基于特征挖掘的IT终端设备异常响应检测方法  

Abnormal Response Detection Method of IT Terminal Equipment Based on Feature Mining

作　　者：毛雯新 MAO Wenxin(Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen Guangdong 518000,China)

机构地区：[1]深圳供电局有限公司,广东深圳518000

出　　处：《信息与电脑》2022年第17期168-170,共3页Information & Computer

摘　　要：为提高异常响应检测方法的检出率与实时性,降低互联网技术(InternetTechnology,IT)终端设备异常响应误报率,提出了基于特征挖掘的IT终端设备异常响应检测方法。先利用最小协方差行列式估算IT终端设备的响应分布情况,再获取历史异常响应数据,构建基于关联规则的异常响应特征挖掘算法,最后对设备运行数据进行自相似系数检测,并通过数据比对的方式完成异常检测。实验结果表明,该方法有效提升了IT终端设备异常响应检出率与实时性,且有效控制了检测结果的误报率,说明该方法具有较好的应用效果。In order to improve the detection rate and real-time performance of the abnormal response detection method and reduce the false alarm rate of the abnormal response of Internet Technology(IT)terminal equipment,this research proposes an abnormal response detection method of IT terminal equipment based on feature mining.Firstly,it is advantageous to estimate the response distribution of IT terminal equipment by the least covariance determinant,then obtain the historical abnormal response data,and build an abnormal response feature mining algorithm based on association rules.Finally,the self similarity coefficient of the equipment operation data is detected,and the anomaly detection is completed by data comparison.The comparative experimental results show that after the application of this method,the abnormal response detection rate and real-time performance of IT terminal equipment are effectively improved,and the false alarm rate of the detection results is controlled,which indicates that this method has achieved good application effect.

关 键 词：特征挖掘 关联规则 互联网技术(IT)终端设备 异常响应检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]