计算机与现代化 ›› 2025, Vol. 0 ›› Issue (08): 31-38.doi: 10.3969/j.issn.1006-2475.2025.08.005

• 人工智能 • 上一篇    下一篇

用户评论数据中城市街区细粒度主观感知发现

  


  1. (1.沈阳建筑大学计算机科学与工程学院,辽宁 沈阳 110168; 2.辽宁省城市建设大数据管理与分析重点实验室,辽宁 沈阳 110168; 3.国家特种计算机工程技术研究中心沈阳分中心,辽宁 沈阳 110168)
  • 出版日期:2025-08-27 发布日期:2025-08-27
  • 作者简介: 作者简介:孙焕良(1969—),男,黑龙江望奎人,教授,博士生导师,博士,CCF会员,研究方向:空间数据管理,数据挖掘,E-mail: sunhl@sjzu.edu.cn; 通信作者:李宇航(1999—),女,黑龙江鹤岗人,硕士研究生,CCF学生会员,研究方向:数据挖掘,表示学习,E-mail: 1255696226@qq.com; 刘俊岭(1972—),辽宁沈阳人,副教授,博士,CCF会员,研究方向:空间数据挖掘,人工智能; 许景科(1976—),男,辽宁海城人,教授,博士,CCF会员,研究方向:时空数据库和数据挖掘。
  • 基金资助:
     基金项目:国家自然科学基金资助项目(62073227); 国家重点研发计划课题(2021YFF0306303); 辽宁省教育厅项目(LJKMZ20220916, JYTMS20231596)
       

Discovery of Fine-grained Subjective Perception of Urban Blocks in User Comment Data


  1. SUN Huanliang1,2, LI Yuhang1,2, LIU Junling1,2, XU Jingke1,2,3
  • Online:2025-08-27 Published:2025-08-27

摘要: 摘要:城市街区的主观感知作为评估城市建设与规划的重要维度之一,合理分析街区与主观感知的联系将有助于打造更人性化和宜居的城市空间。本文基于表示学习技术,结合用户评论内容来发现街区与主观感知间的结构特征,并解决了现有街区感知粒度粗、数据缺失等问题。首先,提出一种细粒度感知类别体系,通过分析感知词典与POI (Points of Interest)用户评论数据,采用LDA分析主题词并结合层次聚类构建细粒度的街道感知类别;其次,针对数据不完整问题,设计相似度加权的k近邻填充方法,通过大类、小类、地理位置等信息有效地补充了缺失的POI评价内容;最后,采用自编码器将街区感知转化为潜在的特征向量。利用北京的真实数据集,针对街区房价进行分级排序、实验评估,验证所提出方法的有效性。



关键词: 关键词:城市感知, 细粒度感知, 缺失值填充, 表示学习, KNN

Abstract: (1. School of Computer Science and Engineering, Shenyang Jianzhu University, Shenyang 110168, China;
2. Liaoning Provincial Key Laboratory of Big Data Management and Analysis for Urban Construction, Shenyang 110168, China;
3. Shenyang Branch of National Special Computer Engineering Technology Research Center, Shenyang 110168, China)
Abstract: As one of the important dimensions for evaluating urban construction and planning, the subjective perception of urban blocks will help to create a more humane and livable urban space. Based on the representation learning technology and combined with the content of user comments, this paper discovers the structural characteristics between the neighborhood and the subjective perception, and solves the problems of coarse granularity and lack of data in the existing neighborhood perception. Firstly, a fine-grained perception category system is proposed, which analyzes the perception dictionary and POI (Points of Interest) user comment data, analyzes the subject words by LDA and combined with hierarchical clustering to construct a fine-grained street perception category. Secondly, in order to solve the problem of incomplete data, a similarity-weighted k-nearest neighbor filling method is designed, which effectively supplementes the missing POI evaluation content through the information of large category, small category, and geographical location. Finally, the autoencoder is used to transform the neighborhood perception into potential feature vectors. The real dataset of Beijing is used to evaluate the grading and ranking of housing prices in the neighborhood, and the effectiveness of the proposed method is verified.

Key words: Key words: urban perception, fine-grain perception, missing value padding, representation learning, KNN

中图分类号: