At IBM Research – Ireland we are developing AI technologies to understand and connect this data in new ways. We combine machine learning with knowledge graph reasoning to enhance the data with layers of semantic abstraction. This gives us new ways to automatically derive new insights from the data and present them in natural understandable interfaces.
Our knowledge graph for IoT is a digital thread that understands IoT systems and the meaning of the various types of data within their life cycle. It works in a similar way to the way our brains think by learning new knowledge and linking it to existing one to form a larger understanding. Let’s take a temperature sensor in a car or a building. It has sensor readings, a type and a location. Our system understands general concepts of physics and how temperature is influenced by heating or cooling. This allows the system to form a knowledge graph that explains the temperature in the car or the building and enables it to learn this relationship over time.