Using NLP techniques, we provide an automated way to create a knowledge graph from the texts from technician service documents. The aim is to create a model that represents the digital twin of a vehicle and to create a feedback loop to update the knowledge graph based on the actions taken by the human (technicians). Why do we need a knowledge graph with feedback loop?
With a footprint of close to 80-90 ECU’s in today’s automotive, and a multitude of trouble codes (often ambiguous), questions are being raised around the ability and effectiveness of traditional Diagnostic tools to accurately diagnose and detect the underlying cause of a given problem/defect.