شبیه سازی جریان کاری برای حمایت از تصمیم گیری عملیاتی با استفاده از گراف رویداد از طریق فرآیند داده کاوی

It is increasingly common to see computer-based simulation being used as a vehicle to model and analyze business processes in relation to process management and improvement. While there are a number of business process management (BPM) and business process simulation (BPS) methodologies, approaches and tools available, it is more desirable to have a systemic BPS approach for operational decision support, from constructing process models based on historical data to simulating processes for typical and common problems. In this paper, we have proposed a generic approach of BPS for operational decision support which includes business processes modeling and workflow simulation with the models generated. Processes are modeled with event graphs through process mining from workflow logs that have integrated comprehensive information about the control-flow, data and resource aspects of a business process. A case study of a credit card application is presented to illustrate the steps involved in constructing an event graph. The evaluation detail is also given in terms of precision, generalization and robustness. Based on the event graph model constructed, we simulate the process under different scenarios and analyze the simulation logs for three generic problems in the case study: 1) suitable resource allocation plan for different case arrival rates; 2) teamwork performance under different case arrival rates; and 3) evaluation and prediction for personal performances. Our experimental results show that the proposed approach is able to model business processes using event graphs and simulate the processes for common operational decision support which collectively play an important role in process management and improvement.

Business process management (BPM) has been attracting attention for more than a decade now, and its attention is now shifting from the enactment of business processes towards improving business processes [14]. The field of BPM now supports the design, enactment, control and analysis of business processes [41]. An important part of the evaluation of designed and redesigned business processes is business process simulation (BPS). It enables the analysis of business process models with respect to some performance characteristics such as throughput time, cost or resource utilization. In business process analysis and management, it is possible to have multiple change possibilities concerning the process. Therefore, design and redesign of business process play an important role in process performance improvement. Simulation is mentioned as one of the techniques suitable for the support of redesign [18]. After the simulation of a redesigned process, the simulation result is analyzed to provide a quantitative estimate of the impact that the redesign is likely to have on the process performance. The redesigned processes are compared with the current process helping us to make decisions on the best design. There are a number of BPM and BPS methodologies, approaches and tools available for different applications. However, different model formalisms have different limitations, which make the simulation results deviate from real-world processes. Petri net is a prevailing formalism for process models. However, it is a non-trivial task to mine the relations between activities, such as choice and parallelism, in Petri net. Some tools can deal with loops, but each of them imposes restrictions on the structure of these loops. Although workflow logs contain rich information, e.g. timestamps, organizer and other process related data, they have not been made full use in the majority of existing modeling formalisms. Therefore, it is necessary to research a better formalism which integrates all the aspects of processes in the model so as to express processes more comprehensively. In the meantime, a generic and systemic approach of BPS is lacking for operational decision support, from constructing process models based on historical data to simulating processes for typical and common problems. Enterprises are increasingly using modern software tools such as workflow management systems and enterprise resource planning systems in BPM. As a result, these systems contain rich knowledge of business process in the form as historical data, which can be used to discover underlying process models. Based on these models, BPS can be carried out to estimate the impact on process and support operational decision-making when different design possibilities are considered to be implemented. Current research about BPS is primarily concerned with developing simulation theories, methods and software tools that will directly address the problem of process-based organizational design, but it lacks a generic BPS approach for decision support in general applications. In our attempt to tackle these problems, we propose an approach of workflow simulation for operational decision support using event graphs, which are constructed from log files through process mining [22] and [43] to model business processes and is able to integrate various kinds of process-related information with their different elements. In BPM, we usually need to focus on these problems, i.e. finding a suitable resource allocation plan to help enterprises to economize on resources and reduce cost, judging whether the coming case arrival rate is under control with a specific resource allocation plan to adjust resources flexibly, and analyzing and evaluating personal performances. As a result, we simulate the process based on the generated event graph model under different scenarios and analyze the simulation logs for these three problems: 1) suitable resource allocation plan for a specific case arrival rate; 2) teamwork performance under different case arrival rates with a specific resource allocation plan; and 3) evaluation and prediction from personal performances. All these three problems play an important role in supporting operational decisions to optimize the process. The rest of this paper is organized as follows. Section 2 reviews related work on BPS, event graph and process mining. Our approach for workflow simulation with event graphs through process mining is briefly outlined in Section 3. Section 4 elaborates the approach of deriving an event graph through process mining and its evaluation plans with a case study of a credit card application. The workflow simulation for operational decision support based on the generated event graph model is presented in Section 5. We discuss its comparison with Petri nets and our further considerations about event graph in Section 6. Section 7 concludes.

BPS plays a significant role in process management and improvement. In this paper, we have proposed an approach of workflow simulation for operational decision support with event graphs. Our model is constructed from log files through process mining and evaluations of deriving event graphs are given in terms of precision, generalization and robustness. Based on the generated model, we proceeded with workflow simulation under different scenarios for three typical problems during BPM with a case study of a credit card application. Based on the simulation logs, we are able to find the suitable resource allocation plan for different case arrival rates, judge whether the coming case arrival rate is under control with a specific resource allocation plan and evaluate personal performance. The analysis results of simulations enable enterprises to make operational decisions, which are critical for business process management and improvement.