Checking Conformance of High-Level Business Process Models to Event Logs
Process mining is a new technology, that provides us a variety of methods to discover, monitor and improve real processes by extracting knowledge from event logs. The two most prominent process mining tasks are process discovery and conformance checking. Conformance checking deals with diagnosing and quantifying discrepancies between observed behavior, represented in event logs, and modeled behavior. We present a method for checking conformance of abstract models and low-level event logs.
BPM 2013 was the 11th conference in a series that provides a prestigious forum for researchers and practitioners in the field of business process management (BPM). The conference was organized by Tsinghua University, China, and took place during August 26–30, 2013, in Beijing, China. Compared to previous editions of BPM, this year we noted a lower focus by authors on topics like process modeling, while we also observed a considerable growth of submissions regarding areas like process mining, conformance/compliance checking, and process model matching. The integrated consideration of processes and data remains popular, and novel viewpoints focus, among others, on data completeness in business processes, the modeling and runtime support of event streaming in business processes, and business process architectures.
Recent breakthroughs in process mining research make it possible to discover, analyze, and improve business processes based on event data. The growth of event data provides many opportunities but also imposes new challenges. Process mining is typically done for an isolated well-defined process in steady-state. However, the boundaries of a process may be fluid and there is a need to continuously view event data from different angles. This paper proposes the notion of process cubes where events and process models are organized using different dimensions. Each cell in the process cube corresponds to a set of events and can be used to discover a process model, to check conformance with respect to some process model, or to discover bottlenecks. The idea is related to the well-known OLAP (Online Analytical Processing) data cubes and associated operations such as slice, dice, roll-up, and drill-down. However, there are also significant differences because of the process-related nature of event data. For example, process discovery based on events is incomparable to computing the average or sum over a set of numerical values. Moreover, dimensions related to process instances (e.g. cases are split into gold and silver customers), subprocesses (e.g. acquisition versus delivery), organizational entities (e.g. backoffice versus frontoffice), and time (e.g., 2010, 2011, 2012, and 2013) are semantically different and it is challenging to slice, dice, roll-up, and drill-down process mining results efficiently.
Журналы событий, сохраняемые современными информационными и техническими системами, как правило, содержат достаточно данных для автоматизированного восстановления моделей соответствующих процессов. Разработано множество алгоритмов для построения моделей процессов, проверки соответствия фактического поведения системы модельному, сравнения моделей процессов, и т.д. Однако возможность быстрого анализа выбираемых пользователями частей журнала до сих пор не нашла полноценной реализации. В статье описан метод многомерного хранения журналов событий для извлечения и анализа процессов, основанный на подходе ROLAP. Результатом анализа журнала является направленный невзвешенный граф, представляющий собою сумму возможных последовательностей событий, упорядоченных по вероятности их возникновения с учетом заданных условий. Разработанный инструмент позволяет выполнять совместный анализ моделей подпроцессов, восстановленных из частей журнала путем задания критериев отбора событий и требуемого уровня детализации модели.
The practical relevance of process mining is increasing as more and more event data become available. Process mining techniques aim to discover, monitor and improve real processes by extracting knowledge from event logs. The two most prominent process mining tasks are: (i) process discovery: learning a process model from example behavior recorded in an event log, and (ii) conformance checking: diagnosing and quantifying discrepancies between observed behavior and modeled behavior. The increasing volume of event data provides both opportunities and challenges for process mining. Existing process mining techniques have problems dealing with large event logs referring to many different activities. Therefore, we propose a generic approach to decompose process mining problems. The decomposition approach is generic and can be combined with different existing process discovery and conformance checking techniques. It is possible to split computationally challenging process mining problems into many smaller problems that can be analyzed easily and whose results can be combined into solutions for the original problems.
This book constitutes the proceedings of the 37th International Conference on Application and Theory of Petri Nets and Concurrency, PETRI NETS 2016, held in Toruń, Poland, in June 2016. Petri Nets 2016 was co-located with the Application of Concurrency to System Design Conference, ACSD 2016. The 16 papers including 3 tool papers with 4 invited talks presented together in this volume were carefully reviewed and selected from 42 submissions. Papers presenting original research on application or theory of Petri nets, as well as contributions addressing topics relevant to the general field of distributed and concurrent systems are presented within this volume.
Operational processes leave trails in the information systems supporting them. Such event data are the starting point for process mining – an emerging scientific discipline relating modeled and observed behavior. The relevance of process mining is increasing as more and more event data become available. The increasing volume of such data (“Big Data”) provides both opportunities and challenges for process mining. In this paper we focus on two particular types of process mining: process discovery (learning a process model from example behavior recorded in an event log) and conformance checking (diagnosing and quantifying discrepancies between observed behavior and modeled behavior). These tasks become challenging when there are hundreds or even thousands of different activities and millions of cases. Typically, process mining algorithms are linear in the number of cases and exponential in the number of different activities. This paper proposes a very general divide-and-conquer approach that decomposes the event log based on a partitioning of activities. Unlike existing approaches, this paper does not assume a particular process representation (e.g., Petri nets or BPMN) and allows for various decomposition strategies (e.g., SESE- or passage-based decomposition). Moreover, the generic divide-and-conquer approach reveals the core requirements for decomposing process discovery and conformance checking problems.