CN110378206A - A kind of intelligence Audit System and method - Google Patents
A kind of intelligence Audit System and method Download PDFInfo
- Publication number
- CN110378206A CN110378206A CN201910498656.3A CN201910498656A CN110378206A CN 110378206 A CN110378206 A CN 110378206A CN 201910498656 A CN201910498656 A CN 201910498656A CN 110378206 A CN110378206 A CN 110378206A
- Authority
- CN
- China
- Prior art keywords
- check
- drawings
- engineering drawing
- model
- intelligence
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to management of blueprint fields, more particularly to a kind of intelligent Audit System and method, applied in engineering drawing, the engineering drawing at least has a label, it to reflect its attribute, and establishes by manual examination and verification or/and improves multiple check of drawings models, the described method comprises the following steps: according to the label of current engineering drawing, corresponding check of drawings model is selected, and intelligent check of drawings is carried out to engineering drawing;Compared with prior art, the present invention is by designing a kind of intelligent Audit System and method, instead of existing artificial check of drawings, reduce cost of labor, manual operation is further reduced, on the one hand may make that check of drawings is more efficient, on the other hand, manual operation error can be reduced, so that check of drawings accuracy rate is higher.
Description
Technical field
The present invention relates to management of blueprint fields, and in particular to a kind of intelligence Audit System and method.
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,
A large amount of drawing can be generated in each City Construction Project.
Wherein, the quality of engineering drawing is to be related to a most important ring in construction quality, due to architectural engineering drawing
Diversity and the complexity for examining rule, currently, the audit of architectural drawing relies only on manually, there are low efficiencys, artificial to lose
The problems such as being accidentally difficult to avoid that, also, on the other hand, with the development of artificial intelligence technology, artificial intelligence can be opposite
The form of thinking of complicated technical field simulation people, handles corresponding problem.
Therefore, a kind of efficient and accurate intelligent Audit System and method are designed, is always asking for this field primary study
Topic.
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, it is a kind of efficiently and accurate to provide
Intelligent Audit System and method, overcome the defect that artificial check of drawings cost is big and low efficiency, accuracy rate be not high.
The technical solution adopted by the present invention to solve the technical problems is: providing a kind of intelligent check of drawings method, is applied to work
In journey drawing, preferred embodiment is, the engineering drawing at least has a label, to reflect its attribute, and by artificial
Audit establishes or/and improves multiple check of drawings models, the described method comprises the following steps:
According to the label of current engineering drawing, corresponding check of drawings model is selected, and intelligent check of drawings is carried out to engineering drawing.
Wherein, preferred version is that the foundation or/and perfect audit model are further comprising the steps of:
Engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, forms multiple check of drawings samples
Data;
Check of drawings sample data corresponding to engineering drawing based on different labels is established or/and perfect by machine learning
Multiple check of drawings models.
Wherein, preferred version is the foundation or/and to improve check of drawings model further comprising the steps of:
After completing intelligent check of drawings, by manually checking check of drawings result;
Alternatively, after completing intelligent check of drawings, by manually check of drawings result being checked and being annotated feedback;
Review and annotation content are increased into total check of drawings model, for improving total check of drawings model.
Wherein, preferred version is the foundation or/and to improve check of drawings model further comprising the steps of:
Engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, obtains and is deposited in engineering drawing
The problem of, and store form check of drawings sample data;
By machine learning, a large amount of check of drawings sample data of finishing analysis obtains general character;
The check of drawings model based on machine learning is established according to general character.
Wherein, preferred version is that establish the intelligent check of drawings method further include step:
By obtaining the key word information in engineering drawing, so that the label of corresponding engineering drawing is identified, to reflect its category
Property.
Wherein, preferred version is to establish the classification group of multiple reflection different attributes, the identification corresponding engineering drawing
Label is further comprising the steps of:
By identifying the information of corresponding engineering drawing, multiple keywords in its information are extracted;
The label of the engineering drawing is arranged and is generated, to the keyword of extraction to reflect its attribute;
Corresponding engineering drawing is sorted out into corresponding classification group according to label, to reflect the class of the engineering drawing
Not.
Wherein, preferred version is that the intelligent check of drawings method is further comprising the steps of:
According to the category attribute of current engineering drawing, orientation is searched, and obtains the specific drawing content of engineering drawing.
Wherein, preferred version is that described to establish/improve sub- check of drawings model method further comprising the steps of:
S31, sub- check of drawings model is established, the check of drawings model in total check of drawings model is carried out according to the category attribute of engineering drawing
Classification Management, to the sub- check of drawings model of each category attribute correspondence establishment one of engineering drawing.
Wherein, preferred version is that described to establish/improve sub- check of drawings model method further comprising the steps of:
S32, the review and annotation result that manually carry out to check of drawings result are analyzed, and identifies its corresponding classification category
Property;
S33. according to the category attribute of current engineering drawing, its corresponding review and annotation result are increased into corresponding son
In check of drawings model.
For the defect for solving the prior art, the present invention also provides a kind of intelligent Audit System, the intelligence knows drawing system packet
Include processing unit and memory module, the processing unit is stored with computer program, the computer program can be performed with
The step of realizing the above method, related data information caused by the memory module storage processing unit.
The beneficial effects of the present invention are, compared with prior art, the present invention by design a kind of intelligent Audit System and
Method reduces cost of labor instead of existing artificial check of drawings, further reduces manual operation, on the one hand check of drawings may make to imitate
Rate is higher, on the other hand, manual operation error can be reduced, so that check of drawings accuracy rate is higher.
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 a kind of flow chart one of intelligence check of drawings method in the present invention;
Fig. 2 is a kind of structural block diagram of intelligence Audit System in the present invention;
Fig. 3 is a kind of flowchart 2 of intelligence check of drawings method in the present invention;
Fig. 4 is the flow chart one that total check of drawings model method is established/improved in the present invention;
Fig. 5 is the flowchart 2 that sub- check of drawings model method is established/improved in the present invention;
Fig. 6 is the flow chart 3 that sub- check of drawings model method is established/improved in the present invention;
Fig. 7 is the flow chart four that sub- check of drawings model method is established/improved in the present invention;
Fig. 8 is the flow chart that the label of corresponding engineering drawing is identified in the present invention.
Specific embodiment
Now in conjunction with attached drawing, elaborate to presently preferred embodiments of the present invention.
As shown in Figure 1-Figure 3, the present invention provides a kind of most preferred embodiment of intelligent check of drawings method.
With reference to Fig. 1, a kind of intelligence check of drawings method is applied in engineering drawing, and the engineering drawing at least has a mark
Label, to reflect its attribute, the described method comprises the following steps:
S1, multiple check of drawings models are established or/and improved by manual examination and verification;
S2, according to the label of current engineering drawing, select corresponding check of drawings model, and intelligence is carried out to engineering drawing and is examined
Figure.
Further, with reference to Fig. 2, the present invention provides a kind of most preferred embodiment of intelligent Audit System.
A kind of intelligence Audit System, it includes processing unit 100 and memory module 200, the place that the intelligence, which knows drawing system,
The step of reason unit 100 is stored with computer program, and the computer program can be performed to realize the above method, it is described to deposit
Store up related data information caused by 200 storage processing unit 100 of module.
Further, and Fig. 3 is referred to, the intelligence check of drawings method is further comprising the steps of:
S3, according to the category attribute of current engineering drawing, orientation is searched, and the specific drawing content of engineering drawing is obtained.
Wherein, the label orientation of recognitive engineering drawing searches its attribute specifically by the keyword obtained in engineering drawing
Information, so that the label of corresponding engineering drawing is identified, to reflect its attribute.
Wherein, engineering drawing refers to the inside deployment scenarios for indicating building, outer shape, and fit up, construct,
The related drawing of the contents such as construction requirement is divided into architectural working drawing, structural working drawing, equipment construction figure, it is also examination & approval building
The foundation of engineering project;In production and construction, it is the foundation of stock and construction;It, be according to engineering drawing when completion of works
Design requirement carries out quality inspection and acceptance, and with this evaluation engineering quality good or not;Architectural drawings still work out Budgetary Estimates,
Budget and final accounts and the foundation for auditing project cost;Architectural drawings are the technological documents with legal effect;Usually to throw
Based on shadow principle, by the drafting standard of national regulation, having built up or shape, the size of still unestablished architectural engineering etc.
Pattern in the plane is accurately expressed, and indicates the requirement of material used in engineering and production, installation etc. simultaneously, due to work
The mission requirements in Cheng Jianshe each stage are different, and content, depth and mode expressed by all kinds of drawings also have difference.
Preferably, the engineering drawing is the drawing of PDF format.
Wherein, the label is to be arranged and generated to match and be used to corresponding engineering drawing to drawing information area information
Reflecting in the label, in particular to the engineering drawing information area of the drawing self attributes can be used for reflecting the engineering drawing category
The noun of property type, including information content vocabulary included in generic items noun and generic items, the generic items noun packet
Such as designation of drawing, drawing type, designer's name, the organization or drawing date etc. vocabulary is included, it is described general
The information content included in is then specific designation of drawing XXX, drawing type XXX, designer's name XXX, the unit name
Claiming XXX or drawing date XXX etc., common drawing type includes: architectural working drawing, structural working drawing and equipment construction figure,
Its architectural working drawing includes site plan, architectural plan, architectural elevation, architectural section and building detail drawing;Structure
Construction drawing includes foundation plan, basic sectional view, roof structure layout drawing, floor structure arrangement figure, column beam slab arrangement of reinforcement, building
Ladder figure, structural elements figure or table and necessary detail drawing;Equipment construction figure includes heating construction drawing, electric appliance construction drawing, divulges information and apply
Work figure and water supply and drainage construction figure;The label knows automatic acquisition after drawing system is scanned engineering drawing for intelligence, and every
One engineering drawing corresponds to multiple labels.
Wherein, the check of drawings model refers to that intelligence knowledge drawing system constructed can be to each engineering based on after machine learning
The foundation that drawing is audited, finishing analysis difference engineering drawing is not through the processing unit for the specially described intelligent Audit System
With check of drawings data, obtain a kind of data general character, can automatically by the corresponding check of drawings data of a certain engineering drawing content one by one
It is mapped, forms check of drawings model, and be 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, a large amount of check of drawings data are generated by a large amount of artificial check of drawings, it is arranged by processing module 100
Analysis to establish or/and improve multiple check of drawings models, and multiple check of drawings modules is stored in memory module 200, wherein
Each check of drawings model foundation is on the basis of the corresponding a collection of check of drawings data of each engineering drawing, therefore processing module 100 can root
According to the label of current engineering drawing, corresponding check of drawings model is selected in memory module 200, and intelligence is carried out to engineering drawing and is examined
Figure, simultaneously as the label of engineering drawing and its category attribute are corresponded for intuitively reflecting the engineering drawing category attribute
, therefore can orient and search, to obtain the specific drawing content of engineering drawing according to the category attribute of current engineering drawing.
As shown in figs. 4-7, the present invention provides the most preferred embodiment established or/and improve audit model.
With reference to Fig. 4, the foundation or/and perfect audit model are further comprising the steps of:
S11, engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, forms multiple checks of drawings
Sample data;
Check of drawings sample data corresponding to S12, the engineering drawing based on different labels, by machine learning, establish or/and
Improve multiple check of drawings models.
Further, and Fig. 5 is referred to, the foundation or/and to improve check of drawings model further comprising the steps of:
S121, engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, obtains engineering drawing
The problem of, and store and form check of drawings sample data;
S122, pass through machine learning, a large amount of check of drawings sample data of finishing analysis, acquisition general character;
S123, the check of drawings model based on machine learning is established according to general character.
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, general character refers to the general properties that different things have jointly, and in the present embodiment, the data general character refers to
The common ground of great amount of samples data.
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 sample by artificial check of drawings
Data general character, and all sample datas and its general character are supplied to the study part of computer system, further, learn part
Sample database is modified using these information, is further held with promoting the efficiency of computer system execution part completion task
Row part is carried out according to sample database, and by content in the particular content and sample database of the engineering drawing currently recognized
It compares and completes intelligent check of drawings, while giving study part intelligent check of drawings structural feedback, to improve sample database.
Specifically, engineering drawing is examined by artificial check of drawings mode, directly to current engineering drawing when examination & approval
Problem is annotated, and further, the processing module carries out finishing analysis to artificial approval record data, and stores it in
In memory module, sample data is formed, a large amount of sample data will be obtained after manually examining to a large amount of engineering drawing,
To form sample database, and store in a storage module;Further, by machine learning, processing module can be to sample
Great amount of samples data in database are compared, and obtain its data general character;Further, it is built based on data general character
Vertical check of drawings model, finally, by the label in current engineering drawing, positioning obtains the particular content of the engineering drawing, and by its
Identification, which is carried out, with great amount of samples data content compares carry out plan approval.
Further, and Fig. 6 is referred to, the foundation or/and to improve check of drawings model further comprising the steps of:
S21, after completing intelligent check of drawings, by manually checking check of drawings result;
S22 or, after completing intelligent check of drawings, by manually check of drawings result being checked and being annotated feedback;
S221, review and annotation content are increased into total check of drawings model, for improving total check of drawings model.
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.
Further, and Fig. 7 is referred to, the foundation or/and to improve check of drawings model further comprising the steps of:
S13, sub- check of drawings model is established, the check of drawings model in total check of drawings model is carried out according to the category attribute of engineering drawing
Classification Management, to the sub- check of drawings model of each category attribute correspondence establishment one of engineering drawing.
Further, and Fig. 7 is referred to, described to establish/improve sub- check of drawings model method further comprising the steps of:
S14, the review and annotation result that manually carry out to check of drawings result are analyzed, and identifies its corresponding classification category
Property;
S15, according to the category attribute of current engineering drawing, its corresponding review and annotation result are increased into corresponding son
In check of drawings model.
Specifically, Classification Management is carried out to the check of drawings model in total check of drawings model according to the category attribute of engineering drawing, it is right
The sub- check of drawings model of each category attribute correspondence establishment one of engineering drawing can be according to current when carrying out intelligent check of drawings
The category attribute of engineering drawing directly selects the sub- check of drawings model under its corresponding category attribute, reduces and needs to select in machine check of drawings
Check of drawings model scope so that intelligent check of drawings is quicker, to improve check of drawings efficiency.
Further, the review and annotation result that manually carry out to check of drawings result are analyzed, and identifies that its is corresponding
Category attribute, and according to review and annotation resulting class attribute, and increased in corresponding sub- check of drawings model, it has been used for
It is apt to sub- check of drawings model, so that the corresponding a kind of corresponding sub- check of drawings model of the engineering drawing of each different classes of attribute, is used
In the accuracy for improving intelligent check of drawings.
As shown in figure 8, the present invention provides the specific embodiment of the label of identification corresponding engineering drawing.
With reference to Fig. 8, the classification group of multiple reflection different attributes is established, the label of the identification corresponding engineering drawing also wraps
Include following steps:
S31, the information by identifying corresponding engineering drawing, extract multiple keywords in its information;
S32, the label that the keyword of extraction is arranged and generates the engineering drawing, to reflect its attribute;
S33, corresponding engineering drawing is sorted out into corresponding classification group according to label, to reflect the engineering drawing
Classification.
Specifically, firstly, the information area of Scan Engineering Drawings, extracts multiple keywords in its information area, then to each
One-to-one label therewith is set in advance in a keyword;Further, the keyword of extraction arrange and form key
Word list, the known terms finally obtained in lists of keywords produce matched label;Such as: include in the keyword got
Construction unit, the design phase, designation of drawing, figure number, goes out in the project names such as figure date and its project name engineering name
Specifying information, then be ranked up production lists of keywords according to specifically actual conditions, and show institute in the lists of keywords
There are the corresponding all labels of keyword, to reflect the attribute of the engineering drawing;Further, according to label by engineering drawing into
Row classified finishing is into corresponding classification group, to reflect the classification of engineering drawing.
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 intelligence check of drawings method, is applied in engineering drawing, which is characterized in that the engineering drawing at least has a mark
Label to reflect its attribute, and are established by manual examination and verification or/and improve multiple check of drawings models, the described method comprises the following steps:
According to the label of current engineering drawing, corresponding check of drawings model is selected, and intelligent check of drawings is carried out to engineering drawing.
2. intelligence check of drawings method according to claim 1, which is characterized in that the foundation or/and perfect audit model are also
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;
Check of drawings sample data corresponding to engineering drawing based on different labels is established or/and is improved and is multiple by machine learning
Check of drawings model.
3. intelligence check of drawings method according to claim 1, which is characterized in that described to establish or/and improve check of drawings model also
The following steps are included:
After completing intelligent check of drawings, by manually checking check of drawings result;
Alternatively, after completing intelligent check of drawings, by manually check of drawings result being checked and being annotated feedback;
Review and annotation content are increased into total check of drawings model, for improving total check of drawings model.
4. intelligence check of drawings method according to claim 2 or 3, which is characterized in that described to establish or/and improve check of drawings model
It is further comprising the steps of:
Engineering drawing is examined by artificial check of drawings mode or/and machine check of drawings mode, is obtained present in engineering drawing
Problem, and store and form check of drawings sample data;
By machine learning, a large amount of check of drawings sample data of finishing analysis obtains general character;
The check of drawings model based on machine learning is established according to general character.
5. intelligence check of drawings method according to claim 1, which is characterized in that establishing the intelligent check of drawings method further includes one
Lower step:
By obtaining the key word information in engineering drawing, so that the label of corresponding engineering drawing is identified, to reflect its attribute.
6. intelligence check of drawings method according to claim 5, which is characterized in that establish the sorting group of multiple reflection different attributes
Not, the label of the identification corresponding engineering drawing is further comprising the steps of:
By identifying the information of corresponding engineering drawing, multiple keywords in its information are extracted;
The label of the engineering drawing is arranged and is generated, to the keyword of extraction to reflect its attribute;
Corresponding engineering drawing is sorted out into corresponding classification group according to label, to reflect the classification of the engineering drawing.
7. intelligence check of drawings method according to claim 6, which is characterized in that the intelligence check of drawings method further includes following step
It is rapid:
According to the category attribute of current engineering drawing, orientation is searched, and obtains the specific drawing content of engineering drawing.
8. intelligence check of drawings method according to claim 2, which is characterized in that described to establish/improve sub- check of drawings model method
It is further comprising the steps of:
S31, sub- check of drawings model is established, is classified according to the category attribute of engineering drawing to the check of drawings model in total check of drawings model
Management, to the sub- check of drawings model of each category attribute correspondence establishment one of engineering drawing.
9. intelligence check of drawings method according to claim 8, which is characterized in that described to establish/improve sub- check of drawings model method
It is further comprising the steps of:
S32, the review and annotation result that manually carry out to check of drawings result are analyzed, and identifies its corresponding category attribute;
S33. according to the category attribute of current engineering drawing, its corresponding review and annotation result are increased into corresponding sub- check of drawings
In model.
10. a kind of intelligence Audit System, it is characterised in that: it includes processing unit and memory module, institute that the intelligence, which knows drawing system,
It states processing unit and is stored with computer program, the computer program can be performed to realize such as any one of claim 1 to 9
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 |
---|---|---|---|
CN201910498656.3A CN110378206B (en) | 2019-06-10 | 2019-06-10 | Intelligent image examination system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910498656.3A CN110378206B (en) | 2019-06-10 | 2019-06-10 | Intelligent image examination system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110378206A true CN110378206A (en) | 2019-10-25 |
CN110378206B CN110378206B (en) | 2021-09-17 |
Family
ID=68249895
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910498656.3A Active CN110378206B (en) | 2019-06-10 | 2019-06-10 | Intelligent image examination system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110378206B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047274A (en) * | 2019-11-12 | 2020-04-21 | 深圳市毕美科技有限公司 | Method and system for examining engineering design drawing |
CN111581683A (en) * | 2020-04-27 | 2020-08-25 | 深圳市华星光电半导体显示技术有限公司 | Display panel information extraction method and device and electronic equipment |
CN111832445A (en) * | 2020-06-29 | 2020-10-27 | 万翼科技有限公司 | Engineering drawing positioning method and related device |
CN112486384A (en) * | 2020-11-27 | 2021-03-12 | 万翼科技有限公司 | Picture examination processing method and related device |
CN112507431A (en) * | 2020-12-04 | 2021-03-16 | 国泰新点软件股份有限公司 | Intelligent image examination method and device based on BIM model and storage medium |
CN114511303A (en) * | 2022-04-06 | 2022-05-17 | 四川省大数据中心 | Investigation result examination system, method and equipment |
US11752639B2 (en) | 2022-01-21 | 2023-09-12 | Saudi Arabian Oil Company | Engineering drawing review using robotic process automation |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2364813A (en) * | 2000-07-13 | 2002-02-06 | Vhsoft Technologies Company Lt | Computer automated process for analysing and interpreting engineering drawings |
US20130103361A1 (en) * | 2011-10-20 | 2013-04-25 | Hon Hai Precision Industry Co., Ltd. | Computing device, storage medium and method for processing dimension numbers using the computing device |
CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
CN106067101A (en) * | 2016-08-02 | 2016-11-02 | 杭州凯达电力建设有限公司 | A kind of distribution power engineering acceptance method and system |
CN108805510A (en) * | 2017-04-27 | 2018-11-13 | 中国铁道科学研究院铁道建筑研究所 | A kind of construction drawing design BIM model compliance checking methods and system |
CN108920048A (en) * | 2018-06-06 | 2018-11-30 | 武汉新迪数字工程***有限公司 | Large scale drawing browsing method, system, server and computer readable storage medium |
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 |
CN109002824A (en) * | 2018-06-27 | 2018-12-14 | 淮阴工学院 | A kind of architectural drawing label information detection method based on OpenCV |
CN109086735A (en) * | 2018-08-17 | 2018-12-25 | 四川网道科技发展有限公司 | A kind of drawing examination system based on big data |
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 |
-
2019
- 2019-06-10 CN CN201910498656.3A patent/CN110378206B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2364813A (en) * | 2000-07-13 | 2002-02-06 | Vhsoft Technologies Company Lt | Computer automated process for analysing and interpreting engineering drawings |
US6941000B2 (en) * | 2000-07-13 | 2005-09-06 | Vhsoft Ip Company Limited | Computer automated process for analyzing and interpreting engineering drawings |
US20130103361A1 (en) * | 2011-10-20 | 2013-04-25 | Hon Hai Precision Industry Co., Ltd. | Computing device, storage medium and method for processing dimension numbers using the computing device |
CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
CN106067101A (en) * | 2016-08-02 | 2016-11-02 | 杭州凯达电力建设有限公司 | A kind of distribution power engineering acceptance method and system |
CN108805510A (en) * | 2017-04-27 | 2018-11-13 | 中国铁道科学研究院铁道建筑研究所 | A kind of construction drawing design BIM model compliance checking methods and system |
CN108920048A (en) * | 2018-06-06 | 2018-11-30 | 武汉新迪数字工程***有限公司 | Large scale drawing browsing method, system, server and computer readable storage medium |
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 |
CN109002824A (en) * | 2018-06-27 | 2018-12-14 | 淮阴工学院 | A kind of architectural drawing label information detection method based on OpenCV |
CN109086735A (en) * | 2018-08-17 | 2018-12-25 | 四川网道科技发展有限公司 | A kind of drawing examination system based on big data |
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 |
Non-Patent Citations (2)
Title |
---|
WANJING DING: "Intelligent Assessment System of Mechanical Drawing Job Based on Entity Comparison", 《SPRINGER BERLIN HEIDELBERG,2012》 * |
王亚楠 等: "基于BIM的混凝土框架结构施工图智能化审图技术探索", 《应用技术学报》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047274A (en) * | 2019-11-12 | 2020-04-21 | 深圳市毕美科技有限公司 | Method and system for examining engineering design drawing |
CN111047274B (en) * | 2019-11-12 | 2023-08-11 | 深圳市毕美科技有限公司 | Engineering design drawing examination method and system |
CN111581683A (en) * | 2020-04-27 | 2020-08-25 | 深圳市华星光电半导体显示技术有限公司 | Display panel information extraction method and device and electronic equipment |
US11880910B2 (en) | 2020-04-27 | 2024-01-23 | Shenzhen China Star Optoelectronics Semiconductor Display Technology Co., Ltd. | Method for extracting information from a display panel, device, and electronic device |
CN111832445A (en) * | 2020-06-29 | 2020-10-27 | 万翼科技有限公司 | Engineering drawing positioning method and related device |
CN112486384A (en) * | 2020-11-27 | 2021-03-12 | 万翼科技有限公司 | Picture examination processing method and related device |
CN112507431A (en) * | 2020-12-04 | 2021-03-16 | 国泰新点软件股份有限公司 | Intelligent image examination method and device based on BIM model and storage medium |
US11752639B2 (en) | 2022-01-21 | 2023-09-12 | Saudi Arabian Oil Company | Engineering drawing review using robotic process automation |
CN114511303A (en) * | 2022-04-06 | 2022-05-17 | 四川省大数据中心 | Investigation result examination system, method and equipment |
CN114511303B (en) * | 2022-04-06 | 2022-07-22 | 四川省大数据中心 | Investigation result examination system, method and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110378206B (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378206A (en) | A kind of intelligence Audit System and method | |
CN108287822A (en) | A kind of Chinese Similar Problems generation System and method for | |
CN108717433A (en) | A kind of construction of knowledge base method and device of programming-oriented field question answering system | |
CN111325529A (en) | Talent evaluation-based personnel and post matching method and system | |
CN1794234A (en) | Data semanticizer | |
CN107291902A (en) | Automatic marking method is checked in a kind of popular contribution based on hybrid classification technology | |
CN111177322A (en) | Ontology model construction method of domain knowledge graph | |
CN104536881A (en) | Public testing error report priority sorting method based on natural language analysis | |
CN111651270B (en) | Visualization method and device for completing multitask semantic annotation on legal data | |
CN108256022A (en) | Talent evaluation model building method and personnel evaluation methods and system | |
CN110096569A (en) | A kind of crowd survey personnel set recommended method | |
JP2005501321A (en) | How to automatically index documents | |
US20220327398A1 (en) | Technology maturity judgment method and system based on science and technology data | |
CN103955429B (en) | Determine the method and device of regression test scope | |
CN110399787A (en) | A kind of management system and method for engineering drawing | |
CN110377768A (en) | It is a kind of intelligently to know drawing system and method | |
CN106503050B (en) | Method and system for recommending reading articles based on big data | |
CN111651271B (en) | Multi-task learning semantic annotation method and device based on legal data | |
CN110399510A (en) | A kind of the check of drawings method for pushing and system of engineering drawing | |
CN110414819B (en) | Work order scoring method | |
TWI695285B (en) | Regression method and system based on system program infrastructure | |
Kobets et al. | Creation of Logical Models for Conducting Forensic Linguistic Expertise | |
CN101236615A (en) | Intelligent pronunciation learning material creation method | |
Ryabinin et al. | Ontology-driven data mining platform for fuzzy classification of mental maps | |
Zhang et al. | Influencing factors of the development of green building by designers based on grounded theory |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230629 Address after: A601, Zhongke Naneng Building, No. 06 Yuexing 6th Road, Gaoxin District Community, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province, 518063 Patentee after: Shenzhen Wanyi Digital Technology Co.,Ltd. Address before: 519000 room 105-24914, No.6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province (centralized office area) Patentee before: WANYI TECHNOLOGY Co.,Ltd. |