Event abstraction in process mining: literature review and taxonomy

Abstract

The execution of processes in companies generates traces of event data, stored in the underlying information system(s), capturing the actual execution of the process. Analyzing event data, i.e., the focus of process mining, yields a detailed understanding of the process, e.g., we are able to discover the control flow of the process and detect compliance and performance issues. Most process mining techniques assume that the event data are of the same and/or appropriate level of granularity. However, in practice, the data are extracted from different systems, e.g., systems for customer relationship management, Enterprise Resource Planning, etc., record the events at different granularity levels. Hence, pre-processing techniques that allow us to abstract event data into the right level of granularity are vital for the successful application of process mining. In this paper, we present a literature study, in which we assess the state-of-the-art in the application of such event abstraction techniques in the field of process mining. The survey is accompanied by a taxonomy of the existing approaches, which we exploit to highlight interesting novel directions.

Towards IoT-driven Process Event Log Generation for Conformance Checking in Smart Factories

“…First of all, event abstraction is needed to map multiple fine-grained sensor data to coarse-grained process events [18], e. g., with the help of CEP [6], which also supports data pre-processing and context enrichment [2]; or with machine learning approaches such as clustering [19] or supervised learning [20]. Wanner et al combine these two methods based on expert knowledge and observations in the context of a smart factory [21].…”

“…Then, such coarse-granular events need to be matched to the process activities in a process model or correlated to the process instances through event-to-activity mappings [15], [22]. We discuss work about event log generation from IoT events that mostly relates to our contribution and refer the interested reader to [6], [18] for a broader literature overview.…”

Conformance Checking of a Longwall Shearer Operation Based on Low-Level Events

“…This action requires a great amount of domain knowledge and it mostly involves manual and ad hoc solutions. The challenge mentioned gave rise to a number of solutions and techniques for event log creation, presented, among others, in [14,[18][19][20][21].…”

Domain-Specific Event Abstraction

“…Moreover, the fact that many events are documented manually by physicians or other medical personnel typically leads to varying degrees of detail in the recorded events. Using the resulting event logs would result in complex process models [3]- [5]. In order to generate event logs with events of comparable granularity and to elicit useful process models, event abstraction is needed.…”

“…methods and techniques exists, as shown in [3], [6]. But fewer research works utilize existing domain knowledge.…”