随着精细化城市治理需求的不断提升，依赖单一数据源或粗粒度土地利用分类的方法已难以满足实际需求。为此，本文提出一种基于地块级别的细粒度土地利用识别模型——三元交互注意力网络（TIA-Net）。TIA-Net融合遥感影像（RSI）、兴趣点（POI）语义信息以及时空人口密度（TPD）数据。采用Swin-BiFPN提取遥感影像的多尺度空间特征。

With the increasing demand for refined urban management, methods that rely on a single data source or coarse-grained land use classification are no longer sufficient. Therefore, this article proposes a parcel-level fine-grained land use recognition model, called the triple interaction attention network (TIA-Net). TIA-Net integrates remote sensing imagery (RSI), semantic information of points of interest (POI), and temporal population density (TPD). Swin-BiFPN is used to extract multiscale spatial features from RSI.