System and Method for Proximity Detection

• US 20140087769A1
• Filed: 10/11/2013
• Published: 03/27/2014
• Est. Priority Date: 03/17/2011
• Status: Active Grant

• Current Assignee: Kaarya LLC
• Original Assignee: Kaarya LLC
• Inventors: Nath, Ujjual, Sharma, Gaurav, MacGlashan, Douglas, Billett, Brian, Fletcher, William
• Granted Patent: US 9,726,749 B2
• Time in Patent Office: Days
• US Class Current: 455/456.6
• CPC Class Codes: G01S 5/02529 not involving signal parameters, i.e. only involving identifiers
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

The present invention is for a system and method for determining the proximity of a mobile device to a location without the use of a satellite based or other location awareness system, nor a stationary beacon of any kind Instead, the mobile device monitors radio frequency broadcast identification codes from nearby mobile devices, and determines if the set of detected identification codes is sufficiently similar to a weighted set of identification codes attributed to specified location. If the calculation of similarity meets the confidence conditions of the system, notification is made that the customer or visitor has arrived. The invention utilizes a combination of confidence interval computation, machine learning, and fault tolerance mechanisms to optimize the success of correctly detecting that the device is near the relevant location.

Claims

1. A system for detecting a presence of a user'"'"'s mobile device at a location comprising:

a central server computing device configured to receive data from the user'"'"'s mobile device, wherein the user'"'"'s mobile device is configured to detect and identify devices by the use of a short range radio frequency digital communication protocol;

non-transitory computer readable media comprising computer instructions which when executed by the computing device cause the system;

to receive and process said data from the user'"'"'s mobile device on the computing device, said data including device identities detected by the user'"'"'s mobile device;

to compute a probability of the user'"'"'s mobile device presence at the location based at least in part on a set of said device identities received from the user'"'"'s mobile device;

whereby when the computed probability exceeds a threshold value, the system indicates the presence of the user'"'"'s mobile device at the location.

2. A system as in claim 1 wherein, the computer instructions are further configured to communicate the user presence at the location to one or more client devices.

3. A system as in claim 1, wherein the user is a pre-registered retail customer.

4. A system as in claim 1, wherein the user'"'"'s mobile device is a smartphone.

5. A system as in claim 1, wherein the location is a department within a retail business location.

6. A system as in claim 1, wherein said set comprises two or more mobile devices.

7. A system as in claim 1, wherein the computer instructions are further configured:

to assign a weight value to at least a portion of the devices in said set;

to modify the weight values of at least a portion of the devices in said set by machine learning based upon successes and failures.

8. A system as in claim 1, wherein the computing device is configured to receive data from more than one user device.

9. A method of detecting a presence of a user with a mobile device at a location comprising:

receiving data on a computing system , the data comprising device identification information corresponding to devices detected by the user mobile device, wherein the user'"'"'s mobile device is equipped with a radio frequency signal interface, wherein the user'"'"'s mobile device uses a short range radio frequency communication protocol, wherein said device identification information forms a set of device identities;

determining a confidence level of said user presence at the location based on the set of device identities;

comparing the confidence level to a confidence boundary of the user'"'"'s presence at the location;

communicating an indication of the user'"'"'s mobile device presence, based on said comparison, wherein if the confidence level exceeds the confidence boundary, the indication is positive.

10. A method as in claim 9 wherein, said device identification information comprises the identification of other identifiable radio frequency emitting devices using said communication protocol.

11. A method as in claim 9, wherein the computing device is configured to receive identification information from more than one users'"'"' mobile devices.

12. A method as in claim 9, wherein at least a portion of the device identities are assigned weight values used in the determination of the confidence level of the user presence at the location.

13. A method as in claim 9, wherein:

at least a portion of the device identities are assigned weight values used in the determination of the confidence level of the user presence at the location and,

at least a portion of the device weight values may be modified by machine learning to improve the determination of the confidence level of the user presence at the location.

14. Non-transitory computer readable media comprising computer instructions executed by a computing device, the instructions comprising:

instructions to receive data from a user'"'"'s mobile device comprising the identification information of nearby devices detected with a radio frequency signal interface using a short range digital communication protocol;

instructions to process said received identification information as a set of nearby device identities;

instructions to process said set of nearby device identities to determine the probability of a presence of the user'"'"'s mobile device at a location.

15. Non-transitory computer readable media as in claim 14, further comprising:

instructions to communicate the probability of the presence of the user'"'"'s mobile device at said location to one or more client devices.

16. Non-transitory computer readable media as in claim 14, further comprising:

instructions to assign weight values to at least a portion of the identities of detected devices relating to the association of the location to the detected devices.

17. Non-transitory computer readable media as in claim 14, further comprising:

instructions to assign weight values to at least a portion of the identities of detected devices relating to the association of the location to the detected device;

instructions to determine the probability of the user presence utilizing at least a portion of said detected and weighted device identities.

18. Non-transitory computer readable media as in claim 14, further comprising:

instructions to assign weight values to at least a portion of the identities of detected devices relating to the association of the location to the detected devices;

instructions to determine the probability of the user presence utilizing at least a portion of said detected and weighted device identities;

instructions to utilize machine learning to improve the probability determination by the adjustment of at least a portion of said weight values based upon feedback of success and failure.

19. Non-transitory computer readable media as in claim 14, wherein the computing device is configured to receive data from more than one user'"'"'s device.