摘要
利用数据挖掘技术分析潜在盗窃人员的异常数据能够有效提高对盗窃行为的预警和治安力量的优化配置。文章研究如何利用信息增益决策树对涉嫌盗窃的情报信息进行快速分类,分类过程为从根节点的涉嫌盗窃的行为人属性开始不断产生新的分支。产生每个分支都需要计算不同属性的信息增益并选择分裂属性。该方法可以对大量涉嫌盗窃的情报信息基础数据进行快速分类,在实际工作中可以与关联分析、聚类分析、异常检测等其他数据挖掘方法组合使用。
Using data mining technology to analyze abnormal data of potential thieves can effectively improve the early warning of theft and optimize the allocation of public security forces.This article will study how to use information gain decision trees to quickly classify intelligence information suspected of theft.The classification process involves continuously generating new branches starting from the suspected theft behavior attribute of the root node.Generating each branch requires calculating the information gain of different attributes and selecting split attributes.The method in the article can quickly classify a large amount of intelligence information basic data suspected of theft,and can be combined with other data mining methods such as association analysis,clustering analysis,and anomaly detection in practical work.
作者
张鹏
ZHANG Peng(ChinaPeople's Police University,Langfang 065000)
出处
《长江信息通信》
2023年第11期157-161,共5页
Changjiang Information & Communications
基金
2022-2023年中国人民警察大学学生科技创新计划项目“面向社会安全事件的公安开源情报开发利用策略研究”(项目编号:yjskc22004)。
关键词
盗窃
信息增益
决策树
数据挖掘
theft
Information gain
Decision tree
data mining
