Semantic Quality Assurance of Heterogeneous Unstructured Repair Reports

Service technicians spend a considerable amount of their working hours in order to search for information regarding a current work order. In case of an IPS² malfunction for example, they can either search for potential failure causes within previously documented repair reports that describe a similar malfunction or manually inspect the IPS². On the one hand the former IT-related information procurement is caused by a large amount of irrelevant search results rendered by current state of the art information retrieval approaches implemented in maintenance-related IT systems. On the other hand many repair reports suffer from missing or ambiguous information and a holistically low data quality, which makes it difficult for the service technicians to derive task-related information from a particular repair report, although this report basically describes the same malfunction. These current difficulties will be amplified once service partners get access to maintenance-related information documented by other service partners (companies) within the IPS² network as the amount of available data will increase drastically and new problems will raise concerning the heterogeneity of the data. The paper on hand presents a semantic quality assurance concept for heterogeneous unstructured repair reports that addresses the low data quality problem by utilizing natural language processing and machine learning methods to automatically analyze the service technician’s inputs during the repair report creation process and by notifying him of potential losses in data quality. The concept’s feasibility has been shown by performing a case study with a prototype that utilizes the developed methods.