Power field named entity recognition method based on BiLSTM-CRF model

Abstract

The invention relates to an electric power field named entity identification method, in particular to an electric power field named entity identification method based on a BiLSTM-CRF model, and belongs to the technical field of natural language processing. Comprising the following steps: acquiring a power field data set; training a training set in a data set in the power field through a CNN-BiLSTM-Attention-CRF algorithm model, and obtaining an algorithm model trained by the model according to values of related evaluation indexes, namely the accuracy rate, the recall rate and the F1 value; and dividing a data set in the power field into a training set and a test set, performing named entity recognition on the test set by using the algorithm model trained in the step 2, and labeling a test result. The named entity identification of the data in the power field is realized in an efficient, high-accuracy and credible manner.

Description

technical field [0001] The invention relates to a named entity recognition method in the power field, in particular to a named entity recognition method in the power field based on a BiLSTM-CRF model, and belongs to the technical field of natural language processing. Background technique [0002] As a field of electric power production and consumption with complex assets and knowledge-intensive, the electric power field has exploded in the amount of data, making data an increasingly important factor of production, which constitutes the electric power big data that is commonly concerned by the academic and industrial circles today. Most of the current research in the field of electric power usually focuses on structured data, such as: fault cases, equipment defects and elimination cases, which are generally recorded in the form of text by electric power patrol staff, including equipment components and state descriptions , component defect description and other professional in...

AI Technical Summary

Problems solved by technology

[0003] Due to the complexity and particularity of data in the power field, and the related entity information is domain-specific, BiLSTM-CRF alone cannot achieve good results, and the inaccurate results of named entity recognition will make it impossible to carry out follow-up work, such as In the joint extraction of entity relationships, the results of entity recognition will directly affect the results of relationship extraction; the results of named entity recognition will affect the labeling of entities constructed by knowledge graphs; the results of named entity recognition will affect the classification of user questions in question answering systems will have an impact

Images