SPAR：通过真实世界空间感知增强工业级生成式兴趣点推荐

中文摘要 AI 辅助

生成式兴趣点（POI）推荐通过自回归方式生成目标POI的语义ID（SID），在基于位置的服务中具有巨大应用潜力，这类服务中只有当用户能够到达推荐的POI时，推荐才具有实际意义。然而，现有方法仅在由行为序列和协同信号定义的兴趣空间中运行，地理信息仅作为SID的文本属性被纳入，缺乏明确的机制来学习或保留城市场所之间的距离、方向和可达性关系，因此其预测结果在行为层面看似合理，但与用户的实时实际位置相差甚远。我们认为这类服务需要将真实的城市空间知识注入兴趣空间，而非仅从行为中推断地理信息。为此，我们提出了SPAR，这是一个统一框架，其三个协同阶段共同构建、培育和保留城市空间知识：（1）在分词层面，空间内在SID（SI-SID）将经纬度坐标显式编码为正弦地理空间嵌入，并与文本语义嵌入融合，通过RQ-Kmeans生成在语义和地理上一致的标识符；（2）在认知层面，多粒度地理空间条件预训练转换器（MG-CPT）在25个精心整理的地理空间数据集上对基础大语言模型（LLM）进行持续预训练，这些数据集分为基础属性、成对关系和城市规模导航三个层级，使分散的POI形成连通的城市空间；（3）在适应层面，任务向量锚定的微调（TV-SFT）将获取的空间知识作为冻结的参数空间任务向量进行锚定，以防止在行为微调过程中出现灾难性遗忘，从而实现两个空间的融合。在两个公共数据集和四个工业级数据集上进行的大量定量与可视化实验验证了SPAR的有效性。

英文摘要

Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's semantic ID (SID), holds great promise for Location-Based Services, where a recommendation helps only if the user can reach it. Yet, existing methods operate within an interest space defined by behavior sequences and collaborative signals, where geography enters only as a textual attribute of the SID, leaving no explicit mechanism to learn or preserve how urban places are related by distance, direction, and reachability; their predictions are thus behaviorally plausible yet far from the user's real-time location. We argue that such services require injecting real urban spatial knowledge into the interest space, rather than inferring geography from behavior alone. Hence, we propose SPAR, a unified framework whose three synergistic stages jointly construct, cultivate, and preserve urban spatial knowledge: (1) at the tokenization level, Spatially-Intrinsic SID (SI-SID) explicitly encodes longitude--latitude coordinates into a sinusoidal geospatial embedding and fuses it with the textual semantic embedding, producing identifiers via RQ-Kmeans that are simultaneously semantically and geographically consistent; (2) at the cognition level, Multi-Granular Geospatial CPT (MG-CPT) continually pre-trains the base LLM on 25 curated geospatial datasets organized into three tiers of basic attributes, pairwise relations, and city-scale navigation, so that scattered POIs cohere into a connected urban space; and (3) at the adaptation level, Task-Vector Anchored SFT (TV-SFT) anchors the acquired spatial knowledge as a frozen parameter-space task vector to prevent its catastrophic forgetting during behavioral fine-tuning, thereby fusing the two spaces. Extensive quantitative and visualization experiments on two public and four industrial-scale datasets demonstrate the effectiveness of SPAR.

发表机构

• AMAP, Alibaba Group（高德，阿里巴巴集团）
• The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

机构由 AI 辅助整理，请以论文原文为准。