Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (5): 1284-1289.DOI: 10.11772/j.issn.1001-9081.2016.05.1284

Previous Articles     Next Articles

Importance sorting method of organizational enities based on trace clustering

XU Tao1,2, MENG Ye1   

  1. 1. College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China;
    2. Information Technology Research Base of Civil Aviation Administration of China, Tianjin 300300, China
  • Received:2015-10-19 Revised:2016-01-09 Online:2016-05-10 Published:2016-05-09
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61502499), the Grant from Civil Aviation Administration of China (MHRD20140105), the Fundamental Research Funds for the Central Universities (3122015D015).

踪迹聚类下组织实体的重要度排序方法

徐涛1,2, 孟野1   

  1. 1. 中国民航大学 计算机科学与技术学院, 天津 300300;
    2. 中国民航大学 中国民航信息技术科研基地, 天津 300300
  • 通讯作者: 孟野
  • 作者简介:徐涛(1963-),男,重庆人,教授,主要研究方向:数据挖掘、智能信息处理;孟野(1990-),男,江苏南京人,硕士研究生,主要研究方向:机器学习、业务流程挖掘。
  • 基金资助:
    国家自然科学基金资助项目(61502499);中国民航科技创新引导资金项目重大专项(MHRD20140105);中央高校科研业务费专项资金资助项目(3122015D015)。

Abstract: Aiming at the issue that the social network analysis method like hand-over network cannot express the importance of organizational entities precisely, a method to sort the quantified importance of organizational entities organized under the trace clusters was proposed. Firstly, a relation network was constructed to describe the relationship between trace clusters and organizational entities; secondly, a quantitative assessment of the nodes' importance of this network was defined; finally, all these nodes were sorted respectively according to their quantified importance. The experimental results show that this relation network can express the actual importance of organizational entities more precisely than the hand-over network generated by trace clustering. Compared to the importance sorting algorithm of network community nodes based on topological potential, the proposed method is more suitable for the actual business processes, meanwhile it can distinguish distinct organizational entities better than the importance-sorting algorithm based on topological potential.

Key words: process mining, organizational mining, importance sorting, social network, complex network

摘要: 针对简单套用交接网络等社会网络分析方式不能很好地反映踪迹聚类生成的一系列流程的组织实体的重要度的问题,提出了一种踪迹聚类下组织实体的重要度排序方法。首先,对于参与踪迹聚类生成的一系列流程的组织实体构建踪迹聚类与组织实体关系网络;其次,定义基于踪迹聚类与组织实体关系网络的节点重要度评估方法;最后,对踪迹聚类下的各个组织实体节点计算其在关系网络中的重要度评分并排序。实验结果表明,所提方法构建的关系网络相比踪迹聚类下的交接网络能够更准确地反映组织实体的实际重要度;与基于拓扑势的网络社区节点重要度排序算法相比,所提方法的节点重要度排序结果更符合实际业务流程,能更好地区分关系网络中重要度不同的节点。

关键词: 流程挖掘, 组织挖掘, 重要度排序, 社会网络, 复杂网络

CLC Number: