地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (1): 43-57.doi: 10.12082/dqxxkx.2021.200247

• 地球信息科学综述 • 上一篇    下一篇

犯罪时空预测方法研究综述与展望

顾海硕1,*, 陈鹏1(), 李慧波2   

  1. 1.中国人民公安大学信息网络安全学院,北京 102600
    2.社会安全风险感知与防控大数据应用国家工程实验室,北京 100043
  • 收稿日期:2020-05-19 修回日期:2020-06-29 出版日期:2021-01-25 发布日期:2021-03-25
  • 通讯作者: 顾海硕,陈鹏 E-mail:chenpeng@ppsuc.edu.cn
  • 作者简介:顾海硕(1995—),男,硕士生,浙江嘉兴人,研究方向为警务大数据分析。E-mail: 603263780@qq.com
  • 基金资助:
    北京市自然科学基金项目(9192022);社会安全风险感知与防控大数据应用国家工程实验室主任基金项目

Overview and Prospect for Spatial-Temporal Prediction of Crime

GU Haisuo1,*, CHEN Peng1(), LI Huibo2   

  1. 1. School of Information Network Security, People's Public Security University of China, Beijing 102600 China
    2. National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data (PSRPC), Beijing 100043, China
  • Received:2020-05-19 Revised:2020-06-29 Online:2021-01-25 Published:2021-03-25
  • Contact: GU Haisuo,CHEN Peng E-mail:chenpeng@ppsuc.edu.cn
  • Supported by:
    National Natural Science Foundation of Beijing(9192022);National Engineering Laboratory Director Fund for Social Security Risk Perception and Prevention and Control of Large Data Applications

摘要:

犯罪时空预测作为预测警务的核心支撑技术,自2000年左右至今得到了快速的发展。本文介绍了犯罪时空预测的实践背景和理论基础,将犯罪时空预测解构为利用历史案件的时空位置、时空环境和个体行为等要素,结合相应的算法模型预测未来案件时空分布的过程。然后,从输入要素的视角对当前的犯罪时空预测方法进行了总结和归纳,将其划分为基于案件时空位置信息的犯罪时空预测、基于时空环境要素的犯罪时空预测,以及融合行为轨迹和时空环境要素的犯罪时空预测3种类型,详细总结了不同类型犯罪时空预测的方法原理,并从适应场景和预测效果等方面对不同的方法模型进行了比较。最后,结合当前的大数据技术发展趋势,对未来的犯罪时空预测进行了展望。本文认为犯罪时空预测未来需要从数据角度重点解决输入数据的体系融合、粒度细化和新型数据融合等问题,从模型优化角度应着重提高多源异构数据融合能力,平衡模型的可解释性与预测效果。

关键词: 犯罪预测, 犯罪时空风险, 大数据, 预测警务, 预测技术, 环境犯罪学

Abstract:

As the core technology of predictive policing, Spatial-Temporal (ST) prediction of crime has developed rapidly from around 2000 to the present. We introduce the basic theory of ST prediction of crime at the beginning. We regard the ST prediction method of crime as a process combining corresponding models to predict the ST distribution of crimes in the future and deconstruct it into relationships between three objects: case, ST backcloth, and individual behavior. Then, based on the input factors of prediction models, we sum up three current main methods, including ① the prediction method based on the information of cases' ST location, ② the prediction method based on the backcloth and the information of cases' ST location, and ③ the prediction method based on individual behavior, the backcloth, and the information of cases' ST location. We further summarize the mechanisms of different methods in detail respectively. In addition, we compare and analyze each method based on their applicable scenarios and predictive capacities. Finally, with the development of big data technology, we present solutions to improve current prediction methods, that are to construct a data-fusion system, refine data granularity, and integrate new types of data. For model optimization, we need to improve the ability of integrating heterogeneous data from multiple sources and balancing the interpretability and predictive ability of models.

Key words: crime prediction, crime spatio-temporal risk, big data, predictive policing, predictive methods, environmental criminology