AI for process conformity

Focus:	Talents
Type of funding:	Individual funding programmes
Programme:	CZS research boost
Funded institution:	Hochschule Koblenz

Prof. Dr. Wied Pakusa of Koblenz University of Applied Sciences is conducting research on new AI-based methods for process compliance testing. His research findings are intended to contribute to the secure and trustworthy automation of processes.

Goals

Prof. Wied Pakusa's research project at Koblenz University of Applied Sciences is being carried out in collaboration with partners from research, public administration and industry.

The aim is to develop new procedures for checking the conformity of processes in the field of process mining in order to ensure the reliability of AI systems in various sectors.

The focus is on the design and implementation of a process alignment notion based on a non-local cost assessment. This method should enable more precise analyses of deviations and their causes, in contrast to current methods that can only perform local assessments.

The unreliability of AI systems can have serious consequences in critical areas such as healthcare or public administration. Constant monitoring and control of processes is therefore necessary to avert potential damage, financial losses or legal problems.

The project closes an important research gap in the cross-sectional field of artificial intelligence and process analysis and contributes to the development of Prof. Pakusa's research activities. The transfer of the results into practice will be ensured by integrating them into existing open source tools to ensure broad applicability of the results.