Journal of Intelligent Agricultural Mechanization ›› 2024, Vol. 5 ›› Issue (4): 39-50.DOI: 10.12398/j.issn.2096-7217.2024.04.003
Previous Articles Next Articles
ZHAO Zexing1(), WU Xiaopeng1, WANG Yixin2, YAN Xiaoli1, HUANG Yuxiang1, GAO Xiaojun3,4()
Received:
2023-12-27
Revised:
2024-03-21
Online:
2024-11-15
Published:
2024-11-15
Corresponding author:
GAO Xiaojun
CLC Number:
ZHAO Zexing, WU Xiaopeng, WANG Yixin, YAN Xiaoli, HUANG Yuxiang, GAO Xiaojun. Research on question answering system for crop diseases and pests based on knowledge graph[J]. Journal of Intelligent Agricultural Mechanization, 2024, 5(4): 39-50.
Add to citation manager EndNote|Ris|BibTeX
URL: http://znhnyzbxb.niam.com.cn/EN/10.12398/j.issn.2096-7217.2024.04.003
实体类别 | 含义描述 | 实体定义 |
---|---|---|
农作物 | 常见农作物 | CRO |
病害 | 农作物常见病害 | DIS |
虫害 | 农作物常见虫害/害虫 | PES |
症状 | 农作物病害的为害症状 | SYM |
病原 | 引发农作物病害的根源 | PAT |
传播途径 | 病害病原的传播方法 | TRA |
寄主 | 农作物害虫的为害对象 | HOS |
为害特点 | 农作物虫害的为害症状 | CHA |
形态特征 | 农作物害虫的形态特征 | FIG |
生活习性 | 农作物害虫的生活习性 | HAB |
防治方法 | 农作物病虫害的防治途径 | MET |
Table 1 Knowledge domain entity categories
实体类别 | 含义描述 | 实体定义 |
---|---|---|
农作物 | 常见农作物 | CRO |
病害 | 农作物常见病害 | DIS |
虫害 | 农作物常见虫害/害虫 | PES |
症状 | 农作物病害的为害症状 | SYM |
病原 | 引发农作物病害的根源 | PAT |
传播途径 | 病害病原的传播方法 | TRA |
寄主 | 农作物害虫的为害对象 | HOS |
为害特点 | 农作物虫害的为害症状 | CHA |
形态特征 | 农作物害虫的形态特征 | FIG |
生活习性 | 农作物害虫的生活习性 | HAB |
防治方法 | 农作物病虫害的防治途径 | MET |
关系类别 | 含义描述 |
---|---|
Disease Pest | 农作物——病/虫害 |
Disease Symptom | 病害——症状 |
Disease Pathogeny | 病害——病原 |
Disease Transmission | 病害——传播途径 |
Pest Host | 虫害——寄主 |
Pest Character | 虫害——为害特点 |
Pest Figure | 虫害——形态特征 |
Pest Habit | 虫害——生活习性 |
Prevent Method | 病/虫害——防治方法 |
Table 2 Knowledge domain relationship categories
关系类别 | 含义描述 |
---|---|
Disease Pest | 农作物——病/虫害 |
Disease Symptom | 病害——症状 |
Disease Pathogeny | 病害——病原 |
Disease Transmission | 病害——传播途径 |
Pest Host | 虫害——寄主 |
Pest Character | 虫害——为害特点 |
Pest Figure | 虫害——形态特征 |
Pest Habit | 虫害——生活习性 |
Prevent Method | 病/虫害——防治方法 |
首实体 | 关系 | 尾实体 |
---|---|---|
水稻恶苗病 | DiseasePathogeny | Fusarium moniliforme Sheld |
水稻烂秧病 | DiseasePathogeny | Fusarium graminearum Schw |
水稻白绢病 | DiseasePathogeny | Sclerotium rolfsii Sacc |
水稻白叶枯病 | DiseasePathogeny | Xanthomonas oryzae |
… | DiseasePathogeny | … |
Table 3 Storage of triple
首实体 | 关系 | 尾实体 |
---|---|---|
水稻恶苗病 | DiseasePathogeny | Fusarium moniliforme Sheld |
水稻烂秧病 | DiseasePathogeny | Fusarium graminearum Schw |
水稻白绢病 | DiseasePathogeny | Sclerotium rolfsii Sacc |
水稻白叶枯病 | DiseasePathogeny | Xanthomonas oryzae |
… | DiseasePathogeny | … |
工具/试验环境 | 版本参数 |
---|---|
Python | 3.7 |
Pytorch | 1.7.1 + cu110 |
Sklearn | 0.24.1 |
Numpy | 1.20.1 |
GPU | RTX 3090 |
操作系统 | Ubnutu 22.04 |
Table 4 Experimental environment configuration
工具/试验环境 | 版本参数 |
---|---|
Python | 3.7 |
Pytorch | 1.7.1 + cu110 |
Sklearn | 0.24.1 |
Numpy | 1.20.1 |
GPU | RTX 3090 |
操作系统 | Ubnutu 22.04 |
参数名称 | 参数值 |
---|---|
Batch size | 64 |
Optimizer | Adam |
Transformer layer | 12 |
Learning rate | 0.000 1 |
Dropout ratio | 0.3/0.2 |
Embedding Size | 512/256 |
LSTM_emb | 200/- |
Epoch | 100/200 |
Table 5 Model hyperparameter configuration
参数名称 | 参数值 |
---|---|
Batch size | 64 |
Optimizer | Adam |
Transformer layer | 12 |
Learning rate | 0.000 1 |
Dropout ratio | 0.3/0.2 |
Embedding Size | 512/256 |
LSTM_emb | 200/- |
Epoch | 100/200 |
模型对比 | P/% | R/% | F1/% | |
---|---|---|---|---|
实体识别 | BiLSTM | 88.68 | 87.36 | 86.91 |
BiLSTM-CRF | 91.85 | 90.33 | 90.54 | |
BERT-BiLSTM-CRF | 93.22 | 92.69 | 92.21 | |
问题分类 | BERT | 94.04 | 93.26 | 92.21 |
RNN | 93.55 | 93.36 | 91.95 | |
BERT-RNN | 94.37 | 93.92 | 92.66 |
Table 6 Experimental result
模型对比 | P/% | R/% | F1/% | |
---|---|---|---|---|
实体识别 | BiLSTM | 88.68 | 87.36 | 86.91 |
BiLSTM-CRF | 91.85 | 90.33 | 90.54 | |
BERT-BiLSTM-CRF | 93.22 | 92.69 | 92.21 | |
问题分类 | BERT | 94.04 | 93.26 | 92.21 |
RNN | 93.55 | 93.36 | 91.95 | |
BERT-RNN | 94.37 | 93.92 | 92.66 |
1 | GUANXI Y, THIERRY B, HABIBULLAH B, et al. The technical challenges for applying unsaturated soil sensors to conduct laboratory-scale seepage experiments [J]. Sensors, 2022, 22(10): 3724-3724. |
2 | 韩文霆, 李广, 苑梦婵, 等. 基于无人机遥感技术的玉米种植信息提取方法研究[J]. 农业机械学报, 2017, 48(1): 139-147. |
HAN Wenting, LI Guang, YUAN Mengchan, et al. Extraction method of maize planting information based on UAV remote sensing technology [J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(1): 139-147. | |
3 | AMINE F, MOHAMED S, ESSAID S. An agile AI and IoT-augmented smart farming: A cost-effective cognitive weather station [J]. Agriculture, 2022, 12(1): 35. |
4 | 苗小爱. 基于大数据分析的农业信息化研究[J]. 智慧农业导刊, 2023, 3(7): 4-6,10. |
MIAO Xiaoai. Research on agricultural informatization based on big data analysis [J]. Journal of Smart Agriculture, 2023, 3(7): 4-6, 10. | |
5 | 吴赛赛, 周爱莲, 谢能付, 等. 基于深度学习的作物病虫害可视化知识图谱构建[J]. 农业工程学报, 2020, 36(24): 177-185. |
WU Saisai, ZHOU Ailian, XIE Nengfu, et al. Construction of visualization domain-specific knowledge graph of crop diseases and pests based on deep learning [J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(24): 177-185. | |
6 | 李林, 周晗, 郭旭超, 等. 基于多源信息融合的中文农作物病虫害命名实体识别[J]. 农业机械学报, 2021, 52(12): 253-263. |
LI Lin, ZHOU Han, GUO Xuchao, et al. Named entity recognition of diseases and insect pests based on multi source information fusion [J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(12): 253-263. | |
7 | POPPING R. Knowledge graphs and network text analysis [J]. Social Science Information, 2003, 42(1): 91-106. |
8 | 陈佳云, 徐向英, 章永龙, 等. 多模态知识图谱在农业中的研究进展[J]. 农业大数据学报, 2022, 4(3): 126-134. |
CHEN Jiayun, XU Xiangying, ZHANG Yonglong, et al. Research progress of multimodal knowledge graph in agriculture [J]. Journal of Agricultural Big Data, 2022, 4(3): 126-134. | |
9 | 徐畅, 张领先, 乔岩. 基于电子病历的作物病虫害关联挖掘及智能诊断[J]. 智能化农业装备学报(中英文), 2023, 4(4): 1-10. |
XU Chang, ZHANG Lingxian, QIAO Yan. Association mining of crop diseases and intelligent diagnosis based on electronic medical records [J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(4): 1-10. | |
10 | 王丹丹. 宁夏水稻知识图谱构建方法研究与应用[D]. 银川: 北方民族大学, 2020. |
WANG Dandan. Research and application of construction method of rice knowledge graph in Ningxia [D]. Yinchuan: North Minzu University, 2020. | |
11 | 张永亮. 基于知识图谱的苹果病虫害智能问答系统研究[D]. 杨凌: 西北农林科技大学, 2022. |
ZHANG Yongliang. Research on intelligent question answering system of apple diseases and insect pests based on knowledge graph [D]. Yangling: Northwest A&F University, 2022. | |
12 | 闫丽华. 基于知识图谱的葡萄病虫害自动问答系统[D]. 杨凌: 西北农林科技大学, 2021. |
YAN Lihua. Automatic question answering system of grape diseases and pests based on knowledge graph [D]. Yangling: Northwest A&F University, 2021. | |
