CN116110072B - CAD drawing analysis method and system - Google Patents
CAD drawing analysis method and system Download PDFInfo
- Publication number
- CN116110072B CN116110072B CN202310383350.XA CN202310383350A CN116110072B CN 116110072 B CN116110072 B CN 116110072B CN 202310383350 A CN202310383350 A CN 202310383350A CN 116110072 B CN116110072 B CN 116110072B
- Authority
- CN
- China
- Prior art keywords
- layer
- frame
- cad
- information
- cad drawing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/418—Document matching, e.g. of document images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application provides a CAD drawing analysis method and a CAD drawing analysis system, wherein the method comprises the following steps: acquiring CAD drawings and dividing the CAD drawings to obtain a plurality of professional attribute CAD drawings; acquiring a professional attribute CAD drawing, extracting drawing information, checking whether the drawing information is wrong or not, and checking the frame completeness of the professional attribute CAD drawing to obtain a frame complete CAD drawing; and acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to carry out layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to finish CAD drawing analysis. According to the method, the CAD drawings are subjected to professional division to obtain the plurality of professional attribute CAD drawings, so that different servers are matched, accurate analysis of the CAD drawings is realized, and the analysis precision is improved.
Description
Technical Field
The application relates to the technical field of drawing analysis, in particular to a CAD drawing analysis method and system.
Background
With the rapid development of artificial intelligence technology, artificial intelligence has been able to solve problems in relatively complex industrial fields. The artificial intelligence is applied to the field of construction, and the problem to be solved is to analyze and process a data source (namely CAD drawing) of a construction project, so that analysis precision of CAD drawing information directly influences deep ploughing and wide popularization of the artificial intelligence in the construction industry.
At present, domestic building CAD design drawings have no unified standard, and different design houses and even different designers can have respective standard, such as different expression modes of the content of the icons in the frames; the layers used for the same kind of building information are not strictly divided; the pattern patterns used for the same building element are different. These seemingly small differences have little effect on the drawing information expression of the respective items themselves, but have a large effect on computers.
In the prior art, CAD drawing analysis is generally carried out by adopting an artificial intelligence technology, and mostly, vision, graphic and text analysis is carried out on the general logic of drawing content. The difference of CAD drawings directly influences the accuracy of analyzing the CAD drawings by artificial intelligence technology, and two types of results are easy to appear: the method is characterized in that the method reduces the universality logic to improve the suitability of the analysis CAD drawing, so that the analysis accuracy is low, and even a large number of error results appear; the other is to improve the universality logic for improving the precision of the analysis CAD drawing, so that the requirement on the original CAD drawing is high, a large number of non-standard CAD drawings cannot be accurately analyzed, and the compatibility of the CAD drawing is reduced.
Disclosure of Invention
Based on the above, the application aims to provide a CAD drawing analysis method and a CAD drawing analysis system, which are used for solving the technical problem that the accuracy of the CAD drawing analysis by the artificial intelligence technology is affected due to the difference of CAD drawings in the prior art.
The application provides a CAD drawing analysis method, which comprises the following steps:
obtaining CAD drawings, dividing the CAD drawings according to the specialty of the drawings to obtain a plurality of specialty CAD drawings, and matching the specialty CAD drawings with a server according to the specialty of the drawings, wherein each specialty CAD drawing corresponds to a server;
acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to carry out frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of drawing layers;
and acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to carry out layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to finish CAD drawing analysis.
According to the CAD drawing analysis method, the CAD drawings are subjected to professional division to obtain the plurality of professional attribute CAD drawings, so that different servers are matched, accurate analysis of the CAD drawings is realized, and then, the CAD drawings are subjected to frame completeness check and layer completeness check to solve the problem that differences exist in different CAD drawings, so that complete and correct CAD drawings are provided for analysis, the analysis precision is improved, and the technical problem that the accuracy of the CAD drawings is affected by the differences of the CAD drawings in the prior art is solved.
In addition, according to the CAD drawing analysis method provided by the application, the method can also have the following additional technical characteristics:
further, the step of obtaining the layer information of the frame-complete CAD drawing includes:
acquiring layer information of a complete CAD drawing of a frame and comparing the layer information with a complete recommended layer list;
judging whether the layer division is correct or not according to the comparison result;
if the layer division is incorrect, the layer is readjusted by the marking tool until the adjusted layer division is correct.
