Robotic Process Automation (RPA) has gained widespread adoption in corporate organizations, streamlining work processes while also introducing additional maintenance tasks. Effective governance of RPA can be achieved through the reusability of RPA components. However, refactoring RPA processes poses challenges when dealing with larger development teams, outsourcing, and staff turnover. This research aims to explore the possibility of identifying similarities in RPA processes for refactoring. To address this issue, we have developed Similarity Discovering Techniques for RPA (SiDiTeR). SiDiTeR utilizes source code or process logs from RPAautomations to search for similar or identical parts within RPA processes. The techniques introduced are specifically tailored to the RPA domain. We have expanded the potential matches by introducing a dictionary feature which helps identify different activities that produce the same output, and this has led to improved results in the RPA domain. Through our analysis, we have discovered 655 matches across 156 processes, with the longest match spanning 163 occurrences in 15 processes. Process similarity within the RPA domain proves to be a viable solution for mitigating the maintenance burden associated with RPA. This underscores the significance of process similarity in the RPA domain.

翻译：摘要：机器人流程自动化（RPA）在企业组织中已得到广泛应用，其在优化工作流程的同时亦引入了额外的维护任务。通过实现RPA组件的可复用性，可达成对RPA的有效治理。然而，当面对大型开发团队、业务外包及人员流动时，重构RPA流程面临诸多挑战。本研究旨在探索通过识别RPA流程中的相似性来实现重构的可能性。针对该问题，我们开发了面向RPA的相似性发现技术（SiDiTeR）。该技术利用RPA自动化过程中的源代码或流程日志，搜索RPA流程中的相似或相同部分。所提出的技术专为RPA领域定制。通过引入字典特征——该特征有助于识别产生相同输出的不同活动——我们扩充了潜在匹配项，进而提升了RPA领域内的分析效果。经分析，我们在156个流程中共发现655个匹配项，其中最长匹配项横跨15个流程、累计出现163次。RPA领域的流程相似性被证明是缓解RPA维护负担的可行方案，这凸显了流程相似性在RPA领域的重要价值。