Research On Business Process Recommendation Method Based On Metadata

With the rapid development and wide application of information technology,human society has gradually entered the information overload period from the information scarcity period.The globalization,digitalization and information of enterprises have made Business Process Management(BPM)widely used,which has resulted in a large number of business processes in the industry.Business process is becoming more and more complex with the change of application environment.And business process management is facing a series of new challenges,especially higher requirements for business process recommendation.At present,the existing similarity based business process recommendation are the main methods used in the field of business process recommendation.Among them,business process recommendation based on Graph Structure Similarity(GSS)measures and recommends business process based on the graph structure of business process.Business process recommendation based on String Matching Similarity(SMS)measures and recommends business process based on string matching degree of business process diagram.Business process recommendation based on process diagram Similarity(PDS)measures and recommends business process based on the structure and function of business process framework and process entities.However,the business process similarity measurement in the above methods generally lack other typical metadata features of business process,and the validity and accuracy of recommendation in multidimensional metadata feature space are insufficient.For this reason,a method is proposed: metadata based business process recommendation.Firstly,this thesis elaborates the concepts and framework of business process recommendation in detail,defines the related issues of business process research detailedly,and summarizes the business process recommendation framework and similarity measurement.Secondly,the business process recommendation technologies are studied and analyzed,and the technical characteristics of business process oriented metadata and metadata based business process description framework are analyzed.Thirdly,the limitations of existing typical business process recommendation methods are analyzed.Finally,in view of the shortcomings of the existing methods,metadata based business process recommendation is developed,and a series of experiments are carried out on the actual data set,and the proposed method is experimentally verified from many aspects.The experimental results show that the proposed method can effectively improve the performance of business process recommendation in practical applications.