Intelligent bus scheduling method and system

• Main Authors: HE JIAN, LIU FEI, ZHANG BIN, YANG TAO, MIAO YUN, WEI PENG, HUANG BING, JIANG ZHENG, ZHANG RONGGANG, YANG MENGMENG
• Format: Patent
• Language: Chinese; English
• Published: 08.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SIGNALLING; TRAFFIC CONTROL SYSTEMS

The invention relates to the technical field of bus scheduling, in particular to an intelligent bus scheduling method and system, and the method comprises the following steps: carrying out the time sequence analysis based on real-time traffic monitoring data and historical traffic flow data through employing a long-short-term memory network and a convolutional neural network, and processing and learning a traffic data mode; and identifying the trend and periodic change of the traffic flow, and generating a traffic flow prediction model. According to the method, the long-short-term memory network and the convolutional neural network are applied, traffic flow prediction is more accurate, changes and periodic fluctuations are captured and reflected in real time, an urban traffic network is analyzed and key nodes and fragile road sections are identified by utilizing a graph theory and network science, and a support vector machine and a decision-making tree algorithm are combined, so that potential congestion can