US Patent 10356244 Automated predictive call routing using reinforcement learning

Methods and apparatuses are described for automated predictive call routing using reinforcement learning. A server captures a bitstream of an incoming call from a first client device, the bitstream including metadata comprising attributes of the incoming call and attributes of a user of the device. The server determines an identity of the user based upon the metadata. The server generates a first context vector comprising a multidimensional array corresponding to the metadata. The server inserts the first vector into a high-dimensional vector space comprising historical context vectors, each historical vector (i) corresponding to metadata associated with a historical call and (ii) associated with an income value and a routing decision. The server determines historical vectors in proximity to the first vector. The server identifies one of the determined historical vectors with an optimal income value and routes the bitstream to a second device using the routing decision.