融合文本与知识图谱的蛋鸡疫病智能诊断模型

TP391%S24; 针对利用单一文本描述进行蛋鸡疫病诊断存在关联信息分析不够全面、未能提供完整蛋鸡疫病知识,进而导致在复杂蛋鸡疫病诊断中存在准确率不高等问题,该研究提出一种采用基于转换器的双向编码预训练模型(bidirectional encoder representation from transformers,BERT)融合蛋鸡典型疫病知识图谱和文本的方法,结合双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络构建了 BERT-LHDKG(BERT-laying hens disease knowledge graph)诊断...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 40; no. 17; pp. 265 - 272
Main Authors 王书君, 童勤, 刘羽, 李奇峰, 王朝元, 高荣华, 余礼根, 李海燕
Format Journal Article
LanguageChinese
Published 北京市农林科学院信息技术研究中心,北京 100097 01.09.2024
国家数字畜牧业创新中心,北京 100097%中国农业大学水利与土木工程学院,北京 100083%北京市农林科学院信息技术研究中心,北京 100097
中国农业大学水利与土木工程学院,北京 100083
国家数字畜牧业创新中心,北京 100097
Subjects
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.202405021

Cover

Abstract TP391%S24; 针对利用单一文本描述进行蛋鸡疫病诊断存在关联信息分析不够全面、未能提供完整蛋鸡疫病知识,进而导致在复杂蛋鸡疫病诊断中存在准确率不高等问题,该研究提出一种采用基于转换器的双向编码预训练模型(bidirectional encoder representation from transformers,BERT)融合蛋鸡典型疫病知识图谱和文本的方法,结合双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络构建了 BERT-LHDKG(BERT-laying hens disease knowledge graph)诊断模型,实现对滑液囊支原体、新城疫、传染性鼻炎等38种蛋鸡典型疫病的智能诊断.模型通过引入表示知识图谱的三元组向量,使模型更全面地结合疫病文本和知识图谱数据对蛋鸡发病情况进行综合分析;通过增加BERT模型的Embedding结构,将文本特征向量与三元组向量在BERT模型内部相加形成融合向量,有助于模型提取更有用的特征进行疫病分析和诊断.性能对比试验结果显示,BERT-LHDKG诊断模型的宏准确率为94.27%,宏召回率为94.12%,宏 F1 为 94.01%,与 TextCNN、结合 CNN(convolutional neural networks)的 BERT 模型、结合 BiLSTM 的 ERNIE 模型等深度学习模型相比,宏准确率分别提升了 10.02、2.64、2.18个百分点,宏召回率分别提升了 10.28、2.29、2.29个百分点,宏F1分别提升了 10.66、2.51、2.19个百分点.对于蛋鸡养殖过程中容易发生的病毒性疫病、细菌性疫病、中毒性疫病和代谢性疫病,BERT-LHDKG诊断模型的宏Fl分别为96.43%、95.57%、96.72%、98.24%,性能均优于其他对比模型.研究结果表明融入知识图谱可以使模型将疫病文本中的实体、关系链接到知识图谱中对应的实体,丰富文本的语义信息,提升模型全面理解文本内容的能力,进而提高模型进行疫病诊断的准确性和鲁棒性,为畜禽疫病智能诊断提供了新的思路;此外,基于BERT-LHDKG诊断模型开发的蛋鸡疫病诊断Web系统以人机对话的形式提高了养殖户远程诊断蛋鸡疫病的灵活性.
AbstractList TP391%S24; 针对利用单一文本描述进行蛋鸡疫病诊断存在关联信息分析不够全面、未能提供完整蛋鸡疫病知识,进而导致在复杂蛋鸡疫病诊断中存在准确率不高等问题,该研究提出一种采用基于转换器的双向编码预训练模型(bidirectional encoder representation from transformers,BERT)融合蛋鸡典型疫病知识图谱和文本的方法,结合双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络构建了 BERT-LHDKG(BERT-laying hens disease knowledge graph)诊断模型,实现对滑液囊支原体、新城疫、传染性鼻炎等38种蛋鸡典型疫病的智能诊断.模型通过引入表示知识图谱的三元组向量,使模型更全面地结合疫病文本和知识图谱数据对蛋鸡发病情况进行综合分析;通过增加BERT模型的Embedding结构,将文本特征向量与三元组向量在BERT模型内部相加形成融合向量,有助于模型提取更有用的特征进行疫病分析和诊断.性能对比试验结果显示,BERT-LHDKG诊断模型的宏准确率为94.27%,宏召回率为94.12%,宏 F1 为 94.01%,与 TextCNN、结合 CNN(convolutional neural networks)的 BERT 模型、结合 BiLSTM 的 ERNIE 模型等深度学习模型相比,宏准确率分别提升了 10.02、2.64、2.18个百分点,宏召回率分别提升了 10.28、2.29、2.29个百分点,宏F1分别提升了 10.66、2.51、2.19个百分点.对于蛋鸡养殖过程中容易发生的病毒性疫病、细菌性疫病、中毒性疫病和代谢性疫病,BERT-LHDKG诊断模型的宏Fl分别为96.43%、95.57%、96.72%、98.24%,性能均优于其他对比模型.研究结果表明融入知识图谱可以使模型将疫病文本中的实体、关系链接到知识图谱中对应的实体,丰富文本的语义信息,提升模型全面理解文本内容的能力,进而提高模型进行疫病诊断的准确性和鲁棒性,为畜禽疫病智能诊断提供了新的思路;此外,基于BERT-LHDKG诊断模型开发的蛋鸡疫病诊断Web系统以人机对话的形式提高了养殖户远程诊断蛋鸡疫病的灵活性.