Further, before the step of obtaining the CAD drawing and dividing the CAD drawing according to the profession to which the drawing belongs to obtain a plurality of professional attribute CAD drawings, the method comprises the following steps:
and acquiring a CAD drawing and performing first pre-analysis processing on the CAD drawing to perform primary screening on the CAD drawing, wherein the first pre-analysis processing comprises drawing frame information extraction, drawing layer recommendation correction and component combination.
Further, in the step of performing the first pre-parsing processing on the CAD drawing, the method for extracting the frame information includes:
obtaining a picture frame and a picture tab name of a CAD drawing, and carrying out picture frame proportion matching and picture tab name analysis;
and according to the frame proportion matching result and the tab name analysis result, acquiring each frame and the related category information of the tab name corresponding to the frame so as to extract correct frame information.
Further, in the step of performing the first pre-parsing processing on the CAD drawing, the method for layer recommendation correction includes:
acquiring a plurality of CAD drawings and analyzing to classify the layer naming modes of the similar drawing contents to form a unified recommended layer;
and matching the naming characteristics of each layer in the CAD drawing to be analyzed with the recommended layer so as to uniformly correct various matched layers into corresponding recommended layers.
Further, in the step of performing the first pre-parsing process on the CAD drawing, the method for merging the components includes:
obtaining similar CAD graphics of various existing building components as an original training set to perform neural network model training, and obtaining a graphic classification database of the components;
and merging intersecting lines under the component related recommended layers in the original CAD drawing in a mode of minimum circumscribed rectangle, and matching the merged block pattern with a pattern classification database.
Further, the step of checking whether the drawing information is wrong to perform frame completeness checking on the professional attribute CAD drawing includes:
judging whether the frame information is extracted according to the checking result;
if the frame information is not extracted, the frame or the label is analyzed incorrectly, a standard frame is inserted to cover the original frame, the required extracted information prompt is defined by default beside the standard frame, and the information is complemented according to the prompt.
In one aspect, the present application further provides a CAD drawing parsing system, including:
the acquisition module is used for acquiring CAD drawings and dividing the CAD drawings according to the professions of the drawings to obtain a plurality of professional attribute CAD drawings so as to match the professional attribute CAD drawings with a server according to the professions of the drawings, wherein each professional attribute CAD drawing corresponds to a server;
the frame checking module is used for acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to perform frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of layers;
and the layer checking module is used for acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to perform layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to complete CAD drawing analysis.
Drawings
FIG. 1 is a flowchart of a CAD drawing parsing method according to a first embodiment of the present application;
FIG. 2 is a system block diagram of a CAD drawing parsing system according to a second embodiment of the present application;
the application will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the application may be readily understood, a more complete description of the application will be rendered by reference to the appended drawings. Several embodiments of the application are presented in the figures. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In order to solve the technical problem that the accuracy of an artificial intelligence technology analysis CAD drawing is affected due to the difference of CAD drawings in the prior art, the application provides a CAD drawing analysis method and a CAD drawing analysis system, which are used for obtaining a plurality of professional attribute CAD drawings by carrying out professional division on the CAD drawing so as to match different servers and realize the accurate analysis of the CAD drawing, and secondly, carrying out frame completeness check and layer completeness check on the CAD drawing so as to solve the problem that the difference exists among different CAD drawings, thereby providing complete and correct CAD drawing for analysis, improving the analysis accuracy and solving the technical problem that the accuracy of the artificial intelligence technology analysis CAD drawing is affected due to the difference of CAD drawings in the prior art.
Example 1
Referring to fig. 1, a CAD drawing parsing method according to a first embodiment of the application includes steps S101-S103:
s101, acquiring CAD drawings, dividing the CAD drawings according to the professions of the drawings to obtain a plurality of professional attribute CAD drawings, and matching the professional attribute CAD drawings with a server according to the professions of the drawings, wherein each professional attribute CAD drawing corresponds to a server.
In this embodiment, the completeness checking interactive interface is a plug-in based on CAD secondary development, and is distributed on a server side of each specialty. And after pre-analyzing the original CAD drawing, sending the original CAD drawing to a server side of the corresponding specialty according to the specialty to which the drawing belongs, storing the CAD drawing in a task list of the completeness checking interaction interface, and opening and loading the CAD drawing into the completeness checking interaction interface by selecting the CAD drawing from the list.
As a specific example, the step of obtaining a CAD drawing and dividing the CAD drawing according to the specialty to which the drawing belongs to obtain a plurality of professional attribute CAD drawings includes:
and acquiring a CAD drawing, and performing first pre-analysis processing on the CAD drawing to perform primary screening on the CAD drawing, wherein the first pre-analysis processing comprises drawing frame information extraction, drawing layer recommendation correction and component combination.
Specifically, the method for extracting the frame information comprises the following steps:
obtaining a picture frame and a picture tab name of a CAD drawing, and carrying out picture frame proportion matching and picture tab name analysis; and according to the frame proportion matching result and the frame name analysis result, acquiring each frame and the frame name related category information corresponding to the frame so as to extract correct frame information.
As a specific example, the original CAD drawing may have a single or multiple frames, and related item category information in each frame and the icon is extracted through matching the frame proportion and analyzing the icon name.
Further, the layer recommendation correction method comprises the following steps:
acquiring a plurality of CAD drawings and analyzing to classify the layer naming modes of the similar drawing contents to form a unified recommended layer; and matching the naming characteristics of each layer in the CAD drawing to be analyzed with the recommended layers so as to uniformly correct various matched layers into the corresponding recommended layers.
As a specific example, based on analysis of a large number of CAD drawing databases, the layer naming modes of the similar drawing contents are classified to form a unified recommended layer. And uniformly correcting various matching layers into corresponding recommended layers by matching the naming characteristics of each layer in the original CAD drawing with the recommended layers.
Still further, the method of component merging includes:
obtaining similar CAD graphics of various existing building components as an original training set to perform neural network model training, and obtaining a graphic classification database of the components; and merging intersecting lines under the component related recommended layers in the original CAD drawing in a mode of minimum circumscribed rectangle, and matching the merged block pattern with a pattern classification database.
As a specific example, similar CAD graphics of various existing building components are used as an original training set to carry out neural graphics deep learning, and a graphic classification database of the components is obtained. And merging intersecting lines under the recommended layers related to the components in the original CAD in a mode of minimum circumscribed rectangle, and matching the merged block pattern with a pattern classification database.
S102, acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to carry out frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of layers.
In this embodiment, the step of checking whether drawing information is wrong to perform frame completeness checking on the professional attribute CAD drawing includes:
judging whether the frame information is extracted according to the checking result; if the frame information is not extracted, the frame or the label is analyzed incorrectly, a standard frame is inserted to cover the original frame, and the required extracted information prompt is defined by default beside the standard frame to complement the information.
In this embodiment, the loaded pre-parsed CAD drawing extracts the important information associated with parsing in each frame to the side of the frame, where the frame includes a label, and the label is provided with frame information, such as an engineering name, a sub-item name, a picture number, and a picture name. Checking whether the analyzed frame information is wrong or not, and when the extracted frame information is wrong, quickly modifying the extracted information; if the frame information is not extracted, i.e. the frame or the label is in analysis error, a standard frame can be inserted into the system to cover the original frame, the frame information prompt to be extracted is defined by default beside the standard frame, and the corresponding frame information is completed according to the frame information prompt to be extracted. It can be understood that in this embodiment, when the frame information analyzed by the frame has an error, the standard frame is inserted to cover and replace the original frame, the corresponding position in the standard frame is provided with the icon, the system identifies the icon by identifying the frame to obtain the information in the icon, and then the acquired icon information is marked by combining with the frame information prompt to be extracted to form the frame information. The standard picture frame comprises the standard picture frame, and the corresponding position in the standard picture frame is provided with the relevant picture frame information, so that the system can rapidly identify the picture frame in the standard picture frame by identifying the standard picture frame, and further identify the picture frame information in the picture frame.
In this embodiment, in order to accurately identify useful information in the icon, the system performs frame identification first, then performs icon identification, and further identifies the frame information in the icon to construct the frame information beside the frame, specifically, the frame information may be advanced to the right of the frame. By setting the identification and detection sequence of the picture frame first and the picture tag second, the identification accuracy of the picture frame information is convenient to improve, excessive character information is prevented from being identified due to picture tag identification first, the identification quantity of the system to effective information is improved, and the identification difficulty is further improved.
And S103, acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to carry out layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to complete CAD drawing analysis.
In this embodiment, all layers of the loaded pre-parsed CAD drawing are in a locked state. The interface synchronously displays two layer lists, wherein one layer list is a current layer list after all pre-analysis in the existing drawing, and the list comprises classified recommended layers and layers to be classified; the other layer list is a complete recommended layer list of the current specialty. And clicking a single or a plurality of layers in the current layer list, namely unlocking and highlighting drawing content under the corresponding layer, selecting the content of the layer to be corrected in a frame, and selecting the correct layer from the complete recommended layer to finish the layer replacement of the drawing content.
