Title: A process recommendation method using bag-of-fragments

Authors: Jiaxing Wang; Sichao Gui; Bin Cao

Addresses: College of Computer Science and Software Engineering, Zhejiang University of Technology, Hangzhou, 310023, China ' College of Computer Science and Software Engineering, Zhejiang University of Technology, Hangzhou, 310023, China ' College of Computer Science and Software Engineering, Zhejiang University of Technology, Hangzhou, 310023, China

Abstract: Process modelling is one of the key techniques in business process management, which needs to meet the frequent changes in custom and market demands effectively and efficiently. Most of existing methods focus on the structural feature of a process when modelling a process by using graph edit distance (GED) technology. However, GED is low-efficiency and the costs need to be adjusted for different scenarios. Besides, two process models with the same structure may contain different behaviours. To address this, we use a bag-of-fragments based on m, n-grams that are excerpts in terms of structure and behaviour to summary a process model. Given a process that is under modelling, we recommend the top k similar process models in the process repository for process modelers, which provides them the relevant decision support and assists them in modelling this process model. A prototype is implemented to show the practicality of the proposed technique.

Keywords: process model; m; n-gram; process difference; process recommendation; process similarity.

DOI: 10.1504/IJIITC.2019.104734

International Journal of Intelligent Internet of Things Computing, 2019 Vol.1 No.1, pp.32 - 42

Received: 29 May 2019
Accepted: 24 Jun 2019
Published online: 29 Jan 2020 *