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, 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