Process Mining: A New Approach for Simplifying the Process Model Control Flow Visualization

Abstract

Process mining is a young discipline that provides a variety of techniques for extracting data from recorded event logs. In this context, process model is simulated, from event logs, to help enterprises to better understand their business processes. In this context, the discovery technique has always been a significant focus of process mining research. But despite the availability of several proposed approaches, participated in this process model visualization, we observe as the number of activities increases, the representation of the entire control flow becomes quite tedious. Indeed, event logs complexity make the process model visualization more difficult in terms of logical links and number of causal relationships between activities. Therefore, we propose a new method for simplifying the process model control flow visualization. This is done by using mainly string similarity algorithms to visually summarizes the number of activities, sequence of execution, relative significance, and dependencies.