Systems and methods for automated network state and network inventory tracking
AssigneeDISH Wireless L.L.C.
InventorPaul-André Raymond
Life of this patent
Estimating the term…
Abstract
A network state tracking system tracks the state of a network and recommends an action when the state of the network changes. The network state tracking system detects one or more nodes on the network and generates one or more snapshots of the network. The snapshots are generated by obtaining first and second status data from the nodes and detecting whether a change in the network has occurred based on the status data. The snapshots are generated based on the first and second status data when a change in the network is detected. The snapshots are then used to train a machine learning model to recommend an action to take when a change in the network occurs.
Claims20
A system, comprising:
- at least one processor;
- and
- at least one memory coupled to the at least one processor, the memory having computer-executable instructions stored thereon that, when executed by the at least one processor, cause the system to:
- electronically detect one or more nodes of a network;
- electronically generate one or more snapshots of the network, wherein the one or more snapshots of the network are generated by:
- electronically obtaining first status data for each node of the one or more nodes;
- electronically obtaining second status data for each node of the one or more nodes;
- electronically detecting whether a change in a state of the network has occurred based on at least the first status data and the second status data;
- and
- electronically generating the one or more snapshots of the network based on the first status data and the second status data based on a determination that a change in the network has occurred;
- electronically obtain an indication of a prior state of the network;
- electronically reconstruct the prior state of the network based on the one or more snapshots;
- and
- electronically train a machine learning model to recommend an action to take based on the one or more snapshots of the network and the reconstructed prior state of the network.
A method in a node, the method comprising:
- electronically obtaining, by at least one processor, first status data, the first status data including network state information of the node;
- electronically transmitting, by the at least one processor, the first status data to a network state tracking system;
- electronically obtaining, by the at least one processor, second status data, the second status data including network state information of the node;
- electronically transmitting, by the at least one processor, the second status data to a network state tracking system;
- and
- electronically obtaining, by at the at least one processor, an indication of an action to take, the action being determined based on at least:
- the first status data;
- the second status data;
- and
- a machine learning model trained based on a plurality of network state snapshots, one or more past actions, and a set of rules.
One or more storage devices collectively storing a network state tracking data structure for access and processing by a program executed by at least one computer processor that, when accessed and processed by at least one computer processor, functionally enables the computer processor to:
- obtain one or more network snapshots describing a state of a network at one or more time periods;
- and
- determine an action to take based on the state of the network, the network state tracking data structure comprising:
- information specifying one or more nodes;
- information specifying first status data obtained from the one or more nodes;
- information specifying second status data obtained from the one or more nodes;
- and
- information specifying the one or more network snapshots,
- such that the information specifying first status data and the information specifying the second status data are usable to detect whether a change in the state of the network has occurred,
- such that the information specifying the one or more nodes and the information specifying one or more snapshots are usable to reconstruct a previous state of the network, and
- such that the information specifying one or more network snapshots and the reconstructed previous state of the network is usable to train a machine learning model to determine an action to take when a change in the state of the network is detected.
Dependencies are inferred from the claim text.