SYSTEM AND METHOD FOR IMPLEMENTING A LEARNING MODEL FOR PREDICTING THE GEOGRAPHIC LOCATION OF AN INTERNET PROTOCOL ADDRESS

• US 20130031033A1
• Filed: 07/28/2011
• Published: 01/31/2013
• Est. Priority Date: 07/28/2011
• Status: Active Grant

• Current Assignee: NeuStar IP Intelligence, Inc. (Neustar Incorporated)
• Original Assignee: Quova Inc. (Neustar Incorporated)
• Inventors: Prieditis, Armand Erik
• Granted Patent: US 8,788,437 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04L 2101/69 using geographic information, e.g. room number
• CPC Class Codes: H04L 61/5007 Internet protocol [IP] addresses
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

A system and method for implementing a learning model for predicting the geographic location of an Internet Protocol (IP) address are disclosed. A particular embodiment of the system and method includes receiving a model to predict a geographic coordinates position of an Internet Protocol (IP) address, the model including one or more parameters and one or more variables associated with coordinates of the IP address and corresponding information associated with the IP address; receiving training data including a plurality of pairs of coordinates of a target IP address and corresponding information associated with the target IP address; determining, by use of a processor, the one or more parameters based on the training data and the model; and returning a result including information indicative of the determined parameters.

Claims

1. A method for implementing a learning model for predicting the geographic location of an Internet Protocol (IP) address, the method comprising:

receiving a model to predict a geographic coordinates position of an Internet Protocol (IP) address, the model including one or more parameters and one or more variables associated with coordinates of the IP address and corresponding information associated with the IP address;

receiving training data including a plurality of pairs of coordinates of a target IP address and corresponding information associated with the target IP address;

determining, by use of a processor, the one or more parameters based on the training data and the model; and

returning a result including information indicative of the determined parameters.

2. The method of claim 1 wherein the model is a parametric model.

3. The method of claim 1 including using at least one mean vector generated from the training data.

4. The method of claim 1 including using at least one covariance matrix generated from the training data.

5. The method of claim 1 wherein the result includes model parameters for use with the model to predict the geographic coordinates of the target IP address.

6. The method of claim 1 including generating at least one sum of values in a column of the training data.

7. The method of claim 1 including generating at least one product of values in a pair of columns of the training data.

8. An Internet Protocol (IP) address geo-location learning model system comprising:

a processor;

a model receiving component, in data communication with the processor, to receive a model to predict a geographic coordinates position of an Internet Protocol (IP) address, the model including one or more parameters and one or more variables associated with coordinates of the IP address and corresponding information associated with the IP address;

a training data receiving component, in data communication with the processor, to receive training data including a plurality of pairs of coordinates of a target IP address and corresponding information associated with the target IP address;

a parameter determining component to determine the one or more parameters based on the training data and the model, and to return a result including information indicative of the determined parameters.

9. The geo-location learning model system of claim 8 wherein the model is a parametric model.

10. The geo-location learning model system of claim 8 being configured to use at least one mean vector generated from the training data.

11. The geo-location learning model system of claim 8 being configured to use at least one covariance matrix generated from the training data.

12. The geo-location learning model system of claim 8 wherein the result includes model parameters for use with the model to predict the geographic coordinates of the target IP address.

13. The geo-location learning model system of claim 8 being configured to generate at least one sum of values in a column of the training data.

14. The geo-location learning model system of claim 8 being configured to generate at least one product of values in a pair of columns of the training data.

15. An article of manufacture comprising a non-transitory machine-readable storage medium having machine executable instructions embedded thereon, which when executed by a machine, cause the machine to:

receive a model to predict a geographic coordinates position of an Internet Protocol (IP) address, the model including one or more parameters and one or more variables associated with coordinates of the IP address and corresponding information associated with the IP address;

receive training data including a plurality of pairs of coordinates of a target IP address and corresponding information associated with the target IP address;

determine the one or more parameters based on the training data and the model; and

return a result including information indicative of the determined parameters.

16. The article of manufacture of claim 15 wherein the model is a parametric model.

17. The article of manufacture of claim 15 being configured to use at least one mean vector generated from the training data.

18. The article of manufacture of claim 15 being configured to use at least one covariance matrix generated from the training data.

19. The article of manufacture of claim 15 being configured to generate at least one sum of values in a column of the training data.

20. The article of manufacture of claim 15 being configured to generate at least one product of values in a pair of columns of the training data.