NextLocLLM:利用 LLM 进行位置语义建模与基于坐标的下一位置预测
NextLocLLM: Location Semantics Modeling and Coordinate-Based Next Location Prediction with LLMs
AI总结:
本文提出 NextLocLLM,将下一位置预测转化为坐标回归,利用 LLM 编码 POI 功能语义并统一预测坐标,在监督与零样本城市迁移实验中均优于基线。
摘要:
下一位置预测是人类移动性分析中的一项关键任务。现有方法通常将其构建为基于离散位置 ID 的分类任务,这阻碍了空间连续性建模,并限制了向新城市的泛化能力。本文提出 NextLocLLM,这是一种新颖框架,将下一位置预测重新表述为坐标回归,并整合 LLM 同时用于位置语义编码和坐标级预测。为建模位置功能语义,该框架利用 LLM 的语言理解能力,从 POI 类别的文本描述中提取功能语义,从而构建 LLM 增强的 POI 嵌入。这些 POI 嵌入与时空轨迹表示相结合,并输入同一个 LLM,从而实现统一的语义与预测建模。一个轻量级回归头生成坐标输出,这些输出再通过预测后检索模块映射到 top-k 候选位置,以确保结构化输出。在多个不同城市进行的实验表明,NextLocLLM 在监督和零样本设置下均优于现有基线。代码可在 https://github.com/liuwj2000/NexelocLLM 获取。
英文摘要:
Next location prediction is a critical task in human mobility analysis.Existing methods typically formulate it as a classification task based on discrete location IDs, which hinders spatial continuity modeling and limits generalization to new cities. In this paper, we propose NextLocLLM, a novel framework that reformulates next-location prediction as coordinate regression and integrates LLMs for both location semantics encoding and coordinate-level prediction. To model location functional semantics, it constructs LLM-enhanced POI embeddings by leveraging language understanding capabilities of LLMs to extract functional semantics from textual descriptions of POI categories. These POI embeddings are combined with spatiotemporal trajectory representation and fed into the same LLM, enabling unified semantic and predictive modeling. A lightweight regression head generates coordinate outputs, which are mapped to top-k candidate locations via post-prediction retrieval module, ensuring structured outputs. Experiments across diverse cities show that NextLocLLM outperforms existing baselines in both supervised and zero-shot settings. Code is available at: https://github.com/liuwj2000/NexelocLLM.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。