqing. Challenges and prospects for constructing the new-type power system towards a carbon neutrality future[J]. Proceedings of the CSEE, 2022, 42(8): 2806-2819.
[4]	李鹏, 习伟, 蔡田田, 等. 数字电网的理念、架构与关键技术[J]. 中国电机工程学报, 2022, 42(14): 5002-5017.
	LI Peng, XI Wei, CAI Tiantian, et al. Concept, architecture and key technologies of digital power grids[J]. Proceedings of the CSEE, 2022, 42(14): 5002-5017.
[5]	邬炜, 赵腾, 李隽, 等. 考虑碳预算与碳循环的能源规划方法及建议[J]. 电力建设, 2021, 42(10): 1-8. doi: 10.12204/j.issn.1000-7229.2021.10.001
	WU Wei, ZHAO Teng, LI Jun, et al. Energy planning methods and proposals considering carbon budget and carbon cycle[J]. Electric Power Construction, 2021, 42(10): 1-8. doi: 10.12204/j.issn.1000-7229.2021.10.001
[6]	王利兵, 张赟. 中国能源碳排放因素分解与情景预测[J]. 电力建设, 2021, 42(9): 1-9. doi: 10.12204/j.issn.1000-7229.2021.09.001
	WANG Libing, ZHANG Yun. Factors decomposition and scenario prediction of energy-related CO₂ emissions in China[J]. Electric Power Construction, 2021, 42(9): 1-9. doi: 10.12204/j.issn.1000-7229.2021.09.001
[7]	杨晓宇, 郭晓鹏, 杨昆. 电力物联网用户用电信息全过程管理风险评估[J]. 智慧电力, 2022, 50(10): 53-60.
	YANG Xiaoyu, GUO Xiaopeng, YANG Kun. Whole process management risk assessment of user’s power consumption information through electric internet of things[J]. Smart Power, 2022, 50(10): 53-60.
[8]	毛亚哲, 何柏娜, 王德顺, 等. 基于改进深度强化学习的智能微电网群控制优化方法[J]. 智慧电力, 2021, 49(3): 19-25, 58.
	MAO Yazhe, HE Baina, WANG Deshun, et al. Optimization method for smart multi-microgrid control based on improved deep reinforcement learning[J]. Smart Power, 2021, 49(3): 19-25, 58.
[9]	ZHU L P, LU C, LUO Y H. Time series data-driven batch assessment of power system short-term voltage security[J]. IEEE Transactions on Industrial Informatics, 2020, 16(12): 7306-7317. doi: 10.1109/TII.9424 URL
[10]	张帆, 杨志, 李文娟, 等. 基于数据中台的电力数据报表模型研究与应用[J]. 电力大数据, 2020, 23(10): 63-69.
	ZHANG Fan, YANG Zhi, LI Wenjuan, et al. Research and application of power data report model based on data center[J]. Power Systems and Big Data, 2020, 23(10): 63-69.
[11]	高雅. 加快数字化转型推进能源互联网企业建设: 公司2021年互联网专业工作会议解读[N]. 国家电网报, 2021-02-08( 2).
[12]	唐敏, 徐玮, 李昭原. 基于Web的报表工具的设计与实现[J]. 北京航空航天大学学报, 2001, 27(4): 482-485.
	TANG Min, XU Wei, LI Zhaoyuan. Design and implementation of a web reporting tool[J]. Journal of Beijing University of Aeronautics and Astronautics, 2001, 27(4): 482-485.
[13]	黄龙达, 庄卫金, 龙苏岩, 等. 电力交易平台数据指标监视技术研究与应用[J]. 电网技术, 2021, 45(8): 3200-3206.
	HUANG Longda, ZHUANG Weijin, LONG Suyan, et al. Research and application of data monitoring technologies on electricity trading platform[J]. Power System Technology, 2021, 45(8): 3200-3206.
[14]	李迎春, 孙学波. 非交互式报表生成器组件的设计和实现[J]. 计算机工程与设计, 2009, 30(10): 2558-2560, 2563.
	LI Yingchun, SUN Xuebo. Design and implementation of noninteractive report generator using.NET component technology[J]. Computer Engineering and Design, 2009, 30(10): 2558-2560, 2563.
[15]	毛燠锋, 潘玉春, 朱玉付. 基于报表和模板的报告生成方法研究[J]. 软件工程, 2021, 24(5): 30-32.
	MAO Yufeng, PAN Yuchun, ZHU Yufu. A report generation method based on report form and template[J]. Software Engineering, 2021, 24(5): 30-32.
[16]	林艳华, 吴健, 周胜杰. 基于Excel的电力监控通用报表系统的设计与实现[J]. 计算机工程与科学, 2008, 30(4): 124-127.
	LIN Yanhua, WU Jian, ZHOU Shengjie. Design and implementation of an excel-based universal power monitoring spreadsheet system[J]. Computer Engineering & Science, 2008, 30(4): 124-127.
[17]	付红军, 孟远景, 熊浩清, 等. 电网运行方式综合管理系统设计与应用[J]. 电力自动化设备, 2010, 30(4): 119-123.
	FU Hongjun, MENG Yuanjing, XIONG Haoqing, et al. Design and application of power system operating mode management system[J]. Electric Power Automation Equipment, 2010, 30(4): 119-123.
[18]	王志南, 张宇华, 黄珂, 等. 计及多种柔性负荷的虚拟电厂热电联合鲁棒优化调度模型[J]. 电力建设, 2021, 42(7): 1-10. doi: 10.12204/j.issn.1000-7229.2021.07.001
	WANG Zhinan, ZHANG Yuhua, HUANG Ke, et al. Robust optimal scheduling model of virtual power plant combined heat and power considering multiple flexible loads[J]. Electric Power Construction, 2021, 42(7): 1-10. doi: 10.12204/j.issn.1000-7229.2021.07.001
[19]	张稳, 盛万兴, 杜松怀, 等. 基于海量数据的配电网运行分析系统架构与技术实现[J]. 电力系统自动化, 2020, 44(3): 147-153.
	ZHANG Wen, SHENG Wanxing, DU Songhuai, et al. Architecture and technology implementation of massive data based distribution network operation analysis system[J]. Automation of Electric Power Systems, 2020, 44(3): 147-153.
[20]	周杨珺, 梁朔, 俞小勇, 等. 基于多源异构数据的配电网运行分析平台: 系统架构与技术实现[J]. 南方电网技术, 2018, 12(8): 59-64.
	ZHOU Yangjun, LIANG Shuo, YU Xiaoyong, et al. Research and implementation of distribution network operating analysis platform based on multi-source heterogeneous data[J]. Southern Power System Technology, 2018, 12(8): 59-64.
[21]	孙名扬, 于芳, 赵家庆, 等. 新一代调控系统一体化运维架构及关键技术[J]. 电力系统自动化, 2019, 43(22): 217-223.
	SUN Mingyang, YU Fang, ZHAO Jiaqing, et al. Integrated operation/maintenance architecture and key technologies of new generation dispatching and control system[J]. Automation of Electric Power Systems, 2019, 43(22): 217-223.
[22]	LI H, CHIANG H D, GALE W G, et al. A novel system for automatic generation of service reliability reports from automated mapping and facility management (AM/FM) systems[J]. IEEE Transactions on Power Systems, 2002, 17(3): 812-817. doi: 10.1109/TPWRS.2002.801039 URL
[23]	秦凤梅, 秦安碧, 邱玉辉. SOA架构在呼叫中心报表系统的研究与实践[J]. 计算机科学, 2013, 40(S2): 426-427, 435.
	QIN Fengmei, QIN Anbi, QIU Yuhui. Research and implementation of SOA frame in call center reporting systems[J]. Computer Science, 2013, 40(S2): 426-427, 435.
[24]	EITO-BRUN R, AMESCUA-SECO A. Automation of quality reports in the aerospace industry[J]. IEEE Transactions on Professional Communication, 2018, 61(2): 166-177. doi: 10.1109/TPC.2017.2788678 URL
[25]	ZHANG N, ZHAO W. Privacy-preserving OLAP: an information-theoretic approach[J]. IEEE Transactions on Knowledge and Data Engineering, 2011, 23(1): 122-138. doi: 10.1109/TKDE.2010.25 URL
[26]	FIORE S, ELIA D, PIRES C E, et al. An integrated big and fast data analytics platform for smart urban transportation management[J]. IEEE Access, 2019, 7: 117652-117677. doi: 10.1109/Access.6287639 URL
[27]	冯兴杰, 曾云泽. 基于评分矩阵与评论文本的深度推荐模型[J]. 计算机学报, 2020, 43(5): 884-900.
	FENG Xingjie, ZENG Yunze. Joint deep modeling of rating matrix and reviews for recommendation[J]. Chinese Journal of Computers, 2020, 43(5): 884-900.
[28]	张晨, 肖君儒, 周丽. 基于矩阵填充的混合协同过滤推荐算法研究[J]. 数学的实践与认识, 2021, 51(10): 81-89.
	ZHANG Chen, XIAO Junru, ZHOU Li. Research on hybrid collaborative filtering recommendation algorithm based on matrix filling[J]. Mathematics in Practice and Theory, 2021, 51(10): 81-89.
[29]	王永, 冉珣, 尹恩民, 等. 满足差分隐私保护的矩阵分解推荐算法[J]. 电子科技大学学报, 2021, 50(3): 405-413.
	WANG Yong, RAN Xun, YIN Enmin, et al. Matrix factorization recommendation algorithm for differential privacy protection[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(3): 405-413.
[30]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907. doi: 10.11772/j.issn.1001-9081.2019122067
	TIAN Baojun, LIU Shuang, FANG Jiandong. Hybrid recommendation algorithm by fusion of topic information and convolution neural network[J]. Journal of Computer Applications, 2020, 40(7): 1901-1907. doi: 10.11772/j.issn.1001-9081.2019122067
[31]	HE X N, DENG K, WANG X, et al. LightGCN: simplifying and powering graph convolution network for recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. July 25 - 30, 2020, Virtual Event, China. New York: ACM, 2020: 639-648.
[32]	王渝红, 沈靖, 曾琦, 等. 基于谱图论和图卷积神经网络的直流电网节点电压估计研究[J]. 电网技术, 2022, 46(2): 521-532.
	WANG Yuhong, SHEN Jing, ZENG Qi, et al. Voltage estimation for DC grid nodes based on spectral theory and graph convolutional neural network[J]. Power System Technology, 2022, 46(2): 521-532.
[33]	陈源奕, 王玉彬, 杨强. 基于时空特征图卷积网络的配电网实时状态估计方法[J]. 高电压技术, 2021, 47(7): 2386-2395.
	CHEN Yuanyi, WANG Yubin, YANG Qiang. Real-time state estimation method for distribution networks based on spatial-temporal feature graph convolution network[J]. High Voltage Engineering, 2021, 47(7): 2386-2395.
[34]	叶欣智, 尚磊, 董旭柱, 等. 面向配电网故障处置的知识图谱研究与应用[J]. 电网技术, 2022, 46(10): 3739-3749.
	YE Xinzhi, SHANG Lei, DONG Xuzhu, et al. Knowledge graph for distribution network fault handling[J]. Power System Technology, 2022, 46(10): 3739-3749.