• • 上一篇    

基于BiLSTM-CRF的食品行业质量安全风险分析

张海航1, 陈进东1,2, 张健1,3   

  1. 1. 北京信息科技大学, 北京 100083;
    2. 智能决策与大数据应用北京市国际科技合作基地, 北京 100192;
    3. 绿色发展大数据决策北京市重点实验室, 北京 100192
  • 收稿日期:2022-05-13 修回日期:2022-06-19 发布日期:2022-11-04
  • 通讯作者: 陈进东,Email:j.chen@bistu.edu.cn.
  • 基金资助:
    国家重点研发计划项目(2019YFB1405303),国家自然科学基金面上项目(72174018)资助课题.

张海航, 陈进东, 张健. 基于BiLSTM-CRF的食品行业质量安全风险分析[J]. 系统科学与数学, 2022, 42(10): 2616-2633.

ZHANG Haihang, CHEN Jindong, ZHANG Jian. Quality and Safety Risks Analysis of Food Industry Based on BiLSTM-CRF[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(10): 2616-2633.

Quality and Safety Risks Analysis of Food Industry Based on BiLSTM-CRF

ZHANG Haihang1, CHEN Jindong1,2, ZHANG Jian1,3   

  1. 1. Beijing Information Science and Technology University, Beijing 100083;
    2. Beijing International Science and Technology Cooperation Base for Intelligent Decision and Big Data Application, Beijing 100192;
    3. Beijing Key Lab of Green Development Decision Making Based on Big Data, Beijing 100192
  • Received:2022-05-13 Revised:2022-06-19 Published:2022-11-04
以2018——2020年国家及各省市市场监督管理局发布的食品安全监督抽检报告为数据源,基于实体识别、规则匹配及统计分析等方法,分析中国食品行业质量安全风险现状及演化趋势.首先,基于BiLSTM-CRF模型提取报告中检测类别、检测项目实体名称,并结合所提取出的实体名称进行规则匹配,挖掘报告中食品行业质量安全风险相关信息;其次,针对所挖掘的信息归纳整理,从时域、地域角度研究中国食品行业高发性质量安全风险问题成因,并探究食品行业安全现状与演化趋势.研究发现,中国食品行业整体处于良好状态,质量安全风险较低;部分安全风险的成因及解决方式需紧抓根本,行业生产、储存及销售过程中所暴露出问题的亟待解决;行业监管力度需进一步加强,食品行业从业者整体素质仍存在提升空间,部分安全风险问题的改善仍应从实际出发.
Collecting the food safety supervision and inspection reports issued by the national and provincial market supervision and administration bureaus from 2018 to 2020,this paper analyzes the current situation and evolution trend of China's food industry safety based on entity recognition,text mining and statistical analysis.Firstly,based on BiLSTM-CRF model,the entity names of the inspection category and inspection item in the reports are extracted,and the extracted entity names are combined for rule matching to mine the quality and safety risk information of food industry;Secondly,based on the collected information,this paper studies the causes of high-frequency quality and safety risks in China's food industry with the perspective of time and region,and explores the current situation and evolution trend of food industry safety.The results show that China's food industry is still in a good state with low safety risks;The causes and solutions to part of the quality and safety risks need to grasp the essence of the problems,and the problems exposed in the process of production,storage and sales need to be resolved urgently;Industry supervision needs to be further strengthened,the overall quality of food industry practitioners still has room for improvement,and part of the safety risks should be proceeded from reality.

MR(2010)主题分类: 

