Method and device for determining arrival point, and program product

Abstract

The embodiment of the invention discloses an arrival point determination method and device and a program product, and the method comprises the steps: obtaining multi-dimensional information corresponding to a POI, and the multi-dimensional information comprises the following types of information: attribute information of the POI, track type information, road network type information, building contour type information and remote sensing image type information; performing feature extraction on the multi-dimensional information to obtain multi-dimensional feature information; extracting multi-dimensional features from the multi-dimensional feature information based on a feature extraction layer in a prediction model; and inputting the multi-dimensional features into an output layer in the prediction model, executing the output layer, and outputting an arrival point region corresponding to the POI by the output layer. According to the technical scheme, the reachability between the arrival point and the POI can be considered, and the arrival point area which is easier to arrive at the POI is provided for the user.

Description

technical field [0001] The embodiments of the present disclosure relate to the technical field of geographic information processing, and in particular, to a method, an apparatus, and a program product for determining an arrival point. Background technique [0002] The development of technologies such as autonomous driving, robotic logistics and distribution, and online car-hailing distribution is an important driving force for improving the efficiency of urban operations. How to accurately determine the location of the arrival point and accurately distribute the passengers or goods to the destination is the bottleneck of vehicle navigation and logistics distribution efficiency improvement, and the key to solving the problem of the last mile of traffic and logistics. [0003] The existing arrival point recommendation method mainly finds a matching POI (Point of Interest) according to the end point information input by the user, and takes the street closest to the POI as a pot...

AI Technical Summary

Problems solved by technology

The above method has the advantages of fast query speed, high calculation efficiency, and high system integration, but it ignores the availability between the arrival point and the POI, which will easily cause a large deviation between the determined arrival point and the user's real destination. Large, such as the determined arrival point is located on the back / side of the POI or outside the fence in front of the POI and other places that cannot be directly reached, etc.

Images