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

Drawing architectural element identification method and system based on machine learning

A technology of building element identification and machine learning, applied in the field of drawing building element identification method and system, can solve problems such as affecting users' reading of drawings, analysis efficiency, effect not satisfying users, affecting the overall progress of construction, etc. The effect of high rate, improved recognition rate and high precision rate

Inactive Publication Date: 2014-02-26
HUAZHONG NORMAL UNIV
View PDF2 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, a lot of practice shows that this kind of method can't satisfy users when analyzing more complex design drawings.
For example, when a design drawing contains multiple architectural elements of the same type with different attribute parameters, some architectural elements that do not have general attribute parameters are often ignored, which confuses the readers of the drawings; in addition, pure The recognition algorithm based on rules and written for specific drawings has poor versatility due to the diversity of drawing content, or has a single function and can only recognize individual architectural elements
These problems will affect the efficiency of users' reading and analysis of drawings, and affect the overall progress of construction.

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
  • Drawing architectural element identification method and system based on machine learning
  • Drawing architectural element identification method and system based on machine learning
  • Drawing architectural element identification method and system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described below in conjunction with specific embodiments and drawings.

[0061] The technical solution adopted by the method of the present invention is: a method for identifying architectural elements of drawings based on machine learning, which includes the following steps:

[0062] Step 1: Read the basic data set of primitive elements and all the marked building element data sets from the original CAD engineering design drawings. The basic data of primitive elements include point data, line data, text data and other geometric data ; The specific implementation includes the following sub-steps:

[0063] Step 1.1: Convert the original CAD engineering design drawings to DXF engineering design drawings;

[0064] Step 1.2: Analyze the group code of the DXF engineering design drawing file to extract the basic data of the primitive. The basic data of the primitive element includes point data, line data, text data and other geometric data, there...

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 discloses a drawing architectural element identification method and system based on machine learning. The drawing architectural element identification method is based on the method of combining a rule and machine learning. Rule matching and mathematical modeling are conducted on vector diagram metainformation obtained from a drawing, the feature distribution law of an architectural element in the drawing is strictly and accurately analyzed through the training process, the data sets of a primitive database, an architectural element rule base and an architectural element feature base are formed, the architectural element identification method in the probability sense is obtained, and the recognition rate of an architectural element and a property parameter of the architectural element are further improved. The drawing architectural element identification system based on machine learning tries to break through the limitation of an existing drawing identification method, provides an efficient drawing analysis and identification tool for a metro design and construction department, and has the three advantages of being high in precision ratio, identification efficiency and intelligent degree.

Description

Technical field [0001] The invention belongs to the technical field of machine learning, and specifically relates to a method and system for recognizing drawing architectural elements based on machine learning. The method and system are based on traditional machine learning technology, and propose a recognition method that is different from the recognition of architectural elements based on image processing, which can effectively analyze and extract architectural drawings and judge the category of unknown architectural elements to be tested. Background technique [0002] With the continuous improvement of the national economic development level, in order to improve people's work efficiency and quality of life, more and more cities have already or are preparing to construct subway projects. Usually, the design unit of subway engineering projects uses mature CAD software to design corresponding engineering drawings according to the actual conditions of local geology, hydrology, etc...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/66G06F17/50
Inventor 何婷婷张勇郭喜跃王艳李鹏张明
Owner HUAZHONG NORMAL UNIV
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