CN110399787A - A kind of management system and method for engineering drawing - Google Patents
A kind of management system and method for engineering drawing Download PDFInfo
- Publication number
- CN110399787A CN110399787A CN201910498089.1A CN201910498089A CN110399787A CN 110399787 A CN110399787 A CN 110399787A CN 201910498089 A CN201910498089 A CN 201910498089A CN 110399787 A CN110399787 A CN 110399787A
- Authority
- CN
- China
- Prior art keywords
- engineering drawing
- check
- drawings
- model
- engineering
- 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.)
- Pending
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
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- 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
Abstract
The present invention relates to management of blueprint fields, and in particular to a kind of management system and method for engineering drawing;It is preset with the check of drawings model for intelligent checks engineering drawing, and for the identification model of intelligent recognition engineering drawing, the management method is the following steps are included: carry out content recognition to the engineering drawing according to identification model;Intelligent check of drawings is carried out to current engineering drawing according to check of drawings model;To the engineering drawing classified finishing audited;Compared with prior art, the present invention is by designing the management system and method for a kind of engineering drawing, it realizes and audit management is carried out to complicated and diversified Building class engineering drawing, it is instead of labor management, on the one hand reduce management cost, the management of engineering drawing is on the other hand made more efficiently, more comprehensively and to there is higher accuracy.
Description
Technical field
The present invention relates to management of blueprint fields, and in particular to a kind of management system and method for engineering drawing.
Background technique
With the economic growth and social progress in China, living standards of the people are continuously improved, and urban construction is maked rapid progress, In
A large amount of drawing can be generated in each City Construction Project, including finalizing a text from manuscript base at the beginning of initial design to final design
All engineering drawing data of figure, on the one hand these engineering drawing data need to audit in constructing and implementing guarantees its quality, separately
On the one hand need to carry out it management of Life cycle, and the audit management of engineering drawing is a complicated process, it is right
The requirement of process is very high.
Due to the diversity of architectural engineering drawing and the complexity of examination, management requirement is very high, and enterprise is in management engineering
Need to put into a large amount of management cost in terms of drawing, currently, the audit management of architectural engineering drawing depends on manually, a side
Face high labor cost and low efficiency, another aspect labor management are easy to appear the loss that managerial competency causes engineering drawing, at present
Also occur some management of blueprint softwares on the market, but the generally existing insufficiency of these softwares, inconvenient for use and low efficiency
The problem of, it is not particularly suited for complicated and diversified Building class engineering drawing management.
Therefore, one kind is designed to be suitable for complicated and diversified Building class engineering drawing management, manage comprehensive and efficient engineering
The problem of management system and method for drawing are always this field primary study.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the above drawbacks of the prior art, provide a kind of management comprehensively and
The management system and method for efficient engineering drawing overcome at high cost, the not comprehensive and low efficiency of management in existing way to manage
Defect.
The technical solution adopted by the present invention to solve the technical problems is: a kind of management method of engineering drawing is provided,
Preferred embodiment is, is preset with the check of drawings model for intelligent checks engineering drawing, and for intelligent recognition engineering drawing
Identification model, the management method the following steps are included:
Content recognition is carried out to the engineering drawing according to identification model;
Intelligent check of drawings is carried out to current engineering drawing according to check of drawings model;
To the engineering drawing classified finishing audited.
Wherein, preferred version be the default knowledge graph model the following steps are included:
The a series of recognition rule of the curriculum offering according to involved in engineering drawing;
A series of recognition rules in each engineering drawing arrange and form identification model.
Wherein, preferred version is described the step of carrying out content recognition to engineering drawing further include:
If there are unidentified regions for engineering drawing, recognition rule corresponding to unidentified region is obtained;
It is increased in a series of existing recognition rules of current engineering drawing, improves identification model again.
Wherein, preferred version be the default check of drawings model the following steps are included:
Engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, forms multiple check of drawings samples
Data;
Multiple sample datas in each engineering drawing are arranged, by machine learning, establish check of drawings model.
Wherein, preferred version is described the step of carrying out intelligent check of drawings to current engineering drawing further include:
If there are unexamined core regions for engineering drawing, the drawing content in the region is identified again according to identification model;
Unexamined core region is audited by artificial check of drawings mode or/and machine check of drawings mode, forms new sample number
According to.
Wherein, preferred version is described the step of carrying out intelligent check of drawings to current engineering drawing further include:
New sample data is arranged, and is increased in corresponding engineering drawing in existing multiple sample datas, shape
The check of drawings model of Cheng Xin.
Wherein, preferred version be the default check of drawings model the following steps are included:
Manually to after completing intelligent check of drawings, by manually checking check of drawings result;
In conjunction with review as a result, modify to check of drawings model/it is perfect.
Wherein, preferred version is the step of engineering drawing to intelligent check of drawings sorts out processing to include:
Engineering drawing information is obtained, and corresponding label is arranged according to the information, to reflect the classification category of the engineering drawing
Property;
Combination tag carries out classified finishing to the engineering drawing audited.
Wherein, preferred version is the drawing that the engineering drawing is PDF format.
In order to solve the problems existing in the prior art, the present invention also provides a kind of management systems of engineering drawing, preferably side
Case is: the management system includes processing unit and memory module, and the processing unit is stored with computer program, the meter
The step of calculation machine program can be performed to realize the above method, dependency number caused by the memory module storage processing unit
It is believed that breath.
The beneficial effects of the present invention are compared with prior art, the present invention is by designing the management of engineering drawing a kind of
System and method realizes and carries out audit management to complicated and diversified Building class engineering drawing, instead of labor management, a side
Face reduces management cost, and the management of engineering drawing is on the other hand made more efficiently, more comprehensively and to have higher accuracy.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the flow diagram of the management method of engineering drawing in the present invention;
Fig. 2 is the structural block diagram of the management system of engineering drawing in the present invention;
Fig. 3 is the flow diagram one for carrying out content recognition in the present invention to engineering drawing;
Fig. 4 is the flow diagram two for carrying out content recognition in the present invention to engineering drawing;
Fig. 5 is the flow diagram one for carrying out intelligent check of drawings in the present invention to engineering drawing;
Fig. 6 is the flow diagram two for carrying out intelligent check of drawings in the present invention to engineering drawing;
Fig. 7 is the flow diagram three for carrying out intelligent check of drawings in the present invention to engineering drawing;
Fig. 8 is the flow diagram for sorting out processing in the present invention to the engineering drawing of intelligent check of drawings.
Specific embodiment
Now in conjunction with attached drawing, elaborate to presently preferred embodiments of the present invention.
As Figure 1-Figure 2, the present invention provides a kind of management system of engineering drawing and the most preferred embodiment of method.
With reference to Fig. 1, a kind of management method of engineering drawing is preset with the check of drawings model for intelligent checks engineering drawing,
And the identification model for intelligent recognition engineering drawing, the management method the following steps are included:
S1, content recognition is carried out to the engineering drawing according to identification model;
S2, intelligent check of drawings is carried out to current engineering drawing according to check of drawings model;
S3, to the engineering drawing classified finishing audited.
Further, and Fig. 2 is referred to, a kind of Management System of Project Drawing, the management system includes 100 He of processing unit
Memory module 200, the processing unit 100 are stored with computer program, and the computer program can be performed on to realize
The step of stating method, related data information caused by 200 storage processing unit 100 of memory module.
Wherein, the engineering drawing refers to the inside deployment scenarios for indicating building, outer shape, and fit up,
The related drawing of the contents such as construction, construction requirement is divided into architectural working drawing, structural working drawing, equipment construction figure, it is also examination & approval
The foundation of construction-engineering project;In production and construction, it is the foundation of stock and construction;It, be according to engineering when completion of works
The design requirement of figure carries out quality inspection and acceptance, and with this evaluation engineering quality good or not;Architectural drawings still work out engineering
Budgetary estimate, budget and final accounts and the foundation for auditing project cost;Architectural drawings are the technological documents with legal effect;Usually
Based on projection theory, by the drafting standard of national regulation, having built up or the shape of still unestablished architectural engineering, big
The small equal pattern accurately expressed in the plane, and the requirement of material used in engineering and production, installation etc. is indicated simultaneously, by
Different in the mission requirements in engineering construction each stage, content, depth and mode expressed by all kinds of drawings also have difference.
In the present embodiment, the engineering drawing is the drawing of PDF format.
Wherein, the identification model, which refers to, specifically refers to management system finishing analysis difference engineering through the processing unit
The information area and content regions of drawing, a kind of data general character got can be automatically by the information area of a certain engineering drawing content
It corresponds with content regions, forms identification model, and be automatically stored in a storage module, it can be straight in subsequent knowledge figure
The information area for scanning current engineering drawing is connect, the particular content of the engineering drawing is identified further according to identification model.
Wherein, check of drawings model refers to that management system building can carry out each engineering drawing based on after machine learning
The foundation of audit, the different check of drawings data of specially described management system finishing analysis difference engineering drawing through the processing unit,
A kind of data general character is obtained, can correspond by the corresponding check of drawings data of a certain engineering drawing content automatically, shape
At check of drawings model, and it is automatically stored in a storage module.
Wherein, the processing unit is computer or dedicated identification device.
Computer is by hardware system (hardware system) and software systems (software system) two parts
Composition, the hardware unit of conventional computer system generally can be divided into input unit, output unit, arithmetic logic unit, control
Unit and memory unit, wherein arithmetic logic unit and control unit are collectively referred to as central processing unit (Center Processing
Unit, CPU), i.e., the processing unit being previously mentioned in the present embodiment, the storage list being wherein previously mentioned in memory unit, that is, the present embodiment
Member.
Specifically, current engineering drawing is identified according to identification model by the processing unit in Management System of Project Drawing
Particular content, and its particular content is matched to corresponding check of drawings model, intelligent check of drawings is realized, to after the completion of intelligent check of drawings
The engineering drawing of audit carries out classified finishing, realizes the Building class engineering drawing of complex management multiplicity quickly and efficiently.
As Figure 3-Figure 4, the present invention provides the most preferred embodiment that content recognition is carried out to engineering drawing.
With reference to Fig. 3, described the step of content recognition is carried out to engineering drawing further include:
S11, a series of recognition rule of the curriculum offering according to involved in engineering drawing;
S12, to a series of recognition rules in each engineering drawing carry out arrange form identification model.
Wherein, the knowledge rule map refers to including engineering drawing contents attribute, property parameters and drawing code requirement etc.
A whole set of rule of data, such as:
1, the contents attribute of the engineering drawing includes the specific common building object such as door, window, column, beam slab.
2, the property parameters of the engineering drawing include size and its corresponding positional relationship of some specific object etc..
3, drawing code requirement includes that extension line (range of dimensioning for limiting) is drawn with fine line, generally by
Extension line is made in contour line, axis, line of symmetry extraction, can also be directly extension line with the above line style, exceed dimension line terminal
2-3mm;Dimension line (containing arrow) is drawn with fine line;It is parallel with infused line segment;The symbol of dimension figure dimensioning is straight
Diameter indicates that ball is indicated with " S Ф ", " SR " with " Ф ".Radius indicates that square structure is indicated with " " with " R ", and extension line is main
Indicate that the metrics range of size is drawn as dimension line with fine line, representation method by the contour line of figure, axis or
It is drawn at symmetrical center line, directly can also make extension line using them;Generally require all marks all in a figure layer, no
Can block mark number (it is wired from mark number pass through when, to interrupt herein), mark be desirable to marshalling, should not be in disorder,
Rational deployment.Architectural engineering drawing is intended to indicate that the inside deployment scenarios of building, outer shape, and fits up, constructs, applies
The related drawing of the contents such as work requirement, it is the foundation for examining construction-engineering project;In production and construction, it is stock and construction
Foundation;When completion of works, quality inspection and acceptance is carried out according to the design requirement of engineering drawing, and with this evaluation engineering matter
Measure superiority and inferiority;Architectural drawings still work out Budgetary Estimates, budget and final accounts and audit the foundation of project cost;Architectural drawings are
Technological document with legal effect, architectural drawing code requirement further include the perspective view of building shape, although clear
The shape of body and the correlation of each section are expressed in ground, but must also infuse enough sizes, the reality of the clear body of ability
The relative position of size and each section.When marking the size of building shape, to consider two problems: should be marked on perspective view
Where which size and size should be labeled in perspective view.
Specifically, the knowledge rule map of the engineering drawing is obtained by the content information of processing module Scan Engineering Drawings,
In, each engineering drawing corresponds to multiple knowledge rule maps, and the processing module stores multiple knowledge rule maps in a storage module, most
Afterwards each engineering drawing and corresponding insighted rule map one-to-one correspondence are got up to form the identification model of the engineering drawing.
Further, and Fig. 4, described the step of content recognition is carried out to engineering drawing are referred to further include:
If there are unidentified regions for S13, engineering drawing, recognition rule corresponding to unidentified region is obtained;
S14, it is increased in a series of existing recognition rules of current engineering drawing, improves identification model again.
Specifically, firstly, obtaining the corresponding knowledge rule map in unidentified region, the knowledge rule map and above-mentioned knowledge rule map one
It causes, is a whole set of rule including data such as engineering drawing contents attribute, property parameters and drawing code requirements, further
It is manually audited after obtaining new knowledge rule map in ground, further, after audit is errorless that unidentified region institute is right
The knowledge rule map answered increases in other knowledge rule maps corresponding to current engineering drawing, knows graph model to improve again.
As shown in Figure 5-Figure 8, the present invention provides the most preferred embodiment that intelligent check of drawings is carried out to current engineering drawing.
With reference to Fig. 5, it is described intelligent check of drawings is carried out to current engineering drawing the following steps are included:
S21, engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, forms multiple checks of drawings
Sample data;
S22, multiple sample datas in each engineering drawing are arranged, by machine learning, establishes check of drawings model.
Wherein, actual observation or a part of individual of investigation are known as sample (sample) in research, the whole of research object
It is referred to as overall;In order to enable sample correctly to reflect overall situation, there is specific regulation to overall;All observations are single in totality
Position must be homogeneity;During sample drawn, it is necessary to abide by randomization;The observation unit of sample will also have enough
Quantity;Also known as " increment ".A part of individual taken out from totality according to certain sampling prescription;Individual number in sample
Referred to as " sample size ".
In the present embodiment, check of drawings sample data refers to the check of drawings record data generated during artificial check of drawings early period,
An a foundation either reference as subsequent intelligent check of drawings is found for carrying out intelligent comparison when machine intelligence check of drawings
Its data general character, to complete intelligent check of drawings.
Wherein, machine learning (Machine Learning, ML) is a multi-field cross discipline, is related to probability theory, system
The multiple subjects such as, Approximation Theory, convextiry analysis, algorithm complexity theory are counted, specialize in the mankind are simulated or realized to computer how
Learning behavior reorganize the existing structure of knowledge to obtain new knowledge or skills and be allowed to constantly improve the performance of itself;
It is the core of artificial intelligence, is the fundamental way for making computer have intelligence, and application spreads the every field of artificial intelligence,
It is mainly using conclusion, comprehensive rather than deduction;Environment provides certain information to the study part of system, and study part utilizes this
A little information modify knowledge base, and to promote the efficiency that system execution part completes task, execution part completes task according to knowledge base,
The information of acquisition is fed back to study part simultaneously.In specific application, environment, knowledge base and execution part determine specifically
Action.
In the present embodiment, machine learning is primarily referred to as generating a large amount of sample data, and will own by artificial check of drawings
Sample data and its general character are supplied to the study part of computer system, and further, study part is modified using these information
Sample database, to promote the efficiency that computer system execution part completes task, further, execution part is according to sample number
It is compared to form check of drawings mould with content in sample database according to library, and by the particular content of the engineering drawing currently recognized
Type.
Further, and Fig. 6, described the step of intelligent check of drawings is carried out to current engineering drawing are referred to further include:
If there are unexamined core regions for S23, engineering drawing, identified again according to identification model in the drawing in the region
Hold;
S24, unexamined core region is audited by artificial check of drawings mode or/and machine check of drawings mode, forms new sample
Notebook data.
S25, new sample data is arranged, and increases to existing multiple sample datas in corresponding engineering drawing
In, form new check of drawings model.
Wherein, it is continuously updated check of drawings module, so that intelligent check of drawings is more comprehensively accurate, to improve examining for engineering drawing
Nuclear mass.
Further, and Fig. 7, described the step of intelligent check of drawings is carried out to current engineering drawing are referred to further include:
S26, manually to after completing intelligent check of drawings, by manually checking check of drawings result;
S27, in conjunction with review as a result, modify to check of drawings model/it is perfect.
Wherein, in machine learning, the most important factor for influencing studying system design is letter that environment is provided to system
Breath, or the quality of more specifically information.What is stored in knowledge base is the rule for instructing execution part to act, but ring
Border is various to the information that learning system provides, the difference ratio if the quality of information is relatively high, with rule
It is smaller, then learn part and be easier to handle, if providing rambling guidance to learning system executes specific movement
Specifying information, then learning system needs to delete unnecessary details after obtaining enough data, popularization of summarizing, shape
At the rule that guidance acts, it is put into knowledge base, the task of study part in this way with regard to burdensome, get up also more tired by design
It is difficult.
Because the information that learning system obtains is often incomplete, the reasoning that learning system is carried out is not fully
It is that reliably, it sums up the rule come may be correct, it is also possible to which incorrect, this will be examined by implementation effect, correctly
Rule the efficiency of system can be made to improve, should retain;Incorrect rule should be modified or be deleted from database.
In the present embodiment, it is equally based on machine learning, since the check of drawings rule stored in sample database is check of drawings
Rule, the rule for summing up and is made inferences by this and removes check of drawings, check of drawings structure may be correct, it is also possible to not just
Really, it needing to be verified by manually carrying out review to check of drawings result, correct check of drawings model enables to system effectiveness to improve,
Therefore retained, and incorrect check of drawings model should carry out annotation feedback after compound, examine further according to annotation incorrect
After graph model delete or modified to it and save.
As shown in figure 8, the present invention provides the most preferred embodiment for sorting out processing to the engineering drawing of intelligent check of drawings.
The engineering drawing to intelligent check of drawings sorts out the step of handling and includes:
S31, engineering drawing information is obtained, and corresponding label is arranged according to the information, to reflect the class of the engineering drawing
Other attribute;
S32, combination tag carry out classified finishing to the engineering drawing audited.
Specifically, the label is to be arranged and generated and corresponding engineering figure to the keyword in drawing information area information
Paper matches and is used to reflect can be used for reflecting in the label, in particular to the engineering drawing information area of the drawing self attributes
The noun of the engineering drawing attribute type carries out classified finishing, the efficiency of management to the engineering drawing for having audited completion by label
High and accuracy rate is high.
As described above, only preferred embodiment is not intended to limit the scope of the present invention, Fan Yibenfa
Equivalent change or modification made by bright claim is all that the present invention is covered.
Claims (10)
1. a kind of management method of engineering drawing, which is characterized in that it is preset with the check of drawings model for intelligent checks engineering drawing,
And the identification model for intelligent recognition engineering drawing, the management method the following steps are included:
Content recognition is carried out to the engineering drawing according to identification model;
Intelligent check of drawings is carried out to current engineering drawing according to check of drawings model;
To the engineering drawing classified finishing audited.
2. management method according to claim 1, which is characterized in that the default knowledge graph model the following steps are included:
The a series of recognition rule of the curriculum offering according to involved in engineering drawing;
A series of recognition rules in each engineering drawing arrange and form identification model.
3. management method according to claim 2, which is characterized in that described the step of carrying out content recognition to engineering drawing
Further include:
If there are unidentified regions for engineering drawing, recognition rule corresponding to unidentified region is obtained;
It is increased in a series of existing recognition rules of current engineering drawing, improves identification model again.
4. management method according to claim 1, which is characterized in that the default check of drawings model the following steps are included:
Engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, forms multiple check of drawings sample datas;
Multiple sample datas in each engineering drawing are arranged, by machine learning, establish check of drawings model.
5. management method according to claim 4, which is characterized in that described to carry out intelligent check of drawings to current engineering drawing
Step further include:
If there are unexamined core regions for engineering drawing, the drawing content in the region is identified again according to identification model;
Unexamined core region is audited by artificial check of drawings mode or/and machine check of drawings mode, forms new sample data.
6. management method according to claim 5, which is characterized in that described to carry out intelligent check of drawings to current engineering drawing
Step further include:
New sample data is arranged, and is increased in corresponding engineering drawing in existing multiple sample datas, is formed new
Check of drawings model.
7. management method according to claim 4, which is characterized in that the default check of drawings model the following steps are included:
Manually to after completing intelligent check of drawings, by manually checking check of drawings result;
In conjunction with review as a result, modify to check of drawings model/it is perfect.
8. management method according to claim 1, which is characterized in that it is described to the engineering drawing classification of intelligent check of drawings at
The step of reason includes:
Engineering drawing information is obtained, and corresponding label is arranged according to the information, to reflect the category attribute of the engineering drawing;
Combination tag carries out classified finishing to the engineering drawing audited.
9. management method according to claim 1, it is characterised in that: the engineering drawing is the drawing of PDF format.
10. a kind of management system of engineering drawing, it is characterised in that: the management system includes processing unit and memory module,
The processing unit is stored with computer program, and the computer program can be performed to realize as claim 1 to 9 is any
The step of the method, related data information caused by the memory module storage processing unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910498089.1A CN110399787A (en) | 2019-06-10 | 2019-06-10 | A kind of management system and method for engineering drawing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910498089.1A CN110399787A (en) | 2019-06-10 | 2019-06-10 | A kind of management system and method for engineering drawing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110399787A true CN110399787A (en) | 2019-11-01 |
Family
ID=68323157
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910498089.1A Pending CN110399787A (en) | 2019-06-10 | 2019-06-10 | A kind of management system and method for engineering drawing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110399787A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111401231A (en) * | 2020-03-13 | 2020-07-10 | 华黔科技有限公司 | Engineering drawing identification and verification method and device |
CN111783562A (en) * | 2020-06-12 | 2020-10-16 | 万翼科技有限公司 | Intelligent image examination method and related device |
CN111932198A (en) * | 2020-07-22 | 2020-11-13 | 万翼科技有限公司 | File auditing method and related product |
CN111783562B (en) * | 2020-06-12 | 2024-04-26 | 万翼科技有限公司 | Intelligent drawing examining method and related device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006014097A1 (en) * | 2004-08-04 | 2006-02-09 | Daulet Kulenov | Method for automatically determining the conformity of a normalised electronic image with a face image |
CN102609687A (en) * | 2012-01-31 | 2012-07-25 | 华中科技大学 | Subway construction drawing and engineering parameter automatic identification method |
CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
CN108875599A (en) * | 2018-05-30 | 2018-11-23 | 成都小智审图科技有限公司 | A kind of identification check of drawings method of building trade ENGINEERING CAD drawing |
CN108985293A (en) * | 2018-06-22 | 2018-12-11 | 深源恒际科技有限公司 | A kind of image automation mask method and system based on deep learning |
