信息网络安全

信息网络安全 ›› 2021, Vol. 21 ›› Issue (12): 31-37.doi: 10.3969/j.issn.1671-1122.2021.12.005

• 入选论文 • 上一篇    下一篇

基于离散轨迹的重点人员伴随关系挖掘模型

康文杰1,2,3, 赵薇1,4(), 刘绪崇1, 苏欣1   

  1. 1.湖南警察学院网络侦查技术湖南省重点实验室,长沙 410138
    2.国防科技大学系统工程学院,长沙 410073
    3.警务物联网应用技术公安部重点实验室,北京 100089
    4.国防科技大学计算机学院,长沙 410073
  • 收稿日期:2021-09-25 出版日期:2021-12-10 发布日期:2022-01-11
  • 通讯作者: 赵薇 E-mail:zhaowei08a@nudt.edu.cn
  • 作者简介:康文杰（1987—）,男,山西,讲师,博士,主要研究方向为复杂网络、物联网安全、警务大数据|赵薇（1982—）,女,湖南,副教授,硕士,主要研究方向为大数据与网络安全|刘绪崇（1974—）,男,湖南,教授,博士,主要研究方向为警务大数据|苏欣（1983—）,男,湖南,副教授,博士,主要研究方向为警务大数据
  • 基金资助:
    湖南省科技厅重点研发项目(2022SK2109);长沙市自然科学基金(kq2007088);高新技术产业科技创新引领计划(2020GK2029);网络犯罪侦查湖南省普通高校重点实验室开放基金课题(2020WLZC003);湖南警察学院2021年度高层次人才科研启动基金(2021KYQD16);湖南警察学院2021年度高层次人才科研启动基金(2021KYQD15);警务物联网应用技术公安部重点实验室2020年度开放课题

Adjoint Relation Mining Model of Key Personnel Based on Discrete Trajectory

KANG Wenjie1,2,3, ZHAO Wei1,4(), LIU Xuchong1, SU Xin1   

  1. 1. Hunan Provincial Key Laboratory of Network Investigational Technology, Hunan Police Academy, Changsha 410138, China
    2. College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
    3. The Key Laboratory of Police Internet of Things Application Ministry of Public Security, Beijing 100089, China
    4. College of Computer, National University of Defense Technology, Changsha 410073, China
  • Received:2021-09-25 Online:2021-12-10 Published:2022-01-11
  • Contact: ZHAO Wei E-mail:zhaowei08a@nudt.edu.cn

RichHTML

21

PDF (PC)

95

摘要：

文章提出一种基于离散空间轨迹矩阵分析的重点人员伴随关系挖掘方法,针对离散空间轨迹构建人与地址的映射矩阵,通过对人员地址关系矩阵进行关联分析识别伴随关系,针对离散时空轨迹构建基于有效距离判定的伴随关系挖掘模型,通过距离、时间、空间等特征对重点人员进行伴随关系挖掘。实验结果表明,基于离散空间轨迹矩阵分析方法可以快速识别人群中存在伴随关系的人,且在给定某个重点人员的情况下,可以快速找到与之存在伴随关系的人群,并对这些人的伴随次数进行排序,便于安防人员溯源和追踪;伴随人的数量与有效距离在一定程度上成正比,伴随次数与数据量正相关。

关键词: 离散空间轨迹, 离散时空轨迹, 重点人员, 伴随关系挖掘

Abstract:

This paper proposes a method for mining key personnel adjoint relations based on discrete space trajectory matrix analysis. A mapping matrix between people and addresses is constructed for discrete space trajectories. The adjoint relations are identified through correlation analysis of the personnel address relationship matrix, and the discrete spatio-temporal trajectories are constructed. An adjoint relationship mining model based on effective distance judgments can mine the adjoint relationship of key personnel through features such as distance, time, and space. The experimental results show that the analysis method based on the discrete space trajectory matrix can quickly identify the people who have an adjoint relationship in the crowd, and given a certain key person, you can quickly find the people who have an adjoint relationship with them, and deal with these people. The number of adjoint persons is sorted, which is convenient for security personnel to trace and track in the future. In addition, the number of adjoint pairs is directly proportional to the effective distance to a certain extent, and the number of adjoint pairs is positively correlated with the increase of the amount of data.

Key words: discrete space trajectory, discrete spatio-temporal trajectory, key personnel, adjoint relation mining

中图分类号: