An Automatic Verification Method of Intelligent Substation Operation Order Based on Chinese Semantic Deep Learning

Verifying the intelligent substation Chinese operation order is an important step to ensure the accuracy of substation operations. The current manual verification method based on experience has strong subjectivity, low efficiency and low reliability. In view of this, this paper proposes an automatic verification method of operation order based on the Chinese semantic deep learning model: Global vectors for word representation-convolution Recurrent Neural Network (Glove-RCNN). By combining the text vectorization model Glove and text mining model RCNN, this method is feasible in realizing the semantic discrimination and automatic verification of correctness and error of the operation order texts. The experimental result shows that the MicroF
score
and MacroF
score
of the operation order verification model is 93.98% and 94.19%, which can accurately judge the correctness of the operation order, so as to effectively improve the verification efficiency.