Abstract_FL Frequent occurrence of diseases has posed a serious threat to the healthy development of the laying hens industry.Previous studies have focused mainly on the application of artificial intelligence technologies to the intelligent diagnosis of laying hens diseases at present.However,the low accuracy with single data or knowledge cannot fully meet the diagnosis of complex laying hens diseases,particularly for the small number of diagnosable diseases.Graph structure and knowledge graphs can be expected to easily acquire a large amount of data.Furthermore,diagnosing diseases has been limited in the incomplete analysis of correlation information and incomplete knowledge of laying hens using a single text description.This study aims to propose a Bidirectional Encoder Representation from Transformers(BERT)that integrates the knowledge graph and text of typical laying hens diseases using a Transformer based Bidirectional Long Short Term Memory Network(BiLSTM),in order to construct BERT-LHDKG(BERT Laying Hens Disease Knowledge).The diagnostic model was used for intelligent diagnosis of 38 typical diseases in the laying hens,such as Mycoplasma Synoviae,Newcastle Disease,and Infectious Rhinitis.The disease text and knowledge graph data were more comprehensively combined to conduct a comprehensive analysis of the incidence of laying hens.The triple vectors were introduced to represent the knowledge graph.The text feature vector and the triple vector were added inside the BERT model to form a fusion vector.More useful features were extracted for the disease analysis and diagnosis.The performance comparison test showed that the macroprecision of the BERT-LHDKG diagnostic model was 94.27%,the macrorecall was 94.12%,and the macro-Fl was 94.01%.The macroprecision was improved by 10.02,2.64,2.18 percentage points,the macrorecall was improved by 10.28,2.29,2.29 percentage points,and macro-Fl was improved by 10.66,2.51,2.19 percentage points,respectively,compared with deep learning models,such as TextCNN,the BERT model combined with CNN(convolutional neural networks),and the ERNIE model combined with BiLSTM.Better performance was also achieved in the five viral,bacterial,toxic,and metabolic diseases that were prone to occur in laying hens farming.The macro-F1 values of the BERT-LHDKG diagnostic model were 96.43%,95.57%,96.72%,and 98.24%,respectively.The ablation experiments showed that the removal of each layer from the BERT-LHDKG structure reduced the diagnostic accuracy of the improved model.Meanwhile,the macroprecision,macrorecall,and macro-Fl of the improved model decreased by 5.14,4.98,and 5.46 percentage points,respectively,after the removal of the laying hens disease knowledge graph.Therefore,the knowledge graph was integrated to link the entities and relationships in the epidemic texts to the corresponding entities in the knowledge graph.The semantic information of the text was enriched to fully understand the content of the text.Thereby,the accuracy and robustness of the improved model was improved for epidemic diagnosis.In addition,the laying hen disease diagnosis web system was developed on the basis of the BERT-LHDKG diagnostic model,indicating the flexibility of remote diagnosis for laying hen diseases through human-machine dialogue.
