Power equipment and subject continuous trust evaluation method for optimizing AdaBi-LSTM model based on quantum flower pollination algorithm
The invention discloses a power equipment and subject continuous trust evaluation method for optimizing an AdaBi-LSTM model based on a quantum flower pollination algorithm. The method comprises the following steps: firstly, collecting information such as static information, interaction history, acti...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a power equipment and subject continuous trust evaluation method for optimizing an AdaBi-LSTM model based on a quantum flower pollination algorithm. The method comprises the following steps: firstly, collecting information such as static information, interaction history, action attributes and environment attributes of power equipment and a main body, balancing a data set through an ADASYN method, cleaning and normalizing data, and forming a training set and a test set of a model; then, through a self-adaptive bidirectional long-short-term memory network, transfer learning and the bidirectional long-short-term memory network are organically combined, the model is effectively trained, model parameters are continuously updated by adopting a quantum flower pollination algorithm, and the correlation between historical information and future information of the power equipment and the subject is fully considered; and finally, taking the established model as a prediction model of the behaviors |
---|