As a specific example, the step of acquiring layer information of the frame-completed CAD drawing includes:
acquiring layer information of a frame-complete CAD drawing; judging whether the layer division is correct or not; if the layer division is incorrect, readjusting the layer by a marking tool until the layer division is correct.
In the actual drawing process, due to different habits or standards of different drawing operators or drawing units, the same drawing may have different layer labels, for example, the same window layer may be labeled by different drawing units or individuals: in order to improve the later recognition rate of the system, the layers of the pattern definition but different labels need to be unified, and the layers need to be divided at the moment.
When the division of the layers is incorrect, for example, when a drawing operator draws a drawing, a window layer in a CAD drawing is marked as a '1 layer', but because the '1 layer' belongs to a custom layer of the drawing operator and is not divided according to the layer division standard, the system does not prepare to identify the '1 layer' and divide the window layer when dividing the window layer, and the '1 layer' is incorrectly divided in the CAD drawing and needs to be adjusted.
In the process of adjusting the layer, identifying graphic elements in the layer, matching the elements in the layer through preset graphics in a graphic database to divide the layer according to a matching result, and therefore performing secondary labeling on the layer to obtain a standard layer name. For example, when "1 layer" is a window layer, since "1 layer" is a custom layer, the system cannot be correctly identified and errors are reported, and at this time, it is necessary to further identify the graphic features in the layer to locate the graphic as a window, and perform layer location, and adjust "1 layer" to be a window layer.
As a specific example, in order to further improve accuracy of the drawing analysis result and avoid misjudgment of the classification result, auxiliary mark inspection is also needed for the CAD drawing, specifically, the component merging result is fed back in the pre-analyzed CAD drawing, and since the component merging classification result is obtained by deep learning and matching of the neural patterns, there may be a situation that the similarity of different components is extremely high from the view level of the patterns. Therefore, there may be a case of misjudgment of the classification result, and therefore, the misjudged classification result is marked as a correct classification result by the marking tool, and the result deviation existing in the simple visual processing may be compensated, thereby further improving the overall accuracy.
After each inspection is completed, the adjusted CAD drawing is sent and submitted to a server, a task to be processed is refreshed in a task list, the completeness inspection task is completed, and the completeness inspection task is submitted. And the total server receives the submitted CAD drawing after the completeness check, carries out the second analysis processing, and is more accurate in drawing frame information extraction, drawing layer recommendation correction and component combination results based on the assistance of the completeness check.
In summary, in the CAD drawing analysis method in the above embodiment of the present application, the CAD drawings are subjected to professional division to obtain a plurality of professional attribute CAD drawings, so as to match with different servers, thereby implementing accurate analysis on the CAD drawings, and then, the CAD drawings are subjected to frame completeness check and layer completeness check to solve the problem of differences between different CAD drawings, thereby providing complete and correct CAD drawings for analysis, improving the accuracy of analysis, and solving the technical problem in the prior art that the accuracy of the CAD drawings is affected by the differences of CAD drawings in the analysis of artificial intelligence technology.
Example two
Referring to FIG. 2, a CAD drawing parsing system according to a second embodiment of the present application is shown, comprising
The acquisition module is used for acquiring CAD drawings and dividing the CAD drawings according to the professions of the drawings to obtain a plurality of professional attribute CAD drawings so as to match the professional attribute CAD drawings with a server according to the professions of the drawings, wherein each professional attribute CAD drawing corresponds to a server;
the frame checking module is used for acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to perform frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of layers;
and the layer checking module is used for acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to perform layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to complete CAD drawing analysis.
In summary, in the CAD drawing analysis system according to the foregoing embodiments of the present application, the CAD drawings are subjected to professional division to obtain a plurality of professional attribute CAD drawings, so as to match with different servers, thereby implementing accurate analysis on the CAD drawings, and then, the CAD drawings are subjected to frame completeness check and layer completeness check to solve the problem of differences between different CAD drawings, thereby providing complete and correct CAD drawings for analysis, improving the accuracy of analysis, and solving the technical problem in the prior art that the accuracy of the artificial intelligence technology analysis CAD drawings is affected due to the differences of CAD drawings.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (3)
1. The CAD drawing analysis method is characterized by comprising the following steps of:
obtaining CAD drawings, dividing the CAD drawings according to the specialty of the drawings to obtain a plurality of specialty CAD drawings, and matching the specialty CAD drawings with a server according to the specialty of the drawings, wherein each specialty CAD drawing corresponds to a server;
acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to carry out frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of drawing layers;
acquiring layer information of a complete CAD drawing of a frame, judging whether the layer information is correct according to a preset complete recommended layer list so as to carry out layer completeness checking on the professional attribute CAD drawing, and acquiring the complete CAD drawing of the layer according to a layer completeness checking result so as to finish CAD drawing analysis;
the step of obtaining the layer information of the frame-complete CAD drawing comprises the following steps:
acquiring layer information of a complete CAD drawing of a frame and comparing the layer information with a complete recommended layer list;
judging whether the layer division is correct or not according to the comparison result;
if the layer division is incorrect, readjusting the layer by a marking tool until the adjusted layer division is correct;
the step of readjusting the layers by the marking tool until the adjusted layers are divided correctly comprises the following steps:
when the layer is adjusted, identifying graphic elements in the layer, and matching the elements in the layer through a preset graphic in a graphic database to divide the layer according to a matching result, so that the layer is marked for the second time, and a standard layer name is obtained;
the method for obtaining the CAD drawings comprises the following steps of:
acquiring a CAD drawing and performing first pre-analysis processing on the CAD drawing to perform primary screening on the CAD drawing, wherein the first pre-analysis processing comprises drawing frame information extraction, drawing layer recommendation correction and component combination;
in the step of performing the first pre-analysis processing on the CAD drawing, the method for extracting the frame information comprises the following steps:
obtaining a picture frame and a picture tab name of a CAD drawing, and carrying out picture frame proportion matching and picture tab name analysis;
according to the frame proportion matching result and the frame name analysis result, acquiring each frame and the frame name related category information corresponding to the frame so as to extract correct frame information;
in the step of performing the first pre-analysis processing on the CAD drawing, the method for recommending and correcting the drawing layer comprises the following steps:
acquiring a plurality of CAD drawings and analyzing to classify the layer naming modes of the similar drawing contents to form a unified recommended layer;
matching the naming characteristics of each layer in the CAD drawing to be analyzed with the recommended layer so as to uniformly correct various matched layers into corresponding recommended layers;
the step of checking whether the drawing information is wrong or not to check the frame completeness of the professional attribute CAD drawing comprises the following steps:
judging whether the frame information is extracted according to the checking result;
if the frame information is not extracted, the frame or the label is analyzed incorrectly, a standard frame is inserted to cover the original frame, the required extracted information prompt is defined by default beside the standard frame, and the information is complemented according to the prompt.
2. The CAD drawing parsing method according to claim 1, wherein in the step of performing the first pre-parsing process on the CAD drawing, the method of merging the components includes:
obtaining similar CAD graphics of various existing building components as an original training set to perform neural network model training, and obtaining a graphic classification database of the components;
and merging intersecting lines under the component related recommended layers in the original CAD drawing in a mode of minimum circumscribed rectangle, and matching the merged block pattern with a pattern classification database.
3. A CAD drawing parsing system, comprising:
the acquisition module is used for acquiring CAD drawings and dividing the CAD drawings according to the professions of the drawings to obtain a plurality of professional attribute CAD drawings so as to match the professional attribute CAD drawings with a server according to the professions of the drawings, wherein each professional attribute CAD drawing corresponds to a server;
the frame checking module is used for acquiring a professional attribute CAD drawing and extracting drawing information, wherein the drawing information comprises a drawing name, a drawing number and a drawing level, checking whether the drawing information is wrong or not so as to perform frame completeness checking on the professional attribute CAD drawing, and acquiring a frame completeness CAD drawing according to a frame completeness checking result, wherein the frame completeness CAD drawing comprises a plurality of layers;
the layer checking module is used for acquiring layer information of the frame complete CAD drawing, judging whether the layer information is correct according to a preset complete recommended layer list so as to perform layer completeness checking on the professional attribute CAD drawing, and acquiring the layer complete CAD drawing according to a layer completeness checking result so as to complete CAD drawing analysis;
the step of obtaining the layer information of the frame-complete CAD drawing comprises the following steps:
acquiring layer information of a complete CAD drawing of a frame and comparing the layer information with a complete recommended layer list;
judging whether the layer division is correct or not according to the comparison result;
if the layer division is incorrect, readjusting the layer by a marking tool until the adjusted layer division is correct;
the step of readjusting the layers by the marking tool until the adjusted layers are divided correctly comprises the following steps:
when the layer is adjusted, identifying graphic elements in the layer, and matching the elements in the layer through a preset graphic in a graphic database to divide the layer according to a matching result, so that the layer is marked for the second time, and a standard layer name is obtained;
the method for obtaining the CAD drawings comprises the following steps of:
acquiring a CAD drawing and performing first pre-analysis processing on the CAD drawing to perform primary screening on the CAD drawing, wherein the first pre-analysis processing comprises drawing frame information extraction, drawing layer recommendation correction and component combination;
in the step of performing the first pre-analysis processing on the CAD drawing, the method for extracting the frame information comprises the following steps:
obtaining a picture frame and a picture tab name of a CAD drawing, and carrying out picture frame proportion matching and picture tab name analysis;
according to the frame proportion matching result and the frame name analysis result, acquiring each frame and the frame name related category information corresponding to the frame so as to extract correct frame information;
in the step of performing the first pre-analysis processing on the CAD drawing, the method for recommending and correcting the drawing layer comprises the following steps:
acquiring a plurality of CAD drawings and analyzing to classify the layer naming modes of the similar drawing contents to form a unified recommended layer;
matching the naming characteristics of each layer in the CAD drawing to be analyzed with the recommended layer so as to uniformly correct various matched layers into corresponding recommended layers;
the step of checking whether the drawing information is wrong or not to check the frame completeness of the professional attribute CAD drawing comprises the following steps:
judging whether the frame information is extracted according to the checking result;
if the frame information is not extracted, the frame or the label is analyzed incorrectly, a standard frame is inserted to cover the original frame, the required extracted information prompt is defined by default beside the standard frame, and the information is complemented according to the prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383350.XA CN116110072B (en) | 2023-04-12 | 2023-04-12 | CAD drawing analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383350.XA CN116110072B (en) | 2023-04-12 | 2023-04-12 | CAD drawing analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116110072A CN116110072A (en) | 2023-05-12 |
| CN116110072B true CN116110072B (en) | 2023-08-15 |
Family
ID=86264111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310383350.XA Active CN116110072B (en) | 2023-04-12 | 2023-04-12 | CAD drawing analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116110072B (en) |
Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8032409B1 (en) * | 1999-11-22 | 2011-10-04 | Accenture Global Services Limited | Enhanced visibility during installation management in a network-based supply chain environment |
| CN102567014A (en) * | 2011-11-14 | 2012-07-11 | 南京天溯自动化控制系统有限公司 | Method for realizing animation in SCADA (supervisory control and data acquisition) system by using Lua script |
