Back to results
US 12,764,033 B2Granted
Systems and methods of flow size classification using machine learning
AssigneeMellanox Technologies, Ltd.
InventorsGil Levy, Ran Sandhaus, Shie Mannor
Life of this patent
Estimating the term…
Abstract
A network device, system-on-a-chip, and method of performing packet handling are described. A packet is received, and data associated with the packet is processed, using a configurable artificial intelligence engine, to generate a size classification for a flow associated with the packet. An action is performed based, at least in part, on the size classification for the flow associated with the packet.
Claims20
A network device comprising:
- a configurable artificial intelligence engine;
- and
- one or more circuits to:
- receive a packet;
- process, using the configurable artificial intelligence engine, data associated with the packet to determine, from among at least three possible size classifications, a size classification for a flow associated with the packet;
- and
- perform an action based, at least in part, on the size classification for the flow associated with the packet.
4 more elements
A system, comprising:
- one or more circuits to:
- determine model parameters for a flow size classification model, wherein the flow size classification model classifies individual flows into one of at least three possible flow size classes;
- deploy the flow size classification model using the determined model parameters;
- and
- process data associated with packets to determine a flow size class, from among the at least three possible flow size classes, for each packet.
2 more elements
A method for generating a flow size classification model using machine learning, the method comprising:
- generating a training data set;
- classifying the generated training data set into a classified training data set comprising at least three possible flow size classes;
- training the flow size classification model based on the classified training data set;
- determining model parameters for the flow size classification model;
- deploying the flow size classification model using the determined model parameters;
- receiving a packet associated with a flow;
- and
- processing data associated with the packet to determine a flow size class, from among the at least three possible flow size classes, for the packet.
5 more elements
Dependencies are inferred from the claim text.