首页> 外国专利> DEMAND FORECAST DEVICE FOR PASSENGER VEHICLES, DEMAND FORECAST METHOD FOR PASSENGER VEHICLES, AND PROGRAM

DEMAND FORECAST DEVICE FOR PASSENGER VEHICLES, DEMAND FORECAST METHOD FOR PASSENGER VEHICLES, AND PROGRAM

机译:客运车辆的需求预测装置,客运车辆的需求预测方法以及程序

摘要

PROBLEM TO BE SOLVED: To provide a demand forecast device, etc., for passenger vehicles with which it is possible to perform highly accurate demand forecast for efficiently allocating vehicles while observing predetermined departure and arrival times.;SOLUTION: A demand forecast device for passenger vehicles of an embodiment includes a reservation prediction count acquisition unit. The reservation prediction count acquisition unit acquires, for each of prescribed periods, reservation prediction counts equivalent to reservation counts that may hold true in the future as boarding and alighting reservations for passenger vehicles in a plurality of prescribed areas, using a model with a neural network having been machine learned using, as input data, reservation data that indicates a reservation state when a reservation for a passenger vehicle is confirmed, movement data that indicates an area where an end user actually boarded and alighted on the day of operation of the passenger vehicle, and cause-of-boarding and alighting data that includes data that may be the cause of boarding and alighting of the end user on the day of operation of the passenger vehicle.;SELECTED DRAWING: Figure 1;COPYRIGHT: (C)2020,JPO&INPIT
机译:要解决的问题:为乘用车提供需求预测装置等,通过该装置可以执行高精度的需求预测,以便在遵守预定的出发和到达时间的同时有效地分配车辆。一个实施例的车辆包括预约预测计数获取单元。预约预测计数获取单元使用神经网络模型,针对每个规定时间段获取与将来可能适用的预约计数相等的预约预测计数,该预约计数作为多个规定区域中的乘用车上下车预约。已经使用表示当确认对乘用车的预订时的预订状态的预订数据,表示在乘用车的工作日最终用户实际上下车的区域的运动数据作为输入数据而机器学习;以及登机原因和下车数据,其中包括可能是在乘用车运营之日最终用户登机和下车的原因的数据。;选定的图纸:图1;版权:(C)2020,日本特许厅

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号