Urban scale carbon emission accounting method, device and equipment fusing building attributes and storage medium

Abstract

The application relates to a building attribute-fused urban-scale carbon emission accounting method, device, equipment and storage medium. Building attribute information and energy consumption data of a target city are acquired, feature fusion processing and cluster analysis processing are performed on the building attribute information and the energy consumption data, and building energy consumption feature clusters are determined. A building carbon emission accounting channel library is constructed based on the building energy consumption feature clusters and carbon emission data of the target city, the building carbon emission accounting channel library comprising carbon emission accounting models corresponding to different building energy consumption feature clusters. A building energy consumption data set of the target city is acquired, carbon emission accounting is performed based on the building carbon emission accounting channel library and the building energy consumption data set, and a plurality of building carbon emission accounting data are obtained. A building carbon emission influence network of the target city is acquired, and carbon emission accounting results of the target city are determined based on the building carbon emission influence network and the plurality of building carbon emission accounting data. The method can improve the accuracy of urban-scale carbon emission accounting.

Description

Technical Field

[0001] This application relates to the field of carbon emission technology, and in particular to a method, apparatus, equipment and storage medium for calculating carbon emissions at the urban scale that integrates building attributes. Background Technology

[0002] Carbon emission accounting, as the core foundation of urban low-carbon management, is a crucial prerequisite for understanding carbon emission levels in the building sector and formulating scientific emission reduction strategies. As the primary carriers of energy consumption and carbon emissions, the reliability of carbon emission accounting results for urban buildings directly impacts the decomposition and implementation of carbon reduction targets, the assessment of emission reduction potential, and the optimization of low-carbon development pathways.

[0003] Therefore, there is an urgent need for a city-scale carbon emission accounting method that integrates building attributes. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for calculating urban-scale carbon emissions that integrates building attributes, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a city-scale carbon emission accounting method that integrates building attributes, including:

[0006] Obtain building attribute information and energy consumption data of the target city, and perform feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters;

[0007] Based on building energy consumption characteristic clusters and carbon emission data of target cities, a building carbon emission accounting channel library is constructed, which contains carbon emission accounting models corresponding to different building energy consumption characteristic clusters.

[0008] Obtain building energy consumption datasets for the target city, and perform carbon emission accounting based on the building carbon emission accounting channel library and building energy consumption datasets to obtain multiple building carbon emission accounting data.

[0009] Obtain the building carbon emission impact network for the target city, and based on the building carbon emission impact network and multiple building carbon emission accounting data, determine the carbon emission accounting results for the target city. The carbon emission accounting results are used to indicate the carbon emissions of the target city.

[0010] In one embodiment, feature fusion processing and cluster analysis are performed on building attribute information and energy consumption data to determine building energy consumption feature clusters. This includes: extracting associated features from building attribute information and energy consumption data to obtain a building attribute feature set and an energy consumption feature set; performing principal component analysis and feature filtering on the building attribute feature set and energy consumption feature set to obtain a key feature set of building attributes and a key feature set of energy consumption; performing time-series alignment and association fusion processing on the key feature set of building attributes and the key feature set of energy consumption to obtain a fused feature set of building energy consumption; and performing cluster analysis based on the fused feature set of building energy consumption to obtain building energy consumption feature clusters.

[0011] In one embodiment, cluster analysis is performed based on a building energy consumption fusion feature set to obtain building energy consumption feature clusters. This includes: performing cluster analysis on the building energy consumption fusion feature set to obtain multiple building energy consumption cluster result clusters; calculating the intra-cluster sum of squares for the multiple building energy consumption cluster result clusters to obtain multiple intra-cluster sums of squares, and determining the target number of clusters based on the multiple intra-cluster sums of squares of squares; and performing cluster analysis and cluster label assignment on the building energy consumption fusion feature set based on the target number of clusters to obtain multiple building energy consumption feature clusters.

[0012] In one embodiment, a building carbon emission accounting channel library is constructed based on building energy consumption feature clusters and carbon emission data of target cities. This includes: associating and identifying building energy consumption feature clusters and carbon emission data of target cities to obtain multiple feature cluster-carbon emission sample sets; selecting multiple feature cluster accounting model structures based on the data characteristics of multiple building energy consumption feature clusters and accounting requirements; and performing accounting fitting on multiple feature cluster-carbon emission sample sets based on the multiple feature cluster accounting model structures to construct the building carbon emission accounting channel library.

[0013] In one embodiment, a building carbon emission accounting channel library is constructed by performing accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures. This includes: performing accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to generate multiple initial accounting channel sets; performing cross-validation and iterative optimization on the multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets; and integrating the multiple carbon emission accounting channel sets according to multiple building energy consumption feature clusters to construct a building carbon emission accounting channel library.

