摘要 |
A series of transaction records is extracted for each case from a database storing processing results of respective performed jobs to generate, for each case, a process instance including job names and time data of the performed jobs arranged in a time series. Then, process instances satisfying a designated condition are classified among the process instances to calculate, for each classification, an average value and standard deviation of transition periods that are differences between a start time and an end time of a job section to be processed in the pertinent process instances. By identifying a process instance, which has correlation with the route before the job section and for which the reduction of the transition period is expected and/or a process instance, which has correlation with the entire route and for which the reduction of the transition period is expected, an improvement candidate is automatically shown to the user.
|