Abstract：［Objective］ Artificial intelligence and big data technologies have been used to solve many scientific problems, including crime analysis. The investigation of criminal cases has always been a critical and difficult point in the domain of crime analysis. The investigation stage of criminal cases primarily consists of evidence collection and evidence reasoning, and comprehensive and efficient collection and reasoning of evidence are critical to the rapid detection of cases. Simultaneously, the significance of the various pieces of evidence in the case varies. Evidence of high importance gathered during the investigation stage is critical for the accurate and efficient resolution of crime cases. However, existing research lacks the application of artificial intelligence methods to crime investigation decision support. ［Methods］ Aiming at the problem of crime investigation, this research proposes a decision support model based on the Bayesian network to help domain experts determine the direction of the investigation and reasoning the criminal facts. First, the Bayesian network is used to reason the hypothesis of criminal facts. Second, the weighted information entropy method is used to calculate the importance of criminal evidence. Four different types of weighted information entropy methods are employed to test the efficiency of the calculation method. The two methodologies are then combined to create the decision support model for crime investigation. Finally, the proposed model is applied to 420 crime cases to verify its accuracy, and the proposed model is also applied to a real case analysis to illustrate the application process of the model. ［Results］ The analysis of 420 crime cases reveals that calculations based on weighted information entropy are the best of all four methods. The top 3, 5, and 10 evidence pieces provided with the weighted information entropy method all have the highest coverage of importance, given any arbitrary evidence missing ratio. Meanwhile, when 50% of the evidence is missing, the output result's coverage of the top 3, 5, and 10 important pieces of evidence is greater than 50%, 65%, and 80%, respectively; when 90% of the evidence is missing, the coverage of the top 3, 5, and 10 evidence pieces is greater than 40%, 60% and 75%, respectively. These suggest that the model's detection recommendations are effective and can be used to assist in crime detection. Furthermore, the analysis of a real-world case also shows that the proposed model can generate effective investigation suggestions and provide decision support for evidence collection and reasoning during the investigation stage. ［Conclusions］ Finally, the proposed decision support model for crime investigation can analyze available case information and generate effective investigation suggestions and reasoning conclusions. However, it should be noted that the model developed in this study does not completely replace the role of professionals in the field of criminal investigations but rather provides analysis results to scientifically support the decisions of subsequent investigators in the initial stages of the investigation. Furthermore, this study focuses on the research of evidence collection and reasoning during the investigation stage of criminal cases but pays limited attention to the “evidence standard” involved in the process of evidence collection. Therefore, we can continue to investigate this aspect in the future to aid intelligence and standardization of evidence collection during the investigation stage.
王佳, 王维曦, 王李韬, 申世飞. 犯罪侦查决策支持模型[J]. 清华大学学报（自然科学版）, 2023, 63(10): 1598-1607.
WANG Jia, WANG Weixi, WANG Litao, SHEN Shifei. A decision support model for crime investigation. Journal of Tsinghua University(Science and Technology), 2023, 63(10): 1598-1607.
[1] 高航.提高侦查效率的逻辑方法:奥卡姆剃刀[J].湖北警官学院学报, 2014, 27(4):37-39. GAO H. Logical method to improve the efficiency of investigation:Occam's razor[J]. Journal of Hubei University of Police, 2014, 27(4):37-39.(in Chinese) [2] SKERRETT J, NEUMANN C, MATEOS-GARCIA I. A Bayesian approach for interpreting shoemark evidence in forensic casework:Accounting for wear features[J]. Forensic Science International, 2011, 210(1-3):26-30. [3] VLEK C S, PRAKKEN H, RENOOIJ S, et al. A method for explaining Bayesian networks for legal evidence with scenarios[J]. Artificial Intelligence and Law, 2016, 24(3):285-324. [4] KEPPENS J, SHEN Q, PRICE C. Compositional Bayesian modelling for computation of evidence collection strategies[J]. Applied Intelligence, 2011, 35(1):134-161. [5] 蒋莉莉.基于贝叶斯网络的刑事侦查决策模型研究[D].