Drawing classification and signature method and device, equipment and medium

Abstract

The invention relates to a drawing classification and signature method, device and equipment and a medium, and belongs to the technical field of engineering drawing identification, and the drawing classification and signature method comprises the steps of obtaining a drawing and length and width information of the drawing, carrying out text information extraction on the drawing, obtaining a keyword, and determining coordinates of the keyword based on an established coordinate system. Establishing a feature matrix based on the coordinates of the keywords; determining the lengthening proportion and the mapsheet size of the drawings based on the length and width information, classifying the drawings based on the keywords, the feature matrix, the lengthening proportion and the mapsheet size, and determining the types of the drawings; the signature picture is obtained based on the keyword of the drawing, the feature matrix, the lengthening proportion, the mapsheet size and the drawing type, and the signature area of the drawing is signed based on the signature picture, so that the recognition efficiency and accuracy of the drawing type are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering drawing recognition, and in particular to a method, device, equipment and medium for classifying and signing drawings. Background Art

[0002] Engineering drawings are the medium for designers to express their design ideas and requirements. They can accurately and clearly display the structure, size, shape and other information of the product. In production and construction, engineering drawings are the basis for material preparation and construction. Manufacturers use drawings to understand design requirements and organize production and processing. During quality inspection, engineering drawings are the basis for inspecting product quality. When the project is completed, quality inspection and acceptance must be carried out in accordance with the design requirements of the drawings. Engineering drawings are a platform for technical exchange and cooperation, promoting communication and collaboration between different professions and teams. Engineering drawings are an important basis for budget and cost control, providing basic data for economic analysis and cost control of engineering projects. Engineering drawings facilitate later maintenance and provide detailed reference for the inspection and renovation of the project.

[0003] With the widespread application of PDF format in the engineering field, the classification management of PDF engineering drawings has become particularly important. In order to efficiently manage and quickly retrieve a large number of PDF drawings, a variety of classification methods and technologies have emerged. These classification methods help engineers and designers quickly find the required drawings and improve work efficiency.

[0004] However, the traditional method of classifying engineering drawings has the problem of difficulty in identifying drawing types and being time-consuming. Summary of the invention

[0005] In view of this, it is necessary to provide a drawing classification and signing method, device, equipment and medium to solve the technical problem of difficulty in identifying drawing types when classifying PDF drawings.

[0006] In order to solve the above problems, the present invention provides a method for classifying and signing drawings, comprising: Acquire drawings and length and width information of the drawings, extract text information from the drawings, obtain keywords, determine coordinates of the keywords based on an established coordinate system, and establish a feature matrix based on the coordinates of the keywords; Determine the lengthening ratio and the size of the drawing based on the length and width information, classify the drawing based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determine the type of the drawing; A signature image is obtained based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and a signature area of ​​the drawing is signed based on the signature image.

[0007] In a possible implementation, the keywords include reviewer role information keywords and map basic information keywords, the reviewer role information includes at least one or more of design, verification, review, review, professional person in charge, signature, project person in charge, and project manager, and the map basic information includes at least one or more of date, stage, part, drawing number, countersignature column, profession, signature, description, scale, edition, seal, and professional seal.

[0008] In a possible implementation manner, determining the coordinates of the keyword based on the established coordinate system includes: Take the lower left corner of the drawing as the coordinate origin and establish a two-dimensional coordinate system; The absolute coordinates of the keywords and the relative coordinates between the keywords are determined based on the two-dimensional coordinate system.

[0009] In a possible implementation, establishing a feature matrix based on the coordinates of the keyword includes: A feature matrix is ​​established based on the absolute coordinates of the keywords and the relative coordinates between the keywords.

[0010] In a possible implementation, determining the lengthening ratio and the size of the drawing based on the length and width information includes: Extracting length and width information of the drawing according to the standard, wherein the length and width information includes length information and width information of the drawing; Determine the drawing size based on the width information of the drawing, wherein the drawing size includes A0, A1, A2, A3, and A4; The lengthening ratio of the drawing is determined based on the length information of the drawing and the standard drawing length.

[0011] In a possible implementation, the classifying the drawings based on the keywords, feature matrix, lengthening ratio, and drawing size to determine the drawing type includes: A multi-level screening mechanism is established based on the keywords, feature matrix, lengthening ratio and map size, wherein the multi-level screening mechanism includes a primary screening mechanism, a secondary screening mechanism and a tertiary screening mechanism, wherein the primary screening mechanism is established based on the lengthening ratio and map size, the secondary screening mechanism is established based on the keywords, and the tertiary screening mechanism is established based on the feature matrix; The drawings are classified based on the multi-level screening mechanism to determine the drawing types, wherein the drawing types include municipal drawings, water transport drawings, road and bridge drawings, and architectural drawings.

[0012] In a possible implementation, obtaining a signature image based on the keyword, feature matrix, lengthening ratio, drawing size, and drawing type of the drawing, and signing a signature area of ​​the drawing based on the signature image includes: Based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, an OCR recognition method is used to determine the signature image, offset and signature font of the drawing; The signature area of ​​the drawing is signed based on the signature image, the offset, and the signature font.

[0013] On the other hand, the present invention also provides a drawing classification and signature device, comprising: A feature matrix acquisition module is used to obtain drawings and length and width information of the drawings, extract text information from the drawings, obtain keywords, determine the coordinates of the keywords based on the established coordinate system, and obtain a feature matrix based on the coordinates of the keywords; A drawing classification module, used to determine the lengthening ratio and the size of the drawing based on the length and width information, classify the drawing based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determine the drawing type; The drawing signature module is used to obtain a signature image based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and sign the signature area of ​​the drawing based on the signature image.

[0014] In another aspect, the present invention further provides an electronic device, comprising: a processor and a memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the method for classifying and signing drawings as described above are implemented.

[0015] On the other hand, the present invention also provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the method for classifying and signing drawings as described above.

[0016] The beneficial effects of the present invention are as follows: drawings are classified based on keywords, feature matrices, lengthened ratios, and sheet sizes to determine drawing types; a multi-level screening mechanism is constructed through keywords, feature matrices, lengthened ratios, and sheet sizes; PDF drawings are classified through the multi-level screening mechanism, a flexible drawing classification method is provided, the efficiency and accuracy of identifying drawing types are improved, the problem of difficulty in identifying drawing types is solved, a signature image is obtained based on the keywords, feature matrices, lengthened ratios, sheet sizes, and drawing types of the drawings; a signature area of ​​the drawing is signed based on the signature image, the security of the drawing is improved, and the accuracy of the drawing signature is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of an embodiment of the method for classifying and signing drawings provided by the present invention; Figure 2 A schematic diagram of the proportion of drawings of the drawings in the classification and signature method of drawings provided by the present invention; Figure 3 A schematic diagram of automatic signature for drawings of the classification and signature method of drawings provided by the present invention; Figure 4 A schematic diagram of the structure of an embodiment of the drawing classification and signature device provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0019] The present invention discloses a method, device, equipment and medium for classifying and signing drawings, which can be used in a computer. The method, equipment or computer-readable storage medium involved in the present invention can be integrated with the above-mentioned equipment or can be relatively independent.

[0020] A specific embodiment of the present invention discloses a method for classifying and signing drawings, which can be executed by a computer, and specifically by one or more processors of the computer. Figure 1 As shown, the classification and signature methods of drawings include: S101, obtaining drawings and length and width information of the drawings, extracting text information from the drawings, obtaining keywords, determining coordinates of the keywords based on an established coordinate system, and establishing a feature matrix based on the coordinates of the keywords; S102, determining the lengthening ratio and the size of the drawing based on the length and width information, classifying the drawings based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determining the type of the drawing; S103, obtaining a signature image based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and signing the signature area of ​​the drawing based on the signature image.

[0021] Among them, the process of drawing classification is not only based on the size of the drawings, but also preliminarily screens the drawings through keywords, and then further matches them in combination with the keyword matrix. This multi-level screening mechanism improves the efficiency and flexibility of drawing classification.

[0022] Compared with the prior art, the classification and signing method of drawings provided in this embodiment obtains drawings and length and width information of drawings, extracts text information of drawings, obtains keywords, determines the coordinates of keywords based on the established coordinate system, and establishes a feature matrix based on the coordinates of keywords; determines the lengthening ratio and sheet size of drawings based on the length and width information, classifies drawings based on keywords, feature matrix, lengthening ratio and sheet size, and determines the drawing type; constructs a multi-level screening mechanism through keywords, feature matrix, lengthening ratio and sheet size, and classifies PDF drawings through the multi-level screening mechanism, provides a flexible drawing classification method, improves the recognition efficiency and accuracy of drawing types, obtains signature images based on the keywords, feature matrix, lengthening ratio, sheet size and drawing type of drawings, and signs the signature area of ​​the drawing based on the signature image, thereby improving the security of the drawings and ensuring the accuracy of the drawing signatures.

[0023] In some embodiments, in step S101, the drawings and the length and width information of the drawings are obtained, the text information of the drawings is extracted, the keywords are obtained, a series of PDF drawings are obtained, the PDF drawings are pre-processed, the text information of the PDF drawings is extracted, and the keywords of the PDF drawings are obtained, wherein the keywords include two types of keywords: the reviewer role information keywords and the basic information keywords of the drawing. The reviewer role information includes at least one or more of design, verification, review, review, professional person in charge, signature, project person in charge, and project manager. The basic information of the drawing includes at least one or more of date, stage, part, drawing number, countersignature column, profession, signature, description, scale, edition, seal, and professional seal. The coordinates of the keywords are determined based on the established coordinate system, with the lower left corner of the drawing as the coordinate origin. , establish a two-dimensional coordinate system, determine the absolute coordinates of the keywords and the relative coordinates between the keywords based on the two-dimensional coordinate system, the absolute coordinates of the keywords are the coordinates between the coordinate origin and the keywords, the relative coordinates between the keywords are the coordinates between the keywords and other keywords, establish a feature matrix based on the coordinates of the keywords, establish a feature matrix based on the absolute coordinates of the keywords and the relative coordinates between the keywords, for example, the keywords in the drawing are project manager, design, review, verification, approval, and audit. According to the coordinate system, the relative coordinates of the project manager and the design, review, verification, approval, and audit are determined with the project manager as the starting point, respectively: , , , , , After calculating the absolute coordinates of the keywords relative to the coordinate origin, a feature matrix is ​​established based on the absolute coordinates of the keywords and the relative coordinates between the keywords. The feature matrix is: , PDF drawings contain multiple keywords, which can form multiple feature matrices; by extracting the keyword position features of PDF drawings and combining the relative coordinates of the project manager's keywords relative to other review roles, a multi-dimensional feature matrix is ​​formed. By obtaining the relative coordinates of review roles such as project managers, designers, and auditors, a keyword matrix is ​​formed. The keyword matrix is ​​not based on the absolute coordinates of the drawings, but is calculated based on the relative positions of the keywords in the drawings. This relative coordinate system improves the adaptability to different drawing types.

[0024] In some embodiments, in step S102, the lengthening ratio and the size of the drawing are determined based on the length and width information, and the length and width information of the drawing are extracted according to the standard, wherein the length and width information includes the length information and the width information of the drawing, and the size of the drawing is determined based on the width information of the drawing, wherein the drawing size includes A0, A1, A2, A3, and A4; the lengthening ratio of the drawing is determined based on the length information of the drawing and the standard drawing length; according to the national standard GB / T14689-1993 "Technical Drawing Sheet Size and Format", the length and width of the PDF drawing are extracted, the size of the drawing is determined by the short side, and then the lengthening ratio of the drawing is obtained by the long side length / standard drawing length; standard drawing frame A0: , A1: , A2: , A3: , A4: For example, extract the length and width information of the PDF drawing such as , according to the short side (width) 841, the drawing size is determined as A0 drawing, and the lengthening ratio is determined by the long side. , the lengthening ratio is 0.5. For the schematic diagram of the drawing scale, please refer to Figure 2 .

[0025] Based on keywords, feature matrix, lengthening ratio and drawing size, the drawings are classified to determine the drawing type. A multi-level screening mechanism is established based on keywords, feature matrix, lengthening ratio and drawing size, wherein the multi-level screening mechanism includes a primary screening mechanism, a secondary screening mechanism and a tertiary screening mechanism. A primary screening mechanism is established based on the lengthening ratio and drawing size, a secondary screening mechanism is established based on keywords, and a tertiary screening mechanism is established based on the feature matrix. Drawings are classified based on the multi-level screening mechanism to determine the drawing type, wherein the drawing types include municipal drawings, water transport drawings, road and bridge drawings and architectural drawings; the drawings are preliminarily classified through the primary screening mechanism established by the lengthening ratio and drawing size, and then the drawings are preliminarily screened through the secondary screening mechanism established by the keywords of the PDF drawings, and then the drawings are matched through the tertiary screening mechanism established by the keyword feature matrix to determine the final drawing type. The setting for drawing classification according to keywords is as follows: In municipal drawings, the review role information keywords are: design, verification, review, re-review, audit, Professional person in charge; the keywords for the basic information of the map are: date, stage, part, drawing number, counter-signature column, profession, signature; in water transport drawings, the keywords for the review role information are: design, verification, review, re-examination, approval, project manager; the keywords for the basic information of the map are: edition, date, description, unit special seal for drawing (stamp), stage, scale, part, date, drawing number, electronic file name, edition, counter-signature; in road and bridge drawings, the keywords for the review role information are: design, verification, review, re-examination (excluding the keywords of approval, professional person in charge, and project manager); the keywords for the basic information of the map are: date, stage, drawing number, profession, signature, counter-signature column; in architectural drawings, the keywords for the review role information are: project person in charge, professional person in charge, design, proofreading, review, approval, signature, and the keywords for the basic information of the map are: The keywords of this information are: profession, scale, drawing number, edition, stage, date, drawing signature, and practice signature; when the keywords in the drawing are not included in the set keywords, such drawings are marked as undefine type drawings, that is, when the drawing is not a municipal drawing, water transport drawing, road and bridge drawing, or architectural drawing according to the set keywords, the drawing is an undefine drawing; after the keywords in the drawing are preliminarily screened according to the set keywords, the drawings are matched according to the feature matrix of the keywords in the drawing to determine the final drawing type; the classification process of drawing types is not only based on the size of the drawing (such as A0~A4), but also preliminarily screened by keywords, and then further matched in combination with the keyword matrix. This multi-level screening mechanism improves the efficiency and accuracy of drawing classification.

[0026] In some embodiments, in step S103, a signature image is obtained based on the keywords, feature matrix, lengthening ratio, sheet size and drawing type of the drawing, and the signature area of ​​the drawing is signed based on the signature image. Based on the keywords, feature matrix, lengthening ratio, sheet size and drawing type of the drawing, an OCR recognition method is used to determine the signature image, offset and signature font of the drawing, and the signature area of ​​the drawing is signed based on the signature image, offset and signature font; after determining the drawing type, keywords, feature matrix, lengthening ratio and sheet size of the drawing to be signed, the drawing with the same drawing type as the drawing to be signed is trained through OCR recognition to obtain the signature image, signature font and offset of the signature area in the drawing of the drawing to be signed, and the signature image is the name of the reviewer in the drawing, such as design: Zhang San, verification: Li Si, review: Wang Wu, review: Zhao Liu, approved by Zhu Qi; Signing is performed by querying the keywords of the drawing to be signed and the offset of the signature area. For example, if the drawing to be signed is a municipal A2 drawing, the optimal offset and font size of the A2 type drawing are obtained after training, and then the optimal offset and font size of the A2 type drawing are used as the specific parameters of the drawing to be signed. When signing, the optimal offset and font size are directly taken; during the signing process, the lengthening ratio and keyword matrix are combined to provide precise adjustment of the signature area to ensure that the signature font and signature area remain consistent when the drawing is lengthened; by extracting the keyword position features of the drawing template and combining the relative coordinate system, a feature matrix is ​​established for classification; by obtaining the drawing information and the relative coordinates of the review role, the drawing type recognition and lengthening ratio processing are realized to ensure the uniformity of the signature position and font size. For the schematic diagram of the automatic signature of the drawing, please refer to Figure 3 . In order to better implement the classification and signature method of drawings in the embodiment of the present invention, based on the classification and signature method of drawings, correspondingly, Figure 4 As shown, the embodiment of the present invention further provides a drawing classification and signature device, and the drawing classification and signature device 400 includes: The feature matrix acquisition module 401 is used to obtain the drawings and the length and width information of the drawings, extract text information from the drawings, obtain keywords, determine the coordinates of the keywords based on the established coordinate system, and obtain the feature matrix based on the coordinates of the keywords; A drawing classification module 402 is used to determine the lengthening ratio and the size of the drawing based on the length and width information, classify the drawings based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determine the type of the drawing; The drawing signature module 403 is used to obtain a signature image based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and sign the signature area of ​​the drawing based on the signature image.

[0027] like Figure 5As shown, the present invention also provides an electronic device 500 , which can be a computing device such as a mobile terminal, a desktop computer, a notebook, a palmtop computer, a server, etc. The electronic device 500 includes a processor 501 , a memory 502 , and a display 503 . Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0028] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500. Further, the memory 502 may also include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software and various types of data installed in the electronic device 500, such as program codes installed in the electronic device 500. The memory 502 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 502 stores a drawing classification and signature program, which can be executed by the processor 501, thereby realizing the drawing classification and signature method of each embodiment of the present invention.

[0029] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 502, such as the classification and signing method of drawings.

[0030] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display the classification of drawings and the identification information of the signature program and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other through a system bus.

[0031] In some embodiments, when the processor 501 executes the drawing classification and signing program in the memory 502, the various steps in the drawing classification and signing method described in the above embodiments are implemented. Since the drawing classification and signing method has been described in detail above, it will not be repeated here.

[0032] Accordingly, the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the drawing classification and signing methods provided in the above-mentioned method embodiments.

[0033] In summary, the classification and signing method, device, equipment and medium for drawings provided by the present invention obtain drawings and length and width information of drawings, extract text information from drawings, obtain keywords, determine the coordinates of the keywords based on an established coordinate system, and establish a feature matrix based on the coordinates of the keywords; determine the lengthening ratio and size of the drawings based on the length and width information, classify the drawings based on the keywords, feature matrix, lengthening ratio and size, and determine the drawing type; obtain a signature image based on the keywords, feature matrix, lengthening ratio, size and drawing type of the drawings, and sign the signature area of ​​the drawing based on the signature image, thereby improving the recognition efficiency and accuracy of the drawing type.

[0034] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0035] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for classifying and signing drawings, characterized in that: include: Acquire drawings and length and width information of the drawings, extract text information from the drawings, obtain keywords, determine coordinates of the keywords based on an established coordinate system, and establish a feature matrix based on the coordinates of the keywords; Determine the lengthening ratio and the size of the drawing based on the length and width information, classify the drawing based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determine the type of the drawing; A signature image is obtained based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and a signature area of ​​the drawing is signed based on the signature image.

2. The method for classifying and signing drawings according to claim 1, characterized in that: The keywords include reviewer role information keywords and map basic information keywords. The reviewer role information includes at least one or more of design, verification, review, recheck, professional leader, signature, project leader, and project manager. The basic map information includes at least one or more of date, stage, part, drawing number, countersignature column, profession, signature, description, scale, edition, seal, and professional seal.

3. The method for classifying and signing drawings according to claim 2, characterized in that: The determining the coordinates of the keyword based on the established coordinate system includes: Take the lower left corner of the drawing as the coordinate origin and establish a two-dimensional coordinate system; The absolute coordinates of the keywords and the relative coordinates between the keywords are determined based on the two-dimensional coordinate system.

4. The method for classifying and signing drawings according to claim 3, characterized in that: The step of establishing a feature matrix based on the coordinates of the keywords includes: A feature matrix is ​​established based on the absolute coordinates of the keywords and the relative coordinates between the keywords.

5. The method for classifying and signing drawings according to claim 4, characterized in that: The determining the lengthening ratio and the size of the drawing based on the length and width information includes: Extracting length and width information of the drawing according to the standard, wherein the length and width information includes length information and width information of the drawing; Determine the drawing size based on the width information of the drawing, wherein the drawing size includes A0, A1, A2, A3, and A4; The lengthening ratio of the drawing is determined based on the length information of the drawing and the standard drawing length.

6. The method for classifying and signing drawings according to claim 5, characterized in that: The classifying the drawings based on the keywords, feature matrix, lengthening ratio and drawing size to determine the drawing type includes: A multi-level screening mechanism is established based on the keywords, feature matrix, lengthening ratio and map size, wherein the multi-level screening mechanism includes a primary screening mechanism, a secondary screening mechanism and a tertiary screening mechanism, wherein the primary screening mechanism is established based on the lengthening ratio and map size, the secondary screening mechanism is established based on the keywords, and the tertiary screening mechanism is established based on the feature matrix; The drawings are classified based on the multi-level screening mechanism to determine the drawing types, wherein the drawing types include municipal drawings, water transport drawings, road and bridge drawings, and architectural drawings.

7. The method for classifying and signing drawings according to claim 6, characterized in that: The step of obtaining a signature image based on the keywords, feature matrix, lengthening ratio, drawing size, and drawing type of the drawing, and signing the signature area of ​​the drawing based on the signature image includes: Based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, an OCR recognition method is used to determine the signature image, offset and signature font of the drawing; The signature area of ​​the drawing is signed based on the signature image, the offset, and the signature font.

8. A drawing classification and signature device, characterized in that: include: A feature matrix acquisition module is used to obtain drawings and length and width information of the drawings, extract text information from the drawings, obtain keywords, determine the coordinates of the keywords based on the established coordinate system, and obtain a feature matrix based on the coordinates of the keywords; A drawing classification module, used to determine the lengthening ratio and the size of the drawing based on the length and width information, classify the drawing based on the keywords, feature matrix, lengthening ratio and the size of the drawing, and determine the drawing type; The drawing signature module is used to obtain a signature image based on the keywords, feature matrix, lengthening ratio, drawing size and drawing type of the drawing, and sign the signature area of ​​the drawing based on the signature image.

9. An electronic device, characterized in that: including memory and processor; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the processor implements the steps in the method for classifying and signing drawings as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the method for classifying and signing drawings as described in any one of claims 1-7.

Images