Method and device for estimating carbon footprint of building representation based on artificial intelligence recognition and inference

Abstract

The present invention provides a method and device for estimating the carbon footprint of building representations based on artificial intelligence identification and inference, belonging to the technical field of carbon emission estimation. The present invention collects building data to obtain a structural classification model dataset and a material classification model dataset; calculates building characteristic values, establishes a machine learning-based building structure prediction model, and based on the YOLOV11 model, utilizes a SwinTransformerV2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model to establish a deep learning-based building material prediction model; collects current status data of the building to be evaluated, and obtains the building's current status characteristic values ​​through the above-mentioned model; constructs a carbon emission calculation model based on the building's current status characteristic values ​​and carbon emission factors; and calculates an estimated value of the building's carbon emissions. The present invention enables more convenient, efficient, and accurate estimation of building materials and carbon emissions.

Description

Technical Field

[0001] The present invention belongs to the technical field of carbon emission estimation, and in particular relates to a method and device for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference. Background Art

[0002] With the acceleration of urbanization, the renovation of old buildings is closely related to carbon sequestration activities. Old buildings will become the main targets for carbon sequestration calculation and renovation. Through energy-saving renovations and increased greening measures, carbon emissions can be effectively reduced and the city's carbon sequestration capacity can be increased. However, the calculation of carbon sequestration in old buildings is currently quite difficult. Due to the large number of old urban areas, relevant information and data are incomplete or difficult to obtain, making it difficult to accurately calculate carbon emissions.

[0003] The existing carbon emission measurement methods for old buildings mainly include:

[0004] 1. Geographic Information System (GIS) Method: This approach uses GIS technology to integrate data on urban buildings, transportation, energy consumption, and other areas to conduct spatial analysis of carbon emissions. Disadvantages: Data acquisition and updating are difficult, and there may be missing or inaccurate information. Furthermore, models are often oversimplified and fail to reflect the complex urban ecosystem.

[0005] 2. Life Cycle Assessment (LCA): This method assesses the carbon emissions of buildings and facilities throughout their lifecycle, including the extraction, production, transportation, use, and demolition of raw materials. Disadvantages: High implementation cost and time; high reliance on data, requiring a large amount of accurate material and energy data.

[0006] 3. Energy Audit: This method estimates a building's carbon emissions by auditing its energy consumption. Disadvantages: It focuses solely on energy consumption data and fails to consider other sources of carbon emissions (such as transportation and waste disposal). The audit process is cumbersome, making it difficult to apply on a large scale.

[0007] 4. Statistical methods: Use statistical data and models to estimate a city's overall carbon emissions. Disadvantages: These methods are often based on macro-level statistics and may not accurately reflect the actual situation in a specific region. They may also overlook local differences and the characteristics of individual buildings.

[0008] 5. Building Energy Consumption Simulation: Use simulation software to predict building energy consumption and thus calculate carbon emissions. Disadvantages: The accuracy of the model depends on the accuracy of the input parameters, and the simulation results may be affected by simplifying assumptions.

[0009] In summary, these methods have certain shortcomings in data acquisition, calculation accuracy and implementation feasibility, resulting in carbon emission assessments in old urban areas often being incomplete and inaccurate. Summary of the Invention

[0010] In response to the problems existing in the above-mentioned existing technologies, the present invention provides a method and device for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference, combining computer vision and deep learning technology to carry out more convenient, efficient and accurate monitoring of building materials and carbon emissions.

[0011] A carbon footprint is a metric used to measure the amount of carbon dioxide emissions caused directly or indirectly by an individual, organization, product, or country over a specific period of time. The carbon footprint calculation covers emissions throughout the entire life cycle of a product or service, from production and transportation to end use and disposal.

[0012] The present invention provides a method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference, comprising the following steps:

[0013] Step S1: collecting data, collecting structure classification model data, including building data and building point of interest (POI) data, and collecting material classification model data, including street view images;

[0014] Step S2: Pre-training data processing: For the structure classification model data, the buildings are labeled and matched with the points of interest to obtain the structure classification model data set; for the material classification model data, the data is segmented and labeled to obtain the material classification model data set;

[0015] Step S3: Establishing a machine learning-based building structure prediction model: extracting building features and calculating building feature values, evaluating and screening the building features, determining a machine learning algorithm, establishing and training a machine learning-based building structure prediction model, and obtaining a machine learning-based building structure prediction model that meets a preset accuracy;

[0016] Step S4: Establishing a deep learning-based building material prediction model: Performing data enhancement on the material classification model dataset, based on the YOLOV11 model, using the Swin Transformer V2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model, establishing a deep learning-based building material prediction model and training it to obtain a deep learning-based building material prediction model that meets the preset accuracy;

[0017] Step S5: Collect the current status data of the building to be evaluated, and obtain the building structure characteristic value and the building material characteristic value respectively through the building structure prediction model based on machine learning and the building material prediction model based on deep learning, and obtain the building current status characteristic value;

[0018] Step S6: Constructing a carbon emission calculation model based on building structure characteristics, building material characteristics, and corresponding carbon emission factors;

[0019] Step S7: Obtain an estimated value of the building's carbon emissions based on the building's current characteristic values ​​and the carbon emissions calculation model.

[0020] Preferably, step S1 includes the following steps:

[0021] Step S101: Obtain building data including building footprints, outlines, and attributes through a geographic information system, and collect building point of interest (POI) data through a web map.

[0022] Step S102: Collect street view images through real photos and online maps.

[0023] Preferably, step S2 includes the following steps:

[0024] Step S201: Processing the structural classification model data, manually annotating buildings with reference to building codes and technical standards, building-related publications, online satellite and street view maps, matching the building data with point of interest (POI) data, and obtaining a complete structural classification dataset in shp format;

[0025] Step S202: Use RoboFlow to segment and annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement on the annotated material classification model dataset.

[0026] Step S203: Divide the structure classification dataset and the street view dataset into a training set and a test set.

[0027] Preferably, data enhancement is performed on the labeled material classification model dataset using techniques including random cropping, rotation, tilting, and noise blurring.

