Facilitation of mobile device geolocation

• US 9,848,301 B2
• Filed: 11/20/2015
• Issued: 12/19/2017
• Est. Priority Date: 11/20/2015
• Status: Active Grant

• Current Assignee: AT&T Mobility II LLC (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.), AT&T Mobility II LLC (AT&T, Inc.)
• Inventors: Mappus, Rudolph, Fix, Jeremy, Doejode, Ravishankar, White, James Morgan
• Primary Examiner(s): Shen, Qun
• Application Number:
  US14/947,152
• Publication Number:
  US 20170150318A1
• Time in Patent Office: 760 Days
• Field of Search: 4554561
• CPC Class Codes: H04W 4/025 using location based information parameters

Abstract

More efficient mobile device location data can be obtained by estimating a most likely location point in a coverage pattern using a kernel density estimation technique. The kernel density estimation technique can provide a continuous estimate of the most frequented locations of a mobile device(s) within a coverage area. For each wireless sector, the collected location data can grouped to the closest geographic coordinate system, and an inference can be made based on the grouped data.

Claims

1. A method, comprising:

receiving, by a wireless network device of a wireless network comprising a processor, location data representing previous locations of a mobile device of mobile devices;

grouping, by the wireless network device, the location data according to a geographic coordinate system;

estimating, by the wireless network device, a probability density of a random variable associated with the grouping, resulting in an estimated number of the mobile devices;

based on the estimated number of mobile devices exceeding a defined number of the mobile devices associated with a network capacity of a transceiver of the wireless network, generating an indication that additional network capacity beyond the network capacity is needed;

identifying, by the wireless network device, a location point based on the probability density; and

based on the location point and the indication, determining, by the wireless network device, a probable location of the mobile device according to a defined probability function.

2. The method of claim 1, wherein the grouping comprises mapping the location data to another value representative of an interval associated with the location data.

3. The method of claim 2, wherein the grouping comprises mapping the location data to a military grid reference system.

4. The method of claim 1, wherein the estimating comprises a kernel density estimation.

5. The method of claim 1, further comprising:

storing, by the wireless network device, the location point within an indexed data structure.

6. The method of claim 5, wherein the indexed data structure is indexed by a sector identifier relating to a sector of the wireless network.

7. The method of claim 5, further comprising:

updating, by the wireless network device, the data structure at a defined interval based on historical location data.

8. The method of claim 5, further comprising:

updating, by the wireless network device, the data structure at a defined interval based on the location data.

9. The method of claim 1, wherein the estimating comprises estimating the probability density of the random variable associated with the grouping according to defined time intervals.

10. A system, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

receiving mobile device location data associated with preceding locations of a mobile device of mobile devices;

binning the location data according to bins of a geographic coordinate system wherein the binning results in an estimated number of the mobile devices;

based on the estimated number of the mobile devices and in response to a condition associated with a network capacity of a transceiver device being determined to have been satisfied, generating a request for additional network capacity over the network capacity; and

in response to determining a probable location of the mobile device and the generating the request, determining a frequented location of the mobile device, wherein the determining the probable location comprises estimating a probability density of a random variable associated with the binning.

11. The system of claim 10, wherein the binning comprises mapping the location data to areas of a universal transverse mercator grid system.

12. The system of claim 10, wherein the binning comprises mapping the location data to areas of a universal polar stereographic grid system.

13. The system of claim 10, wherein the estimating comprises a kernel density estimation.

14. The system of claim 13, wherein the kernel density estimation comprises a determination based on a Gaussian function.

15. The system of claim 10, wherein the operations further comprise:

storing the frequented location within an indexed data structure.

16. The system of claim 15, wherein the operations further comprise:

updating the indexed data structure according to a daily interval based on historical location data.

17. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

receiving location data representing previous locations of mobile devices of a wireless network;

grouping the location data according to areas of a geographic coordinate system resulting in groups of the location data;

estimating a probability density of a random variable associated with the groups, resulting in an estimated number of the mobile devices;

in response to a determination that the estimated number of the mobile devices exceeds a network capacity of a transceiver of the wireless network, generating an indication that additional network capacity for the wireless network is to be requested;

identifying a location point based on the probability density; and

based on the previous locations of the mobile devices and the location point, determining a probable location of a mobile device of the mobile devices.

18. The non-transitory machine-readable storage medium of claim 17, wherein the estimating the probability density comprises estimating a kernel density of the groups.

19. The non-transitory machine-readable storage medium of claim 18, wherein the estimating the kernel density comprises estimating a triangular kernel density of the groups.

20. The non-transitory machine-readable storage medium of claim 19, wherein the estimating the triangular kernel density is performed at a defined time interval.