2009 | OriginalPaper | Buchkapitel
Case Construction for Mining Supply Chain Processes
verfasst von : Kerstin Gerke, Jan Mendling, Konstantin Tarmyshov
Erschienen in: Business Information Systems
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Process mining algorithms aim at the automatic extraction of business process models from logs. Most of these algorithms perform well on single-system event traces that explicitly refer to a process instance or case. However, in many operational environments such case identifiers are not directly recorded for events. In supply chain processes there are even further challenges, since different identification numbers, vertical integration and numerous aggregation steps prevent individual work steps to become traceable as a case. As a result, there are little experiences with the use of process mining in supply chains. To address this problem, we consider Radio Frequency Identification (RFID) for identifying the movements of the business objects. Based on an example process from the Supply Chain Operations Reference Model (SCOR), we highlight the two key challenges of making RFID events available for process mining: case identification and focus shifts. We demonstrate how RFID events that conform to the EPCglobal standard can be used to construct cases such that process mining can be applied. A respective algorithm is sketched that we implemented in a tool which generates MXML process mining data from EPCglobal event traces. In this way, we provide a contribution towards applying process mining techniques for supply chain analysis.