Author 童勤
高荣华
李奇峰
王书君
李海燕
余礼根
刘羽
王朝元
AuthorAffiliation 北京市农林科学院信息技术研究中心,北京 100097;中国农业大学水利与土木工程学院,北京 100083;国家数字畜牧业创新中心,北京 100097%中国农业大学水利与土木工程学院,北京 100083%北京市农林科学院信息技术研究中心,北京 100097;国家数字畜牧业创新中心,北京 100097
AuthorAffiliation_xml – name: 北京市农林科学院信息技术研究中心,北京 100097;中国农业大学水利与土木工程学院,北京 100083;国家数字畜牧业创新中心,北京 100097%中国农业大学水利与土木工程学院,北京 100083%北京市农林科学院信息技术研究中心,北京 100097;国家数字畜牧业创新中心,北京 100097
Author_FL WANG Shujun
WANG Chaoyuan
LIU Yu
YU Ligen
LI Haiyan
TONG Qin
LI Qifeng
GAO Ronghua
Author_FL_xml – sequence: 1
  fullname: WANG Shujun
– sequence: 2
  fullname: TONG Qin
– sequence: 3
  fullname: LIU Yu
– sequence: 4
  fullname: LI Qifeng
– sequence: 5
  fullname: WANG Chaoyuan
– sequence: 6
  fullname: GAO Ronghua
– sequence: 7
  fullname: YU Ligen
– sequence: 8
  fullname: LI Haiyan
Author_xml – sequence: 1
  fullname: 王书君
– sequence: 2
  fullname: 童勤
– sequence: 3
  fullname: 刘羽
– sequence: 4
  fullname: 李奇峰
– sequence: 5
  fullname: 王朝元
– sequence: 6
  fullname: 高荣华
– sequence: 7
  fullname: 余礼根
– sequence: 8
  fullname: 李海燕
BookMark eNo9j7tKA0EYRqeIYIx5CgurXf9_dmdnFmwkeIOAjdZhdmc2JMgEXEStvWKIWK1oJJJCEFSiXRD0adyLb2FEsfrgFOfwzZCS6RhNyByCjehzttC2W3FsbASglifQtylQFxhQLJHyP50m1ThuBcDQ4QAulsliMeill2dZcprdPn2OL_K7-2J0kvY_ipfX_Oao6He_xsM8ecyvjrPrt-LwvRidZ8lz9jBMB91ZMhXJ7VhX_7ZCtlaWN2trVn1jdb22VLdiBCosGioERXWoGEgK3A2V58sAPVf5UkgdCU1BC8oZh4C5kQIMFNdh5AgBIfOdCpn_9e5JE0nTbLQ7uztmUmyYg2a4H_x8RT5JOd-h2mOH
ClassificationCodes TP391%S24
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.11975/j.issn.1002-6819.202405021
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Agriculture
DocumentTitle_FL Intelligent diagnosis model for laying hens diseases using text and knowledge graph
EndPage 272
ExternalDocumentID nygcxb202417028
GrantInformation_xml – fundername: (国家科技重大专项); (北京市智慧农业创新团队项目); (北京市博士后工作经费资助项目)
  funderid: (国家科技重大专项); (北京市智慧农业创新团队项目); (北京市博士后工作经费资助项目)
GroupedDBID -04
2B.
4A8
5XA
5XE
92G
92I
93N
ABDBF
ABJNI
ACGFO
ACGFS
ACUHS
AEGXH
AIAGR
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CHDYS
CW9
EOJEC
FIJ
IPNFZ
OBODZ
PSX
RIG
TCJ
TGD
TUS
U1G
U5N
ID FETCH-LOGICAL-s1028-2cd10d2ecd50a2074cd69ab164d9a8aef8e20e827570b54fd01bd7ecf3880c593
ISSN 1002-6819
IngestDate Thu May 29 04:08:37 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 17
Keywords BERT模型
laying hens diseases
BERT model
蛋鸡疫病
文本
text
知识图谱
智能诊断
knowledge graph
intelligent diagnosis
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1028-2cd10d2ecd50a2074cd69ab164d9a8aef8e20e827570b54fd01bd7ecf3880c593
PageCount 8
ParticipantIDs wanfang_journals_nygcxb202417028
PublicationCentury 2000
PublicationDate 2024-09-01
PublicationDateYYYYMMDD 2024-09-01
PublicationDate_xml – month: 09
  year: 2024
  text: 2024-09-01
  day: 01
PublicationDecade 2020
PublicationTitle 农业工程学报
PublicationTitle_FL Transactions of the Chinese Society of Agricultural Engineering
PublicationYear 2024
Publisher 北京市农林科学院信息技术研究中心,北京 100097
国家数字畜牧业创新中心,北京 100097%中国农业大学水利与土木工程学院,北京 100083%北京市农林科学院信息技术研究中心,北京 100097
中国农业大学水利与土木工程学院,北京 100083
国家数字畜牧业创新中心,北京 100097
Publisher_xml – name: 国家数字畜牧业创新中心,北京 100097
– name: 北京市农林科学院信息技术研究中心,北京 100097
– name: 国家数字畜牧业创新中心,北京 100097%中国农业大学水利与土木工程学院,北京 100083%北京市农林科学院信息技术研究中心,北京 100097
– name: 中国农业大学水利与土木工程学院,北京 100083
SSID ssib051370041
ssj0041925
ssib001101065
ssib023167668
Score 2.4437702
Snippet TP391%S24; 针对利用单一文本描述进行蛋鸡疫病诊断存在关联信息分析不够全面、未能提供完整蛋鸡疫病知识,进而导致在复杂蛋鸡疫病诊断中存在准确率不高等问题,该研究提出一种采用基于转换器的双向编码预训练模型(bidirectional encoder representation from...
