Process Model Change Mining And Change Propagation Based On Petri Net

The analysis of business process is one of the important contents of business process management.It aims to discover the hidden changes in the operating system at different levels or different process perspectives,and lay the foundation for system repair or optimization.With the gradual enhancement of the openness of computer systems and the constant changes in user requirements,the same business system can generate multiple operating entities with different differences,making the original business process model vulnerable to adapt to the new changing environment.Therefore,mining the hidden changes in the business system is the core issue of the business management system.At present,the research of business processes mainly focuses on process mining and change propagation analysis,and there is a lack of research on change mining.The existing process mining is based on the static event log.The target model is mined by behavioral contour or weak order relationship.It has certain limitations for the dynamic event log.The existing change propagation mainly deals with the expansion of a single business process.Similar problem-changing domain problems,it is more difficult to study the interaction process with information transfer.Based on the Petri net principle and behavioral contour theory and its behavioral inclusion and feature log,this paper mines the local variants existing in the actual system given the original reference model and the dynamic change event log.The applied change process is analyzed and analyzed to facilitate further resolution of the change propagation problem between interaction processes.The main contents are as follows:(1)Aiming at the mining change domain problem of change event log,existing literature deals with consistency or variation domain issues between process models,but little consideration for implicit changes in their original event logs.A log change mining method based on behavior inclusion is proposed.The event log is analyzed from the behavioral point of view of the activity,and the behavioral inclusion relationship between the activities is calculated.Based on this,the model consistency is judged,and the local variation domain is discovered by using the change mining technology in combination with the behavioral contour of the model and the log.This method analyzes the log from a dynamic behavioral perspective and overcomes the singularity of the existing methods.(2)For the change log mining change domain problem of interactive system,he existing researches are more based on the process model,dealing with the changes in the single similar system,and less involved in the interactive system with information transfer.A feature log-based module log change mining method is proposed.The interaction log is divided into modules from the perspective of feature network,and the log is simplified by the behavioral correspondence of activities.The implicit change in the indirect dependency mining log reduces the complexity of log analysis and improves the accuracy of change detection.Finally,the feasibility of the method is verified by an example.(3)For the problem of change propagation between interactive systems with changes,the existing literature mainly deals with the change between similar processes.The matching alignment method between models locks the change domain and optimizes the system,it ignores that most of the system is composed of several sub-process interactions.The process is not simple correspondence but there is information transfer A method is proposed to analyze interactive process change propagation based on configuration.Based on the location of the change region,the configuration technology is used to improve the intra-region behavior relationship.In the case of the corresponding source change region locked by a given change demand,use choreography and conditional abstraction to find target change region that are affected by changes in other interactive sub-processes.And use the configuration to deal with the change behavior of constraints in the region under the principle of ensuring the consistency of the extra-region structure.Then,the rationality of the configured interactive process model is detected by compatibility.Finally,the feasibility of the method is verified by a specific case.(4)For different changes in the log,existing research has focused on discovering changes in the business system,ignoring the root cause of these changes,a series of operations that lead to system changes.A change process mining method is proposed based on quasi behavior profile.The change log is analyzed from the perspective of the behavior of change operation.According to the state variability of the schema,the relationships of dependence,constraint,equality,and opposition are formed and the quasi behavioral profile is formed.To mine the final change process and optimize via combining the corresponding basic structuresand,which Provides highly similar reference templates for change reuse and lays an important foundation for business process updates.Finally,a concrete example is given to verify the feasibility of the method.Figure[20]table[7]reference[91]...