Autonomic network recovery of devices using machine learning techniques
Systems and methods for autonomic network recovery of mobile devices are disclosed. The system receives an indication that a service network has not received a packet from a device in a threshold period of time and/or that packets received from the device are not interpretable. Responsive to receiving the indication, the system may obtain (1) device profile information of the mobile device and (2) one or more EDRs and input the obtained information and EDRs into a machine learning model to identify an instruction for reconfiguring the mobile device. The system can then transmit the instruction to a remote device for reconfiguring the mobile device.
1 . A method for autonomic network recovery of mobile devices, comprising:
obtaining, (1) device profiles and enhanced data record (EDR) data associated with each of a plurality of mobile devices in a telecommunications network and (2) for one or more of the plurality of mobile devices, data indicative of a modification to a configuration for a corresponding mobile device responsive to an anomalous event;
training a machine learning model using the device profiles, EDR data, and the data indicative of modifications to the configuration, wherein the machine learning model is trained to produce recommended modifications to a device configuration based on device profiles and EDR data;
receiving an indication that a service network of the telecommunications network:
has not received a packet from a target mobile device in a threshold period of time, or
one or more packets received from the target mobile device are not interpretable by the service network;
responsive to receiving the indication, obtaining (1) device profile information of the target mobile device from a database, wherein the device profile information comprises device model data, software version data, or usage pattern data and (2) one or more EDRs generated by a network comprising data indicative of events and transactions linked to the target mobile device;
processing the device profile information and the one or more EDRs using the machine learning model to generate an instruction for reconfiguring the target mobile device; and
transmitting the instruction to a remote device for reconfiguring the target mobile device.
2 . The method of claim 1 , wherein the remote device comprises the target mobile device and wherein the instruction is a command configured to automatically initiate a software update, adjust network settings, or notify a user to modify one or more device settings of the target mobile device.
3 . The method of claim 1 , further comprising:
after transmitting the instruction to the remote device, determining a new packet received from the target mobile device is interpretable by the service network; and
updating the machine learning model using the device profile information of the target mobile device, the one or more EDRs linked to the target mobile device, and the instruction.
4 . The method of claim 1 , wherein the device profile information comprises:
(a) user specific device information unique to individual devices, or
(b) device type information specifying information regarding a device model, device manufacturer, standard software information, or average usage profiles.
5 . The method of claim 1 , wherein the instruction to a remote device comprises a notification to a device manufacturer of the target mobile device.
6 . The method of claim 1 , wherein the instruction is an instruction to adjust parameters of a telecommunications network node comprising one or more of an antenna tilt or orientation adjustment, power output adjustment, or hardware addition to increase capacity.
7 . The method of claim 1 , wherein the indication that packets received by the service network are not interpretable is based on a determination that one or more packets do not adhere to a predetermined message format protocol.
8 . The method of claim 1 , further comprising responsive to an indication that a confidence level for the instruction for reconfiguring the target mobile device does not meet or exceed a predetermined threshold, transmitting a notification to an operator at a remote device.
9 . A non-transitory computer-readable medium containing instructions configured to cause one or more processors to perform a method for autonomic network recovery of mobile device, the method comprising:
receiving an indication that a service network of a telecommunications network:
has not received a packet from a target mobile device in a threshold period of time, or
one or more packets received from the target mobile device are not interpretable by the service network;
responsive to receiving the indication, obtaining (1) device profile information of the target mobile device from a database, wherein the device profile information comprises device model data, software version data, or usage pattern data and (2) one or more EDRs generated by a network comprising data indicative of events and transactions linked to the target mobile device;
processing the device profile information and the one or more EDRs using a machine learning model to generate an instruction for reconfiguring the target mobile device; and
transmitting the instruction to a remote device for reconfiguring the target mobile device.
10 . The non-transitory computer-readable medium of claim 9 , wherein the instructions further cause operations including:
obtaining, (1) device profiles and enhanced data record (EDR) data associated with each of a plurality of mobile devices in the telecommunications network and (2) for one or more of the plurality of mobile devices, data indicative of a modification to a configuration for a corresponding mobile device responsive to an anomalous event; and
training the machine learning model using the device profiles, EDR data, and the data indicative of modifications to the configuration, wherein the machine learning model is trained to produce recommended modifications to a device configuration based on device profiles and EDR data.
11 . The non-transitory computer-readable medium of claim 9 , wherein the remote device comprises the mobile device and wherein the instruction is a command configured to automatically initiate a software update, adjust network settings, and/or notify a user to modify one or more device settings of the mobile device.
12 . The non-transitory computer-readable medium of claim 9 , wherein the instructions further cause operations including:
receiving a new packet from the mobile device, wherein the new packet is interpretable by the service network; and
updating the machine learning model using the device profile information, the one or more EDRs, and the instruction.
13 . The non-transitory computer-readable medium of claim 9 , wherein the device profile information comprises (a) user specific device information unique to individual devices and/or (b) device type information specifying information regarding a device model, device manufacturer, standard software information, and/or average usage profiles.
14 . The non-transitory computer-readable medium of claim 9 , wherein the indication that packets received by the service network are not interpretable is based on a determination that one or more packets do not adhere to a predetermined message format protocol.
15 . The non-transitory computer-readable medium of claim 9 , wherein the instruction to a remote device comprises a notification to a device manufacturer of the mobile device.
16 . A system for autonomic network recovery of mobile devices, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable media comprising instructions that, when executed by the one or more processors, causes operations comprising:
receiving an indication that a service network of a telecommunications network:
has not received a packet from a target mobile device in a threshold period of time, or
one or more packets received from the target mobile device are not interpretable by the service network;
responsive to receiving the indication, obtaining (1) device profile information of the target mobile device from a database, wherein the device profile information comprises device model data, software version data, or usage pattern data and (2) one or more EDRs generated by a network comprising data indicative of events and transactions linked to the target mobile device;
processing the device profile information and the one or more EDRs using a machine learning model to generate an instruction for reconfiguring the target mobile device; and
transmitting the instruction to a remote device for reconfiguring the target mobile device.
17 . The system of claim 16 , wherein the instructions further cause operations including:
obtaining, (1) device profiles and enhanced data record (EDR) data associated with each of a plurality of mobile devices in the telecommunications network and (2) for one or more of the plurality of mobile devices, data indicative of a modification to a configuration for a corresponding mobile device responsive to an anomalous event; and
training the machine learning model using the device profiles, EDR data, and the data indicative of modifications to the configuration, wherein the machine learning model is trained to produce recommended modifications to a device configuration based on device profiles and EDR data.
18 . The system of claim 16 , wherein the remote device comprises the target mobile device and wherein the instruction is a command configured to automatically initiate a software update, adjust network settings, and/or notify a user to modify one or more device settings of the mobile device.
19 . The system of claim 16 , wherein the instructions further cause operations including:
receiving a new packet from the target mobile device, wherein the new packet is interpretable by the service network; and
updating the machine learning model using the device profile information, the one or more EDRs, and the instruction.
20 . The system of claim 16 , wherein the device profile information comprises (a) user specific device information unique to individual devices and/or (b) device type information specifying information regarding a device model, device manufacturer, standard software information, and/or average usage profiles.