Extracting individual trajectories from text by fusing large language models with diverse knowledge
文献类型：期刊论文
| 作者 | Liu, Le1,2; Pei, Tao1,2,3; Fang, Zidong1,2; Yan, Xiaorui1,2; Zheng, Chenglong1,2; Wang, Xi1,2; Song, Ci1,2; Luan, Wenfei1,4; Chen, Jie1 |
| 刊名 | INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
 |
| 出版日期 | 2025-07-01 |
| 卷号 | 141页码:104654 |
| 关键词 | Large language model Human mobility trajectory Geographical information retrieval Prompt learning GeoAI |
| ISSN号 | 1569-8432 |
| DOI | 10.1016/j.jag.2025.104654 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Individual trajectories offer insights into human mobility, with data either passively recorded, such as GPS, or actively recorded, such as natural language text. While the former provides detailed movement data, it lacks important context such as personal experiences, which can be obtained from the latter. Extracting trajectories from text can enhance travel experience optimization, historical analysis, and pandemic management. However, existing trajectory extraction methods rely on rule-based frameworks that fail to capture contextual semantics, resulting in limited generalizability and loss of trajectory semantics. While general-purpose large language models (LLMs) demonstrate potential for contextual reasoning capabilities, their deficient domain-specific knowledge pertinent to trajectory patterns hinders efficient and precise trajectory extraction. To address these limitations, we propose T2TrajLLM, a novel framework that fuses LLMs with domain knowledge through three components: (1) a lightweight trajectory model for structured guidance, (2) a text-to-trajectory transformation model enabling multi-step reasoning, and (3) labelled text-trajectory samples for learning domain-adaptive constraint rules. Central to T2TrajLLM is a prompt method that dynamically fuses these components with LLMs while avoids rigid rule dependency. Evaluated across three heterogeneous datasets, T2TrajLLM achieves similar to 8 % higher accuracy than existing methods, demonstrating strong transferability across datasets and extensibility to diverse application requirements. Overall, T2TrajLLM effectively extracts trajectories from diverse textual sources, providing robust support for the analysis and understanding of individual mobility. |
| URL标识 | 查看原文 |
| WOS关键词 | RECOGNITION ; MOBILE |
| WOS研究方向 | Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:001511184200001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/214600]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Pei, Tao |
| 作者单位 | 1.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China; 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China; 3.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing 210023, Peoples R China; 4.Henan Polytech Univ, Sch Surveying & Land Informat Engn, Jiaozuo 454000, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Le,Pei, Tao,Fang, Zidong,et al. Extracting individual trajectories from text by fusing large language models with diverse knowledge[J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,2025,141:104654. |
| APA | Liu, Le.,Pei, Tao.,Fang, Zidong.,Yan, Xiaorui.,Zheng, Chenglong.,...&Chen, Jie.(2025).Extracting individual trajectories from text by fusing large language models with diverse knowledge.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,141,104654. |
| MLA | Liu, Le,et al."Extracting individual trajectories from text by fusing large language models with diverse knowledge".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 141(2025):104654. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。