System and method for implementing a learning model for predicting the geographic location of an internet protocol address
View Patent ↗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.
1. A method for predicting a geographic location of a target Internet Protocol (IP) address, the method comprising:
obtaining a multivariate normal model which includes one or more parameters derived from (i) training transit time data between a plurality of training IP addresses and beacon IP addresses for one or more beacons over a network, and (ii) known geographic locations for the plurality of training IP addresses;
obtaining transit time information between the target IP address and the beacon IP addresses; and
predicting, by use of a processor, the geographical geographic location of the target IP address by using the obtained transit time information and the one or more parameters of the multivariate normal model.
2. The method of claim 1 , wherein the transit time information comprises one or more message transit times between the target IP address and each of the beacon IP addresses.
3. The method of claim 1 , wherein the one or more parameters of the multivariate normal model comprise a mean vector and a covariance matrix that characterize the training transit time data and the known geographic locations for the plurality of training IP addresses.
4. An apparatus for predicting device geographic location of a target Internet Protocol (IP) address, the apparatus comprising:
a processor;
memory to store instructions that, when executed by the processor, cause the processor to:
obtain a multivariate normal model which includes one or more parameters derived from (i) training transit time data between a plurality of training IP addresses and beacon IP addresses for one or more beacons over a network, and (ii) known geographic locations for the plurality of training IP addresses;
obtain transit time information between the target IP address and the beacon IP addresses; and
predict, by use of a processor, the geographic location of the target IP address by using the obtained transit time information and the one or more parameters of the multivariate normal model.
5. The apparatus of claim 4 , wherein the transit time information comprises one or more message transit times between the target IP address and each of the beacon IP addresses.
6. The apparatus of claim 4 , wherein the one or more parameters of the multivariate normal model comprise a mean vector and a covariance matrix that characterize the training transit time data and the known geographic locations for the plurality of training IP addresses.
7. A non-transitory machine-readable storage medium having machine executable instructions embedded thereon, which when executed by a processor, cause the processor to:
obtain a multivariate normal model which includes one or more parameters derived from (i) training transit time data between a plurality of training IP addresses and beacon IP addresses for one or more beacons over a network, and (ii) known geographic locations for the plurality of training IP addresses;
obtain transit time information between the target IP address and the beacon IP addresses; and
predict, by use of a processor, the geographic location of the target IP address by using the obtained transit time information and the one or more parameters of the multivariate normal model.
8. The method of claim 1 , wherein predicting the geographic location of the target IP address includes relating the obtained transit time information with the training transit time data and the known geographic locations.
9. The method of claim 1 , wherein geographic locations of the one or more beacons are unknown.
10. The method of apparatus of claim 4 , wherein predicting the geographic location of the target IP address includes relating the obtained transit time information with the training transit time data and the known geographic locations.
11. The method of apparatus of claim 4 , wherein geographic locations of the one or more beacons are unknown.