一种信号系统轨旁设备评估方法及预算评估方法
By building a model using text and image recognition technology, the number of trackside equipment can be extracted directly from the design documents, solving the problem of low efficiency in estimating trackside equipment in existing technologies and enabling fast and accurate equipment quantity assessment and budget calculation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TRAFFIC CONTROL TECH CO LTD
- Filing Date
- 2023-11-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for estimating trackside equipment involve a large workload, long estimation cycle, high requirements for personnel professional skills, and low input-output ratio, making it difficult to efficiently assess the number of trackside equipment in signaling systems.
The model is constructed using text recognition and image recognition technologies. The feature recognition model is trained using natural language processing and convolutional neural networks. The number set of trackside equipment is directly extracted from the design requirements document. A linear regression model is used to fit the relationship between features and equipment quantity to achieve fast and accurate budget assessment.
It eliminates the need for drawing equipment layout plans, simplifies professional requirements, improves estimation efficiency, lowers the technical threshold for professionals, and enables rapid and accurate trackside equipment budget assessment.
Smart Images
Figure CN117829923B_ABST