CN116186825A

CN116186825A - Shear wall design method and device based on graph node classification graph neural network

Info

Publication number: CN116186825A
Application number: CN202211516253.5A
Authority: CN
Inventors: 陆新征; 赵鹏举; 廖文杰
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2022-11-29
Filing date: 2022-11-29
Publication date: 2023-05-30
Anticipated expiration: 2042-11-29
Also published as: CN116186825B

Abstract

The invention provides a shear wall design method and device based on a graph node classification graph neural network, comprising the following steps: obtaining a target building plane design drawing to be processed; the method comprises the steps of representing a target building plane design drawing to be processed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form the characteristics of the building plane graph to be input; inputting the characteristics of the building plane map to be input into a map node classification map neural network model of a pre-constructed shear wall design so as to obtain a shear wall design map; and obtaining a shear wall design result based on the shear wall design map. The invention can rapidly design the shear wall, and greatly improves the design efficiency and the design quality of the shear wall at the preliminary structural design stage.

Description

Shear wall design method and device based on graph node classification graph neural network

Technical Field

The invention relates to the field of building structure design, in particular to a shear wall design method and device based on a graph node classification graph neural network.

Background

For a building structure containing shear walls, a high-quality primary design scheme has important significance for later-stage deepening design and construction drawing design. However, the conventional design method at present depends on the design experience of the structural engineer seriously, the design efficiency is low, the time consumption is long, the interactive design efficiency between the construction engineer and the structural engineer is low, and the design quality is uneven due to the difference of experience levels of the designers. Meanwhile, the existing structural design optimization method based on computer assistance has the problems of long finite element calculation time consumption, high resource consumption, difficulty in forming a universal design flow, unfriendly engineer and the like. The existing shear wall design method based on artificial intelligence assistance is carried out by relying on pixel images, and the spatial position and spatial topological characteristics of the shear wall arrangement in the structure are difficult to consider.

Disclosure of Invention

The invention provides a shear wall design method and device based on a graph node classification graph neural network, which are used for solving the defects of low design efficiency, long time consumption and uneven quality existing in the prior art, realizing the effect of quickly generating vectorization map data of the shear wall and improving the design efficiency and quality of the shear wall at the preliminary design stage of a building structure.

The invention provides a shear wall design method based on a graph node classification graph neural network, which comprises the following steps:

obtaining a target building plane design drawing to be processed;

the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes;

extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input;

inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map;

the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data;

and obtaining a shear wall design result based on the shear wall design map.

According to the shear wall design method based on the graph node classification graph neural network, which is provided by the invention, the target building plane design drawing to be processed is expressed as a graph format formed by graph nodes and graph edges, and the method specifically comprises the following steps:

Extracting skeleton lines of key elements in the target building plane design drawing; wherein the key elements comprise a wall body or at least one of an indoor door opening, an outdoor door opening and a window opening and a wall body in the target building plane design drawing;

the skeleton line of the key element is the central line of the key element and is represented by a line segment, and comprises a wall skeleton line or a wall skeleton line and a door and window opening skeleton line; wherein the door and window opening framework lines comprise at least one of an indoor door opening framework line, an outdoor door opening framework line and a window opening framework line;

taking the intersection point of each wall skeleton line or the intersection point of the wall skeleton line and the door and window opening skeleton line as a graph node of the graph, and taking the wall skeleton line or the wall skeleton line and the door and window opening skeleton line as a graph edge of the graph;

subdividing the graph edges of the graph according to a predetermined length dimension, and adopting node intervals, wherein the nodes are also used as graph nodes of the graph.

According to the shear wall design method based on the graph node classification graph neural network, which is provided by the invention, the characteristics of graph nodes and graph edges in the graph are extracted to form the building plane graph characteristics to be input, and the method comprises the following steps:

The building plane map features to be input comprise map node features and map edge features;

the graph node feature comprises: category of graph node, location of graph node;

the graph edge feature comprises: category of the drawing edge;

the categories of the graph nodes comprise four categories of wall nodes, indoor door opening nodes, outdoor door opening nodes and window opening nodes;

the types of the drawing edges comprise four types of wall edges, indoor door opening edges, outdoor door opening edges and window opening edges.

According to the shear wall design method based on the graph node classification graph neural network, provided by the invention, the shear wall design result is obtained based on the shear wall design map, and the method specifically comprises the following steps:

extracting characteristics representing a structural shear wall in the shear wall design map, wherein the characteristics representing the structural shear wall comprise graph node characteristics and graph edge characteristics;

the categories of the graph nodes in the graph node characteristics of the structural shear wall comprise five categories of structural shear wall nodes, non-structural filler wall nodes, indoor door opening nodes, outdoor door opening nodes and window opening nodes; the wall body nodes in the building plane map features to be input, which correspond to the map node features representing structural shear wall nodes and non-structural filler wall nodes in the shear wall design map, are classified into two categories of structural shear wall nodes and non-structural filler wall nodes by a map node classification map neural network model of the pre-constructed shear wall design;

Determining the position of the shear wall according to the position of a graph node, namely a structural shear wall, in graph node characteristics in the shear wall design map and the position of a wall body edge in graph edge characteristics in the shear wall design map connected with the graph node, namely the structural shear wall;

and determining the arrangement of the target shear wall in the building structure to obtain the design result of the shear wall.

According to the shear wall design method based on the graph node classification graph neural network provided by the invention, a graph node classification graph neural network model of the shear wall design is created based on building plane graph sample data and pre-calibrated shear wall design graph sample data, and the method specifically comprises the following steps:

dividing a data set by the building plane map sample data and the pre-calibrated shear wall design map sample data; the data of a certain proportion is a training set, and the data of the rest part is a testing set;

training to obtain a graph node classification graph neural network model of the shear wall design based on the training set;

testing the design effect of the graph node classification graph neural network model of the shear wall design by using a test set to obtain a test result, wherein the test result comprises a generated shear wall design graph test result corresponding to building plane graph test data; the test set comprises building plane map test data and pre-calibrated shear wall design map test data;

Evaluating the test result to obtain a comprehensive evaluation index of the shear wall design;

and using a graph node classification graph neural network model of the shear wall design, wherein the comprehensive evaluation index of the graph node classification graph neural network model is larger than a preset comprehensive evaluation index threshold value, of the shear wall design, to generate a shear wall design map.

According to the design method of the shear wall based on the graph node classification graph neural network, provided by the invention, the test result is evaluated to obtain the comprehensive evaluation index of the shear wall design, and the method specifically comprises the following steps:

physical evaluation index Score by structural mechanics analysis _Physics Index Score for evaluating map data of similarity with shear wall design map features _Graph Structure comprehensive evaluation index Score for weighting shear wall design _ShearWall Structural comprehensive evaluation index Score of shear wall design _ShearWall The calculation formula of (2) is as follows:

Score _ShearWall ＝(η _Graph ×Score _Graph +η _Physics ×Score _Physics )

wherein eta _Graph Is Score _Graph Weighting coefficient, eta of the value _Physics Is Score _Physics Weighting coefficients of the values, score _Physics Score as a physical evaluation index for structural mechanics analysis _Graph Designing a map data evaluation index of the map feature similarity for the shear wall;

physical evaluation index Score of the structural mechanics analysis _Physics Based on the structural dynamic analysis and the gravity load analysis carried out by the structural mechanical calculation model, calculating the maximum interlayer displacement angle of the structural mechanical calculation model under the structural dynamic analysis and the maximum vertical deformation of the floor structure of the structural mechanical calculation model under the gravity load analysis to respectively obtain interlayer displacement angle index Score _Drift And floor structural index Score _slab Further weighting and combining to obtain a physical evaluation index Score _Physics Physical evaluation index Score of the structural mechanics analysis _Physics The calculation formula of (2) is as follows:

Score _Physics ＝(η _Drift ×Score _Drift +η _slab ×Score _slab )

wherein eta _Drift Is Score _Drift Weighting coefficient, eta of the value _slab Is Score _slab Weighting coefficients of the values, score _Drift Score as an index of interlayer displacement angle _slab Is a structural index of the floor slab;

the shear wall design spectrum feature similarity spectrum data evaluation index Score _Graph Obtaining a graph node category similarity between a generated shear wall design graph test result corresponding to the building plane graph test data and pre-calibrated shear wall design graph test data; calculating graph nodes and graph nodes of categories predicted to be structural shear walls and non-structural filling walls in generated shear wall design atlas test results corresponding to the building plan atlas test dataThe category of the pre-calibrated shear wall design map test data is a confusion matrix of map nodes of the structural shear wall and the non-structural filling wall;

the method comprises the steps of determining the number of graph nodes of the structural shear wall, wherein the number of graph nodes of the structural shear wall is predicted to be the number of graph nodes of the structural shear wall in a generated shear wall design spectrum test result, wherein the categories of the graph nodes are corresponding to the pre-calibrated shear wall design spectrum test data, and the number of graph nodes of the structural shear wall is recorded as SS; corresponding to the map nodes with the categories of the structural shear wall in the pre-calibrated shear wall design map test data, and marking the number of the map nodes with the categories of the non-structural filling wall as SF in the generated shear wall design map test result; corresponding to the nodes with the categories of non-structural filling walls in the pre-calibrated shear wall design pattern test data, and marking the number of the nodes with the categories of structural shear walls predicted in the generated shear wall design pattern test result as FS;

The shear wall design spectrum feature similarity spectrum data evaluation index Score _Graph The calculation formula of (2) is as follows:

Score _Graph ＝2×SS/(2×SS+SF+FS)。

according to the shear wall design method based on the graph node classification graph neural network, which is provided by the invention, the loss function of the graph node classification graph neural network model training of the shear wall design is as follows:

wherein N is the number of nodes of the wall body side of the map to be calculated, t _i The true class value of the ith node is 1 for the structural shear wall, and 0 for the non-structural filler wall; p is p _i Log () is a function that computes a base 2 logarithm, which is the probability that the i-th node is predicted to be a structural shear wall.

The invention also provides a shear wall design device based on the graph node classification graph neural network, which comprises:

the acquisition module is used for acquiring a target building plane design drawing to be processed;

the map generation module is used for representing the target building plane design drawing to be processed into a map format formed by a map node and a map edge; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes;

the map feature extraction module is used for extracting the features of the map nodes and the map edges in the map to form building plane map features to be input;

The generation module is used for inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design so as to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data;

and the result module is used for obtaining a shear wall design result based on the shear wall design map.

The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the shear wall design method based on the graph node classification graph neural network when executing the program.

The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of designing a shear wall based on a graph node class graph neural network as described in any one of the above.

The invention provides a shear wall design method and a shear wall design device based on a graph node classification graph neural network, which are implemented by acquiring a target building plane design drawing to be processed; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map. According to the invention, the target building plane design drawing to be processed is expressed as a map format formed by map nodes and map edges, the characteristics of the map nodes and the map edges in the map are extracted to form building plane map characteristics to be input, the building plane map characteristics to be input are converted into a shear wall design map based on a map node classification map neural network model of a pre-constructed shear wall design, and then a shear wall design result is obtained, the efficiency of a structure preliminary scheme design stage is greatly improved, the defect that the space position and the topology characteristics of the shear wall in the structure are not fully considered in the existing artificial intelligence-assisted shear wall design method is overcome, and the reliability and the applicability of the map node classification map neural network model of the shear wall design generated by training are improved.

Drawings

In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a shear wall design method based on a graph node classification graph neural network provided by the invention;

FIG. 2 is a second flow chart of a method for designing a shear wall based on a graph node classification graph neural network according to the present invention;

FIG. 3 is a schematic diagram of a shear wall design pattern format of one embodiment of a shear wall design method based on a graph node classification graph neural network provided by the invention;

FIG. 4 is a schematic structural diagram of a shear wall design device based on a graph node classification graph neural network provided by the invention;

fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.

Reference numerals:

410: an acquisition module; 420: a map generation module; 430: the atlas feature extraction module; 440: a generating module; 450: a result module;

510: a processor; 520: a communication interface; 530: a memory; 540: a communication bus.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. 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.

The present embodiment takes a shear wall structure as an example, but the present invention is not limited to the shear wall structure, and the present invention is applicable to all building structure types including shear walls.

The following describes a shear wall design method based on a graph node classification graph neural network with reference to fig. 1, and fig. 1 is one of flow diagrams of the shear wall design method based on the graph node classification graph neural network provided by the invention, as shown in fig. 1, the method includes:

step 110: and obtaining a target building plane design drawing to be processed.

The method comprises the steps of obtaining a to-be-processed building plane design drawing, wherein one of the purposes of the method for designing the shear wall based on the graph node classification graph neural network is to use the graph neural network method to design the shear wall in the structure based on the to-be-processed building plane design drawing.

Step 120: the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes.

In other words, after the target building plane design drawing to be processed is obtained, the target building plane design drawing is expressed as a map format formed by map nodes and map edges, wherein the map nodes represent key elements, and the map edges represent connection relations of the key element map nodes;

the key elements refer to key constituent elements in a target building plane design drawing to be processed, and comprise a wall body or at least one of an indoor door opening, an outdoor door opening and a window opening and the wall body in the target building plane design drawing. That is, the key elements must include walls, and three elements, i.e., an indoor door opening, an outdoor door opening, and a window opening, may be present, none, or any of them.

Step 130: and extracting the characteristics of graph nodes and graph edges in the graph to form the characteristics of the building plane graph to be input.

After the target building plane design drawing to be processed is expressed into a graph format formed by graph nodes and graph edges, the graph nodes and the graph edges of the graph have characteristics, the graph nodes represent key elements, and the graph edges represent the connection relation of the key element graph nodes, so that the building plane graph characteristics to be input comprise graph node characteristics and graph edge characteristics.

Step 140: inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map;

the graph node classification graph neural network model of the shear wall design is obtained by training based on building plane graph sample data and pre-calibrated shear wall design graph sample data.

In other words, building plane map features to be input are input into a map node classification map neural network model of a pre-constructed shear wall design, and a shear wall design map is generated.

The graph node classification graph neural network model of the shear wall design is obtained after training based on building plane graph sample data and pre-calibrated shear wall design graph sample data.

In the generated shear wall design map, the categories of map nodes comprise five categories of structural shear wall nodes, non-structural filler wall nodes, indoor door opening nodes, outdoor door opening nodes and window opening nodes; the generated shear wall design map corresponds to the nodes of wall body types in the building plane map features to be input, and the map node classification map neural network model of the shear wall design is classified into two types of structural shear wall nodes and non-structural filler wall nodes.

Step 150: and obtaining a shear wall design result based on the shear wall design map.

And determining the position of the shear wall according to the position of the graph node, namely the structural shear wall, in the graph node characteristics in the shear wall design map and the position of the wall edge in the graph edge characteristics in the shear wall design map connected with the graph node, namely the structural shear wall, so as to obtain the scheme design result of the shear wall in the structure.

And then, constructing a mechanical calculation model of the whole structure according to the scheme design result of the shear wall in the structure, and analyzing and calculating.

Based on the above embodiment, in the method, the target building plane design drawing to be processed is represented as a graph format formed by graph nodes and graph edges, which specifically includes:

Specifically, before representing a target building plane design drawing to be processed as a map format formed by map nodes and map edges, skeleton lines of key elements in the target building plane design drawing need to be extracted first, and then the building plane design drawing is represented as a map format formed by map nodes and map edges according to the skeleton lines of the key elements.

The key elements comprise at least one of a wall body or an indoor door opening, an outdoor door opening and a window opening in the target building plane design drawing and the wall body; that is, the key elements must include walls, and the indoor door openings, the outdoor door openings, and the window openings may be provided, or may be provided with any of the above.

The skeleton line of the key element refers to the central line of the key element, and is expressed by line segments, and comprises a wall skeleton line or a wall skeleton line and a door and window opening skeleton line; during operation, the critical element framework lines must include wall framework lines, which may or may not be present at the door and window openings. If the key element in the target building plane design drawing does not contain the door and window opening, the skeleton line of the key element does not contain the skeleton line of the door and window opening. The door and window openings are collectively called an indoor door opening, an outdoor door opening and a window opening. Wherein the door and window opening framework lines comprise at least one of an indoor door opening framework line, an outdoor door opening framework line and a window opening framework line.

The center line is a line for identifying the center of the object in a certain direction, which is a set of line segments representing the middle point, and in this embodiment, the direction is the extending direction of the key element. The centerline can provide accurate positioning of the object, and in this embodiment, the centerline of the key element functions to represent the key element with a line segment of the centerline.

Based on the extracted skeleton lines of the key elements, the intersection points of the skeleton lines of all walls or the intersection points of the skeleton lines of the walls and the skeleton lines of the door and window openings are used as graph nodes of the graph, and the skeleton lines of the walls or the skeleton lines of the walls and the skeleton lines of the door and window openings are used as edges of the graph. That is, in actual operation, if the key element does not include a door window opening, performing: based on the extracted skeleton lines of the key elements, taking the intersection points of the skeleton lines of each wall body as graph nodes of the graph and taking the skeleton lines of the wall body as graph edges of the graph; if the key element contains a door window opening, performing: based on the extracted skeleton lines of the key elements, taking the intersection points of the wall skeleton lines and the door and window opening skeleton lines as graph nodes of the graph, and taking the wall skeleton lines and the door and window opening skeleton lines as graph edges of the graph.

And then subdividing the graph edges of the graph according to a predetermined length dimension, adopting node intervals, wherein the nodes are also used as graph nodes of the graph, and representing the target building plane design drawing to be processed into a graph format consisting of nodes and edges. The predetermined length dimension may be selected according to practical situations, and is not limited in this embodiment.

In the operation process, extracting key elements including four types of walls, indoor door openings, outdoor door openings and window openings from the target building plane design drawing based on the obtained target building plane design drawing to be processed; extracting skeleton lines of the extracted key elements, namely extracting central lines of the skeleton lines, and accurately positioning the key elements; then, based on the skeleton line of the key element, taking the wall skeleton line or the intersection point of the wall skeleton line and the door and window opening skeleton line as a graph node of the graph, and taking the wall skeleton line or the wall skeleton line and the door and window opening skeleton line as the graph edge of the graph; subdividing the graph edges of the graph according to a predetermined length dimension, adopting node intervals, wherein the nodes are also used as graph nodes of the graph, and further representing the target building plane design drawing to be processed into a graph format formed by the nodes and the edges.

Based on the above embodiment, in the method, the extracting the features of the graph nodes and the graph edges in the graph to form the building plane graph features to be input includes:

the graph edge feature comprises: category of the drawing edge;

Specifically, extracting the characteristics of graph nodes and graph edges in the graph to form the characteristics of the building plane graph to be input, wherein the characteristics of the building plane graph to be input refer to information of the building plane represented by the nodes and the edges as graph format, and the graph format is the data format of the graph neural network.

The graph node features include: category of graph node, location of graph node;

the graph edge features include: category of the drawing edge;

Of the classes of edges of the map, both structural shear walls and non-structural infill walls are denoted as a class of walls.

Based on the above embodiment, in the method, the obtaining a shear wall design result based on the shear wall design map specifically includes:

Specifically, extracting characteristics representing the structural shear wall in the shear wall design map, wherein the characteristics representing the structural shear wall comprise graph node characteristics and graph edge characteristics; in the generated shear wall design map, the categories of map nodes comprise five categories of structural shear wall nodes, non-structural filler wall nodes, indoor door opening nodes, outdoor door opening nodes and window opening nodes; the generated shear wall design map corresponds to map nodes of wall body types in building plane map features to be input, and the map node classification map neural network model of the shear wall design is classified into two types of structural shear wall nodes and non-structural filler wall nodes.

That is, after the shear wall design map is generated, features representing the structural shear wall in the generated shear wall design map are extracted, wherein the features representing the structural shear wall include graph node features and graph side features.

The graph node characteristics of the generated shear wall design map, which represent the structural shear wall, comprise: category of graph node, location of graph node; the drawing edge features representing the structural shear wall in the generated shear wall design map include classes of edges.

It should be noted that in this embodiment, the main roles of the drawing edge are two: one is to function as a connection node, indicating how the nodes are connected (i.e., indicating the connection relationship of the graph nodes). Secondly, because the nodes have no length, in an actual structure, the wall is long. Therefore, when the shear wall design result is obtained based on the shear wall design map, after the wall nodes are classified into two categories of structural shear walls and non-structural filling walls, the positions of edges of the wall in the map edge feature are needed to be used as the supplement of the length in the shear wall design result. In practice, half the length of those wall edges connected to nodes classified as structural shear walls may be considered structural shear walls.

Determining vectorized position coordinates according to graph node positions in a shear wall design map, determining the positions of the structure shear walls according to two graph node categories of the structure shear wall and the non-structure filling wall in the shear wall design map, and determining vectorized position coordinates of the structure shear wall in the structure by combining the positions of wall edges in graph edge features in the shear wall design map connected with the graph nodes of the structure shear wall; in the preliminary structural scheme design stage, the position of the non-structural filling wall between the structural shear walls can be used as a structural beam member, and the vectorized position coordinate of the structural beam in the structure can be determined by eliminating cantilever beam members which are not connected with the structural shear walls at the end points of the two ends.

The structural beam is a part of the wall body except for the shear wall; that is, the structural beams are non-structural infill walls. In the preliminary structural scheme design stage, the part except the shear wall in the nodes of the wall type can be used as a structural beam member, and the cantilever beam members which are not connected with the structural shear wall are eliminated from the end points at the two ends of the structural beam member, so that the vectorized position coordinates of the structural beam in the structure can be determined; the above description is provided only for a method of determining structural beam placement, and is not necessarily used by the present invention, but is merely a conventional step in building a structural analysis model.

And then, constructing a mechanical calculation model of the whole structure according to the design result of the shear wall, and analyzing and calculating.

Based on the vectorized position coordinates of the structural shear wall and the vectorized position coordinates of the structural beam, calling an application program interface of structural design analysis software, and automatically constructing a standard layer structural mechanics calculation model; determining a plane outline according to the overall building plane layout comprising four key elements of a wall body, an indoor door opening, an outdoor door opening and a window opening, and defining a floor position for a standard layer structure mechanics calculation model according to the outline in structural design analysis software; and according to design experience, in structural design analysis software, floor load is defined for a standard layer structure mechanics calculation model, and the floor thickness, the shear wall thickness size and the structural beam size of the preliminary scheme design stage are defined.

And constructing a structural mechanics calculation model of the whole building in structural design analysis software according to the standard layer structural mechanics calculation model, and analyzing and calculating.

The standard layer structure mechanics calculation model refers to a finite element model used by certain structural analysis software, such as an ETABS software model, a PKPM software model, a built-in software model, an ABAQUS software model and the like. In the next evaluation process in the test process, mechanical property calculation needs to be performed on the designed structure, and the mechanical calculation can be performed on the structural mechanical calculation model of the whole building and the standard layer structural analysis model in the evaluation stage.

The standard layer structure analysis model and the structural mechanics calculation model of the whole building can be built by calling a structural design analysis software API besides a manual modeling method. Therefore, the corresponding shear wall design scheme can be rapidly output according to the standard layer plane drawing in the building design, the vectorized shear wall arrangement data are obtained, the structural mechanics calculation model is automatically built, calculation analysis is carried out, and the full-automatic design-modeling-analysis of the corresponding structure of the building design is realized.

Based on the above embodiment, in the method, a graph node classification graph neural network model of the shear wall design is created based on building plane graph sample data and pre-calibrated shear wall design graph sample data, and specifically includes:

Specifically, dividing a data set by building plane map sample data and pre-calibrated shear wall design map sample data; the data of a certain proportion is a training set, and the data of the rest part is a testing set; based on the training set, the graph node classification graph neural network model of the shear wall design is obtained by utilizing the deep neural network training.

Testing the design effect of a graph node classification graph neural network model of the shear wall design by using a test set to obtain a test result, wherein the test result comprises a generated shear wall design graph test result corresponding to building plane graph test data; the test set comprises building plane map test data and pre-calibrated shear wall design map test data;

And testing the node classification graph neural network model of the shear wall design which is completed through training by adopting a corresponding test data set, and carrying out evaluation by adopting the comprehensive evaluation index provided by the invention. And testing the design effect of the graph node classification graph neural network model of the shear wall design according to the test set, evaluating the test result based on the comprehensive evaluation method, wherein the model with qualified evaluation can be put into application. Wherein, when the comprehensive evaluation index Score _ShearWall When the threshold value defined in advance is exceeded, the result of the generation is considered to be good. The graph node classification graph neural network model of the adopted shear wall design adopts the comprehensive evaluation index evaluation of the shear wall design with coupled graph data and structural physical characteristics to evaluate the qualification, so that the reliability of the graph node classification graph neural network model of the shear wall design is improved.

Based on the above embodiment, in the method, the test result is evaluated to obtain a comprehensive evaluation index of the shear wall design, which specifically includes:

Score _ShearWall ＝(η _Graph ×Score _Graph +η _Physics ×Score _Physics )

physical evaluation index Score of the structural mechanics analysis _Physics Is obtained by structural dynamic analysis and gravity load analysis based on the structural mechanics calculation model, and calculates theMaximum interlayer displacement angle of the structural mechanical calculation model under structural dynamic analysis and maximum vertical deformation of the floor structure of the structural mechanical calculation model under gravity load analysis are respectively obtained to obtain interlayer displacement angle index Score _Drift And floor structural index Score _slab Further weighting and combining to obtain a physical evaluation index Score _Physics Physical evaluation index Score of the structural mechanics analysis _Physics The calculation formula of (2) is as follows:

Score _Physics ＝(η _Drift ×Score _Drift +η _slab ×Score _slab )

the shear wall design spectrum feature similarity spectrum data evaluation index Score _Graph Obtaining a graph node category similarity between a generated shear wall design graph test result corresponding to the building plane graph test data and pre-calibrated shear wall design graph test data; calculating confusion matrixes of graph nodes of which the categories are predicted to be the structural shear wall and the non-structural filling wall in the generated shear wall design graph test results corresponding to the building plane graph test data and graph nodes of which the categories are the structural shear wall and the non-structural filling wall in the pre-calibrated shear wall design graph test data;

Score _Graph ＝2×SS/(2×SS+SF+FS)。

specifically, the graph node classification graph neural network model of the shear wall design is comprehensively evaluated by using the evaluation index, and the model with qualified evaluation can be put into application. That is, the generated shear wall design spectrum data and the pre-calibrated shear wall design spectrum sample data are subjected to the comprehensive evaluation of the difference, and the graph node classification graph neural network model of the shear wall design which is qualified by the comprehensive evaluation can be put into application.

Based on the above embodiment, in the method, the loss function of the graph node classification graph neural network model training of the shear wall design is:

Specifically, the function is used to evaluate the loss of the graph node class graph neural network model of the shear wall design in training.

According to the shear wall design method based on the graph node classification graph neural network, a target building plane design drawing to be processed is obtained; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map. According to the invention, the target building plane design drawing to be processed is expressed as a map format formed by map nodes and map edges, the characteristics of the map nodes and the map edges in the map are extracted to form building plane map characteristics to be input, the building plane map characteristics to be input are converted into a shear wall design map based on a map node classification map neural network model of a pre-constructed shear wall design, and then a shear wall design result is obtained, the efficiency of a structure preliminary scheme design stage is greatly improved, the defect that the space position and the topology characteristics of the shear wall in the structure are not fully considered in the existing artificial intelligence-assisted shear wall design method is overcome, and the reliability and the applicability of the map node classification map neural network model of the shear wall design generated by training are improved.

In order to further illustrate the design method of the shear wall based on the graph node classification graph neural network, the invention provides a specific embodiment.

FIG. 2 is a second flow chart of the design method of the shear wall based on the graph node classification graph neural network, as shown in FIG. 2, collecting CAD drawing data sets matched with the building-structure of the shear wall residential building, and extracting skeleton lines of key elements in the CAD drawing; further, representing the building plane as map format data comprising map nodes and map edges according to skeleton lines, wherein the map nodes represent key elements, and the map edges represent connection relations of the map nodes of the key elements; dividing a data set according to the obtained map format data, and training a map node classification map neural network model of the shear wall design; performing model evaluation on a graph node classification graph neural network model of the shear wall design, inputting building plane graph sample data of a test set into the graph node classification graph neural network model of the shear wall design obtained by training, generating shear wall design graph data, performing differential comprehensive evaluation on the generated shear wall design graph data and pre-calibrated shear wall design graph sample data, and putting the graph node classification graph neural network model of the shear wall design qualified by comprehensive evaluation into application; inputting the brand-new design building plane map data into a map node classification map neural network model of the shear wall design which is comprehensively evaluated to be qualified, and generating corresponding shear wall design map data; the characteristics of the shear wall representing the structure in the newly generated shear wall design map data are extracted, the vectorized shear wall component coordinates can be obtained, vectorized arrangement of beams and floors can be further obtained on the basis of the shear wall components according to design experience, an API (application program interface (API) of ETABS software is used in the embodiment of the application) of structural design analysis software is called, and a structural mechanics calculation model is automatically built, calculated and analyzed.

The method comprises the steps of collecting a CAD drawing data set matched with a building-structure of a shear wall residential building, and extracting skeleton lines of key elements in the CAD drawing. In the embodiment of the application, 300 building-structure matched CAD drawings are collected altogether, and structural shear walls, non-structural filler walls, indoor door openings, outdoor door openings and window openings are extracted from the building-structure matched CAD drawings, wherein the central lines of five key element components are represented by line segments and serve as skeleton lines of key elements.

The structural shear wall and the non-structural filler wall are collectively called as a wall body, the indoor door opening, the outdoor door opening and the window opening are collectively called as door and window openings, and then the wall body skeleton line comprises a structural shear wall skeleton line and a non-structural filler wall skeleton line, and the door and window opening skeleton line comprises an indoor door opening skeleton line, an outdoor door opening skeleton line and a window opening skeleton line.

Taking the intersection point of the wall skeleton line and the door and window opening skeleton line as a graph node of the graph and taking the wall skeleton line and the door and window opening skeleton line as graph edges of the graph; subdividing the edges of the map according to a predetermined length dimension, and adopting node intervals, wherein the nodes are also used as map nodes of the map; the graph node characteristics of the graph comprise: category of graph node, location of graph node; the edge features of the map comprise: category of the drawing edge; the categories of map nodes of the map comprise four categories of wall nodes, indoor door opening nodes, outdoor door opening nodes and window opening nodes in the building plane map features to be input; the classes of the sides of the map comprise four classes of wall body sides, indoor door opening sides, outdoor door opening sides and window opening sides; of the classes of edges of the map, both structural shear walls and non-structural infill walls are denoted as a class of walls.

FIG. 3 is a schematic diagram of a graph format provided by an embodiment of the present invention, wherein the graph characteristics of the building plane to be input represent the graph characteristics for inputting the graph node classification graph neural network, and the shear wall design graph is the graph of the output of the graph node classification graph neural network; in this schematic, different colors are used to demonstrate different node categories.

Further, the graph node classification graph neural network model of the shear wall design is subjected to model evaluation, building plane map sample data of a test set are input into the graph node classification graph neural network model of the shear wall design obtained through training, shear wall design map data are generated, the generated shear wall design map data and the pre-calibrated shear wall design map sample data are subjected to comprehensive evaluation, the graph node classification graph neural network model of the shear wall design which is qualified through comprehensive evaluation can be put into application, and the comprehensive evaluation of the graph node classification graph neural network model of the shear wall design after training adopts the following evaluation method.

First, calculating a spectrum data evaluation index Score _Graph 。

The categories of graph nodes of the graph comprise five categories of structural shear walls, non-structural filling walls, indoor door openings, outdoor door openings and window openings in the generation of the shear wall design graph; generating graph nodes of the shear wall design map corresponding to wall categories in the building plane map features to be input, and classifying graph nodes by the shear wall design graph neural network model into two categories of structural shear walls and non-structural filling walls. Therefore, the graph nodes which are classified as the structural shear wall in the corresponding pre-calibrated shear wall design graph test data can be tested at the generated shear wall design graph The number of graph nodes with the predicted category of the structural shear wall is recorded as SS; corresponding to the map nodes with the categories of the structural shear wall in the pre-calibrated shear wall design map test data, and marking the number of the map nodes with the categories of the non-structural filling wall as SF in the generated shear wall design map test result; corresponding to the map nodes with the categories of non-structural filling walls in the pre-calibrated shear wall design map test data, and marking the number of the map nodes with the categories of structural shear walls predicted in the generated shear wall design map test result as FS; then Score _Graph The calculation of (2) is as follows:

Score _Graph ＝2×SS/(2×SS+SF+FS)

second, calculating a physical evaluation index Score _Physics 。

Carrying out gravity load analysis on a structural mechanics calculation model of a structural standard layer corresponding to the design scheme of the shear wall, and calculating the maximum vertical deformation of a floor slab in the structural standard layer; carrying out dynamic analysis on an integral structure mechanical calculation model corresponding to the design scheme of the shear wall by adopting the corresponding anti-seismic fortification grade, and calculating the maximum interlayer displacement angle of the integral structure; calculating an inter-layer displacement angle index Score by comparing the maximum vertical deformation with a corresponding maximum vertical deformation limit and comparing the maximum inter-layer displacement angle with a corresponding maximum inter-layer displacement angle limit _Drift And floor structural index Score _slab As shown in the following two formulas.

Wherein, drift and Disp _slab Respectively the maximum interlayer displacement angle and the maximum vertical displacement of the structural floor slab, drift _max And Disp _slabmax The maximum interlayer displacement angle limit value and the maximum vertical displacement limit value of the structure are respectively set.

Further, the inter-layer displacement angle index Score _Drift And floor structural index Score _slab The physical evaluation index is calculated by performing weighted average as shown in the following formula.

Score _Physics ＝(η _Drift ×Score _Drift +η _slab ×Score _slab )

Wherein eta _Drift 、η _slab The weight coefficients of the interlayer displacement angle and the floor structure evaluation index are respectively 0.5 in the embodiment of the application.

Third, evaluating index Score on the map data _Graph And physical evaluation index Score _Physics Weighted average is carried out, and a structural comprehensive evaluation index Score of the shear wall design is calculated _ShearWall As shown in the following formula.

Score _ShearWall ＝(η _Graph ×Score _Graph +η _Physics ×Score _Physics )

Wherein eta _Graph Is Score _Graph Weighting coefficient, eta of the value _Physics Is Score _Physics The weight coefficients of the values may all take 0.5 in the embodiment of the present application.

And classifying graph nodes of the trained shear wall design into a graph neural network model, testing by adopting a corresponding test data set, and carrying out evaluation by adopting the comprehensive evaluation index provided by the invention. Wherein, when the comprehensive evaluation index Score _ShearWall When the threshold value defined in advance is exceeded, the result of the generation is considered to be good.

Further, the building plane map data of the brand new design is input into a map node classification map neural network model of the shear wall design which is comprehensively evaluated to be qualified, and corresponding shear wall design map data is generated.

Further, the characteristics of the shear wall representing the structure in the newly generated shear wall design map data are extracted.

Determining vectorized position coordinates according to the positions of the picture nodes in the shear wall design map, and determining the positions of the structural shear walls according to two picture node categories, namely the structural shear walls and the non-structural filling walls, in the shear wall design map, namely determining vectorized position coordinates of the structural shear walls in the structure; in the structural preliminary scheme design stage, the position of a non-structural filling wall between structural shear walls can be used as a structural beam member, and the existence of cantilever beam members which are not connected with the structural shear walls at the end points of two ends of the non-structural filling wall can be eliminated, so that the vectorized position coordinates of the structural beam in the structure can be determined;

based on the vectorized position coordinates of the structural shear wall and the vectorized position coordinates of the structural beam, calling an application program interface of structural design analysis software, and automatically constructing a standard layer structural mechanics calculation model; determining a plane outline according to the overall building plane layout comprising four key elements of a wall body, an indoor door opening, an outdoor door opening and a window opening, and defining a floor position for a standard layer structure mechanics calculation model according to the outline in structural design analysis software; according to design experience, in structural design analysis software, floor load is defined for a standard layer structure mechanics calculation model, and the thickness of a floor slab, the thickness of a shear wall and the size of a structural beam in a preliminary scheme design stage are defined;

Calling an application program interface of structural design analysis software based on the vectorized position coordinates of the structural shear wall and the vectorized position coordinates of the structural beam, and automatically constructing a standard layer structural mechanics calculation model, wherein the embodiment of the application calls an API of ETABS software;

and constructing a structural mechanics calculation model of the whole building in ETABS software according to the standard layer structural mechanics calculation model, and analyzing and calculating.

And dividing the data set according to the obtained map format data. The training set and the test set are divided into the data set according to 80% of the data sets as the training set and 20% of the data as the test set, wherein the number of the training sets is 240, and the number of the test sets is 60. The shear wall design device based on the graph node classification graph neural network provided by the invention is described below, and the shear wall design device based on the graph node classification graph neural network described below and the shear wall design method based on the graph node classification graph neural network described above can be correspondingly referred to each other. FIG. 4 is a schematic structural diagram of a shear wall design device based on a graph node classification graph neural network, as shown in FIG. 4, including an acquisition module 410; a map generation module 420; a atlas feature extraction module 430; a generation module 440; the result module 450.

Wherein:

the module 410 is configured to obtain a target building plane design drawing to be processed;

the map generating module 420 is configured to represent the target building plane design drawing to be processed into a map format formed by a map node and a map edge; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes;

the map feature extraction module 430 is configured to extract features of a map node and a map edge in the map to form a building plane map feature to be input;

the generating module 440 is configured to input the building plan map feature to be input to a map node classification map neural network model of a pre-constructed shear wall design, so as to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data;

the result module 450 is configured to obtain a shear wall design result based on the shear wall design map.

Based on the above embodiment, in the apparatus, the target building plane design drawing to be processed is represented as a graph format formed by graph nodes and graph edges, and specifically includes:

Based on the above embodiment, in the device, the extracting the features of the graph nodes and the graph edges in the graph to form the building plane graph features to be input includes:

the graph edge feature comprises: category of the drawing edge;

Based on the above embodiment, in the device, a shear wall design result is obtained based on the shear wall design map, which specifically includes:

Based on the above embodiment, in the device, a graph node classification graph neural network model of the shear wall design is created based on building plane graph sample data and pre-calibrated shear wall design graph sample data, and specifically includes:

Based on the above embodiment, in the device, the test result is evaluated to obtain a comprehensive evaluation index of the shear wall design, which specifically includes:

Score _ShearWall ＝(η _Graph ×Score _Graph +η _Physics ×Score _Physics )

Score _Physics ＝(η _Drift ×Score _Drift +η _slab ×Score _slab )

design map features of the shear wallSimilarity map data evaluation index Score _Graph Obtaining a graph node category similarity between a generated shear wall design graph test result corresponding to the building plane graph test data and pre-calibrated shear wall design graph test data; calculating confusion matrixes of graph nodes of which the categories are predicted to be the structural shear wall and the non-structural filling wall in the generated shear wall design graph test results corresponding to the building plane graph test data and graph nodes of which the categories are the structural shear wall and the non-structural filling wall in the pre-calibrated shear wall design graph test data;

Score _Graph ＝2×SS/(2×SS+SF+FS)。

based on the above embodiment, in the device, the loss function of the graph node classification graph neural network model training of the shear wall design is:

wherein N is the number of nodes of the wall body side of the map to be calculated, t _i The true class value of the ith node is 1 for the structural shear wall, and 0 for the non-structural filler wall; p is p _i For the ith nodePredicted as probability of structural shear wall, log () is a function of the logarithm of the base 2.

In the specific embodiment, the shear wall design method and the shear wall design device based on the graph node classification graph neural network provided by the invention are implemented by acquiring a target building plane design drawing to be processed; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map. According to the invention, the target building plane design drawing to be processed is expressed as a map format formed by map nodes and map edges, the characteristics of the map nodes and the map edges in the map are extracted to form building plane map characteristics to be input, the building plane map characteristics to be input are converted into a shear wall design map based on a map node classification map neural network model of a pre-constructed shear wall design, and then a shear wall design result is obtained, the efficiency of a structure preliminary scheme design stage is greatly improved, the defect that the space position and the topology characteristics of the shear wall in the structure are not fully considered in the existing artificial intelligence-assisted shear wall design method is overcome, and the reliability and the applicability of the map node classification map neural network model of the shear wall design generated by training are improved.

Fig. 5 illustrates a physical schematic diagram of an electronic device, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. The processor 510 may invoke logic instructions in the memory 530 to execute a method of shear wall design based on graph node classification graph neural networks, the method comprising: obtaining a target building plane design drawing to be processed; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map.

Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of executing the method for designing a shear wall based on a graph node class graph neural network provided by the above methods, comprising: obtaining a target building plane design drawing to be processed; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map.

In yet another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the above-provided method for designing a shear wall based on a graph node class graph neural network, the method comprising: obtaining a target building plane design drawing to be processed; the target building plane design drawing to be processed is expressed into a map format formed by map nodes and map edges; wherein, the graph nodes represent key elements, and the graph edges represent the connection relations of the key element graph nodes; extracting the characteristics of graph nodes and graph edges in the graph to form building plane graph characteristics to be input; inputting the building plane map features to be input into a map node classification map neural network model of a pre-constructed shear wall design to obtain a shear wall design map; the map node classification map neural network model of the shear wall design is obtained by training based on building plane map sample data and pre-calibrated shear wall design map sample data; and obtaining a shear wall design result based on the shear wall design map.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The shear wall design method based on the graph node classification graph neural network is characterized by comprising the following steps of:

obtaining a target building plane design drawing to be processed;

and obtaining a shear wall design result based on the shear wall design map.

2. The shear wall design method based on the graph node classification graph neural network according to claim 1, wherein the target building plane design drawing to be processed is represented as a graph format formed by graph nodes and graph edges, and specifically comprises:

3. The method for designing the shear wall based on the graph node classification graph neural network according to claim 2, wherein extracting the characteristics of graph nodes and graph edges in the graph to form the building plane graph characteristics to be input comprises the following steps:

the graph edge feature comprises: category of the drawing edge;

4. The method for designing the shear wall based on the graph node classification graph neural network according to claim 1, wherein the shear wall design result is obtained based on the shear wall design map, and the method specifically comprises the following steps:

5. The method for designing the shear wall based on the graph node classification graph neural network according to claim 1, wherein the method for creating the graph node classification graph neural network model of the shear wall design based on the building plane graph sample data and the pre-calibrated shear wall design graph sample data specifically comprises the following steps:

6. The method for designing the shear wall based on the graph node classification graph neural network according to claim 5, wherein the test result is evaluated to obtain a comprehensive evaluation index of the shear wall design, and the method specifically comprises the following steps:

physical evaluation index Score by structural mechanics analysis _Physics And shear wall design patternIndex Score for evaluating spectrum data of symptom similarity _Graph Structure comprehensive evaluation index Score for weighting shear wall design _ShearWall Structural comprehensive evaluation index Score of shear wall design _ShearWall The calculation formula of (2) is as follows:

Score _ShearWall ＝(η _Graph ×Score _Graph +η _Physics ×Score _Physics )

Score _Physics ＝(η _Drift ×Score _Drift +η _slab ×Score _slab )

the shear wall design spectrum feature similarity spectrum data evaluation index Score _Graph Is used for obtaining the corresponding generated shear wall design pattern test result based on the building plane pattern test data and the pre-calibrated shear wall design pattern test dataGraph node class similarity; calculating confusion matrixes of graph nodes of which the categories are predicted to be the structural shear wall and the non-structural filling wall in the generated shear wall design graph test results corresponding to the building plane graph test data and graph nodes of which the categories are the structural shear wall and the non-structural filling wall in the pre-calibrated shear wall design graph test data;

Score _Graph ＝2×SS/(2×SS+SF+FS)。

7. the method for designing a shear wall based on a graph node classification graph neural network according to claim 5, wherein the loss function of the graph node classification graph neural network model training of the shear wall design is:

8. Shear wall design device based on map node classification map neural network, characterized by comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, performs the steps of the method for designing a shear wall based on graph node classification graph neural network as claimed in any one of claims 1 to 7.

10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the graph node classification graph neural network-based shear wall design method of any one of claims 1 to 7.