计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (3): 95-99.DOI: 10.3778/j.issn.1002-8331.1507-0017

• 大数据与云计算 • 上一篇    下一篇

基于概念格的信息检索及其树形可视化

沈夏炯1,2,叶曼曼2,甘  甜2,韩道军1,2   

  1. 1.河南大学 数据与知识工程研究所,河南,开封 475004
    2.河南大学 计算机与信息工程学院,河南,开封 475004
  • 出版日期:2017-02-01 发布日期:2017-05-11

 Information retrieval based on concept lattice and its tree visualization

SHEN Xiajiong1, 2, YE Manman2, GAN Tian2, HAN Daojun1, 2   

  1. 1.Institute of Data and Knowledge Engineering, Henan University, Kaifeng, Henan 475004, China
    2.School of Computer and Information Engineering, Henan University, Kaifeng, Henan 475004, China
  • Online:2017-02-01 Published:2017-05-11

摘要: 概念格作为形式概念分析理论重要的数据表示形式,因其生动简洁地体现概念之间的泛化和特化关系,被广泛应用于知识获取与信息检索领域。在使用概念格进行检索的过程中,随着概念格中概念以及概念之间关系的增加,呈现的格结构容易产生边交叉现象,造成视觉混淆,导致目标信息遗漏。针对这一问题,结合概念格在信息检索方面的优越性以及树形结构在可视化方面的有序性,首先用概念格结构存储数据信息,然后在信息展示时将格结构转化成树形结构,使用户不仅可以通过多条路径检索到目标信息,且结构清晰。最后通过将概念格树形化方法应用于音乐工具分类检索场景中,验证该方法的实用性。

关键词: 概念格, 信息检索, 树形结构, 可视化

Abstract: Concept lattice as a significant data representation of formal concept lattice has been widely used in knowledge acquisition and information retrieval for embodying the generalization and specialization relationship vividly and succinctly among concepts. In the process of using concept lattice for retrieval, the presenting structure of concept lattice is easily making edges crossover as the number of concepts and their relationships grow significantly, giving rise to confused vision and target information omission. To solve this problem, combining the advantages of concept lattice in information retrieval with the regularity of tree structure in visualization, firstly it stores data information using concept lattice structure, then changes the lattice structure into tree structure before displaying to the users, so that users can not only search target information through multiple paths but also have a clear browsing. Finally, the method is applied to music classification and retrieval, and experimental result shows that the method is efficient and effective.

Key words: concept lattice, information retrieval, tree structure, visualization