CN109146419A (en) * | 2018-08-17 | 2019-01-04 | 四川网道科技发展有限公司 | Drawing classification auditing system based on artificial intelligence |
CN109740965A (en) * | 2019-01-22 | 2019-05-10 | 北京市天元网络技术股份有限公司 | A kind of engineering verification analysis method and device |
CN109766590A (en) * | 2018-12-19 | 2019-05-17 | 上海荷福人工智能科技(集团)有限公司 | One kind method for reporting based on artificial intelligence check of drawings and out |
-
2019
- 2019-06-10 CN CN201910498089.1A patent/CN110399787A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006014097A1 (en) * | 2004-08-04 | 2006-02-09 | Daulet Kulenov | Method for automatically determining the conformity of a normalised electronic image with a face image |
CN102609687A (en) * | 2012-01-31 | 2012-07-25 | 华中科技大学 | Subway construction drawing and engineering parameter automatic identification method |
CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
CN108875599A (en) * | 2018-05-30 | 2018-11-23 | 成都小智审图科技有限公司 | A kind of identification check of drawings method of building trade ENGINEERING CAD drawing |
CN108985293A (en) * | 2018-06-22 | 2018-12-11 | 深源恒际科技有限公司 | A kind of image automation mask method and system based on deep learning |
CN109146419A (en) * | 2018-08-17 | 2019-01-04 | 四川网道科技发展有限公司 | Drawing classification auditing system based on artificial intelligence |
CN109766590A (en) * | 2018-12-19 | 2019-05-17 | 上海荷福人工智能科技(集团)有限公司 | One kind method for reporting based on artificial intelligence check of drawings and out |
CN109740965A (en) * | 2019-01-22 | 2019-05-10 | 北京市天元网络技术股份有限公司 | A kind of engineering verification analysis method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111401231A (en) * | 2020-03-13 | 2020-07-10 | 华黔科技有限公司 | Engineering drawing identification and verification method and device |
CN111783562A (en) * | 2020-06-12 | 2020-10-16 | 万翼科技有限公司 | Intelligent image examination method and related device |
CN111783562B (en) * | 2020-06-12 | 2024-04-26 | 万翼科技有限公司 | Intelligent drawing examining method and related device |
CN111932198A (en) * | 2020-07-22 | 2020-11-13 | 万翼科技有限公司 | File auditing method and related product |
CN111932198B (en) * | 2020-07-22 | 2024-04-12 | 万翼科技有限公司 | File auditing method and related products |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Van Buuren | Flexible imputation of missing data | |
Šmilauer et al. | Multivariate analysis of ecological data using CANOCO 5 | |
CN110378206B (en) | Intelligent image examination system and method | |
Rosemann et al. | A model for business process management maturity | |
Rosemann et al. | Towards a business process management maturity model | |
US20210366055A1 (en) | Systems and methods for generating accurate transaction data and manipulation | |
Mohler et al. | Equivalence, comparability, and methodological progress | |
CN111177322A (en) | Ontology model construction method of domain knowledge graph | |
CN102855542A (en) | Evaluation method of 'learning gene' individual learning abilities | |
CN107844558A (en) | The determination method and relevant apparatus of a kind of classification information | |
CN114968788A (en) | Method, apparatus, medium, and device for automatically evaluating programming capability of artificial intelligence algorithm | |
CN110046264A (en) | A kind of automatic classification method towards mobile phone document | |
Bastan et al. | A new technology acceptance model: a mixed-method of grounded theory and system dynamics | |
CN110399787A (en) | A kind of management system and method for engineering drawing | |
CN116775879A (en) | Fine tuning training method of large language model, contract risk review method and system | |
CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
CN111651271A (en) | Multi-task learning semantic annotation method and device based on legal data | |
CN110377768A (en) | It is a kind of intelligently to know drawing system and method | |
Miura et al. | Epilogue: a framework for bioimage analysis | |
Totawar et al. | Research methodology: A step-by-step guide for beginners | |
Chiu et al. | Visualizing design project team and individual progress using NLP: a comparison between latent semantic analysis and Word2Vector algorithms | |
Osman et al. | Interactive scalable abstraction of reverse engineered UML class diagrams | |
Ma et al. | Improving the quality of commit messages in students’ projects | |
CN114780577A (en) | SQL statement generation method, device, equipment and storage medium | |
Wang et al. | Quantitative analysis of requirements evolution across multiple versions of an industrial software product |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191101 |
|
RJ01 | Rejection of invention patent application after publication |