An event assignment method and system based on dynamic island change

By dividing the traffic network into dynamic islands, using the improved YOLOv5s algorithm to identify vehicle distribution, selecting the two subgraphs with the highest density, and determining the distance and proportion of the subgraphs, the problem of inaccurate traffic congestion detection in existing technologies is solved, and efficient event allocation and management are achieved.

CN120932489BActive Publication Date: 2026-06-12SHANGRAO ACAD OF SCI CLOUD COMPUTING CENT BIG DATA RES INST
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANGRAO ACAD OF SCI CLOUD COMPUTING CENT BIG DATA RES INST
Filing Date
2025-05-30
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

Existing technologies cannot pinpoint specific units, such as main roads or traffic facilities, in the detection and allocation of traffic congestion events, making traffic maintenance difficult and time-consuming, and failing to meet actual needs.

⚗Method used

By acquiring urban road information, dividing dynamic islands, identifying vehicle information, performing clustering and filtering, and using an improved YOLOv5s detection algorithm to identify vehicle distribution, combined with vehicle density and lane ratio, the distance and proportion of sub-graphs are determined, and the event analysis results are pushed to the traffic management department.

🎯Benefits of technology

It enables dynamic detection and analysis of traffic congestion areas, improves the accuracy and efficiency of event detection and allocation technology, and can prevent traffic congestion in a timely manner.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120932489B_ABST
    Figure CN120932489B_ABST
Patent Text Reader

Abstract

The application provides an event distribution method and system based on dynamic island change, which comprises the following steps: acquiring urban road information, dividing the urban road according to the intelligent traffic network to obtain a plurality of regions; identifying vehicle information in the current dynamic island to obtain a vehicle distribution information map according to the identification result, clustering the vehicles according to the vehicle distribution information map to obtain a plurality of vehicle distribution maps, screening the plurality of vehicle distribution maps to obtain a first distribution subgraph and a second distribution subgraph with the top two densities in the same trunk road according to the vehicle density, identifying the first distribution subgraph and the second distribution subgraph to obtain a subgraph distance and a lane proportion of the number of lanes occupied by each distribution subgraph to the total number of lanes of the trunk road; respectively judging whether the subgraph distance is greater than a distance threshold value and whether the lane proportion is less than a proportion threshold value; if not, analyzing the distribution subgraph according to a de-clustering model, and pushing the analysis result to the traffic management department. The application improves the accuracy and efficiency of event detection and distribution technology.
Need to check novelty before this filing date? Find Prior Art