Process Workflow Replay Using Process Mining and Generative AI
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The aging workforce in Process and Automation Engineering (PAEN) and Control Engineering is causing a knowledge and experience gap as experts retire, necessitating a method to capture and utilize their expertise for future engineers and operators.
Innovation Solution
A method utilizing process mining and generative artificial intelligence to analyze historical processes, identify patterns, and suggest next steps or sequences, enabling the capture and replay of expert knowledge through systems and data processing apparatus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If expert knowledge is captured and stored in a system, then knowledge preservation is improved, but system complexity increases
Solution Approach 1:
The patent creates a digital copy of expert knowledge by recording historical process data, sequences, and outcomes from expert operators. This copy is stored in a database and can be replayed without requiring the original expert to be present, thus preserving knowledge while avoiding the complexity of maintaining multiple expert systems
Solution Approach 2:
The system performs preliminary analysis of historical expert processes to identify key sequences, decisions, and outcomes before they are needed. By pre-processing and structuring the knowledge in advance, the system reduces the complexity of real-time knowledge retrieval and application
2Measurement precision
If process mining and generative AI are used to analyze historical data, then knowledge accuracy is improved, but computational requirements increase
Solution Approach 1:
The patent extracts only the essential and relevant features from historical process data, such as key process steps, critical decisions, and important outcomes. By taking out only the necessary information rather than processing entire datasets, the system maintains knowledge accuracy while reducing computational energy requirements
Solution Approach 2:
The system applies different levels of analysis depth to different parts of the historical data based on their importance. Critical process steps receive more detailed analysis while routine steps receive lighter processing, optimizing the balance between knowledge accuracy and computational energy
3Productivity
If expert knowledge is made accessible to less experienced engineers, then productivity is improved, but information overload may occur
Solution Approach 1:
The patent segments expert knowledge into discrete, manageable units such as individual process steps, decision points, and actionable recommendations. This segmentation allows less experienced engineers to access only the specific knowledge relevant to their current task rather than being overwhelmed by the entire body of expert knowledge
Solution Approach 2:
The system provides partial knowledge delivery by offering only the necessary expert insights needed for the current situation rather than presenting all available knowledge. This partial action approach prevents information overload while still delivering sufficient guidance to improve productivity
Data Source
AI summary
A method for saving and utilizing expert process knowledge with regard to an industrial plant includes obtaining first data indicative of historical processes comprising sequences of historical process steps occurred in an industrial plant; obtaining second data based on analysing the first data, wherein the second data is indicative of occurrence statistics and thereon-based probabilities for several historical processes and several historical process steps; based on the second data, suggesting, for at least one of a process step, a sequence of process steps and a process, at least one of a next process step, a next sequence of process steps and a next process; analysing the first data using process mining and/or processing the first data using generative AI; and suggesting the at least one of the next process step, the next sequence and the next process by using process mining and/or by using generative AI.