食品安全大数据可视化关联分析  

Visual associations analysis of big data in food safety

作　　者：陈谊[1] 孙梦[1] 武彩霞 孙小然 CHEN Yi;SUN Meng;WU Caixia;SUN Xiaoran(Beijing Key Laboratory of Big Data Technology for Food Safety,School of Computer Science and Engineering,Beijing Technology and Business University,Beijing 100048,China)

机构地区：[1]北京工商大学计算机学院食品安全大数据技术北京市重点实验室,北京100048

出　　处：《大数据》2021年第2期61-77,共17页Big Data Research

基　　金：国家重点研发计划资助项目(No.2018YFC1603602);国家自然科学基金资助项目(No.61972010)。

摘　　要：随着检测技术的提高和互联网技术的广泛应用,食品安全数据的规模不断增大、类型不断增多,对数据分析技术提出了极大挑战。近年来出现的可视分析技术,通过提供图形交互界面,帮助领域人员深入理解数据并洞悉数据中的隐含规律,提高对食品安全风险的分析、发现、预警和溯源能力,为食品安全监测和管控提供了新手段。首先分析了食品安全数据的主要来源、特征和分析任务;然后提出了一种关联可视分析技术分类方法,从属性关联、实体关联、对比分析和时空分析4个方面阐述了近10年来的食品安全大数据可视化关联分析方法;最后提出了该领域存在的问题和挑战。With the improvement of detection technology and the wide application of Internet technology,the scale and types of food safety data continue to increase,which poses great challenges to data analysis technology.Visual analysis,which has emerged in recent years,can help domain experts gain a deeper understanding of the data and insight into the hidden patterns in the data by providing a graphical interactive interface.This in turn can improve the detection,analysis,early warning and traceability of food safety risks,providing new tools for food safety monitoring and surveillance.Firstly,the main sources,characteristics and analysis tasks of food safety big data were analyzed.Then,a classification method for visual associations analysis techniques was proposed,and the visual associations analysis methods for food safety big data in the past 10 years were described from four aspects:attribute correlation,entity associations,comparative analysis and spatio-temporal analysis.Finally,the problems and challenges in this field were presented.

关 键 词：可视分析 大数据 食品安全 关联关系 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]