Morales-Sandoval Miguel, Molina José A, Marin-Castro Heidy M, Gonzalez-Compean Jose Luis
Unidad Tamaulipas, Centro de Investigacion y de Estudios Avanzados, Victoria, Tamaulipas, Mexico.
Facultad de Ingeniería y Ciencias, Cátedras-CONACYT, Universidad Autónoma de Tamaulipas, Victoria, Tamaulipas, México.
PeerJ Comput Sci. 2021 Sep 29;7:e731. doi: 10.7717/peerj-cs.731. eCollection 2021.
In an Inter-Organizational Business Process (IOBP), independent organizations (collaborators) exchange messages to perform business transactions. With process mining, the collaborators could know what they are actually doing from process execution data and take actions for improving the underlying business process. However, process mining assumes that the knowledge of the entire process is available, something that is difficult to achieve in IOBPs since process execution data generally is not shared among the collaborating entities due to regulations and confidentiality policies (exposure of customers' data or business secrets). Additionally, there is an inherently lack-of-trust problem in IOBP as the collaborators are mutually untrusted and executed IOBP can be subject to dispute on counterfeiting actions. Recently, Blockchain has been suggested for IOBP execution management to mitigate the lack-of-trust problem. Independently, some works have suggested the use of Blockchain to support process mining tasks. In this paper, we study and address the problem of IOBP mining whose management and execution is supported by Blockchain. As contribution, we present an approach that takes advantage of Blockchain capabilities to tackle, at the same time, the lack-of-trust problem (management and execution) and confident execution data collection for process mining (discovery and conformance) of IOBPs. We present a method that () ensures the business rules for the correct execution and monitoring of the IOBP by collaborators, () creates the event log, with data cleaning integrated, at the time the IOBP executes, and () produces useful event log in XES and CSV format for the discovery and conformance checking tasks in process mining. By a set of experiments on real IOBPs, we validate our method and evaluate its impact in the resulting discovered models (fitness and precision metrics). Results revealed the effectiveness of our method to cope with both the lack-of-trust problem in IOBPs at the time that contributes to collect the data for process mining. Our method was implemented as a software tool available to the community as open-source code.
在组织间业务流程（IOBP）中，独立组织（协作方）通过交换消息来执行商业交易。借助流程挖掘，协作方能够从流程执行数据中了解他们实际在做什么，并采取行动改进基础业务流程。然而，流程挖掘假定整个流程的知识是可用的，而这在IOBP中很难实现，因为由于法规和保密政策（客户数据或商业机密的暴露），流程执行数据通常不会在协作实体之间共享。此外，IOBP中存在固有的信任缺失问题，因为协作方相互不信任，并且执行的IOBP可能会因伪造行为而引发争议。最近，有人建议将区块链用于IOBP执行管理，以缓解信任缺失问题。独立地，一些工作建议使用区块链来支持流程挖掘任务。在本文中，我们研究并解决了由区块链支持管理和执行的IOBP挖掘问题。作为贡献，我们提出了一种利用区块链功能的方法，同时解决信任缺失问题（管理和执行）以及为IOBP的流程挖掘（发现和一致性）收集可信执行数据的问题。我们提出了一种方法，该方法（1）确保协作方正确执行和监控IOBP的业务规则，（2）在IOBP执行时创建集成了数据清理的事件日志，以及（3）以XES和CSV格式生成用于流程挖掘中的发现和一致性检查任务的有用事件日志。通过对实际IOBP进行的一组实验，我们验证了我们的方法，并评估了其对所得发现模型（适合度和精度指标）的影响。结果表明，我们的方法在解决IOBP中信任缺失问题的同时，有助于为流程挖掘收集数据，具有有效性。我们的方法作为一个软件工具实现，并以开源代码的形式提供给社区。
