信息见解引导的可视化推荐  

Insight-Guided Visualization Recommendation

作　　者：陈滨 张钰涵 胡瑞珍 Chen Bin;Zhang Yuhan;Hu Ruizhen(Visual Computing Research Center,Shenzhen University,Shenzhen 518061)

机构地区：[1]深圳大学可视计算研究中心,深圳518061

出　　处：《计算机辅助设计与图形学学报》2023年第1期135-145,共11页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61872250);广东省自然科学基金(2021B1515020085)。

摘　　要：对高维数据的探索和分析需要在数据中提取有价值的信息见解并生成合适的可视化图表.为降低生成有效图表的门槛,以信息见解为中心自动生成可视化图表,提出一个可视化推荐框架,包含数据片段推荐和视觉编码推荐2部分.在数据片段推荐中,相比现有方法使用单一指标,所提框架结合多种分析方法和机器学习算法进行信息见解的挖掘和数据片段的排序,为用户推荐信息见解丰富的数据片段;在视觉编码推荐中,该框架结合规则和机器学习方法,基于信息见解的特征建立视觉编码映射,并对图表中的关键信息进行高亮以增强用户的理解.在图表类型预测任务中,使用用户绘制的真实可视化图表数据进行实验的结果表明,所提框架比现有方法具有更高的预测准确率;用户调查的结果则证明,该框架能帮助用户更好、更快地了解一个陌生的数据表格中蕴含的关键信息.Exploration and analysis of high-dimensional datasets require extracting valuable insights and generating proper charts from data.To lower the barriers of creating effective visualizations,a new insight-centric visualization recommendation framework is presented that recommends both what to visualize(data query recommendations)and how to visualize it(visual encoding recommendations).For the former,instead of using single indicators,multiple analysis methods and learning-based algorithms are utilized to automatically rank data queries based on the insights and the most informative ones are provided to the users.For the later,rule-based and learning-based methods are combined to generate visual mappings from data queries to charts and further highlight the key information in the generated charts to enhance their readability.It is demonstrated that proposed method achieves higher accuracy than existing methods for the chart type prediction task with real-world charts dataset.A user study is also conducted to show that proposed method can help users quickly explore new data tables and find important insights.

关 键 词：信息可视化 可视化推荐 信息见解 可视分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]