一种面向船舶制造的数据关联规则挖掘算法  

A data association rule mining algorithm for shipbuilding

作　　者：徐鹏 孟宇龙[3] 杨哲 董乃波 邓博伟 XU Peng;MENG Yu-long;YANG Zhe;DONG Nai-bo;DENG Bo-wei(The 716 Research Institute of CSSC,Lianyungang 222006,China;Jiangsu JARI Technology Group Co.Ltd.,Lianyungang 222006,China;College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]中国船舶集团有限公司第七一六研究所,江苏连云港222006 [2]江苏杰瑞科技集团有限责任公司,江苏连云港222006 [3]哈尔滨工程大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《舰船科学技术》2022年第20期143-148,共6页Ship Science and Technology

摘　　要：针对船舶制造海量数据关联规则挖掘过程中,事务集占用空间过多导致挖掘效率较低的问题,提出一种基于局部敏感位图存储结构(locally sensitive hash bitmap,LBM)的LBM-Eclat算法。该算法结合了局部敏感哈希和位图2种数据结构,并可以根据存储数据量的变化动态调整内部数据存储结构。通过对比实验证明基于LBM的LBM-Eclat算法能够有效提升对密集型数据集的挖掘效率,同时减少挖掘过程中的空间消耗。In order to solve the problem of low mining efficiency caused by too much space occupied by transaction sets in the process of mining association rules of shipbuilding massive data,the Eclat algorithm is used to convert the merging of transactions into set operations using vertical databases.A LBM-Eclat algorithm based on locally sensitive hash bitmap(LBM)is proposed.LBM Eclat combines two data structures,local sensitive hash and bitmap,and can dynamically adjust the internal data storage structure according to the changes of the amount of stored data.Through comparative experiments,it is proved that LBM-Eclat algorithm based on LBM can effectively improve the mining efficiency of dense data sets and reduce the space consumption in the mining process.

关 键 词：船舶制造数据 关联规则挖掘 LBM-Eclat算法 局部敏感哈希 位图 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]