Tracking in-service IP phones using machine learning
A method of determining whether an end user device coupled to a voice over Internet Protocol (VOIP) network is online or offline assembling source data from a variety of network monitoring devices and services including at least one selected from the group consisting of: of asset inventories, VoIP Call Control Servers, routers, firewalls, and intrusion protection systems (IPSs) concerning an online and offline status of a plurality of end user device in the network. The method also comprises training a machine learning algorithm using the source data to determine whether the end user devices coupled to the VoIP network are online or offline, and after training, executing the machine learning algorithm to determine whether a specific end user device currently coupled to the VoIP network is online or offline.
1 . A method of determining whether an end user device coupled to a voice over Internet Protocol (VOIP) network is online or offline, comprising:
assembling source data from a variety of network monitoring devices and services including at least one selected from the group consisting of: of asset inventories, VOIP Call Control Servers, routers, firewalls, and intrusion protection systems (IPSs) concerning an online and offline status of a plurality of end user device in the network;
training a machine learning algorithm using the source data to determine whether the end user devices coupled to the VoIP network are online or offline; and
after training, executing the machine learning algorithm to determine whether a specific end user device currently coupled to the VoIP network is online or offline.
2 . The method of claim 1 , further comprising vectorizing the assembled source data into a format suited for input to the machine learning algorithm.
3 . The method of claim 1 , wherein the source data is assembled from all of the group consisting of: asset inventories, VOIP Call Control Servers, routers, firewalls, and intrusion protection systems (IPSs).
4 . The method of claim 1 , wherein the source data includes an IP address, a MAC address, a phone number, a network status and a hardware model of the end user device.
5 . The method of claim 4 , wherein the source data further includes a Session Initiation Protocol (SIP) registration state and SIP registration time, as well as a local area network (LAN) hostname and LAN switch port.
6 . A method of diagnosing a potential outage in a voice over Internet Protocol (VOIP) network, comprising:
assembling source data from a variety of network monitoring devices and services including at least one selected from the group consisting of: of asset inventories, VOIP Call Control Servers, routers, firewalls, and intrusion protection systems (IPSs) concerning an online and offline status of a plurality of end user devices in the network;
training a first machine learning algorithm using the source data to determine whether the end user devices coupled to the VoIP network are online or offline;
training a second machine learning algorithm using the source data to diagnose outages in the VoIP network based on patterns of online or offline end user devices in the VoIP network;
monitoring a plurality of end user device currently coupled to the VoIP network;
detecting a potential outage among the end user devices in the VoIP network;
executing the first trained machine learning algorithm to determine whether end user devices perceived to be offline are likely actually offline due to an outage; and
executing the second machine learning algorithm to determine diagnostic features of the outage, when end users devices are determined to be actually offline, including whether the outage is confined to one or more of a specific location, a building, a geographic area, or a subnet.
7 . The method of claim 6 , wherein diagnostic features of the outage include information regarding whether the outage is confined to one or more of the specific location, the building, the geographic area, or the subnet.
8 . The method of claim 7 , wherein diagnostic features of the outage further include a determination of the location in the VoIP network that is a source of power-failure issue or malfunction.
9 . The method of claim 6 , further comprising vectorizing the assembled source data into a format suited for input to the first and second machine learning algorithms.
10 . The method of claim 6 , wherein the source data is assembled from all of the group consisting of: asset inventories, VOIP Call Control Servers, routers, firewalls, and intrusion protection systems (IPSs).
11 . The method of claim 6 , wherein the source data includes an IP address, a MAC address, a phone number, a network status and a hardware model of the end user device.
12 . The method of claim 11 , wherein the source data further includes a Session Initiation Protocol (SIP) registration state and SIP registration time, as well as a local area network (LAN) hostname and LAN switch port.