电网故障处置预案文本中的命名实体识别研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TM732

基金项目:

国家重点研发计划资助项目(2017YFB0902600);国家电网有限公司科技项目(SGJS0000DKJS1700840)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    电网故障处置预案是电网故障处置的重要参考,对电网故障处置预案文本中各类电力设备、名称编号等细粒度的关键实体信息进行抽取,是实现计算机学习理解预案内容并进一步支撑故障处置智能化的重要基础。文中提出一种基于深度学习的电网故障处置预案文本命名实体识别技术,首先采用字向量表征预案文本,然后将注意力机制以及双向长短期记忆网络相结合,有所侧重地提取实体词深层字符特征,最后采用条件随机场求解最优序列化的标注。算例表明:文中所提预案文本命名实体识别模型不依赖人工特征,能够自动高效地提取文本特征,准确识别预案文本中细粒度的实体词,满足预案文本中关键实体信息精确定位和识别的要求。

    参考文献
    相似文献
    引证文献

Named entity recognition in power fault disposal preplan text
Author:
Affiliation:

Fund Project:

National Key R&D Program of China(2017YFB0902600);State Grid Corporation of China Project (SGJS0000DKJS1700840)

    Abstract:

    Power grid fault disposal preplan is an important reference for power grid fault disposal. Hence,extracting fine-grained key entity information such as power equipments,name and number from the preplan is an important basis for the computer to understand the content and further support the intelligent disposal. A named entity recognition technology for power grid fault disposal preplan is proposed based on deep learning. Firstly,the word vector is used to represent the preplan text. Then the word vector features are extracted by combining the attention mechanism and the bidirectional long short-term memory network. Finally,the optimal serialization annotation is solved by the conditional random field. The example shows that the proposed entity recognition model can automatically and efficiently extract text features,thus accurately identifying entity words in the preplan. It proves that the model meets the requirement of extracting key entity information in the preplan better than another commonly used model dose.

引用本文

江叶峰,孙少华,仇晨光,王波,戴则梅,李杰.电网故障处置预案文本中的命名实体识别研究[J].电力工程技术,2021,40(5):177-183

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-03-05
  • 最后修改日期:2021-05-13
  • 录用日期:2020-12-21
  • 在线发布日期: 2021-09-30
  • 出版日期: 2021-09-28