The invention relates to a hybrid neural network training method, a traffic flow prediction method, computer equipment, a storage medium and a computer program product. According to the method, a hybrid neural network comprising an LSTM module and a first self-attention mechanism module is used, the LSTM module is coupled with the first self-attention mechanism module, and the first self-attention mechanism module comprises an attention matrix subjected to dimension reduction mapping processing; and after the traffic flow data of the plurality of road network nodes are obtained, inputting the traffic flow data into the hybrid neural network for training to obtain the trained hybrid neural network. The problems of high time complexity and low traffic flow prediction efficiency when a machine learning method is used for learning complex spatial-temporal correlation of traffic flow data in related technologies are solved, and the traffic flow prediction efficiency is improved.
本申请涉及一种混合神经网络训练方法、交通流预测方法、计算机设备、存储介质和计算机程序产品。所述方法通过使用包括LSTM模块和第一自注意力机制模块的混合神经网络,其中,LSTM模块和第一自注意力机制模块耦接,第一自注意力机制模块包含有经降维映射处理的注意力矩阵,在获取多个道路网络节点的交通流数据之后将交通流数据输入到混合神经网络中进行训练,得到训练后的混合神经网络。解决了相关技术中利用机器学习方法学习交通流数据复杂的时空相关性时存在时间复杂度较高,交通流预测效率较低的问题,提升了交通流预测的效率。
Hybrid neural network training method, traffic flow prediction method, equipment and medium
混合神经网络训练方法、交通流预测方法、设备和介质
2022-07-12
Patent
Elektronische Ressource
Chinesisch
Neural network training method, traffic flow prediction method, device, equipment and medium
Europäisches Patentamt | 2024
|Traffic flow prediction model training method, traffic flow prediction method, device and equipment
Europäisches Patentamt | 2023
|Traffic flow prediction method and device based on hybrid neural network, and medium
Europäisches Patentamt | 2023
|Traffic flow prediction method based on neural network
Europäisches Patentamt | 2020
|Short traffic flow prediction method based on ARIMA and LSTM hybrid neural network
Europäisches Patentamt | 2021
|