Spatial transcriptomics plays a crucial role in identifying specific gene expression patterns, discovering novel cell type markers, and revealing cellular self-organization and cooperation. This article systematically classifies and reviews spatial transcriptomics data analysis methods developed in recent years based on artificial intelligence theories and techniques, each with distinct characteristics suited to different research scenarios. Through in-depth analysis of these methods, it offers a comprehensive perspective on understanding the cutting-edge analytical technologies in the field of spatial transcriptomics, promotes their application in biomedical research, and aids in exploring the spatial heterogeneity and ecological niches of cells within complex tissues.