[0028] Preferably, step S3 includes the following steps:

[0029] Step S301: extract building features; and calculate building feature values;

[0030] Step S302: Evaluate and screen building characteristics;

[0031] Step S303: Determine a machine learning algorithm and establish a building structure prediction model based on machine learning;

[0032] Step S304: training a building structure prediction model based on machine learning;

[0033] Step S305: Evaluate the prediction results of the machine learning-based building structure prediction model to obtain a machine learning-based building structure prediction model that meets a preset accuracy.

[0034] Preferably, evaluating and screening building characteristics includes:

[0035] Use the feature scoring function to score each feature;

[0036] Sort the features by their ratings from highest to lowest.

[0037] Select features that rank in the top K of the preset positions.

[0038] Preferably, the building features include building geometric features, building shape features, and building point of interest (POI) features.

[0039] Preferably, the calculation of the building geometric characteristic value includes the following steps:

[0040] Predefine the number of building floors and building height;

[0041] The height between floors is calculated using formula (1):

[0042] (1);

[0043] Use the geometry calculation function in the ArcGIS platform to calculate the outline area and perimeter of the building;

[0044] Simplify the building outline into the minimum bounding rectangle (MBR) surrounding the building, and calculate the length and width of the minimum bounding rectangle (MBR) using the minimum bounding geometry function of ArcGIS;

[0045] The length of the minimum bounding rectangle MBR is used to represent the true length of the building;

[0046] The width of the minimum bounding rectangle (MBR) is weighted and expressed as the true width of the building outline using the formula (2):

[0047] (2);

[0048] Calculate the height-to-width ratio and the length-to-width ratio of a building:

[0049] The height-to-width ratio of a building Use formula (3) to calculate:

[0050] (3);

[0051] The building's true length-to-width ratio Use formula (4) to calculate:

[0052] (4);

[0053] Among them, among them, is the height between floors, is the building height, is the number of floors of the building; is the true width of the building outline, is the building's outline area, is the area of ​​the minimum bounding rectangle MBR that encloses the building outline, is the true length of the building, and are the length and width of the minimum bounding rectangle MBR respectively.

[0054] Preferably, the building shape characteristic value of the building is calculated using formula (5):

[0055] (5);

[0056] in, is the shape irregularity of the building outline, with a value range of (0, 1.0], where lower values ​​indicate higher irregularity.

[0057] Preferably, the calculation of the building point of interest POI feature value includes the following steps:

[0058] Count the total number of building points of interest (POIs) and the total number of building points of interest (POI) types for each building;

[0059] The building point of interest POI type is evaluated step by step using a decision tree until a leaf node is reached. The leaf node indicates the building point of interest POI type, and the corresponding Boolean value is obtained according to the building point of interest POI type.

[0060] Preferably, the determined machine learning algorithm is a gradient boosting decision tree.

[0061] Preferably, the building structure characteristic value obtained by the building structure prediction model based on machine learning includes the building structure type identified by the building structure prediction model based on machine learning, and the building structure volume Vmain body is calculated through street view image data, and the total volume of the building is determined according to the proportion of the building structure volume in building structures of different structure types, different building floors and heights.

[0062] Preferably, step S4 includes the following steps:

[0063] Step S401: annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement using random cropping, rotation, tilting, and noise blurring techniques;

[0064] Step S402: Based on the YOLO V11 model, the feature extraction part of the YOLO V11 model is replaced by the Swin Transformer V2 or ConvNeXtV2 computer vision network to establish a building material prediction model based on deep learning;

[0065] Step S403: Optimizing the hyperparameters of the deep learning-based building material prediction model to select optimal hyperparameters;

[0066] Step S404: training the deep learning-based building material prediction model after hyperparameter optimization;

[0067] Step S405: Evaluate the trained deep learning-based building material prediction model to obtain a deep learning-based building material prediction model that meets a preset accuracy.

[0068] Preferably, step S5 includes the following steps:

[0069] Step S501: collecting current feature values ​​of building features through a geographic information system, including building geometric feature values, building shape feature values, and building point of interest (POI) feature values;

[0070] Step S502: Collecting street view images of the current status of buildings through online maps;

[0071] Step S503: The machine learning-based building structure prediction model and the deep learning-based building material prediction model respectively obtain building structure characteristic values ​​and building material characteristic values, and obtain building status characteristic values;

[0072] Step S504: sorting building structure categories, building material ratios, building geometric feature values, building shape feature values, and building point of interest (POI) feature values.

[0073] Preferably, step S6 includes the following steps:

[0074] Step S601: Collect existing data to obtain carbon emission factors C of different structures 主体 and carbon emission factors C of different materials 维护 ;

[0075] Step S602: Obtaining the area and volume of the building through the building geometric feature values;

[0076] Step S603: Construct a building structure carbon emission model and a building material carbon emission model. Based on the building's area and volume, combined with the carbon emission coefficient corresponding to its structural type and materials, calculate the building's main structure carbon emissions and building envelope carbon emissions. The carbon emission calculation formula is as follows:

[0077] (6)

[0078] in:

[0079] : No. The volume of the structure ( );

[0080] : No. Carbon emission standard value of this structure ( );

[0081] : No. The carbon emission coefficient of each structure is used to adjust the impact of different structures;

[0082] : No. The surface area of ​​the material ( );

[0083] : No. Carbon emission standard value of the material ( );

[0084] : No. Carbon emission coefficients of different materials are used to take into account the characteristics of different materials;

[0085] : Carbon emissions from other construction processes ( );

[0086] : Total carbon emissions ( );

[0087] : total number of structures;

[0088] : Total number of materials;

[0089] Step S604: Evaluate the building structure carbon emission model and the building material carbon emission model;

[0090] Step S605: Obtain the final carbon emission calculation model.

[0091] The present invention provides a device for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference, comprising a processor, which executes the steps of the above-mentioned method for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference.

[0092] Compared with the prior art, the present invention has at least the following beneficial effects:

[0093] 1. Efficient use of limited data

[0094] To address the lack of data in older urban areas, this method uses computer vision technology and deep learning models to directly extract key information such as building materials and structural characteristics by analyzing publicly available street view imagery and a small amount of existing building data. This approach reduces reliance on large-scale data, enabling accurate identification of building characteristics and high-quality carbon emissions assessments even with limited data.

[0095] 2. Low-cost data collection and processing

[0096] Unlike traditional, costly methods that rely on comprehensive data collection and on-site sampling, this method uses automated visual recognition technology to obtain building information, requiring only publicly available data sources and minimal manual annotation, significantly reducing data collection and processing costs. This low-cost data processing approach is suitable for resource-constrained situations and makes large-scale carbon emission assessment feasible in older urban areas.

[0097] 3. Efficient calculation process

[0098] This paper incorporates deep learning algorithms to efficiently process building information. Compared to traditional methods such as GIS analysis or life cycle assessment, this method can assess a building's carbon emissions in a fraction of the time, reducing manual intervention and data processing. This highly efficient assessment process significantly improves the efficiency of carbon footprint calculations and meets the needs of large-scale, rapid monitoring.

[0099] Through a low-cost and efficient solution under limited data conditions, the present invention provides a building carbon emission assessment method with strong adaptability and high resource utilization, providing important support for carbon emission monitoring and management in old urban areas.

[0100] 4. Accurate calculation

[0101] The present invention takes into account the structural type and material characteristics of the building, and innovatively provides a method for calculating the true length and width of the building, as well as the irregularity of the building. The resulting building characteristics are more accurate, thereby making the calculated carbon emissions more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Figure 1 The present invention is a flowchart of a method for estimating the carbon footprint of a building representation based on artificial intelligence identification and speculation according to an embodiment of the present invention.

[0103] Figure 2 This is a technical roadmap for a method for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference in one embodiment of the present invention.

[0104] Figure 3This is a technical roadmap for constructing a building structure prediction model in accordance with an embodiment of the present invention to obtain a building structure prediction model that meets a preset accuracy.

[0105] Figure 4 This is a technical roadmap for constructing a building material prediction model in accordance with an embodiment of the present invention, and obtaining a building material prediction model that meets a preset accuracy.

[0106] Figure 5 This is a technical roadmap for calculating carbon emissions based on the current characteristics of a building using a building structure prediction model and a building material prediction model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0107] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0108] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are also within the scope of protection of the present invention.

[0109] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0110] In order to better understand the purpose, structure and function of the present invention, the present invention is further described in detail below with reference to the accompanying drawings.

[0111] The present invention provides a method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference, comprising the following steps:

[0112] Step S1: collecting data, collecting structure classification model data, including building data and building point of interest (POI) data, and collecting material classification model data, including street view images;

[0113] Step S2: Pre-training data processing: For the structure classification model data, the buildings are labeled and matched with the points of interest to obtain the structure classification model data set; for the material classification model data, the data is segmented and labeled to obtain the material classification model data set;

[0114] Step S3: Establishing a machine learning-based building structure prediction model: extracting building features and calculating building feature values, evaluating and screening the building features, determining a machine learning algorithm, establishing and training a machine learning-based building structure prediction model, and obtaining a machine learning-based building structure prediction model that meets a preset accuracy;

[0115] Step S4: Establishing a deep learning-based building material prediction model: Performing data enhancement on the material classification model dataset, based on the YOLOV11 model, using the Swin Transformer V2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model, establishing a deep learning-based building material prediction model and training it to obtain a deep learning-based building material prediction model that meets the preset accuracy;

[0116] Step S5: Collect the current status data of the building to be evaluated, and obtain the building structure characteristic value and the building material characteristic value respectively through the building structure prediction model based on machine learning and the building material prediction model based on deep learning, and obtain the building current status characteristic value;

[0117] Step S6: Constructing a carbon emission calculation model based on building structure characteristics, building material characteristics, and corresponding carbon emission factors;

[0118] Step S7: Obtain an estimated value of the building's carbon emissions based on the building's current characteristic values ​​and the carbon emissions calculation model.

[0119] According to a specific embodiment of the present invention, step S1 includes the following steps:

[0120] Step S101: Obtain building data including building footprints, outlines, and attributes through a geographic information system, and collect building point of interest (POI) data through a web map.

[0121] Step S102: Collect street view images through real photos and online maps.

[0122] According to a specific embodiment of the present invention, step S2 comprises the following steps:

[0123] Step S201: Processing the structural classification model data, manually annotating buildings with reference to building codes and technical standards, building-related publications, online satellite and street view maps, matching the building data with point of interest (POI) data, and obtaining a complete structural classification dataset in shp format;

[0124] Step S202: Use RoboFlow to segment and annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement on the annotated material classification model dataset.

[0125] Step S203: Divide the structure classification dataset and the street view dataset into a training set and a test set.

[0126] According to a specific embodiment of the present invention, data enhancement is performed on the labeled material classification model data set using techniques including random cropping, rotation, tilting, and noise blurring.

[0127] According to a specific embodiment of the present invention, step S3 includes the following steps:

[0128] Step S301: extract building features; and calculate building feature values;

[0129] Step S302: Evaluate and screen building characteristics;

[0130] Step S303: Determine a machine learning algorithm and establish a building structure prediction model based on machine learning;

[0131] Step S304: training a building structure prediction model based on machine learning;

[0132] Step S305: Evaluate the prediction results of the machine learning-based building structure prediction model to obtain a machine learning-based building structure prediction model that meets a preset accuracy.

[0133] According to a specific embodiment of the present invention, evaluating and screening building characteristics includes:

[0134] Use the feature scoring function to score each feature;

[0135] Sort the features by their ratings from highest to lowest.

[0136] Select features that rank in the top K of the preset positions.

[0137] According to a specific embodiment of the present invention, the building features include building geometric features, building shape features, and building point of interest (POI) features.

[0138] According to a specific embodiment of the present invention, the calculation of the building geometric characteristic value includes the following steps:

[0139] Predefine the number of building floors and building height;

[0140] The height between floors is calculated using formula (1):

[0141] (1);

[0142] Use the geometry calculation function in the ArcGIS platform to calculate the outline area and perimeter of the building;

[0143] Simplify the building outline into the minimum bounding rectangle (MBR) surrounding the building, and calculate the length and width of the minimum bounding rectangle (MBR) using the minimum bounding geometry function of ArcGIS;

[0144] The length of the minimum bounding rectangle MBR is used to represent the true length of the building;

[0145] The width of the minimum bounding rectangle (MBR) is weighted and expressed as the true width of the building outline using the formula (2):

[0146] (2);

[0147] Calculate the height-to-width ratio and the length-to-width ratio of a building:

[0148] The height-to-width ratio of a building Use formula (3) to calculate:

[0149] (3);

[0150] The building's true length-to-width ratio Use formula (4) to calculate:

[0151] (4);

[0152] in, is the height between floors, is the building height, is the number of floors of the building; is the true width of the building outline, is the building's outline area, is the area of ​​the minimum bounding rectangle MBR that encloses the building outline, is the true length of the building, and are the length and width of the minimum bounding rectangle MBR respectively.

[0153] According to a specific embodiment of the present invention, the building shape characteristic value of the building is calculated using formula (5):

[0154] (5);

[0155] in, is the shape irregularity of the building outline, with a value range of (0, 1.0], where lower values ​​indicate higher irregularity.

[0156] According to a specific embodiment of the present invention, the calculation of the building point of interest POI feature value includes the following steps:

[0157] Count the total number of building points of interest (POIs) and the total number of building points of interest (POI) types for each building;

[0158] The building point of interest POI type is evaluated step by step using a decision tree until a leaf node is reached. The leaf node indicates the building point of interest POI type, and the corresponding Boolean value is obtained according to the building point of interest POI type.

[0159] According to a specific embodiment of the present invention, the determined machine learning algorithm is a gradient boosting decision tree.

[0160] According to a specific embodiment of the present invention, the building structure characteristic value obtained by the building structure prediction model based on machine learning includes the building structure type identified by the building structure prediction model based on machine learning, and the building structure volume Vmain body is calculated through street view image data. The total volume of the building is determined according to the proportion of the building structure volume in building structures of different structure types, different numbers of floors and heights.

[0161] According to a specific embodiment of the present invention, step S4 includes the following steps:

[0162] Step S401: annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement using random cropping, rotation, tilting, and noise blurring techniques;

[0163] Step S402: Based on the YOLO V11 model, the feature extraction part of the YOLO V11 model is replaced by the Swin Transformer V2 or ConvNeXtV2 computer vision network to establish a building material prediction model based on deep learning;

[0164] Step S403: Optimizing the hyperparameters of the deep learning-based building material prediction model to select optimal hyperparameters;

[0165] Step S404: training the deep learning-based building material prediction model after hyperparameter optimization;

[0166] Step S405: Evaluate the trained deep learning-based building material prediction model to obtain a deep learning-based building material prediction model that meets a preset accuracy.

[0167] According to a specific embodiment of the present invention, step S5 includes the following steps:

[0168] Step S501: collecting current feature values ​​of building features through a geographic information system, including building geometric feature values, building shape feature values, and building point of interest (POI) feature values;

[0169] Step S502: Collecting street view images of the current status of buildings through online maps;

[0170] Step S503: The machine learning-based building structure prediction model and the deep learning-based building material prediction model respectively obtain building structure characteristic values ​​and building material characteristic values, and obtain building status characteristic values;

[0171] Step S504: sorting building structure categories, building material ratios, building geometric feature values, building shape feature values, and building point of interest (POI) feature values.

[0172] According to a specific embodiment of the present invention, step S6 includes the following steps:

[0173] Step S601: Collect existing data to obtain carbon emission factors C of different structures 主体 and carbon emission factors C of different materials 维护 ;

[0174] Step S602: Obtaining the area and volume of the building through the building geometric feature values;

[0175] Step S603: Construct a building structure carbon emission model and a building material carbon emission model. Based on the building's area and volume, combined with the carbon emission coefficient corresponding to its structural type and materials, calculate the building's main structure carbon emissions and building envelope carbon emissions. The carbon emission calculation formula is as follows:

[0176] (6)

[0177] in:

[0178] : No. The volume of the structure ( );

[0179] : No. Carbon emission standard value of this structure ( );

[0180] : No. The carbon emission coefficient of each structure is used to adjust the impact of different structures;

[0181] : No. The surface area of ​​the material ( );

[0182] : No. Carbon emission standard value of the material ( );

[0183] : No. Carbon emission coefficients of different materials are used to take into account the characteristics of different materials;

[0184] : Carbon emissions from other construction processes ( );

[0185] : Total carbon emissions ( );

[0186] : total number of structures;

[0187] : Total number of materials;

[0188] Step S604: Evaluate the building structure carbon emission model and the building material carbon emission model;

[0189] Step S605: Obtain the final carbon emission calculation model.

[0190] The present invention provides a device for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference, comprising a processor, which executes the steps of the above-mentioned method for estimating the carbon footprint of building representation based on artificial intelligence recognition and inference.

[0191] Example 1

[0192] like Figure 1 The present invention provides a method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference, comprising the following steps:

[0193] Step S1: collecting data, collecting structure classification model data, including building data and building point of interest (POI) data, and collecting material classification model data, including street view images;

[0194] Step S2: Pre-training data processing: For the structure classification model data, the buildings are labeled and matched with the points of interest to obtain the structure classification model data set; for the material classification model data, the data is segmented and labeled to obtain the material classification model data set;

[0195] Step S3: Establishing a machine learning-based building structure prediction model: extracting building features and calculating building feature values, evaluating and screening the building features, determining a machine learning algorithm, establishing and training a machine learning-based building structure prediction model, and obtaining a machine learning-based building structure prediction model that meets a preset accuracy;

[0196] Step S4: Establishing a deep learning-based building material prediction model: Performing data enhancement on the material classification model dataset, based on the YOLOV11 model, using the Swin Transformer V2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model, establishing a deep learning-based building material prediction model and training it to obtain a deep learning-based building material prediction model that meets the preset accuracy;

[0197] Step S5: Collect the current status data of the building to be evaluated, and obtain the building structure characteristic value and the building material characteristic value respectively through the building structure prediction model based on machine learning and the building material prediction model based on deep learning, and obtain the building current status characteristic value;

[0198] Step S6: Constructing a carbon emission calculation model based on building structure characteristics, building material characteristics, and corresponding carbon emission factors;

[0199] Step S7: Obtain an estimated value of the building's carbon emissions based on the building's current characteristic values ​​and the carbon emissions calculation model.

[0200] Example 2

[0201] refer to Figure 2-5 The present invention provides a method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference, comprising the following steps:

[0202] 1. Construct a building structure prediction model and a building material prediction model to obtain a building structure prediction model and a building material prediction model that meet the preset accuracy:

[0203] Step S1: collecting data, collecting structure classification model data, including building data and building point of interest (POI) data, and collecting material classification model data, including street view images;

[0204] Wherein, step S1 includes the following steps:

[0205] Step S101: Obtain building data including building footprints, outlines, and attributes through a geographic information system, and collect building point of interest (POI) data through a web map.

[0206] Step S102: Collect street view images through real photos and online maps.

[0207] Step S2: Pre-training data processing: For the structure classification model data, the buildings are labeled and matched with the points of interest to obtain the structure classification model data set; for the material classification model data, the data is segmented and labeled to obtain the material classification model data set;

[0208] Wherein, step S2 includes the following steps:

[0209] Step S201: Processing the structural classification model data, manually annotating buildings with reference to building codes and technical standards, architectural publications, online satellite and street view maps, matching building data with point of interest (POI) data, and compiling to obtain a complete structural classification dataset in shp format (dataset 2);

[0210] Structural tags were defined, with five common building structure types—masonry, concrete frame, concrete frame with shear wall, concrete shear wall, and steel structure—used as structural tags to categorize the structural classification model data. Point of Interest (POI) data matching the selected buildings was crawled from Amap and represented in a four-tuple format: {POI ID, x-coordinate, y-coordinate, POI type code}. "POI ID" is the unique identifier for each POI; "x-coordinate" and "y-coordinate" are the latitude and longitude coordinates of the POI in the Amap coordinate system. These coordinates were then converted to the WGS 1984 Mercator World Coordinate System, the same coordinate system as the .shp file, to match the POIs to the buildings.

[0211] To ensure the accuracy of the annotations, the following are referenced:

[0212] Building codes and technical standards, which may include distinguishing features.

[0213] Related publications, such as journal articles, construction documents, and technical reports, may shed light on the building's structural type.

[0214] Online satellite and street view maps (such as Amap) for visual identification of building structures.

[0215] Based on the above codes and publications, the present invention proposes three assumptions to avoid confusion and resolve labeling conflicts: first, all masonry buildings have fewer than six stories; second, public buildings have fewer than 10 stories in concrete frame structures, while concrete frame-shear wall structures have 10 or more stories; and finally, residential buildings have 20 or more stories in concrete shear wall structures, while concrete frame-shear wall structures have 7 to 19 stories, and concrete frame structures have fewer than 7 stories.

[0216] Step S202: Use RoboFlow to segment and annotate the street view image to obtain an annotated material classification model dataset. The annotated material classification model dataset (dataset 1) is enhanced using techniques including random cropping, rotation, tilting, and noise blurring.

[0217] Step S203: Divide the structure classification dataset and the street view dataset into a training set and a test set.

[0218] Step S3: Establishing a machine learning-based building structure prediction model: extracting building features and calculating building feature values, evaluating and screening the building features, determining that the machine learning algorithm is a gradient boosting decision tree, establishing a machine learning-based building structure prediction model and training it, and obtaining a machine learning-based building structure prediction model that meets the preset accuracy; wherein the building features include building geometric features, building shape features, and building point of interest (POI) features.

[0219] Wherein step S3 comprises the following steps:

[0220] Step S301: extract building features; and calculate building feature values;

[0221] Step S302: Evaluate and screen building characteristics;

[0222] Step S303: Determine a machine learning algorithm and establish a building structure prediction model based on machine learning;

[0223] Step S304: training a building structure prediction model based on machine learning;

[0224] Step S305: Evaluate the prediction results of the machine learning-based building structure prediction model to obtain a machine learning-based building structure prediction model that meets a preset accuracy.

[0225] Wherein, step S302 of evaluating and screening building characteristics includes:

[0226] Use the feature scoring function to score each feature;

[0227] Sort the features by their ratings from highest to lowest.

[0228] Select features that rank in the top K of the preset positions.

[0229] In step S301, the calculation of the building characteristic value specifically includes:

[0230] The calculation of the building geometric characteristic values ​​includes the following steps:

[0231] Predefine the number of building floors and building height;

[0232] The height between floors is calculated using formula (1):

[0233] (1);

[0234] Use the geometry calculation function in the ArcGIS platform to calculate the outline area and perimeter of the building;

[0235] Simplify the building outline into a minimum bounding rectangle (MBR) that encloses the building. Calculate the length and width of the MBR using the ArcGIS minimum bounding rectangle geometry function; set the parameter to geometry type = Rectangle_By_WIDTH.

[0236] The length of the minimum bounding rectangle MBR is used to represent the true length of the building;

[0237] The width of the minimum bounding rectangle (MBR) is weighted and expressed as the true width of the building outline using the formula (2):

[0238] (2);

[0239] Calculate the height-to-width ratio and the length-to-width ratio of a building:

[0240] The height-to-width ratio of a building Use formula (3) to calculate:

[0241] (3);

[0242] The building's true length-to-width ratio Use formula (4) to calculate:

[0243] (4);

[0244] in, is the height between floors, is the building height, is the number of floors of the building; is the true width of the building outline, is the building's outline area, is the area of ​​the minimum bounding rectangle MBR that encloses the building outline, is the true length of the building, and are the length and width of the minimum bounding rectangle MBR respectively.

[0245] The building shape characteristic value of the building is calculated using formula (5):

[0246] (5);

[0247] in, is the shape irregularity of the building outline. Since the MBR area is always greater than or equal to the building area, its value range is (0, 1.0], and the lower the value, the higher the irregularity.

[0248] The calculation is done using the ArcGIS “Feature Vertices To Points” function with the parameter Point_Type set to ALL. This function splits the building outline into a series of line segments and points, with the number of vertices being the total number of these points.

[0249] The calculation of building point of interest (POI) feature values ​​includes the following steps:

[0250] Count the total number of building points of interest (POIs) and the total number of building points of interest (POI) types for each building;

[0251] The building point of interest POI type is evaluated step by step using a decision tree until a leaf node is reached. The leaf node indicates the building point of interest POI type, and the corresponding Boolean value is obtained according to the building point of interest POI type.

[0252] Building POI patterns in the training data are identified using a decision tree (maximum depth 9). Building POIs are evaluated step by step along the decision tree until a leaf node is reached, which indicates the main POI type.

[0253] The string value of the major POI type is then converted to a numeric feature using binary one-hot encoding, creating a Boolean feature for each possible value of the major POI type. For example, if majorPOIType has two values, 010000 and 020000, two Boolean features are generated: majorPOIType=010000 and majorPOIType=020000, each with a value of 0 or 1.

[0254] Finally, the majorPOIType feature has 16 major POI types, which are converted into 16 Boolean features.

[0255] In step S305, the model is evaluated using multiple indicators, including precision, recall, and F1 value;

[0256] Precision:

[0257] ;

[0258] Where: Pi is the precision of class i; tpi is the number of buildings correctly identified as class i (true positives); fpi is the number of buildings incorrectly identified as class i (false positives);

[0259] Recall:

[0260] ;

[0261] Where: R i is the recall of category i; fn i is the number of buildings that should be identified as class i but were not (false negatives);

[0262] F1 value:

[0263]

[0264] Among them: F1 i is the F1 value of category i, which measures the harmonic mean of precision and recall.

[0265] The present invention is a single-label multi-classification problem (i.e., each building can only belong to one category), so macro-based precision, recall, and F1 value are used to ensure that each category is equally weighted.

[0266] The formula for macro-average is as follows:

[0267] 1. Macro Precision:

[0268] ;

[0269] C is the total number of categories.

[0270] 2. Macro Recall:

[0271] ;

[0272] 3. Macro F1 value (Macro F1):

[0273] ;

[0274] Step S4: Establishing a deep learning-based building material prediction model: Performing data enhancement on the material classification model dataset, based on the YOLOV11 model, using the Swin Transformer V2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model, establishing a deep learning-based building material prediction model and training it to obtain a deep learning-based building material prediction model that meets the preset accuracy;

[0275] Wherein, step S4 includes the following steps:

[0276] Step S401: Annotate the street view image (e.g., material standards, door and window annotations, and viewpoint classification) to obtain an annotated material classification model dataset (dataset 1). This data is then enhanced using random cropping, rotation, tilting, and noise blurring techniques.

[0277] Random cropping: Randomly crop areas from the original image and enlarge them to the original size, allowing the model to focus on different areas.

[0278] Rotation: Rotate the image by a random angle to enable the model to adapt to changes in the image's orientation.

[0279] Tilt: Use affine transformation to adjust the tilt of the image to account for different shooting angles.

[0280] Noise and blur: Add Gaussian noise or perform Gaussian blur to improve the robustness of the model.

[0281] Step S402: Based on the YOLO V11 model, the feature extraction part of the YOLO V11 model is replaced by the Swin Transformer V2 or ConvNeXtV2 computer vision network to establish a building material prediction model based on deep learning;

[0282] YOLO V11 was chosen as the base model. YOLO V11 is an advanced object detection model known for its efficient detection capabilities and low computational requirements. YOLO divides the image into grids and predicts the object category and location within each grid, enabling fast and efficient detection.

[0283] The target detection formula is as follows:

[0284]

[0285] in:

[0286] Loss coord is the location loss, which evaluates the difference between the predicted bounding box and the true bounding box.

[0287] Loss confidence It is the confidence loss, indicating whether the predicted box contains an object.

[0288] Loss class It is the category loss, the loss of the object category in the prediction box.

[0289] In order to improve the feature extraction capability of the YOLO V11 model, its feature extraction module is replaced with two visual networks, SwinTransformer V2 or ConvNeXt V2:

[0290] Swin Transformer V2: uses a multi-head self-attention mechanism to divide the image into non-overlapping windows and perform self-attention calculations in each window, allowing the model to capture a wider range of features. Its formula is as follows:

[0291]

[0292] Among them, Q (query), K (key) and V (value) are matrices obtained by transforming the image block, d k is the scaling factor.

[0293] ConvNeXt V2: It is an improved structure based on the convolutional network, using deeper convolution layers and improved convolution kernel size to enhance the learning ability of features. The convolution calculation formula is:

[0294]

[0295] Among them, O(i, j) is the pixel value of the output image, I(i+m, j+n) is the pixel value of the input image, and K(m, n) is the convolution kernel.

[0296] Step S403: Optimizing the hyperparameters of the deep learning-based building material prediction model to select optimal hyperparameters;

[0297] Step S404: training the deep learning-based building material prediction model after hyperparameter optimization;

[0298] Step S405: Evaluate the trained deep learning-based building material prediction model to obtain a deep learning-based building material prediction model that meets a preset accuracy.

[0299] In step S405, the model is evaluated using precision, recall, average precision and F1 score as evaluation indicators;

[0300] The model is evaluated using precision, recall, mean average precision (mAP), and F1 score as indicators. The formula is as follows:

[0301] Precision:

[0302] ;

[0303] Among them, TP (True Positives) is the number of correctly predicted positive samples, and FP (False Positives) is the number of incorrectly predicted positive samples.

[0304] Recall:

[0305] ;

[0306] Among them, FN (False Negatives) is the number of samples that are actually positive but predicted to be negative.

[0307] Mean Average Precision (mAP): mAP is the average precision of all classes. For each class c, calculate the average precision (AP) at different thresholds and then average it over all classes:

[0308] ;

[0309] F1 score: The F1 value is the harmonic average of precision and recall, and the formula is as follows:

[0310] ;

[0311] These metrics comprehensively measure the model's classification performance. By comparing precision, recall, mAP, and F1 scores, we evaluate the model's recognition accuracy and generalization ability for building materials.

[0312] 2. Use the building structure prediction model and building material prediction model to calculate carbon emissions based on the current characteristics of the building:

[0313] Step S5: Collect the current status data of the building to be evaluated, and obtain the building structure characteristic value and the building material characteristic value respectively through the building structure prediction model based on machine learning and the building material prediction model based on deep learning, and obtain the building current status characteristic value;

[0314] Wherein, step S5 includes the following steps:

[0315] Step S501: collecting current feature values ​​of building features through a geographic information system, including building geometric feature values, building shape feature values, and building point of interest (POI) feature values;

[0316] Step S502: Collecting street view images of the current status of buildings through online maps;

[0317] Step S503: The machine learning-based building structure prediction model and the deep learning-based building material prediction model respectively obtain building structure characteristic values ​​and building material characteristic values, and obtain building status characteristic values; the building status characteristic values ​​include building structure category, building material ratio, building geometry characteristic value, building shape characteristic value and building point of interest (POI) characteristic value;

[0318] Step S504: sorting building structure categories, building material ratios, building geometric feature values, building shape feature values, and building point of interest (POI) feature values.

[0319] Among them, the building structure characteristic value obtained by the building structure prediction model based on machine learning includes the building structure type identified by the building structure prediction model based on machine learning, and the building structure volume Vmain body is calculated through street view image data. The total volume of the building is determined according to the proportion of the building structure volume in building structures of different structure types, different numbers of floors and heights.

[0320] The main reference material "Building Structure" was used to obtain the proportion of building structures in different structures, different numbers of floors and heights.

[0321] Frame structure: The structural volume accounts for about 10%-15% of the total volume;

[0322] Shear wall structure: the structural volume accounts for 15%-20% of the total volume;

[0323] Steel structure: The structural volume accounts for 8%-12% of the total volume;

[0324] Low-rise buildings (1-3 floors): The structural volume accounts for a small proportion, usually around 10%-15%;

[0325] Medium- and high-rise buildings (4-20 floors): the structural volume accounts for between 15% and 20%;

[0326] Super high-rise buildings (more than 20 floors): the structural volume may account for 20%-25%;

[0327] Step S6: Constructing a carbon emission calculation model based on building structure characteristics, building material characteristics, and corresponding carbon emission factors;

[0328] Wherein step S6 comprises the following steps:

[0329] Step S601: Collect existing data to obtain carbon emission factors C of different structures 主体 and carbon emission factors C of different materials 维护 ;

[0330] Step S602: Obtaining the area and volume of the building through the building geometric feature values;

[0331] Step S603: Construct a building structure carbon emission model and a building material carbon emission model. Based on the building's area and volume, combined with the carbon emission coefficient corresponding to its structural type and materials, calculate the building's main structure carbon emissions and building envelope carbon emissions. The carbon emission calculation formula is as follows:

[0332] (6)

[0333] in:

[0334] : No. The volume of the structure ( );

[0335] : No. Carbon emission standard value of this structure ( );

[0336] : No. The carbon emission coefficient of each structure is used to adjust the impact of different structures;

[0337] : No. The surface area of ​​the material ( );

[0338] : No. Carbon emission standard value of the material ( );

[0339] : No. Carbon emission coefficients of different materials are used to take into account the characteristics of different materials;

[0340] : Carbon emissions from other construction processes ( );

[0341] : Total carbon emissions ( );

[0342] : total number of structures;

[0343] : Total number of materials;

[0344] Step S604: Evaluate the building structure carbon emission model and the building material carbon emission model;

[0345] Evaluate whether the calculation results are reasonable from the following four aspects

[0346] Compare to industry standards and reference values:

[0347] Compare the calculated carbon emissions with industry averages or reference values ​​from existing research to determine the rationality of the results. For example, you can compare them with carbon emission standards for similar buildings or data from relevant research.

[0348] Outlier Detection:

[0349] Check for outliers in the calculation results (such as unusually large carbon emissions) and analyze whether there are deviations between the data input and model calculations. Statistical analysis can be performed on the distribution of carbon emissions to identify and explain possible unreasonable data.

[0350] Sensitivity analysis:

[0351] Conduct sensitivity analysis on key parameters (such as carbon emission coefficient, building life, etc.) to determine the sensitivity of the results to parameter changes, thereby evaluating the robustness of the model and the rationality of the results.

[0352] Expert Assessment:

[0353] Invite experts in construction, carbon emissions or environmental science to review and evaluate the model results to ensure that the results are consistent with the reality of building carbon emissions.

[0354] Step S605: Obtain the final carbon emission calculation model.

[0355] Step S7: Obtain an estimated value of the building's carbon emissions based on the building's current characteristic values ​​and the carbon emissions calculation model.

[0356] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A building characterization carbon footprint estimation method based on artificial intelligence recognition and inference, characterized in that: The steps include: Step S1: collecting data, collecting structure classification model data, including building data and building point of interest (POI) data, and collecting material classification model data, including street view images; Step S2: Pre-training data processing: For the structure classification model data, the buildings are labeled and matched with the points of interest to obtain the structure classification model data set; for the material classification model data, the data is segmented and labeled to obtain the material classification model data set; Step S3: Establishing a machine learning-based building structure prediction model: extracting building features and calculating building feature values, evaluating and screening the building features, determining a machine learning algorithm, establishing and training a machine learning-based building structure prediction model, and obtaining a machine learning-based building structure prediction model that meets a preset accuracy; Step S4: Establishing a deep learning-based building material prediction model: Performing data enhancement on the material classification model dataset, based on the YOLOV11 model, using the Swin Transformer V2 or ConvNeXtV2 computer vision network to replace the feature extraction part of the YOLOV11 model, establishing a deep learning-based building material prediction model and training it to obtain a deep learning-based building material prediction model that meets the preset accuracy; Step S5: Collect the status data of the building to be evaluated, and obtain the building structure characteristic value and the building material characteristic value through the building structure prediction model based on machine learning and the building material prediction model based on deep learning, respectively, to obtain the building status characteristic value, which includes the building structure category, building material ratio, building geometry characteristic value, building shape characteristic value, and building point of interest (POI) characteristic value; Step S6: Constructing a carbon emission calculation model based on building structure characteristics, building material characteristics, and corresponding carbon emission factors; Step S7: Obtain an estimated value of the building's carbon emissions based on the building's current characteristic values ​​and the carbon emissions calculation model.

2. The method for estimating the building characterization carbon footprint based on artificial intelligence identification and inference according to claim 1 is characterized in that: Step S1 includes the following steps: Step S101: Obtain building data including building footprints, outlines, and attributes through a geographic information system, and collect building point of interest (POI) data through a web map; Step S102: Collect street view images through real photos and online maps.

3. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 1 is characterized in that: Step S2 includes the following steps: Step S201: Processing the structural classification model data, manually annotating buildings with reference to building codes and technical standards, building-related publications, online satellite and street view maps, matching the building data with point of interest (POI) data, and obtaining a complete structural classification dataset in shp format; Step S202: Use RoboFlow to segment and annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement on the annotated material classification model dataset; Step S203: Divide the structure classification dataset and the street view dataset into a training set and a test set.

4. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 3 is characterized in that: The labeled material classification model dataset is enhanced using techniques including random cropping, rotation, tilting, and noise blurring.

5. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 1 is characterized in that: Step S3 includes the following steps: Step S301: extracting building features; And calculate the building characteristic value; Step S302: Evaluate and screen building characteristics; Step S303: Determine a machine learning algorithm and establish a building structure prediction model based on machine learning; Step S304: training a building structure prediction model based on machine learning; Step S305: Evaluate the prediction results of the machine learning-based building structure prediction model to obtain a machine learning-based building structure prediction model that meets a preset accuracy.

6. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 5 is characterized in that: Assessment and screening of building characteristics include: Use the feature scoring function to score each feature; Sort the characteristics from high to low based on their ratings; Select features that rank in the top K of the preset positions.

7. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to any one of claims 1 to 6, characterized in that: Building features include building geometric features, building shape features, and building point of interest (POI) features.

8. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 7 is characterized in that: The calculation of building geometric characteristics includes the following steps: Predefine the number of building floors and building height; The height between floors is calculated using formula (1): （1）； Use the geometry calculation function in the ArcGIS platform to calculate the outline area and perimeter of the building; Simplify the building outline into the minimum bounding rectangle (MBR) surrounding the building, and calculate the length and width of the minimum bounding rectangle (MBR) using the minimum bounding geometry function of ArcGIS; The length of the minimum bounding rectangle MBR is used to represent the true length of the building; The width of the minimum bounding rectangle (MBR) is weighted and expressed as the true width of the building outline using the formula (2): （2）； Calculate the height-to-width ratio and the length-to-width ratio of a building: The height-to-width ratio of a building Use formula (3) to calculate: （3）； The building's true length-to-width ratio Use formula (4) to calculate: （4）； in, is the height between floors, is the building height, is the number of floors of the building; is the true width of the building outline, is the building's outline area, is the area of ​​the minimum bounding rectangle MBR that encloses the building outline, is the true length of the building, and are the length and width of the minimum bounding rectangle MBR respectively.

9. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 8 is characterized in that: The building shape characteristic value of the building is calculated using formula (5): （5）； in, is the shape irregularity of the building outline, with a value range of (0, 1.0], where lower values ​​indicate higher irregularity.

10. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 7 is characterized in that: The calculation of building point of interest POI feature values ​​includes the following steps: Count the total number of building points of interest (POIs) and the total number of building points of interest (POI) types for each building; The building point of interest POI type is evaluated step by step using a decision tree until a leaf node is reached. The leaf node indicates the building point of interest POI type, and the corresponding Boolean value is obtained according to the building point of interest POI type.

11. The method for estimating building carbon footprint based on artificial intelligence identification and inference according to claim 1 is characterized in that: The machine learning algorithm identified is gradient boosted decision tree.

12. The method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference according to claim 1 is characterized in that: The building structure characteristic values ​​obtained through the building structure prediction model based on machine learning include the building structure type identified by the building structure prediction model based on machine learning, and the building structure volume Vmain is calculated through street view image data. The total volume of the building is determined according to the proportion of the building structure volume in different structure types, different number of floors and heights.

13. The method for estimating building carbon footprint based on artificial intelligence recognition and inference according to claim 1 is characterized in that: Step S4 includes the following steps: Step S401: annotate the street view image to obtain an annotated material classification model dataset, and perform data enhancement using random cropping, rotation, tilting, and noise blurring techniques; Step S402: Based on the YOLO V11 model, the feature extraction part of the YOLO V11 model is replaced by the Swin Transformer V2 or ConvNeXtV2 computer vision network to establish a building material prediction model based on deep learning; Step S403: Optimizing the hyperparameters of the deep learning-based building material prediction model to select optimal hyperparameters; Step S404: training the deep learning-based building material prediction model after hyperparameter optimization; Step S405: Evaluate the trained deep learning-based building material prediction model to obtain a deep learning-based building material prediction model that meets a preset accuracy.

14. The method for estimating the carbon footprint of a building representation based on artificial intelligence identification and inference according to claim 7 is characterized in that: Step S5 includes the following steps: Step S501: collecting current feature values ​​of building features through a geographic information system, including building geometric feature values, building shape feature values, and building point of interest (POI) feature values; Step S502: Collecting street view images of the current status of buildings through online maps; Step S503: The machine learning-based building structure prediction model and the deep learning-based building material prediction model respectively obtain building structure characteristic values ​​and building material characteristic values, and obtain building status characteristic values, where the building status characteristic values ​​include building structure category, building material ratio, building geometry characteristic values, building shape characteristic values, and building point of interest (POI) characteristic values. Step S504: sorting building structure categories, building material ratios, building geometric feature values, building shape feature values, and building point of interest (POI) feature values.

15. The method for estimating building carbon footprint based on artificial intelligence identification and inference according to claim 14, characterized in that: Step S6 includes the following steps: Step S601: Collect existing data to obtain carbon emission factors C of different structures 主体 and carbon emission factors C of different materials 维护 ; Step S602: Obtaining the area and volume of the building through the building geometric feature values; Step S603: Construct a building structure carbon emission model and a building material carbon emission model. Based on the building's area and volume, combined with the carbon emission coefficient corresponding to its structural type and materials, calculate the building's main structure carbon emissions and building envelope carbon emissions. The carbon emission calculation formula is as follows: (6) in: : No. The volume of the structure ( ); : No. Carbon emission standard value of this structure ( ); : No. The carbon emission coefficient of each structure is used to adjust the impact of different structures; : No. The surface area of ​​the material ( ); : No. Carbon emission standard value of the material ( ); : No. Carbon emission coefficients of different materials are used to take into account the characteristics of different materials; : Carbon emissions from other construction processes ( ); : Total carbon emissions ( ); : total number of structures; : Total number of materials; Step S604: Evaluate the building structure carbon emission model and the building material carbon emission model; Step S605: Obtain the final carbon emission calculation model.

16. A building characterization carbon footprint estimation device based on artificial intelligence recognition and inference, characterized in that: The method comprises a processor, wherein the processor executes the steps of the method for estimating the carbon footprint of a building representation based on artificial intelligence recognition and inference according to any one of claims 1 to 15.

Images