SourceID wanfang
SourceType Aggregation Database
StartPage 265
Title 融合文本与知识图谱的蛋鸡疫病智能诊断模型
URI https://d.wanfangdata.com.cn/periodical/nygcxb202417028
Volume 40
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1JaxRBFC6ygOhBXHEnoHWSjl09XRt4qZrpIQh6SiC3ML3F0wjJBDRXVwyKp4hGIjkI4kL0FgT9NWZm_Be-V90z0ySKy6Upqt579dX3uue96qmqJuQSq3GZq4R7ImPCC3OeeHGcZl6axT5PdC1ppfiP7vUbYmYuvDbP58fG31VWLa104ulk9Zf7Sv7Hq1AHfsVdsv_g2aFRqIAy-Beu4GG4_pWPaaSojqhq0IhT7VOlaCSoFhRm-FioU1OnUUitoiqikaS6SQ1HLdOkSjgtS22ENdanljkZQ1XoLFuqLI00qpuiSVBjXUFSxV0X0GpQWNWobQwsmxKGaWDBFOrcQbXVbBgrlcNZgISuocZKB1KiIgLgaMcINAWWDR_cIyiiIicC2tqJOBq0rYoAYjTHUdCEoxaOdGmFIsCAbYxaAFHDEcZRE7kEUDA-v_qKJAiHa8CKm9pZrCM1CMc46rmjPqiMUyALKAPAgEdWGZ5GNk3g1JuOMhgwQ0KLkSt_4NSmU4eBhq4APhAlg8bdCqAO_gjq-yFdZm5PTSUUYawSqgwoZawqjrYaPJOyGnmKT26USUxQfA9pf3zUkrsAiV1MD7uYRtZ87heb1fccQN6-s5jcjlGCSchGx8lkICUuiZg0tmGbo-Sb4fuFYXQI8IwFMZrMclbDTykMF2Dh8gPu1iKUIA6QiwOIV34P0G2ua-et9mIlD5w9Qg6XE7gpUzyNR8nY6s1j5JBZXCoPscmOk6v9zSe7zx511x92X334vvO09_pNf_vB7sa3_qfPvZf3-htrP3a2euvve8_vd1986d_92t9-3F3_2H27tbu5doLMNaPZ-oxXfqXEW8bk3AuSlPlpkCUp91sBZORJKnQrZiJMdUu1slxlgZ-pQHLpxzzMU5_FqcySHI9hSriunSQT7Vvt7BSZkglMuDIWgwURxmms41zkCUu4DEXOlThNpsqxL5S_QssLe7xz5s8iZ8nB0UNyjkx0llay85BZd-ILpUt_AtiDmvE
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E8%9E%8D%E5%90%88%E6%96%87%E6%9C%AC%E4%B8%8E%E7%9F%A5%E8%AF%86%E5%9B%BE%E8%B0%B1%E7%9A%84%E8%9B%8B%E9%B8%A1%E7%96%AB%E7%97%85%E6%99%BA%E8%83%BD%E8%AF%8A%E6%96%AD%E6%A8%A1%E5%9E%8B&rft.jtitle=%E5%86%9C%E4%B8%9A%E5%B7%A5%E7%A8%8B%E5%AD%A6%E6%8A%A5&rft.au=%E7%8E%8B%E4%B9%A6%E5%90%9B&rft.au=%E7%AB%A5%E5%8B%A4&rft.au=%E5%88%98%E7%BE%BD&rft.au=%E6%9D%8E%E5%A5%87%E5%B3%B0&rft.date=2024-09-01&rft.pub=%E5%8C%97%E4%BA%AC%E5%B8%82%E5%86%9C%E6%9E%97%E7%A7%91%E5%AD%A6%E9%99%A2%E4%BF%A1%E6%81%AF%E6%8A%80%E6%9C%AF%E7%A0%94%E7%A9%B6%E4%B8%AD%E5%BF%83%2C%E5%8C%97%E4%BA%AC+100097&rft.issn=1002-6819&rft.volume=40&rft.issue=17&rft.spage=265&rft.epage=272&rft_id=info:doi/10.11975%2Fj.issn.1002-6819.202405021&rft.externalDocID=nygcxb202417028
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fnygcxb%2Fnygcxb.jpg