An electric power defect level identification method based on deep semantic matching

Abstract

The invention discloses an electric power defect level identification method based on deep semantic matching, and relates to the technical field of electric power defect level identification. A traditional text classification model has a vector space model based on Boolean values, the defects that deep context semantics cannot be considered, vectors are sparse, interpretability does not exist andthe like are overcome, and the classification precision is not high for defective texts of power equipment. According to the method, a deep neural network is adopted to divide sentences into five layers of structures including an input layer, a representation layer, a matching layer, a sorting layer and an output layer, and a deep structure semantic model is achieved; then, the text is preprocessed on the input layer based on word hashing and a word segmentation model; on the basis of the deep neural network, an input layer, a representation layer and a matching layer are trained in sequence to obtain a low-dimensional representation vector of the defect text; and finally, obtaining the average defect level of the to-be-classified text based on the semantic similarity of the cosin distanceand the TopK sorting model. The level identification rate of the defect text is effectively improved, and high-precision power defect level identification is realized.

Description

technical field [0001] The invention relates to the technical field of power defect level recognition, in particular to a power defect level recognition method based on deep semantic matching. Background technique [0002] During the daily operation and maintenance of power equipment, it is usually necessary to record the defects of power equipment. The recorded content usually includes the type, name, date of defect discovery, defect description, defect classification, etc., thus forming a large number of power defect texts. Different from other content of the defect record, the defect description is recorded in the form of short text, without a fixed format and structure, but it contains more important defect information, such as the specific part of the device where the defect occurs, the specific phenomenon of the defect, etc., is An important supplement to other defect records, especially for some ambiguous defects, the inspection personnel will record the specific defe...

AI Technical Summary

Problems solved by technology

[0008] 4) The defect description text has a large amount of data, which is conducive to machine learning to mine the hidden laws in the text, but at the same time, it also puts forward certain requirements for the classification efficiency and storage overhead of the classification model

However, the above traditional methods cannot consider deep contextual semantics, sparse vectors, and lack of interpretability, which lead to low classification accuracy or poor generalization ability.

Images