Servicing of autonomous vehicles

摘要

A method includes generating a plurality of training vectors relating to different respective historical service requests generated by respective autonomous vehicles, each of the training vectors including respective features associated with the historical request to which the training vector relates. The method further includes, using the training vectors, training a model configured to generate a prediction relating to one or more future service requests, generating the prediction using the model, and outputting the generated prediction. Other embodiments are also described.