{"title":"利用 LLM 进行跨城市外径流量预测","authors":"Chenyang Yu, Xinpeng Xie, Yan Huang, Chenxi Qiu","doi":"arxiv-2409.03937","DOIUrl":null,"url":null,"abstract":"Understanding and predicting Origin-Destination (OD) flows is crucial for\nurban planning and transportation management. Traditional OD prediction models,\nwhile effective within single cities, often face limitations when applied\nacross different cities due to varied traffic conditions, urban layouts, and\nsocio-economic factors. In this paper, by employing Large Language Models\n(LLMs), we introduce a new method for cross-city OD flow prediction. Our\napproach leverages the advanced semantic understanding and contextual learning\ncapabilities of LLMs to bridge the gap between cities with different\ncharacteristics, providing a robust and adaptable solution for accurate OD flow\nprediction that can be transferred from one city to another. Our novel\nframework involves four major components: collecting OD training datasets from\na source city, instruction-tuning the LLMs, predicting destination POIs in a\ntarget city, and identifying the locations that best match the predicted\ndestination POIs. We introduce a new loss function that integrates POI\nsemantics and trip distance during training. By extracting high-quality\nsemantic features from human mobility and POI data, the model understands\nspatial and functional relationships within urban spaces and captures\ninteractions between individuals and various POIs. Extensive experimental\nresults demonstrate the superiority of our approach over the state-of-the-art\nlearning-based methods in cross-city OD flow prediction.","PeriodicalId":501479,"journal":{"name":"arXiv - CS - Artificial Intelligence","volume":"81 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Harnessing LLMs for Cross-City OD Flow Prediction\",\"authors\":\"Chenyang Yu, Xinpeng Xie, Yan Huang, Chenxi Qiu\",\"doi\":\"arxiv-2409.03937\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Understanding and predicting Origin-Destination (OD) flows is crucial for\\nurban planning and transportation management. Traditional OD prediction models,\\nwhile effective within single cities, often face limitations when applied\\nacross different cities due to varied traffic conditions, urban layouts, and\\nsocio-economic factors. In this paper, by employing Large Language Models\\n(LLMs), we introduce a new method for cross-city OD flow prediction. Our\\napproach leverages the advanced semantic understanding and contextual learning\\ncapabilities of LLMs to bridge the gap between cities with different\\ncharacteristics, providing a robust and adaptable solution for accurate OD flow\\nprediction that can be transferred from one city to another. Our novel\\nframework involves four major components: collecting OD training datasets from\\na source city, instruction-tuning the LLMs, predicting destination POIs in a\\ntarget city, and identifying the locations that best match the predicted\\ndestination POIs. We introduce a new loss function that integrates POI\\nsemantics and trip distance during training. By extracting high-quality\\nsemantic features from human mobility and POI data, the model understands\\nspatial and functional relationships within urban spaces and captures\\ninteractions between individuals and various POIs. Extensive experimental\\nresults demonstrate the superiority of our approach over the state-of-the-art\\nlearning-based methods in cross-city OD flow prediction.\",\"PeriodicalId\":501479,\"journal\":{\"name\":\"arXiv - CS - Artificial Intelligence\",\"volume\":\"81 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.03937\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.03937","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
了解和预测始发站-目的地(OD)流量对于城市规划和交通管理至关重要。传统的出发地-目的地预测模型虽然在单个城市内有效,但由于交通状况、城市布局和社会经济因素的不同,在跨城市应用时往往面临局限性。本文采用大型语言模型(LLM),介绍了一种新的跨城市 OD 流量预测方法。我们的方法利用大型语言模型先进的语义理解和上下文学习能力,在具有不同特征的城市之间架起了一座桥梁,为准确的 OD 流量预测提供了一个稳健且适应性强的解决方案,并可从一个城市转移到另一个城市。我们新颖的框架包括四个主要部分:从源城市收集 OD 训练数据集、指导调整 LLM、预测目标城市的目的地 POI,以及识别与预测的目的地 POI 最匹配的地点。我们引入了一个新的损失函数,该函数在训练过程中将 POI 语义和行程距离整合在一起。通过从人类移动和 POI 数据中提取高质量语义特征,该模型能够理解城市空间内的空间和功能关系,并捕捉个人与各种 POI 之间的互动。广泛的实验结果表明,在跨城市 OD 流量预测方面,我们的方法优于最先进的基于学习的方法。
Understanding and predicting Origin-Destination (OD) flows is crucial for
urban planning and transportation management. Traditional OD prediction models,
while effective within single cities, often face limitations when applied
across different cities due to varied traffic conditions, urban layouts, and
socio-economic factors. In this paper, by employing Large Language Models
(LLMs), we introduce a new method for cross-city OD flow prediction. Our
approach leverages the advanced semantic understanding and contextual learning
capabilities of LLMs to bridge the gap between cities with different
characteristics, providing a robust and adaptable solution for accurate OD flow
prediction that can be transferred from one city to another. Our novel
framework involves four major components: collecting OD training datasets from
a source city, instruction-tuning the LLMs, predicting destination POIs in a
target city, and identifying the locations that best match the predicted
destination POIs. We introduce a new loss function that integrates POI
semantics and trip distance during training. By extracting high-quality
semantic features from human mobility and POI data, the model understands
spatial and functional relationships within urban spaces and captures
interactions between individuals and various POIs. Extensive experimental
results demonstrate the superiority of our approach over the state-of-the-art
learning-based methods in cross-city OD flow prediction.