工作流成批处理方面的增量式挖掘算法研究-计算机科学与技术专业论文.docxVIP

II II Abstract Batch processing in workflow is to integrate workflow activity instances generated from the same class of activities, changing the separately executing pattern of traditional multiple workflow instances to one -time executing pattern by merging them. Batch processing of workflow can reduce the cost of activity and improve the efficiency. Because the enterprise business process and application is complex and dynamically changed, comprehensively grasping and understanding ways of workflow batch processing way is as difficult as definition of workflow process. Workflow mining becomes a new branch of research, when data mining technology is introduced to workflow mining. Workflow mining of batch processing is as important a s Workflow mining. Therefore, aiming at the workflow batch processing mining, this paper makes the following outcomes or contributions: Existing research about workflow batch processing mining, didnt consider the problem that the ―dirty data‖ will affect the accuracy of the mining results. Aimed at this problem, this paper cleans the workflow log data by condition functional dependency, and presents an incremental discovering algorithm for CFDs, which is named as CFUP and is based on CFINDER algorithm. The main idea of CFUP reduce scan for the original data by the last of mining result, then reduce the running time and improve the efficiency. The feasibility and validity of CFUP is proved by theoretical analysis and experimental results. Existing research about workflow batch-favor mining, didnt consider the problem that workflow log data will incremental update . Aimed at this problem, this paper presents an incremental mining algorithm for batch-favor dependency, which is named as Inc_Mine_BD and is based on Mine_BD algorithm. When the workflow log data incremental update, Inc_Mine_BD algorithm scans dataset to decide whether existing batch dependency is valid, and the new data produces new batch dependency. Theoretical analysis and