Autor: Martin Benter

MTM methods are a proven standard for analyzing and designing human work processes. However, work planners continue to face challenges in applying these methods correctly and efficiently. Artificial intelligence — particularly in the case of large language models — holds significant potential for combatting these challenges. However, the use of AI raises legitimate questions regarding the reliability and traceability of the results. The approach presented here combines LLMs with a rule-based algorithm to extract the information required for MTM analyses from textual process descriptions such as work instructions. This information is then translated into MTM analyses in accordance with the MTM methodology. This approach ensures that the resulting analyses can be transparently traced back to the original input data by the user.

For around 15 years, German labor productivity per working hour has been increasing at significantly less than 1% per year. At the same time, more detailed productivity analyses reveal high potential in companies. The issue is that the required MTM analyses are complex and not yet employed as broadly and frequently as would be necessary. One solution is the use of digital technologies such as motion capture. These make it possible to carry out productivity analyses with little effort, as they provide data that accelerates the analysis. The MTMmotion® tool from the MTM ASSOCIATION e. V. was developed with the aim of carrying out valid and compliant MTM analyses using data provided by other technologies. This article compares the method developed for a motion capture system and MTMmotion® with a conventional MTM-1® analysis. The main result is that digital technologies can be used to create valid MTM analyses in early planning phases with little effort in order to make early ...