Self-learning localization data repository

A method of updating a self-learning data repository, the method executed in a processor of a server computing device and comprising:

• storing, in a memory of the server computing device that constitutes the self-learning data repository, a fingerprint map of an indoor facility, the fingerprint map having positioning fingerprint data that includes magnetic spatial derivative fingerprint data;
• receiving, from a mobile device, at the self-learning data repository, at least one of mobile device signal data and mobile device sensor data correlated with a sequence of positions describing a movement of a mobile device along a trajectory within the indoor facility, the sensor data including mobile device magnetic spatial derivative data derived in accordance with a magnetic spatial gradient established based on differences in absolute magnetic field measurements and a spatial separation existing across at least a pair of contiguous positions in the sequence of positions along the trajectory;
• compensating, using the processor, for variations in the absolute magnetic measurements of the mobile device by performing a spatial shifting of at least one of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data of the self-learning data repository for at least a segment of the trajectory within the indoor facility to create updated mobile device sensor data, wherein the spatial shifting increases a coincidence in overlay of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data for the segment of the trajectory;
• and
• automatically updating, using the processor, the self-learning data repository by adding at least one of the mobile device signal data and the updated mobile device sensor data to the positioning fingerprint data.