Model training method, network congestion prediction method, equipment and medium

The invention discloses a model training method, a network congestion prediction method, equipment and a medium, and relates to the technical field of communication. The method comprises the following steps: acquiring a plurality of sample parameters and a plurality of target parameters of a sample network, wherein the sample network comprises a plurality of sample communication nodes; performing normalization processing on each sample parameter and each target parameter to obtain a sample data matrix corresponding to the sample parameter and a target data matrix corresponding to the target parameter; training a preset neural network model according to the sample data matrix and the target data matrix to obtain a target network model; the target network model is used for analyzing the to-be-tested parameters of the target network and determining the network state of the target network, and the network state comprises a normal communication state or a network congestion state. According to the embodiment of th