Data driven composite location system using modeling and inference methods
Embodiments respond to a position inference request from a computing device to determine a location of a computing device. The position inference request received from the computing device identifies a set of beacons observed by the computing device. A geographic area is estimated in which the computing device is located using the set of beacons. At least one location method is selected to identify a location of the computing device within the geographic area. In some cases two or more location methods may be employed and their results combined using, for example, a weighting function. The location of the computing device is determined within the geographic area using the set of beacons and the selected location method(s). The location that is determined is communicated to the computing device.
1. A mobile communication device, comprising:
one or more wireless transmitters and receivers for communicating over a wireless communication network using one or more beacons associated with the wireless communication network;
one or more processors for executing machine-executable instructions;
one or more machine-readable storage media for storing the machine-executable instructions, the instructions including beacons models and position inference algorithms received from a service over the wireless communication network and cached on the mobile communication device, at least one of the beacons models being determined using crowd-sourced positioned observations in a training dataset, each of the crowd-sourced positioned observations including a set of beacons observed by one of a plurality of computing devices and an observation position of the computing device when the set of beacons is being observed; and
processing logic configured, based on a set of observed beacons with which the one or more wireless transmitters and receivers communicate, to determine the location of the mobile communication device within a geographic area using at least one of the received and cached beacon models and position inference algorithms.
2. The mobile communication device of claim 1 in which the instructions further include a combining function based on data analytics obtained for geographic tiles.
3. The mobile communication device of claim 2 in which the combining function includes a weighting function.
4. The mobile communication device of claim 3 the instructions further comprising selecting the weighting function based on an error characteristic associated with each selected location method such that a location method having a lower error characteristic within the geographic area is more highly weighted than a location method having a higher error characteristic within the estimated geographic area.
5. The mobile communication device of claim 3 the instructions further comprising selecting the weighting function based at least in part on a number of beacons identified in the position inference request.
6. The mobile communication device of claim 1 in which at least one of the receivers periodically receives updated beacons models and position inference algorithms from the service which are stored in the memory area.
7. The mobile communication device of claim 1 in which the instructions further include a combining function specifying how to combine location results obtained using different cached beacons models and position inference algorithms.
8. The mobile communication device of claim 1 in which at least one of the beacons models or the position inference algorithms stored in the memory area has an expiration time after which it is no longer usable.