当前位置: X-MOL 学术Int. J. Coop. Inf. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Business Process Model Abstraction Based on Fuzzy Clustering Analysis
International Journal of Cooperative Information Systems ( IF 1.5 ) Pub Date : 2019-09-09 , DOI: 10.1142/s0218843019500072
Nan Wang 1 , Shanwu Sun 1 , Ying Liu 1 , Senyue Zhang 2
Affiliation  

The most prominent Business Process Model Abstraction (BPMA) use case is a construction of a process “quick view” for rapidly comprehending a complex process. Researchers propose various process abstraction methods to aggregate the activities most of which are based on [Formula: see text]-means hard clustering. This paper focuses on the limitation of hard clustering, i.e. it cannot identify the special activities (called “edge activities” in this paper) and each activity must be classified to some subprocess. A new method is proposed to classify activities based on fuzzy clustering which generates a fuzzy matrix by computing the possibilities of activities belonging to subprocesses. According to this matrix, the “edge activities” can be located. Considering the structure correlation feature of the activities in subprocesses, an approach is provided to generate the initial clusters based on the close connection characteristics of subprocesses. A hard partition algorithm is proposed to classify the edge activities and it evaluates the generated abstract models according to a new index designed by control flow order preserving requirement and the evaluation results guide the edge activities to be classified to the optimal hard partition. The proposed method is applied to a process model repository in use. The results verify the validity of the measurement based on the virtual document to generating fuzzy matrix. Also it mines the threshold parameter in the real world process model collection enriched with human designed subprocesses to compute the fuzzy matrix. Furthermore, a comparison is made between the proposed method and the [Formula: see text]-means clustering and the results show our approach more closely approximating the decisions of the involved modelers to cluster activities and it contributes to the development of modeling support for effective process model abstraction.

中文翻译:

基于模糊聚类分析的业务流程模型抽象

最突出的业务流程模型抽象 (BPMA) 用例是构建流程“快速视图”以快速理解复杂流程。研究人员提出了各种流程抽象方法来聚合活动,其中大部分是基于 [公式:见正文] - 意味着硬聚类。本文关注硬聚类的局限性,即它不能识别特殊的活动(本文称为“边缘活动”),每个活动都必须分类到某个子流程。提出了一种基于模糊聚类的活动分类新方法,该方法通过计算活动属于子流程的可能性来生成一个模糊矩阵。根据这个矩阵,可以定位“边缘活动”。考虑到子流程中活动的结构关联特征,提供了一种基于子流程的紧密连接特征生成初始集群的方法。提出了一种对边缘活动进行分类的硬分区算法,根据控制流保序要求设计的新指标对生成的抽象模型进行评估,评估结果指导边缘活动分类到最优的硬分区。所提出的方法应用于正在使用的过程模型存储库。结果验证了基于虚拟文档生成模糊矩阵的测量的有效性。它还挖掘了真实世界过程模型集合中的阈值参数,该集合富含人工设计的子过程来计算模糊矩阵。此外,对所提出的方法和[公式:
更新日期:2019-09-09
down
wechat
bug