The invention discloses a parking space recommendation method and system based on a graph network, and the method comprises the steps: obtaining a parking space recommendation request; wherein the parking space recommendation request comprises the current position of the vehicle and the target position of the vehicle; preprocessing the parking space recommendation request to obtain the vector representation of the current position of the vehicle and the vector representation of the target position of the vehicle; according to the vector representation of the current position of the vehicle and the vector representation of the target position of the vehicle, searching in a pre-constructed parking space map network, and determining all feasible paths; and performing priority ranking on all the feasible paths according to different dimensions, and performing parking space recommendation according to a ranking result. When a vehicle wants to find a parking space, the system can provide the vehicle owner with the most appropriate parking space selection according to the parking space information, the distance information, the price information and the road condition information so as to find the parking space in time.
本发明公开了基于图网络的停车位推荐方法及系统,其中,所述方法包括:获取停车位推荐请求;其中,所述停车位推荐请求,包括:车辆当前位置和车辆目的位置;对停车位推荐请求进行预处理,得到车辆当前位置的向量表示和车辆目的位置的向量表示;根据车辆当前位置的向量表示和车辆目的位置的向量表示,从预先构建的停车位图网络中进行查找,确定所有可行路径;对所有可行路径,按照不同维度进行优先级排序,按照排序结果进行停车位推荐。当车辆想寻找停车位时,系统会根据车位信息、距离信息、价格信息、道路状况信息给与车主最合适的车位选择,及时寻找车位。
Parking space recommendation method and system based on graph network
基于图网络的停车位推荐方法及系统
2022-04-29
Patent
Electronic Resource
Chinese
Automatic-parking parking space detection method based on graph neural network
European Patent Office | 2021
|PARKING RECOMMENDATION METHOD AND SYSTEM FOR WIRELESS CHARGING PARKING SPACE
European Patent Office | 2022
|Parking space reservation recommendation method and system
European Patent Office | 2021
|