| 引用本文: | 左殷恺1,2 ,卢 可1,2.业务流程一致性检查方法 ———基于直接跟随规则模型(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2025，42（2）：95-104 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 目的 针对传统一致性检测方法大多只考虑控制流层面,并未考虑流程中数据对于一致性检查过程的影响
这一局限性,提出一种基于直接跟随规则模型( DFRM) 的一致性检查方法,扩展了传统的直接跟随模型。 方法 首
先将现实流程模型的控制流和数据流分别转换为各自视角的业务流程规则,然后利用关联规则将控制流规则与数
据流规则相结合,并利用满足性模理论( SMT) 对数据规则进行处理,最终实现基于直接跟随规则模型的表现形式;
接着通过从事件数据中提取事件日志,优先对控制流对齐,然后再进行数据流对齐,实现多视角业务流程一致性检
查。 结果 利用真实医疗事件日志对所提出的方法进行评估,与其他传统方法相比,所提出的方法在模型的拟合度、
F1 分数上都有较好表现且直接跟随规则模型,因其模型简单,具有较少的执行时间。 结论 将数据视角以数据关联
规则的形式与直接跟随模型相结合,这为目前业务流程商业软件的模型表现形式提供了新的扩展方向;将数据视
角引入到业务流程中,解决了现有流程模型无法表达与数据相关的一些决策需求问题,对一致性检查过程中其他
视角的可能偏差也纳入了考量。 |
| 关键词: 一致性检测 关联规则 智慧医疗 直接跟随规则模型( DFRM) |
| DOI： |
| 分类号: |
| 基金项目: |
|
| A Conformance Checking Method for Business Process Based on Directly Following Rule Model |
|
ZUO Yinkai1 2 LU Ke1 2
|
|
1. School of Mathematics and Big Data Anhui University of Science and Technology Anhui Huainan 232001 China
2. Anhui Province Engineering Laboratory for Big Data Analysis and Early Warning Technology of Coal Mine Safety
Anhui Huainan 232001 China
|
| Abstract: |
| Objective Traditional conformance detection methods mostly consider the control flow and do not take into
account the impact of data on the conformance checking process in process. To address this limitation a conformance
checking method based on the directly following rule model DFRM was proposed extending the traditional directly
following model. Methods Firstly the control flow and data flow of the real process model were respectively transformed
into business process rules from their own perspectives. Then the control flow rules were combined with the data flow
rules using association rules and the data rules were processed using satisfiability modulo theory SMT ultimately
obtaining the representation based on the direct-following rule model. Then event logs were extracted from event data
and control flow alignment was prioritized before data flow alignment to achieve multi-perspective business process
conformance checking. Results The proposed method was evaluated using real medical event logs. Compared with other
traditional methods the proposed method has better performance in terms of model fitness and F1 score and the model has less execution time due to its simplicity. Conclusion Combining the data perspective with the directly following model
in the form of data association rules provides a new extension direction for the model representation of current business
process software. Introducing the data perspective into the business process solves the problem that existing process models
cannot express some decision requirements related to data and also takes into account the possible biases of other
perspectives in the conformance checking process. |
| Key words: conformance checking association rules smart healthcare directly following rule model DFRM |
