摘要
为解决铁路客流预测结果准确度受外部客观环境变化因素影响较大、传统客流预测模型结果准确度难以进一步有效提升的问题,提出基于大语言模型的铁路客流预测优化方法,借助DeepSeekR1模型高效的文字阅读、内容检索和信息整合能力,定时筛选天气、特殊事件等影响客流的重点外部事件,并将其作为建模要素加入到客流预测模型当中,有效提升模型预测准确率。经北京—上海实际铁路客流数据验证,引入大语言模型的客流预测模型相较于传统时序预测模型的平均百分比绝对误差减少了5.5%,且能够有效避免临时性外部事件所导致的预测异常,在客流预测工作中有良好的应用效果。
To solve the problem that the accuracy of railway passenger flow forecasting results was greatly affected by external objective environmental changes,and the accuracy of traditional passenger flow forecasting models was difficult to further improve effectively,this paper proposed an optimization method for railway passenger flow forecasting based on large language model.With the efficient text reading,content retrieval,and information integration capabilities of the DeepSeek-R1 model,the paper regularly screened key external events such as weather and special events that affect passenger flow,and added them as modeling key elements to the passenger flow forecasting model,effectively improved the accuracy of the model forecasting.Verified by actual railway passenger flow data from Beijing to Shanghai,the passenger flow forecasting model introduced with the large language model has reduced the average percentage absolute error by 5.5%compared to traditional time series forecasting models,and can effectively avoid forecasting anomalies caused by temporary external events.It has a good application effect in passenger flow forecasting work.
作者
孔德越
张理臻
程默
王彦驰
王洪业
KONG Deyue;ZHANG Lizhen;CHENG Mo;WANG Yanchi;WANG Hongye(Postgraduate Department,China Academy of Railway Sciences,Beijing 100081,China;Department of Passenger Transpot,China Railway Beijing Group Co.Ltd.,Beijing 100860,China;Institute of Computing Technologies,China Academy of Railway Sciences Corporation Limited,Beijing 100081,China)
出处
《铁路计算机应用》
2025年第6期65-69,共5页
Railway Computer Application
基金
中国国家铁路集团有限公司科技研究开发计划课题(P2023S006)。
关键词
铁路客流预测
大语言模型
自回归积分滑动平均模型
DeepSeek-R1模型
外部感知
railway passenger flow forecasting
large language model
Auto Regressive Integrated Moving Average(ARIMA)model
DeepSeek-R1 model
external perception
