工业生产设备故障领域问答系统的意图识别
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP391.1

基金项目:

科技创新 2030-“新一代人工智能”重大项目(2020AAA0109300)


Research on Intent Detection of Question Answering System in the Field of Industrial Production Equipment Failure
Author:
Affiliation:

Fund Project:

  • 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:

    为了解决工业生产设备故障领域的问答系统缺乏标注数据、意图识别槽位填充性能不足的问题,提出了一种基于BERT的联合模型。利用BERT进行文本序列编码,并通过双向长短时记忆网络(Bi-LSTM)捕捉文本上下文语义关系。通过最大池化和致密层提取关键信息,同时使用条件随机场(CRF)增强模型泛化能力。构建了工业领域设备故障问答语料库,并提出了针对该领域的模型部署框架。在ATIS等公共数据集上进行实验,相对于基线模型,本文模型在句子级准确率、F1值和意图识别准确率上,分别提高4.4、2.1和0.5个百分点。本研究有效提升了问答系统性能,为缺乏工业生产数据的问答系统领域提供了数据集和部署框架。

    Abstract:

    To address the lack of annotated data and insufficient performance in intent detection and slot filling in the domain of industrial equipment failure, a joint model based on BERT is proposed. BERT is utilized for text sequence encoding, while a Bidirectional Long Short-Term Memory (Bi-LSTM) network is employed to capture the semantic relationships within the context. Max pooling and dense layers are used to extract key information, and a Conditional Random Field (CRF) is incorporated to enhance the model's generalization capability. A question-and-answer corpus specifically tailored to the industrial domain of equipment failure was constructed, and a deployment framework for this domain is proposed. Experimental evaluations conducted on public datasets such as ATIS demonstrated that the proposed model outperforms baseline models by improving sentence-level accuracy, F1 score, and intent detection accuracy by 4.4%, 2.1%, and 0.5% respectively. This research effectively enhances the performance of question-and-answer systems and provides a dataset and deployment framework for the field of industrial equipment failure, which lacks sufficient real-world data.

    参考文献
    相似文献
    引证文献
引用本文

王雨萱,万卫兵,程锋. 工业生产设备故障领域问答系统的意图识别[J]. 科学技术与工程, 2024, 24(18): 7746-7759.
Wang Yuxuan, Wan Weibing, Cheng Feng. Research on Intent Detection of Question Answering System in the Field of Industrial Production Equipment Failure[J]. Science Technology and Engineering,2024,24(18):7746-7759.

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:2023-07-16
  • 最后修改日期:2024-04-18
  • 录用日期:2023-10-24
  • 在线发布日期: 2024-07-05
  • 出版日期: