A Method for Improving Business Process Efficiency Based on Alternative Branching

Abstract

The invention discloses a method for improving the efficiency of a business process based on a selection branch. The method aims at the technical problem that the existing model repair method cannot accurately find the location of the new activity and the efficiency of the business process is reduced. A model repair method based on logical Petri nets, which can add new activities to the original process model as a selection branch. The specific process is as follows: firstly, find new activities in the event log generated by the system; construct two sequence sets respectively To describe the relationship between the activities in the log and the relationship between the changes in the model; compare these two sets to obtain a deviation set containing new activities; based on the deviation set, add the new activity as a selection branch to the original process model, and complete the original process model repair, and then use the repaired model to replay the new logs generated in the actual process, which will help improve the efficiency of the actual business process.

Description

technical field [0001] The invention relates to a method for improving the efficiency of business processes constructed based on selection branches. Background technique [0002] With the development of business processes, more and more event logs are recorded in enterprise information systems. As a supplement to the business process management method, process mining establishes two connections, one is the connection between business processes and event logs, and the other is the connection between business processes and process models. Process mining techniques can extract knowledge from event logs to discover, detect and improve actual processes. It has three main functions: process discovery, consistency check and process enhancement. Process discovery builds process models based on event logs. At present, many process discovery algorithms have been proposed. There are four criteria for evaluating the quality of a process model: fit, precision, simplicity, and general...

AI Technical Summary

Problems solved by technology

However, the existing model repair methods usually repair the original process model by adding new activities as self-loops or skipping activities with invisible transitions. This repair method often cannot accurately find the location where new activities are added, which will lead to the failure of transitions. Duplication, making the repaired model complex and redundant

Therefore, the existing model repair methods cannot ensure that the repaired model has high accuracy and simplicity, and thus cannot correctly reflect and express the updated actual business process, resulting in a significant decrease in the efficiency of the updated actual business process

Images