()
[1] 侯博,刘强,王志威.我国食品安全风险治理研究的时空分布与热点研判.食品科学, 2022, 43(13):237-245.((Hou B, Liu Q, Wang Z W. Temporal and spatial distribution and hotspot analysis of studies on food safety risk governance in China. Food Science, 2022, 43(13):237-245.)
[2] 何紫琪,李丹阳.脆弱性理论视角下传统生鲜食品市场公共卫生风险及其治理.中国食品卫生杂志, 2020, 32(6):648-653.(He Z Q, Li D Y. Public health risks and their governance in traditional fresh food market from the perspective of vulnerability theory. Chinese Journal of Food Hygiene, 2020, 32(6):648-653.)
[3] Fearne A, Martinez M G. Opportunities for the coregulation of food safety:Insights from the United Kingdom. Choices, 2005, 20(2):109-116.
[4] 张红霞.我国食品安全风险因素识别与分布特征-基于9314起食品安全事件的实证分析.当代经济管理, 2021, 43(4):66-71.(Zhang H X. Identification and distribution characteristics of food safety risk factors-An empirical analysis based on 9314 food safety incidents. Contemporary Economic Management, 2021, 43(4):66-71.)
[5] 曹恒.浅析网络新闻失实的成因及应对措施.传播与版权, 2019,(2):166-168.(Cao H. An analysis of the causes and countermeasures of online news inaccuracy. Cuanbo yu Banquan, 2019,(2):166-168.)
[6] Goldberg D M, Khan S, Zaman N, et al. Text mining approaches for postmarket food safety surveillance using online media. Risk Analysis, 2022, 42(8):1749-1768.
[7] 李太平,李佳睿.中国东中西部六省市食品安全状况比较.中国公共卫生, 2019, 35(2):193-196.(Li T P, Li J R. Food safety in six provinces and cities in eastern, central and western China:A comparison study. Chinese Journal of Public Health, 2019, 35(2):193-196.)
[8] 高航,于兆锋.基于食品抽检报告的吉林省食品安全探微.食品工业, 2020, 41(9):411.(Gao H, Yu Z F. Probe into food safety in Jilin province based on food sampling report. The Food Industry, 2020, 41(9):411.)
[9] 冀振燕,孔德焱,刘伟,等.基于深度学习的命名实体识别研究.计算机集成制造系统, 2022, 28(6):1603-1615.(Ji Z Y, Kong D Y, Liu W, et al. Named entity recognition based on deep learning. Computer Integrated Manufacturing Systems, 2022, 28(6):1603-1615.)
[10] 刘浏,王东波.命名实体识别研究综述.情报学报, 2018, 37(3):329-340.(Liu L, Wang D B. A review on named entity recognition. Journal of the China Society for Scientific and Technical Information, 2018, 37(3):329-340.)
[11] 许力,李建华.基于BERT和BiLSTM-CRF的生物医学命名实体识别.计算机工程与科学, 2021, 43(10):1873-1879.(Xu L, Li J H. Biomedical named entity recognition based on BERT and BiLSTM-CRF. Computer Engineering&Science, 2021, 43(10):1873-1879.)
[12] 曾青霞,熊旺平,杜建强,等.结合自注意力的BiLSTM-CRF的电子病历命名实体识别.计算机应用与软件, 2021, 38(3):159-162, 242.(Zeng Q X, Xiong W P, Du J Q, et al. Electronic medical record named entity recogition combined with self-attention BiLSTM-CRF. Computer Applications and Software, 2021, 38(3):159-162, 242.)
[13] 刘文聪,张春菊,汪陈,等.基于BiLSTM-CRF的中文地质时间信息抽取.地球科学进展, 2021, 36(2):211-220.(Liu W C, Zhang C J, Wang C, et al. Geological time information extraction from Chinese text based on BiLSTM-CRF. Advances in Earth Science, 2021, 36(2):211-220.)
[14] 徐建国,刘泳慧,刘梦凡.基于BILSTM-CRF的高校政策语义角色标注研究.计算机工程与应用, 2021, 57(6):207-211.(Xu J G, Liu Y H, Liu M F. Research on semantic role labeling of university policy based on BiLSTM-CRF. Computer Engineering and Applications, 2021, 57(6):207-211.)
[15] 杨锦锋,关毅,何彬,等.中文电子病历命名实体和实体关系语料库构建.软件学报, 2016, 27(11):2725-2746.(Yang J F, Guan Y, He B, et al. Corpus construction for named entities and entity relations on Chinese electronic medical records. Journal of Software, 2016, 27(11):2725-2746.)
[16] 王学锋,杨若鹏,朱巍.基于深度学习的军事命名实体识别方法.装甲兵工程学院学报, 2018, 32(4):94-98.(Wang X F, Yang R P, Zhu W. Military named entity recognition method based on deep learning. Journal of Armored Forces, 2018, 32(4):94-98.)
[17] 车翔玖,徐欢,潘明阳,等.生物医学命名实体识别的两阶段学习算法.吉林大学学报(工学版):1-10[2022-8-11]. DOI:10.13229/j.cnki.jdxbgxb20211156.(Chen X J, Xu H, Pan M Y, et al. A two-stage learning algorithm for biomedical named entity recognition. Journal of Jilin University (Engineering and Technology Edition):1-10[2022-8-11]. DOI:10.13229/j.cnki.jdxbgxb20211156.)
[18] 毕金峰,易建勇,陈芹芹,等.国内外休闲食品产业与科技现状及发展趋势.中国食品学报, 2020, 20(12):320-328.(Bi J F, Yi J Y, Chen Q Q, et al. Current status and development trend of international leisure food industry and technology. Journal of Chinese Institute of Food Science and Technology, 2020, 20(12):320-328.)\newpage
[19] 李韧,李童,杨建喜,等.基于Transformer-BiLSTM-CRF的桥梁检测领域命名实体识别.中文信息学报, 2021, 35(4):83-91.(Li R, Li T, Yang J X, et al. Bridge inspection named entity recognition based on Transformer-BiLSTM-CRF. Journal of Chinese Information Processing, 2021, 35(4):83-91.)
[20] 罗熹,夏先运,安莹,等.结合多头自注意力机制与BiLSTM-CRF的中文临床实体识别.湖南大学学报(自然科学版), 2021, 48(4):45-55.(Luo X, Xia X Y, An Y, et al. Chinese CNER combined with Multi-head self-attention and BiLSTM-CRF. Journal of Hunan University (Natural Sciences), 2021, 48(4):45-55.)
[21] 陈汉炎."一带一路"战略中的休闲食品制造业的机遇与挑战.食品工业, 2017, 38(3):193-196.(Chen H Y. The opportunity and challenge of leisure food manufacturing enterprise in the"One Belt and One Road"national strategy. The Food Industry, 2017, 38(3):193-196.)
[22] Kharroubi S, Nasser N A, El-Harakeh M D, et al. First nation-wide analysis of food safety and acceptability data in Lebanon. Foods, 2020, 9(11):1717.
[23] Lin X, Cui S, Han Y, et al. An improved ISM method based on GRA for hierarchical analyzing the influencing factors of food safety. Food Control, 2019, 99:48-56.
[1] 曹丽娜,唐锡晋. BBS话题的地理分布分析[J]. 系统科学与数学, 2016, 36(5): 671-682.
[2] 许诺, 赵薇, 尚柯源, 陈浩宇. 基于预训练语言模型的健康谣言检测[J]. 系统科学与数学, 2022, 42(10): 2582-2589.
[3] 孔令云, 陈进东. 全国电子电器行业质量安全现状与对策建议[J]. 系统科学与数学, 2022, 42(10): 2602-2615.
阅读次数
全文


摘要