CN110378206B - Intelligent image examination system and method - Google Patents
Intelligent image examination system and method Download PDFInfo
- Publication number
- CN110378206B CN110378206B CN201910498656.3A CN201910498656A CN110378206B CN 110378206 B CN110378206 B CN 110378206B CN 201910498656 A CN201910498656 A CN 201910498656A CN 110378206 B CN110378206 B CN 110378206B
- Authority
- CN
- China
- Prior art keywords
- examination
- engineering
- intelligent
- steps
- engineering 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
Images
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 invention relates to the field of drawing management, in particular to an intelligent drawing examination system and an intelligent drawing examination method, which are applied to engineering drawings, wherein each engineering drawing is at least provided with a label to reflect the attribute of the engineering drawing, and a plurality of drawing examination models are established or/and perfected through manual examination, and the method comprises the following steps: selecting a corresponding examination model according to the label of the current engineering drawing, and carrying out intelligent examination on the engineering drawing; compared with the prior art, the intelligent image examination system and the intelligent image examination method are designed to replace the existing manual image examination, so that the labor cost is reduced, the manual operation is further reduced, on one hand, the image examination efficiency is higher, on the other hand, the manual operation error is reduced, and the image examination accuracy is higher.
Description
Technical Field
The invention relates to the field of drawing management, in particular to an intelligent drawing examination system and an intelligent drawing examination method.
Background
With the economic development and social progress of China, the living standard of people is continuously improved, the city construction is changed day by day, and a large amount of drawings are generated in each city construction project.
The quality of the engineering drawings is the most important part in the good and bad construction, due to the diversity of the construction engineering drawings and the complexity of examination rules, at present, examination of the construction drawings only depends on manual work, the efficiency is low, manual errors are difficult to avoid and the like, and on the other hand, along with the development of the artificial intelligence technology, the artificial intelligence can simulate the thinking mode of a human in the relatively complex technical field to process corresponding problems.
Therefore, designing an efficient and accurate intelligent image reviewing system and method is always a matter of intensive research in the field.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an efficient and accurate intelligent image examination system and method aiming at the defects in the prior art, and overcome the defects of high manual image examination cost, low efficiency and low accuracy.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method is applied to engineering drawings, and the preferred scheme is that the engineering drawings are provided with at least one label to reflect the attributes of the engineering drawings, and a plurality of drawing examination models are established or/and perfected through manual review, and the method comprises the following steps:
and selecting a corresponding examination model according to the label of the current engineering drawing, and carrying out intelligent examination on the engineering drawing.
Wherein, the preferable scheme is that the establishing or/and perfecting the auditing model further comprises the following steps:
examining and approving the engineering drawing by a manual drawing examination mode or/and a machine drawing examination mode to form a plurality of drawing examination sample data;
based on the picture examination sample data corresponding to the engineering drawings with different labels, a plurality of picture examination models are established or/and perfected through machine learning.
Wherein, the preferable scheme is that the establishing or/and perfecting of the examination graph model further comprises the following steps:
after the intelligent image examination is completed, manually rechecking the image examination result;
or after the intelligent image examination is completed, the image examination result is rechecked and annotated and fed back manually;
and adding the rechecking and annotation contents to the general examination graph model for perfecting the general examination graph model.
Wherein, the preferable scheme is that the establishing or/and perfecting of the examination graph model further comprises the following steps:
examining and approving the engineering drawing by a manual drawing examination mode or/and a machine drawing examination mode, acquiring problems in the engineering drawing, and storing and forming drawing examination sample data;
through machine learning, a large amount of examination sample data is sorted and analyzed, and commonality is obtained;
and establishing a trial graph model based on machine learning according to the commonality.
In a preferred embodiment, the method for establishing the intelligent image examination further includes the following steps:
by acquiring the keyword information in the engineering drawing, the label corresponding to the engineering drawing is identified to reflect the attribute of the engineering drawing.
In a preferred embodiment, the method further includes the following steps:
extracting a plurality of keywords in the information of the engineering drawing by identifying the information corresponding to the engineering drawing;
the extracted keywords are sorted and labels of the engineering drawings are generated to reflect the attributes of the engineering drawings;
and classifying the corresponding engineering drawings into corresponding classification groups according to the labels so as to reflect the categories of the engineering drawings.
Preferably, the intelligent image reviewing method further comprises the following steps:
and directionally searching according to the category attribute of the current engineering drawing to obtain the specific drawing content of the engineering drawing.
Wherein, the preferable scheme is that the method for establishing/perfecting the sub-trial graph model further comprises the following steps:
and S31, establishing sub-review graph models, carrying out classification management on the review graph models in the general review graph model according to the category attributes of the engineering drawings, and establishing a sub-review graph model corresponding to each category attribute of the engineering drawings.
Wherein, the preferable scheme is that the method for establishing/perfecting the sub-trial graph model further comprises the following steps:
s32, manually rechecking the examination result and analyzing the annotation result, and identifying the corresponding category attribute;
and S33, adding corresponding rechecking and annotating results to corresponding sub-examination graph models according to the category attributes of the current engineering drawings.
In order to solve the defects of the prior art, the invention further provides an intelligent image examination system, which comprises a processing unit and a storage module, wherein the processing unit stores a computer program, the computer program can be executed to realize the steps of the method, and the storage module stores the relevant data information generated by the processing unit.
Compared with the prior art, the intelligent image examination system and the intelligent image examination method have the advantages that the intelligent image examination system and the intelligent image examination method are designed to replace the existing manual image examination, so that the labor cost is reduced, the manual operation is further reduced, on one hand, the image examination efficiency is higher, on the other hand, the manual operation error is reduced, and the image examination accuracy is higher.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a first flowchart of an intelligent image examination method according to the present invention;
FIG. 2 is a block diagram of an intelligent image examination system according to the present invention;
FIG. 3 is a second flowchart of an intelligent review method of the present invention;
FIG. 4 is a first flowchart of a method for building/refining a general exam graph model according to the present invention;
FIG. 5 is a flow chart diagram II of a method of building/perfecting a sub-audit map model of the present invention;
FIG. 6 is a flow chart III of a method of building/perfecting a sub-inspection map model of the present invention;
FIG. 7 is a fourth flowchart of a method of building/perfecting a sub-audit map model of the present invention;
fig. 8 is a flowchart for identifying a label corresponding to an engineering drawing in the present invention.
Detailed Description
The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1 to 3, the present invention provides a preferred embodiment of an intelligent map viewing method.
Referring to fig. 1, an intelligent map reviewing method is applied to engineering drawings, each of which has at least one label to reflect its attributes, and the method includes the following steps:
s1, establishing or/and perfecting a plurality of examination graph models through manual examination;
and S2, selecting a corresponding examination model according to the label of the current engineering drawing, and intelligently examining the engineering drawing.
Further, referring to fig. 2, the present invention provides a preferred embodiment of an intelligent map-reviewing system.
An intelligent image examination system comprises a processing unit 100 and a storage module 200, wherein the processing unit 100 stores a computer program which can be executed to realize the steps of the method, and the storage module 200 stores relevant data information generated by the processing unit 100.
Further, and referring to fig. 3, the intelligent map viewing method further includes the following steps:
and S3, directionally searching according to the category attribute of the current engineering drawing to obtain the specific drawing content of the engineering drawing.
Specifically, the step of identifying the label of the engineering drawing and directionally searching the attribute of the label is to identify the label of the corresponding engineering drawing by acquiring the keyword information in the engineering drawing so as to reflect the attribute of the label.
The engineering drawings are related drawings for expressing the internal arrangement condition and the external shape of a building, decoration, construction requirements and the like, are divided into building construction drawings, structural construction drawings and equipment construction drawings, and are also bases for examining and approving building engineering projects; in the production and construction, the method is the basis of material preparation and construction; when the construction is completed, quality inspection and acceptance are carried out according to the design requirements of the engineering drawing, and the quality of the engineering is evaluated according to the quality inspection and acceptance; the construction project diagram is also a basis for planning project approximate calculation, budget and final calculation and auditing project cost; the construction project map is a technical document with legal effectiveness; generally, based on the projection principle, according to the drawing standard specified by the state, the shapes, sizes and the like of the built or not built construction projects are accurately expressed on a plane pattern, and the requirements of materials used by the projects, production, installation and the like are marked at the same time.
Preferably, the engineering drawings are drawings in a PDF format.
The label is a label which is used for sorting information in the drawing information area and generating a pair with a corresponding engineering drawing and is used for reflecting the property of the drawing, specifically, a noun which can be used for reflecting the property type of the engineering drawing in the engineering drawing information area includes a general term noun and information content vocabularies included in the general term, the general term noun includes vocabularies such as a drawing name, a drawing type, a designer name, the unit name or a drawing date and the like, the information content included in the general term includes a specific drawing name XXX, a drawing type XXX, a designer name XXX, a unit name XXX or a drawing date XXX and the like, and the common drawing type includes: the construction method comprises the following steps of (1) building construction drawings, structure construction drawings and equipment construction drawings, wherein the building construction drawings comprise a building general plan view, a building elevation view, a building section view and building detailed views; the construction drawings comprise a foundation plan view, a foundation section view, a roof structure arrangement view, a floor structure arrangement view, a column beam plate reinforcement arrangement view, a stair view, a structural member view or table and necessary detailed views; the equipment construction drawing comprises a heating construction drawing, an electrical appliance construction drawing, a ventilation construction drawing and a water supply and drainage construction drawing; the labels are automatically obtained after the engineering drawings are scanned by the intelligent drawing recognition system, and each engineering drawing corresponds to a plurality of labels.
The map examination model is a basis which is constructed by an intelligent map recognition system and can be used for auditing each engineering drawing after machine learning, specifically, the intelligent map examination system sorts and analyzes different map examination data of different engineering drawings through a processing unit to obtain a data commonality, namely, a certain engineering drawing content can be automatically in one-to-one correspondence with the corresponding map examination data to form a map examination model, and the map examination model is automatically stored in a storage module.
Wherein, the processing unit is a computer or a special identification device.
The computer is composed of a hardware system (hardware system) and a software system (software system), the hardware Unit of a conventional computer system can be generally divided into an input Unit, an output Unit, an arithmetic logic Unit, a control Unit, and a memory Unit, wherein the arithmetic logic Unit and the control Unit are collectively called a Central Processing Unit (CPU), i.e., the Processing Unit mentioned in this embodiment, and the memory Unit is the storage Unit mentioned in this embodiment.
Specifically, a large amount of examination drawing data is generated through a large amount of manual examination drawings, the examination drawing data is sorted and analyzed through the processing module 100, so that a plurality of examination drawing models are built or/and perfected, the examination drawing modules are stored in the storage module 200, each examination drawing model is built on the basis that each engineering drawing corresponds to a batch of examination drawing data, therefore, the processing module 100 can select a corresponding examination drawing model in the storage module 200 according to a label of the current engineering drawing and carry out intelligent examination drawing on the engineering drawing, meanwhile, the label of the engineering drawing and the class attribute thereof are in one-to-one correspondence for directly reflecting the class attribute of the engineering drawing, and therefore, directional search can be carried out according to the class attribute of the current engineering drawing, and specific drawing content of the engineering drawing is obtained.
As shown in fig. 4-7, the present invention provides the best embodiment for establishing or/and perfecting an audit model.
Referring to fig. 4, the establishing or/and perfecting the audit model further comprises the following steps:
s11, examining and approving the engineering drawing in a manual drawing examination mode or/and a machine drawing examination mode to form a plurality of drawing examination sample data;
and S12, establishing or/and perfecting a plurality of map-reviewing models through machine learning based on map-reviewing sample data corresponding to engineering drawings with different labels.
Further, and with reference to fig. 5, the creating or/and refining of the trial graph model further comprises the steps of:
s121, examining and approving the engineering drawing in a manual drawing examination mode or/and a machine drawing examination mode, acquiring problems in the engineering drawing, and storing and forming drawing examination sample data;
s122, sorting and analyzing a large amount of examination sample data through machine learning to obtain commonalities;
and S123, establishing a trial graph model based on machine learning according to the commonalities.
Wherein, a part of individuals actually observed or investigated in the research is called sample (sample), and the whole research objects are called population; in order to enable the sample to correctly reflect the overall situation, the overall situation needs to be clearly specified; all units of observation within the population must be homogeneous; in the process of sampling, the randomization principle must be observed; there should be a sufficient number of observation units of the sample; also called as "subsamples". A part of individuals are taken out from the population according to a certain sampling rule; the number of individuals in a sample is referred to as the "sample volume".
In this embodiment, the image examination sample data refers to image examination record data generated in an early manual image examination process, and is used as a basis or a reference for subsequent intelligent image examination, so that intelligent comparison can be performed during intelligent image examination by a machine to find data commonalities, and thus intelligent image examination is completed.
In this embodiment, the data commonality refers to a common point of a large amount of sample data.
Machine Learning (ML) is a multi-field cross subject, relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis and algorithm complexity theory, and is used for specially researching how a computer simulates or realizes the Learning behavior of human beings so as to obtain new knowledge or skills and reorganizing the existing knowledge structure to continuously improve the performance of the computer; it is the core of artificial intelligence, it is the fundamental way to make the computer have intelligence, its application is spread over every field of artificial intelligence, it mainly uses induction, synthesis but not deduction; the environment provides some information to the learning part of the system, the learning part uses the information to modify the knowledge base to improve the efficiency of the system execution part to complete the task, the execution part completes the task according to the knowledge base, and simultaneously feeds back the obtained information to the learning part. In a specific application, the environment, the knowledge base and the execution part determine specific work content.
In this embodiment, machine learning mainly refers to generating a large amount of sample data and sample data commonalities by manually reviewing a drawing, and providing all the sample data and the commonalities thereof to a learning part of a computer system, further, the learning part modifies a sample database by using the information to enhance the efficiency of the computer system to execute part of tasks, further, the executing part completes intelligent drawing review by comparing the specific content of the currently recognized engineering drawing with the content in the sample database according to the sample database, and simultaneously feeds back the intelligent drawing review structure to the learning part, thereby perfecting the sample database.
Specifically, engineering drawings are approved in a manual image approval mode, problems of the current engineering drawings are directly annotated during approval, furthermore, manual approval record data are sorted and analyzed by the processing module and stored in the storage module to form sample data, and a large amount of sample data are obtained after a large amount of engineering drawings are approved manually, so that a sample data base is formed and stored in the storage module; furthermore, through machine learning, the processing module can compare and analyze a large amount of sample data in the sample database to acquire the data commonality; furthermore, an examination model is established based on data commonality, and finally, the specific content of the engineering drawing is located and obtained through a label in the current engineering drawing, and is identified and compared with a large amount of sample data content for drawing examination and approval.
Further, and with reference to fig. 6, the creating or/and refining of the trial graph model further comprises the steps of:
s21, after the intelligent image examination is completed, manually rechecking the image examination result;
s22, or after completing the intelligent image examination, manually rechecking and annotating the image examination result;
and S221, adding the review and annotation contents to the general examination graph model for perfecting the general examination graph model.
Among the most important factors that influence the design of a learning system in machine learning are the information provided by the environment to the system, or more specifically, the quality of the information. The general principle of guiding the execution of part of actions is stored in the knowledge base, but the information provided by the environment to the learning system is various, if the quality of the information is high and the difference from the general principle is small, the learning part is easy to process, and if the information provided to the learning system is the detailed information of disorderly guiding the execution of the specific actions, the learning system needs to delete unnecessary details after obtaining enough data, summarize and popularize to form the general principle of guiding the actions, and put the general principle into the knowledge base, so that the tasks of the learning part are heavy and the design is difficult.
Because the information obtained by the learning system is often incomplete, the reasoning carried out by the learning system is not completely reliable, and the rules summarized by the system can be correct or incorrect, and the rules are checked by the execution effect, so that the correct rules can improve the efficiency of the system and should be reserved; incorrect rules should be modified or deleted from the database.
In this embodiment, also based on machine learning, because the examination rule stored in the sample database is only a general principle of examination, the examination result is reviewed by the rule summarized by reasoning, the examination structure may be correct or incorrect, and the examination result needs to be reviewed and verified manually, and the correct examination model can improve the system performance, so that the examination result is retained, and the incorrect examination model should be subjected to annotation feedback after being composited, and then the incorrect examination model is deleted or modified according to the annotation and stored.
Further, and with reference to fig. 7, the creating or/and refining of the trial graph model further comprises the steps of:
and S13, establishing sub-review graph models, carrying out classification management on the review graph models in the general review graph model according to the category attributes of the engineering drawings, and establishing a sub-review graph model corresponding to each category attribute of the engineering drawings.
Further, and with reference to fig. 7, the method for establishing/perfecting a sub-inspection map model further comprises the following steps:
s14, manually rechecking the examination result and analyzing the annotation result, and identifying the corresponding category attribute;
and S15, adding corresponding rechecking and annotating results to corresponding sub-review graph models according to the category attributes of the current engineering drawings.
Specifically, classification management is carried out on the review models in the general review model according to the category attributes of the engineering drawings, a sub-review model is correspondingly established for each category attribute of the engineering drawings, when intelligent review is carried out, the sub-review models corresponding to the category attributes of the current engineering drawings can be directly selected according to the category attributes of the current engineering drawings, the scope of the review models needing to be selected in machine review is reduced, intelligent review is faster, and accordingly review efficiency is improved.
Further, the review and annotation results of the review result are analyzed manually, the corresponding category attributes of the review and annotation results are identified, and the review and annotation results are added to the corresponding sub-review models according to the category attributes of the review and annotation results for perfecting the sub-review models, so that each engineering drawing with different category attributes corresponds to one corresponding sub-review model, and the accuracy of intelligent review is improved.
As shown in fig. 8, the present invention provides a specific embodiment of identifying a label corresponding to an engineering drawing.
Referring to fig. 8, establishing a plurality of classification groups reflecting different attributes, wherein the step of identifying the label of the corresponding engineering drawing further comprises the following steps:
s31, extracting a plurality of keywords in the information by identifying the information corresponding to the engineering drawing;
s32, arranging the extracted keywords and generating labels of the engineering drawings so as to reflect the attributes of the engineering drawings;
and S33, classifying the corresponding engineering drawings into corresponding classification groups according to the labels so as to reflect the categories of the engineering drawings.
Specifically, firstly, scanning an information area of an engineering drawing, extracting a plurality of keywords in the information area, and setting labels corresponding to the keywords in advance; further, the extracted keywords are sorted to form a keyword list, and finally known items in the keyword list are obtained to produce matched tags; for example: the obtained keywords comprise project names such as construction units, project names, design stages, drawing names, drawing numbers, drawing dates and the like, and specific information in the project names, the keywords are sorted according to specific practical conditions to produce a keyword list, and all labels corresponding to all the keywords in the keyword list are displayed to reflect the attributes of the engineering drawings; furthermore, the engineering drawings are classified and sorted into corresponding classification groups according to the labels so as to reflect the categories of the engineering drawings.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the scope of the present invention, but rather as embodying the invention in a wide variety of equivalent variations and modifications within the scope of the appended claims.
Claims (9)
1. An intelligent map examination method is applied to engineering drawings, and is characterized in that each engineering drawing is provided with at least one label to reflect the attribute of the engineering drawing, and a plurality of map examination models are established or/and perfected through manual review, wherein the method comprises the following steps:
examining and approving the engineering drawing by a manual drawing examination mode or/and a machine drawing examination mode to form a plurality of drawing examination sample data;
establishing or/and perfecting a plurality of examination model through machine learning based on examination sample data corresponding to engineering drawings with different labels;
and selecting a corresponding examination model according to the label of the current engineering drawing, and carrying out intelligent examination on the engineering drawing.
2. The intelligent image examination method according to claim 1, wherein the establishing or/and perfecting the image examination model further comprises the following steps:
after the intelligent image examination is completed, manually rechecking the image examination result;
or after the intelligent image examination is completed, the image examination result is rechecked and annotated and fed back manually;
and adding the rechecking and annotation contents to the general examination graph model for perfecting the general examination graph model.
3. The intelligent image examination method according to claim 1 or 2, wherein the establishing or/and perfecting the image examination model further comprises the following steps:
examining and approving the engineering drawing by a manual drawing examination mode or/and a machine drawing examination mode, acquiring problems in the engineering drawing, and storing and forming drawing examination sample data;
through machine learning, a large amount of examination sample data is sorted and analyzed, and commonality is obtained;
and establishing a trial graph model based on machine learning according to the commonality.
4. The intelligent picture examination method according to claim 1, wherein the intelligent picture examination method is established by the method further comprising the following steps:
by acquiring the keyword information in the engineering drawing, the label corresponding to the engineering drawing is identified to reflect the attribute of the engineering drawing.
5. The intelligent map reviewing method of claim 4, wherein a plurality of classification groups reflecting different attributes are established, and the step of identifying the label of the corresponding engineering drawing further comprises the steps of:
extracting a plurality of keywords in the information of the engineering drawing by identifying the information corresponding to the engineering drawing;
the extracted keywords are sorted and labels of the engineering drawings are generated to reflect the attributes of the engineering drawings;
and classifying the corresponding engineering drawings into corresponding classification groups according to the labels so as to reflect the categories of the engineering drawings.
6. The intelligent image examination method according to claim 5, further comprising the following steps:
and directionally searching according to the category attribute of the current engineering drawing to obtain the specific drawing content of the engineering drawing.
7. The intelligent picture examination method according to claim 1, wherein the method for establishing/perfecting the sub-picture examination model further comprises the following steps:
and S31, establishing sub-review graph models, carrying out classification management on the review graph models in the general review graph model according to the category attributes of the engineering drawings, and establishing a sub-review graph model corresponding to each category attribute of the engineering drawings.
8. The intelligent picture examination method according to claim 7, wherein the establishing/perfecting sub-picture examination model method further comprises the following steps:
s32, manually rechecking the examination result and analyzing the annotation result, and identifying the corresponding category attribute;
and S33, adding corresponding rechecking and annotating results to corresponding sub-examination graph models according to the category attributes of the current engineering drawings.
9. An intelligent picture examination system is characterized in that: the smart map recognition system comprises a processing unit storing a computer program executable to implement the steps of the method according to any one of claims 1 to 8 and a storage module storing the relevant data information generated by the 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 CN110378206A (en) | 2019-10-25 |
| CN110378206B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111581683B (en) * | 2020-04-27 | 2023-07-04 | 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 |
| CN111832445B (en) * | 2020-06-29 | 2024-06-18 | 深圳市万翼数字技术有限公司 | Positioning method and related device for engineering drawing |
| CN112486384B (en) * | 2020-11-27 | 2022-12-20 | 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 |
| CN114511303B (en) * | 2022-04-06 | 2022-07-22 | 四川省大数据中心 | Investigation result examination system, method and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
| 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 |
| 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 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2364813B (en) * | 2000-07-13 | 2004-12-29 | Vhsoft Technologies Company Lt | Computer automated process for analysing and interpreting engineering drawings |
| CN103064993A (en) * | 2011-10-20 | 2013-04-24 | 鸿富锦精密工业（深圳）有限公司 | Processing system and method of size number information |
| 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 |
| CN108805510B (en) * | 2017-04-27 | 2021-11-23 | 中国铁道科学研究院铁道建筑研究所 | Construction drawing design BIM model compliance auditing method and system |
| 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 |
-
2019
- 2019-06-10 CN CN201910498656.3A patent/CN110378206B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729635A (en) * | 2012-10-10 | 2014-04-16 | 三星泰科威株式会社 | Apparatus and method for providing digital drawing |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378206A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378206B (en) | Intelligent image examination system and method | |
| Pearson et al. | Machine learning using digitized herbarium specimens to advance phenological research | |
| CN105955889B (en) | A kind of graphical interfaces automated testing method | |
| Soibelman et al. | Management and analysis of unstructured construction data types | |
| Liu et al. | Crowdsourcing construction activity analysis from jobsite video streams | |
| CN111652232B (en) | Bill identification method and device, electronic equipment and computer readable storage medium | |
| US20210366055A1 (en) | Systems and methods for generating accurate transaction data and manipulation | |
| CN112597038B (en) | Software defect prediction method and system | |
| CN110554995A (en) | Deep learning model management method and system | |
| CN109101519B (en) | Information acquisition system and heterogeneous information fusion system | |
| CN111177322A (en) | Ontology model construction method of domain knowledge graph | |
| JP2005501321A (en) | How to automatically index documents | |
| CN110046264A (en) | A kind of automatic classification method towards mobile phone document | |
| Nagwani et al. | Predicting expert developers for newly reported bugs using frequent terms similarities of bug attributes | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN110399787A (en) | A kind of management system and method for engineering drawing | |
| Lonij et al. | Open-world visual recognition using knowledge graphs | |
| CN116703328B (en) | Project review method and system | |
| CN106503050B (en) | Method and system for recommending reading articles based on big data | |
| Dasgupta et al. | No patterns in pattern recognition: A systematic literature review | |
| CN115205877A (en) | Irregular typesetting invoice document layout prediction method and device and storage medium | |
| CN115829925A (en) | Appearance defect detection method and device, computer equipment and storage medium | |
| CN114780577A (en) | SQL statement generation method, device, equipment and storage medium | |
| CN111209375B (en) | Universal clause and document matching method | |
| CN109299381B (en) | Software defect retrieval and analysis system and method based on semantic concept |
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. |