Miele, a leading appliance manufacturer, was looking to optimize the ways in which it solves customer problems quickly and efficiently. A crucial part of this task is the precise diagnosis of faults before and during technician visits. A correct diagnosis allows technicians to bring with them the necessary parts and complete the repair with minimal time, effort, and spare parts. We created a system to help Miele optimize its service process based on statistics learned from historical data about technician visits; the data contained both structured and unstructured (textual) data that had to be combined to create a probabilistic model. We used a novel process in which a semantic model informed the creation of the probabilistic model as well as the analysis pipelines for the structured and unstructured data, combining expert knowledge with a large amount of heterogenous data. The results of our pilot study demonstrated a significant improvement in efficiency concomitant with an increase of an already very high first-fix rate.