| CN105117573A (en) * | 2015-10-06 | 2015-12-02 | 北京工业大学 | Automatic hydraulic model establishment method based on CAD drainage network drawing information |
| CN106777808A (en) * | 2017-01-13 | 2017-05-31 | 浪潮通信信息系统有限公司 | A kind of Internet resources generation method based on standardization CAD diagram paper |
| CN106815029A (en) * | 2017-01-24 | 2017-06-09 | 南京仁谷系统集成有限公司 | A kind of use Qt carries out drafting and the event-handling method of two-dimentional figure layer |
| CN110245393A (en) * | 2019-05-28 | 2019-09-17 | 长沙市海图科技有限公司 | CAD diagram paper checking method, device, equipment and the storage medium of planning construction |
| CN110516383A (en) * | 2019-08-30 | 2019-11-29 | 兰州深蓝图形技术有限公司 | A kind of parsing of railway signals equipment vector graphics file, display methods and device |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| CN111553131A (en) * | 2019-01-24 | 2020-08-18 | 北京京东尚科信息技术有限公司 | PSD file analysis method, device, equipment and readable storage medium |
| CN112818456A (en) * | 2021-02-26 | 2021-05-18 | 万翼科技有限公司 | Layer configuration method, electronic equipment and related product |
| CN112929732A (en) * | 2019-12-06 | 2021-06-08 | 腾讯科技（深圳）有限公司 | Video processing method and device and computer storage medium |
| CN112989923A (en) * | 2021-01-20 | 2021-06-18 | 上海品览智造科技有限公司 | Method for accurately judging whether shielding exists in neutral plane window in CAD elevation graph |
| CN113010944A (en) * | 2021-02-26 | 2021-06-22 | 万翼科技有限公司 | Model checking method, electronic equipment and related product |
| CN113886931A (en) * | 2021-10-21 | 2022-01-04 | 上海品览数据科技有限公司 | CAD drawing fire-fighting linkage alarm wire casing arrangement method based on B-star algorithm |
| CN113903050A (en) * | 2021-10-26 | 2022-01-07 | 上海品览数据科技有限公司 | Distribution box subgraph identification method in electrical professional distribution box system graph based on deep learning |
| CN113962000A (en) * | 2021-10-21 | 2022-01-21 | 上海品览数据科技有限公司 | Method for dynamically arranging smoke detectors in CAD (computer-aided design) drawing |
| CN113971813A (en) * | 2021-10-25 | 2022-01-25 | 上海品览数据科技有限公司 | Accurate identification method for parking spaces in construction professional general plane construction drawing and underground garage construction drawing |
| CN114022895A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying house type in building professional residential plan |
| CN114022894A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying front rooms of stairs in CAD (computer-aided design) drawing |
| CN114048539A (en) * | 2021-01-13 | 2022-02-15 | 万翼科技有限公司 | CAD file analysis and rule judgment method and related device |
| CN114065351A (en) * | 2021-11-17 | 2022-02-18 | 北京蜂鸟视图科技有限公司 | System and method for constructing indoor map based on CAD (computer-aided design) electronic drawing |
| CN114283415A (en) * | 2021-12-08 | 2022-04-05 | 万翼科技有限公司 | Parking space identification method and device, electronic equipment and storage medium |
| CN114781314A (en) * | 2021-12-31 | 2022-07-22 | 杭州广立微电子股份有限公司 | Method and system for rapidly drawing layout |
| CN115082622A (en) * | 2022-06-24 | 2022-09-20 | 合肥坤颐建筑科技合伙企业(有限合伙) | Three-dimensional model generation method, device, equipment and storage medium |
| CN115688209A (en) * | 2022-11-01 | 2023-02-03 | 上海顺凯信息技术有限公司 | CAD secondary development investigation drawing aided design system |
| CN115935493A (en) * | 2023-03-15 | 2023-04-07 | 江西中至科技有限公司 | Method and system for converting two-dimensional CAD drawing into BIM model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10830818B2 (en) * | 2017-09-25 | 2020-11-10 | International Business Machines Corporation | Ensuring completeness of interface signal checking in functional verification |
-
2023
- 2023-04-12 CN CN202310383350.XA patent/CN116110072B/en active Active
Patent Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8032409B1 (en) * | 1999-11-22 | 2011-10-04 | Accenture Global Services Limited | Enhanced visibility during installation management in a network-based supply chain environment |
| CN102567014A (en) * | 2011-11-14 | 2012-07-11 | 南京天溯自动化控制系统有限公司 | Method for realizing animation in SCADA (supervisory control and data acquisition) system by using Lua script |
| CN105117573A (en) * | 2015-10-06 | 2015-12-02 | 北京工业大学 | Automatic hydraulic model establishment method based on CAD drainage network drawing information |
| CN106777808A (en) * | 2017-01-13 | 2017-05-31 | 浪潮通信信息系统有限公司 | A kind of Internet resources generation method based on standardization CAD diagram paper |
| CN106815029A (en) * | 2017-01-24 | 2017-06-09 | 南京仁谷系统集成有限公司 | A kind of use Qt carries out drafting and the event-handling method of two-dimentional figure layer |
| CN111553131A (en) * | 2019-01-24 | 2020-08-18 | 北京京东尚科信息技术有限公司 | PSD file analysis method, device, equipment and readable storage medium |
| CN110245393A (en) * | 2019-05-28 | 2019-09-17 | 长沙市海图科技有限公司 | CAD diagram paper checking method, device, equipment and the storage medium of planning construction |
