CN111553187B

CN111553187B - Method and system for identifying form in CAD drawing

Info

Publication number: CN111553187B
Application number: CN202010202020.2A
Authority: CN
Inventors: 师玉鹏
Original assignee: Glodon Co Ltd
Current assignee: Glodon Co Ltd
Priority date: 2020-03-20
Filing date: 2020-03-20
Publication date: 2023-06-02
Anticipated expiration: 2040-03-20
Also published as: CN111553187A

Abstract

The invention discloses a method for identifying a form in a CAD drawing, which comprises the steps of analyzing the characteristics of lines by an algorithm, importing an artificial intelligent model for analysis, obtaining form data according to an analysis result, and complementing or eliminating useless form lines according to requirements. According to the method, through a full-automatic algorithm for extracting the form by artificial intelligence, a user can automatically extract the form data by clicking a button, and through intelligent identification of the form information, the operation cost of the user is saved, and the accuracy and time are improved; the method is suitable for all CAD column large sample scenes, and avoids the limitation of applicability; the user only needs to trigger the identification function, the algorithm automatically performs checking calculation, and the operation is simple, convenient and quick.

Description

Method and system for identifying form in CAD drawing

Technical Field

The invention belongs to the technical field of computer information, and relates to a technology for accurately identifying a form of a column large sample in a CAD drawing, in particular to a method and a system for identifying the form in the CAD drawing by compression and blocking technology.

Background

With the development of computer technology, artificial intelligence technology has begun to be introduced into the construction industry for better convenience to users for rapid modeling. In the modeling process, the original data is analyzed through artificial intelligence, so that required information can be accurately and rapidly identified, and the waste of labor cost is avoided. How to quickly and accurately help users extract needed information is a problem that related software needs to solve.

In the existing column large sample modeling process, a budgeter is required to manually select specific column large sample information on a CAD drawing, and specific use is performed after different information types are classified. The mode is large in workload, graphic information of different drawings is complex and changeable, and no correlation can be used as a reference. Meanwhile, a large amount of errors or useless information are also present in the drawing to interfere, which is too high in cost for manual classification. It is difficult to perfectly solve using the conventional method.

In the actual drawing, the information of the column large sample is basically concentrated in the table, so that the basic position of the column large sample can be determined only after the table is identified, and the position of the column large sample can be determined without manual operation of a user, so that the preparation of the follow-up information extraction algorithm is performed.

The existing form extraction mode is that a user manually selects form lines one by one and then extracts the form lines. On the one hand, in the case of facing a large amount of table data, the number of lines is very large; meanwhile, the CAD drawing has the later picture compensating condition, so the CAD drawing looks like a straight line, and is formed by splicing a plurality of segments; there are also situations where an invalid form is connected to a column-like form, which is very cumbersome and slow for the user to extract.

Disclosure of Invention

Aiming at the defects of the background technology, the invention aims at solving the problem of how to realize intelligent and rapid form extraction.

In order to achieve the above object, the present invention provides a method for identifying a form in a CAD drawing, including:

step one, extracting digital form characteristics and establishing a training model;

step two, processing and deleting invalid digital table information;

and thirdly, supplementing the vacant digital table grid lines to the complete state.

Preferably, the first step specifically includes:

analyzing table characteristics, analyzing in an intersection mode, grouping according to line types, and obtaining the number of edges at the intersection point of all lines and the angle of each edge;

step 1.2, analyzing line group characteristics, respectively analyzing the intersection point duty ratio of different edge numbers, and determining whether the number of lines and the line type are continuous lines or not;

step 1.3, adding the colors of the table grid lines as characteristic factors for analysis;

step 1.4, obtaining the ratio of the average length of the form lines to the average length of the whole drawing as a characteristic;

and 1.5, establishing a random forest model, and training by taking the table features, the line group features, the color features and the average length features obtained in the steps 1.1-1.4 as the features of the model.

Preferably, the second step performs secondary filtering of the table grid lines according to the internal information of the table, and deletes the useless table.

Preferably, when the useless table is deleted in the step two, the text information ratio in the table is calculated, more than half of the text information ratio in all elements are reserved as a non-column large-sample table, and other tables are deleted.

Preferably, the above-mentioned step three complements the non-closed area to form a completely closed form.

Preferably, the third step is to complement the vertical line with the horizontal line if the number of the end point lines is less than 1, and the vertical line complements the horizontal line.

Preferably, the lines in step 1.1 are grouped into vertical lines and parallel lines.

Preferably, the number of the different sides in the step 1.2 includes 1, 2, 3, 4 and 5.

A system for identifying forms in CAD drawings, comprising:

the table feature extraction unit is used for extracting digital table features and establishing a training model;

the form screening and removing unit is used for processing and deleting invalid digital form information;

and the table grid line complementing unit is used for complementing the vacant digital table grid lines to the complete state.

Preferably, the table feature extraction unit includes:

the table characteristic analysis module is used for analyzing table characteristics, analyzing in an intersection mode, grouping according to line types and solving the number of edges at the intersection point of all lines and the angle of each edge;

the line group characteristic module is used for analyzing line group characteristics, respectively analyzing the intersection point duty ratio of different edge numbers, and determining whether the number of lines and the line type are continuous lines or not;

the color characteristic analysis module is used for taking the colors of the table grid lines as characteristic factors to be added into analysis;

the average length ratio feature module is used for obtaining the average length ratio of the table line to the average length of the whole drawing as a feature;

and the model training module is used for establishing a random forest model and training the table features, the line group features, the color features and the average length features as the features of the model.

Compared with the prior art, the invention has the following advantages:

1. by intelligentizing the identification form information, the operation cost of a user is saved, and the accuracy and time are improved;

2. the method is suitable for all CAD column large sample scenes, and avoids the limitation of applicability;

3. the user only needs to trigger the identification function, the algorithm automatically performs checking calculation, and the operation is simple, convenient and quick.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings that are needed to be used in the embodiments of the present invention will be briefly described, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for identifying a form in a CAD drawing according to the present invention;

FIG. 2 is a schematic diagram showing the characteristic effect of analyzing line-to-line intersections in accordance with an embodiment of the present invention;

FIG. 3 is a schematic diagram showing the effect of line set feature analysis according to an embodiment of the present invention;

FIG. 4 shows a line set eigenvalue graph of an embodiment of the present invention;

FIG. 5 shows a schematic diagram of a table effect obtained by a model according to an embodiment of the present invention;

FIG. 6 is a diagram showing the effectiveness of an invalidation table according to an embodiment of the present invention;

FIG. 7 is a diagram showing the effect of different layers of table lines according to an embodiment of the present invention;

FIG. 8 is a diagram showing the effect of the table in which the table grid lines need to be completed according to the embodiment of the invention.

Detailed Description

Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely configured to illustrate the invention and are not configured to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the invention by showing examples of the invention.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

As shown in fig. 1, the present embodiment provides a method for identifying a form in a CAD drawing, including:

step two, processing and deleting invalid digital table information;

In some embodiments, step one specifically includes:

step 1.1, analyzing the table characteristics, analyzing in a crossing point mode, grouping according to line types, and obtaining the number of edges at the crossing point of all lines and the angles of each edge, and taking fig. 2 as an example for a detailed description.

At the intersection point, 4 lines (up, down, left and right) are arranged around the intersection point, and each line forms an included angle of 90 degrees (270 degrees) or 180 degrees (0 degrees), so that the characteristic value at the intersection point is as follows: 4, (0, 90, 180, 270).

as shown in fig. 3, it is analyzed whether the number of sides is 1, 2, 3, 4, 5, and the number of lines and the line type are continuous lines instead of broken lines, respectively.

And thus can derive the characteristic values as shown in fig. 4.

the form color is also added as a feature, since the figure blends with the remaining lines, such as the axis net, the dead form, etc., while the column-like form is mostly dark in color.

in the drawing of the column large sample, the average length of the lines of the column large sample is lower than that of the whole drawing, and the average length of the table is higher than that of the table, and the table can be added as a characteristic.

And 1.5, establishing a random forest model, and training by taking the table features, the line group features, the color features and the average length features obtained in the steps 1.1-1.4 as the features of the model. Specific table information can be obtained by using the model as shown in fig. 5.

In some embodiments, step two performs a secondary filtering of the table grid lines according to the table internal information, and deletes the useless table. In the column large sample drawing, other text forms possibly exist besides the column large sample form, so that the secondary filtering of the form lines can be performed according to the internal information of the form at the moment, and useless forms are removed.

The text information in the table accounts for more than half of all elements, and can be regarded as a non-column large-sample table. As shown in fig. 6.

In some embodiments, when deleting the useless table, the step two calculates the ratio of text information in the table, and more than half of the text information in all elements are reserved as a non-column large-sample table, and other tables are deleted.

The border lines of the column-like form are formed with non-identical layers as shown in fig. 7, so that they may not be included in the first step of grouping, so that the non-closed areas need to be complemented to form a completely closed form.

In some embodiments, step three complements the non-occluded area to form a fully occluded form. According to the number of the end point lines, if less than 1, the horizontal lines complement the vertical lines, and the vertical lines complement the horizontal lines, as shown in fig. 8.

In some embodiments, the grouping in line form in step 1.1 is vertical and parallel.

In some embodiments, the different edge numbers in step 1.2 include an edge number of 1, an edge number of 2, an edge number of 3, an edge number of 4, and an edge number of 5.

The invention also provides an embodiment of a system for identifying a form in a CAD drawing, comprising:

In some embodiments, the table feature extraction unit includes:

Furthermore, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, implements the steps of the above-mentioned method.

Furthermore, a server may be provided comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the steps of the above method when said program is executed.

Compared with the prior art, the invention has the following advantages:

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method of identifying a form in a CAD drawing, the method comprising:

step two, processing and deleting invalid digital table information;

step three, supplementing the vacant digital table grid lines to an intact state;

the second step further comprises:

2. The method for identifying a form in a CAD drawing according to claim 1, wherein said step two performs a secondary filtering of the form lines based on the form internal information, and deletes the useless form.

3. The method for identifying forms in CAD drawing according to claim 2, wherein the step two is to calculate the ratio of text information in the forms when deleting useless forms, and more than half of the text information in all elements are reserved as non-column large-sample forms, and delete other forms.

4. The method of claim 1, wherein the third step complements the non-closed area to form a fully closed form.

5. The method of claim 4, wherein the third step is to complement the vertical line with the horizontal line if the number of the end point lines is less than 1, and the vertical line complements the horizontal line.

6. The method of claim 1, wherein the line-type grouping in step 1.1 is vertical lines and parallel lines.

7. The method of claim 1, wherein the different numbers of sides in step 1.2 include a number of sides of 1, a number of sides of 2, a number of sides of 3, a number of sides of 4, and a number of sides of 5.

8. A system for identifying forms in CAD drawings, said system comprising:

the table grid line complementing unit is used for complementing the vacant digital table grid lines to an intact state;

the table feature extraction unit includes: