Design of Question Answering System in Substation Fault Field Based on Knowledge Graph

He Jun; Wu Sheng Ke; Rao Fang Xi; Zhong Ke Jia; Liu Peng Zheng; Sun Jian Ming

doi:doi:10.11648/j.sd.20221005.23

| Peer-Reviewed

Design of Question Answering System in Substation Fault Field Based on Knowledge Graph

He Jun, Wu Sheng Ke, Rao Fang Xi, Zhong Ke Jia, Liu Peng Zheng, Sun Jian Ming

Published in Science Discovery (Volume 10, Issue 5)

Received: 26 September 2022 Accepted: 27 October 2022 Published: 29 October 2022

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

The operation and maintenance of substation equipment is of great significance to ensure the safety and stability of the power grid. In order to summarize the historical operation and maintenance experience of substation equipment and facilitate the management personnel to uniformly manage and accurately query the historical data of substation faults, this paper constructs an intelligent question and answer system for substation faults based on the knowledge map. At present, the research on knowledge atlas in power field mainly focuses on the construction and visualization of knowledge atlas. This paper combines natural language processing, deep learning, knowledge atlas, graph database and other knowledge with power. Firstly, the substation fault data is cleaned and extracted, and the substation fault knowledge map is constructed; Secondly, based on Bert+TextCNN algorithm, the intention recognition function of questions is realized; Thirdly, based on BILSTM-CRF algorithm, the named entity recognition function of questions is realized. Finally, combined with Flask deployment model, the API interface is released, and the substation fault question answering system is built through the establishment of WeChat automatic question answering robot. The experimental results show that the accuracy of the system reaches 96%. Finally, a complete question answering system for substation fault is formed, and accurate, fast and intelligent knowledge question answering service is realized.

Published in	Science Discovery (Volume 10, Issue 5)
DOI	10.11648/j.sd.20221005.23
Page(s)	366-373
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Knowledge Graph, Substation Faults, Named Entity Recognition, Question Answering System

References

[1]	刘欢, 刘浏, 王东波. 数字人文视角下的领域知识图谱自动问答研究 [J]. 科技情报研究, 2022, 4 (01): 46-59.
[2]	郑泳智, 吴惠粦, 朱定局, 陈炳旭, 李文景. 基于荔枝和龙眼病虫害知识图谱的问答系统 [J]. 计算机与数字工程, 2021, 49 (12): 2618-2622.
[3]	陈一龙, 卜嘉彬, 李景宇, 李东泽, 龚力, 万智. 基于知识图谱的罕见病就医决策引擎设计研究 [J]. 华西医学, 2021, 36 (12): 1730-1733.
[4]	杨迪, 梁懿, 王秋琳, 陈新梅, 陈恩光, 王燕蓉. 一种知识图谱的电力设备缺陷检索方案设计与实现 [J]. 微型电脑应用, 2022, 38 (01): 191-194.
[5]	蒲天骄, 谈元鹏, 彭国政, 徐会芳, 张中浩. 电力领域知识图谱的构建与应用 [J]. 电网技术, 2021, 45 (06).
[6]	李刚, 李银强, 王洪涛, 谢庆, 黄文琦, 侯佳萱. 电力设备健康管理知识图谱：基本概念、关键技术及研究进展 [J]. 电力系统自动化, 2022, 46 (03): 1-13.
[7]	郑泳智, 吴惠粦, 朱定局, 等. 基于荔枝和龙眼病虫害知识图谱的问答系统 [J]. 计算机与数字工程, 2021 (049-012).
[8]	陈旻杰, 魏轩, 郑莹, 周世元. 基于BERT的智能问答系统 [J]. 数字技术与应用, 2022, 40 (01): 161-163.
[9]	邵辉. 基于BERT-TextCNN的中文短文本情感分析 [J]. 信息与电脑 (理论版), 2022, 34 (01): 77-80.
[10]	杨飞洪, 王序文, 李姣. 基于BERT-TextCNN模型的临床试验筛选短文本分类方法 [J]. 中华医学图书情报杂志, 2021, 30 (01): 54-59.
[11]	曾勇. 基于BiLSTM-CRF模型的中文命名实体识别研究与实现 [D]. 江西财经大学, 2020.
[12]	张耀允. 基于用户意图分析的交互式问答技术研究 [D]. 哈尔滨工业大学, 2012.

Cite This Article

Plain Text BibTeX RIS

APA Style

He Jun, Wu Sheng Ke, Rao Fang Xi, Zhong Ke Jia, Liu Peng Zheng, et al. (2022). Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Science Discovery, 10(5), 366-373. https://doi.org/10.11648/j.sd.20221005.23

Copy | Download

ACS Style

He Jun; Wu Sheng Ke; Rao Fang Xi; Zhong Ke Jia; Liu Peng Zheng, et al. Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Sci. Discov. 2022, 10(5), 366-373. doi: 10.11648/j.sd.20221005.23

Copy | Download

AMA Style

He Jun, Wu Sheng Ke, Rao Fang Xi, Zhong Ke Jia, Liu Peng Zheng, et al. Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Sci Discov. 2022;10(5):366-373. doi: 10.11648/j.sd.20221005.23

Copy | Download

@article{10.11648/j.sd.20221005.23,
  author = {He Jun and Wu Sheng Ke and Rao Fang Xi and Zhong Ke Jia and Liu Peng Zheng and Sun Jian Ming},
  title = {Design of Question Answering System in Substation Fault Field Based on Knowledge Graph},
  journal = {Science Discovery},
  volume = {10},
  number = {5},
  pages = {366-373},
  doi = {10.11648/j.sd.20221005.23},
  url = {https://doi.org/10.11648/j.sd.20221005.23},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221005.23},
  abstract = {The operation and maintenance of substation equipment is of great significance to ensure the safety and stability of the power grid. In order to summarize the historical operation and maintenance experience of substation equipment and facilitate the management personnel to uniformly manage and accurately query the historical data of substation faults, this paper constructs an intelligent question and answer system for substation faults based on the knowledge map. At present, the research on knowledge atlas in power field mainly focuses on the construction and visualization of knowledge atlas. This paper combines natural language processing, deep learning, knowledge atlas, graph database and other knowledge with power. Firstly, the substation fault data is cleaned and extracted, and the substation fault knowledge map is constructed; Secondly, based on Bert+TextCNN algorithm, the intention recognition function of questions is realized; Thirdly, based on BILSTM-CRF algorithm, the named entity recognition function of questions is realized. Finally, combined with Flask deployment model, the API interface is released, and the substation fault question answering system is built through the establishment of WeChat automatic question answering robot. The experimental results show that the accuracy of the system reaches 96%. Finally, a complete question answering system for substation fault is formed, and accurate, fast and intelligent knowledge question answering service is realized.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Design of Question Answering System in Substation Fault Field Based on Knowledge Graph
AU  - He Jun
AU  - Wu Sheng Ke
AU  - Rao Fang Xi
AU  - Zhong Ke Jia
AU  - Liu Peng Zheng
AU  - Sun Jian Ming
Y1  - 2022/10/29
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221005.23
DO  - 10.11648/j.sd.20221005.23
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 366
EP  - 373
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221005.23
AB  - The operation and maintenance of substation equipment is of great significance to ensure the safety and stability of the power grid. In order to summarize the historical operation and maintenance experience of substation equipment and facilitate the management personnel to uniformly manage and accurately query the historical data of substation faults, this paper constructs an intelligent question and answer system for substation faults based on the knowledge map. At present, the research on knowledge atlas in power field mainly focuses on the construction and visualization of knowledge atlas. This paper combines natural language processing, deep learning, knowledge atlas, graph database and other knowledge with power. Firstly, the substation fault data is cleaned and extracted, and the substation fault knowledge map is constructed; Secondly, based on Bert+TextCNN algorithm, the intention recognition function of questions is realized; Thirdly, based on BILSTM-CRF algorithm, the named entity recognition function of questions is realized. Finally, combined with Flask deployment model, the API interface is released, and the substation fault question answering system is built through the establishment of WeChat automatic question answering robot. The experimental results show that the accuracy of the system reaches 96%. Finally, a complete question answering system for substation fault is formed, and accurate, fast and intelligent knowledge question answering service is realized.
VL  - 10
IS  - 5
ER  -

Copy | Download

Author Information

He Jun

College of Information and Engineering, Nanchang University, Nanchang, China
Wu Sheng Ke

College of Information and Engineering, Nanchang University, Nanchang, China
Rao Fang Xi

College of Information and Engineering, Nanchang University, Nanchang, China
Zhong Ke Jia

