Process Discovery Contest Models [1st Edition]

The Process Discovery approach described in the submitted document is directed towards discovery of process models from a Training Event log representing 10 different real time business process executions, and cross-validating the derived model with a set of two Test Event logs provided for evaluation of the process discovery technique. Each of the Test event logs ((test_log_april_1 to test_log_april_10) and (test_log_may_1 to test_log_may_10)) represents part of the model from the Training Log with complete total of 20 traces for each of the logs, and are characterized by having 10 traces that can be replayed (allowed) and 10 traces that cannot be replayed (disallowed) by the model. The total number of traces for the Test event logs (i.e. April log and May log) is therefore ((10 logs x 20 traces) x 2) = 400 Traces. Our aim is to carry out a classification task to determine the 400 individual traces that makes up the two test event log and then provide a Petri Net representation of the Training model as well as Business Process Model Notation (BPMN) mapping that allows for testing and evaluation of the behaviours/traces recorded in the Test logs. The objective of the proposed approach is to discover and provide process models that matches the original process models in term of balancing between “overfitting” and “underfitting”. A process model is seen as overfitting (the event log) if it is too restrictive, disallowing behaviour which is part of the underlying process. On the other hand, it is underfitting (the reality) if it is not restrictive enough, allowing behaviour which is not part of the underlying process. Following this challenge, we aim to provide a model which is as good in balancing “overfitting” and “underfitting” as it is able to correctly classify the traces that can be replayed in the “test” event log: Thus, • Given a trace (t) representing real process behaviour, the process model (m) classifies it as allowed, or • Given a trace (t) representing a behaviour not related to the process, the process model (m) classifies it as disallowed. The submitted document contains the classification attempts for the events logs provided and discusses the replaying semantics of the process modelling notation that has been employed. In other words, we discuss how, given any process trace t (for the Test event Log) and process model m (for the training log) in the discovered Petri Net and BPMN replaying notation, it can be unambiguously determined whether or not trace t can be replayed on model (m). We also provide a description of the tools used to discover the process models as well as checking the result of the classification task.所提交文档中提出的流程发现（Process Discovery）方法，旨在从一份涵盖10种不同实时业务流程执行情况的训练事件日志（Training Event log）中挖掘流程模型，并借助用于评估该流程发现技术的两份测试事件日志（Test Event log）集合，对所得到的模型进行交叉验证。 该两份测试事件日志（分别为test_log_april_1至test_log_april_10，以及test_log_may_1至test_log_may_10）均对应训练日志中模型的部分片段，每份日志总计包含20条轨迹；其中各有10条轨迹可被该模型回放（即允许通过），另外10条轨迹无法被模型回放（即不允许通过）。因此，测试事件日志（含四月日志与五月日志）的总轨迹数为((10条日志 ×20条轨迹) ×2)=400条轨迹。 本研究的目标是完成一项分类任务，以识别构成这两份测试事件日志的全部400条独立轨迹，并提供训练模型的佩特里网（Petri Net）表示形式，以及可用于测试、评估测试日志中记录的行为/轨迹的业务流程模型与符号（Business Process Model Notation，BPMN）映射规则。 所提方法的目标是挖掘得到可在“过拟合（overfitting）”与“欠拟合（underfitting）”之间取得平衡的流程模型，使其匹配原始业务流程模型。若流程模型过于严苛，不允许本应属于目标流程的行为，则称该模型存在过拟合（针对事件日志而言）；反之，若模型约束不足，允许不属于目标流程的行为，则称该模型存在欠拟合（针对实际业务场景而言）。针对这一挑战，本研究旨在构建能够在过拟合与欠拟合间取得良好平衡的模型，使其可准确对测试事件日志中的可回放轨迹进行分类：即： • 若轨迹t代表真实的流程行为，则流程模型m应将其归类为允许通过； • 若轨迹t代表与目标流程无关的行为，则流程模型m应将其归类为不允许通过。 所提交文档包含针对所提供事件日志的分类尝试，并讨论了所采用的流程建模符号的回放语义。换言之，针对所发现的佩特里网与BPMN回放符号，本文将讨论如何基于测试事件日志中的任意流程轨迹t与训练日志对应的流程模型m，明确判定轨迹t是否可在模型m上进行回放。此外，本文还对用于挖掘流程模型以及验证分类任务结果的工具进行了说明。