{"type":"ScholarlyArticle","title":"TrajCogn: Leveraging LLMs for Cognizing Movement Patterns and Travel Purposes from Trajectories","authors":[{"name":"Zeyu Zhou","slug":"zeyu-zhou","given":"Zeyu","family":"Zhou","affiliation":""},{"name":"Yan Lin","slug":"yan-lin","given":"Yan","family":"Lin","affiliation":""},{"name":"Haomin Wen","slug":"haomin-wen","given":"Haomin","family":"Wen","affiliation":""},{"name":"Shengnan Guo","slug":"shengnan-guo","given":"Shengnan","family":"Guo","affiliation":""},{"name":"Jilin Hu","slug":"jilin-hu","given":"Jilin","family":"Hu","affiliation":""},{"name":"Youfang Lin","slug":"youfang-lin","given":"Youfang","family":"Lin","affiliation":""},{"name":"Huaiyu Wan","slug":"huaiyu-wan","given":"Huaiyu","family":"Wan","affiliation":""}],"abstract":"Spatio-temporal trajectories are crucial for data mining tasks, requiring versatile learning methods that can accurately extract movement patterns and travel purposes. While large language models (LLMs) have shown remarkable versatility through training on extensive datasets, and trajectories share similarities with natural language, standard LLMs cannot directly handle spatio-temporal features or extract trajectory-specific information.\r\nWe propose TrajCogn, a model that effectively adapts LLMs for trajectory learning. TrajCogn incorporates a novel trajectory semantic embedder to process spatio-temporal features and extract movement patterns and travel purposes, along with a trajectory prompt that integrates this information into LLMs for various downstream tasks. Experiments on three real-world datasets and four representative tasks demonstrate TrajCogn's effectiveness.","doi":"10.24963/ijcai.2025/411","url":"https://ijcai.org/proceedings/2025/411","pdf":"https://ijcai.org/proceedings/2025/0411.pdf","markdown":"https://ijcai.org/proceedings/2025/411.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/411","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":411,"pages":{"first":3698,"last":3706},"keywords":["Data Mining: DM: Mining spatial and/or temporal data"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}