[0014] In one embodiment, obtaining the building carbon emission impact network of a target city includes: obtaining the building distribution attributes of the target city, which include building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions; determining a set of individual buildings based on the building distribution attributes, and identifying each individual building in the set of individual buildings as a network node; performing edge influence degree analysis on the network nodes according to the building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions to obtain a set of node connection edge influence degrees; and performing directed topological connections between the network nodes based on the set of node connection edge influence degrees to obtain the building carbon emission impact network.

[0015] Secondly, this application also provides a city-scale carbon emission accounting device that integrates building attributes, including:

[0016] The building attribute information and energy consumption data are subjected to feature fusion processing and cluster analysis to determine building energy consumption feature clusters;

[0017] The execution module is used to build a building carbon emission accounting channel library based on building energy consumption feature clusters and carbon emission data of the target city. The building carbon emission accounting channel library contains carbon emission accounting models corresponding to different building energy consumption feature clusters.

[0018] The second acquisition module is used to acquire the building energy consumption dataset of the target city and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data.

[0019] The determination module is used to obtain the building carbon emission impact network of the target city, and based on the building carbon emission impact network and multiple building carbon emission accounting data, determine the carbon emission accounting results of the target city. The carbon emission accounting results are used to indicate the carbon emissions of the target city.

[0020] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the embodiments of the first aspect above.

[0021] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0022] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0023] The aforementioned urban-scale carbon emission accounting method, apparatus, computer equipment, computer-readable storage medium, and computer program product that integrates building attributes first acquires building attribute information and energy consumption data of the target city, and performs feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters. Then, based on the building energy consumption feature clusters and the carbon emission data of the target city, a building carbon emission accounting channel library is constructed. The building carbon emission accounting channel library contains carbon emission accounting models corresponding to different building energy consumption feature clusters. Next, the building energy consumption dataset of the target city is acquired, and carbon emission accounting is performed based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data. Finally, the building carbon emission impact network of the target city is acquired, and based on the building carbon emission impact network and multiple building carbon emission accounting data, the carbon emission accounting result of the target city is determined. The carbon emission accounting result is used to indicate the carbon emissions of the target city. The urban-scale carbon emission accounting method that integrates building attributes provided in this application makes full use of building attribute information in the process of determining carbon emission accounting results, effectively improving the accuracy of urban-scale carbon emission accounting and thus enhancing the efficiency of carbon emission management. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating a city-scale carbon emission accounting method that integrates building attributes in one embodiment.

[0026] Figure 2 This is a flowchart illustrating a method for determining building energy consumption characteristic clusters in one embodiment;

[0027] Figure 3 This is a flowchart illustrating a method for obtaining building energy consumption feature clusters in one embodiment;

[0028] Figure 4 This is a flowchart illustrating a method for constructing a building carbon emission accounting channel library in one embodiment;

[0029] Figure 5 This is a flowchart illustrating a method for constructing a building carbon emission accounting channel library in one embodiment;

[0030] Figure 6 This is a flowchart illustrating a method for obtaining a building carbon emission impact network in one embodiment;

[0031] Figure 7 This is a flowchart illustrating a city-scale carbon emission accounting method that integrates building attributes in another embodiment.

[0032] Figure 8 A structural block diagram of a city-scale carbon emission accounting device that integrates building attributes in one embodiment;

[0033] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0034] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0037] Carbon emission accounting, as the core foundation of urban low-carbon management, is a crucial prerequisite for understanding carbon emission levels in the building sector and formulating scientific emission reduction strategies. As the primary carriers of energy consumption and carbon emissions, the reliability of carbon emission accounting results for urban buildings directly impacts the decomposition and implementation of carbon reduction targets, the assessment of emission reduction potential, and the optimization of low-carbon development pathways.

[0038] Existing methods for calculating carbon emissions from urban buildings typically simplify a building to the product of its total energy consumption and a uniform emission factor, neglecting the specific differences in building attributes such as age, function, building envelope materials, and orientation. Because different building types have complex energy consumption structures, and their energy efficiency levels, usage patterns, and responses to the external environment vary, using a uniform emission factor for carbon emission accounting fails to effectively reflect the actual carbon emission levels of each building, leading to significant biases in the calculation results. Furthermore, existing methods ignore the mutual influence of carbon emissions between different buildings in a city. These interactions can lead to the superposition or offsetting of carbon emissions, thus affecting the accuracy of overall urban carbon emission accounting.

[0039] In view of this, this application provides a city-scale carbon emission accounting method that integrates building attributes. First, it acquires building attribute information and energy consumption data for the target city, and then performs feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters. Next, based on the building energy consumption feature clusters and the carbon emission data of the target city, it constructs a building carbon emission accounting channel library, which contains carbon emission accounting models corresponding to different building energy consumption feature clusters. Then, it acquires the building energy consumption dataset of the target city, and performs carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data. Finally, it acquires the building carbon emission impact network of the target city, and based on the building carbon emission impact network and multiple building carbon emission accounting data, it determines the carbon emission accounting result of the target city. The carbon emission accounting result is used to indicate the carbon emissions of the target city. The city-scale carbon emission accounting method that integrates building attributes provided in this application fully utilizes building attribute information in the process of determining the carbon emission accounting result, effectively improving the accuracy of city-scale carbon emission accounting, and thus enhancing the efficiency of carbon emission management.

