POP-ON: Prediction of Process Using One-Way Language Model Based on NLP Approach

Junhyung Moon,Gyuyoung Park,Jongpil Jeong

doi:10.3390/app11020864

Abstract

In business process management, the monitoring service is an important element that can prevent various problems in advance from before they occur in companies and industries. Execution log is created in an information system that is aware of the enterprise process, which helps predict the process. The ultimate goal of the proposed method is to predict the process following the running process instance and predict events based on previously completed event log data. Companies can flexibly respond to unwanted deviations in their workflow. When solving the next event prediction problem, we use a fully attention-based transformer, which has performed well in recent natural language processing approaches. After recognizing the name attribute of the event in the natural language and predicting the next event, several necessary elements were applied. It is trained using the proposed deep learning model according to specific pre-processing steps. Experiments using various business process log datasets demonstrate the superior performance of the proposed method. The name of the process prediction model we propose is “POP-ON”.

Highlights

The main characteristics of corporate and industrial processes are dynamics, complexity, and uncertainty
We propose a new model modified from GPT-2, which is a one-way language modelbased transformer approach in process prediction
We investigated the efficiency of a one-way language model approach among fully attention-based transformer models for predicting future process events of the current process instance being executed

Summary

Introduction

The main characteristics of corporate and industrial processes are dynamics, complexity, and uncertainty. The manufacturing industry increases in complexity due to the dynamic situation change of many infrastructures and various products and services produced. The globalization of industry makes the development cycle of new and innovative technologies shorter and leads to shorter product life cycles [1]. Grasping the planning deviations of a business process in real dynamic situations is essential to enabling companies to respond flexibly to all situations [3]. Process management through general documentation can lead to discrepancies between the actual and documented [4]. Many and various event logs are generated. More business management systems can appear based on these logs. Process mining helps keep complex processes up to date and monitored

Objectives

Results

Conclusion