vAMoS: eVent Abstraction via Motifs Search

Gemma Di Federico*, Andrea Burattin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

69 Downloads (Pure)

Abstract

Process mining analyzes events that are logged during the execution of a business process. The level of abstraction at which a process model is recorded is reflected in the level of granularity of the data in the event log. When process activities are recorded as sensors readings, typically, they are very fined-grained and therefore difficult to interpret. To increase the understandability of the process model, events need to be abstracted into higher-level activities. This paper proposes vAMoS, a trace-based approach for event abstraction, which focuses on the identification of motifs on the traces, allowing some level of flexibility. The objective is the identification of recurring motifs on the traces in the event log. The presented algorithm uses a distance function to deal with the variability in the execution of activities. The result is a set of readable and interpretable motifs.

Original languageEnglish
Title of host publicationBusiness Process Management Workshops
PublisherSpringer
Publication date2023
Pages101–112
ISBN (Print)978-3-031-25382-9
DOIs
Publication statusPublished - 2023
Event20th International Conference of Business Process Management - Münster, Germany
Duration: 11 Sept 202216 Sept 2022
Conference number: 20

Conference

Conference20th International Conference of Business Process Management
Number20
Country/TerritoryGermany
CityMünster
Period11/09/202216/09/2022
SeriesLecture Notes in Business Information Processing
Volume460
ISSN1865-1348

Keywords

  • Event abstraction
  • Motifs search
  • Sensor data

Fingerprint

Dive into the research topics of 'vAMoS: eVent Abstraction via Motifs Search'. Together they form a unique fingerprint.

Cite this