AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Machine Learning and the Geo-Summerizer
We have a process we call it our geo-summerizer and it's how do we summarize all of those inputs and turn them into the right output. It uses things like building polygons so we know there are roads and there are buildings but the input coordinates from a source they that you know it's in the middle of a forest or you know not where it should be according to the roads and buildings of that address is discarded. We can average or cluster them together and pick out a either synthetic coordinate from all of our sources or pick the best one that has the most corroborating features. This is kind of where a lot of the user the user input data comes in definitely in dense