基于增广Petri网生成受控日志  

Generation of controlled logs based on extended Petri Net

作　　者：邵叱风 方贤文 王吴松 SHAO Chi-feng;FANG Xian-wen;WANG Wu-song(School of Mathematics and Big Data,Anhui University of Science and Technology,Huainan 232001,China;College of Information and Network Engineering,Anhui Science and Technology University,Bengbu 233030,China)

机构地区：[1]安徽理工大学数学与大数据学院,安徽淮南232001 [2]安徽科技学院信息与网络工程学院,安徽蚌埠233030

出　　处：《计算机工程与设计》2022年第3期876-885,共10页Computer Engineering and Design

基　　金：国家自然科学基金项目(61402011、61572035);安徽省自然科学基金项目(1508085MF111、1608085QF149);安徽理工大学研究生创新基金项目(2019CX2068)。

摘　　要：为减少冗余日志,降低事件约束不可控对算法评估及验证的影响,提出基于可达状态的随机选择生成受控日志的方法。利用增广Petri网为系统建立模型,依据模型中库所与变迁的结构关系及标识分布构建输入矩阵;基于Petri网可达状态分析方法,随机选择触发可发生变迁,记录变迁序列;对记录进行受控分析,拼装生成多重集事件日志和XES标准日志。实现相关日志生成工具,利用BPIC2020数据进行实验,与已有工具进行比较,实验结果表明了工具的效率和有效性。To reduce the redundant logs and the impact of uncontrollable event constraints on algorithm evaluation and verification,a method for generating controlled logs based on random selection of the available states was proposed,and the extended Petri Net was used to build a model for the system,and an input matrix was constructed based on the structural relationship between the library and the transformations and the token distribution in the model.Based on the available states analysis method of the Petri Net,random selection triggered the occurrence of transitions and the transition sequence was recorded.Controlled analysis of the records and collocation was carried out to generate multiple set event logs and XES standard logs.The relevant log generation tool was implemented,and experiments were conducted using BPIC2020 data,in which existing tools were adopted for comparison.Experimental results show the efficiency and effectiveness of the proposed approach.

关 键 词：日志冗余 事件约束 佩特里网 可达状态 受控分析 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]