System and method for detecting location anomalies of mobile devices
Aspects of the subject disclosure may include, for example, a device, having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of: generating a hash table of keys from identifiers for mobile devices in a communications network; filtering records of signaling events received from the communications network; sorting the records of signaling events to generate a time sequence of records for each key; determining a trajectory for each key in the time sequence of records; and generating an alert responsive to discovering a location anomaly in the trajectory. Other embodiments are disclosed.
1 . A device, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
generating a hash table of keys from International Mobile Equipment Identifiers (IMEIs) for mobile devices in a communications network;
filtering records of signaling events received from the communications network;
sorting the records of the signaling events to generate a time sequence of the records for each key;
determining a trajectory for each key in the time sequence of the records;
calculating a speed of a mobile device from the trajectory, wherein the mobile device is associated with a respective key; and
generating an alert responsive to discovering a location anomaly in the trajectory, wherein the alert is based on the speed exceeding a threshold.
2 . The device of claim 1 , wherein the trajectory is determined from real time difference measurements in each of the signaling events.
3 . The device of claim 2 , wherein a distance between two adjacent points in the trajectory are determined using a haversine formula.
4 . The device of claim 1 , wherein a first number of IMEIs exceeds ten million.
5 . The device of claim 4 , wherein a second number of records of the signaling events exceeds 100 million and wherein the operations are performed in about two hours.
6 . The device of claim 5 , wherein the signaling events comprise a handover event, a tracking area update, a service request, or a combination thereof.
7 . The device of claim 6 , wherein the operations further comprise eliminating false positives from the alert.
8 . The device of claim 7 , wherein eliminating the false positives comprise checking that a first distance between the mobile device and a cell tower identified in the signaling events is below a first threshold.
9 . The device of claim 8 , wherein eliminating the false positives comprise checking that a second distance between two adjacent points in the trajectory is above a second threshold.
10 . The device of claim 9 , wherein the first threshold and the second threshold are determined by machine learning.
11 . The device of claim 10 , wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
12 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
generating a hash table of keys from International Mobile Equipment Identifiers (IMEIs) for mobile devices in a communications network;
filtering records of signaling events received from the communications network;
generating a time sequence of the records associated with each key in the hash table;
determining a trajectory for each key in the time sequence of the records;
calculating a speed of a mobile device associated with a respective key; and
generating an alert responsive to discovering a location anomaly, wherein the alert is based on the speed exceeding a threshold.
13 . The non-transitory machine-readable medium of claim 12 , wherein a first number of IMEIs exceeds ten million.
14 . The non-transitory machine-readable medium of claim 12 , wherein a second number of records of the signaling events exceeds 100 million and wherein the operations are performed in about two hours.
15 . The non-transitory machine-readable medium of claim 12 , wherein the operations further comprise determining points in the trajectory from real time difference measurements in each of the signaling events, wherein a distance between two adjacent points in the trajectory are determined using a haversine formula.
16 . The non-transitory machine-readable medium of claim 12 , wherein the signaling events comprise a handover event, a tracking area update, a service request, or a combination thereof.
17 . The non-transitory machine-readable medium of claim 16 , wherein the operations further comprise eliminating false positives from the alert, wherein eliminating the false positives comprise checking that a first distance between the mobile device and a cell tower identified in the signaling events is below a first threshold and checking that a second distance between two adjacent points in the trajectory is above a second threshold, wherein the first threshold and the second threshold are determined by machine learning.
18 . The non-transitory machine-readable medium of claim 17 , wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
19 . A method, comprising:
hashing, by a processing system including a processor, International Mobile Equipment Identifiers (IMEIs) for mobile devices in records of signaling events in a communications network to generate keys for the records;
generating, by the processing system, a time sequence of the records associated with each key;
determining, by the processing system, a trajectory for a mobile device associated with each key in the time sequence of the records;
calculating, by the processing system, a speed of the mobile device based on the trajectory; and
generating, by the processing system, an alert responsive to discovering a location anomaly in the trajectory, wherein the alert is based on the speed exceeding a threshold.
20 . The method of claim 19 , wherein the signaling events comprise a handover event, a tracking area update, a service request, or a combination thereof.