Mining Algorithm Based On The Time Log Of Processes

During the last decade workflow management technology has become readily available. Workflow management system such as Staffwar, IBM MQSeries and COSA, etc. offer generic modeling and enactment capabilities for structured business processes .Current workflow management systems require the explicit design of the workflow that express the business process of an organization . i.e., a completely specified workflow design is required to enact a given workflow process. Creating a workflow design is a complicated time-consuming process and typically there are discrepancies between the actual workflow processes and the processes as perceived by the management. Therefore, new techniques for discovering workflow models have been required. Starting point for such techniques are so-called "workflow logs" containing information about the workflow process as it is actually being executed.In this thesis, new mining technique based on time information is proposed. The algorithm consists of two major steps: 1.The construction of the average values tables; AVT keeps the average succession waiting time, the average following waiting time, the edge validity ratio, the average intersection time and the task overlapping ratio and the average execution time of the task. Hence for every task in the workflow log an AVT is constructed. We assume all workflow logs considered are sorted by workflow instance case. While constructing the average values table, first a trace line is read from the workflow log. Then the case, activity, event type, and event time values are extracted from the trace line. If the extracted case value is different from current, we reset all the temporary variables. If the extracted event type is a start event, we keep this time in the variable of the corresponding activity event to use later. If there were any preceding complete events, total succession waiting time and total succession count could be calculated by using this start event...