Estimating Whether Or Not A Wireless Terminal Is In A Geographic Zone Using Pattern Classification

• US 20080207222A1
• Filed: 08/23/2007
• Published: 08/28/2008
• Est. Priority Date: 02/28/2007
• Status: Active Grant

• Current Assignee: Polaris Wireless Incorporated
• Original Assignee: Polaris Wireless Incorporated
• Inventors: Gordon, Scot Douglas, Feuerstein, Martin, Bhattacharya, Tarun Kumar
• Granted Patent: US 9,247,516 B2
• Time in Patent Office: Days
• US Class Current: 455/456.1
• CPC Class Codes: G01S 5/02525 Gathering the radio frequency fingerprints
• CPC Class Codes: H04W 4/02 Services making use of location information
• 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

A method and apparatus are disclosed for estimating whether or not a wireless terminal is in a geographic zone. The illustrative embodiment employs a pattern classifier that is trained on traits of electromagnetic signals at various locations. A computer-executable program is then generated based on the trained pattern classifier, and the program is installed and executed on a subscribed identity module of the terminal.

Claims

1. A method comprising:

generating a computer-executable program that

(i) accepts an input based on one or more traits of one or more electromagnetic signals at a geo-location, and

(ii) outputs an indication of whether said geo-location is inside a geographic zone Z; and

transmitting said computer-executable program to a wireless terminal for local execution at said wireless terminal.

2. The method of claim 1 wherein said computer-executable program is based on a pattern classifier that is trained on a plurality of input-output mappings, and wherein each of said input-output mappings is associated with a respective geo-location, and wherein each of said input-output mappings comprises

(i) an input based on one or more traits of one or more electromagnetic signals at said respective geo-location, and

(ii) a Boolean output that indicates whether said respective geo-location is inside said geographic zone Z.

3. The method of claim 2 wherein said computer-executable program is also based on a characteristic, C, of said wireless terminal.

4. The method of claim 1 wherein the generation of said computer-executable program is performed in response to an expected change in at least one trait at least one geo-location.

5. The method of claim 1 further comprising installing said computer-executable program on a subscriber identity module of said wireless terminal.

6. The method of claim 1 further comprising executing said computer-executable program locally at said wireless terminal.

7. The method of claim 6 further comprising:

generating an input for said computer-executable program that is based on one or more traits of one or more electromagnetic signals measured at said wireless terminal; and

generating at said wireless terminal a signal based on the output of said computer-executable program.

8. A method comprising:

receiving at a wireless terminal a computer-executable program that

(i) accepts an input based on one or more traits of one or more electromagnetic signals at a geo-location, and

(ii) outputs an indication of whether said geo-location is inside a geographic zone Z; and

executing said computer-executable program locally at said wireless terminal.

9. The method of claim 8 wherein said computer-executable program is based on a pattern classifier that is trained on a plurality of input-output mappings, and wherein each of said input-output mappings is associated with a respective geo-location, and wherein each of said input-output mappings comprises

(i) an input based on one or more traits of one or more electromagnetic signals at said respective geo-location, and

(ii) a Boolean output that indicates whether said respective geo-location is inside said geographic zone Z.

10. The method of claim 8 further comprising installing said computer-executable program on a subscriber identity module of said wireless terminal.

11. The method of claim 8 further comprising:

inputting to said computer-executable program one or more traits of one or more electromagnetic signals measured at said wireless terminal; and

generating at said wireless terminal a signal based on the output of said computer-executable program.

12. The method of claim 8 wherein said computer-executable program is based on a characteristic of said wireless terminal.

13. The method of claim 8 further comprising removing from a memory of said wireless terminal a prior version of said computer-executable program.

14. A method comprising:

receiving one or more data values at a wireless terminal, wherein said parameter values are for a computer-executable program that executes locally at said wireless terminal, and wherein said computer-executable program

(i) accepts an input based on one or more traits of one or more electromagnetic signals at a geo-location, and

(ii) outputs an indication of whether said geo-location is inside a geographic zone Z; and

executing said computer-executable program with said data values at said wireless terminal.

15. The method of claim 14 wherein said computer-executable program is based on a pattern classifier, and wherein at least one of said data values is for a parameter of said pattern classifier.

16. The method of claim 15 wherein said pattern classifier is a support vector machine, and wherein said parameter is a weight of said support vector machine.

17. The method of claim 14 further comprising substituting said one or more data values for a prior set of values.

18. The method of claim 14 wherein at least one of said data values is based on a characteristic of said wireless terminal.

19. A method comprising:

training a pattern classifier on a plurality of input-output mappings, wherein each of said input-output mappings is associated with a respective geo-location, and wherein each of said input-output mappings comprises

(i) an input based on one or more traits of one or more electromagnetic signals at a geo-location, and

(ii) a Boolean output that indicates whether said respective geo-location is inside a geographic zone Z; and

generating a computer-executable program based on the trained pattern classifier.

20. The method of claim 19 wherein said computer-executable program is for local execution at a wireless terminal.

21. The method of claim 20 wherein said computer-executable program is based on a characteristic of said wireless terminal.

22. The method of claim 19 further comprising:

re-training said pattern classifier on a new plurality of input-output mappings in response to a change in said geographic zone Z; and

generating a new computer-executable program based on the re-trained pattern classifier.

23. The method of claim 19 further comprising:

re-training said pattern classifier on a new plurality of input-output mappings in response to a change in a network comprising one or more electromagnetic signal transmitters; and

generating a new computer-executable program based on the re-trained pattern classifier.

24. A method comprising:

training a pattern classifier on a plurality of input-output mappings, wherein each of said input-output mappings is associated with a respective geo-location, and wherein each of said input-output mappings comprises

(i) an input based on one or more traits of one or more electromagnetic signals at a geo-location, and

(ii) a Boolean output that indicates whether said respective geo-location is inside a geographic zone Z; and

transmitting one or more parameter values of the trained pattern classifier to a wireless terminal.

25. The method of claim 24 wherein said parameter values are for instantiating a computer-executable program that executes locally at said wireless terminal and that estimates whether said wireless terminal is inside said geographic zone Z.

26. The method of claim 24 further comprising:

re-training said pattern classifier on a new plurality of input-output mappings in response to a change in said geographic zone Z; and

transmitting one or more parameter values of the re-trained pattern classifier to said wireless terminal.

27. The method of claim 24 further comprising:

re-training said pattern classifier on a new plurality of input-output mappings in response to a change in a network comprising one or more electromagnetic signal transmitters; and

transmitting one or more parameter values of the re-trained pattern classifier to said wireless terminal.