文旅场景交通流量时间序列预测方法、装置、设备、存储介质及程序产品
By combining KAN networks and SICM modules with graph convolutional networks, the accuracy problem of traffic flow prediction in cultural and tourism scenarios is solved, achieving precise capture of tourist flow characteristics and efficient support for traffic management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 湖南工商大学
- Filing Date
- 2025-07-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing traffic flow prediction technologies are ill-suited to the "tidal" traffic changes and sudden congestion on roads surrounding cultural and tourism sites. They fail to accurately capture the complex characteristics of tourist flow, impacting the efficiency of visitor flow management and surrounding traffic control in cultural and tourism sites.
The KAN network module is used to extract feature information, and the SICM module is combined to capture local and long-distance dependency features through convolutional attention and multi-head attention mechanisms. A graph structure is constructed for spatial feature analysis, and the weights are optimized through a graph convolutional network to finally generate traffic flow time series prediction results.
Accurately capture the spatiotemporal characteristics of tourist flow in cultural and tourism scenarios, improve the accuracy of traffic flow prediction, meet the dynamic and high-concurrency traffic management needs, and improve the efficiency of passenger flow guidance and traffic management.
Smart Images
Figure CN121010036B_ABST