Traffic jam emergency disposal method based on dynamic risk field

By building a dynamic risk field model, combining physical drive and data drive methods, the real-time, computing efficiency and interpretability problems of traffic congestion prediction are solved, high-precision and low-latency traffic risk quantification and early warning are achieved, edge equipment deployment is supported, and hardware resource occupation and deployment costs are reduced.

CN120388471AActive Publication Date: 2025-07-29CHANGCHUN INST OF TECH
8 Cites 2 Cited by

Patent Information

Application Number
CN202510590862.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-08
Publication Date
2025-07-29
Estimated Expiration
2045-05-08

AI Technical Summary

Technical Problem

The existing traffic congestion prediction methods have shortcomings in real-time, computing efficiency, generalization ability and interpretability, and it is difficult to dynamically adapt to traffic flow changes and emergencies, and the model is complex and the hardware resources are used too much.

Method used

Build an emergency response method for traffic congestion based on dynamic risk fields. By integrating physically driven risk field theory and data-driven deep learning, adopting a lightweight computing framework and a spatial-temporal parallel architecture, realizing dynamic parameter updates and multi-source data fusion, and optimizing model response time and accuracy.

Benefits of technology

It realizes high-precision and low-latency traffic risk quantification and early warning, supports edge device deployment, improves the real-time, generalization and interpretability of the model, and reduces hardware resource occupation and deployment costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a traffic jam emergency disposal method based on a dynamic risk field. The method comprises the following steps: step (1), carrying out data acquisition and preprocessing; (2) calculating a basic risk field; (3) calculating a comprehensive risk field; (4) calculating the influence of a specific event or condition on the risk field; and (5) calculating the influence of the dynamic driving behavior on the risk field. According to the method, the technical bottlenecks of a traditional prediction method in the aspects of real-time performance, calculation efficiency, generalization ability, interpretability and the like are solved, and collaborative optimization of real-time performance improvement, calculation resource optimization, generalization ability enhancement, low data dependence, space risk quantification, interpretability optimization, hardware compatibility, energy saving performance and safety performance is achieved.
Need to check novelty before this filing date? Find Prior Art