Road condition predicting method and apparatus, computer device and readable medium

A computer device, wherein the device comprises:

• one or more processors,
• a memory for storing one or more programs,
• the one or more programs, when executed by said one or more processors, enabling said one or more processors to implement the following operation:
• obtaining N-order neighboring roads of a target road in a road network;
• respectively obtaining feature information of the target road at a current time instant and feature information of N-order neighboring roads of the target road, the feature information including road conditions at the current time instant and road conditions at at least one historical time instant;
• predicting road conditions of the target road at a preset future time instant according to the feature information of the target road at the current time instant, the feature information of the N-order neighboring roads of the target road and a pre-trained road condition predicting model,
• wherein the pre-trained road condition predicting model is configured for:
• performing recurrent processing for each of the N-order neighboring roads after performing convolution processing for each of the N-order neighboring roads;
• max-pooling processing for a result of the recurrent processing, so as to constitute a synthetic matrix for each of the N-order neighboring roads;
• concatenating synthetic matrixes of upstream neighboring roads of the N-order neighboring roads to obtain an upstream synthetic matrix;
• concatenating synthetic matrixes of downstream neighboring roads of the N-order neighboring roads to obtain a downstream synthetic matrix;
• processing the feature information of the target road by a Fully Connected (FC) operation, to obtain a target matrix corresponding to the target road;
• and
• predicting road conditions of the target road at different future time instants based at least on the upstream synthetic matrix, the downstream synthetic matrix, the target matrix corresponding to the target road, and respective parameters of the different future time instants.

A non-transitory computer readable medium on which a computer program is stored, wherein the program, when executed by the processor, implements the following operation:

• obtaining N-order neighboring roads of a target road in a road network;
• respectively obtaining feature information of the target road at a current time instant and feature information of N-order neighboring roads of the target road, the feature information including road conditions at the current time instant and road conditions at at least one historical time instant;
• predicting road conditions of the target road at a preset future time instant according to the feature information of the target road at the current time instant, the feature information of the N-order neighboring roads of the target road and a pre-trained road condition predicting model,
• wherein the pre-trained road condition predicting model is configured for:
• performing recurrent processing for each of the N-order neighboring roads after performing convolution processing for each of the N-order neighboring roads;
• max-pooling processing for a result of the recurrent processing, so as to constitute a synthetic matrix for each of the N-order neighboring roads;
• concatenating synthetic matrixes of upstream neighboring roads of the N-order neighboring roads to obtain an upstream synthetic matrix;
• concatenating synthetic matrixes of downstream neighboring roads of the N-order neighboring roads to obtain a downstream synthetic matrix;
• processing the feature information of the target road by a Fully Connected (FC) operation, to obtain a target matrix corresponding to the target road;
• and
• predicting road conditions of the target road at different future time instants based at least on the upstream synthetic matrix, the downstream synthetic matrix, the target matrix corresponding to the target road, and respective parameters of the different future time instants.