一种基于近距离最大子图优先的业务流程推荐技术  

A Near Neighbour and Maximal Subgraph First Based Business Process Recommendation Technique

作　　者：曹斌[1] 尹建伟[1] 邓水光[1] 王东京[1] 徐悦甡[1] 

机构地区：[1]浙江大学计算机科学与技术学院,杭州310027

出　　处：《计算机学报》2013年第2期263-274,共12页Chinese Journal of Computers

基　　金：国家科技支撑计划(2012BAH06F02;2011BAD21B02);国家自然科学基金(61272129);教育部博士点基金(20110101110066)资助

摘　　要：业务流程的动态性和不确定性,为企业流程建模过程带来了巨大挑战,传统基于流程挖掘或流程检索的方式在一定程度上提高了建模的智能性,但仍需大量人工参与,如何更大程度地提高业务流程建模效率和准确度成为当前企业亟待解决的问题.论文借鉴传统推荐技术思想,提出了一种业务流程推荐技术,该技术以业务流程资源库作为出发点,利用图挖掘方法进行流程模式的提取,基于近距离最大子图优先的流程匹配策略对参考流程与流程模式的相同性进行判断,进而选取相关候选节点集作为推荐结果.基于业务流程推荐系统原型JTangWFR,通过对比现有相关技术表明,文中方法能够支持实际应用中的复杂流程结构,其效率和准确度方面能够满足实际应用的需求.The frequent changes of custom demands and the professionalization of the business process both bring huge challenges for the enterprise workflow modeling or design. Traditional methods for improving process design, such as process mining and process retrieval, still involve much manual work. How to greatly improve the efficiency and accuracy for business process de- sign has become a burning problem. The traditional recommendation technique provides us the possible solution. This paper proposes a process recommendation technique which starts from the process repository. Graph mining technique is used to extract the process patterns. Based on near neighbor and maximal subgraph first （NMSF） strategy, we judge the equvalance between the ref- erence process and process patterns for derterming the candidate node sets for recommendation. A prototype called JTangWFR is implemented, and its recommendation scenarios and implementa- tion details are also discussed. The experimental evaluation proves that our system is efficient and effective for practical use.

关 键 词：流程推荐 近距离最大子图 业务流程建模 流程匹配 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]