Sentiment analysis of 95598 work orders based on parallel hybrid neural networks

张 霞; 刘宝龙; 何湘英; 王恭玥; 刘晓捷

doi:10.3969/j.issn.1009-1831.2025.01.015

您当前的位置：

首页 >

文章列表页 >

Sentiment analysis of 95598 work orders based on parallel hybrid neural networks

更新时间：2026-03-05

- Sentiment analysis of 95598 work orders based on parallel hybrid neural networks
- Vol. 27, Issue 1, (2025)
- 作者机构：
  
  1. 国网江苏省电力有限公司常州供电分公司,江苏,常州,213000
  2. 东南大学电气工程学院,南京,210018
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2025.01.015
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
张霞, 刘宝龙, 何湘英, et al. Sentiment analysis of 95598 work orders based on parallel hybrid neural networks[J]. 2025, 27(1).
DOI：

张霞, 刘宝龙, 何湘英, et al. Sentiment analysis of 95598 work orders based on parallel hybrid neural networks[J]. 2025, 27(1). DOI： 10.3969/j.issn.1009-1831.2025.01.015.

摘要

为了解决95598对紧急工单处理不及时导致严重后果的问题

提出了基于注意力机制的并行混合神经网络电力工单文本情感分析模型

以满足紧急工单自动化智能提醒的要求。首先通过情感词典和规则集的方式辅助人工标注工单文本情感紧急程度生成了电力工单文本情感分析数据集；利用文本预训练BERT模型进行文本向量化；然后使用文本卷积神经网络（text convolutionneural network

TextCNN）和双向长短期记忆网络（bidirectional long short term memory

BiLSTM）分别提取文本局部特征和上下文特征并进行特征融合；利用注意力机制对融合后的文本特征中的关键信息进行加强处理

以增强模型识别关键信息的能力。算例结果表明

融合了注意力机制的神经网络模型与其他深度学习模型相比

对电力工单文本情感分类有着更好的效果。

Abstract

In order to solve the problem of serious consequences caused by untimely processing of 95598 emergency work orders

a parallel hybrid neural network sentiment analysis model for power work order texts based on attention mechanism is proposed to meet the requirements of automatic intelligent reminders for emergency work orders. Firstly

a sentiment analysis dataset for electric power work order texts is generated by manually annotating the emotional urgency of work order texts through sentiment dictionaries and rule sets；Using text pre trained BERT model for text vectorization；Then

use text convolutional neural network（TextCNN）and bidirectional long short term memory（BiLSTM）to extract local and contextual features of the text

respectively

and perform feature fusion；Using attention mechanism to enhance the ability of the model to recognize key information in the fused text features. The calculation results show that the neural net?work model that integrates attention mechanism has better performance in sentiment classification of power work order texts compared toother deep learning models.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Load forecasting and adjustable potential analysis of silicon carbide enterprises based on CNN-Attention-BiLSTM

Electrical load forecasting model based on hybrid deep learning

Short-term load probability forecasting based on VaR and integrated neural network quantile regression

综合信息

世界中密度纤维板发展态势

Related Author

任明远

马国瀚

唐聪

曹万雄

孟涛

杨彤

冯崇峰

孟春旅

Related Institution

国网甘肃省电力公司

国网甘肃省电力公司兰州供电公司

海南电网有限责任公司乐东供电局

国网浙江省电力有限公司杭州供电公司

浙大宁波理工学院信息科学与工程学院

AI问答

⁰