CN112486384B

CN112486384B - Picture examination processing method and related device

Info

Publication number: CN112486384B
Application number: CN202011368332.7A
Authority: CN
Inventors: 李晨楠
Original assignee: Wanyi Technology Co Ltd
Current assignee: Shenzhen Wanyi Digital Technology Co ltd
Priority date: 2020-11-27
Filing date: 2020-11-27
Publication date: 2022-12-20
Anticipated expiration: 2040-11-27
Also published as: CN112486384A

Abstract

The embodiment of the application discloses a picture examination processing method and a related device, comprising the following steps: inputting a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset drawing examination rule in the target engineering drawing; marking the reference abnormal area on the target engineering drawing, wherein the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, and the problem mark is used for explaining the abnormal condition of the reference abnormal area; determining a target abnormal area where the target engineering drawing really exists according to the modification operation of a user aiming at the reference abnormal area; and optimizing the image examination model according to the reference abnormal region and the target abnormal region to obtain the optimized image examination model. The image examination model identification method and device are beneficial to improving the identification accuracy of the image examination model.

Description

Picture examination processing method and related device

Technical Field

The application relates to the field of construction drawing auditing, in particular to a drawing auditing processing method and a related device.

Background

With the development of Computer technology, many drawing tools appear on the market, and the most widely used drawing tool is Computer Aided Design (CAD). In industries such as construction and machinery, review of CAD drawings is a very important link, and a designer needs a lot of time and effort to review drawings by naked eyes alone, so that the efficiency of reviewing drawings is very low. At present, few Artificial Intelligence (AI) image examination tools are available, the functions of the image examination tools are single, many image examination tools can only be used for examining structures such as Liang Peijin and Liang Jiangtiao in civil building structure specialties, and in order to achieve high quality of control drawings, designers are helped to put more energy on design innovation, and AI image examination takes place.

Disclosure of Invention

The embodiment of the application provides a review image processing method and a related device, which can optimize a review image model for multiple times according to the modification operation of a user on a reference abnormal area in a review image result, so that the review image model which accords with the use habit of the user and has higher identification accuracy is obtained.

In a first aspect, an embodiment of the present application provides an examination image processing method, which is applied to an electronic device, and the method includes:

inputting a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset drawing examination rule in the target engineering drawing;

marking the reference abnormal area on the target engineering drawing, wherein the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, and the problem mark is used for explaining the abnormal condition of the reference abnormal area;

determining a target abnormal area where the target engineering drawing really exists according to the modification operation of a user aiming at the reference abnormal area;

and optimizing the image examination model according to the reference abnormal region and the target abnormal region to obtain the optimized image examination model.

In a second aspect, an embodiment of the present application provides an image examination processing apparatus, which is applied to an electronic device, and includes a processing unit and a communication unit, wherein,

the processing unit is used for inputting a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset drawing examination rule in the target engineering drawing; the system comprises a target engineering drawing, a reference abnormal area and a fault mark, wherein the reference abnormal area is marked on the target engineering drawing, the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, and the problem mark is used for explaining the abnormal condition of the reference abnormal area; the target abnormal area which is really existed in the target engineering drawing is determined according to the modification operation of the user aiming at the reference abnormal area; and the image examination model is optimized according to the reference abnormal area and the target abnormal area to obtain an optimized image examination model.

In a third aspect, an embodiment of the present application provides a server, including a controller, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the controller, and the program includes instructions for executing steps in any method of the first aspect of the embodiment of the present application.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program causes a computer to perform some or all of the steps described in any one of the methods in the first aspect of the embodiment of the present application.

In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

In the embodiment of the application, the electronic device firstly inputs a target engineering drawing into a map review model to obtain a reference abnormal area of the target engineering drawing, the reference abnormal area is an area which is not in accordance with a preset map review rule in the target engineering drawing, secondly, the reference abnormal area is marked on the target engineering drawing, the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, the problem mark is used for explaining the abnormal situation of the reference abnormal area, then, the modification operation of the reference abnormal area is determined according to a user, the target abnormal area really exists in the target engineering drawing is optimized according to the reference abnormal area and the target abnormal area, and the optimized map review model is obtained. After the reference abnormal area of the target engineering drawing identified by the reviewing model is obtained, the user can modify the reference abnormal area manually to obtain the real target abnormal area of the target engineering drawing, so that the electronic equipment can optimize the reviewing model according to the reference abnormal area and the target abnormal area, and the identification accuracy of the reviewing model is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flowchart of a graph review processing method provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of another examination graph processing method provided in an embodiment of the present application;

fig. 3 is a schematic structural diagram of a server according to an embodiment of the present application;

fig. 4 is a block diagram of functional units of an image examination processing apparatus according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

The electronic device may include a terminal or a server, which is not limited in the embodiments of the present application. Terminals include a variety of handheld devices with wireless communication capabilities, in-vehicle devices, wearable devices (e.g., smartwatches, smartbands, pedometers, etc.), computing devices, or other processes connected to a wireless modem. User Equipment (UE), mobile Station (MS), terminal Equipment (terminal device), and so on. For convenience of description, the above-mentioned devices are collectively referred to as electronic devices.

The following describes embodiments of the present application in detail.

And after the target engineering drawing is input into the picture examination model, obtaining a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset picture examination rule in the target engineering drawing detected by the picture examination model. Wherein, examine the drawing model and include five main modules: the device comprises a Python interface module, a DB analysis module, a picture preprocessing module, a picture segmentation module and a picture examination rule module, and finally outputs a result to an Azure database.

Python interface module: used for uploading DWG files.

A DB analysis module: and analyzing the drawing through RealDWG to obtain layer information, picture frame information, a view port list and component information of each picture frame, storing the layer information, the picture frame information, the view port list and the component information of each picture frame into db files, and analyzing the drawing through RealDWG. AutoCAD is generally used, but has the following limitations: the AutoCAD is divided into two versions of 64 bits and 32 bits, developers need to rewrite codes aiming at Windows64 and Windows32, and the codes are packaged into two installation programs; some requirements for processing DWG directly without AutoCAD, such as: extracting information (characters, block attributes, etc.) in the DWG, and for conversion, printing, etc. of the DWG format itself, it is not necessary to employ AutoCAD. The application program generated by the RealDWG can run in a Windows32 system or a Windows64 system, and the application program generated by the RealDWG can completely run independently from AutoCAD.

The picture preprocessing module: the method comprises five main parts, namely obtaining a recommended layer, printing a picture, converting a CAD coordinate of a component into a png coordinate, combining the components and classifying the components.

The picture segmentation module: the method mainly comprises the steps of engine initialization, component variable receiving, openCV preprocessing, user-defined preprocessing, space segmentation and pipeline operation of processing result returning.

The examination rule module: the audit rules accumulate over a hundred rules, including experience in field studies and country-related regulations. The method mainly comprises the pipeline operations of engine initialization, component variable receiving, openCV preprocessing, custom preprocessing, relational logic processing, processing result returning and program exception processing.

And each module of the image examination model is packaged completely, so that the speed of the project process is improved. Determining the overall flow of the examination model, extracting each key step and independently packaging, so that each module of the examination model is independent from each other, development and debugging can be respectively carried out, the steps are synchronously carried out, and the development process is accelerated; when the development is finished and the whole operation is finished, the module with errors can be marked, so that the errors are more concise and clearer, and the test process is accelerated; meanwhile, all the modules are mutually linked, and the modules can be mutually called, so that the program is more attractive and concise. In addition, the examination model is wide in covering range, drawings on the ground, underground, indoors and the like can be directly processed, wrong drawing design is marked, the drawings can be directly input, the drawing types do not need to be manually selected, the system can directly judge the drawing types, then corresponding rule examination is automatically carried out on the drawing types, the result is finally output, the wrong design drawings are visualized, and the examination system is concise and clear and high in processing efficiency. In the process of identifying abnormal areas on a drawing of an examination graph by the examination graph model, the obtained identification result may have a false identification condition, so that after a user obtains a reference abnormal area automatically identified by the examination graph model, the user can manually modify the position mark or the problem mark of the reference area by marking the reference abnormal area, and meanwhile, the examination graph model optimizes the system model according to the modification operation of the user to obtain an optimized examination graph model, and the optimized examination graph model has higher identification accuracy.

Referring to fig. 1, fig. 1 is a schematic flowchart of a method for processing an examination graph, which is provided in an embodiment of the present application and applied to an electronic device, where the electronic device runs an examination graph model. As shown in the figure, the examination graph processing method includes:

s101, the electronic equipment inputs a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset drawing examination rule in the target engineering drawing.

The electronic device can be a user terminal or a server, the electronic device runs the image examination model, and a carrier of the image examination model can be an application or a webpage. And after the target engineering drawing is input into the image examination model, outputting a reference abnormal area of the obtained target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset image examination standard in the target engineering drawing detected by the image examination model, for example, the abnormal area is a toilet, and when the position arrangement errors of a wash platform and a toilet in the toilet are detected or the distance between the wash platform and the toilet is incorrect, the toilet is identified as an abnormal area.

S102, the electronic equipment marks the reference abnormal area on the target engineering drawing, wherein the marks comprise position marks and problem marks, the position marks are used for marking the position of the reference abnormal area, and the problem marks are used for explaining the abnormal condition of the reference abnormal area.

When the target engineering drawing is displayed, a reference abnormal area on the target engineering drawing is marked, wherein the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, for example, the position mark can be a square frame which frames the abnormal area, and the problem mark is used for explaining the abnormal condition of the reference abnormal area, for example, a comment or a segment of text which explains the problem of the reference abnormal area.

S103, the electronic equipment determines a target abnormal area where the target engineering drawing really exists according to the modification operation of the user on the reference abnormal area.

When the user manually reviews the reference abnormal area in the review result, the reference abnormal area can be modified, and the electronic device determines the target abnormal area of the target engineering drawing which really exists according to the modification operation of the user on the reference abnormal area. For example, a certain reference abnormal area is mistakenly identified as an abnormal area, the user can manually delete the position mark of the reference abnormal area, the electronic device can synchronously delete the problem mark of the electronic device, or the user can manually modify the problem mark of the certain reference abnormal area when the description of the abnormal condition is inaccurate, and the reference abnormal area modified by the user is the target abnormal area actually existing in the target engineering drawing.

And S104, the electronic equipment optimizes the image examination model according to the reference abnormal area and the target abnormal area to obtain an optimized image examination model.

The method comprises the steps of obtaining a reference abnormal area according to an examination model and a target abnormal area obtained after a user modifies the reference abnormal area manually, comparing the reference abnormal area with the target abnormal area, optimizing the examination model to obtain an optimized examination model, inputting a target engineering drawing into the optimized examination model, wherein the reference abnormal area of the obtained target engineering drawing is possibly the same as or has the same height as the target abnormal area.

In one possible example, the review model includes a first set of parameters and a second set of parameters, the parameters in the first set of parameters being used to determine the location indicia of the reference anomaly region, the parameters in the second set of parameters being used to determine the problem indicia of the reference anomaly region; the optimizing the trial model according to the reference abnormal region and the target abnormal region to obtain an optimized trial model, including: determining the type of the modification operation according to the reference abnormal area and the target abnormal area; when the type of the modification operation is detected to be a modification position mark, adjusting parameters in the first parameter set, wherein the adjustment is used for enabling the position mark of the abnormal area in the target engineering drawing output by the optimized examination model to be consistent with the position mark of the target abnormal area; and when the type of the modification operation is detected to be a modified problem mark, adjusting the parameters in the second parameter set, wherein the adjustment is used for enabling the problem mark of the abnormal area in the target engineering drawing outputted by the optimized examination model to be consistent with the modified problem mark.

The modification of the reference abnormal area by the user includes two types, one type is that the original normal area is identified as abnormal, the user is required to manually delete the abnormal area which is identified by mistake, the other type is that the area is actually abnormal, but the description of the abnormal condition in the problem mark has deviation and is inaccurate, and the user can change the specific description of the abnormal condition at this time. Therefore, the examination graph model comprises a first parameter set and a second parameter set, the parameters in the first parameter set are used for determining a position mark of a reference abnormal region in the examination graph model, namely for identifying whether a certain region is an abnormal region, the parameters in the second parameter set are used for determining a problem mark of the reference abnormal region in the examination graph model, namely for determining an abnormal condition of the abnormal region, and the first parameter set and the second parameter set form the examination graph model.

And determining the type of the modification operation according to the reference abnormal area and the target abnormal area, wherein the type of the modification operation comprises a modification position mark and a modification problem mark. When the type of the modification operation is detected to be the modification position mark, it is indicated that the parameters in the first parameter set need to be adjusted, and the position mark of the abnormal area in the target engineering drawing output by the optimized examination model is consistent with the position mark of the target abnormal area through adjustment. The modification of the position mark comprises deleting the position mark, adding the position mark and moving the position mark, the corresponding problem mark can be synchronously deleted when the position mark is deleted, and the user can be prompted to input the corresponding problem mark when the position mark is added.

When the type of the modification operation is detected to be the modification problem mark, it is indicated that the parameters in the second parameter set need to be adjusted, and the problem mark of the abnormal area in the target engineering drawing output by the optimized examination model is consistent with the problem mark of the target abnormal area through adjustment.

As can be seen, in this example, the renting field of the image review model includes a first parameter set used for determining the position mark of the abnormal region and a second parameter set used for determining the problem mark of the abnormal region, the type of the modification operation can be determined according to the reference abnormal region and the target abnormal region, and thus whether the image review model needs to be adjusted by the first parameter set or the second parameter set is determined according to the type of the modification operation, and the optimized image review model can be obtained through the corresponding parameters of the parameter image review model.

In one possible example, the method further comprises: acquiring first abnormal data, wherein the first abnormal data is obtained after the target engineering drawing is input into the examination model; acquiring second abnormal data, wherein the second abnormal data is obtained after the target engineering drawing is input into the optimized examination model; determining an optimized value of the optimized examination graph model according to the first abnormal data and the second abnormal data; and when the optimization value is detected to be larger than a preset threshold value, finishing the optimization of the image examination model.

The method comprises the steps that an examination model can be optimized according to a reference abnormal area and a target abnormal area to obtain an optimized examination model, when a user modifies the examination model for multiple times, the examination model is optimized once every time the user modifies the examination model, at the moment, first abnormal data are obtained, the first abnormal data are abnormal data obtained after target engineering drawings are input into the examination model, namely data corresponding to a reference abnormal area part, second abnormal data are obtained, the second abnormal data are abnormal data obtained after the target engineering drawings are input into the optimized examination model, namely data corresponding to a target abnormal area part, an optimized value of the optimized examination model can be determined according to the first abnormal data and the second abnormal data, and when the optimized value is detected to be larger than a preset threshold value, the optimization of the examination model can be finished. And when the similarity of the first abnormal data and the second abnormal data is lower, the optimized value is indicated to be lower.

In this example, in the process of continuously optimizing the image-examination model, the optimization value of the optimized image-examination model is calculated according to the first abnormal data output by the image-examination model before optimization and the second abnormal data output by the optimized image-examination model, so as to determine whether to stop optimizing the image-examination model, and to make the recognition accuracy of the optimized image-examination model high.

In one possible example, the map-reviewing model includes a missing component detection module, a redundant component detection module, and a wrong component detection module; the optimizing the trial model according to the reference abnormal region and the target abnormal region to obtain an optimized trial model, including: when the modification operation is detected to be modification of the problem mark, determining the type of the problem mark according to the reference abnormal area and the target abnormal area; determining a module to be adjusted in the examination graph model according to the type of the problem mark; and adjusting the parameter set of the module to be adjusted to obtain the optimized examination graph model, wherein the adjustment is used for enabling the abnormal area of the target engineering drawing output by the optimized examination graph model to be the target abnormal area.

The diagram examination model comprises a component missing detection module, a component redundant detection module and a component error detection module, wherein the component missing detection module can detect a certain missing component in a target engineering drawing, the component redundant detection module can detect a certain redundant component in the target engineering drawing, the component error detection module can detect a certain component with wrong parameters in the target engineering drawing, and the parameter errors comprise position errors, size errors, shape errors, type errors and the like.

When the problem mark is detected to be modified by modification operation, the type of the problem mark is determined, then a module to be adjusted in the image examination model is determined according to the type of the problem mark, the optimized image examination model can be obtained by adjusting the parameter set of the module to be adjusted, and the purpose of adjustment is to enable the abnormal area of the target engineering drawing output by the optimized image examination model to be a target abnormal area.

The module to be adjusted is at least one of a missing detection module, a component redundant detection module and a component error detection module. When the problem mark modified by the user is a missing mark, the module to be adjusted is a component missing detection module, when the problem mark modified by the user is a new mark, the module to be adjusted is a component new detection module, and when the problem mark modified by the user is an error mark, the module to be adjusted is a component error detection module.

In this example, the image examination model includes a missing part detection module, a redundant part detection module, and a wrong part detection module, and the module to be adjusted in the image examination model is determined according to the type of the problem mark modified in the modification operation, so that the parameter of the module is adjusted, and the optimized image examination model can be obtained.

In one possible example, the type of issue flag includes at least one of: a missing marker for marking missing member elements in the reference abnormal region, the missing marker comprising a first position marker and a first text marker; newly added marks, wherein the newly added marks are used for marking redundant component elements in the reference abnormal region and comprise second position marks and second character marks; error marks used for marking the member elements with wrong parameters in the reference abnormal area, wherein the parameters comprise the length, the width, the area, the angle, the shape and the position relation of the member elements, and the error marks comprise third position marks and third literal marks.

The type of the problem mark comprises a missing mark, the missing mark is used for marking the missing member elements in the reference abnormal region, the missing mark comprises a first position mark and a first character mark, the first position mark marks the position of the missing member, and the first character mark explains the missing member.

The type of the problem mark comprises a newly added mark, the newly added mark is used for marking redundant component elements in the reference abnormal region, the newly added mark comprises a second position mark and a second character mark, the second position mark marks the position of the newly added component, and the second character mark explains the newly added component.

The error marks comprise a third position mark and a third character mark, the third position mark marks the position of the error component, and the third character mark explains the error component.

It can be seen that, in this example, the types of the problem flags include a missing flag, a newly added flag, and an error flag, and according to the types of the problem flags, a module that needs to be adjusted may be determined, so that the parameter of the module is adjusted, and the optimized trial model may be obtained.

In one possible example, the determining, according to the modification operation of the user for the reference abnormal area, a target abnormal area where the target engineering drawing really exists includes: when the frame selection operation aiming at the reference abnormal area is detected, acquiring a picture frame track and a preselected frame size; determining a plurality of reference abnormal areas in the preselected frame according to the size of the preselected frame; determining the sequence of the plurality of reference abnormal areas covered according to the picture frame track; and determining the priorities of the plurality of reference abnormal areas according to the sequence, and highlighting the plurality of reference abnormal areas in sequence according to the priority sequence.

When the review result is manually reviewed based on the reference abnormal area in the review result, the review result is used for selecting the reference abnormal area to be modified in a frame mode, the size of the frame and the track of the frame are preselected by a user, and the number of the reference abnormal areas needing to be highlighted and the priority of highlighting can be dynamically calculated.

When detecting the frame selection operation for the reference abnormal area, acquiring a picture frame track and a preselected frame size, wherein the picture frame track can be, for example, dragging a picture frame from top left to bottom right, and can be, for example, dragging the picture frame from bottom left to top right, and the larger the preselected frame is, the more the reference abnormal area can be covered.

The method comprises the steps of determining a plurality of reference abnormal areas in a pre-selection frame according to the size of the pre-selection frame, determining the sequence of the plurality of reference abnormal areas which are covered according to a picture frame track, determining the priority of the plurality of reference abnormal areas according to the sequence, and highlighting the plurality of abnormal reference areas in sequence according to the priority of the plurality of reference abnormal areas.

The priority is determined according to the picture frame track of a user, the picture frame track of the user determines the sequence of covering each reference abnormal area in the preselected frame, the purpose of highlighting the plurality of reference abnormal areas in the preselected frame is to facilitate the user to modify each reference abnormal area in sequence, and the highlighting mode can be, for example, amplification display or changing the display colors of the plurality of reference abnormal areas.

Therefore, in this example, when the user modifies the reference abnormal region to obtain the target abnormal region, the plurality of reference abnormal regions may be selected through a frame selection operation, and the electronic device may sequentially highlight the plurality of reference abnormal regions selected by the user, so that the user can modify the target abnormal region conveniently.

In one possible example, the determining, according to the modification operation of the user for the reference abnormal area, a target abnormal area where the target engineering drawing really exists includes: when modification operation aiming at a first abnormal area in the reference abnormal area is detected, determining a viewpoint corresponding to the first abnormal area; switching the viewpoint of the target engineering drawing to the viewpoint corresponding to the first abnormal area; and determining a target abnormal area which really exists in the target engineering drawing according to the modification operation.

The reference abnormal area comprises a plurality of abnormal areas in the target engineering drawing detected by the review model, and when modification operation on a first abnormal area in the reference abnormal area is detected, a viewpoint corresponding to the first abnormal area needs to be determined, so that the target engineering drawing is switched to the viewpoint corresponding to the first abnormal area from the current viewpoint.

Therefore, in this example, when the user performs the modification operation on the reference abnormal area, the current viewpoint of the target drawing can be switched to the viewpoint corresponding to the first abnormal area according to the first abnormal area to be modified by the user currently, so that the user can modify the first abnormal area more clearly.

Referring to fig. 2, fig. 2 is a schematic flowchart of a diagram reviewing processing method provided in an embodiment of the present application, and the diagram reviewing module is implemented in an electronic device, where the server runs the diagram reviewing module. As shown in the figure, the method for processing the examination graph comprises the following steps:

s201, the electronic equipment inputs a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the reference abnormal area is an area which does not accord with a preset drawing examination rule in the target engineering drawing.

S202, the electronic equipment marks the reference abnormal area on the target engineering drawing, wherein the marks comprise position marks and problem marks, the position marks are used for marking the position of the reference abnormal area, and the problem marks are used for explaining the abnormal condition of the reference abnormal area.

S203, when the electronic equipment detects the modification operation of a first abnormal area in the reference abnormal area, the electronic equipment determines the viewpoint corresponding to the first abnormal area.

And S204, the electronic equipment switches the viewpoint of the target engineering drawing to the viewpoint corresponding to the first abnormal area.

And S205, the electronic equipment determines a target abnormal area where the target engineering drawing really exists according to the modification operation.

And S206, the electronic equipment optimizes the image examination model according to the reference abnormal area and the target abnormal area to obtain an optimized image examination model.

In the embodiment of the application, the electronic device firstly inputs a target engineering drawing into a map review model to obtain a reference abnormal area of the target engineering drawing, the reference abnormal area is an area which is not in accordance with a preset map review rule in the target engineering drawing, secondly, the reference abnormal area is marked on the target engineering drawing, the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, the problem mark is used for explaining the abnormal situation of the reference abnormal area, then, the modification operation of the reference abnormal area is determined according to a user, the target abnormal area really exists in the target engineering drawing is optimized according to the reference abnormal area and the target abnormal area, and the optimized map review model is obtained. After the reference abnormal area of the target engineering drawing identified by the image examination model is obtained, the user can manually modify the reference abnormal area to obtain the real target abnormal area of the target engineering drawing, so that the electronic equipment can optimize the image examination model according to the reference abnormal area and the target abnormal area, and the identification accuracy of the image examination model is improved.

In addition, when the user performs modification operation on the reference abnormal area, the current viewpoint of the target drawing can be switched to the viewpoint corresponding to the first abnormal area according to the first abnormal area to be modified by the user, so that the user can modify the first abnormal area more clearly.

Consistent with the embodiments shown in fig. 1 and fig. 2, please refer to fig. 3, fig. 3 is a schematic structural diagram of a server 300 provided in the embodiments of the present application, the server 300 runs with one or more application programs and an operating system, as shown, the server 300 includes a processor 310, a memory 320, a communication interface 330, and one or more programs 321, wherein the one or more programs 321 are stored in the memory 320 and configured to be executed by the processor 310, and the one or more programs 321 include instructions for performing the following steps;

In one possible example, the review model includes a first set of parameters and a second set of parameters, the parameters in the first set of parameters being used to determine the location indicia of the reference anomaly region, the parameters in the second set of parameters being used to determine the problem indicia of the reference anomaly region; in the aspect that the review model is optimized according to the reference abnormal region and the target abnormal region to obtain an optimized review model, the instructions in the program are specifically used for executing the following operations: determining the type of the modification operation according to the reference abnormal area and the target abnormal area; when the type of the modification operation is detected to be a modification position mark, adjusting parameters in the first parameter set, wherein the adjustment is used for enabling the position mark of the abnormal area in the target engineering drawing output by the optimized examination model to be consistent with the position mark of the target abnormal area; and when the type of the modification operation is detected to be a modified problem mark, adjusting parameters in the second parameter set, wherein the adjustment is used for enabling the problem mark of the abnormal area in the target engineering drawing outputted by the optimized examination model to be consistent with the modified problem mark.

In one possible example, the instructions in the program are specifically for performing the following: acquiring first abnormal data, wherein the first abnormal data is obtained after the target engineering drawing is input into the examination model; acquiring second abnormal data, wherein the second abnormal data is obtained after the target engineering drawing is input into the optimized examination model; determining an optimized value of the optimized examination graph model according to the first abnormal data and the second abnormal data; and when the optimization value is detected to be larger than a preset threshold value, finishing the optimization of the examination graph model.

In one possible example, the map-reviewing model includes a missing component detection module, a redundant component detection module, and a wrong component detection module; in the aspect that the review model is optimized according to the reference abnormal region and the target abnormal region to obtain an optimized review model, the instructions in the program are specifically used for executing the following operations: when the modification operation is detected to be modification of the problem mark, determining the type of the problem mark according to the reference abnormal area and the target abnormal area; determining a module to be adjusted in the examination graph model according to the type of the problem mark; and adjusting the parameter set of the module to be adjusted to obtain the optimized examination graph model, wherein the adjustment is used for enabling the abnormal area of the target engineering drawing output by the optimized examination graph model to be the target abnormal area.

In one possible example, in the aspect that the target abnormal area where the target engineering drawing really exists is determined according to the modification operation of the user on the reference abnormal area, the instructions in the program are specifically configured to perform the following operations: when the frame selection operation aiming at the reference abnormal area is detected, acquiring a picture frame track and a preselected frame size; determining a plurality of reference abnormal areas in the preselected frame according to the size of the preselected frame; determining the sequence of the plurality of reference abnormal areas covered according to the picture frame track; and determining the priorities of the plurality of reference abnormal areas according to the sequence, and highlighting the plurality of reference abnormal areas in sequence according to the priority sequence.

In one possible example, in the aspect that the target abnormal area where the target engineering drawing really exists is determined according to the modification operation of the user on the reference abnormal area, the instructions in the program are specifically configured to perform the following operations: when modification operation aiming at a first abnormal area in the reference abnormal area is detected, determining a viewpoint corresponding to the first abnormal area; switching the viewpoint of the target engineering drawing to the viewpoint corresponding to the first abnormal area; and determining a target abnormal area actually existing in the target engineering drawing according to the modification operation.

The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It is understood that the server includes hardware structures and/or software modules for performing the respective functions in order to implement the above-described functions. Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the server may be divided into the functional units according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one control unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Fig. 4 is a block diagram of functional units of an apparatus 400 involved in the embodiments of the present application. The examination graph processing device 400 is applied to an electronic device, and the examination graph processing device 400 includes a processing unit 401 and a communication unit 402, wherein:

the processing unit 401 is configured to input a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, where the reference abnormal area is an area in the target engineering drawing that does not meet a preset drawing examination rule; the system comprises a target engineering drawing, a reference abnormal area and a fault mark, wherein the reference abnormal area is marked on the target engineering drawing, the mark comprises a position mark and a problem mark, the position mark is used for marking the position of the reference abnormal area, and the problem mark is used for explaining the abnormal condition of the reference abnormal area; the target abnormal area which is really existed in the target engineering drawing is determined according to the modification operation of the user aiming at the reference abnormal area; and the image examination model is optimized according to the reference abnormal area and the target abnormal area to obtain an optimized image examination model.

In one possible example, the review model includes a first set of parameters and a second set of parameters, the parameters in the first set of parameters being used to determine the location indicia of the reference anomaly region, the parameters in the second set of parameters being used to determine the problem indicia of the reference anomaly region; in the aspect that the review model is optimized according to the reference abnormal region and the target abnormal region to obtain an optimized review model, the processing unit 401 is specifically configured to: determining the type of the modification operation according to the reference abnormal area and the target abnormal area; when the type of the modification operation is detected to be a modification position mark, adjusting parameters in the first parameter set, wherein the adjustment is used for enabling the position mark of the abnormal area in the target engineering drawing output by the optimized examination model to be consistent with the position mark of the target abnormal area; and when the type of the modification operation is detected to be a modified problem mark, adjusting the parameters in the second parameter set, wherein the adjustment is used for enabling the problem mark of the abnormal area in the target engineering drawing outputted by the optimized examination model to be consistent with the modified problem mark.

In one possible example, the processing unit 401 is specifically configured to: acquiring first abnormal data, wherein the first abnormal data is obtained after the target engineering drawing is input into the examination model; acquiring second abnormal data, wherein the second abnormal data is obtained after the target engineering drawing is input into the optimized examination model; determining an optimized value of the optimized trial graph model according to the first abnormal data and the second abnormal data; and when the optimization value is detected to be larger than a preset threshold value, finishing the optimization of the image examination model.

In one possible example, the map-reviewing model includes a missing component detection module, a redundant component detection module, and a wrong component detection module; in the aspect that the review model is optimized according to the reference abnormal region and the target abnormal region to obtain an optimized review model, the processing unit 401 is specifically configured to: when the modification operation is detected to be modification of the problem mark, determining the type of the problem mark according to the reference abnormal area and the target abnormal area; determining a module to be adjusted in the examination graph model according to the type of the problem mark; and adjusting the parameter set of the module to be adjusted to obtain the optimized examination graph model, wherein the adjustment is used for enabling the abnormal area of the target engineering drawing output by the optimized examination graph model to be the target abnormal area.

In a possible example, in terms of determining the target abnormal area where the target engineering drawing really exists according to the modification operation of the user on the reference abnormal area, the processing unit 401 is specifically configured to: when the frame selection operation aiming at the reference abnormal area is detected, acquiring a picture frame track and a preselected frame size; determining a plurality of reference abnormal areas in the preselected frame according to the size of the preselected frame; determining the sequence of the plurality of reference abnormal areas covered according to the picture frame track; and determining the priorities of the plurality of reference abnormal areas according to the sequence, and highlighting the plurality of reference abnormal areas in sequence according to the priority sequence.

In a possible example, in the aspect of determining the target abnormal area where the target engineering drawing really exists according to the modification operation of the user on the reference abnormal area, the processing unit 401 is specifically configured to: when modification operation aiming at a first abnormal area in the reference abnormal area is detected, determining a viewpoint corresponding to the first abnormal area; switching the viewpoint of the target engineering drawing to the viewpoint corresponding to the first abnormal area; and determining a target abnormal area which really exists in the target engineering drawing according to the modification operation.

Wherein the server may further include a storage unit 403, the processing unit 401 and the communication unit 402 may be a controller or a processor, and the storage unit 403 may be a memory.

Embodiments of the present application also provide a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the methods described in the above method embodiments, and the computer includes a mobile terminal.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package, the computer comprising a mobile terminal.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated into one control unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-mentioned method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, read-Only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing embodiments have been described in detail, and specific examples are used herein to explain the principles and implementations of the present application, where the above description of the embodiments is only intended to help understand the method and its core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. The image examination processing method is characterized by being applied to electronic equipment, wherein the electronic equipment comprises an image examination model, and the image examination model comprises a Python interface module, a DB analysis module, an image preprocessing module, an image segmentation module and an image examination rule module; the Python interface module is used for uploading DWG files; the DB analysis module is used for analyzing the drawing through RealDWG to obtain layer information, drawing frame information, a view port list and component information of each drawing frame, storing the drawing frame information, the view port list and the component information of each drawing frame into DB files, and analyzing the drawing through RealDWG; the image preprocessing module is used for acquiring a recommended layer, printing an image, converting a CAD coordinate of the component into a png coordinate, combining the components and classifying the components; the image segmentation module is used for executing pipeline operations of engine initialization, component variable receiving, openCV preprocessing, custom preprocessing, space segmentation and processing result returning; the image examination rule module is used for executing the pipeline operations of engine initialization, component variable receiving, openCV preprocessing, custom preprocessing, relation logic processing, processing result returning and program exception processing; the method comprises the following steps:

inputting a target engineering drawing into a drawing examination model to obtain a reference abnormal area of the target engineering drawing, wherein the drawing examination model further comprises a first parameter set and a second parameter set, parameters in the first parameter set are used for determining a position mark of the reference abnormal area, parameters in the second parameter set are used for determining a problem mark of the reference abnormal area, the position mark is used for marking the position of the reference abnormal area, the problem mark is used for explaining the abnormal condition of the reference abnormal area, and the reference abnormal area is an area which does not accord with preset drawing examination rules in the target engineering drawing;

determining the type of the modification operation according to the reference abnormal area and the target abnormal area;

when the type of the modification operation is detected to be a modification position mark, adjusting parameters in the first parameter set, wherein the adjustment is used for enabling the position mark of the abnormal area in the target engineering drawing output by the optimized examination model to be consistent with the position mark of the target abnormal area;

and when the type of the modification operation is detected to be a modified problem mark, adjusting the parameters in the second parameter set, wherein the adjustment is used for enabling the problem mark of the abnormal area in the target engineering drawing outputted by the optimized examination model to be consistent with the modified problem mark.

2. The method of claim 1, further comprising:

acquiring first abnormal data, wherein the first abnormal data is obtained after the target engineering drawing is input into the examination model;

acquiring second abnormal data, wherein the second abnormal data is obtained after the target engineering drawing is input into the optimized examination model;

determining an optimized value of the optimized examination graph model according to the first abnormal data and the second abnormal data;

and when the optimization value is detected to be larger than a preset threshold value, finishing the optimization of the examination graph model.

3. The method of claim 1, wherein the adjusting the parameters in the second parameter set comprises:

determining the type of the problem mark according to the reference abnormal area and the target abnormal area;

determining a module to be adjusted in the image examination model according to the type of the problem mark, wherein the module to be adjusted comprises a component missing detection module, a component redundant detection module and a component error detection module;

and adjusting the parameter set of the module to be adjusted to obtain the optimized examination graph model, wherein the adjustment is used for enabling the abnormal area of the target engineering drawing output by the optimized examination graph model to be the target abnormal area.

4. The method of claim 3, wherein the type of issue flag comprises at least one of:

a missing marker for marking missing member elements in the reference abnormal region, the missing marker comprising a first position marker and a first text marker;

newly added marks, wherein the newly added marks are used for marking redundant component elements in the reference abnormal region and comprise second position marks and second character marks;

error marks used for marking the member elements with wrong parameters in the reference abnormal area, wherein the parameters comprise the length, the width, the area, the angle, the shape and the position relation of the member elements, and the error marks comprise third position marks and third literal marks.

5. The method according to claim 1, wherein the determining of the target abnormal area where the target engineering drawing really exists according to the modification operation of the user on the reference abnormal area comprises:

when the frame selection operation aiming at the reference abnormal area is detected, acquiring a picture frame track and a preselected frame size;

determining a plurality of reference abnormal regions within the preselected frame according to the preselected frame size;

determining the sequence of the plurality of reference abnormal areas covered according to the picture frame track;

and determining the priorities of the plurality of reference abnormal areas according to the sequence, and highlighting the plurality of reference abnormal areas in sequence according to the priority sequence.

6. The method according to claim 1, wherein the determining of the target abnormal area where the target engineering drawing really exists according to the modification operation of the user on the reference abnormal area comprises:

when modification operation aiming at a first abnormal area in the reference abnormal area is detected, determining a viewpoint corresponding to the first abnormal area;

switching the viewpoint of the target engineering drawing to the viewpoint corresponding to the first abnormal area;

and determining a target abnormal area actually existing in the target engineering drawing according to the modification operation.

7. The image examination processing device is applied to electronic equipment, wherein the electronic equipment comprises an image examination model, and the image examination model comprises a Python interface module, a DB analysis module, an image preprocessing module, an image segmentation module and an image examination rule module; the Python interface module is used for uploading DWG files; the DB analysis module is used for analyzing the drawing through RealDWG to obtain layer information, drawing frame information, a view port list and component information of each drawing frame, storing the drawing frame information, the view port list and the component information of each drawing frame into DB files, and analyzing the drawing through RealDWG; the picture preprocessing module is used for acquiring a recommended layer, printing a picture, converting a CAD (computer-aided design) coordinate of a component into a png coordinate, combining the components and classifying the components; the image segmentation module is used for executing pipeline operations of engine initialization, component variable receiving, openCV preprocessing, custom preprocessing, space segmentation and processing result returning; the examination rule module is used for executing the pipeline operations of engine initialization, component variable receiving, openCV preprocessing, custom preprocessing, relation logic processing, processing result returning and program exception processing; the examination graph processing device comprises a processing unit and a communication unit, wherein,

the processing unit is used for inputting a target engineering drawing into a review model to obtain a reference abnormal area of the target engineering drawing, the review model further comprises a first parameter set and a second parameter set, parameters in the first parameter set are used for determining a position mark of the reference abnormal area, parameters in the second parameter set are used for determining a problem mark of the reference abnormal area, the position mark is used for marking the position of the reference abnormal area, the problem mark is used for explaining the abnormal condition of the reference abnormal area, and the reference abnormal area is an area which does not accord with a preset review rule in the target engineering drawing; the target abnormal area which is really existed in the target engineering drawing is determined according to the modification operation of the user aiming at the reference abnormal area; and the modifying operation is used for determining the type of the modifying operation according to the reference abnormal area and the target abnormal area; when the type of the modification operation is detected to be a modification position mark, adjusting parameters in the first parameter set, wherein the adjustment is used for enabling the position mark of the abnormal area in the target engineering drawing output by the optimized examination model to be consistent with the position mark of the target abnormal area; and when the type of the modification operation is detected to be a modified problem mark, adjusting the parameters in the second parameter set, wherein the adjustment is used for enabling the problem mark of the abnormal area in the target engineering drawing outputted by the optimized examination model to be consistent with the modified problem mark.

8. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-6.

9. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-6.