Large power texts contain numerous abbreviations of technical terms,alternative names,and irregular ex-pressions.Existing word segmentation tools often fail to identify specialized vocabulary in the electrical engineering field,significantly hindering the analysis and utilization of unstructured texts.To address this challenge,this paper proposes a set of indexing rules tailored to the characteristics of unstructured texts in electrical engineering.Segmen-tation based on these rules can significantly enhance segmentation accuracy,laying a solid foundation for feature ex-traction of power texts.Furthermore,by employing effective long-text segmentation algorithms to preserve the seman-tic information of the original text,the paper integrates and embeds text feature information extracted by the BERT model with vocabulary feature information extracted by Word2Vec.This combined approach enables the extraction of precise features from large unstructured power texts.Finally,experimental results have demonstrated the effec-tiveness of the proposed method for extracting features from large unstructured power texts.
large power textfeature extractionBERTtext segmentationintegrate and embed
国家科技期刊平台
NSTL
万方数据
