Online car-hailing demand prediction method based on convolutional network and non-local network

Abstract

The invention discloses an online car-hailing demand prediction method based on a convolutional network and a non-local network. Local spatial features can be extracted by using the convolutional neural network, and global spatial features can be extracted by using the non-local network. A convolutional neural network model and a non-local network model are respectively established for online car-hailing historical demand tensors corresponding to a previous moment of a current moment, the same moment of a previous day and the same moment of a previous week, then modeling is performed on time and weather characteristics, label coding is performed on time data and weather data, then one-hot coding is performed, finally, each time period corresponds to one k-dimensional vector, a full-connection neural network is built, the k-dimensional vectors serve as input and are sent into a two-layer full-connection neural network, and the output shape of the k-dimensional vectors is made to be the same as the shape of a space grid. And finally, the models are fused by using a Hadamard product to complete online car-hailing demand prediction. According to the method, the urban online car-hailing demand prediction precision can be remarkably improved, and the calculation efficiency is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a method for forecasting online car-hailing demand. Background technique [0002] The data-driven online car-hailing demand prediction model is one of the most important innovative applications in the development of intelligent transportation. At present, there are several methods of predicting future online car-hailing demand based on historical user taxi data. Specifically, these existing methods are based on statistical analysis forecasting methods to establish time series models, or based on machine learning or deep learning. into a supervised learning problem. The above methods have achieved satisfactory accuracy in some aspects, but there are some defects. First of all, other characteristics such as space and weather are not considered, and historical data is simply used to build a model to predict the future demand for online car-hailing. This will make...

AI Technical Summary

Problems solved by technology

First of all, other characteristics such as space and weather are not considered, and historical data is simply used to build a model to predict the future demand for online car-hailing. This will make it difficult to predict the demand for online car-hailing in some special circumstances (such as sudden changes in weather and holidays).

In addition, multi-layer network stacking with deep learning can easily lead to gradient explosion or gradient disappearance, and the model has a large amount of calculation and poor interpretability

Images