Automated discovery of network inventory from raw configuration files using machine learning

A non-transitory computer readable medium comprising instructions stored in a memory and executed by a processor of a network inventory discovery engine to carry out an automated network inventory discovery method, comprising:

• coupling a network configuration management/task automation tool to a device of a network element (NE) of a network to provide an interface for receiving unstructured network configuration data associated with the NE from the NE;
• at a network inventory discovery engine coupled to a network data source, receiving the unstructured network configuration data through a distributed network event streaming platform and a distributed configuration/inventory management hub responsive to a device of the NE being initiated or modified, wherein the network configuration management/task automation tool publishes network configuration changes or updates to topics of the distributed network event streaming platform;
• using a trained machine learning (ML) model of the network inventory discovery engine, parsing named entity attributes from text of the unstructured network configuration data without a parser script and mapping the named entity attributes to a common information model having a predetermined data structure, wherein the named entity attributes comprise at least device identifier information associated with the device of the NE;
• and
• one or more of automating, managing, controlling, or analyzing the network comprising the NE and the device of the NE that is initiated or modified using the common information model via a network configuration management system displaying an output on a graphical user interface that incorporates data in the common information model.