Systems and methods to evaluate accuracy of locations of mobile devices

1. A method implemented in a computing device, the method comprising:

storing, in the computing device, mapping data that connect identifiers of cells in a grid reference system to regions that contain respective cells identified by the identifiers in the grid reference system;

receiving, in the computing device, coordinates of a mobile device;

receiving, in the computing device, an accuracy indicator of the coordinates of the mobile device; and

identifying, by computing device, a region in which the mobile device is located, by:

identifying, from the accuracy indicator and the coordinates of the mobile device, a plurality of locations, including a location specified by the coordinates of the mobile device and at least one location different from the location specified by the coordinates of the mobile device;

converting coordinates of the plurality of locations into respective cell identifiers in the grid reference system, wherein respective cells in the grid reference system identified by the respective cell identifiers contain respective coordinates from which the respective cell identifiers are converted;

determining, from the mapping data, one or more regions that are connected to the cell identifiers in the mapping data, including the region in which the mobile device is subsequently identified to be located; and

evaluating, based on a portion of the plurality of locations that is in the region, a confidence level that the mobile device is located in the region, wherein the mobile device is identified to be located within the region in response to a determination that the confidence level is above a threshold.

2. The method of claim 1 , wherein the accuracy indicator identifies a possible range of at least one of:

longitudinal coordinate of the mobile device;

latitudinal coordinate of the mobile device; and

altitudinal coordinate of the mobile device.

3. The method of claim 1 , further comprising:

identifying a size of a cell that has an identifier in the mapping data and contains the coordinates of the mobile device; and

selecting the at least one location, different from the location specified by the coordinates of the mobile device, based on the size of the cell.

4. The method of claim 3 , wherein each respective location in the plurality of locations is assigned a predetermined weight for evaluation of the confidence level based on whether the respective location is in the region.

5. The method of claim 4 , wherein the confidence level is based on a sum of weights assigned to locations in the portion located within the region.

6. The method of claim 4 , wherein the confidence level is based on a sum of weights assigned to locations in a portion of the plurality of locations that is outside of the region.

7. The method of claim 4 , wherein the predetermined weight is based on a distribution of probability of the mobile device being at locations in a local area represented by the respective location.

8. The method of claim 1 , further comprising:

receiving device attributes of the mobile device;

identifying region attributes of the coordinates of the mobile device; and

determining the accuracy indicator based on the device attributes and the region attributes.

9. The method of claim 8 , wherein the determining of the accuracy indicator includes applying the device attributes and the region attributes in a predictive model trained using location data from a plurality of mobile devices having different device attributes and located in a plurality of regions having different region attributes.

10. A non-transitory computer storage medium storing instructions which, when executed by a computing device, instruct the computing device to perform a method, the method comprising:

storing, in the computing device, mapping data that connect identifiers of cells in a grid reference system to regions that contain respective cells identified by the identifiers in the grid reference system;

receiving, in the computing device, coordinates of a mobile device;

receiving, in the computing device, an accuracy indicator of the coordinates of the mobile device; and

identifying, by computing device, a region in which the mobile device is located, by:

identifying, from the accuracy indicator and the coordinates of the mobile device, a plurality of locations, including a location specified by the coordinates of the mobile device and at least one location different from the location specified by the coordinates of the mobile device;

converting coordinates of the plurality of locations into respective cell identifiers in the grid reference system, wherein respective cells in the grid reference system identified by the respective cell identifiers contain respective coordinates from which the respective cell identifiers are converted;

determining, from the mapping data, one or more regions that are connected to the cell identifiers in the mapping data, including the region in which the mobile device is subsequently identified to be located; and

evaluating, based on a portion of the plurality of locations that is in the region, a confidence level that the mobile device is located in the region, wherein the mobile device is identified to be located within the region in response to a determination that the confidence level is above a threshold.

11. The non-transitory computer storage medium of claim 10 , wherein the method further comprises:

identifying a size of a cell that has an identifier in the mapping data and contains the coordinates of the mobile device; and

selecting the at least one location, different from the location specified by the coordinates of the mobile device, based on the size of the cell.

12. The non-transitory computer storage medium of claim 10 , wherein the method further comprises:

receiving device attributes of the mobile device;

identifying region attributes of the coordinates of the mobile device; and

determining the accuracy indicator based on the device attributes and the region attributes.

13. A computing device, comprising:

at least one microprocessor;

memory storing instructions which, when executed by the at least one microprocessor, instruct the computing device to:

store, in the computing device, mapping data that connect identifiers of cells in a grid reference system to regions that contain respective cells identified by the identifiers in the grid reference system;

receive, in the computing device, coordinates of a mobile device having an accuracy indicator of the coordinates of the mobile device; and

identify, by computing device, a region in which the mobile device is located, by:

identifying, from the accuracy indicator and the coordinates of the mobile device, a plurality of locations, including a location specified by the coordinates of the mobile device and at least one location different from the location specified by the coordinates of the mobile device;

converting coordinates of the plurality of locations into respective cell identifiers in the grid reference system, wherein respective cells in the grid reference system identified by the respective cell identifiers contain respective coordinates from which the respective cell identifiers are converted;

determining, from the mapping data, one or more regions that are connected to the cell identifiers in the mapping data, including the region in which the mobile device is subsequently identified to be located; and

evaluating, based on a portion of the plurality of locations that is in the region, a confidence level that the mobile device is located in the region, wherein the mobile device is identified to be located within the region in response to a determination that the confidence level is above a threshold.

14. The computing device of claim 13 , wherein the instructions are further configured to instruct the computing device to:

receive device attributes of the mobile device;

identify region attributes of the coordinates of the mobile device; and

determine the accuracy indicator based on the device attributes and the region attributes.

15. The computing device of claim 14 , wherein the accuracy indicator is determined by applying the device attributes and the region attributes in a predictive model trained using location data from a plurality of mobile devices having different device attributes and located in a plurality of regions having different region attributes.

16. The computing device of claim 13 , wherein the instructions are further configured to instruct the computing device to:

identify a size of a cell that has an identifier in the mapping data and contains the coordinates of the mobile device; and

select the at least one location, different from the location specified by the coordinates of the mobile device, based on the size of the cell.

17. The computing device of claim 16 , wherein each respective location in the plurality of locations is assigned a predetermined weight for evaluation of the confidence level based on whether the respective location is in the region.

18. The computing device of claim 17 , wherein the confidence level is based on a sum of weights assigned to locations in the portion located within the region.

19. The computing device of claim 17 , wherein the confidence level is based on a sum of weights assigned to locations in a portion of the plurality of locations that is outside of the region.

20. The computing device of claim 17 , wherein the predetermined weight is based on a distribution of probability of the mobile device being at locations in a local area represented by the respective location.