Architectural style design method, device and equipment

Abstract

The present invention provides an architectural style design method, device and equipment, which relate to the field of computer information processing technology. The method comprises: obtaining architectural parameter data input by a user; extracting feature data from the architectural parameter data to obtain feature quantities; inputting the feature quantities into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it. The solution of the present invention improves design efficiency, reduces design costs, and can provide highly customized architectural design to meet the unique needs of different customers.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information processing, and in particular to an architectural style design method, device and equipment. Background Art

[0002] Currently, the architectural design process mostly relies on the experience and creativity of human architects, as well as some auxiliary design software, which mainly provides engineering drawing and modeling functions, but has limited ability to automatically generate innovative and personalized architectural styles.

[0003] Relying on manual design is not only time-consuming and labor-intensive, but also difficult to quickly adapt to changing market demands and personalized design requirements. In addition, existing design software has limited functions in generating ideas and is difficult to provide highly innovative and diverse architectural style solutions. Summary of the invention

[0004] The present invention provides an architectural style design method, device and equipment to solve the problem.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] An architectural style design method, comprising:

[0007] Get the building parameter data input by the user;

[0008] Extracting characteristic data from the building parameter data to obtain characteristic quantities;

[0009] The characteristic quantity is input into the architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it; wherein the architectural style design model is obtained by training a preset model according to an observation set and a characteristic quantity set of historical architectural style designs.

[0010] Optionally, feature data is extracted from the building parameter data to obtain feature quantities, including:

[0011] When the building parameter data is a line drawing, extracting picture feature data in the building parameter data to obtain a first feature value;

[0012] When the building parameter data is text information, the building type feature data in the building parameter data is extracted to obtain a second feature value.

[0013] Optionally, the feature quantity is input into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it, including:

[0014] The architectural style design model generates, based on the first feature value, an architectural style design drawing having the same style features as the first feature value, and outputs the drawing;

[0015] The architectural style design model generates, based on the second feature value, architectural style design drawings having a plurality of different style features of the same building type as the second feature value, and outputs the drawings.

[0016] Optionally, the feature quantity is input into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it, further comprising:

[0017] The architectural style design drawing is updated in real time according to the real-time adjustment parameter data input by the user.

[0018] Optionally, the architectural style design model is obtained by training a preset model according to an observation set and a feature set of historical architectural style designs, including:

[0019] Obtaining an observation set and a set of feature quantities of historical architectural style design, wherein the observation set is generated by a generator of a preset model;

[0020] Mixing the observation set and the feature quantity set of the historical architectural style design and inputting them into the discriminator of the preset model;

[0021] The discriminator of the preset model distinguishes the observation set and the feature quantity set, and outputs evaluation values ​​for the observation set and the feature quantity set;

[0022] Iteratively update the first network weight of the discriminator of the preset model, and when the evaluation value output of the observation set is 0 and the evaluation value output of the feature quantity set is 1, obtain the discriminator of the architectural style design model.

[0023] Optionally, the architectural style design model is obtained by training a preset model according to an observation set and a set of characteristic quantities of historical architectural style design, and further includes:

[0024] Inputting the observation set into the discriminator of the preset model;

[0025] Iteratively updating the second network weights of the generator of the preset model according to the evaluation value output by the discriminator of the preset model;

[0026] When the evaluation value output of the discriminator of the preset model is 1, the iteration is terminated to obtain a generator of the architectural style design model.

[0027] Optionally, the set of characteristic quantities of the historical architectural style design includes:

[0028] Obtain historical architectural style design data;

[0029] Preprocessing the historical architectural style design data to identify and remove outliers, duplicate data and irrelevant information in the historical architectural style design data;

[0030] Converting the preprocessed historical architectural style design data into a preset format image;

[0031] A description tag is added to the preset format image to obtain a set of feature quantities of historical architectural style design data.

[0032] The present invention also provides an architectural style design device, comprising:

[0033] An acquisition module is used to obtain the building parameter data input by the user;

[0034] The processing module is used to extract feature data from the building parameter data to obtain feature quantities; input the feature quantities into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it; wherein the architectural style design model is obtained by training a preset model based on an observation set and a feature quantity set of historical architectural style designs.

[0035] The present invention also provides a computing device, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed.

[0036] The present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above.

[0037] The above solution of the present invention includes at least the following beneficial effects:

[0038] The above solution of the present invention obtains architectural parameter data input by the user; extracts feature data from the architectural parameter data to obtain feature quantities; inputs the feature quantities into the architectural style design model to perform architectural style design, obtains architectural style design drawings, and outputs them. This not only speeds up the design process, but also ensures the quality and innovation of the design solution, avoids the duplication and limitations that may occur in human design, and improves design efficiency and quality. It can provide highly customized architectural design to meet the unique needs of different customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of an architectural style design method provided by an embodiment of the present invention;

[0040] Figure 2 It is a module schematic diagram of the architectural style design device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0042] like Figure 1 As shown, an embodiment of the present invention provides an architectural style design method, comprising:

[0043] Step 11, obtaining the building parameter data input by the user;

[0044] Step 12, extracting characteristic data from the building parameter data to obtain characteristic quantities;

[0045] Step 13, input the feature quantity into the architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it; wherein the architectural style design model is obtained by training a preset model based on the observation set and the feature quantity set of historical architectural style design.

[0046] In this embodiment, the architectural parameter data input by the user includes text information and picture information of text description. Furthermore, based on the parameters and requirements required for architectural style design, the architectural parameter data input by the user is analyzed and processed, and descriptive keywords such as building type, architectural style, functional requirements, etc. in the text information of the architectural parameter data and simple line drafts in the picture information are extracted as feature quantities, wherein the building types include residential buildings, commercial buildings, industrial buildings, educational buildings, medical buildings, religious buildings, entertainment and sports buildings, etc.; architectural style features include classicism, Romanesque architecture, Gothic architecture, Baroque style, neoclassicism, academic architecture, Art Nouveau style, Art Deco style, Bauhaus style, modernism, postmodernism, deconstructionism, etc.; functional requirements include safety, durability, comfort, accessibility, functionality, privacy, environmental adaptability, flexibility, aesthetics, economy, etc.

[0047] Furthermore, the feature quantity is input into the architectural style design model, and the architectural style design model generates multiple design schemes at one time based on the input feature quantity, and outputs the architectural style design drawing.

[0048] Here, the architectural style design model is obtained by training the preset model based on the observation set and the feature quantity set of the historical architectural style design. Preferably, the preset model can use a generative adversarial network; the generative adversarial network consists of two parts: a generator and a discriminator. The generator is responsible for generating new data, and the discriminator is responsible for distinguishing between real data and generated data. Through competitive training, the two continuously improve the quality and authenticity of the generated data, and can generate high-quality architectural design drawings.

[0049] In this embodiment, the architectural parameter data input by the user is obtained; the feature data of the architectural parameter data is extracted to obtain the feature quantity; the feature quantity is input into the architectural style design model to perform architectural style design, and the architectural style design drawing is obtained and output. This not only speeds up the design, but also ensures the quality and innovation of the design scheme, avoids the duplication and limitations that may occur in human design, and improves the design efficiency and quality. It can provide highly customized architectural design to meet the unique needs of different customers.

[0050] In an optional embodiment of the present invention, step 12 may include:

[0051] Step 121, when the building parameter data is a line drawing, extracting picture feature data in the building parameter data to obtain a first feature value;

[0052] Step 122: When the building parameter data is text information, extract the building type feature data in the building parameter data to obtain a second feature value.

[0053] In this embodiment, when the architectural parameter data provided by the user is a line drawing, the line drawing is identified and the basic elements such as lines, shapes, structures, and the spatial relationships between them are analyzed. The architectural style expected by the user (such as classical, modern, Gothic, etc.) is analyzed based on the style characteristics of the line drawing, and the basic elements, spatial relationships, and style characteristics of the line drawing are used as feature data to obtain a first feature value;

[0054] When the architectural parameter data provided by the user is only text information and no line drawing is provided, the text description will be parsed first to understand the keywords, concepts, spatial relationships and other information contained therein (such as building type, architectural style and functional requirements, etc.), and the keywords, concepts, spatial relationships and other information will be used as feature data to obtain the second feature quantity.

[0055] In an optional embodiment of the present invention, step 13 may include:

[0056] Step 131, the architectural style design model generates an architectural style design drawing having the same style characteristics as the first feature value according to the first feature value, and outputs the drawing;

[0057] Step 132: the architectural style design model generates, based on the second feature value, architectural style design drawings having a plurality of different style features of the same building type as the second feature value, and outputs the drawings.

[0058] In this embodiment, the feature quantity is input into the architectural style design model:

[0059] When the user provides a line drawing, the first feature quantity is input into the architectural style design model. After identifying the content and style requirements of the line drawing, the architectural style design model applies the style transfer technology to fix the basic layout of the image to be generated, and further optimizes the details in the image, such as texture, light and shadow effects, etc., to generate an architectural image that conforms to the line drawing layout and has a specific style.

[0060] When the user does not provide a line drawing but provides text information, the second feature value is input into the architectural style design model. The architectural style design model conceives possible architectural shapes, structures, layouts, etc. based on the keywords, concepts, spatial relationships and other information in the second feature value, and then uses image generation technology to randomly generate corresponding architectural pictures based on the text information provided by the user.

[0061] In an optional embodiment of the present invention, step 13 further includes:

[0062] Step 133: updating the architectural style design drawing in real time according to the real-time adjustment parameter data input by the user.

[0063] In this embodiment, the architectural style design model can generate multiple design schemes at one time according to the input feature quantity, and the user can also adjust and optimize the generated design, such as increasing the clarity, cropping, etc.

[0064] Users can adjust parameters (descriptors, resolution, style type, etc.) and view the effects in real time during the design process to improve design efficiency.

[0065] Users can also evaluate and provide feedback on the generated solutions, and the model will be optimized and iterated based on the feedback until user needs are met.

[0066] In an optional embodiment of the present invention, in step 13, the process of training and obtaining the architectural style design model includes:

[0067] Step 134, obtaining an observation set and a set of feature quantities of historical architectural style design, wherein the observation set is generated by a generator of a preset model;

[0068] Step 135, mixing the observation set and the feature quantity set of the historical architectural style design into the discriminator of the preset model;

[0069] Step 136, the discriminator of the preset model distinguishes the observation set and the feature quantity set, and outputs evaluation values ​​for the observation set and the feature quantity set;

[0070] Step 137, iteratively update the first network weight of the discriminator of the preset model, when the evaluation value output of the observation set is 0 and the evaluation value output of the feature value set is 1, the discriminator of the architectural style design model is obtained.

[0071] In this embodiment, the observation set is generated by a generator of a preset model, and the feature quantity set of historical architectural style design is obtained by collecting real landscapes and design cases of various architectural styles and processing the data.

[0072] The architectural style design model is shown below:

[0073]

[0074] Among them, D is the discriminator, G is the generator, A set of characteristic quantities designed for historical architectural styles, x~P data (x) is the distribution of x that follows the feature set, x is the image data in the feature set, D(x) is the output of the discriminator, which is a number between 0 and 1, is a random image generated by the generator, i.e., the observation set, z~P z (z) is the distribution of z obeying the observation set, z is the image data in the observation set, and G(z) is the output of the generator.

[0075] In this embodiment, the discriminator D is iteratively optimized to optimize the discriminator D so that and The value of is the largest.

[0076] Here the model is rewritten as

[0077]

[0078] Input the feature set and observation set into the architectural style design model, record the evaluation value of the discriminator D on the feature set and observation set, and update the network weight of the discriminator D, that is, update the following function:

[0079]

[0080] Where N is the number of samples, is the model's evaluation value for the observation set, x i is the evaluation value of the feature set;

[0081] Make logD(x) as large as possible, that is, D(x) as large as possible. At this time, when the input is a feature set, the output of the discriminator D is close to 1; then log(1-D(G(z))) is as large as possible, that is, 1-D(G(z)) is as large as possible, that is, D(G(z)) is as small as possible. At this time, when the input is an observation set, the output of the discriminator D is close to 0. At this point, the iterative optimization of the discriminator D is completed, and the discriminator of the architectural style design model is obtained.

[0082] In an optional embodiment of the present invention, in step 13, the process of training and obtaining the architectural style design model further includes:

[0083] Step 138, inputting the observation set into the discriminator of the preset model;

[0084] Step 139, iteratively updating the second network weights of the generator of the preset model according to the evaluation value output by the discriminator of the preset model;

[0085] Step 1310: When the evaluation value output of the discriminator of the preset model is 1, the iteration is terminated to obtain a generator of the architectural style design model.

[0086] In this embodiment, the generator G is iteratively optimized. First, the model is rewritten as

[0087]

[0088] The observation set is continuously updated through the generator G, and the observation set is input into the architectural style design model, and the output result of the discriminator D is recorded; the gradient descent method is used Update the learning rate η of the generator G;

[0089] When the output result of the discriminator D is close to 1, the iterative optimization is completed and the generator of the architectural style design model is obtained.

[0090] In an optional embodiment of the present invention, the characteristic quantity set of the historical architectural style design includes:

[0091] Obtain historical architectural style design data;

[0092] Preprocessing the historical architectural style design data to identify and remove outliers, duplicate data and irrelevant information in the historical architectural style design data;

[0093] Converting the preprocessed historical architectural style design data into a preset format image;

[0094] A description tag is added to the preset format image to obtain a set of feature quantities of historical architectural style design data.

[0095] In this embodiment, real landscapes and design cases of various architectural styles are first collected, and the collected data are preprocessed to identify and remove outliers, duplicate data, and irrelevant information in the data set. Useful data includes: architectural floor plans and 3D model drawings. Outliers include: images of abnormal size, low image clarity, and too many interfering architectural factors. Duplicate data refers to duplicate image files, and irrelevant information refers to non-architectural images. Then all images are converted to a unified format (such as JPEG or PNG) and resized to a standard resolution (512×512). One or more tags are assigned to each image, which describe the architectural style of the image or the design elements it contains.

[0096] The architectural style design method described in the above embodiment of the present invention not only speeds up the design process, but also ensures the quality and innovation of the design solution, and avoids the duplication and limitations that may occur in manual design.

[0097] Ability to innovate and expand existing designs, and even create entirely new architectural styles, bringing unprecedented innovation momentum to the field of architectural design;

[0098] By deeply learning the specific needs and preferences of users, we can provide highly customized architectural designs to meet the unique needs of different customers and provide highly personalized design solutions.

[0099] The embodiment of the present invention further provides an architectural style design device 20, comprising:

[0100] An acquisition module 21 is used to acquire building parameter data input by a user;

[0101] The processing module 22 is used to extract feature data from the building parameter data to obtain feature quantities; input the feature quantities into the architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it; wherein the architectural style design model is obtained by training a preset model based on an observation set and a set of feature quantities of historical architectural style designs.

[0102] Optionally, feature data is extracted from the building parameter data to obtain feature quantities, including:

[0103] When the building parameter data is a line drawing, extracting picture feature data in the building parameter data to obtain a first feature value;

[0104] When the building parameter data is text information, the building type feature data in the building parameter data is extracted to obtain a second feature value.

[0105] Optionally, the feature quantity is input into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it, including:

[0106] The architectural style design model generates, based on the first feature value, an architectural style design drawing having the same style features as the first feature value, and outputs the drawing;

[0107] The architectural style design model generates, based on the second feature value, architectural style design drawings having a plurality of different style features of the same building type as the second feature value, and outputs the drawings.

[0108] Optionally, the feature quantity is input into an architectural style design model to perform architectural style design, obtain an architectural style design drawing, and output it, further comprising:

[0109] The architectural style design drawing is updated in real time according to the real-time adjustment parameter data input by the user.

[0110] Optionally, the architectural style design model is obtained by training a preset model according to an observation set and a feature set of historical architectural style designs, including:

[0111] Obtaining an observation set and a set of feature quantities of historical architectural style design, wherein the observation set is generated by a generator of a preset model;

[0112] Mixing the observation set and the feature quantity set of the historical architectural style design and inputting them into the discriminator of the preset model;

[0113] The discriminator of the preset model distinguishes the observation set and the feature quantity set, and outputs evaluation values ​​for the observation set and the feature quantity set;

[0114] Iteratively update the first network weight of the discriminator of the preset model, and when the evaluation value output of the observation set is 0 and the evaluation value output of the feature quantity set is 1, obtain the discriminator of the architectural style design model.

[0115] Optionally, the architectural style design model is obtained by training a preset model according to an observation set and a set of characteristic quantities of historical architectural style design, and further includes:

[0116] Inputting the observation set into the discriminator of the preset model;

[0117] Iteratively updating the second network weights of the generator of the preset model according to the evaluation value output by the discriminator of the preset model;

[0118] When the evaluation value output of the discriminator of the preset model is 1, the iteration is terminated to obtain a generator of the architectural style design model.

[0119] Optionally, the set of characteristic quantities of the historical architectural style design includes:

[0120] Obtain historical architectural style design data;

[0121] Preprocessing the historical architectural style design data to identify and remove outliers, duplicate data and irrelevant information in the historical architectural style design data;

[0122] Converting the preprocessed historical architectural style design data into a preset format image;

[0123] A description tag is added to the preset format image to obtain a set of feature quantities of historical architectural style design data.

[0124] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects.

[0125] The embodiment of the present invention further provides a computing device, including: a processor, a memory storing a computer program, and when the computer program is executed by the processor, the method described in the above embodiment is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0126] In an embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions, and when the instructions are executed on a computer, the computer executes the method described in the above embodiment. All implementations in the above method embodiment are applicable to this embodiment, and can also achieve the same technical effect.

[0127] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0129] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0132] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0133] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0134] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0135] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for designing an architectural style, characterized in that: include: Get the building parameter data input by the user; Extracting characteristic data from the building parameter data to obtain characteristic quantities; Inputting the characteristic quantity into the architectural style design model to perform architectural style design, obtaining an architectural style design drawing, and outputting the drawing; wherein the architectural style design model is obtained by training a preset model according to an observation set and a characteristic quantity set of historical architectural style designs; The training process of the architectural style design model includes: Obtaining an observation set and a set of feature quantities of historical architectural style design, wherein the observation set is generated by a generator of a preset model; Mixing the observation set and the feature quantity set of the historical architectural style design and inputting them into the discriminator of the preset model; The discriminator of the preset model distinguishes the observation set and the feature quantity set, and outputs evaluation values ​​for the observation set and the feature quantity set; Iteratively updating the first network weight of the discriminator of the preset model, when the evaluation value output of the observation set is 0 and the evaluation value output of the feature value set is 1, obtaining the discriminator of the architectural style design model; Inputting the observation set into the discriminator of the preset model; Iteratively updating the second network weights of the generator of the preset model according to the evaluation value output by the discriminator of the preset model; When the evaluation value output of the discriminator of the preset model is 1, the iteration is terminated to obtain a generator of the architectural style design model.

2. The architectural style design method according to claim 1, characterized in that: Extracting characteristic data from the building parameter data to obtain characteristic quantities includes: When the building parameter data is a line drawing, extracting picture feature data in the building parameter data to obtain a first feature value; When the building parameter data is text information, the building type feature data in the building parameter data is extracted to obtain a second feature value.

3. The architectural style design method according to claim 2, characterized in that: Inputting the feature quantity into the architectural style design model to perform architectural style design, obtaining an architectural style design drawing, and outputting the drawing, including: The architectural style design model generates, based on the first feature value, an architectural style design drawing having the same style features as the first feature value, and outputs the drawing; The architectural style design model generates, based on the second feature value, architectural style design drawings having a plurality of different style features of the same building type as the second feature value, and outputs the drawings.

4. The architectural style design method according to claim 1, characterized in that: Inputting the feature quantity into the architectural style design model to perform architectural style design, obtaining an architectural style design drawing, and outputting the drawing, further comprising: The architectural style design drawing is updated in real time according to the real-time adjustment parameter data input by the user.

5. The architectural style design method according to claim 1, characterized in that: The characteristic quantity set of the historical architectural style design includes: Obtain historical architectural style design data; Preprocessing the historical architectural style design data to identify and remove outliers, duplicate data and irrelevant information in the historical architectural style design data; Converting the preprocessed historical architectural style design data into a preset format image; A description tag is added to the preset format image to obtain a set of feature quantities of historical architectural style design data.

6. An architectural style design device, characterized in that: include: An acquisition module is used to obtain the building parameter data input by the user; A processing module, used for extracting characteristic data from the building parameter data to obtain characteristic quantities; Inputting the characteristic quantity into the architectural style design model to perform architectural style design, obtaining an architectural style design drawing, and outputting the drawing; wherein the architectural style design model is obtained by training a preset model according to an observation set and a characteristic quantity set of historical architectural style designs; The training process of the architectural style design model includes: Obtaining an observation set and a set of feature quantities of historical architectural style design, wherein the observation set is generated by a generator of a preset model; Mixing the observation set and the feature quantity set of the historical architectural style design and inputting them into the discriminator of the preset model; The discriminator of the preset model distinguishes the observation set and the feature quantity set, and outputs evaluation values ​​for the observation set and the feature quantity set; Iteratively updating the first network weight of the discriminator of the preset model, when the evaluation value output of the observation set is 0 and the evaluation value output of the feature value set is 1, obtaining the discriminator of the architectural style design model; Inputting the observation set into the discriminator of the preset model; Iteratively updating the second network weights of the generator of the preset model according to the evaluation value output by the discriminator of the preset model; When the evaluation value output of the discriminator of the preset model is 1, the iteration is terminated to obtain a generator of the architectural style design model.

7. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 5 is performed.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 5.

Images