Port state identification method, device, equipment, medium and product

By using an improved Yolov5 model to identify ODF port status, the problems of low efficiency and poor accuracy in ODF port detection have been solved, achieving fast and accurate port status identification, reducing costs, and facilitating the transition to machine detection.

CN121585249APending Publication Date: 2026-02-27CHINA MOBILE GROUP JIANGSU +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202511772071.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-28
Publication Date
2026-02-27

AI Technical Summary

Technical Problem

ODF port detection suffers from problems such as severe obstruction, overlapping target frames, numerous plug types, inconsistent colors, and insufficient lighting in the equipment room. These issues result in low efficiency and poor accuracy of manual inspection, inconsistencies between the system and on-site port resources, and high costs associated with RFID, making it unsuitable for large-scale applications.

Method used

An improved Yolov5 model is used for ODF port status identification. The pre-trained improved Yolov5 model is used to identify ODF image data, and a multi-head self-attention mechanism is used to enhance network performance to identify the idle, occupied and unknown states of ODF ports.

Benefits of technology

It achieves fast and accurate ODF port status identification, reduces the workload of manual inspection, improves inspection efficiency and accuracy, reduces costs, realizes the transition to machine inspection, and frees up manpower.

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

Abstract

The invention discloses a port state identification method and device, equipment, a medium and a product. The method comprises the following steps: acquiring optical fiber distribution frame (ODF) picture data; the ODF picture data is recognized through a pre-trained final improved Yov5 model, a recognition result is determined, and the final improved Yov5 model comprises an improved input layer, a backbone network layer fused with a self-attention mechanism, a neck feature fusion layer and a prediction layer; the identification result comprises states of all ODF ports in the ODF picture data, and the states comprise an idle state, an occupied state and an unknown state. According to the method, the sensitive capture capability of a multi-head self-attention mechanism on remote space information is integrated into a backbone network layer, the performance of a network on a target detection task is enhanced, then ODF port recognition is carried out through an improved Yolov5 algorithm, and the state of an ODF port is quickly and accurately recognized.
Need to check novelty before this filing date? Find Prior Art