Electrical operator attribute speculation method based on convolutional neural network

The invention discloses an electrical operator attribute speculation method based on a convolutional neural network, and the method comprises the steps: collecting the accumulated data information of an electrical operator in a database, and constructing a training data set; performing word segmentation and stop word removal preprocessing operation on the training data set text; randomly initializing a word vector and continuously adjusting and training on the training data set so as to obtain the word vector, and using the word vector as input to be used in the convolutional neural network; using the constructed word vector as input, and using a convolutional neural network (CNN) algorithm to train a classification model; and performing data preprocessing and word vectorization on the information description of the electrical operator, and inputting the information description into the trained convolutional network and the fully connected network to obtain an attribute speculation label of the electrical ope