Training pattern recognition systems for determining user device locations

• US 8,774,830 B2
• Filed: 06/22/2012
• Issued: 07/08/2014
• Est. Priority Date: 06/24/2011
• Status: Active Grant

• Current Assignee: Plainsight Technologies Incorporated
• Original Assignee: ZOS Communications LLC
• Inventors: Ziskind, Russell, McKechney, Chris, Seaman, Jeffrey, Patel, Ankur, Pastuszek, Brandon, Impellizzieri, Joseph, Gottfried, Samuel
• Primary Examiner(s): Ajayi, Joel
• Application Number:
  US13/531,398
• Publication Number:
  US 20130165143A1
• Time in Patent Office: 746 Days
• Field of Search: 455/456.1
• US Class Current: 455/456.1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

A query device scans radio frequencies for visible transmitting devices. The querying device receives at least a signal strength and identifier information associated with each of the transmitting devices. The list of visible devices is used to query a database containing location information for a plurality of visible devices. The list may be sent to a locationing system that may perform a location analysis on the resulting data to return a location to the query device. The weighted average of the locations returned in the database query may be computed to determine the location of the querying device, with the weight for each of the locations being the current signal strength detected by the querying device. Neural network analysis may also be used to determine the location of the querying device. Learning and seeding operations many also be used to populate the database with location information for transmitting devices.

Claims

1. A computer-implemented method for determining a location of a device, comprising the steps of:

scanning with the device one or more radio frequencies for one or more visible transmitting devices;

receiving with the device a signal strength and an identifier for each visible transmitting device among the one or more visible transmitting devices;

using the identifier to query a database containing location points for a plurality of visible transmitting devices;

for visible transmitting devices having location points within the database, performing a weighted average analysis of those location points for each identifier to determine an average of those location points for the identifier, resulting in a set of averages, wherein a weight assigned to each location point is based on the signal strength for the visible transmitting device corresponding to that location point;

storing the set of averages in the database;

sending the set of averages to a pattern recognition system; and

deriving the location of the device using the pattern recognition system based on the set of averages.

2. The method as recited in claim 1, wherein the pattern recognition system is trained using mapped associations between patterns associated with the set of averages for the visible transmitting devices within a plurality of regions within a geographic area.

3. The method as recited in claim 1, wherein the pattern recognition system includes one or more of a neural network, a classifier system, a decision tree, a support vector machine, and a clustering algorithm.

4. The method as recited in claim 1, further comprising the step of sending the set of averages to one or more other pattern recognition systems generating a location estimate for the device with a confidence level, and wherein the location estimate with a highest confidence level is selected as the location of the device.

5. The method as recited in claim 4, wherein an output from the one or more other pattern recognition systems is weighted by a weight.

6. The method as recited in claim 5, wherein the weight is based on the confidence level associated with each pattern recognition system among the one or more other pattern recognition systems.

7. The method as recited in claim 1, further comprising the step of sending the set of averages to one or more other pattern recognition systems, wherein an output from the one or more pattern recognition systems is weighted by a weight.

8. The method as recited in claim 7, wherein the weight is determined by a user.

9. The method as recited in claim 1, wherein the identifier includes at least one of a media access control address, a service set identifier, or another unique identifier.

10. The method as recited in claim 1, wherein the location of the device includes a longitude coordinate and a latitude coordinate.

11. The method as recited in claim 10, wherein the location of the device further includes an altitude coordinate.

12. The method as recited in claim 1, wherein the location of the device is a label representative of the location of the device.

13. The method as recited in claim 1, wherein the database is populated with averages of location points from one or more seeding devices.

14. The method as recited in claim 1, wherein the one or more seeding devices are location-aware devices.

15. A system for determining a location of a device, comprising:

a computer processor;

a memory in communication with the computer processor when the system is activated, the memory comprising computer readable instructions that upon execution by the computer processor cause the system to scan with the device one or more radio frequencies for one or more visible transmitting devices, receive with the device a signal strength and an identifier for each visible transmitting device among the one or more visible transmitting devices, use the identifier to query a database containing location points for a plurality of visible transmitting devices, for visible transmitting devices having location points within the database, perform a weighted average analysis of those location points for each identifier to determine an average of those location points for the identifier, resulting in a set of averages, wherein a weight assigned to each location point is based on the signal strength for the visible transmitting device corresponding to that location point, store the set of averages in the database, send the set of averages to a pattern recognition system, and derive the location of the device using the pattern recognition system based on the set of averages.