CN116150849A - Structural member feature map generation method and device, electronic equipment and storage medium - Google Patents
Structural member feature map generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116150849A CN116150849A CN202310139974.7A CN202310139974A CN116150849A CN 116150849 A CN116150849 A CN 116150849A CN 202310139974 A CN202310139974 A CN 202310139974A CN 116150849 A CN116150849 A CN 116150849A
- Authority
- CN
- China
- Prior art keywords
- structural member
- information
- column
- structural
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000010586 diagram Methods 0.000 claims abstract description 77
- 238000013461 design Methods 0.000 claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 238000000605 extraction Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Architecture (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a structural member feature map generation method, a device, an electronic device and a storage medium, comprising the following steps: removing redundant information except structural information required by intelligent design from the obtained structural member feature vector diagram, extracting structural member information of each structural member, and converting the structural member information into image expression information; the structural information required by intelligent design at least comprises a concrete strength value, a beam height, a beam span-height ratio and the like, and is used for improving the machine learning efficiency; according to the concrete strength value of each structural member, determining the gray value of each structural member; and processing the structural member characteristic vector diagram according to the image expression information, the gray value and the preset pixel conversion proportion of each structural member to obtain the structural member characteristic pixel diagram. The invention converts the structural member information expressed by characters in the structural member feature map into image expression, strengthens the structural member information feature of the image, and effectively improves the training efficiency and quality of the intelligent design of the frame structure.
Description
Technical Field
The invention relates to the technical field of building structure design and computers, in particular to a method and a device for generating a feature map of a structural member, electronic equipment and a storage medium.
Background
In the process of building engineering design, each professional cooperation is usually required, a building designer provides a building plan with building functional components through building design, and the structural designer needs to arrange structural stress components according to own experience on the basis of the building drawing to form a structural component layout. With the wide application of artificial intelligence algorithms, image features in building plan are extracted for image deep learning, intelligent design of structural member layout can be realized, and design efficiency is improved, wherein the accuracy of image feature expression influences learning efficiency and quality.
For the design of the frame structure intelligent scheme, on the basis of extracting the building plan features, the image features in the structural member layout are overlapped, so that the image learning effect is effectively improved. However, the expression of the structural information in the conventional structural member layout is limited for image learning, for example, concrete strength information, three-dimensional size information and other information which is difficult to express through images are expressed by characters, are difficult to directly extract from the images, and cannot meet the requirements of a related image deep learning algorithm on image feature extraction.
Disclosure of Invention
One of the purposes of the present invention is to provide a method, a device, an electronic device and a storage medium for generating a feature map of a structural member, which are used for converting text information in the feature map of the structural member into image expression, expanding the feature of the information of the structural member of the image, and meeting the requirement of image deep learning on an image dataset, and the technical scheme of the present invention can be realized as follows:
in a first aspect, an embodiment of the present invention provides a structural member feature map generating method, including: acquiring a feature vector diagram of a structural member; removing redundant information except structural information required by intelligent design from the structural member feature vector diagram, and extracting structural member information of each structural member; the structure information required by the intelligent design at least comprises the structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency; the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio; determining a gray value for each of the structural members based on the concrete strength value for each of the structural members; and processing the structural member characteristic vector image according to the structural member information of each structural member, the gray value and the preset pixel conversion proportion to obtain a structural member characteristic pixel image.
In a second aspect, the present invention provides a structural member feature map generating apparatus including: the acquisition module is used for acquiring the feature vector diagram of the structural member; the extraction module is used for removing redundant information except the structural information required by intelligent design from the structural member feature vector diagram and extracting structural member information of each structural member; the structure information required by the intelligent design at least comprises the structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency; the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio; a determining module for determining a gray value of each of the structural members according to the concrete strength value of each of the structural members; and the conversion module is used for processing the structural member characteristic vector diagram according to the structural member information of each structural member, the gray value and the preset pixel conversion proportion to obtain a structural member characteristic pixel diagram.
In a third aspect, the invention provides an electronic device comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being executable to implement the method of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect.
The invention provides a structural member feature map generation method, a device, electronic equipment and a storage medium, wherein the method mainly comprises the following steps: in the obtained structural member feature vector diagram, redundant information except structural information required by intelligent design can be removed, structural member information of each structural member is extracted, gray values of each structural member can be determined for the structural member information such as concrete strength values, then the structural member feature vector diagram is converted into a structural member feature pixel diagram based on the determined gray values of each structural member, the structural member information and a preset pixel conversion proportion, and therefore, the converted feature pixel diagram contains image features of the structural member information of each structural member, the effect of converting text information in the structural member feature diagram into image expression is achieved, the structural member information features of images can be improved, and the requirements of image deep learning on an image dataset are met. In addition, the embodiment of the invention also removes redundant information which is not used for the structural information required by intelligent design in machine learning, reduces invalid information and interference factors in the machine learning, and thus improves the efficiency of the machine learning: part of the structural member information is specified in a text or other mode, and for the process of machine learning by adopting a raster image, the non-graphical information content of a normal structural diagram is required to be converted into graphical expression by the method so as to be read and used by a machine learning model.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for generating a feature map of a structural member provided by an embodiment of the present invention;
FIG. 2 is a beam-column layout diagram provided by an embodiment of the present invention;
FIG. 3 is a diagram showing an example of structural member information of a column according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an example of structural member information of a beam provided by an embodiment of the present invention;
FIG. 5 is a diagram of an exemplary calculation of the beam aspect ratio provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of a mapping relationship between a concrete strength value and a gray value according to an embodiment of the present invention;
fig. 7 is a schematic flowchart of step S104 provided in an embodiment of the present invention;
FIG. 8 is an exemplary diagram of a feature pixel map of a structural member provided by an embodiment of the present invention;
FIG. 9 is a functional block diagram of a feature map generating device for a structural member according to an embodiment of the present invention;
fig. 10 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, if the terms "upper", "lower", "inner", "outer", and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or the azimuth or the positional relationship in which the inventive product is conventionally put in use, it is merely for convenience of describing the present invention and simplifying the description, and it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be configured and operated in a specific azimuth, and thus it should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, if any, are used merely for distinguishing between descriptions and not for indicating or implying a relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
From the view of image expression, the embodiment of the invention provides a structural member feature diagram generation method for intelligent design of a frame structure, which establishes an image expression rule for expressing structural member information in a text form in the conventional structural member layout, expands the expression capability of the structural member layout for the structural member information, and improves the learning efficiency and quality of related algorithms of intelligent scheme design of the frame structure.
Referring to fig. 1, fig. 1 is a schematic flowchart of a method for generating a feature map of a structural member according to an embodiment of the present invention, where the method may include the following steps:
s101, acquiring a feature vector diagram of the structural member.
S102, removing redundant information except structural information required by intelligent design from the structural member feature vector diagram, extracting structural member information of each structural member, and converting the structural member information into image expression information;
the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio; the structure information required by the intelligent design at least comprises structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency;
s103, determining gray values of the structural members according to the concrete strength values of the structural members;
s104, processing the feature vector diagram of the structural member according to the image expression information, the gray value and the preset pixel conversion proportion of each structural member to obtain the feature pixel diagram of the structural member.
In the method for generating the structural member feature map, redundant information except structural information required by intelligent design can be removed from the obtained structural member feature vector map, structural member information of each structural member is extracted, gray values of each structural member can be determined for the structural member information such as concrete strength values, and then the structural member feature vector map is converted into the structural member feature pixel map based on the determined gray values of each structural member, the structural member information and a preset pixel conversion ratio, so that the converted feature pixel map contains image features of the structural member information of each structural member, the effect of converting text information in the structural member feature map into image expression is realized, the structural member information features of images can be improved, and the requirements of image deep learning on an image dataset are met. In addition, the embodiment of the invention also removes a lot of information which is not used for redundant information in machine learning, reduces invalid information and interference factors in the machine learning, and thus improves the efficiency of the machine learning: part of the structural member information is specified in a text or other mode, and for the process of machine learning by adopting a raster image, the non-graphical information content of a normal structural diagram is required to be converted into graphical expression by the method so as to be read and used by a machine learning model.
In an optional implementation manner, the structural member feature pixel map in the embodiment of the invention can be used for image deep learning, namely, the image features extracted from the building plane gray level map are overlapped with the image features extracted from the structural member feature pixel map obtained in the embodiment of the invention, so that the image learning effect is effectively improved.
In another alternative embodiment, after the structural member feature pixel map is obtained, the influence of the anti-seismic fortification intensity on the structural member feature pixel map may be further processed in a span scaling manner, the processed structural member feature pixel map may be used for image deep learning, specifically, an equivalent span factor may be determined according to the anti-seismic fortification intensity and a feature period corresponding to the anti-seismic fortification intensity, the equivalent span factor is used for characterizing the degree of scaling processing of the image, and then scaling processing is performed on the structural member feature pixel map based on the equivalent span factor.
The following describes the above steps S101 to S104 in detail.
In step S101, a structural member feature vector diagram is acquired.
In the embodiment of the invention, the structural member feature vector diagram may also be referred to as a structural member layout diagram, and the structural member feature vector diagram may be obtained by: the frame structure construction CAD drawing and the Revit can be directly extracted from the frame structure construction CAD drawing and the Revit or can be obtained from a locally stored structural member drawing and can be received in real time, and the frame structure construction CAD drawing and the Revit can be used for being received in real time.
As an alternative embodiment, the structural member may include, but is not limited to: beams and columns. As shown in fig. 2, fig. 2 is a beam-column layout diagram according to an embodiment of the present invention, where a beam profile and a column profile may be included.
In step S102, redundant information other than structural information required for intelligent design is removed from the structural member feature vector diagram, structural member information of each structural member is extracted, and the structural member information is converted into image expression information;
the structure information required by the intelligent design at least comprises structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency; the structural member information includes at least a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length, and a beam span height ratio.
In the embodiment of the present invention, the structural member information includes concrete strength value and size information of the structural member, and { elements: attribute }, comprising { columns: column section length, column section width, column concrete strength }, { beam: beam section width, beam section height, beam length, beam concrete strength, beam span-to-height ratio }.
The above step S102 will be described in detail with reference to beams and columns.
When the structural member is a column, then the corresponding structural member information includes: the column section length, column section width, step S102 may include the steps of:
a1, determining the section length of the column as the column edge length of the column in the horizontal direction.
a2, determining the section width of the column as the column edge length of the column in the vertical direction.
For convenience of understanding, please refer to fig. 3, fig. 3 is an exemplary diagram of structural member information of a column provided by the embodiment of the present invention, in which a dark gray rectangle represents a column, a width of the rectangle is a cross-sectional length along a horizontal direction, a length of the rectangle in a vertical direction is a cross-sectional width, wherein a gray value of the rectangle may represent a concrete strength of the column, a column edge length of the column in the horizontal direction and a column edge length of the column in the vertical direction are recorded as image expression information corresponding to the column, and by the above embodiment, the structural member information corresponding to the column is converted into a post-form: { column: the effect of converting the structural member information of the column into image expression information is achieved.
When the structural member is a beam, then the corresponding structural member information includes: the beam section length, the beam section width and the beam length and the beam span-to-height ratio, i.e. step S102 may comprise the steps of:
b1, determining the length of the beam as the length of the beam center line.
b2, determining the width of the beam section as the length of the beam edge in the direction perpendicular to the arrangement direction of the beams.
In an embodiment of the present invention, liang Bianxian may represent a beam cross-sectional width, which may be represented by Liang Bianxian for a vertically disposed beam and by Liang Bianxian for a vertically disposed beam.
And b3, determining the central position of the beam based on the length of the beam, performing expansion deformation treatment on the region where the central position is located, and determining the vertical line section of the central line in the region where the expanded central position is located as the height of the beam section.
As an alternative implementation manner, the size of the area where the central position is located is not fixed, and may be customized according to the actual scene.
And b4, determining a line segment formed by connecting the starting point of the beam center line and the end point of the beam section height as an aspect ratio positioning line based on the beam section height.
b5, determining the bridge span-to-height ratio as the slope of the span-to-height ratio bit line based on the span-to-height ratio bit line, wherein the slope of the span-to-height ratio bit line is the tangent of the included angle formed by the bridge length and the span-to-height ratio bit line.
In the embodiment of the invention, assuming that the span-to-height ratio of the beam is K, the length of the beam is L, the height of the section is H, and the included angle between the span-to-height ratio positioning line and the length of the beam is alpha, K satisfies the following relation:
for easy understanding, please refer to fig. 4 and 5, fig. 4 is an exemplary diagram of structural member information of a beam according to an embodiment of the present invention, and fig. 5 is an exemplary diagram of determining a span-to-height ratio of a beam according to an embodiment of the present invention, in which a region between two columns is a beam. As can be seen from the above embodiments, the length of the beam center line, the length of the beam edge line in the direction perpendicular to the arrangement direction of the beams, and the like are the image expression information corresponding to the structural member information of the beams, and the structural member information corresponding to the beams is converted into the following shape: { beam: the cross-section width, the cross-section height, the beam length, the gray value corresponding to the concrete strength, the beam span-to-height ratio }, wherein the effect of converting the structural member information of the beam into the image expression information is achieved.
As can be seen from fig. 3, 4 and 5, the size information of each structural member in the structural member feature vector diagram can be directly extracted from the image after the structural member information of each structural member is converted into the image expression information through the steps a1 to a2 and the steps b1 to b 4.
After the design parameters of different structural members are obtained, the expression mode of the gray values is considered to be more beneficial to computer recognition and reading, and the requirement of image deep learning on an image data set can be met, so that the embodiment of the invention replaces the concrete strength value with the gray values for different structural members, namely, the step S203 is executed.
In step S103, the gray value of each structural member is determined from the concrete strength value of each structural member.
In the embodiment of the invention, the gray value of the structural member is the image expression information of the concrete strength of the structural member, and different gray values are adopted to express the concrete strength of the structural member, and the higher the concrete strength level is, the deeper the gray value is, and the smaller the gray value is.
It will be appreciated that according to the specification of GB50010-2010 "concrete Structure design Specification", ordinary concrete is divided into fourteen classes, namely: c15 In designing CAD vector drawings, C20, C25, C30, C35, C40, C45, C50, C55, C60, C65, C70, C75 and C80, concrete strength values corresponding to various structural members have been marked in text form, and the concrete strength values are one of the fourteen grades.
Thus, in determining the gray values of the respective structural members, the embodiment of the present invention gives an embodiment that the gray values of the beams and columns can be determined as follows.
c1, if the structural member is a column, taking the difference between the first preset value and the concrete strength value corresponding to the column as a gray value of the column;
and c2, if the structural member is a beam, calculating a difference value between the first preset value and a concrete strength value corresponding to the beam, and taking the sum of the difference value and a preset threshold value as a gray value of the beam.
As an optional implementation manner, the first preset value may be set according to actual requirements, for example, the first preset value is 100, and the preset threshold is used to avoid repetition of gray values of the beam column, achieve the effect of reducing difficulty of learning the beam column profile, and may be set to 1 or other values.
For example, assuming that the first preset value is 100, the mapping relationship between the concrete strength values and the gray values of the beams and the columns obtained by the above embodiment may be shown in fig. 6, and fig. 6 is a schematic diagram of the mapping relationship between the concrete strength values and the gray values provided by the embodiment of the present invention, it can be seen that, in the case that the beams and the columns have the same concrete strength value, the beams and the columns are finally determined to have different gray values by the above embodiment, so that the gray values of the beams and the columns are prevented from being repeated, and thus, the difficulty of learning the contours of the beams and the columns can be prevented from being increased.
In another embodiment, the difference between the first preset value and the concrete strength value corresponding to the column may be used as the gray value of the beam, and the sum of the difference in step c2 and the preset threshold value may also be used as the gray value of the column.
After obtaining the design information of each structural member, in particular, the gray value corresponding to the concrete strength of the structural member, step S104 may be performed to convert the structural member feature vector map into the structural member feature pixel map.
In step S104, the structural member feature vector diagram is processed according to the image expression information, the gray value and the preset pixel conversion ratio of each structural member, so as to obtain a structural member feature pixel diagram.
In the embodiment of the invention, the pixel conversion ratio between the structural member feature vector diagram and the structural member feature vector diagram can be established according to the learning precision, and the pixel diagram obtained by converting the pixel conversion ratio is more beneficial to computer recognition and reading, and can meet the requirement of image deep learning on an image data set.
As an alternative embodiment, the above-mentioned pixel conversion ratio may implement conversion between the structural member pixel map and the structural member feature vector map, for example, the preset learning accuracy is 50mm, and then the pixel conversion ratio may be set to: 50mm = 1 pixel.
Thus, for the above step S104, an embodiment of the present invention is shown in fig. 7, referring to fig. 7, fig. 7 is a schematic flowchart of step S104 provided by the embodiment of the present invention, where step S104 may include:
s104-1, processing the feature vector diagram of the structural member according to the image expression information and the gray value of each structural member.
S104-2, converting the processed feature vector diagram of the structural member according to the pixel conversion proportion to obtain a feature pixel diagram of the structural member.
It can be understood from the above steps that a whole feature vector image of a structural member can be changed into a gray image, that is, the gray image is obtained by filling colors in the areas where each building member of the feature vector image of the structural member is located according to gray values in the processing process, after the processing of the feature vector image of the structural member is performed in step S104-1, the feature vector image of the structural member is obtained by converting the feature vector image of the structural member according to the pixel conversion ratio on the basis of the gray image, that is, the effect of converting the feature vector image of the structural member into the feature pixel image of the structural member can be achieved, and the feature pixel image of the structural member obtained by the conversion is shown in fig. 8, where fig. 8 is an exemplary view of the feature pixel image of the structural member provided by the embodiment of the invention.
As can be seen from fig. 8, according to the above embodiment, text information in the original feature map of the structural member can be converted into image representation, for example, gray values corresponding to areas where beams and columns are located are different, the structural member in the map can be determined by extracting the gray values in the map, meanwhile, design parameters of the beams and the columns can be determined by extracting the number of pixels, the structural member information can be accurately converted into image features, and the expression capability of the structural plane layout map on the structural member information is expanded.
Based on the same inventive concept, the embodiment of the invention also provides a device for generating the feature map of the structural member of the intelligent design of the frame structure, please refer to fig. 9, and fig. 9 is a functional block diagram of the device for generating the feature map of the structural member provided by the embodiment of the invention.
As shown in fig. 9, the structural member characteristic map generating apparatus 300 may include: the device comprises an acquisition module 310, a removal module 320, an extraction module 330, a determination module 340 and a conversion module 350.
An acquisition module 310 for acquiring a structural member feature vector diagram;
a removing module 320, configured to remove redundant information other than structural information required for intelligent design from the structural member feature vector diagram, and an extracting module 330, configured to extract structural member information of each structural member, and convert the structural member information into image expression information; the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio; the structure information required by the intelligent design at least comprises structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency;
a determining module 330 for determining gray values of the respective structural members according to the concrete strength values of the respective structural members;
the conversion module 340 is configured to process the feature vector image of the structural member according to the image expression information, the gray value, and the preset pixel conversion ratio of each structural member, so as to obtain a feature pixel image of the structural member.
It is understood that the obtaining module 310, the removing module 320, the extracting module 330, the determining module 340, and the converting module 350 may cooperatively perform the steps in fig. 1 to achieve the corresponding technical effects.
As an alternative embodiment, the conversion module 350 is specifically configured to: processing the feature vector diagram of the structural member according to the image expression information and gray values of each structural member; and converting the processed feature vector diagram of the structural member according to the pixel conversion proportion to obtain a feature pixel diagram of the structural member.
As an alternative embodiment, the structural member comprises a post; the structural member information comprises a column section length and a column section width corresponding to the column; the extraction module 330 is specifically configured to: determining the column section length as a column edge length of the column in the horizontal direction; the column cross-section width is determined as the column edge length of the column in the vertical direction.
As an alternative embodiment, the structural member comprises a beam; the structural member information comprises beam section width, beam section height, beam length and beam span-to-height ratio corresponding to the beam; the extraction module 330 is specifically configured to: determining the beam length as the length of the beam center line; determining a beam cross-section width as a beam edge length in a direction perpendicular to an arrangement direction of the beams; based on the length of the beam, determining the central position of the beam, performing expansion deformation treatment on the area where the central position is located, and determining the vertical line section of the central line in the area where the expanded central position is located as the height of the beam section; the method comprises the steps of determining a line segment formed by connecting a starting point of a beam center line and an ending point of the beam section height as a span-to-height ratio positioning line based on the beam section height, determining a beam span-to-height ratio as a span-to-height ratio positioning line slope based on the span-to-height ratio positioning line, wherein the span-to-height ratio positioning line slope is a tangent value of an included angle formed by a beam length and the span-to-height ratio positioning line.
As an alternative embodiment, the determining module 340 is specifically configured to: if the structural member is a column, taking the difference between the first preset value and the concrete strength value corresponding to the column as a gray value of the column; if the structural member is a beam, calculating a difference value between the first preset value and a concrete strength value corresponding to the beam, and taking the sum of the difference value and a preset threshold value as a gray value of the beam.
As an alternative embodiment, the obtaining module 310 is specifically configured to: and extracting the feature vector diagram of the structural member from the CAD drawing or the Revit drawing for frame structure construction.
The above-described architecture feature map generating apparatus 300 for intelligent design of a framework structure according to an embodiment of the present invention may be stored in an Operating System (OS) of the electronic device 400 in the form of software or firmware (firmware).
Referring to fig. 10, fig. 10 is a block diagram of an electronic device provided in an embodiment of the present invention, where the electronic device 400 may be used to execute the method for generating a feature map of a structural member of an intelligent design of a frame structure provided in an embodiment of the present invention, and as an alternative embodiment, the electronic device 400 may be, but is not limited to: tablet computers, personal computers, intelligent terminals, etc.
As shown in fig. 10, the electronic device 400 may include: the memory 401, the processor 402, the communication interface 403, and the bus 404 are electrically connected directly or indirectly to each other, so as to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
Alternatively, bus 404 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 10, but not only one bus or one type of bus.
In an embodiment of the present invention, processor 402 may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, where the methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software module may be located in the memory 401 and the processor 402 reads the program instructions in the memory 401, in combination with its hardware, to perform the steps of the method described above.
In the embodiment of the present invention, the memory 401 may be a nonvolatile memory, such as a hard disk (HDD) or a Solid State Drive (SSD), or may be a volatile memory (RAM). The memory may also be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory in embodiments of the present invention may also be circuitry or any other device capable of performing memory functions for storing instructions and/or data.
The memory 401 may be used to store software programs and modules, such as instructions/modules of the structural component signature generating apparatus 300 provided in the embodiment of the present invention, may be stored in the memory 401 in the form of software or firmware (firmware) or be solidified in an Operating System (OS) of the electronic device 400, and the processor 402 executes the software programs and modules stored in the memory 401, thereby executing various functional applications and data processing. The communication interface 403 may be used for communication of signaling or data with other node devices.
It is to be understood that the configuration shown in fig. 10 is merely illustrative, and that electronic device 400 may also include more or fewer components than shown in fig. 10, or have a different configuration than shown in fig. 10. The components shown in fig. 10 may be implemented in hardware, software, or a combination thereof.
Based on the above embodiments, the present application further provides a computer-readable storage medium in which a computer program is stored, which when executed by a computer, causes the computer to execute the structural member feature map generating method provided in the above embodiments.
Based on the above embodiments, the present embodiments also provide a computer program, which when run on a computer, causes the computer to execute the structural member feature map generating method provided by the above embodiments.
Based on the above embodiments, the present application further provides a chip for reading a computer program stored in a memory, for executing the structural member feature map generating method provided in the above embodiments.
There is also provided in an embodiment of the present application a computer program product comprising instructions which, when run on a computer, cause the computer to perform the structural member feature map generation method provided in the above embodiment.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by instructions. These instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A structural member feature map generation method, characterized by comprising:
acquiring a feature vector diagram of a structural member;
removing redundant information except structural information required by intelligent design from the structural member feature vector diagram, extracting structural member information of each structural member, and converting the structural member information into image expression information; the structure information required by the intelligent design at least comprises the structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency; the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio;
determining a gray value for each of the structural members based on the concrete strength value for each of the structural members;
and processing the feature vector diagram of the structural member according to the image expression information of each structural member, the gray value and the preset pixel conversion proportion to obtain a feature pixel diagram of the structural member.
2. The method according to claim 1, wherein processing the structural member feature vector map according to the image expression information, the gray value, and a preset pixel conversion ratio of each structural member to obtain a structural member feature pixel map includes:
processing the feature vector diagram of the structural member according to the image expression information of each structural member and the gray value;
and converting the processed feature vector diagram of the structural member according to the pixel conversion proportion to obtain the feature pixel diagram of the structural member.
3. The method of claim 1, wherein the structural member comprises a post; the structural member information comprises a column section length and a column section width corresponding to the column;
extracting structural member information of each structural member from the structural member feature vector diagram, and converting the structural member information into image expression information, comprising:
determining the column section length as a column edge length of the column in a horizontal direction;
the column section width is determined as a column edge length of the column in the vertical direction.
4. A method according to claim 3, wherein the structural member comprises a beam; the structural member information comprises a beam section width, a beam section height, a beam length and a beam span-to-height ratio corresponding to the beam;
extracting structural member information of each structural member from the structural member feature vector diagram, and converting the structural member information into image expression information, comprising:
determining the beam length as the length of the beam centerline;
determining the beam section width as a beam edge length in a direction perpendicular to an arrangement direction of the beams;
based on the beam length, determining the central position of the beam, performing expansion deformation treatment on the area where the central position is located, and determining the vertical line section of the central line of the beam in the area where the expanded central position is located as the beam section height;
determining a line segment formed by connecting a start point of the beam center line and an end point of the beam section height as a span-to-height ratio positioning line based on the beam section height,
determining the beam aspect ratio as an aspect ratio bit line slope based on the aspect ratio bit line, the aspect ratio bit line slope being a tangent of an angle formed by the beam length and the aspect ratio bit line.
5. The method of claim 4, wherein determining a gray value for each of the structural members based on the concrete strength values for each of the structural members comprises:
if the structural member is the column, taking the difference between a first preset value and the concrete strength value corresponding to the column as a gray value of the column;
if the structural member is the beam, calculating a difference value between the first preset value and the concrete strength value corresponding to the beam, and taking the sum of the difference value and a preset threshold value as a gray value of the beam.
6. The method of claim 1, wherein obtaining a feature vector map of the structural member comprises:
and extracting the feature vector diagram of the structural member from the CAD drawing or the Revit drawing for frame structure construction.
7. A structural member characteristic map generating apparatus, comprising:
the acquisition module is used for acquiring the feature vector diagram of the structural member;
the removing module is used for removing redundant information except for structural information required by intelligent design from the structural member feature vector diagram, and the extracting module is used for extracting structural member information of each structural member and converting the structural member information into image expression information; the structure information required by the intelligent design at least comprises the structure member information, and the structure information required by the intelligent design is used for improving the machine learning efficiency; the structural member information at least comprises a column concrete strength value, a column section width, a column section height, a beam concrete strength value, a beam section width, a beam section height, a beam length and a beam span-to-height ratio;
a determining module for determining a gray value of each of the structural members according to the concrete strength value of each of the structural members;
and the conversion module is used for processing the structural member characteristic vector image according to the image expression information of each structural member, the gray value and the preset pixel conversion proportion to obtain a structural member characteristic pixel image.
8. The apparatus of claim 7, wherein the conversion module is specifically configured to:
processing the feature vector diagram of the structural member according to the image expression information of each structural member and the gray value;
and converting the processed feature vector diagram of the structural member according to the pixel conversion proportion to obtain the feature pixel diagram of the structural member.
9. An electronic device comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being executable to implement the method of any one of claims 1 to 6.
10. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139974.7A CN116150849B (en) | 2023-02-20 | 2023-02-20 | Structural member feature map generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139974.7A CN116150849B (en) | 2023-02-20 | 2023-02-20 | Structural member feature map generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116150849A true CN116150849A (en) | 2023-05-23 |
| CN116150849B CN116150849B (en) | 2023-11-28 |
Family
ID=86357940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310139974.7A Active CN116150849B (en) | 2023-02-20 | 2023-02-20 | Structural member feature map generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116150849B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327324A (en) * | 2021-06-25 | 2021-08-31 | 广东博智林机器人有限公司 | Method and device for constructing three-dimensional building model, computer equipment and storage medium |
| CN114925416A (en) * | 2022-04-25 | 2022-08-19 | 清华大学 | Building structure generation method and device based on data conversion |
-
2023
- 2023-02-20 CN CN202310139974.7A patent/CN116150849B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327324A (en) * | 2021-06-25 | 2021-08-31 | 广东博智林机器人有限公司 | Method and device for constructing three-dimensional building model, computer equipment and storage medium |
| CN114925416A (en) * | 2022-04-25 | 2022-08-19 | 清华大学 | Building structure generation method and device based on data conversion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116150849B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008809B (en) | Method and device for acquiring form data and server | |
| JP2023541532A (en) | Text detection model training method and apparatus, text detection method and apparatus, electronic equipment, storage medium, and computer program | |
| CN110502985B (en) | Form identification method and device and form identification equipment | |
| CN110689012A (en) | End-to-end natural scene text recognition method and system | |
| KR101402442B1 (en) | Image processing device and method | |
| CN112949707B (en) | Cross-modal face image generation method based on multi-scale semantic information supervision | |
| CN111652181B (en) | Target tracking method and device and electronic equipment | |
| Khan et al. | Lrdnet: lightweight lidar aided cascaded feature pools for free road space detection | |
| CN116150849B (en) | Structural member feature map generation method and device, electronic equipment and storage medium | |
| CN113158970B (en) | Action identification method and system based on fast and slow dual-flow graph convolutional neural network | |
| EP4075381B1 (en) | Image processing method and system | |
| CN110909563A (en) | Method, device and equipment for extracting character skeleton and computer readable storage medium | |
| CN106778844B (en) | Method and system for matching cracks in tunnel | |
| CN111179289B (en) | Image segmentation method suitable for webpage length graph and width graph | |
| CN115620321B (en) | Table identification method and device, electronic equipment and storage medium | |
| JP2003141567A (en) | Three-dimensional city model generating device and method of generating three-dimensional city model | |
| CN115082371B (en) | Image fusion method and device, mobile terminal equipment and readable storage medium | |
| JP2023027782A (en) | Image transition method, image transition model training method, device, electronics, storage medium, and computer program | |
| KR100491723B1 (en) | Method of rendering a digital terrain model in geographic information system | |
| CN112861860B (en) | Text detection method in natural scene based on upper and lower boundary extraction | |
| CN115359502A (en) | Image processing method, device, equipment and storage medium | |
| CN114494302A (en) | Image processing method, device, equipment and storage medium | |
| CN112419208A (en) | Construction drawing review-based vector drawing compiling method and system | |
| CN112419216A (en) | Image interference removing method and device, electronic equipment and computer readable storage medium | |
| CN111753689B (en) | Image texture feature extraction method and image recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |