Detecting Complex Control-Flow Constructs for Choosing Process Discovery Techniques
Hind R’bigui1, Mohammed Abdulhakim Al-Absi2, Chiwoon Cho3
1Hind R’bigui, Digital Enterprise Department, Nsoft, CO., LTD, Ulsan, Republic of Korea.
2Mohammed Abdulhakim Al-Absi, Department of Computer Engineering, Graduate School, Dongseo University, 47 Jurye-ro, Sasang-gu, Busan, Republic of Korea.
3Chiwoon Cho*, School of Industrial Engineering, University of Ulsan, Ulsan 680-749, Republic of Korea.
Manuscript received on October 11, 2019. | Revised Manuscript received on 23 October, 2019. | Manuscript published on November 10, 2019. | PP: 1389-1893 | Volume-9 Issue-1, November 2019. | Retrieval Number: L39141081219/2019©BEIESP | DOI: 10.35940/ijitee.L3914.119119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Process models are the analytical illustration of an organization’s activity. They are very primordial to map out the current business process of an organization, build a baseline of process enhancement and construct future processes where the enhancements are incorporated. To achieve this, in the field of process mining, algorithms have been proposed to build process models using the information recorded in the event logs. However, for complex process configurations, these algorithms cannot correctly build complex process structures. These structures are invisible tasks, non-free choice constructs, and short loops. The ability of each discovery algorithm in discovering the process constructs is different. In this work, we propose a framework responsible of detecting from event logs the complex constructs existing in the data. By identifying the existing constructs, one can choose the process discovery techniques suitable for the event data in question. The proposed framework has been implemented in ProM as a plugin. The evaluation results demonstrate that the constructs can correctly be identified.
Keywords: Process Models, Process Discovery, Event log, Process Structure, Recommendation.
Scope of the Article: Service Discovery and Composition