Method and system for evaluating and selecting traceroutes to be used in determining the geographic location of a network block
View Patent ↗A method and system for evaluating and selecting traceroutes to be used in determining the geographic location of a network block. A particular embodiment of the system includes a set of traceroute feature vector extractors, each traceroute feature vector extractor being associated with at least one of a plurality of traceroutes, each traceroute feature vector extractor being configured to generate a traceroute feature vector for at least one of the plurality of traceroutes; a set of traceroute classifiers each coupled to at least one of the traceroute feature vector extractors, each traceroute classifier being associated with at least one of the plurality of traceroutes, each traceroute classifier being configured to generate at least one traceroute classification and/or regression based on at least one of the traceroute feature vectors; and a traceroute geolocation determining engine.
1. A method of determining a geographic location of a network block comprising:
obtaining geo-location data associated with a plurality of traceroutes, each traceroute corresponding to a data path through a plurality of network nodes;
generating, for each of the plurality of traceroutes, a traceroute feature vector, each traceroute feature vector including a plurality of attributes associated with a particular traceroute of the plurality of traceroutes, a value for a particular attribute of the plurality of attributes representing a degree to which that attribute is present or absent in the particular traceroute, the plurality of attributes being associated with a plurality of network data sources and a particular traceroute, the plurality of network data sources providing statistics related to each of the plurality of attributes;
providing a plurality of traceroute data collectors, each being associated with at least one of the plurality of traceroutes;
providing a plurality of traceroute classifiers, each being associated with at least one of the plurality of traceroute feature vectors;
classifying and/or regressing, by use of a processor, each of the plurality of traceroutes to generate traceroute classifications and/or regressions based on the traceroute feature vectors; and
determining a geographic location of the network block based upon at least one of the traceroute classifications and/or regressions.
2. The method of claim 1 wherein each of the plurality of traceroutes may be complete or incomplete traceroutes.
3. The method of claim 1 wherein the determined geographic location is associated with a best traceroute classification and/or regression.
4. The method of claim 1 including providing a traceroute geolocation determining engine that receives input from the plurality of traceroute classifiers.
5. The method of claim 1 wherein the geographic location is assigned on a country level, a state level, a city level, a zip code level, and/or a specific coordinate level.
6. The method of claim 1 including using supervised learning techniques to classify and/or regress each of the plurality of traceroutes to generate traceroute classifications and/or regressions based on the traceroute feature vectors and training data.
7. The method of claim 1 wherein the determined geographic location of the network block is based upon an interpolation between at least two of the traceroute assignment classifications and/or regressions.
8. The method of claim 1 including using autonomous system penetration data of each traceroute in generating each traceroute's feature vector.
9. 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:
obtain geo-location data associated with a plurality of traceroutes, each traceroute corresponding to a data path through a plurality of network nodes;
generate, for each of the plurality of traceroutes, a traceroute feature vector, each traceroute feature vector including a plurality of attributes associated with a particular traceroute of the plurality of traceroutes, a value for a particular attribute of the plurality of attributes representing a degree to which that attribute is present or absent in the particular traceroute, the plurality of attributes being associated with a plurality of network data sources and a particular traceroute, the plurality of network data sources providing statistics related to each of the plurality of attributes;
provide a plurality of traceroute data collectors, each being associated with at least one of the plurality of traceroutes;
provide a plurality of traceroute classifiers, each being associated with at least one of the plurality of traceroute feature vectors;
classify and/or regress each of the plurality of traceroutes to generate traceroute classifications and/or regressions based on the traceroute feature vectors; and
determine a geographic location of the network block based upon at least one of the traceroute classifications and/or regressions.
10. The article of manufacture of claim 9 wherein the determined geographic location is associated with a best traceroute classification and/or regression.
11. The article of manufacture of claim 9 being further configured to provide a traceroute geolocation determining engine that receives input from the plurality of traceroute classifiers.
12. The article of manufacture of claim 9 wherein the geographic location is assigned on a country level, a state level, a city level, a zip code level, and/or a specific coordinate level.