南京:河海大学, 2007. JIANG L L. Research on crime investigation decision modelling based on Bayesian network[D]. Nanjing:Hohai University, 2007.(in Chinese) [6] 李娟,杨帆.论结构主义视角下犯罪现场的重建与再现[J].山西警察学院学报, 2020, 28(3):105-110. LI J, YANG F. On the reconstruction and reappearance of the crime scene from the perspective of structuralism[J].Journal of Shanxi Police College, 2020, 28(3):105-110.(in Chinese) [7] 王杰,周志杰,胡昌华,等.不确定性信息表示及推理[J/OL].(2022-06-29)[2022-08-22] . https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=KZYC2022062800I&uniplatform=NZKPT&v=SFfl7Znyzm6_iLbtMGuLxosAE7lgyQ5aSzkkC7I2VIk4BNcnJTLsTz6ENnExbI63. WANG J, ZHOU Z J, HU C H, et al. Expression and inference of uncertain information[J/OL].(2022-06-29)[2022-08-22] . https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=KZYC2022062800I&uniplatform=NZKPT&v=SFfl7Znyzm6_iLbtMGuLxosAE7lgyQ5aSzkkC7I2VIk4BNcnJTLsTz6ENnExbI63.(in Chinese) [8] WANG L T, JIA M S, PENG C, et al. Scenario-entity analysis based on an entity-relationship model:Revisiting crime reconstruction[J]. Forensic Science International, 2019, 302:109923. [9] 徐祖润,刘思峰,方志耕,等.基于信息融合的罪案关联证据推理模型[J].控制与决策, 2020, 35(1):228-234. XU Z R, LIU S F, FANG Z G, et al. Crime-related evidence reasoning model based on information fusion[J]. Control and Decision, 2020, 35(1):228-234.(in Chinese) [10] VERHEIJ B, BEX F, TIMMER S T, et al. Arguments, scenarios and probabilities:Connections between three normative frameworks for evidential reasoning[J]. Law, Probability and Risk, 2016, 15(1):35-70. [11] 孙健.溯因推理的逻辑认知研究[D].杭州:浙江大学, 2019. SUN J. Research on abduction from a logical-cognitive view[D]. Hangzhou:Zhejiang University, 2019.(in Chinese) [12] TUZET G. Abduction, IBE and standards of proof[J]. The International Journal of Evidence&Proof, 2019, 23(1-2):114-120. [13] BEX F J. Arguments, stories and criminal evidence:A formal hybrid theory[M]. Dordrecht:Springer, 2011. [14] BEX F J, VAN KOPPEN P J, PRAKKEN H, et al. A hybrid formal theory of arguments, stories and criminal evidence[J]. Artificial Intelligence and Law, 2010, 18(2):123-152. [15] 王万良.人工智能导论[M]. 4版.北京:高等教育出版社, 2017. WANG W L. Introduction to artificial intelligence[M]. 4th ed. Beijing:Higher Education Press, 2017.(in Chinese) [16] 鲁斌,刘丽,李继荣,等.人工智能及应用[M].北京:清华大学出版社, 2017. LU B, LIU L, LI J R, et al. Artificial intelligence and applications[M]. Beijing:Tsinghua University Press, 2017.(in Chinese) [17] BIEDERMANN A, TARONI F. Bayesian networks for evaluating forensic DNA profiling evidence:A review and guide to literature[J]. Forensic Science International:Genetics, 2012, 6(2):147-157. [18] AITKEN C G G, GAMMERMAN A J. Probabilistic reasoning in evidential assessment[J]. Journal of the Forensic Science Society, 1989, 29(5):303-316. [19] TAYLOR D, BIEDERMANN A, HICKS T, et al. A template for constructing Bayesian networks in forensic biology cases when considering activity level propositions[J]. Forensic Science International:Genetics, 2018, 33:136-146. [20] FENTON N, NEIL M, YET B, et al. Analyzing the Simonshaven case using Bayesian networks[J]. Topics in Cognitive Science, 2020, 12(4):1092-1114. [21] BIEDERMANN A, TARONI F, DELEMONT O, et al. The evaluation of evidence in the forensic investigation of fire incidents. Part II. Practical examples of the use of Bayesian networks[J]. Forensic Science International, 2005, 147(1):59-69. [22] WANG J, XU Z J. Bayesian inferential reasoning model for crime investigation[J]. Frontiers in Artificial Intelligence and Applications, 2014, 262:59-67. [23] 杨焘.数字化证据标准的合理性及限度分析:以上海"206 "智能系统为关注点[J].四川师范大学学报(社会科学版), 2020, 47(5):34-45. YANG T. On the rationality and limitation of digital evidence standard:Focusing on Shanghai" 206"intelligent system[J]. Journal of Sichuan Normal University (Social Sciences Edition), 2020, 47(5):34-45.(in Chinese) [24] 李小南,赵璐,易黄建.基于加权信息熵的直觉模糊信息系统的三支决策[J].控制与决策, 2022, 37(10):2705-2713. LI X N, ZHAO L, YI H J. Three-way decision of intuitionistic fuzzy information systems based on the weighted information entropy[J]. Control and Decision, 2022, 37(10):2705-2713.(in Chinese) [25] CHISUM W J. Crime reconstruction[M]//MOZAYANI A, NOZIGLIA C. The forensic laboratory handbook:procedures and practice. Totowa, NJ:Humana Press, 2006:63-77. [26] 郝宏奎.论犯罪现场重建[J].犯罪研究, 2003(4):13-21. HAO H K. On the reconstruction of the crime scene[J].Criminal Research, 2003(4):13-21.(in Chinese) [27] WANG L T, JIA M S, SHIY, et al. A knowledge-based reasoning model for crime reconstruction and investigation[J]. Expert Systems with Applications, 2020, 159:113611. [28] SHANNON C E. A mathematical theory of communication[J]. The Bell System Technical Journal, 1948, 27(3):379-423.
2023, Vol. 63 
