基于机器学习的馆内阅读行为模式分析
2021-04-03许智敏施玲玲肖珊郭雁瑶邹嘉书
许智敏 施玲玲 肖珊 郭雁瑶 邹嘉书



摘 要:针对大量阅读者的阅读能力制约着其阅读效果的难题提出了一种基于机器学习的馆内行为模式分析方法。首先,研究了一种“宏-微”复合视觉成像方法及工作原理;其次,研究了基于图像特征的阅读行为模式识别算法;最后,将基于馆内目标图像获取的阅读行为模式与实际的阅读行为模式进行对比分析。并由实验验证该文提出的方法能够精准、稳定地识别馆内阅读者的阅读行为模式。
关键词:阅读行为模式;机器视觉;眼动跟踪;SVM
中图分类号:TP18 文献标识码:A文章编号:2096-4706(2021)19-0067-05
Analysis of Reading Behavior Patterns in the Library Based on Machine Learning
XU Zhimin, SHI Lingling, XIAO Shan, GUO Yanyao, ZOU Jiashu
(Guangzhou Maritime University, Guangzhou 510725, China)
Abstract: Aiming at the difficult problem that a large number of readers reading ability restricts their reading effect, a library behavior pattern analysis method based on machine learning is proposed. Firstly, a “macro-micro” composite vision imaging method and its working principle are studied; secondly, the reading behavior pattern recognition algorithm based on image features is studied; finally, the reading behavior patterns obtained based on the target images in the library are compared with the actual reading behavior patterns. Experiments show that the proposed method in this paper can accurately and stably identify the reading behavior patterns of readers in the library.
Keywords: reading behavior pattern; machine vision; eye tracking; SVM
0 引 言
閱读是人类互相交流、分享经验、合作创新的重要方式,是学习知识、传承文明、提高人口素质的基本途径[1]。习近平总书记在读者出版集团考察调研时,提倡多读书,建设书香社会,不断提升人民思想境界、增强人民精神力量[2]。在新时代人民物质生活得到保障情况下,精神文化层面的丰富迅速提上日程,因此阅读成为一个时代趋势。在大数据时代背景下,阅读者在阅读过程中普遍存在注意力不集中、阅读效率低下、理解能力不足等等阅读障碍,造成阅读效果不佳等同于无效阅读,目前人们对阅读能力制约着新时代人们精神文化发展水平的快速提升,因此,深入的分析阅读者阅读过程中障碍,成为有效提高阅读效率及质量的关键技术之一。
眼动追踪装备是现有研究阅读障碍的关键设备之一。一方面,荷兰的SKALAR公司研……
