Loading and unloading point recommendation method and device based on graph neural network

Abstract

The present application relates to a graph neural network-based loading and unloading point recommendation method, device, computer equipment and storage medium. The method includes: constructing a point-of-interest map based on geographical location information, a loading and unloading point map based on geographical location information, and an interactive map of point-of-interest loading and unloading points; Fusion to obtain the representation vector of the point of interest that fuses the interaction information and geographic location information; the fusion of the loading and unloading point representation vector based on the interaction information and the loading and unloading point representation vector based on the geographic location information to obtain the loading and unloading point representation that fuses the interaction information and geographic location information Vector; the point of interest representation vector fused with interactive information and geographic location information and the loading and unloading point characterization vector fused with interactive information and geographic location information are input into the graph neural network for recommendation, which can greatly improve the accuracy of the recommendation of loading and unloading points. Reliable, more intelligent, efficient, reasonable, and widely applicable.

Description

technical field [0001] The present application relates to the field of loading and unloading point recommendation, in particular to a graph neural network-based loading and unloading point recommendation method, device, computer equipment and storage medium. Background technique [0002] Nowadays, users place orders on the APP platform, and the point of interest (POI) placed by some order users is far away from the actual loading and unloading point of the user. The driver’s user experience is poor. In order to improve the efficiency of the driver’s cargo meeting, reduce the cost of meeting, improve the experience of drivers and users on the platform, and allow more drivers and users to choose and save on the platform, a smarter method based on the user’s order of interest is needed. Recommended solution for loading and unloading points. [0003] Collaborative filtering is a method widely used in recommendation systems. Its basic idea is to find other points of interest sim...

AI Technical Summary

Problems solved by technology

With the development of word embedding technology, many methods embed the feature information describing interest points and loading and unloading points as the representation vectors of interest points and loading and unloading points, and capture the characteristics of interest points and loading and unloading points. However, the unloading point of this method Point recommendation is not effective, affecting driver and user experience

Images