Process executions in organizations generate a large variety of data. Process mining is a data-driven analytical approach for analyzing this data from a business process point of view. Online conformance checking deals with finding discrepancies between real-life and modeled process behavior on data streams. The current state-of-the-art output of online conformance checking is a prefix-alignment, which is used for pinpointing the exact deviations in terms of the trace and the model while accommodating a trace's unknown termination in a streaming setting. However, producing prefix-alignments entails a state space search to find the shortest path from a common start state to a common end state between the trace and the model. This is computationally expensive and makes the method infeasible in an online setting. Previously, the trie data structure has been shown to be efficient for constructing alignments, utilizing a proxy log representing the process model in a finite way. This paper introduces a new approximate algorithm (IWS) on top of the trie for online conformance checking. The algorithm is shown to be fast, memory-efficient, and able to output both a prefix and a complete alignment event-by-event while keeping track of previously seen cases and their state. Comparative analysis against the current state-of-the-art algorithm for finding prefix-alignments shows that the IWS algorithm achieves, in some cases, an order of magnitude faster execution time while having a smaller error cost. In extreme cases, the IWS finds prefix-alignments roughly three orders of magnitude faster than the current state of the art. The IWS algorithm includes a discounted decay time setting for efficient memory usage and a look-ahead limit for improving computation time. Finally, the algorithm is stress tested for performance using a simulation of high-traffic event streams.
翻译:组织内部的流程执行生成大量数据。 进程采矿是一种数据驱动的分析分析方法, 用于从业务流程角度分析这些数据。 在线合规检查处理数据流中真实生命和模型化进程行为之间的差异。 目前最新的在线合规检查输出是前缀对齐, 用于在流环境中定位跟踪和模型的准确偏差, 同时也在流环境中容纳未知的结束。 但是, 生成前缀对齐要求用州间空间搜索找到从共同起始状态到跟踪和模型之间共同结束状态的最短路径。 这在计算成本上非常昂贵, 使得在线设置中无法采用该方法。 之前, 三角数据结构被显示对构建匹配有效, 使用代表进程模型的代理日志, 在流环境中为在线合规检查提供新的近似算法( IWS) 。 算法显示快速、 记忆节率, 并且能够同时根据当前轨迹的轨迹进行一个时间级算, 最终的运算中, 运行前程的运行前代代程中, 运行前代程的运行前代程中, 运行前代程的运行前代程分析。 排序中, 运行前的运行前的运行中, 运行前的运行前的运行前的运行前路的运行前路段, 显示前的运行前路段的运行前路段。 运行前的运行前路的运行前的运行前路的运行前路的运行前路的运行前路的运行前路的运行前路的运行中, 排序。 显示的运行前路的运行前路的运行前路的运行前路的运行前路的运行状态显示的运行前路。 前路的运行前路。,, 排序的运行前路的运行前路的运行前路的运行前路的运行前路的运行前路的运行前路的运行的运行的运行的预的运行的运行的运行的运行的运行的运行的运行的运行的运行的运行的运行的运行中, 。 显示的运行的运行的运行的运行中, 显示的运行前路。