Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for identifying distribution box diagram in electrical professional distribution box systematic diagram based on deep learning

A technology of deep learning and distribution boxes, applied in the direction of neural learning methods, graphics and image conversion, character and pattern recognition, etc., can solve the problem of inaccurate frame positions, deviations between the number of distribution box diagrams and the actual situation, and error-prone recognition and other issues to achieve the effect of improving the recognition accuracy

Pending Publication Date: 2022-01-07
上海品览数据科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the process of identification of electrical distribution box diagrams, due to business logic merging, the identification of the construction of distribution box diagrams is prone to errors, resulting in deviations between the number of distribution box diagrams obtained and the actual ones, and the position of the borders. Accurate, thus affecting the identification of various attributes of the subsequent distribution box diagram

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for identifying distribution box diagram in electrical professional distribution box systematic diagram based on deep learning
  • Method for identifying distribution box diagram in electrical professional distribution box systematic diagram based on deep learning
  • Method for identifying distribution box diagram in electrical professional distribution box systematic diagram based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0036] Such as Figure 1 to Figure 5 As shown, in the embodiment of the present invention, a method for recognizing the distribution box diagram in the electrical professional distribution box system diagram based on deep learning includes the following steps:

[0037] ① Model training:

[0038] 1) Data preparation: 30-40 drawings are obtained through CAD analysis to obtain the required graphic element information on the drawings, and 300-400 png pictures of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of distribution box systematic diagram identification, and discloses a method for identifying a distribution box diagram in an electrical professional distribution box systematic diagram based on deep learning, which comprises the following steps: 1, model training: 1) data preparation: carrying out CAD analysis on 30-40 drawings to obtain primitive information required on the drawings, generating 300-400 png pictures of the distribution box systematic diagram through a CAD drawing printing service; and 2) checking the distribution box systematic diagram generated by the printing service in the step 1), and marking the position of the distribution box diagram. According to the method, the marked data are trained through a YoV4 detection model to obtain subsequent deployment model parameters, and the parameters are deployed to the ai-service through the deployment model to be called by the AI time identification engine, so that the problem that due to various components, complex component combination logic and limited component identification accuracy, the number and position acquisition of the distribution box diagrams are inaccurate is solved, and the identification accuracy of the distribution box diagrams can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of time identification of distribution box system diagrams, and specifically relates to a method for recognizing distribution box diagrams in electrical professional distribution box system diagrams based on deep learning. Background technique [0002] CAD construction drawing refers to the drawing of the overall layout of the project, the external shape, internal layout, structural structure, internal and external decoration, material method, equipment, construction, etc. of the building through AutoCAD software. The existing electrical professional distribution box system drawing In the technology for obtaining the distribution box diagram in China, firstly, the basic primitives in the distribution box diagram (the primitives refer to the visible basic elements that make up the graphics, corresponding to the visible entities on the drawing interface, such as straight lines, Arcs, circles, etc., these basic...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06V30/422G06V10/82G06T5/30G06T3/40G06N3/08
CPCG06T5/30G06T3/40G06N3/08
Inventor 马玄李一帆
Owner 上海品览数据科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products