关键词: 业务流程模型, 不频繁行为, 通讯行为轮廓, 隐藏变迁, 特征网, 数据意识

Abstract: Business process infrequent behavior refers to the behavior of low frequency event trace,and mining conditional infrequent behavior from the event log is one of the key points in business process optimization.Existing research methods ignores low frequency behavior and rarely deal with infrequent behavior based on data-flow perspective.The data dependencies hidden was considered between events to propose mining and optimization of conditional infrequent behavior based on data consciousness.Based on the communication behavior profile theory between modules,the feasible traces of the reference model were inquired,and attribute values were added to infrequent traces.Data dependency values between the interaction features were calculated,and the infrequent behavior was classified.According to the optimized log,the module net and the feature net were constructed.Through the interaction between module net and feature nets,and the business process optimization communication model of these two nets was mined.The effectiveness of the proposed method was verified by a concrete instance.

Key words: business process model, infrequent behavior, communication behavioral profile, hide transition, feature net, data consciousness