Indoor positioning techniques using beacons

1. A computing system comprising:

a non-transitory computer-readable medium; and

a processor in communication with the non-transitory computer-readable medium, the processor configured to execute instructions stored in the non-transitory computer-readable medium to:

obtain a corpus of location information associated with a plurality of areas of interest from a first client device, the corpus of location information comprising signal strength readings associated with a plurality of signal sources;

receive a location request from a second client device, the location request comprising one or more signal strength readings associated with a current position of the second client device;

determine, using a machine learning model, the current position corresponds to a fingerprint within a location map, the location map comprising one or more physical characteristics of a building, wherein the machine learning model is trained to:

(i) generate the location map comprising a plurality of fingerprints based on the corpus of location information and the one or more physical characteristics; and

(ii) determine a location based on a probability that a position matches a fingerprint in the location map; and

determine that the current position corresponds to the fingerprint; and

generate display information that includes location information associated with the fingerprint.

2. The computing system of claim 1 , wherein the corpus of location information comprises Bluetooth Low Energy (BLE) beacon information.

3. The computing system of claim 1 , wherein the corpus of location information comprises BLE beacon information and Wi-Fi signal information.

4. The computing system of claim 1 , wherein the one or more signal strength readings associated with a current position includes a BLE beacon signal, and wherein the second client device comprises a smartphone, tablet, or laptop.

5. The computing system of claim 1 , wherein the processor is further configured to execute instructions stored in the non-transitory computer-readable medium to:

transmit the location information to the second client device, wherein the location information is configured to cause the second client device to display a graphical user interface (GUI).

6. The computing system of claim 5 , wherein the location request is a first request, wherein the GUI comprises location information associated with the fingerprint, and the processor further configured to execute instructions stored in the non-transitory computer-readable medium to:

receive a second request from the second client device to modify location information associated with the fingerprint; and

in response to the request, modify the location information that is associated with the fingerprint.

7. The computing system of claim 6 , wherein the location information comprises a name or a graphical representation corresponding to an area of interest that is mapped to the fingerprint.

8. The computing system of claim 1 , wherein the machine learning model is further trained to:

retrieve a floorplan associated with the plurality of areas of interest;

determine label information for the plurality of areas of interest based on the floorplan; and

annotate the location map using the label information.

9. The computing system of claim 1 , wherein the machine learning model is further trained to:

retrieve a floorplan associated with the plurality of areas of interest;

compare the location map with the floorplan; and

modify the location map based on one or more differences between the location map and the floorplan.

10. The computing system of claim 1 , wherein the machine learning model is further trained to:

determine the plurality of fingerprints for each of the plurality of areas of interest based on one or more signal strength readings associated with a respective of area of interest.

11. The computing system of claim 1 , wherein the machine learning model is further trained to:

determine the plurality of fingerprints for each of the plurality of areas of interest based on a total number of signal strength readings observed within a respective of area of interest.

12. A method comprising:

obtaining, by a processor, a corpus of location information associated with a plurality of areas of interest from a first client device, the corpus of location information comprising signal strength readings associated with a plurality of signal sources;

receiving, by the processor, a location request from a second client device, the location request comprising a signal strength reading associated with a current position;

determining, using a machine learning model, whether the current position corresponds to a fingerprint within a location map, the location map comprising one or more physical characteristics of a building, wherein the machine learning model is trained by:

(i) generating the location map comprising a plurality of fingerprints based on the corpus of location information and the one or more physical characteristics; and

(ii) determining a location based on a probability that a position matches a fingerprint in the location map; and

determining, by the processor, that the current position corresponds to the fingerprint; and

generating, by the processor, display information that includes location information associated with the fingerprint.

13. The method of claim 12 , wherein the corpus of location information comprises BLE beacon information and Wi-Fi signal information.

14. The method of claim 12 , wherein the location request is a first request, and further comprising:

transmitting, by the processor, the location information to the second client device, wherein the location information is configured to cause the second client device to display a GUI, and wherein the GUI comprises the location information associated with the fingerprint;

receiving, by the processor, a second request to modify location information associated with the fingerprint; and

in response to the second request, modifying, by the processor, the location information that is associated with the fingerprint.

15. The method of claim 14 , wherein the location information comprises a name or a graphical representation corresponding to an area of interest that is mapped to the fingerprint.

16. The method of claim 12 , wherein the machine learning model is further trained by:

retrieving a floorplan associated with the plurality of areas of interest;

determining label information for the plurality of areas of interest based on the floorplan; and

annotating the location map using the label information.

17. The method of claim 12 , wherein the machine learning model is further trained by:

retrieving a floorplan associated with the plurality of areas of interest;

comparing the location map with the floorplan; and

modifying the location map based on one or more differences between the location map and the floorplan.

18. The method of claim 12 , wherein the machine learning model is further trained by:

determining the plurality of fingerprints for each of the plurality of areas of interest based on either (i) one or more signal strength readings associated with a respective of area of interest or (ii) a total number of signal strength readings observed within a respective of area of interest.

19. A non-transitory computer-readable medium comprising program code executable by a processor to cause the processor to train a machine learning model to:

obtain a corpus of location information associated with a plurality of areas of interest from a first client device, the corpus of location information comprising signal strength readings associated with a plurality of signal sources;

receive a location request from a second client device, the location request comprising one or more signal strength readings associated with a current position of the second client device;

determine, using a machine learning model, the current position corresponds to a fingerprint within a location map, the location map comprising one or more physical characteristics of a building, wherein the machine learning model is trained to:

(i) generate the location map comprising a plurality of fingerprints based on the corpus of location information and the one or more physical characteristics; and

(ii) determine a location based on a probability that a position matches a fingerprint in the location map;

(iii) determine that the current position corresponds to the fingerprint; and

(iv) generate display information that includes location information associated with the fingerprint.

20. The non-transitory computer-readable medium of claim 19 , wherein generating the location map further comprises program code executable by a processor to:

retrieve a floorplan associated with the plurality of areas of interest;

compare the location map with the floorplan; and

modify the location map based on one or more differences between the location map and the floorplan.