13 | 刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3): 582-600. |
LIU Qiao, LI Yang, DUAN Hong, et al. Knowledge graph construction techniques [J]. Journal of Computer Research and Development, 2016, 53(3): 582-600. | |
14 | 吴赛赛. 基于知识图谱的作物病虫害智能问答系统设计与实现[D]. 北京: 中国农业科学院, 2021. |
WU Saisai. Design and implementation of intelligent question answering system for crop diseases and pests based on knowledge graph [D]. Beijing: Chinese Academy of Agricultural Sciences, 2021. | |
15 | 张嘉宇, 郭玫, 张永亮, 等. 细粒度苹果病虫害知识图谱构建研究[J]. 计算机工程与应用, 2023, 59(5): 270-280. |
ZHANG Jiayu, GUO Mei, ZHANG Yongliang, et al. Research on construction of fine-grained knowledge graph of apple diseases and pests [J]. Computer Engineering and Applications, 2023, 59(5): 270-280. | |
16 | LOURDUSAMY R, MATTAM X J. Knowledge graph using resource description framework and connectionist theory [C]//IOP Publishing Ltd., 2020:012001.DOI:10.1088/1742-6596/1427/1/012001 . |
17 | 李雪. 一种基于Neo4j图数据库的模糊查询研究与实现[J]. 计算机技术与发展, 2018, 28(11): 78-86. |
LI Xue. Research and implementation of a fuzzy query based on Neo4j graph database [J]. Compute Technology and Development, 2018, 28(11): 78-86. | |
18 | 王婷, 王娜, 崔运鹏, 等. 基于人工智能大模型技术的果蔬农技知识智能问答系统[J]. 智慧农业(中英文), 2023, 5(4): 105-116. |
WANG Ting, WANG Na, CUI Yunpeng, et al. Agricultural technology knowledge intelligent question-answering system based on large language model [J]. Smart Agriculture, 2023, 5(4): 105-116. | |
19 | ZHANG Q, YU H Q, SUN P, et al. Multisource data based agricultural drought monitoring and agricultural loss in China[J]. Global and Planetary Change, 2018, 172(JAN.): 298-306. |
20 | 白皓然, 孙伟浩, 金宁, 等. 基于改进Bi-LSTM-CRF的农业问答系统研究[J]. 中国农机化学报, 2023, 44(2): 99-105. |
BAI Haoran, SUN Weihao, JIN Ning, et al. Research on agricultural question answering system based on improved Bi-LSTM-CRF [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(2): 99-105. | |
21 | ZHANG Y, ZHANG M L, LUO N, et al. Understanding the formation mechanism of high-quality knowledge in social question and answer communities: A knowledge co-creation perspective [J]. International Journal of Information Management, 2019, 48: 72-84. |
22 | 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, 49(12): 2618-2622. |
ZHENG Yongzhi, WU Huilin, ZHU Dingju, et al. Question and answer system based on the knowledge graphs of Litchi and Longan diseases and insect pests [J]. Computer & Digital Engineering, 2021, 49(12): 2618-2622. | |
23 | 赵瑞雪, 杨晨雪, 郑建华, 等. 农业智能知识服务研究现状及展望[J]. 智慧农业(中英文), 2022, 4(4): 105-125. |
ZHAO Ruixue, YANG Chenxue, ZHENG Jianhua, et al. Agricultural intelligent knowledge service: Overview and future perspectives [J]. Smart Agriculture, 2022, 4(4): 105-125. | |
24 | 李源, 丁士宁, 张克旺, 等. 基于CiteSpace的水稻病虫害研究热点与发展趋势分析 [J]. 农业展望, 2022, 18(5): 97-104. |
LI Yuan, DING Shining, ZHANG Kewang, et al. Research hotspots and development trend of rice disease and insect pests based on CiteSpace [J]. Agricultural Outlook, 2022, 18(5): 97-104. |
[1] | XU Chang, ZHANG Lingxian, QIAO Yan. Association mining of crop diseases and intelligent diagnosis based on electronic medical records [J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(4): 1-10. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||