Network equipment intelligent system upgrading method based on deep learning algorithm

The invention discloses a network equipment intelligent system upgrading method based on a deep learning algorithm, and particularly relates to the technical field of system upgrading, split software operation parameters are loaded into a downlink message, then a neural network training model is est...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG XIAO, ZHU JUNZE, WANG WENBO
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a network equipment intelligent system upgrading method based on a deep learning algorithm, and particularly relates to the technical field of system upgrading, split software operation parameters are loaded into a downlink message, then a neural network training model is established, the software operation parameters stored in the message are used as an input layer of a strategy network, and the network equipment intelligent system upgrading method based on the deep learning algorithm is realized. S10, performing neural network model training, generating a neural network training model, performing matching processing on software operation parameters and user operation parameters in real time, taking the firmware target data of the new-version upgrading software obtained in the S10 as an input layer of a new-version strategy network, calculating to obtain a current credible value suitable for upgrading, and updating the new-version strategy network according to the credible value. And