| CN110516383A (en) * | 2019-08-30 | 2019-11-29 | 兰州深蓝图形技术有限公司 | A kind of parsing of railway signals equipment vector graphics file, display methods and device |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| CN112929732A (en) * | 2019-12-06 | 2021-06-08 | 腾讯科技（深圳）有限公司 | Video processing method and device and computer storage medium |
| CN114048539A (en) * | 2021-01-13 | 2022-02-15 | 万翼科技有限公司 | CAD file analysis and rule judgment method and related device |
| CN112989923A (en) * | 2021-01-20 | 2021-06-18 | 上海品览智造科技有限公司 | Method for accurately judging whether shielding exists in neutral plane window in CAD elevation graph |
| CN113010944A (en) * | 2021-02-26 | 2021-06-22 | 万翼科技有限公司 | Model checking method, electronic equipment and related product |
| CN112818456A (en) * | 2021-02-26 | 2021-05-18 | 万翼科技有限公司 | Layer configuration method, electronic equipment and related product |
| CN113886931A (en) * | 2021-10-21 | 2022-01-04 | 上海品览数据科技有限公司 | CAD drawing fire-fighting linkage alarm wire casing arrangement method based on B-star algorithm |
| CN113962000A (en) * | 2021-10-21 | 2022-01-21 | 上海品览数据科技有限公司 | Method for dynamically arranging smoke detectors in CAD (computer-aided design) drawing |
| CN113971813A (en) * | 2021-10-25 | 2022-01-25 | 上海品览数据科技有限公司 | Accurate identification method for parking spaces in construction professional general plane construction drawing and underground garage construction drawing |
| CN113903050A (en) * | 2021-10-26 | 2022-01-07 | 上海品览数据科技有限公司 | Distribution box subgraph identification method in electrical professional distribution box system graph based on deep learning |
| CN114022895A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying house type in building professional residential plan |
| CN114022894A (en) * | 2021-10-27 | 2022-02-08 | 上海品览数据科技有限公司 | Method for accurately identifying front rooms of stairs in CAD (computer-aided design) drawing |
| CN114065351A (en) * | 2021-11-17 | 2022-02-18 | 北京蜂鸟视图科技有限公司 | System and method for constructing indoor map based on CAD (computer-aided design) electronic drawing |
| CN114283415A (en) * | 2021-12-08 | 2022-04-05 | 万翼科技有限公司 | Parking space identification method and device, electronic equipment and storage medium |
| CN114781314A (en) * | 2021-12-31 | 2022-07-22 | 杭州广立微电子股份有限公司 | Method and system for rapidly drawing layout |
| CN115082622A (en) * | 2022-06-24 | 2022-09-20 | 合肥坤颐建筑科技合伙企业(有限合伙) | Three-dimensional model generation method, device, equipment and storage medium |
| CN115688209A (en) * | 2022-11-01 | 2023-02-03 | 上海顺凯信息技术有限公司 | CAD secondary development investigation drawing aided design system |
| CN115935493A (en) * | 2023-03-15 | 2023-04-07 | 江西中至科技有限公司 | Method and system for converting two-dimensional CAD drawing into BIM model |
Non-Patent Citations (1)
| Title |
|---|
| 夏振等.一种从CAD到ArcGIS数据转化方法研究.测绘地理信息.2021,第46卷(第4期),116-118. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116110072A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10860848B2 (en) | Multi-page document recognition in document capture | |
| US6668254B2 (en) | Method and system for importing data | |
| US7607078B2 (en) | Paper and electronic recognizable forms | |
| US8094976B2 (en) | One-screen reconciliation of business document image data, optical character recognition extracted data, and enterprise resource planning data | |
| JP4093012B2 (en) | Hypertext inspection apparatus, method, and program | |
| US20160179313A1 (en) | Page-independent multi-field validation in document capture | |
| US20050203869A1 (en) | Hierarchical database apparatus, components selection method in hierarchical database, and components selection program | |
| CN111582169B (en) | Image recognition data error correction method, device, computer equipment and storage medium | |
| US20040181749A1 (en) | Method and apparatus for populating electronic forms from scanned documents | |
| US11182544B2 (en) | User interface for contextual document recognition | |
| US20100246999A1 (en) | Method and Apparatus for Editing Large Quantities of Data Extracted from Documents | |
| US20160117387A1 (en) | Methods and systems for automated data characterization and extraction | |
| CN113673500A (en) | Certificate image recognition method and device, electronic equipment and storage medium | |
| WO2020237480A1 (en) | Control method and device based on image recognition | |
| CN116110072B (en) | CAD drawing analysis method and system | |
| US20070127822A1 (en) | Method and system for analyzing image differences | |
| CN111581937A (en) | Document generation method and device, computer readable medium and electronic equipment | |
| CN109960707B (en) | College recruitment data acquisition method and system based on artificial intelligence | |
| US20020196290A1 (en) | Time-based evaluation of data verification results | |
| JP2017111500A (en) | Character recognizing apparatus, and program | |
| CN113221875B (en) | Target detection model training method based on active learning | |
| US20220405503A1 (en) | Machine learning-based document splitting and labeling in an electronic document system | |
| CN111506776B (en) | Data labeling method and related device | |
| CN117671681A (en) | Picture labeling method, device, terminal and storage medium | |
| Mao et al. | Style-independent document labeling: design and performance evaluation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |