Methods, apparatus, equipment, and readable storage media for beam span recognition in vector graphics.

Abstract

This invention relates to the field of drawing recognition technology, and discloses a method, apparatus, device, and readable storage medium for beam span recognition in vector graphics. The method includes: acquiring a target vector graphic to be recognized; detecting beam span regions in the target vector graphic; identifying line primitives within the beam span regions; determining the target line primitives of the beam chain in which the beam span is located; identifying beam span support points based on the positional information of the target line primitives; and cutting the beam chain based on the beam span support points to obtain the target beam span primitives in the vector graphic. By implementing this invention, a large amount of feature extraction work is avoided in the beam span primitive recognition process, and it is not limited by the experience of technical personnel. By extracting beam span support points and beam chains, high-precision automatic recognition of beam span primitives is achieved, solving the problem of inaccurate beam span primitive recognition.

Description

Technical Field

[0001] This invention relates to the field of drawing recognition technology, specifically to a method, apparatus, device, and readable storage medium for beam span recognition in vector drawings. Background Technology

[0002] Beams, as common components in building construction, exhibit various stress equilibrium conditions. In CAD vector drawing, beams are typically represented by multiple line segments. Identifying beam elements in CAD vector drawings requires dividing these segments based on the support positions at both ends of the beam to identify the span of each section. Currently, machine learning algorithms or deep learning are commonly used for beam span identification. However, machine learning-based beam span identification in vector drawings primarily involves extracting features such as in-situ annotations at supports and reinforcement lines. This requires highly precise feature extraction, necessitating the design of appropriate feature matrices based on specific business needs. Incorrect feature extraction can severely impact beam span identification. Furthermore, inexperienced technicians often struggle to design different feature matrices for different business requirements, hindering accurate beam span identification in vector drawings. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, apparatus, device, and readable storage medium for beam span identification in vector graphics, in order to solve the problem of difficulty in accurately identifying beam span elements in vector graphics.

[0004] According to a first aspect, embodiments of the present invention provide a method for identifying beam spans in vector graphics, comprising: acquiring a target vector graphics to be identified, detecting beam span regions in the target vector graphics; identifying line primitives in the beam span regions, determining target line primitives of the beam chain in which the beam span is located; identifying beam span support points based on the position information of the target line primitives; and cutting the beam chain based on the beam span support points to obtain the target beam span primitives in the vector graphics.

[0005] The beam span identification method for vector graphics provided in this invention detects beam span regions in the target vector graphics, then identifies beam chains and beam span support points within these regions. By cutting the beam chains according to the beam span support points, multiple target beam span elements are obtained, thereby achieving automatic identification of beam span elements in the target vector graphics. This method avoids extensive feature extraction work, is not limited by the experience of technical personnel, and achieves high-precision identification of beam span elements by extracting beam span support points and beam chains, solving the problem of inaccurate identification of beam span elements.

[0006] In conjunction with the first aspect, in the first embodiment of the first aspect, identifying beam span support points based on the position information of the target line element includes: obtaining the endpoint positions of the target line element to obtain multiple candidate support points; determining whether the candidate support points are endpoints of the beam chain; when the candidate support points are not endpoints of the beam chain, extracting attribute information corresponding to each candidate support point and calculating the feature value of each candidate support point; filtering the candidate support points based on the feature value to obtain the beam span support points.

[0007] The beam span identification method for vector graphics provided in this invention uses the endpoints of target line primitives as candidate support points. When a candidate support point is not an endpoint of the beam chain, the method extracts the attribute information of the candidate support point and calculates its feature value based on this attribute information. Then, the method filters the candidate support points based on the feature value to determine the beam span support point. This method determines whether a candidate support point is a beam span support point by using its attribute information, ensuring the accuracy of beam span support point identification and minimizing misidentification.

[0008] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, the step of extracting the attribute information corresponding to each of the candidate support points and calculating the feature value of each of the candidate support points includes: extracting the force information of the beam chain intersecting with the candidate support point to determine the force equilibrium feature value of the candidate support point; extracting the geometric information of the beam chain intersecting with the candidate support point to determine the geometric feature value of the candidate support point; extracting the beam span identification information corresponding to the candidate support point to determine the identification feature value of the candidate support point; and calculating the feature value of the candidate support point based on the force equilibrium feature value, the geometric feature value, and the preset weight ratio corresponding to the identification feature value.

[0009] The beam span identification method based on vector graphics provided in this invention combines the stress equilibrium feature values, geometric feature values, and beam span identification feature values ​​of candidate support points to determine the final feature values ​​of the candidate support points. By performing multi-dimensional feature extraction on the candidate support points, the feature values ​​are ensured to accurately characterize the candidate support points, facilitating subsequent screening of candidate support points to determine the beam span support points.

[0010] In conjunction with the first embodiment of the first aspect, in the third embodiment of the first aspect, the method further includes: when the candidate support point is the end point of the beam chain, determining the candidate support point as the beam span support point.

[0011] The beam span identification method for vector graphics provided in this invention directly identifies the candidate support point as the beam span support point when the endpoint of the beam chain is one of the beam span support points. This avoids feature extraction of the endpoint, saves feature extraction time, and improves the identification efficiency of beam span support points, thereby improving the identification efficiency of beam span primitives.

[0012] In conjunction with the first aspect, in the fourth embodiment of the first aspect, the step of cutting the beam chain based on the beam span support points to obtain the target beam span element in the vector drawing includes: cutting the beam chain into multiple beam span elements based on the geometric position of the beam span support points on the beam chain; obtaining the span attributes corresponding to the multiple beam span elements; and determining the target beam span element from the multiple beam span elements based on the span attributes.

[0013] The beam span recognition method for vector graphics provided in this invention involves cutting the beam chain according to the geometric position of the beam span support point on the beam chain to obtain multiple beam span elements, and extracting the span attribute corresponding to each beam span element to determine whether the recognition of the beam span element is accurate based on the span attribute, thereby further improving the recognition effect.

[0014] In conjunction with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, the span attribute includes line segment primitives, span-to-height ratio, and beam span width. Determining the target beam span primitive from the plurality of beam span primitives based on the span attribute includes: determining whether the line segment primitives corresponding to the beam span primitive are continuous, whether the beam span width of the beam span primitive changes, and whether the span-to-height ratio of the beam span primitive exceeds a preset ratio. When the line segment primitives corresponding to the beam span primitive are continuous, the beam span width of the beam span primitive does not change, and the span-to-height ratio of the beam span primitive does not exceed the preset ratio, the beam span primitive is determined to be a valid beam span primitive, and the valid beam span primitive is determined as the target beam span primitive.

[0015] In conjunction with the fifth embodiment of the first aspect, in the sixth embodiment of the first aspect, the step of determining the target beam span element from the plurality of beam span elements based on the span attribute further includes: when the line segment element corresponding to the beam span element is discontinuous, the beam span width of the beam span element changes, and the span-to-height ratio of the beam span element exceeds the preset ratio, determining that the beam span element is a beam span element added in the middle, and determining the beam span element added in the middle as the target beam span element.

[0016] In conjunction with the fifth embodiment of the first aspect, in the seventh embodiment of the first aspect, the span attribute further includes beam span stiffness; the step of determining the target beam span element from the plurality of beam span elements based on the span attribute further includes: determining whether the beam span stiffness corresponding to the beam span element exceeds a preset value; when the beam span stiffness exceeds the preset value, determining that there is an end error in the identification of the beam span element, and determining the beam span element as an invalid beam span element.

[0017] The beam span recognition method for vector graphics provided in this invention detects multiple beam span elements by using span attributes, which can more directly reflect the structural information of the beam span elements and thus greatly improve the recognition accuracy of the beam span elements.

[0018] In conjunction with any of the fourth to seventh embodiments of the first aspect, in the eighth embodiment of the first aspect, the method further includes: identifying in-situ annotation information corresponding to the beam span element; and calculating the span feature of the beam span element based on the in-situ annotation information.

[0019] The beam span recognition method for vector graphics provided in this invention reduces the computational complexity of features and improves recognition efficiency to a certain extent by recognizing the in-situ annotation information corresponding to the beam span graphic element and calculating the span feature based on the in-situ annotation information.

[0020] In conjunction with the first aspect, in the ninth embodiment of the first aspect, the step of obtaining the target vector drawing to be identified and detecting the beam span region in the target vector drawing includes: obtaining primitive attribute information in the original vector drawing; filtering interfering primitives in the target vector drawing based on the primitive attribute information to obtain the target vector drawing; converting the target vector drawing into a matrix representation and identifying the beam span region from the matrix representation; and mapping the beam span region to the target vector drawing to obtain the beam span region in the target vector drawing.

[0021] The beam span identification method for vector graphics provided in this invention efficiently and accurately filters interfering elements in the target vector graphics paper using element attribute information, thereby obtaining the target vector graphics paper. This avoids interference from interfering elements in the identification of beam span elements, ensuring accurate identification of beam span elements in subsequent steps. By converting the target vector graphics paper into a matrix representation, identifying the region where the beam span is located from the matrix representation, and then mapping the region where the beam span is located back to the target vector graphics paper, the beam span region in the target vector graphics paper is obtained. This eliminates the need to design different feature matrices based on different business requirements; it only requires converting the target vector graphics paper into a matrix that can represent the structural information of the beam span. This minimizes the limitations of business scenarios and improves its generalization and applicability.

[0022] In conjunction with the first aspect, in the tenth embodiment of the first aspect, the method further includes: obtaining the beam type corresponding to the target beam span element; detecting whether there is a drawing deviation in the drawing of the target beam span element; when there is a drawing deviation in the drawing of the target beam span element, extending the target beam span element based on the beam type, the extension processing being used to correct the drawing deviation.

[0023] The beam span identification method for vector graphics provided in this invention corrects the drawing deviation by extending the target beam span primitives with drawing deviations. It is not limited by the designer's drawing method and improves the generalizability of use.

[0024] In conjunction with the first aspect, in the eleventh embodiment of the first aspect, the method further includes: performing attribute verification on the target beam span element to determine whether the target beam span element is incorrectly identified; when the target beam span element is incorrectly identified, re-identifying the beam span support point.

[0025] The beam span identification method for vector graphics provided in this invention, after automatically identifying beam span elements, performs attribute verification on the target beam span elements to determine whether there are identification errors. If there are identification errors in the target beam span elements, the beam span support points in the target vector graphics need to be re-identified to ensure the accuracy of beam span element identification.

[0026] In conjunction with the first aspect, in a twelfth embodiment of the first aspect, the method further includes: in response to an identification operation of beam span elements, identifying and correcting beam span elements in the target vector drawing based on the identification operation.

[0027] The beam span recognition method for vector graphics provided in this invention can respond to the recognition operation of beam span elements by technicians, select the recognition area of ​​beam span elements to improve recognition efficiency, and correct the position of recognition error to further improve the recognition accuracy of beam span elements.

[0028] According to a second aspect, embodiments of the present invention provide a beam span identification device for vector graphics, comprising: an acquisition module for acquiring a target vector graphics to be identified and detecting beam span regions in the target vector graphics; a first identification module for identifying line elements in the beam span regions and determining target line elements of the beam chain where the beam span is located; a second identification module for identifying beam span support points based on the position information of the target line elements; and a cutting module for cutting the beam chain based on the beam span support points to obtain the target beam span elements in the vector graphics.

[0029] According to a third aspect, embodiments of the present invention provide an electronic device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the beam span recognition method for vector paper as described in the first aspect or any embodiment of the first aspect.

[0030] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the beam span recognition method for vector drawings as described in the first aspect or any embodiment of the first aspect.

[0031] It should be noted that the beneficial effects of the beam span recognition device, electronic device and computer-readable storage medium for vector drawings provided in the embodiments of the present invention can be found in the description of the corresponding content in the beam span recognition method for vector drawings, and will not be repeated here. Attached Figure Description

[0032] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0033] Figure 1 This is a flowchart of a beam span identification method using vector graphics according to an embodiment of the present invention;

[0034] Figure 2 This is another flowchart of a beam span recognition method for vector graphics paper according to an embodiment of the present invention;

[0035] Figure 3 This is another flowchart of a beam span recognition method for vector graphics paper according to an embodiment of the present invention;

[0036] Figure 4 This is another flowchart of a beam span recognition method for vector graphics paper according to an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram illustrating the identification of beam span elements according to an embodiment of the present invention;

[0038] Figure 6 This is a structural block diagram of a beam span recognition device based on a vector graphic according to an embodiment of the present invention;

[0039] Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] According to an embodiment of the present invention, an embodiment of a beam span identification method for vector graphics is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] This embodiment provides a method for beam span identification from vector graphics, which can be used in electronic devices such as mobile phones, tablets, and computers. Figure 1 This is a flowchart of a beam span identification method using vector graphics according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0043] S11, Obtain the target vector drawing to be identified, and detect the beam span area in the target vector drawing.

[0044] The target vector drawing to be identified is a vector drawing containing the beam span elements to be identified, such as different types of CAD vector drawings like gcad, dwg, and pdf. The electronic device can respond to the designer's creation operation of the beam component drawings to obtain the target vector drawing designed by the designer according to actual business needs; it can also retrieve the target vector drawing from local storage space by querying it; or it can retrieve the target vector drawing from external storage space (such as USB flash drive, external hard drive, etc.) through a communication interface. Of course, other methods can also be used to obtain the target vector drawing; these are not specifically limited here, and those skilled in the art can determine them according to actual needs.

[0045] The beam span region is the area where the beam component elements are located in the target vector drawing. Electronic devices can perform target detection on the beam component elements in the target vector drawing to determine the area of ​​the beam component elements in the target vector drawing, thereby obtaining the beam span region.

[0046] S12, identify line elements in the beam span region and determine the target line elements of the beam chain where the beam span is located.

[0047] The target line primitives are the line primitives of multiple beam spans that constitute the beam chain. The electronic device further identifies the attributes of the line primitives contained in the beam span area to obtain the two-dimensional position information of each line primitive, and then determines the target line primitives for generating the beam chain based on the two-dimensional position information of the line primitives.

[0048] S13, Identify beam span support points based on the location information of target line elements.

[0049] Based on the location information of the target line elements, possible support points in the beam span area can be located. For each possible support point, the electronic device can further sort multiple possible support points according to the force characteristics, geometric characteristics, and identification characteristics of the beam span support points, and filter out the support points that meet the force characteristics, geometric characteristics, and identification characteristics as the beam span support points.

[0050] S14, the beam chain is cut based on the support points of the beam span to obtain the target beam span primitive in the vector drawing.

[0051] The target beam span primitive is the multiple beam span primitives actually contained within the beam span area of ​​the target vector drawing. The electronic device can cut the beam chain according to the geometric position of the identified beam span support points to obtain multiple beam span primitives. Then, the geometric properties of each beam span primitive are detected to determine whether each cut beam span primitive is valid. If the beam span primitive is valid, it is identified as the target beam span primitive.

[0052] Electronic devices can also perform feature detection on the in-situ annotation information of beam span elements, and combine the feature detection of beam span elements with geometric attributes to effectively determine each beam span element obtained by cutting the beam chain, so as to identify the target beam span element.

[0053] The beam span identification method for vector graphics provided in this embodiment detects beam span regions in the target vector graphics, then identifies beam chains and beam span support points within these regions. By cutting the beam chains according to the beam span support points, multiple target beam span elements are obtained, thereby achieving automatic identification of beam span elements in the target vector graphics. This method avoids extensive feature extraction work, is not limited by the experience of technical personnel, and achieves high-precision identification of beam span elements by extracting beam span support points and beam chains, solving the problem of inaccurate identification of beam span elements.

[0054] This embodiment provides a method for beam span identification from vector graphics, which can be used in electronic devices such as mobile phones, tablets, and computers. Figure 2 This is a flowchart of a beam span identification method using vector graphics according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps:

[0055] S21, Obtain the target vector drawing to be identified, and detect the beam span region in the target vector drawing. For detailed explanations, please refer to the relevant descriptions of the corresponding steps in the above embodiments; they will not be repeated here.

[0056] S22, Identify the line elements in the beam span region and determine the target line elements of the beam chain where the beam span is located. For detailed explanations, please refer to the relevant descriptions of the corresponding steps in the above embodiments; they will not be repeated here.

[0057] S23, Identify beam span support points based on the location information of target line elements.

[0058] Specifically, step S23 above may include:

[0059] S231, obtain the endpoint positions of the target line primitives and obtain multiple candidate support points.

[0060] After identifying the target line primitive, the electronic device can calculate the endpoint coordinates of the multiple line segments corresponding to the target line primitive using geometric coordinates based on the information of the multiple line segments corresponding to the target line primitive. In other words, it can obtain the multiple endpoint positions corresponding to the target line primitive and use these multiple endpoint positions as candidate support points.

[0061] S232, determine whether the candidate support point is the end point of the beam chain.

[0062] After identifying the beam chain, the electronic device can calculate the coordinates of all endpoints of the beam chain using geometric coordinates. The coordinates of candidate support points are then compared with the endpoint coordinates of the beam chain to determine whether a candidate support point is an endpoint of the beam chain. If a candidate support point is not an endpoint of the beam chain, step S233 is executed; otherwise, step S235 is executed.

[0063] S233, extract the attribute information corresponding to each candidate support point, and calculate the feature value of each candidate support point.

[0064] The eigenvalue represents the feature score of a candidate support point that can be used as a support point of the beam span. This eigenvalue can be determined based on the weights of multiple attribute features. The weight ratio of each attribute feature can be determined based on empirical values ​​and is not limited here.

[0065] When the candidate support point is not the end point of the beam chain, the electronic device can extract the attribute information corresponding to each candidate support point to analyze the candidate support point and calculate the characteristic value used to characterize it as a support point of the beam span.

[0066] Specifically, step S233 above may include:

[0067] (1) Extract the force information of the beam chain intersecting with the candidate support point and determine the force equilibrium characteristic value of the candidate support point.

[0068] The electronic device can extract the force information of the beam chain intersecting with each candidate support point according to the principles of mechanics, calculate the force value of the beam chain, and use the force value of the beam chain intersecting with each candidate support point as the force equilibrium characteristic value of the candidate support point.

[0069] (2) Extract the geometric information of the beam chain that intersects with the candidate support point, and determine the geometric characteristic value of the candidate support point.

[0070] When extracting beam chains that intersect with candidate support points, electronic devices can calculate geometric information such as the parallel pair relationship, intersection pair relationship, and length relationship between the candidate support point and its intersecting beam chains, and use this geometric information as geometric feature values.

[0071] (3) Extract the beam span identification information corresponding to the candidate support points and determine the identification feature value of the candidate support points.

[0072] When extracting candidate support points, the electronic device can identify whether the candidate support point corresponds to a beam span. If the candidate support point corresponds to a beam span, its identification feature value is determined as A; if the candidate support point does not have a corresponding beam span, its identification feature value is determined as B. Here, A can be 1 and B can be 0. The values ​​of A and B are not specifically limited here and can be set by those skilled in the art according to actual needs.

[0073] For example, a target vector drawing is represented by image information. When an electronic device identifies beam spans in the target vector drawing using a neural network model, it is essentially performing beam span target detection on the image information. The beam span identification information is the image feature information. Beam span identification information can be extracted after the image information is identified using a neural network and the identification result is encoded according to business rules. Specifically, after obtaining the beam span identification result, the result can be encoded, and the image feature information can be extracted. For example, the coordinates of identified beam spans can be set to 1, and the coordinates of unidentified beam spans can be set to 0.

[0074] (4) Calculate the feature values ​​of candidate support points based on the force equilibrium feature value, geometric feature value and the preset weight ratio corresponding to the identification feature value.

[0075] The calculated force equilibrium feature values, geometric feature values, and identification feature values ​​are input into a preset decision tree model. The decision tree model then calculates a decision score based on the preset weight ratios corresponding to these feature values, and uses this decision score as the feature value for candidate support points. The decision tree model is trained using a decision tree algorithm, and the preset weight ratios corresponding to the force equilibrium feature values, geometric feature values, and identification feature values ​​are set by technical personnel based on experience.

[0076] By combining the stress equilibrium characteristic values, geometric characteristic values, and beam span identification characteristic values ​​of the candidate support points, the final characteristic values ​​of the candidate support points are determined. Multi-dimensional feature extraction of the candidate support points ensures that the characteristic values ​​accurately represent the candidate support points, facilitating subsequent selection of candidate support points to determine the beam span support points.

[0077] S234. Based on the eigenvalues, candidate support points are screened to obtain the beam span support points.

[0078] The electronic device sorts the calculated feature values ​​using machine learning algorithms and filters out candidate support points with higher feature values. For example, using a percentage system, the electronic device can filter out candidate support points with feature values ​​greater than 95 points and use them as beam span support points.

[0079] S235, the candidate support point is determined as the beam span support point.

[0080] Since the endpoint of the beam chain is one of the support points of the beam span, when the candidate support point is the endpoint of the beam chain, the electronic equipment can directly determine the candidate support point as the support point of the beam span.

[0081] S24, the beam chain is cut based on the support points of the beam span to obtain the target beam span primitive in the vector drawing.

[0082] Specifically, step S24 above may include:

[0083] S241, based on the geometric position of the beam span support point on the beam chain, cuts the beam chain into multiple beam span elements.

[0084] The geometric position of the beam span support point on the beam chain is the intersection point between the beam span support point and the beam chain. When the electronic device obtains the beam span support point, it can obtain its geometric position. Furthermore, the electronic device can cut the beam chain according to the intersection point between the beam chain and the beam span support point, and cut out multiple beam span elements from the beam chain.

[0085] S242, obtain the span attributes corresponding to multiple beam span elements.

[0086] Span attributes are used to characterize the features of beam span primitives, such as continuity, width, and other geometric features. A beam span primitive is a primitive composed of multiple parallel line segments. Electronic devices can traverse each beam span primitive and sequentially detect the span attributes corresponding to each beam span primitive.

[0087] S243, the target beam span element is determined from multiple beam span elements based on the cross attribute.

[0088] Based on the span attribute of the beam span element, determine whether the current beam span element is a valid element. If it is a valid element, then determine it as the target beam span element.

[0089] Specifically, when the span attribute includes line segment primitives, span-to-height ratio, and beam span width, step S243 above may include:

[0090] (1) Determine whether the line segment element corresponding to the beam span element is continuous, whether the beam span width of the beam span element changes, and whether the span-to-height ratio of the beam span element exceeds the preset ratio.

[0091] The electronic device detects whether the line segments corresponding to the cut beam span elements are the same line segment or multiple line segments connected end to end and in the same direction; it also detects whether the beam span width has changed, where the beam span width is the width of the parallel area enclosed by the line segments corresponding to the beam span elements; at the same time, it identifies the height corresponding to the beam span elements, calculates the span-to-height ratio between the beam span width and height, and determines whether the span-to-height ratio exceeds a preset ratio. This preset ratio can be set to 18, but it can also be set to other values ​​according to actual design requirements, which are not specifically limited here.

[0092] When the line segment element corresponding to the beam span element is continuous, the beam span width of the beam span element does not change, and the span-to-height ratio of the beam span element does not exceed the preset ratio, step (2) is executed; otherwise, step (3) is executed.

[0093] (2) Determine that the beam span element is a valid beam span element, and determine the valid beam span element as the target beam span element.

[0094] When the line segment elements corresponding to the beam span element are continuous, the beam span width of the beam span element does not change, and the span-to-height ratio of the beam span element does not exceed the preset ratio, it indicates that the beam span element is the span of a normal beam. Figure 5 As shown. At this point, the electronic device can determine that the beam span element is a valid beam span element and identify it as the target beam span element.

[0095] (3) Determine that the beam span element is the beam span element added in the middle, and determine the beam span element added in the middle as the target beam span element.

[0096] When the line segment element corresponding to the beam span element is discontinuous, the beam span width of the beam span element changes, and the span-to-height ratio of the beam span element exceeds the preset ratio (it should be noted that for normal beams, the span-to-height ratio exceeds 18, and for flat beams, the span-to-height ratio exceeds 22), it indicates that the beam span element is a beam span element added in the middle. Figure 5 As shown. The beam span element added in the middle is also a valid beam span element, and the electronic device can then identify the beam span element added in the middle as the target beam span element.

[0097] Optionally, the span attribute also includes beam span stiffness, and step S243 above may also include:

[0098] (4) Determine whether the beam span stiffness corresponding to the beam span element exceeds the preset value.

[0099] The preset value is the support beam stiffness. The electronic device can compare the beam span stiffness corresponding to the beam span element with the preset value to determine whether the beam span stiffness corresponding to the beam span element exceeds the preset value. When the beam span stiffness exceeds the preset value, step (5) is executed; otherwise, steps (1) to (3) are continued.

[0100] (5) If the identification of the beam span element is found to be incorrect, the beam span element is identified as an invalid beam span element.

[0101] When the beam span stiffness exceeds a preset value, and the stiffness of the combined beam spans is greater than the stiffness of the original support beam, it indicates an end-point error in the beam span element, meaning there is an end-point error in the beam span element identification. Figure 5 As shown. At this point, the electronic device identifies the beam span element as an invalid beam span element and re-identifies the beam span support points to re-identify the beam span element.

[0102] By detecting multiple beam span elements across attributes, the structural information of the beam span elements can be more directly reflected, thereby greatly improving the recognition accuracy of beam span elements.

[0103] Each beam span element in the target vector drawing has corresponding in-situ annotation information, and the in-situ annotation information corresponds to the beam span element, such as... Figure 4 Optionally, step S24 may include:

[0104] S244: Based on the geometric position of the beam span support points on the beam chain, the beam chain is cut into multiple beam span elements. For detailed explanations, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0105] S245, obtain the span attributes corresponding to multiple beam span elements. For detailed explanations, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0106] S246 identifies the in-situ annotation information corresponding to beam span elements.

[0107] The in-situ annotation information is the special design value corresponding to the beam span element. Electronic equipment can search and identify all in-situ annotation information within the range of each beam span element.

[0108] S247, calculate the span characteristics of beam span elements based on in-situ annotation information.

[0109] Electronic equipment can further calculate geometric features such as the parallelism, intersection, length, and width of beam spans based on in-situ annotation information. It can also extract in-situ annotations, calculate structural features such as stirrups, secondary beam reinforcement, and cantilever information, and determine whether beam span elements contain angles, using the threshold range of the angle's location to identify any recognition errors.

[0110] S248, the target beam span element is determined from multiple beam span elements based on cross attributes and cross features.

[0111] Electronic devices can combine span attributes and span features to perform validity detection on multiple beam span elements, in order to determine whether the beam span element is a normal beam span, a beam span added in the middle, an invalid beam span with incorrect endpoint identification, or an invalid beam span added in the middle and with incorrect endpoint identification, and then determine the target beam span element from the multiple beam span elements.

[0112] By identifying the in-situ annotation information corresponding to beam span elements and calculating the span features of the beam span elements based on this in-situ annotation information, the computational complexity of the features is reduced to some extent, and the recognition efficiency is improved. Combining the span features and span attributes to determine the recognition results of beam span elements reduces the recognition error rate and improves the recognition effect.

[0113] The beam span identification method for vector graphics provided in this embodiment determines whether a candidate support point is a beam span support point by using its attribute information, ensuring the accuracy of beam span support point identification and minimizing misidentification. When a candidate support point is an endpoint of a beam chain, it is directly identified as a beam span support point, thus avoiding endpoint feature extraction, saving feature extraction time, and improving the identification efficiency of beam span support points, thereby improving the identification efficiency of beam span elements. The beam chain is cut according to the geometric position of the beam span support points on the beam chain to obtain multiple beam span elements, and the span attribute corresponding to each beam span element is extracted. The span attribute is used to determine the accuracy of beam span element identification, further improving the identification effect.

[0114] This embodiment provides a method for beam span identification from vector graphics, which can be used in electronic devices such as mobile phones, tablets, and computers. Figure 3 This is a flowchart of a beam span identification method using vector graphics according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps:

[0115] S31, Obtain the target vector drawing to be identified, and detect the beam span area in the target vector drawing.

[0116] Specifically, step S31 above may include:

[0117] S311, retrieve the attribute information of the primitives in the original vector paper.

[0118] The element attribute information refers to the attributes used to represent the corresponding elements in the original vector graphic. Specifically, this element attribute information may include dimension annotations, line elements, text elements, and filled elements. The original vector graphic is the vector graphic directly obtained by the electronic device, that is, the vector graphic obtained from storage space, the vector graphic uploaded by the designer, or the vector graphic created by the designer.

[0119] S312, Based on the primitive attribute information, filter the interfering primitives in the target vector paper to obtain the target vector paper.

[0120] In order to more accurately identify beam span elements in vector graphics, electronic devices can filter out interfering elements in the original vector graphics to obtain the target vector graphics. These interfering elements mainly include dimension annotations, text numbers, and grid lines within the vector graphics.

[0121] Specifically, electronic devices can precisely filter dimensions, text numbers, and other elements based on the structured information in the original vector drawings. This means that by using element attribute information, they can efficiently and accurately filter out interfering elements that affect beam span element recognition. Simultaneously, electronic devices can also filter interfering elements in the original vector drawings based on general rules of architectural engineering design. For example, by traversing the elements in the original vector drawings and extracting geometric relationship attributes through geometric operations, such as the number of parallel line segments, the number of perpendicular line segments, average length, and line segment type (solid line, dashed line), they can perform clustering and geometric configuration analysis to filter out interfering elements with specific drawing rules for grid types.

[0122] It should be noted that if there are no interfering elements in the original vector drawing, the electronic device can directly use the original vector drawing it acquires as the target vector drawing for beam span element identification.

[0123] By obtaining the element attribute information from the original vector drawing, the interfering elements in the target vector drawing can be filtered efficiently and accurately based on this element attribute information, thereby obtaining the target vector drawing. This avoids the interference of interfering elements on the identification of beam span elements, making it easier to accurately identify beam span elements in the future.

[0124] S313 converts the target vector drawing into a matrix representation and identifies the area where the beam span is located from the matrix representation.

[0125] The original vector coordinate system of the target vector paper after filtering out interference primitives is converted into a matrix coordinate system. This matrix coordinate system is used to characterize the geometric structure of the beam span. Then, the matrix representation corresponding to the target vector paper is determined through the transformed matrix coordinate system.

[0126] Here, two conversion methods are taken as examples for illustration:

[0127] 1) Convert the target vector drawing into a bitmap primitive matrix. Generate an image matrix with all values being 0 according to the specified resolution, calculate the coordinate range of each line primitive and text primitive in the image matrix according to the resolution, and modify the corresponding values in the matrix to the RGB values in the primitive attributes, so as to obtain the bitmap primitive matrix corresponding to the target vector drawing.

[0128] 2) Generate a feature matrix corresponding to the target vector drawing. Cut the target vector drawing into blocks according to a fixed ratio, calculate the geometric features and text features of each block, and generate the corresponding feature matrix. For example, set the dimension of the generated matrix to 10*10, generate a feature matrix with all values being 0; calculate the area of each coordinate in the target vector drawing in the feature matrix, such as 100 < x < 200, 100 < y < 200; calculate the number of parallel lines, intersection lines, length of all line primitives and the number of texts containing keywords in this area, and use them as features, that is, update them as the values in the matrix to obtain the updated feature matrix.

[0129] Certainly, there may be other conversion methods, which are not specifically limited here, and those skilled in the art can determine according to actual needs.

[0130] When the electronic device obtains the matrix representation corresponding to the target vector drawing, it can input the matrix representation into a preset neural network model for component object detection, and determine the coordinate range where the beam span is located from the matrix representation, that is, represent the area where the beam span is located by the coordinate range. Among them, the neural network model is an open-source model such as YOLO, RetinaNet, Faster R-CNN, etc., and can also be a self-developed neural network model, which is not specifically limited here, as long as it can identify the beam span object, support object, etc. corresponding to the beam component from the matrix representation.

[0131] S314, map the area where the beam span is located to the target vector drawing to obtain the beam span area in the target vector drawing.

[0132] The recognition of the area where the beam span is located is completed in the matrix coordinate system after data conversion, which is different from the original vector coordinate system where the target vector drawing is located. The electronic device can map the area where the beam span is located recognized by it from the current matrix coordinate system to the original vector coordinate system where the target vector drawing is located, and match the primitives in the target vector drawing with the area where the beam span is located to determine the beam span area corresponding to the target vector drawing.

[0133] S32, recognize the line primitives in the beam span area to determine the target line primitive of the beam chain where the beam span is located. For the detailed description, please refer to the relevant description of the corresponding steps in the above embodiments, which will not be elaborated here.

[0134] S33, Based on the positional information of the target line elements, identify the beam span support points. For detailed explanations, please refer to the relevant descriptions of the corresponding steps in the above embodiments; they will not be repeated here.

[0135] S34, the beam chain is cut based on the beam span support points to obtain the target beam span primitive in the vector drawing. For detailed explanations, please refer to the relevant descriptions of the corresponding steps in the above embodiments; they will not be repeated here.

[0136] S35, obtain the beam type corresponding to the target beam span element.

[0137] After acquiring the target beam element, the electronic device can identify the beam type it occupies to determine the corresponding beam type. Specifically, the beam type can include single cantilever beams, double cantilever beams, and non-cantilever beams. The electronic device can determine the beam type corresponding to the target beam element based on the component characteristics of different beams.

[0138] S36, check if there is a drawing deviation in the drawing of the target beam span element.

[0139] Since different designers may have different drawing methods, for target vector drawings with non-standard drawings, electronic devices can correct the drawing deviations to avoid the impact of drawing deviations on element recognition and quantity calculation. Specifically, when identifying the target beam span element in the target vector drawing, the electronic device can detect whether there are drawing deviations, such as insufficient length of line elements or non-compliant connection of adjacent element supports. When there is a drawing deviation in the drawing of the target beam span element, step S37 is executed; otherwise, it means that the drawing of the target beam span element is compliant, and step S38 can continue.

[0140] S37, based on the beam type, the target beam span primitive is extended. This extension process is used to correct drawing deviations.

[0141] When there is a drawing deviation in the target beam span element, the electronic device can extend the target beam span element according to the beam type of the beam in which the target beam span element is located to correct the drawing deviation. Specifically, the extension rules corresponding to the extension processing can be defined according to the adjacent objects: if adjacent to a shear wall in the same direction, the target beam span element is extended to the wall edge; if adjacent to a shear wall in a different direction, the target beam span element is extended to the shear wall centerline; if adjacent to a column, if it is a rectangular column, the target beam span element is extended to the column centerline, and if it is a non-rectangular column, the target beam span element is extended to the center point of the first column direction change; if adjacent to a beam in a different direction, the target beam span element is extended to the beam centerline.

[0142] By extending the target beam span elements with drawing deviations to correct these deviations, the limitations of the designer's drawing methods are eliminated, thus improving the generalizability of the application.

[0143] S38, perform attribute verification on the target beam span element to determine whether the target beam span element has been incorrectly identified.

[0144] The attribute information of the target beam span element is used to characterize the beam span information in the target vector drawing. Specifically, the attribute information of the target beam span element may include the number of beam spans, beam span cantilever, beam stress, and the continuity of the beam span at the mid-section. After identifying the target beam span element, the electronic device can obtain the attribute information of the target beam span element from the target vector drawing.

[0145] The electronic device can perform checks on the target beam span elements in the target vector drawing, including beam span quantity verification, beam span cantilever verification, beam stress verification, and beam span continuity verification at mid-sections. For example, it compares the number of beam spans contained in the target vector drawing with the number of identified beam spans; it calculates the stress on the reinforcing steel information of the identified beam span elements to determine if there are any identification errors in the target beam span elements. If there are identification errors in the target beam span elements, step S39 is executed; otherwise, it indicates that the target beam span elements are accurately identified.

[0146] S39, Re-identify the support points of the beam span.

[0147] When there is an identification error in the target beam span element, it means that the identification of the target beam span element contains incorrect information. At this time, the electronic device can re-identify the beam span support points in the target vector drawing to redetermine the beam span element and automatically correct the incorrect beam span element.

[0148] After the automatic identification of beam span elements is completed, the attributes of the target beam span elements are checked to determine whether there are any identification errors. If there are identification errors, the beam span support points in the target vector drawing need to be re-identified to ensure the accuracy of beam span element identification.

[0149] S310, in response to the identification operation of beam span elements, identifies and corrects beam span elements in the target vector drawing based on the identification operation.

[0150] During the identification process, technicians can delineate the target graphic element area from the target vector drawing according to their needs. Correspondingly, the electronic equipment can respond to the technician's identification operation on the beam span graphic element and identify the target beam span graphic element in the graphic element area delineated by the identification operation, thereby reducing the influence of interfering graphic elements and improving the identification efficiency of beam span graphic elements.

[0151] During the identification process, the electronic device can display the identification boxes for beam span elements. Technicians can use these displayed boxes to determine if there are any erroneous or missing boxes. If an erroneous or missing box is found, the technician can send an identification command to the electronic device to delete the erroneous box or add the missing one. Correspondingly, the electronic device can respond to the technician's operation by deleting erroneous boxes or adding missing ones to ensure the accuracy of beam span element identification.

[0152] After the beam span elements are identified, the electronic device can display the identification results. Technicians can review these results to determine if there are any errors. If errors are found, technicians can send identification commands to the electronic device to correct the erroneous results. Correspondingly, the electronic device can respond to the technician's identification operation and correct the incorrectly identified beam span elements to ensure the accuracy of beam span element identification.

[0153] The beam span identification method for vector graphics provided in this embodiment efficiently and accurately filters interfering elements in the target vector graphics paper using element attribute information, thereby obtaining the target vector graphics paper. This avoids interference from interfering elements in the identification of beam span elements, ensuring accurate identification of beam span elements in subsequent steps. By converting the target vector graphics paper into a matrix representation, identifying the region where the beam span is located from the matrix representation, and then mapping the region where the beam span is located back to the target vector graphics paper, the beam span region in the target vector graphics paper is obtained. This eliminates the need to design different feature matrices based on different business requirements; it only requires converting the target vector graphics paper into a matrix that can represent the structural information of the beam span. This minimizes the limitations of business scenarios and improves its generalization and applicability. The method can also respond to the identification operations of technicians on beam span elements by selecting the identification region of the beam span elements to improve identification efficiency and correcting identification errors, further improving the identification accuracy of beam span elements.

[0154] This embodiment also provides a beam span recognition device for vector graphics, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0155] This embodiment provides a beam span recognition device for vector graphics, such as... Figure 6 As shown, it includes:

[0156] The acquisition module 41 is used to acquire the target vector drawing to be identified and detect the beam span region in the target vector drawing. For detailed explanations, please refer to the relevant descriptions in the above method embodiments; they will not be repeated here.

[0157] The first identification module 42 is used to identify line elements in the beam span region and determine the target line elements of the beam chain where the beam span is located. For detailed explanations, please refer to the relevant descriptions in the above method embodiments; they will not be repeated here.

[0158] The second identification module 43 is used to identify the beam span support points based on the position information of the target line primitives. For detailed explanations, please refer to the relevant descriptions in the above method embodiments; they will not be repeated here.

[0159] The cutting module 44 is used to cut the beam chain based on the beam span support points to obtain the target beam span primitive in the vector drawing. For detailed explanations, please refer to the relevant descriptions in the above method embodiments; they will not be repeated here.

[0160] The beam span recognition device for vector graphics provided in this embodiment detects beam span regions in the target vector graphics, then identifies beam chains and beam span support points within these regions. By cutting the beam chains according to the beam span support points, multiple target beam span elements are obtained, thereby achieving automatic recognition of beam span elements in the target vector graphics. This device avoids extensive feature extraction work, is not limited by the experience of technical personnel, and achieves high-precision recognition of beam span elements by extracting beam span support points and beam chains, solving the problem of inaccurate beam span element recognition.

[0161] In this embodiment, the beam span recognition device of the vector drawing is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0162] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0163] This invention also provides an electronic device having the above-described features. Figure 6 The vector graphic shown shows the beam span recognition device.

[0164] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 7As shown, the electronic device may include: at least one processor 501, such as a CPU (Central Processing Unit), at least one communication interface 503, memory 504, and at least one communication bus 502. The communication bus 502 is used to enable communication between these components. The communication interface 503 may include a display screen or a keyboard; optionally, the communication interface 503 may also include a standard wired interface or a wireless interface. The memory 504 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 504 may also be at least one storage device located remotely from the aforementioned processor 501. The processor 501 may be combined with... Figure 6 The described apparatus has an application program stored in memory 504, and a processor 501 calls the program code stored in memory 504 to perform any of the above method steps.

[0165] The communication bus 502 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 502 can be divided into an address bus, a data bus, and a control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0166] The memory 504 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 504 may also include a combination of the above types of memory.

[0167] The processor 501 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0168] The processor 501 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0169] Optionally, memory 504 is also used to store program instructions. Processor 501 can call the program instructions to implement the functions described in this application. Figures 1 to 4 The beam span identification method of the vector drawing shown in the embodiment.

[0170] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the beam span recognition method for vector drawings in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0171] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method of identifying a beam span of a vector drawing sheet, characterized by, include: Obtain the target vector map to be identified, and detect the beam span region in the target vector map; Identify the line elements in the beam span region and determine the target line elements of the beam chain where the beam span is located; Based on the positional information of the target line element, the beam span support points are identified, including: obtaining the endpoint positions of the target line element to obtain multiple candidate support points; determining whether the candidate support points are endpoints of the beam chain; when the candidate support points are not endpoints of the beam chain, extracting the attribute information corresponding to each candidate support point and calculating the feature value of each candidate support point; filtering the candidate support points based on the feature values ​​to obtain the beam span support points. The beam chain is cut based on the beam span support points to obtain the target beam span primitive in the vector drawing.

2. The method of claim 1, wherein, The step of extracting the attribute information corresponding to each of the candidate support points and calculating the feature values ​​of each of the candidate support points includes: Extract the force information of the beam chain intersecting with the candidate support point, and determine the force equilibrium characteristic value of the candidate support point; Extract the geometric information of the beam chain intersecting with the candidate support point, and determine the geometric feature value of the candidate support point; Extract the beam span identification information corresponding to the candidate support points, and determine the identification feature values ​​of the candidate support points; Based on the force equilibrium feature value, the geometric feature value, and the preset weight ratio corresponding to the identification feature value, the feature value of the candidate support point is calculated.

3. The method of claim 1, wherein, Also includes: When the candidate support point is the end point of the beam chain, the candidate support point is determined as the beam span support point.

4. The method of claim 1, wherein, The step of cutting the beam chain based on the beam span support points to obtain the target beam span primitive in the vector drawing includes: Based on the geometric position of the beam span support point on the beam chain, the beam chain is cut into multiple beam span elements; Obtain the span attribute corresponding to the multiple beam span elements; The target beam span element is determined from the plurality of beam span elements based on the span attribute.

5. The method according to claim 4, characterized in that, The span attribute includes line segment primitives, span-to-depth ratio, and beam span width. Determining the target beam span primitive from the plurality of beam span primitives based on the span attribute includes: Determine whether the line segment element corresponding to the beam span element is continuous, whether the beam span width of the beam span element changes, and whether the span-to-height ratio of the beam span element exceeds a preset ratio; When the line segment elements corresponding to the beam span element are continuous, the beam span width of the beam span element does not change, and the span-to-height ratio of the beam span element does not exceed the preset ratio, the beam span element is determined to be a valid beam span element, and the valid beam span element is determined as the target beam span element.

6. The method according to claim 5, characterized in that, The step of determining the target beam span element from the plurality of beam span elements based on the span attribute further includes: When the line segment element corresponding to the beam span element is discontinuous, the beam span width of the beam span element changes, and the span-to-height ratio of the beam span element exceeds the preset ratio, the beam span element is determined to be a beam span element added in the middle, and the beam span element added in the middle is identified as the target beam span element.

7. The method according to claim 5, characterized in that, The span attribute also includes beam span stiffness; the step of determining the target beam span element from the plurality of beam span elements based on the span attribute further includes: Determine whether the beam span stiffness corresponding to the beam span element exceeds a preset value; When the beam span stiffness exceeds a preset value, it is determined that there is an end error in the identification of the beam span element, and the beam span element is identified as an invalid beam span element.

8. The method according to any one of claims 4-7, characterized in that, Also includes: Identify the in-situ annotation information corresponding to the beam span element; The span characteristics of the beam span element are calculated based on the in-situ annotation information.

9. The method according to claim 1, characterized in that, The process of acquiring the target vector drawing to be identified and detecting the beam span region in the target vector drawing includes: Obtain the attribute information of primitives in the original vector graphics paper; Based on the attribute information of the graphic elements, the interfering graphic elements in the target vector paper are filtered to obtain the target vector paper; The target vector drawing is converted into a matrix representation, and the region where the beam span is located is identified from the matrix representation; The area where the beam span is located is mapped onto the target vector map to obtain the beam span area in the target vector map.

10. The method according to claim 1, characterized in that, Also includes: Obtain the beam type corresponding to the target beam span element; Detect whether there is a drawing deviation in the drawing of the target beam span element; When there is a drawing deviation in the drawing of the target beam span element, the target beam span element is extended based on the beam type, and the extension process is used to correct the drawing deviation.

11. The method according to claim 1, characterized in that, Also includes: Perform attribute verification on the target beam span element to determine whether the target beam span element has been incorrectly identified; If the target beam span element is incorrectly identified, the beam span support point is re-identified.

12. A beam span recognition device for vector graphics, characterized in that, include: The acquisition module is used to acquire the target vector drawing to be identified and to detect the beam span area in the target vector drawing; The first identification module is used to identify line elements in the beam span area and determine the target line elements of the beam chain where the beam span is located. The second identification module is used to identify beam span support points based on the position information of the target line element, including: obtaining the endpoint positions of the target line element to obtain multiple candidate support points; determining whether the candidate support points are endpoints of the beam chain; when the candidate support points are not endpoints of the beam chain, extracting the attribute information corresponding to each candidate support point and calculating the feature value of each candidate support point; filtering the candidate support points based on the feature values ​​to obtain the beam span support points. The cutting module is used to cut the beam chain based on the beam span support points to obtain the target beam span primitive in the vector drawing.

13. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the beam span recognition method of vector paper according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the beam span recognition method of the vector drawing according to any one of claims 1-11.

Images