College of Information and Engineering, Nanchang University, Nanchang, China
Liu Peng Zheng

College of Information and Engineering, Nanchang University, Nanchang, China
Sun Jian Ming

College of Information and Engineering, Nanchang University, Nanchang, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

He Jun, Wu Sheng Ke, Rao Fang Xi, Zhong Ke Jia, Liu Peng Zheng, et al. (2022). Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Science Discovery, 10(5), 366-373. https://doi.org/10.11648/j.sd.20221005.23

Copy | Download

ACS Style

He Jun; Wu Sheng Ke; Rao Fang Xi; Zhong Ke Jia; Liu Peng Zheng, et al. Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Sci. Discov. 2022, 10(5), 366-373. doi: 10.11648/j.sd.20221005.23

Copy | Download

AMA Style

He Jun, Wu Sheng Ke, Rao Fang Xi, Zhong Ke Jia, Liu Peng Zheng, et al. Design of Question Answering System in Substation Fault Field Based on Knowledge Graph. Sci Discov. 2022;10(5):366-373. doi: 10.11648/j.sd.20221005.23

Copy | Download

@article{10.11648/j.sd.20221005.23,
  author = {He Jun and Wu Sheng Ke and Rao Fang Xi and Zhong Ke Jia and Liu Peng Zheng and Sun Jian Ming},
  title = {Design of Question Answering System in Substation Fault Field Based on Knowledge Graph},
  journal = {Science Discovery},
  volume = {10},
  number = {5},
  pages = {366-373},
  doi = {10.11648/j.sd.20221005.23},
  url = {https://doi.org/10.11648/j.sd.20221005.23},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221005.23},
  abstract = {The operation and maintenance of substation equipment is of great significance to ensure the safety and stability of the power grid. In order to summarize the historical operation and maintenance experience of substation equipment and facilitate the management personnel to uniformly manage and accurately query the historical data of substation faults, this paper constructs an intelligent question and answer system for substation faults based on the knowledge map. At present, the research on knowledge atlas in power field mainly focuses on the construction and visualization of knowledge atlas. This paper combines natural language processing, deep learning, knowledge atlas, graph database and other knowledge with power. Firstly, the substation fault data is cleaned and extracted, and the substation fault knowledge map is constructed; Secondly, based on Bert+TextCNN algorithm, the intention recognition function of questions is realized; Thirdly, based on BILSTM-CRF algorithm, the named entity recognition function of questions is realized. Finally, combined with Flask deployment model, the API interface is released, and the substation fault question answering system is built through the establishment of WeChat automatic question answering robot. The experimental results show that the accuracy of the system reaches 96%. Finally, a complete question answering system for substation fault is formed, and accurate, fast and intelligent knowledge question answering service is realized.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Design of Question Answering System in Substation Fault Field Based on Knowledge Graph
AU  - He Jun
AU  - Wu Sheng Ke
AU  - Rao Fang Xi
AU  - Zhong Ke Jia
AU  - Liu Peng Zheng
AU  - Sun Jian Ming
Y1  - 2022/10/29
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221005.23
DO  - 10.11648/j.sd.20221005.23
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 366
EP  - 373
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221005.23
AB  - The operation and maintenance of substation equipment is of great significance to ensure the safety and stability of the power grid. In order to summarize the historical operation and maintenance experience of substation equipment and facilitate the management personnel to uniformly manage and accurately query the historical data of substation faults, this paper constructs an intelligent question and answer system for substation faults based on the knowledge map. At present, the research on knowledge atlas in power field mainly focuses on the construction and visualization of knowledge atlas. This paper combines natural language processing, deep learning, knowledge atlas, graph database and other knowledge with power. Firstly, the substation fault data is cleaned and extracted, and the substation fault knowledge map is constructed; Secondly, based on Bert+TextCNN algorithm, the intention recognition function of questions is realized; Thirdly, based on BILSTM-CRF algorithm, the named entity recognition function of questions is realized. Finally, combined with Flask deployment model, the API interface is released, and the substation fault question answering system is built through the establishment of WeChat automatic question answering robot. The experimental results show that the accuracy of the system reaches 96%. Finally, a complete question answering system for substation fault is formed, and accurate, fast and intelligent knowledge question answering service is realized.
VL  - 10
IS  - 5
ER  -

Copy | Download