测绘学报 ›› 2023, Vol. 52 ›› Issue (4): 670-678.doi: 10.11947/j.AGCS.2023.20220026

• 地图学与地理信息 • 上一篇    下一篇

基于地理空间感知型表征学习的轨迹相似度计算

吴晨昊, 向隆刚, 张叶廷, 吴华意   

  1. 武汉大学测绘遥感信息工程国家重点试验室, 湖北 武汉 430000
  • 收稿日期:2022-01-03 修回日期:2022-07-09 发布日期:2023-05-05
  • 通讯作者: 向隆刚 E-mail:geoxlg@whu.edu.cn
  • 作者简介:吴晨昊(1995-),男,博士生,研究方向为时空数据挖掘、大规模轨迹数据分析与深度表征学习。E-mail:ngch@whu.edu.cn
  • 基金资助:
    国家自然科学基金(42071432);湖北珞珈试验室专项基金(220100010)

Geography-aware representation learning for trajectory similarity computation

WU Chenhao, XIANG Longgang, ZHANG Yeting, WU Huayi   

  1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430000, China
  • Received:2022-01-03 Revised:2022-07-09 Published:2023-05-05
  • Supported by:
    The National Natural Science Foundation of China (No. 42071432);The Special Fund of Hubei Luojia Laboratory (No. 220100010)

摘要: 度量轨迹间的相似性不仅是一项基础的研究问题,同时也为众多轨迹数据挖掘应用提供支持。传统相似性度量方法面临数据噪声敏感、算法效率低等问题,难以进行大规模数据计算。当前研究开始尝试使用深度表征学习方法,将高维轨迹数据映射到低维向量空间,通过度量表征间的距离高效地完成相似度计算任务。本文在轨迹表征学习中引入Transformer机制,提出了一种地理空间感知的深度轨迹表征学习方法。首先,使用Geohash编码将二维空间坐标点转换为一维编码序列,使轨迹点在嵌入过程中保留空间相关性。然后,引入Transformer框架构建轨迹表征的深度学习模型,并采用一种隐轨迹点训练模式,以保证模型能从低频、噪声的数据中习得更稳健的向量表示。最后,设计了一个空间感知损失函数,通过距离因子调整模型误差,拉近空间相近轨迹的表征。试验表明,本文方法在轨迹相似性计算任务中超越了基准模型,并且计算效率远高于传统度量方法。

关键词: 深度表征学习, 轨迹表征, Transformer模型, 相似性计算

Abstract: Quantifying the similarity between two trajectories is a fundamental research that underlies many trajectory-based applications. Conventional methods suffer from inefficiency and noise sensitivity, making it difficult to achieve large-scale deployments. Current researches start to explore the emerging deep representation learning method, which maps high-dimensional trajectory data to a low-dimensional vector space for efficiently performing similarity measurement by computing the distance between trajectory representations. This paper pioneers the idea of Transformer, and proposes a geography-aware deep representation learning model for trajectory similarity computation: First, the two-dimensional coordinate point is converted into a one-dimensional sequence using Geohash algorithm, which can preserve the spatial correlations of the trajectory point during the embedding. Second, a deep trajectory representation learning model is constructed based on the Transformer framework, and a masked point strategy is employed to ensure that the model can acquire robust vector representations from low-frequency, noisy data. Final, a geography-aware loss function is devised to penalize the model and narrow the representation of spatially similar trajectories via a distance factor. Experiments show that the proposed method outperforms the state-of-the-art model in the similarity measurement and is at least one order of magnitude faster than the traditional models in terms of computational efficiency.

Key words: deep representation learning, trajectory representation, Transformer model, similarity measurement

中图分类号: