Under the macro background of the rural revitalization strategy and urban-rural integrated development, rural settlements are undergoing a profound transformation from physical morphology to functional connotation. However, existing studies mainly focus on the expansion of single land elements, lacking long-term quantitative monitoring of the coupling relationship between rural development and policy texts. Taking Fuzhou City as a case study, this research selects long-term Global Human Settlement Layer (GHSL) and Night-Time Light (NTL) data from 1990 to 2025, combined with policy text quantification methods. Based on rural development units, the Coupling Coordination Degree Model (CCDM), Macro-Micro Matching Index (MMI), and gravity center migration analysis are employed to systematically reveal the spatiotemporal evolution characteristics and driving mechanisms of rural settlement morphology under policy institutional changes. The research results indicate that: (1) Fuzhou’s rural settlements exhibit relatively stable gravity centers of construction land, while the gravity center of economic vitality has significantly shifted toward the southeastern coastal area under policy guidance; (2) The coupling coordination degree of rural human–land relationships has generally increased, but with significant spatial heterogeneity, forming a pattern of high-quality coordination in coastal areas and low-efficiency lag in mountainous regions; (3) The shift in policy orientation from scale expansion to functional enhancement has driven economic factors to concentrate in key policy areas ahead of physical spatial expansion. The analytical framework combining remote sensing monitoring and policy quantification constructed in this study reveals the precedence of factor flow and the lag of physical space driven by policies, providing a scientific basis for the differentiated governance of rural areas in coastal mountainous cities.

Classical Chinese poetry preserves long-term cultural memory of built space, but large-scale evidence for differences among pavilion-related built-form families remains limited. We assembled an auditable Sou-yun corpus of 371,918 poems, identified 259,342 valid references to tíng, tái, lóu, gé, and compound forms, and extracted structured semantic profiles for 247,574 poems through a rule–ML–LLM workflow. Effect-size sensitivity tests, dated Qwen reruns, DeepSeek cross-model replication, and independent blinded coding by two non-author experts supported retrieval validity and the main prototype assignments. The five prototype groups showed distinct aggregate profiles: Tíng emphasized pause and close-range garden or waterside experience; Tái emphasized elevation, ritual and commemoration; Lóu emphasized ascent, distant view and river–urban atmosphere; Gé emphasized interior refinement; and the Compound group emphasized multi-trigger scenic assemblages. A site-specific demonstration using 1195 Yellow Crane Tower records translated the Lóu profile into traceable themes for museum interpretation and digital heritage applications.