METHOD FOR AUTOMATIC ESTIMATION OF SPATIO-TEMPORAL ENTITY COUNTS USING MACHINE LEARNING FROM PARTIALLY OBSERVABLE LOCATION DATA

摘要

Disclosed is a system for automatically estimating spatio-temporal entity counts in real time and for a future time window using machine learning from partially observable location data. The system includes a data aggregator, a hyper-cube computational data structure, a geo coder, a geolocation mapper, a key value data structure updater, a hyper cube estimator, a census-based extrapolator, and an entity estimator. The entity estimator (i) determines an entity count for each or combinations of the one or more spatio temporal dimensions in real time by combining lower bound number and upper bound number of the entity count from the hyper cube estimator and the census based extrapolator, and (ii) estimates, using a machine learning based time series model, spatio temporal entity count for a future time window in response to a query criterion.