Method and system for identifying welding engineering drawing information

Abstract

The invention discloses a method and system for recognizing welding engineering drawing information, and the method comprises the steps: obtaining a welding engineering drawing image, and recognizing the image of at least one welding symbol and drawing basic information; according to the welding engineering drawing image, extracting a minimum drawing area containing all welding symbols, and recording the minimum drawing area as a drawing effective area; obtaining coordinate information of at least one welding symbol in the drawing according to the coordinate information of the effective area of the drawing and the at least one welding symbol image; and generating a welding joint statistical table of the drawing according to the basic information of the drawing and the coordinate information of the at least one welding symbol in the drawing. According to the invention, the efficiency of manual welding seam identification is improved, and the omission ratio is obviously reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of engineering drawings, and in particular to a method and system for identifying welding engineering drawing information. Background Art

[0002] At present, there are few studies on welding drawing recognition technology, and only a few companies have products with similar functions. Usually, welding engineers rely mainly on manual recognition and judgment when compiling welding joint statistics. The traditional method is to manually open the PDF drawings and rely on human eyes to find the weld symbols in the drawings and the area where the weld symbols are located in the drawings. Therefore, when performing welding symbol statistics on multiple drawings of a project, it not only consumes people's time and energy, but also easily leads to omission of weld symbols and errors in filling in weld symbol location information.

[0003] Therefore, the prior art needs to provide an automated recognition solution for weld information in welding engineering drawings. Summary of the invention

[0004] The purpose of the present invention is to provide an automatic recognition solution for weld information in welding engineering drawings.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for identifying welding engineering drawing information, including: obtaining a welding engineering drawing image, and identifying an image of at least one welding symbol and basic drawing information; according to the welding engineering drawing image, extracting the minimum drawing area containing all welding symbols, recorded as the effective drawing area; according to the coordinate information of the effective drawing area and at least one welding symbol image, obtaining the coordinate information of at least one welding symbol in the drawing; according to the basic drawing information and the coordinate information of the at least one welding symbol in the drawing, generating a welding joint statistics table of the drawing.

[0006] Preferably, the step of acquiring a welding engineering drawing image and identifying at least one welding symbol image and basic drawing information includes: using a drawing information recognition model to extract at least one welding symbol image and a title bar image from the welding engineering drawing image; extracting text information in the title bar image and obtaining basic drawing information, wherein the basic drawing information includes: a drawing name and a drawing number.

[0007] Preferably, the drawing information recognition model is constructed using the following steps: collecting historically collected welding engineering drawing images, and selecting all weld symbol areas and title bar areas in the image; constructing a data training set and a data verification set based on the historical welding engineering drawing images and the corresponding weld symbol area images and title bar area images; establishing a basic neural network model, and using the data training set and the data verification set to train and verify the basic neural network model to obtain a drawing information recognition model.

[0008] Preferably, the basic neural network model adopts the Faster-RCNN target detection model, wherein the feature extraction part in the Faster-RCNN target detection model is implemented using a ResNet50 module in combination with an FPN module.

[0009] Preferably, in the step of extracting the minimum drawing area containing all welding symbols according to the welding engineering drawing image and recording it as the effective drawing area, it includes: converting the welding engineering drawing image into a grayscale image; traversing the pixel points in the grayscale image, and counting the degree of change of pixel values ​​of adjacent pixel points, the number of times the pixel values ​​exceed a threshold value and the pixel point positions, and locating the effective drawing area representing the grayscale image border area range; marking the coordinate axis range of the effective drawing area, and determining the correlation between the coordinate axis scale and the pixel point coordinate position.

[0010] Preferably, the step of obtaining the coordinate information of at least one welding symbol in the drawing according to the coordinate information of the effective area of ​​the drawing and at least one welding symbol image includes: identifying the central pixel coordinate position of at least one welding symbol image; obtaining the coordinate position of the pixel point cluster corresponding to each welding symbol according to the central pixel coordinate position of the at least one welding symbol image and the correlation relationship between the coordinate axis scale indicated in the effective area of ​​the drawing and the pixel point coordinate position.

[0011] Preferably, the method further comprises: verifying the format of the uploaded file, and obtaining at least one welding engineering drawing image when the current format is a first type of file format.

[0012] Preferably, if the current format is the second type file format, the uploaded file is read page by page, and at least one page of welding engineering drawing image in the second type file format is converted into the first type file format.

[0013] Preferably, the method further comprises: storing a statistical table of welding joints of at least one drawing to form a drawing information storage database, wherein the corresponding statistical table of welding joints is retrieved according to a query instruction containing drawing name or drawing number information.

[0014] On the other hand, an embodiment of the present invention further provides a system for identifying welding engineering drawing information, the system is used to implement the method as described above, wherein the system includes: a file upload module, which is configured to obtain a welding engineering drawing image; an image recognition module, which is configured to identify the image of at least one welding symbol in the welding engineering drawing image and basic drawing information, and then, based on the welding engineering drawing image, extract the minimum drawing area containing all welding symbols, recorded as the effective drawing area, and finally, based on the coordinate information of the effective drawing area and at least one welding symbol image, obtain the coordinate information of at least one welding symbol in the drawing; a statistical table generation module, which is configured to generate a welding joint statistical table of the drawing based on the basic drawing information and the coordinate information of the at least one welding symbol in the drawing.

[0015] Compared with the prior art, one or more embodiments of the above scheme may have the following advantages or beneficial effects:

[0016] The present invention proposes a method and system for identifying welding engineering drawing information. The method and system is a welding engineering drawing information identification technology based on deep learning technology, which can effectively save and manage project drawing information, effectively identify welding symbols, drawing names and drawing numbers in drawings and automatically generate welding joint statistics, effectively helping engineers improve the efficiency of compiling welding joint lists, and at the same time, solve the problem of missed detection and wrong detection in identifying small objects such as weld symbols, improve the efficiency of manual weld identification, and significantly reduce the missed detection rate.

[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0019] Figure 1 A schematic diagram of the steps of a method for identifying welding engineering drawing information according to an embodiment of the present application.

[0020] Figure 2 A schematic diagram of a specific process of a method for identifying welding engineering drawing information according to an embodiment of the present application.

[0021] Figure 3A schematic diagram of the construction process of a drawing information recognition model in a method for identifying welding engineering drawing information according to an embodiment of the present application.

[0022] Figure 4 This is a schematic diagram of the structure of a system for identifying welding engineering drawing information according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will describe the implementation methods of the present invention in detail with reference to the accompanying drawings and embodiments, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that as long as there is no conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0024] In addition, the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions. Also, although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in a sequence different from that here.

[0025] The terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms "one", "one" and "item" used herein are also intended to include plural numbers. It should also be understood that the terms "include" and / or "comprise" used herein specify the existence of stated features, integers, steps, operations, units and / or components, without excluding the existence or addition of one or more other features, integers, steps, operations, units, components and / or combinations thereof.

[0026] In order to solve the problems in the above background technology, the present invention provides a method and system for identifying welding engineering drawing information. The method and system can effectively identify welding symbols, drawing names and drawing numbers in welding engineering drawings, and automatically generate a welding joint statistics table, effectively helping engineers improve the efficiency of compiling welding joint lists.

[0027] Figure 1 A schematic diagram of the steps of a method for identifying welding engineering drawing information according to an embodiment of the present application. Figure 2 This is a schematic diagram of a specific process of the method for identifying welding engineering drawing information in an embodiment of the present application. Figure 1 and Figure 2 , the specific steps of the method for identifying welding engineering drawing information (also called "drawing information identification method") described in an embodiment of the present invention are described.

[0028] like Figure 1As shown, in step S110, a welding engineering drawing image is acquired, and an image of at least one welding symbol and basic drawing information are identified.

[0029] In step S110, first, at least one welding engineering drawing image that needs to be recognized online is obtained.

[0030] Specifically, Figure 2 As shown, the uploaded file is loaded and the format of the uploaded file (for example, the original image of at least one page of welding engineering drawing formed by collecting at least one complete engineering drawing) is verified. When the current format is the first type of file format, at least one welding engineering drawing image is obtained.

[0031] In one embodiment, if the format of the currently uploaded file is the second type of file format, after reading the uploaded file page by page, at least one page of (original) welding engineering drawing image in the second type of file format is converted into the first type of file format to obtain at least one welding engineering drawing image that needs to be recognized online. In addition, if the format of the currently uploaded file is the first type of file format, after reading the uploaded file page by page, at least one welding engineering drawing image that needs to be recognized online is directly obtained.

[0032] In addition, if the format of the currently uploaded file is not the first type of file format or the second type of file format, a notification message indicating that the file format does not meet the system requirements is directly output.

[0033] In the embodiment of the present invention, the second file format is pdf. The first file format is JPG or PNG or JPEG.

[0034] For example: process files uploaded by users to ensure that they meet system requirements. Workflow: detect the format of the uploaded file and determine whether it is one of PDF, JPG, PNG and JPEG. If it is a PDF file, first read the PDF document page by page, and then convert each page of the PDF document into a jpg format image, so as to obtain at least one welding engineering drawing image in jpg format.

[0035] After obtaining at least one qualified welding engineering drawing image that meets the format requirements, an image of at least one welding symbol and basic drawing information in the welding engineering drawing image are identified.

[0036] In one embodiment, on the one hand, the embodiment of the present invention uses a drawing information recognition model to extract at least one welding symbol image and a title bar image from a welding engineering drawing image, and then extracts the text information in the title bar image and obtains basic drawing information. In the embodiment of the present invention, the basic drawing information includes: drawing name and drawing number.

[0037] Before the drawing information recognition model is applied online, the embodiment of the present invention also needs to construct the drawing information recognition model. In the process of constructing the drawing information recognition model, Figure 3 As shown, it includes: collecting historically collected welding engineering drawing images, and selecting all weld symbol areas and title bar areas in the images; constructing a data training set and a data verification set based on the historical welding engineering drawing images and the corresponding weld symbol area images and title bar area images; establishing a basic neural network model, and using the data training set and the data verification set to train and verify the basic neural network model to obtain a drawing information recognition model.

[0038] Furthermore, in an embodiment of the present invention, the basic neural network model is implemented using the Faster-RCNN target detection model, wherein the feature extraction part in the Faster-RCNN target detection model is implemented using a ResNet50 module in conjunction with an FPN module.

[0039] Specifically, the PDF welding engineering drawing images collected historically are first converted into JPEG format images, and then the welding symbol area and the title bar position area are marked on each image using a labeling tool such as LabelImg. Then, the dataset constructed by the labeled JPEG format welding engineering drawing images is divided into a data training set and a data verification set. Then, based on the data training set and the data verification set, the Faster-RCNN target detection model is used for training and verification, wherein the backbone network in the Faster-RCNN target detection model adopts the ResNet50+FPN structure.

[0040] In this way, after replacing the backbone network in the Faster-RCNN model with ResNet50+FPN, the present invention solves the problem of missed detection and false detection in identifying small objects such as weld symbols in welding engineering drawings.

[0041] Next, the verified Faster-RCNN target detection model is used to identify the welding symbol image and the title bar area from at least one welding engineering drawing image that needs to be recognized online. On the one hand, the welding symbol image is cropped into an independent image file I i (i=1,2,3...), and obtain each welding symbol image file I i (i=1,2,3...) pixel position information in the entire drawing. At the same time, the title bar area is cropped into an independent image file II, and the text detection model is combined with the text recognition model PP-OCR to obtain the text information in the title bar area in the image file II. Finally, the text information in the title bar area in the image file II is screened to obtain the drawing name and drawing number of the welding engineering drawing, which is recorded as the basic information of the drawing.

[0042] After obtaining the basic information of the drawing and the pixel position information of at least one welding symbol image, the process proceeds to step S120.

[0043] Step S120, based on at least one welding engineering drawing image that needs to be identified online obtained in step S110, extract the minimum drawing area containing all welding symbols in the drawing image, and record it as the effective drawing area.

[0044] In order to improve the applicability and flexibility of the online drawing information recognition method, the embodiment of the present invention does not set the size of the effective area of ​​the drawing. The effective area of ​​the drawing can be adaptively adjusted according to the position distribution status of all welding symbols in the welding engineering drawing image, and is set on the principle of covering all welding symbols in a drawing image.

[0045] like Figure 2 As shown, in step S120, the welding engineering drawing image is first converted into a grayscale image. Then, the adjacent pixel points in the grayscale image are traversed, and the degree of change of the pixel values ​​of the adjacent pixel points, the number of times the pixel values ​​(per row and per column) exceed the threshold, and the distribution position of the pixel points exceeding the threshold are counted, so as to locate the effective area of ​​the drawing representing the range of the grayscale image border area. Finally, the coordinate axis range of the effective area of ​​the drawing is marked, and the correlation between the coordinate axis scale and the pixel point coordinate position is determined.

[0046] Specifically, at least one welding engineering drawing image that needs to be identified online is first converted into a grayscale image, and then, by judging the number of changes in the image pixel size, the starting coordinates of the effective area of ​​the drawing and the horizontal and vertical coordinate areas marked with letters and numbers are located, the effective area of ​​the drawing is framed out, and the x-axis and y-axis of the effective area of ​​the drawing are located in the coordinate axis range of the drawing.

[0047] Step S130, obtaining coordinate information of at least one welding symbol in the drawing according to the coordinate information of the effective area of ​​the drawing obtained in step S120 and the at least one welding symbol image obtained in step S110.

[0048] In one embodiment, first, the central pixel coordinate position of at least one welding symbol image is identified based on the pixel position information of at least one welding symbol image. Then, the coordinate position of the pixel cluster (in the drawing) corresponding to each welding symbol is obtained based on the central pixel coordinate position of at least one welding symbol image and the coordinate axis scale and pixel coordinate position indicated in the effective area of ​​the drawing.

[0049] Specifically, each welding symbol image I is first calculated iThe center pixel coordinate position of (i=1,2,3...), and then the pixel coordinate information of the coordinate axis area range of the effective area of ​​the drawing in step S120 is combined with each welding symbol image I i The center pixel coordinate position of (i=1,2,3...) is combined and converted to obtain each welding symbol image I i The coordinate position of each pixel point in the pixel point cluster within (i=1, 2, 3...) in the engineering drawing.

[0050] In actual application, each welding symbol image is an image with a specified size limit, which contains pixels that do not belong to the welding position, and the pixels belonging to the welding position in the same welding symbol image are recorded as the pixel cluster corresponding to the welding symbol, so that in step S130, the coordinate position of the corresponding pixel cluster in each welding symbol image in the actual engineering drawing can be converted according to the pixel position information in the welding symbol image and the association relationship between the pixel points indicated in the effective area of ​​the drawing and the actual drawing coordinate position, thereby entering step S140.

[0051] For example: All the information of the welding drawing is contained in a coordinate axis with the upper left corner of the drawing as the origin. By calculating the pixel transformation of the border area of ​​the image, that is, the coordinate axis area, the size of the coordinate axis of this drawing, that is, the effective area of ​​the drawing, is obtained. Then, the range of the coordinate axis and the pixel coordinates corresponding to each scale of the x-axis [1,2,3..] and y-axis [A,B,C,...] are confirmed. The pixel coordinates of the welding symbol in the drawing are converted to the coordinate information in the drawing by calculating the pixel coordinates of the welding symbol in the drawing, for example: the pixel coordinates of the welding symbol [600,500] -> the specific coordinates of the welding symbol in the drawing [6,E].

[0052] Step S140, generating a statistical table of welding joints of the drawing according to the basic information of the drawing obtained in step S120 and the coordinate information of at least one welding symbol in the drawing obtained in step S130.

[0053] In step S140, for at least one welding engineering drawing image with the same drawing number or drawing name, the coordinate position information of all welding symbol pixel point groups corresponding to each welding engineering drawing image is connected in series according to the arrangement order of the drawing images, a corresponding welding joint statistics table is generated, and a word document is automatically generated.

[0054] In addition, the drawing information identification method described in the embodiment of the present invention further includes: storing a statistical table of welding joints of at least one drawing of the engineering drawings to form a drawing information storage database.

[0055] The basic drawing information of the current engineering drawing, at least one welding engineering drawing image and a welding joint statistics table are associated and saved to form a drawing information storage database based on the associated saved information of all engineering drawings.

[0056] According to the query instruction including the drawing name or drawing number information, the welding joint statistics table in the corresponding associated saved information is retrieved, so that the welding engineer can view and download it online.

[0057] On the other hand, based on the above-mentioned drawing information recognition method, an embodiment of the present invention further provides a system for recognizing welding engineering drawing information (also called "drawing information recognition system"). The drawing information recognition system is used to implement the above-mentioned drawing information recognition method.

[0058] Figure 4 Schematic diagram of the structure of the system for identifying welding engineering drawing information according to an embodiment of the present application. Figure 4 As shown, the drawing information recognition system described in the embodiment of the present invention includes: a file uploading module 41, an image recognition module 42 and a statistical table generating module 43.

[0059] Specifically, the file upload module 41 is configured to obtain a welding engineering drawing image; the image recognition module 42 is configured to identify the image of at least one welding symbol in the welding engineering drawing image and basic information of the drawing, and then, based on the welding engineering drawing image, extract the minimum drawing area containing all welding symbols, recorded as the effective area of ​​the drawing, and finally, based on the coordinate information of the effective area of ​​the drawing and at least one welding symbol image, obtain the coordinate information of at least one welding symbol in the drawing; the statistical table generation module 43 is configured to generate a statistical table of welding joints of the drawing based on the basic information of the drawing and the coordinate information of at least one welding symbol in the drawing.

[0060] In an embodiment of the present invention, the three modules of file upload module 41, image recognition module 42 and statistical table generation module 43 are encapsulated based on the microservice architecture module, which can provide functional interfaces such as file upload, file download, and image viewing, and store the drawing information recognized by the system in a database to provide query and application of drawing information in other scenarios.

[0061] The present invention discloses a method and system for identifying welding engineering drawing information. The method and system are a welding engineering drawing information identification technology based on deep learning technology, which can effectively save and manage project drawing information, effectively identify welding symbols, drawing names and drawing numbers in drawings and automatically generate welding joint statistics, effectively helping engineers improve the efficiency of compiling welding joint lists, and at the same time, solve the problem of missed detection and wrong detection in identifying small objects such as weld symbols, improve the efficiency of manual weld identification, and significantly reduce the missed detection rate.

[0062] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any person familiar with the technology within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0063] In the description of the present invention, unless otherwise specified, "plurality" means two or more than two; the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right", "inner", "outer", "front end", "rear end", "head", "tail", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0064] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] It should be understood that the embodiments disclosed in the present invention are not limited to the specific structures, processing steps or materials disclosed herein, but should be extended to equivalent substitutions of these features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0066] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0067] Although the embodiments disclosed in the present invention are as above, the contents described are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A method for identifying welding engineering drawing information, characterized in that: include: Acquire a welding engineering drawing image, and identify at least one welding symbol image and basic drawing information; According to the welding engineering drawing image, extract the minimum drawing area containing all welding symbols and record it as the effective drawing area; Obtaining coordinate information of at least one welding symbol in the drawing according to the coordinate information of the effective area of ​​the drawing and at least one welding symbol image; A statistical table of welding joints of the drawing is generated according to the basic information of the drawing and the coordinate information of the at least one welding symbol in the drawing.

2. The method according to claim 1, characterized in that The step of acquiring a welding engineering drawing image and identifying an image of at least one welding symbol and basic information of the drawing includes: Extracting at least one welding symbol image and a title block image from the welding engineering drawing image using a drawing information recognition model; The text information in the title bar image is extracted to obtain basic information of the drawing, wherein the basic information of the drawing includes: a drawing name and a drawing number.

3. The method according to claim 2, characterized in that The drawing information recognition model is constructed using the following steps: Collect historically acquired welding engineering drawing images and select all weld symbol areas and title bar areas in the images; According to the historical welding engineering drawing images and the corresponding weld symbol area images and title bar area images, a data training set and a data verification set are constructed; A basic neural network model is established, and the data training set and the data verification set are used to train and verify the basic neural network model to obtain a drawing information recognition model.

4. The method according to claim 3, characterized in that: The basic neural network model adopts the Faster-RCNN target detection model, wherein the feature extraction part in the Faster-RCNN target detection model is implemented by using a ResNet50 module in combination with an FPN module.

5. The method according to any one of claims 1 to 4, characterized in that: The step of extracting the minimum drawing area including all welding symbols according to the welding engineering drawing image and recording it as the effective drawing area includes: Converting the welding engineering drawing image into a grayscale image; Traversing the pixel points in the grayscale image, and counting the degree of change of pixel values ​​of adjacent pixel points, the number of times the pixel values ​​exceed the threshold value and the pixel position, to locate the effective area of ​​the drawing representing the range of the grayscale image border area; Mark the coordinate axis range of the effective area of ​​the drawing, and determine the correlation between the coordinate axis scale and the pixel point coordinate position.

6. The method according to claim 5, characterized in that The step of obtaining coordinate information of at least one welding symbol in the drawing according to the coordinate information of the effective area of ​​the drawing and at least one welding symbol image includes: identifying a central pixel coordinate position of at least one welding symbol image; The coordinate position of the pixel point cluster corresponding to each welding symbol is obtained according to the central pixel coordinate position of the at least one welding symbol image and the correlation relationship between the coordinate axis scale indicated in the effective area of ​​the drawing and the pixel point coordinate position.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The format of the uploaded file is verified, and when the current format is the first type of file format, at least one welding engineering drawing image is obtained.

8. The method according to claim 7, characterized in that If the current format is the second type file format, the uploaded file is read page by page, and at least one page of welding engineering drawing image in the second type file format is converted into the first type file format.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: A statistical table of welding joints of at least one drawing is stored to form a drawing information storage database, wherein: According to the query instruction containing the drawing name or drawing number information, the corresponding welding joint statistics table is retrieved.

10. A system for identifying welding engineering drawing information, characterized in that: The system is used to implement the method according to any one of claims 1 to 9, wherein the system comprises: A file upload module configured to obtain welding engineering drawing images; An image recognition module is configured to recognize an image of at least one welding symbol in the welding engineering drawing image and basic drawing information, and then, based on the welding engineering drawing image, extract a minimum drawing area containing all welding symbols, which is recorded as a drawing effective area, and finally, based on the coordinate information of the drawing effective area and at least one welding symbol image, obtain coordinate information of at least one welding symbol in the drawing; A statistical table generating module is configured to generate a statistical table of welding joints of the drawing according to the basic information of the drawing and the coordinate information of the at least one welding symbol in the drawing.

Images