基于深度数据挖掘和区块链技术的智库数据管控方法研究  

Research on think tank data management and control method based on deep data mining and blockchain technology

作　　者：韦冬妮 齐彩娟 张泽龙 唐梦媛 WEI Dongni;QI Caijuan;ZHANG Zelong;TANG Mengyuan(Economic and Technological Research Institute,State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 750002,China)

机构地区：[1]国网宁夏电力有限公司经济技术研究院,宁夏银川750002

出　　处：《电子设计工程》2022年第13期114-118,共5页Electronic Design Engineering

基　　金：国网宁夏电力企业智库建设方法研究项目(B007-300009250-00014)。

摘　　要：针对电力企业尚未专业、系统地开展智库建设,且缺乏完善的智库运营管理机制等问题,文中展开了基于深度数据挖掘和区块链技术的智库数据管控方法研究。文中构建的智库管控系统包括数据层、支撑层、业务层和表现层;该系统对智库数据进行深度数据挖掘,利用K-means聚类算法分类数据特征,并采用深度信念网络获得数据间的关联。利用区块链技术完成智库数据管控全过程,以保证数据的安全性。基于B/S协议和Matlab仿真计算平台对所提方法进行实验,测试结果表明,当数据量为8 MB时,其挖掘时间和准确率分别为1.5 s和93%,优于其他对比方法,而且安全性也更为理想。In view of the lack of professional and systematic think tank construction and perfect think tank operation and management mechanism in power enterprises,this paper studies the think tank data management and control method based on deep data mining and blockchain technology. The think tank management and control system is constructed,including data layer,support layer,business layer and presentation layer;The think tank data is deeply mined,and the K-means clustering algorithm is used to classify the data features,and the deep belief network is used to obtain the association between the data.Blockchain technology is used to complete the whole process of think tank data management and control to ensure data security. Based on B/S protocol and Matlab simulation platform,the proposed method is tested. The test results show that when the data volume is 8 MB,the mining time and accuracy are 1.5 s and 93% respectively,which are better than other comparison methods,and the security is also more ideal.

关 键 词：智库数据管控 区块链技术 深度数据挖掘 深度信念网络 K-MEANS聚类算法 B/S协议 

分 类 号：TN248[电子电信—物理电子学]