Municipal green building design optimization method

Abstract

The invention relates to the field of green building design, and particularly discloses a municipal green building design optimization method, which comprises the following steps of: firstly, extracting geographic position information from municipal green building design condition information input by a user, and obtaining a target area aerial view from a GIS (Geographic Information System) according to the geographic position information; further introducing an image processing technology based on deep learning to perform multi-scale feature extraction on the aerial view of the target area to capture geographic features of the target building area, and performing semantic analysis on budget limitation, function requirements, environment requirements, time frames and other information input by a user by using a natural language processing technology; and attention modulation is carried out on the geographic features of the target building area as design constraint conditions, so that the geographic features of the building area and the design constraint conditions are comprehensively considered, and a municipal green building design sketch is intelligently generated. According to the method, the design efficiency of municipal green buildings can be remarkably improved, the design period is shortened, and the innovativeness and quality of design achievements are ensured.

Description

Technical Field

[0001] The present application relates to the technical field of green building design, and more specifically, to a municipal green building design optimization method. Background Art

[0002] With the acceleration of urbanization, municipal buildings, as an important part of urban infrastructure, must not only meet the needs of functionality and aesthetics, but also put forward higher requirements in terms of environmental protection and sustainability. As an important part of sustainable development, the design optimization of municipal green buildings has become a research hotspot in the field of urban planning and construction. Green buildings aim to achieve harmonious coexistence between man and nature by efficiently utilizing resources, reducing environmental pollution and ecological damage, and providing a healthy and comfortable living and working environment.

[0003] However, traditional municipal building design methods often rely on the designer's experience and manual drawing, which is not only inefficient, but also difficult to ensure the quality and innovation of the design when faced with complex design requirements and diverse geographical environments. In addition, since the manual drawing process is time-consuming and laborious, it takes many repeated revisions from the initial conception to the final draft, which increases the project cost and time investment.

[0004] Therefore, an intelligent municipal green building design optimization method is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a municipal green building design optimization method, which first extracts geographic location information from the municipal green building design condition information input by the user, and obtains a bird's-eye view of the target area from the GIS system based on this. Then, the image processing technology based on deep learning is further introduced to perform multi-scale feature extraction on the bird's-eye view of the target area to capture the geographic characteristics of the target building area. At the same time, natural language processing technology is used to perform semantic analysis on the budget constraints, functional requirements, environmental requirements, and time frames input by the user, and this is used as a design constraint to modulate the attention of the geographic characteristics of the target building area, so as to comprehensively consider the geographic characteristics of the building area and the design constraints, and intelligently generate a municipal green building design sketch. This can significantly improve the design efficiency of municipal green buildings, shorten the design cycle, and ensure the innovation and quality of the design results.

[0006] According to one aspect of the present application, a municipal green building design optimization method is provided, which includes: Obtaining municipal green building design conditions input by a user, wherein the municipal green building design conditions include geographical location, budget constraints, functional requirements, environmental requirements, and time frame; Extracting a geographic location from the municipal green building design conditions, and extracting a bird's-eye view of a target area from a GIS system based on the geographic location; Extracting geographic features from the bird's-eye view of the target area to obtain a multi-scale coded feature map of geographic features of the building area; Performing semantic joint coding on the municipal green building design conditions to obtain a semantic cascade coding vector of design constraint conditions; Performing cross-domain joint encoding based on fine-grained ablation on the multi-scale encoding feature map of the building area geographic features and the semantic cascade encoding vector of the design constraints to obtain a cross-modal ablation encoding feature map of the building area geographic features-design constraints; Based on the cross-modal ablation coding feature map of the building area's geographical features and design constraints, a municipal green building design sketch is generated.

[0007] Preferably, geographic features are extracted from the bird's-eye view of the target area to obtain a multi-scale coded feature map of the geographic features of the building area, including: inputting the bird's-eye view of the target area into a building area geographic feature extractor based on the CrossViT model to obtain the multi-scale coded feature map of the geographic features of the building area.

[0008] Preferably, the municipal green building design conditions are semantically jointly encoded to obtain a semantic cascade coding vector of design constraints, including: extracting the budget constraint, the functional requirements, the environmental requirements and the time frame from the municipal green building design conditions, and semantically encoding the budget constraint, the functional requirements, the environmental requirements and the time frame respectively to obtain a budget constraint semantic coding vector, a functional requirement semantic coding vector, an environmental requirement semantic coding vector and a time frame semantic coding vector; cascading the budget constraint semantic coding vector, the functional requirement semantic coding vector, the environmental requirement semantic coding vector and the time frame semantic coding vector to obtain the design constraint semantic cascade coding vector.

[0009] Preferably, the budget constraint, the functional requirements, the environmental requirements and the time frame are semantically encoded respectively to obtain a budget constraint semantic encoding vector, a functional requirement semantic encoding vector, an environmental requirement semantic encoding vector and a time frame semantic encoding vector, including: using a semantic encoder based on a Bert model to semantically encode the budget constraint, the functional requirements, the environmental requirements and the time frame respectively to obtain the budget constraint semantic encoding vector, the functional requirement semantic encoding vector, the environmental requirement semantic encoding vector and the time frame semantic encoding vector.

[0010] Preferably, the multi-scale coding feature map of the building area's geographic features and the semantic cascade coding vector of the design constraints are cross-domain jointly coded based on fine-grained ablation to obtain a cross-modal ablation coding feature map of the building area's geographic features and design constraints, including: performing fine-grained feature decoupling along the channel dimension on the multi-scale coding feature map of the building area's geographic features to obtain a set of multi-scale coding feature matrices of the building area's geographic features; performing correlation strength ablation measurement on each multi-scale coding feature matrix of the building area's geographic features in the set of the semantic cascade coding vector of the design constraints and the multi-scale coding feature matrix of the building area's geographic features to obtain a set of fine-grained ablation factors of the building area's geographic features and design constraints; based on the set of fine-grained ablation factors of the building area's geographic features and design constraints, performing fine-grained ablation modulation aggregation on the set of multi-scale coding feature matrices of the building area's geographic features to obtain the cross-modal ablation coding feature map of the building area's geographic features and design constraints.

[0011] Preferably, the association strength ablation measurement is performed on each building area geographic feature multi-scale coding feature matrix in the set of the design constraint semantic cascade coding vector and the building area geographic feature multi-scale coding feature matrix to obtain a set of building area geographic feature-design constraint fine-grained ablation factors, including: performing cross-domain query interaction based on the attention mechanism on each building area geographic feature multi-scale coding feature matrix in the set of the design constraint semantic cascade coding vector and the building area geographic feature multi-scale coding feature matrix to obtain a set of building area geographic feature-design constraint cross-domain query interaction feature vectors; and inputting each building area geographic feature-design constraint cross-domain query interaction feature vector in the set of building area geographic feature-design constraint cross-domain query interaction feature vectors into the ablation measurement function respectively to obtain the set of building area geographic feature-design constraint fine-grained ablation factors.

[0012] Preferably, a cross-domain query interaction based on an attention mechanism is performed on each multi-scale coding feature matrix of building area geographic features in the set of the design constraint semantic cascade coding vector and the multi-scale coding feature matrix of building area geographic features to obtain a set of building area geographic features-design constraint cross-domain query interaction feature vectors, including: linearly transforming the design constraint semantic cascade coding vector to obtain a query vector and a value vector; linearly transforming the multi-scale coding feature matrix of building area geographic features to obtain a key matrix; and inputting the query vector, the value vector and the key matrix into a cross-domain interaction encoder based on a simulated converter structure to obtain the building area geographic features-design constraint cross-domain query interaction feature vector.

[0013] Preferably, based on the set of fine-grained ablation factors of the building area's geographic features-design constraints, the set of multi-scale coding feature matrices of the building area's geographic features is subjected to fine-grained ablation modulation aggregation to obtain the building area's geographic features-design constraints cross-modal ablation coding feature map, including: inputting the set of fine-grained ablation factors of the building area's geographic features-design constraints into an ablation effect coding module containing a normalization function and a masking function to obtain a set of fine-grained ablation weight factors of the building area's geographic features-design constraints; based on the set of fine-grained ablation weight factors of the building area's geographic features-design constraints, weighted modulation is performed on the set of multi-scale coding feature matrices of the building area's geographic features to obtain a set of cross-modal ablation coding feature matrices of the building area's geographic features-design constraints; and feature aggregation is performed along the channel dimension on the set of cross-modal ablation coding feature matrices of the building area's geographic features-design constraints to obtain the building area's geographic features-design constraints cross-modal ablation coding feature map.

[0014] Preferably, a municipal green building design sketch is generated based on the cross-modal ablation coding feature map of the building area's geographical features and design constraints, including: inputting the cross-modal ablation coding feature map of the building area's geographical features and design constraints into a municipal green building design sketch generator based on a large model to obtain the municipal green building design sketch.

[0015] This application has at least the following technical effects: Compared with the prior art, the municipal green building design optimization method provided by this application first extracts geographic location information from the municipal green building design condition information input by the user, and obtains the bird's-eye view of the target area from the GIS system based on this information, and then further introduces deep learning-based image processing technology to perform multi-scale feature extraction on the bird's-eye view of the target area to capture the geographic characteristics of the target building area. At the same time, natural language processing technology is used to perform semantic analysis on the budget constraints, functional requirements, environmental requirements, and time frames input by the user, and this is used as a design constraint to modulate the attention of the geographic characteristics of the target building area, so as to comprehensively consider the geographic characteristics of the building area and the design constraints, and intelligently generate a municipal green building design sketch. This application can significantly improve the design efficiency of municipal green buildings, shorten the design cycle, and ensure the innovation and quality of the design results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flow chart of a municipal green building design optimization method according to an embodiment of the present application.

[0018] Figure 2 A data flow diagram of a municipal green building design optimization method according to an embodiment of the present application.

[0019] Figure 3 This is a flowchart of sub-step S4 of the municipal green building design optimization method according to an embodiment of the present application.

[0020] Figure 4 This is a flowchart of sub-step S5 of the municipal green building design optimization method according to an embodiment of the present application.

[0021] Figure 5 This is a flowchart of sub-step S52 of the municipal green building design optimization method according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0023] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0024] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0025] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0026] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0027] Specifically, Figure 1 It is a flow chart of a municipal green building design optimization method according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the municipal green building design optimization method according to the embodiment of the present application. Figure 1 and Figure 2 As shown, the municipal green building design optimization method includes the following steps: S1, obtaining the municipal green building design conditions input by the user, wherein the municipal green building design conditions include geographical location, budget constraints, functional requirements, environmental requirements and time frame; S2, extracting the geographical location from the municipal green building design conditions, and extracting a bird's-eye view of the target area from the GIS system based on the geographical location; S3, extracting geographical features from the bird's-eye view of the target area to obtain a multi-scale coded feature map of the geographical features of the building area; S4, semantically co-encoding the municipal green building design conditions to obtain a semantic cascade coding vector of design constraints; S5, cross-domain co-encoding the multi-scale coded feature map of the geographical features of the building area and the semantic cascade coding vector of the design constraints based on fine-grained ablation to obtain a cross-modal ablation coding feature map of the geographical features of the building area-design constraints; S6, generating a municipal green building design sketch based on the cross-modal ablation coding feature map of the geographical features of the building area-design constraints.

[0028] In the above municipal green building design optimization method, the step S1 obtains the municipal green building design conditions input by the user, and the municipal green building design conditions include geographical location, budget constraints, functional requirements, environmental requirements and time frame. It should be understood that geographical location, budget constraints, functional requirements, environmental requirements and time frame are key elements of municipal green building design, and jointly determine the direction and feasibility of municipal green building design. Among them, the geographical location determines the natural environment and geographical conditions that the building must adapt to; the budget constraint determines the economic feasibility of the design, which helps to rationally plan resource allocation; the functional requirements define the functional layout and use efficiency of the building, and can guide the specific design contents such as the spatial layout, streamline organization and equipment configuration of the building. For example, schools, hospitals or office buildings have different requirements for internal facilities and services; environmental requirements involve energy conservation and emission reduction targets, material selection standards, water resources management and other aspects; the time frame limits the time period of design and construction. By comprehensively obtaining the architectural design demand information of key aspects such as geographical location, budget constraints, functional requirements, environmental requirements and time frame, the overall requirements and goals of municipal green building design can be more accurately grasped. Then reduce design deviations caused by missing or inaccurate information and improve the fit between the design and user expectations.

[0029] Specifically, geographic location is one of the most basic and crucial information in the design of municipal green buildings. The natural and socio-economic conditions in different geographical regions vary significantly, which puts forward diverse requirements for building design. For example, buildings located in tropical areas need to consider adequate ventilation and shading measures to cope with the high temperature and high humidity climate; while in cold areas, thermal insulation design needs to be strengthened to reduce energy consumption. In addition, geographic location also involves many factors such as local cultural traditions and the availability of building materials, which have a profound impact on building design. When collecting geographic location information from users, it should be as specific as possible, including but not limited to the name of the city, specific blocks or lots, surrounding environmental characteristics (such as adjacent rivers, parks, etc.), and even more detailed to the specific coordinate range of the plot. Such information helps to fully understand the actual situation of the project site, thereby providing a solid foundation for the next step of work. At the same time, considering the importance of geological conditions to the safety of building structures, geological surveys may also be required to evaluate factors such as foundation bearing capacity and groundwater level to ensure the safety and stability of the building.

[0030] Budget constraints are an important consideration in the design of municipal green buildings. Reasonable budget planning not only ensures the smooth implementation of the project, but also improves the efficiency of fund use. Therefore, when collecting user input, it is crucial to clearly understand their willingness and ability to invest in the entire project and quantify it into a specific amount range. In addition to the total budget, it is also necessary to subdivide various expenses, such as land acquisition fees, planning and design fees, construction fees, equipment procurement fees, operation and maintenance fees, etc., in order to better control costs. In addition, budget constraints also play a decisive role in the selection and use of certain specific technical applications or materials in the architectural design process, such as high-performance energy-saving equipment, environmentally friendly building materials, etc. By obtaining the user's budget constraint information, the scheme design can be more targeted to ensure that the functional requirements are met while staying within the budget range.

[0031] Functional requirements reflect the basic expectations of users for the use of municipal green buildings, covering multiple levels such as spatial layout and facility configuration. When collecting this information, we must first clarify the main service objects of the building and their activity patterns. For example, office buildings may focus on the flexibility and intelligent management of office space; schools are more concerned with the setting of functional areas such as classrooms and laboratories and safety performance requirements. Secondly, we need to have a deep understanding of the actual problems faced by users in their daily lives so that they can be solved through innovative design concepts, such as creating barrier-free passages and setting up humanized facilities such as mother-and-child rooms. In addition to the above conventional considerations, modern municipal green buildings also place special emphasis on the interactive relationship between man and nature, advocate the creation of open public spaces, and promote community exchanges and vitality. This means that sufficient green space and outdoor leisure places should be reserved during the design process so that residents can find a quiet and comfortable corner in the busy city life. In addition, with the development of science and technology, intelligent building systems have also become part of the functional requirements, such as smart homes, smart security, energy management systems, etc. Intelligent building systems can improve the convenience and safety of buildings, while also meeting the energy-saving and emission reduction goals of green buildings.

[0032] Environmental requirements reflect the sense of responsibility of municipal green buildings for environmental protection and ecological restoration. With the intensification of global climate change and the frequent occurrence of extreme weather events, how to improve the building's own resilience and reduce the impact on the external environment has become an urgent problem to be solved. To this end, users need to convey their expectations for energy conservation and emission reduction, water resource management, waste disposal, etc., in order to explore a set of best practices that can meet current development needs while taking into account long-term interests. For example, you can consider installing solar photovoltaic panels to increase the proportion of renewable energy; adopt rainwater collection systems for irrigation of green plants; or adopt low-carbon emission construction processes and technologies to reduce greenhouse gases generated during construction. In addition, protecting local biodiversity is also an important part that cannot be ignored. While trying to avoid destroying the original ecological environment, actively create microhabitats that are conducive to the growth and reproduction of animals and plants. On this basis, you can also consider the impact of buildings on the surrounding microclimate, such as improving local climate conditions through vegetation coverage and permeable paving, so as to achieve harmonious coexistence between buildings and the environment.

[0033] Finally, there is the time frame, which is the construction cycle of the project. A clear timetable helps all parties coordinate the progress of work, ensure that all links are closely connected, and complete the tasks on time and with high quality. Usually, the time frame varies according to factors such as the size and complexity of the project, ranging from a few months to several years. Therefore, when collecting user input, it is important to confirm the key time nodes of each stage, such as the completion deadline of planning and design, the date of approval of construction permits, and the time of topping out the main structure. At the same time, it should also be noted that since the design of municipal green buildings involves many uncertain factors, such as delays in construction due to bad weather and cost overruns caused by rising raw material prices, a certain amount of flexibility should be left when making plans to allow appropriate adjustments to arrangements to cope with possible risks and challenges.

[0034] In the above-mentioned municipal green building design optimization method, the step S2 extracts the geographical location from the municipal green building design conditions, and extracts the bird's-eye view of the target area from the GIS system based on the geographical location. It should be understood that the present application takes into account that the geographical location is one of the important basic information for the design of municipal green buildings, which determines the natural environment in which the building is located, the surrounding transportation network, the distribution of infrastructure, and the relative position relationship with other functional areas of the city, and has a vital impact on the layout, orientation, appearance design, and integration with the surrounding environment of the building. Based on this, in order to accurately obtain the visualized geographic information of the target building area, the present application further utilizes the powerful spatial data management and query functions of the geographic information system (GIS), and according to the geographical location information provided by the user (such as latitude and longitude coordinates or specific address names), quickly locates and extracts the corresponding bird's-eye view of the target area in its database, so as to intuitively understand the actual situation of the building site, including the surrounding topography, the distribution of existing buildings, the direction of roads, etc. It should be understood that the GIS system can present geographic information in the real world in the form of maps, images, etc. through digital storage and processing of geographic spatial data, providing intuitive geographic spatial reference for subsequent design work, helping to fully consider the actual situation of the site in the early stage of design, optimize the layout and form design of the building, and improve the coordination between the building and the surrounding environment. At the same time, it also provides the original image data basis for the subsequent design sketch generation.

[0035] Specifically, first, ensure that the geographic location information is accurately extracted from the municipal green building design conditions provided by the user. This includes but is not limited to the name of the city, specific blocks or lots, surrounding environmental features (such as adjacent rivers, parks, etc.), and even more detailed to the specific coordinate range of the plot. In order to ensure the accuracy of the information, all documents and materials submitted by the user can be carefully reviewed to screen out information related to the geographic location; at the same time, face-to-face or remote meetings can be held with the user to discuss the details of the geographic location in depth, clarify any ambiguities, and ensure a clear understanding of the project location. Then, with the help of online map services (such as Google Maps, Bing Maps) or specialized geographic information system software (such as ArcGIS Online), the specific location can be quickly located according to the address or description provided by the user, and marked for further analysis. Considering the importance of geological conditions to the safety of building structures, in some cases, professional geological surveys are required to evaluate factors such as foundation bearing capacity and groundwater level to ensure the safety and stability of the building. For some special projects, more background information may need to be collected, such as the scope of historical site protection and the boundaries of nature reserves, to avoid potential legal risks.

[0036] After determining the location of the project, the next step is to use a geographic information system (GIS) to extract a bird's-eye view of the area. GIS is a powerful tool that can integrate spatial data from different sources and provide a visual interface for users to intuitively view and analyze this information. It is crucial to choose the right GIS platform. There are many mature GIS platforms available on the market, such as Esri's ArcGIS, QGIS open source platform, etc. Choose the most suitable tool based on project requirements and personal preferences. Most GIS platforms will be pre-installed with commonly used basic map layers, such as satellite imagery, street maps, etc. If the platform's default map layer does not meet the accuracy requirements, you can obtain higher resolution image data by accessing third-party API interfaces (such as Google EarthEngine, Microsoft Bing Maps API). You can also contact relevant institutions to apply for downloading high-precision DEM (digital elevation model), DOM (digital orthophoto map) and other datasets as supplements.

[0037] Based on the previously extracted geographic location information, a reasonable rectangular or polygonal boundary is delineated on the GIS platform to limit the scope of the target area. This boundary should cover all factors that may affect the architectural design as much as possible, while not being too broad to increase unnecessary computational burden. Various thematic layers are superimposed on the base map, such as land use type, vegetation distribution, transportation network, public facilities layout, etc. In addition, buildings located near transportation hubs need to take special consideration of crowd evacuation. Modern GIS technology can not only present two-dimensional plane images, but also build realistic three-dimensional scenes. By processing DEM data, the terrain undulations of the target area can be obtained; combined with the building outline and height information, a complete three-dimensional urban model can be created, allowing the computer to more intuitively feel the spatial relationship of the building area. The last step is to export the processed data into a high-quality bird's-eye view that meets the design requirements. Most GIS platforms support multiple formats for output, such as JPEG, PNG, TIFF, etc. Adjust parameters such as image resolution and color mode according to actual needs to ensure that the final result is both beautiful and practical. During the export process, attention should be paid to protecting personal privacy and sensitive information to avoid leaking unnecessary content.

[0038] In the above-mentioned municipal green building design optimization method, the step S3 extracts geographic features from the bird's-eye view of the target area to obtain a multi-scale coded feature map of the geographic features of the building area. In a specific example of the present application, the step S3 includes: inputting the bird's-eye view of the target area into a building area geographic feature extractor based on the CrossViT model to obtain a multi-scale coded feature map of the geographic features of the building area. Specifically, considering that the bird's-eye view of the target area contains rich geographic information of different scales, such as the overall topography, building distribution, local vegetation coverage, etc. Therefore, in order to fully capture the geographic features of the target building area, the present application adopts the CrossViT model to extract multi-scale features from the bird's-eye view of the target area. The CrossViT model is a cross-attention multi-scale visual Transformer model for image feature extraction, which can effectively process multi-scale visual information in images. Specifically, the CrossViT model is based on a dual-branch transformer (Transformer) architecture, and processes the input image through parallel branches of different scales. In each branch, the bird's-eye view of the target area is first divided into a series of image blocks, which are then input into a multi-layer transformer encoder as a feature sequence after linear embedding transformation. The transformer encoder models the semantic association between the features of each image block through the self-attention mechanism, thereby capturing the feature information of the bird's-eye view of the target area at different scales. Finally, the geographic features extracted from branches of different scales are fused through a cross-scale feature fusion module to obtain a multi-scale encoding feature map of the geographic features of the building area containing multi-scale geographic feature information. In this way, rich geographic feature information from macroscopic topography to microscopic architectural texture can be effectively obtained, so as to better understand the site characteristics and integrate them into architectural design, realizing the organic combination of green buildings and geographical environment.

[0039] In the above municipal green building design optimization method, the step S4 performs semantic joint coding on the municipal green building design conditions to obtain a semantic cascade coding vector of design constraint conditions. Figure 3 Flow chart of sub-step S4 of the municipal green building design optimization method according to an embodiment of the present application. Figure 3As shown, the step S4 includes the steps of: S41, extracting the budget constraint, the functional requirements, the environmental requirements and the time frame from the municipal green building design conditions, and semantically encoding the budget constraint, the functional requirements, the environmental requirements and the time frame respectively to obtain a budget constraint semantic encoding vector, a functional requirement semantic encoding vector, an environmental requirement semantic encoding vector and a time frame semantic encoding vector; S42, cascading the budget constraint semantic encoding vector, the functional requirement semantic encoding vector, the environmental requirement semantic encoding vector and the time frame semantic encoding vector to obtain the design constraint semantic cascade encoding vector.

[0040] Specifically, in a specific example of the present application, the step S41 includes: using a semantic encoder based on the Bert model to semantically encode the budget limit, the functional requirements, the environmental requirements and the time frame to obtain the budget limit semantic encoding vector, the functional requirements semantic encoding vector, the environmental requirements semantic encoding vector and the time frame semantic encoding vector. It should be understood that since the information such as the budget limit, the functional requirements, the environmental requirements and the time frame is unstructured data input in the form of text, it is difficult for the computer to directly understand its inherent meaning and relationship. Therefore, the present application further semantically encodes the budget limit, the functional requirements, the environmental requirements and the time frame to convert the text information into a vector form that can be processed by the computer, so as to adjust and optimize the design scheme based on the quantitative constraints in the subsequent design process, ensuring that the design scheme not only meets the user's functional and environmental requirements, but also can be implemented within the budget and time constraints. It should be known to those of ordinary skill in the art that the Bert model, using its bidirectional Transformer architecture, can deeply understand the contextual semantics of the text, capture the complex relationship between words through a multi-layer neural network, and generate a high-dimensional vector representation rich in information. In the task of coding municipal green building design conditions, the Bert model is used to extract semantic features and vectorize the unstructured text descriptions of budget constraints, functional requirements, environmental requirements and time frames input by users, ensuring that each design condition is converted into a computable vector form and retains the core meaning of the original text, thereby providing an accurate and rich semantic basis for subsequent analysis.

[0041] Specifically, the step S42 cascades the budget constraint semantic coding vector, the functional requirement semantic coding vector, the environmental requirement semantic coding vector and the time frame semantic coding vector to obtain the design constraint semantic cascade coding vector. It should be understood that since the various design constraints (budget constraints, functional requirements, environmental requirements and time frames) are interrelated and mutually influential entities in the actual architectural design process. Therefore, the present application further cascades and fuses the budget constraint semantic coding vector, the functional requirement semantic coding vector, the environmental requirement semantic coding vector and the time frame semantic coding vector to integrate the scattered constraint information and generate a design constraint semantic cascade coding vector, so that the subsequent design process can comprehensively consider all design constraints and the interactions between the various design constraints, so as to better balance the needs and restrictions of various aspects and realize the comprehensive optimization design of municipal green buildings.

[0042] In the above-mentioned municipal green building design optimization method, the step S5 performs cross-domain joint encoding based on fine-grained ablation on the multi-scale coding feature map of the building area's geographical features and the semantic cascade coding vector of the design constraints to obtain a cross-modal ablation coding feature map of the building area's geographical features and design constraints. In particular, considering that the geographical features and design constraints of the building area come from different modalities (images and texts), the two jointly affect the final design result of the building, but simply combining the information of different modalities may be difficult to fully explore the deep-level associations and interactions between them. Based on this, the present application proposes a cross-domain joint encoding method based on fine-grained ablation, which performs fine-grained ablation analysis on the geographical features and design constraints of the building area to reveal the intrinsic connection and interaction between the two, thereby focusing on the key geographical feature areas that are closely related to the design constraints, and obtaining a cross-modal ablation coding feature map of the geographical features of the building area and the design constraints, so as to provide more accurate and useful information for the subsequent design sketch generation, so that it can fully utilize the geographical advantages of the site and meet the requirements of various design constraints. Among them, Figure 4 FIG. 5 is a flowchart of sub-step S5 of the municipal green building design optimization method according to an embodiment of the present application. Figure 4As shown, the step S5 includes the steps of: S51, performing fine-grained feature decoupling along the channel dimension of the multi-scale coding feature map of the building area geographic features to obtain a set of multi-scale coding feature matrices of the building area geographic features; S52, performing correlation strength ablation measurement on each multi-scale coding feature matrix of the building area geographic features in the set of the design constraint semantic cascade coding vector and the multi-scale coding feature matrix of the building area geographic features to obtain a set of fine-grained ablation factors of the building area geographic features-design constraints; S53, based on the set of fine-grained ablation factors of the building area geographic features-design constraints, performing fine-grained ablation modulation aggregation on the set of multi-scale coding feature matrices of the building area geographic features to obtain the cross-modal ablation coding feature map of the building area geographic features-design constraints.

[0043] Specifically, the step S51 is expressed by the formula: in, Indicates feature decoupling, Represents the multi-scale coded feature map of the building area’s geographic features, , and They represent the first, second and third in the set of multi-scale coding feature matrices of building area geographic features. A multi-scale coding feature matrix of geographical features of building areas, The number of channels of the multi-scale encoding feature map of the geographic features of the building area.

[0044] Specifically, by performing feature decoupling along the channel dimension on the multi-scale encoded feature map of the building area's geographic features, a finer-grained representation of the geographic features is obtained, providing a more detailed feature basis for subsequent ablation analysis.

[0045] Specifically, in step S52, each of the multi-scale coding feature matrices of building area geographic features in the set of the design constraint semantic cascade coding vector and the multi-scale coding feature matrix of building area geographic features is subjected to association strength ablation measurement to obtain a set of fine-grained ablation factors of building area geographic features and design constraints. Figure 5 FIG. 5 is a flowchart of sub-step S52 of the municipal green building design optimization method according to an embodiment of the present application. Figure 5As shown, the step S52 includes the steps of: S521, performing cross-domain query interaction based on the attention mechanism on each building area geographic feature multi-scale coding feature matrix in the set of the design constraint semantic cascade coding vector and the building area geographic feature multi-scale coding feature matrix to obtain a set of building area geographic feature-design constraint cross-domain query interaction feature vectors; S522, inputting each building area geographic feature-design constraint cross-domain query interaction feature vector in the set of building area geographic feature-design constraint cross-domain query interaction feature vectors into the ablation metric function respectively to obtain a set of fine-grained ablation factors of the building area geographic feature-design constraint.

[0046] More specifically, the step S521 includes: first, performing a linear transformation on the semantic concatenated coding vector of the design constraint condition to obtain a query vector and a value vector, which is expressed as: in, represents the semantic concatenated encoding vector of design constraints, and denote the query embedding matrix and the value embedding matrix respectively, and They represent query embedding bias and value embedding bias respectively, represents the matrix multiplication operation, and Represent the key matrices corresponding to the query vector and value vector respectively.

[0047] Then, the multi-scale coding feature matrix of the building area geographic features is linearly transformed to obtain a key matrix, which is expressed as follows: in, Represents the multi-scale coded feature matrix of the building area’s geographic features, represents the key embedding matrix, represents the key embedding bias term, Indicates the The corresponding key matrix.

[0048] Finally, the query vector, the value vector and the key matrix are input into a cross-domain interactive encoder based on a simulated transformer structure to obtain the building area geographic feature-design constraint cross-domain query interactive feature vector, which is expressed as: in, is the normalized exponential function, represents the transpose of a vector, Indicates the and stated Cross-domain query interaction feature vector between building area geographic features and design constraints.

[0049] Specifically, a query vector and a value vector are constructed based on the semantic cascade coding vector of the design constraint condition, a key matrix is ​​constructed based on each building area geographical feature multi-scale coding feature matrix in the set of the building area geographical feature multi-scale coding feature matrix, and the correlation between the building area geographical features and the design constraint condition is captured through cross-domain query interaction based on the transformer structure. In this process, the transformer structure can effectively process the information interaction between different domains, strengthen the significant correlation features between the building area geographical features and the design constraint condition through the attention mechanism, and suppress the interference of irrelevant information, so as to obtain the correlation interaction feature representation between the building area geographical features and the design constraint condition.

[0050] More specifically, the step S522 is expressed by the formula: in, represents the ablation metric function, represents the maximum value function, and Respectively indicate the The feature mean and feature variance of represents the regularization term, Indicates the The corresponding building area geographical characteristics-design constraint fine-grained ablation factors.

[0051] Specifically, the present application further introduces an ablation metric function to evaluate and quantify the representation of the associated interactive features between the geographical features of the building area and the design constraints. Among them, the ablation metric function is similar to the ablation analysis in the experimental design, which is used to judge the impact of removing a certain specific relationship on the final interaction effect, and helps to identify the degree of influence of the design constraint information on the geographical features of the building area. For example, if a specific vegetation coverage area is highly correlated with environmental requirements, then the protection and utilization of vegetation in the area needs to be specially considered during the design process to ensure that the design meets the requirements of environmental sustainability. On the contrary, if the geographical features of a certain area are not closely related to the design constraints, more flexibility can be given in the design to adapt to other more important constraints. Through this fine-grained ablation analysis, the geographical advantages of the site can be more accurately identified and utilized, while ensuring that the architectural design scheme can achieve environmental sustainability and economic rationality while meeting all design constraints.

[0052] Specifically, the step S53 includes: first, inputting the set of fine-grained ablation factors of the building area geographic features-design constraints into an ablation effect encoding module including a normalization function and a masking function to obtain a set of fine-grained ablation weight factors of the building area geographic features-design constraints, which is expressed as: in, represents the exponential function with base e, Indicates the The corresponding normalized building area geographic characteristics-design constraint fine-grained ablation factor, is the mask function, is the gated mask threshold, For the The corresponding building area geographic features-design constraints fine-grained ablation weight factors.

[0053] Specifically, in order to standardize the weights and exclude irrelevant items, the present application further normalizes and masks the generated set of fine-grained ablation factors of building area geographic features and design constraints. Here, the normalization function is used to convert all ablation factors into a standard range (such as between 0 and 1) so that they can be directly compared with each other; while the masking function is used to increase the ablation factors of building area geographic features that are significantly associated with the design constraints, while reducing the ablation factors of building area geographic features that are irrelevant or less relevant to the design constraints, thereby focusing resources and attention on the geographic features that are most closely associated with the design constraints.

[0054] Then, based on the set of fine-grained ablation weight factors of the building area geographic features-design constraints, the set of multi-scale coding feature matrices of the building area geographic features is weighted modulated to obtain a set of cross-modal ablation coding feature matrices of the building area geographic features-design constraints; finally, the set of cross-modal ablation coding feature matrices of the building area geographic features-design constraints is subjected to feature aggregation along the channel dimension to obtain the cross-modal ablation coding feature map of the building area geographic features-design constraints, which is expressed as follows: in, , and Respectively , and stated The corresponding building area geographic features-design constraint fine-grained ablation weight factor, Representing the cross-modal ablation encoding feature map of building area geographical characteristics-design constraints.

[0055] Specifically, the present application performs fine-grained ablation modulation and feature aggregation along the channel dimension on the original set of multi-scale encoding feature matrices of the geographical features of the building area based on the generated set of fine-grained ablation weight factors of the geographical features of the building area and the design constraints, so as to strengthen the geographical features of the building area that are highly related to the design constraints, while also retaining the diversity of the geographical features of the building area, thereby providing a richer and more accurate feature representation for the subsequent design sketch generation.

[0056] In the above-mentioned municipal green building design optimization method, the step S6 generates a municipal green building design sketch based on the building area geographical feature-design constraint cross-modal ablation coding feature map. In a specific example of the present application, the step S6 includes: inputting the building area geographical feature-design constraint cross-modal ablation coding feature map into a municipal green building design sketch generator based on a large model to obtain the municipal green building design sketch. Specifically, in order to transform the building area geographical feature-design constraint cross-modal ablation coding feature map from an abstract feature representation into an intuitive architectural design sketch so that designers and users can quickly understand and evaluate the general outline and layout of the design scheme, the present application further utilizes the powerful generation capability of the large model, based on the rich information contained in the building area geographical feature-design constraint cross-modal ablation coding feature map, combined with its learning experience on large-scale architectural design data, to generate a high-quality municipal green building design sketch that meets the geographical features and design constraints, providing a visual basis and reference for subsequent detailed design and scheme optimization. In an embodiment of the present application, the large model is a generative adversarial network (GANs). Those skilled in the art should know that generative adversarial networks (GANs) consist of a generator and a discriminator, which evolve together through adversarial training. In the generation of municipal green building design sketches, the generative adversarial network transforms the cross-modal ablation encoding feature map of building area geographic features-design constraints into high-quality design sketches through the adversarial training mechanism of its generator and discriminator. The generator learns to create sketches that meet the design requirements, while the discriminator evaluates the similarity of these generated sketches with real samples. The two compete and optimize with each other, and finally generate high-quality design sketches that meet multiple constraints, which significantly improves the efficiency of design.

[0057] Specifically, when the multi-scale encoding feature map of the building area geographic features and the semantic cascade encoding vector of the design constraints respectively represent the multi-scale semantic encoding features of the building area geographic image of the bird's-eye view of the target area and the semantic cascade features of the design constraints, after performing cross-domain attention joint encoding based on fine-grained ablation, the building area geographic features-design constraint cross-modal ablation encoding feature map will also have significant interactive optimization distribution spatial structure differences due to the cross-modal semantic fine-grained ablation differences, affecting the convergence consistency of the municipal green building design sketch generator based on the large model, thereby affecting the image quality of the municipal green building design sketch obtained by the municipal green building design sketch generator based on the large model.

[0058] Therefore, in a preferred example of the present application, the building area geographical feature-design constraint condition cross-modal ablation coding feature map is optimized, and the optimization process includes: First, the absolute value sum and the square root of the sum of squares of all eigenvalues ​​of the building area geographic feature-design constraint cross-modal ablation coding feature map are calculated to obtain the first building area geographic feature-design constraint cross-modal ablation coding spatial structure value and the second building area geographic feature-design constraint cross-modal ablation coding spatial structure value, which can be expressed as follows: in, represents the spatial structure value of the first building area geographic feature-design constraint cross-modal ablation encoding, The first of all feature value sets representing the feature map of the cross-modal ablation coding of the building area geographic features and design constraints eigenvalues, Representing the second building area geographic feature-design constraint cross-modal ablation encoding spatial structure value; Secondly, determine the total number of eigenvalues ​​of all eigenvalues ​​of the building area geographic feature-design constraint cross-modal ablation coding feature map, and for each eigenvalue of the building area geographic feature-design constraint cross-modal ablation coding feature map, calculate the product of the first building area geographic feature-design constraint cross-modal ablation coding spatial structure value minus the eigenvalue and the total number of eigenvalues ​​to obtain the first building area geographic feature-design constraint cross-modal ablation coding long-range dependency value, which is expressed by the formula: in, Indicates the The corresponding first building area geographical features - design constraints cross-modal ablation encoding long-range dependency values, The total number of eigenvalues ​​representing all eigenvalues ​​of the cross-modal ablation coding feature map of the building area geographic characteristics-design constraints; Next, the square root of the total number of eigenvalues ​​multiplied by the product of the eigenvalues ​​minus the second building area geographic feature-design constraint cross-modal ablation coding spatial structure value is calculated to obtain the second building area geographic feature-design constraint cross-modal ablation coding long-range dependency value, which is expressed as: in, Indicates the The corresponding second building area geographical features - design constraints cross-modal ablation encoding long-range dependency values; Then, the index value calculated by taking the first building area geographic feature-design constraint cross-modal ablation coding long-range dependency value as the exponent of the natural constant and the inverse of the second building area geographic feature-design constraint cross-modal ablation coding long-range dependency value are weighted summed to obtain the optimized eigenvalue corresponding to each eigenvalue, which is expressed as follows: in, Indicates the The corresponding optimized eigenvalue is , Represent different weight parameters respectively. Indicates the countdown, It represents the exponential value with the natural constant as the base; Finally, the optimized feature values ​​are combined into an optimized building area geographic feature-design constraint cross-modal ablation coding feature map.

[0059] Specifically, in view of the possible spatial structure loss in the high-dimensional space of the feature set of the building area geographical features-design constraint cross-modal ablation coding feature map, which causes the weight of the generator to implicitly infer the spatial structure information based on the features, resulting in inconsistent convergence. The present application establishes a long-distance feature dependency relationship based on the spatial structure representation of the building area geographical features-design constraint cross-modal ablation coding feature map relative to the overall feature scale of the building area geographical features-design constraint cross-modal ablation coding feature map, so as to establish the local connectivity of the features of the building area geographical features-design constraint cross-modal ablation coding feature map, and captures the spatial ambiguous information of the object feature value through the unstructured feature value point prediction of the building area geographical features-design constraint cross-modal ablation coding feature map, thereby improving the spatial inductive bias perception ability of the feature set of the building area geographical features-design constraint cross-modal ablation coding feature map, improving the convergence consistency of the generator, and improving the image quality of the municipal green building design sketch obtained by the municipal green building design sketch generator based on the large model of the building area geographical features-design constraint cross-modal ablation coding feature map.

[0060] In summary, the municipal green building design optimization method based on the embodiment of the present application is explained, which first extracts geographic location information from the municipal green building design condition information input by the user, and obtains the bird's-eye view of the target area from the GIS system based on this, and then further introduces the image processing technology based on deep learning to extract multi-scale features from the bird's-eye view of the target area to capture the geographic characteristics of the target building area. At the same time, natural language processing technology is used to perform semantic analysis on the budget constraints, functional requirements, environmental requirements, and time frames input by the user, and use this as a design constraint to modulate the attention of the geographic characteristics of the target building area, so as to comprehensively consider the geographic characteristics of the building area and the design constraints, and intelligently generate a municipal green building design sketch. In this way, the design efficiency of municipal green buildings can be significantly improved, the design cycle can be shortened, and the innovation and quality of the design results can be ensured.

[0061] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0062] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0063] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0064] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A municipal green building design optimization method, characterized in that: include: Obtaining municipal green building design conditions input by a user, wherein the municipal green building design conditions include geographical location, budget constraints, functional requirements, environmental requirements, and time frame; Extracting a geographic location from the municipal green building design conditions, and extracting a bird's-eye view of a target area from a GIS system based on the geographic location; Extracting geographic features from the bird's-eye view of the target area to obtain a multi-scale coded feature map of geographic features of the building area; Performing semantic joint coding on the municipal green building design conditions to obtain a semantic cascade coding vector of design constraint conditions; Performing cross-domain joint encoding based on fine-grained ablation on the multi-scale encoding feature map of the building area geographic features and the semantic cascade encoding vector of the design constraints to obtain a cross-modal ablation encoding feature map of the building area geographic features-design constraints; Based on the cross-modal ablation coding feature map of the building area's geographical features and design constraints, a municipal green building design sketch is generated.

2. The municipal green building design optimization method according to claim 1, characterized in that: Extracting geographic features from the bird's-eye view of the target area to obtain a multi-scale coded feature map of geographic features of the building area includes: The bird's-eye view of the target area is input into a building area geographic feature extractor based on the CrossViT model to obtain a multi-scale coded feature map of the building area geographic features.

3. The municipal green building design optimization method according to claim 2 is characterized in that: The municipal green building design conditions are semantically jointly encoded to obtain a design constraint condition semantic cascade encoding vector, including: Extracting the budget constraint, the functional requirement, the environmental requirement and the time frame from the municipal green building design conditions, and semantically encoding the budget constraint, the functional requirement, the environmental requirement and the time frame respectively to obtain a budget constraint semantic encoding vector, a functional requirement semantic encoding vector, an environmental requirement semantic encoding vector and a time frame semantic encoding vector; The budget constraint semantic coding vector, the functional requirement semantic coding vector, the environmental requirement semantic coding vector and the time frame semantic coding vector are cascaded to obtain the design constraint semantic cascade coding vector.

4. The municipal green building design optimization method according to claim 3 is characterized in that: Semantically encoding the budget constraint, the functional requirement, the environmental requirement, and the time frame to obtain a budget constraint semantic encoding vector, a functional requirement semantic encoding vector, an environmental requirement semantic encoding vector, and a time frame semantic encoding vector, including: Use a semantic encoder based on the Bert model to semantically encode the budget constraint, the functional requirements, the environmental requirements and the time frame respectively to obtain the budget constraint semantic coding vector, the functional requirements semantic coding vector, the environmental requirements semantic coding vector and the time frame semantic coding vector.

5. The municipal green building design optimization method according to claim 4 is characterized in that: The multi-scale coding feature map of the building area geographic features and the semantic cascade coding vector of the design constraint conditions are cross-domain jointly coded based on fine-grained ablation to obtain a building area geographic feature-design constraint condition cross-modal ablation coding feature map, including: Performing fine-grained feature decoupling along the channel dimension on the multi-scale coded feature map of the building area geographic features to obtain a set of multi-scale coded feature matrices of the building area geographic features; Performing correlation strength ablation measurement on each building area geographic feature multi-scale coding feature matrix in the set of the design constraint semantic cascade coding vector and the building area geographic feature multi-scale coding feature matrix to obtain a set of building area geographic feature-design constraint fine-grained ablation factors; Based on the set of fine-grained ablation factors of the building area geographic features-design constraints, the set of multi-scale coding feature matrices of the building area geographic features is subjected to fine-grained ablation modulation aggregation to obtain a cross-modal ablation coding feature map of the building area geographic features-design constraints.

6. The municipal green building design optimization method according to claim 5, characterized in that: The association strength ablation measurement is performed on each building area geographic feature multi-scale coding feature matrix in the set of the design constraint semantic cascade coding vector and the building area geographic feature multi-scale coding feature matrix to obtain a set of building area geographic feature-design constraint fine-grained ablation factors, including: Performing cross-domain query interaction based on the attention mechanism on each building area geographic feature multi-scale encoding feature matrix in the set of the design constraint semantic cascade encoding vector and the building area geographic feature multi-scale encoding feature matrix to obtain a set of building area geographic feature-design constraint cross-domain query interaction feature vectors; Each building area geographic feature-design constraint cross-domain query interactive feature vector in the set of the building area geographic feature-design constraint cross-domain query interactive feature vectors is input into the ablation metric function to obtain a set of fine-grained ablation factors of the building area geographic feature-design constraint.

7. The municipal green building design optimization method according to claim 6, characterized in that: The attention mechanism-based cross-domain query interaction is performed on each building area geographic feature multi-scale encoding feature matrix in the set of the design constraint semantic cascade encoding vector and the building area geographic feature multi-scale encoding feature matrix to obtain a set of building area geographic feature-design constraint cross-domain query interaction feature vectors, including: Performing a linear transformation on the semantic concatenated encoding vector of the design constraint condition to obtain a query vector and a value vector; Performing a linear transformation on the multi-scale coding feature matrix of the building area geographic features to obtain a key matrix; The query vector, the value vector and the key matrix are input into a cross-domain interactive encoder based on a simulated transformer structure to obtain the building area geographic feature-design constraint condition cross-domain query interactive feature vector.

8. The municipal green building design optimization method according to claim 7, characterized in that: Based on the set of fine-grained ablation factors of the building area geographic features-design constraints, a set of multi-scale coding feature matrices of the building area geographic features is subjected to fine-grained ablation modulation aggregation to obtain a cross-modal ablation coding feature map of the building area geographic features-design constraints, including: Inputting the set of fine-grained ablation factors of the building area geographic features-design constraints into an ablation effect encoding module including a normalization function and a masking function to obtain a set of fine-grained ablation weight factors of the building area geographic features-design constraints; Based on the set of fine-grained ablation weight factors of the building area geographic features-design constraint conditions, weighted modulation is performed on the set of multi-scale coding feature matrices of the building area geographic features to obtain a set of cross-modal ablation coding feature matrices of the building area geographic features-design constraint conditions; The set of the building area geographic feature-design constraint cross-modal ablation coding feature matrices is subjected to feature aggregation along the channel dimension to obtain the building area geographic feature-design constraint cross-modal ablation coding feature map.

9. The municipal green building design optimization method according to claim 8, characterized in that: Based on the cross-modal ablation coding feature map of the building area geographical features and design constraints, a municipal green building design sketch is generated, including: The building area geographic feature-design constraint cross-modal ablation coding feature map is input into a municipal green building design sketch generator based on a large model to obtain the municipal green building design sketch.

Images