VENUE IDENTIFICATION FROM WIRELESS SCAN DATA

• US 20160295372A1
• Filed: 03/31/2015
• Published: 10/06/2016
• Est. Priority Date: 03/31/2015
• Status: Active Grant

• Current Assignee: Foursquare Labs, Inc.
• Original Assignee: Foursquare Labs, Inc.
• Inventors: Kapicioglu, Cagatay Berk, Shaw, Blake
• Granted Patent: US 9,860,704 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

In non-limiting examples, wireless scan data collected from a processing device is directly mapped to venues. Wireless scan data is received from a processing device where the wireless scan data comprises at least a first identifier of a wireless connection. Venues associated with the first identifier are identified from a mapping of wireless identifiers to venues based on active validation data associated with particular venues including historical wireless scan data of the particular venues. The plurality of venues are ranked according to a likelihood that the processing device is located at a particular venue based on evaluating the active validation data including the historical wireless scan data from the mapping. A predicted venue that the processing device is located at is determined based on the ranking of the plurality of venues. Other examples are also described.

Claims

1. A computer-implemented method comprising:

receiving wireless scan data from a processing device, the wireless scan data comprising a first identifier of a wireless connection;

identifying a plurality of venues associated with the first identifier of the collected wireless scan data from a mapping of wireless identifiers to venues, wherein the mapping is based on active validation data associated with particular venues including historical wireless scan data of the particular venues;

ranking the plurality of venues according to a likelihood that the processing device is located at a particular venue based on evaluating the active validation data including the historical wireless scan data from the mapping; and

determining a predicted venue that the processing device is located at based on the ranking of the plurality of venues.

2. The computer-implemented method according to claim 1, wherein wireless scan data comprises a plurality of wireless identifiers, and the wireless identifier is at least one of a MAC address, beacon data and Bluetooth data.

3. The computer-implemented method according to claim 1, wherein the ranking further comprises applying a first machine-learning model to determine the likelihood the processing device is located at the predicted venue, wherein the first machine-learning model assigns a probability to at least a first venue of the plurality of venues that the first venue is associated with the first identifier based on evaluation of a second identifier associated with the active validation data accumulated from previous visits at the first venue.

4. The computer-implemented method according to claim 1, further comprising transmitting a notification including the predicted venue to the processing device, wherein the notification indicates that the processing device is located at the predicted venue.

5. The computer-implemented method according to claim 3, wherein the ranking further comprises applying at least a second machine-learning process to determine the likelihood the processing device is located at the venue, the second machine-learning process is a filtering process that removes one or more venues from the plurality of venues based on application of one or more filter processes.

6. The computer-implemented method according to claim 1, wherein the ranking further comprises applying a machine-learning model to determine the likelihood the processing device is located at the predicted venue, the machine learning model comparing similarities between signal strength detected for a wireless connection associated with the first identifier and a predicted signal strength.

7. The computer-implemented method according to claim 1, further comprising generating the mapping from a plurality of wireless scan data collected from the devices and a plurality of active validation data collected during visits at a plurality of venues, wherein the mapping associates wireless scan data with venues corresponding to a user at a visit to a venue.

8. The computer-implemented method according to claim 1, wherein determining the predicted venue further comprises transmitting, to the processing device, a listing comprising one or more venues based on the ranking of the plurality of venues.

9. The computer-implemented method according to claim 1, wherein determining the predicted venue further comprises receiving telemetry data regarding correctness of the predicted venue, and updating the mapping based on the received telemetry data.

10. The computer-implemented method according to claim 1, wherein the active validation data further comprises social signals from a user profile associated with the processing device, and the ranking of the identified venues evaluates at least one of spatial signals collected from the processing device and the social signals to determine a probability that a venue is associated with the identifier of the wireless scan data.

11. A system comprising:

a memory; and

at least one processor connected with the memory, configured to execute operations comprising;

receiving wireless scan data from a processing device, the wireless scan data comprising a plurality of MAC addresses,

identifying venues associated with the MAC addresses of the collected wireless scan data from a mapping of MAC addresses to venues, wherein the mapping is based on active validation data associated with particular venues including historical wireless scan data of the particular venues,

ranking the plurality of venues according to a likelihood that the processing device is located at a particular venue based on evaluating the active validation data including the historical wireless scan data from the mapping, and

determining a predicted venue that the processing device is located at based on the ranking of the plurality of venues.

12. The system according to claim 11, wherein the ranking executed by the processor further comprises applying a first machine-learning model to determine the likelihood the processing device is located at the predicted venue, wherein the first machine-learning model assigns a probability to at least a first venue of the plurality of venues that the first venue is associated with a MAC address based on evaluation of a second MAC address associated with the active validation data accumulated for previous visits at the first venue.

13. The system according to claim 11, wherein the operations executed by the processor further comprising transmitting a notification including the predicted venue to the processing device, wherein the notification indicates that the processing device is located at the predicted venue.

14. The system according to claim 12, wherein the ranking executed by the processor further comprises applying at least a second machine-learning model to determine the likelihood the processing device is located at the predicted venue, and wherein the second machine-learning model is a filtering process that removes one or more venues from the plurality of venues based on application of one or more filtering processes.

15. The system according to claim 11, wherein the ranking executed by the processor further comprises applying a machine-learning model to determine the likelihood the processing device is located at the predicted venue, the machine learning model comparing similarities between signal strength detected for a wireless connection associated with a MAC address and a predicted signal strength for a wireless connection of a venue.

16. The system according to claim 11, wherein the operations executed by the processor further comprising generating the mapping from a plurality of pieces of wireless scan data collected from the devices and a plurality of active validation data collected during visits at a plurality of venues, wherein the mapping associates wireless scan data with venues corresponding to a processing device at a time of a visit to a venue.

17. The system according to claim 11, wherein the determining of the predicted venue executed by the processor further comprises transmitting, to the processing device, a listing comprising one or more venues based on the ranking of the plurality of venues.

18. The system according to claim 11, wherein the determining of the predicted venue executed by the processor further comprises receiving telemetry data regarding correctness of the predicted venue, and updating the mapping based on the received telemetry data.

19. The system according to claim 11, wherein the active validation data further comprises social signals associated with a user profile operating on the processing device, and the ranking of the identified venues evaluates at least one of spatial signals collected from the processing device and the social signals associated with the user profile to determine a probability that a venue is associated with a MAC address of the wireless scan data.

20. (canceled)

21. A method comprising:

receiving wireless scan data from a first processing device;

evaluating the wireless scan data using at least one stored mapping structure to identify candidate venues;

associating the wireless scan data with one or more candidate venues.