Network data processing driver for a cognitive artificial intelligence system
AssigneeIntellective Ai, Inc.
InventorsTao Yang, Ming-Jung Seow
Life of this patent
Estimating the term…
Abstract
Techniques are disclosed for processing data collected from network components for analysis by a machine learning engine of a Cognitive AI System. A network data processing driver receives a stream of data from a data collector which obtains data from one or more network data sources. The driver normalizes the stream of data to one or more feature values each corresponding to the network data sources and generates a sample vector from the feature values. The sample vector is formatted to be analyzed by the machine learning engine.
Claims20
A method, comprising:
- receiving a first stream of data at a network data processing driver, and via a network, from at least one of a system log, a network device, a monitor system, and a simple network management protocol (SNMP) agent;
- identifying a packet header from the first stream of data and extracting address information from the packet header;
- separating the extracted address information into multiple address information components and converting the separated address information components into feature values, the feature values associated with the at least one of the system log, the network device, the monitor system, and the SNMP agent;
- normalizing the feature values;
- generating, via a neuro-linguistic model, patterns associated with the normalized feature values and related to network traffic attributes of the network;
- generating statistics from the patterns;
- generating a logical network topology based on the generated statistics;
- generating a context-aware description of activity of the network based at least in part on a mapping of the normalized feature values in the logical network topology to corresponding network components;
- and
- sending an alert signal representing an anomaly, via a cloud computing infrastructure, in response to detecting the anomaly in the activity of the network based on the patterns.
A non-transitory processor-readable medium storing instructions to cause a processor to:
- receive a first stream of data at a network data processing driver and via a network from at least one of a system log, a network device, a monitor system, and a simple network management protocol (SNMP) agent;
- identify a packet header from the first stream of data and extracting address information from the packet header;
- separate the extracted address information into multiple address information components and converting the separated address information components to feature values, the feature values associated with the at least one of the system log, the network device, the monitor system, and the SNMP agent;
- normalize the feature values;
- generate, via a neuro-linguistic model, patterns associated with the normalized feature values and related to network traffic attributes of the network;
- generate statistics from the patterns;
- generate a logical network topology based on the generated statistics;
- generate a context-aware description of activity of the network based at least in part on a mapping of the normalized feature values in the logical network topology to corresponding network components;
- and
- send an alert signal representing an anomaly, via a cloud computing infrastructure, in response to detecting the anomaly in the activity of the network based on the patterns.
Dependencies are inferred from the claim text.