[0040] The urban-scale carbon emission accounting method that integrates building attributes provided in this application can be implemented by computer equipment, which can be a terminal or a server.

[0041] In one exemplary embodiment, such as Figure 1 As shown, a city-scale carbon emission accounting method integrating building attributes is provided. This method includes the following steps:

[0042] Step 101: Obtain building attribute information and energy consumption data for the target city, and perform feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters.

[0043] Optionally, building attribute information can be various data used to describe the basic characteristics of a building, and this information affects the building's energy efficiency and carbon emission levels. Examples of building attribute information include, but are not limited to, building age, functional type, building structure, materials, number of floors, area, orientation, window type, and building envelope.

[0044] The functional types can include residential, commercial, and industrial. Residential buildings encompass residential and mixed-use housing. Within residential buildings, specific energy sources and their associated CO2 emissions include cooking, household lighting, refrigeration, hot water systems, washing machines, and other appliances. Commercial buildings include businesses, restaurants, retail spaces, and hotel services. CO2 emissions are quantified across different sectors, including food and beverage services, commercial HVAC, commercial lighting, commercial electrical equipment, and overall commercial electricity consumption. Public buildings involve functional buildings such as educational, medical, sports, and community service buildings. CO2 emissions calculations cover public HVAC systems, public lighting, public electrical equipment, and electricity consumption by public institutions.

[0045] Energy consumption data can be the energy consumption data of a building over a certain period of time, reflecting the building's energy efficiency and energy usage patterns. For example, energy consumption data can include electricity, heating, gas, and other consumption data, usually expressed monthly, quarterly, or annually.

[0046] Building energy consumption feature clusters can be collections of buildings with similar building attributes and consistent energy consumption patterns. For example, buildings within the same feature cluster can be highly similar in attributes such as building age, functional type, building structure, and building envelope. At the same time, their energy consumption intensity, temporal distribution patterns, and carbon emission levels, such as electricity, heating, and gas, also show convergent characteristics. Furthermore, there are significant differences in attributes and energy consumption patterns between different feature clusters.

[0047] In some exemplary embodiments, the computer device can acquire building attribute information and energy consumption data of the target city.

[0048] Specifically, computer equipment can obtain building attribute information of the target city through a building attribute information database, and obtain energy consumption data of the target city through an energy consumption database.

[0049] Furthermore, after acquiring building attribute information and energy consumption data of the target city, the computer equipment can perform feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters.

[0050] Specifically, computer equipment can first perform feature fusion processing on building attribute information and energy consumption data, and then perform cluster analysis on the feature fusion-processed building attribute information and energy consumption data to obtain building energy consumption feature clusters.

[0051] Step 102: Based on building energy consumption characteristic clusters and carbon emission data of target cities, construct a building carbon emission accounting channel library.

[0052] Carbon emission data for a target city refers to the carbon emission data corresponding to buildings in that city. For example, this includes greenhouse gas emissions directly or indirectly generated by buildings during their operation. Carbon emission data can be calculated based on the building's energy consumption.

[0053] For example, if the emission factor for electricity is 0.6 kg CO2e / kWh and the emission factor for gas is 2.16 kg CO2e / m³, heating energy consumption is uniformly calculated based on thermal equivalent (1 kWh of heat is approximately equal to 0.12 kg CO2e). Building T1 consumes 2000 kWh / month for electricity, 1500 kWh / month for heating, and 500 m³ / month for gas, resulting in carbon emissions of 2460 kg CO2e / month; Building T2 consumes 4500 kWh / month for electricity, 1400 kWh / month for heating, and 800 m³ / month for gas, resulting in carbon emissions of 4596 kg CO2e / month; Building T3 consumes 2200 kWh / month for electricity and 1600 kWh / m³ for heating. For example, if the gas consumption is 600 m³ / month, the carbon emission is 2808 kg CO2e / month; for building T4, the electricity consumption is 1500 kWh / month, the heating energy consumption is 1200 kWh / month, and the gas consumption is 300 m³ / month, resulting in a carbon emission of 1692 kg CO2e / month; for building T5, the electricity consumption is 2100 kWh / month, the heating energy consumption is 1700 kWh / month, and the gas consumption is 650 m³ / month, resulting in a carbon emission of 2868 kg CO2e / month.

[0054] Optionally, the building carbon emission accounting channel library contains carbon emission accounting models corresponding to different building energy consumption characteristic clusters. Each carbon emission accounting model can predict carbon emissions based on the building's energy efficiency characteristics. Through the building carbon emission accounting channel library, carbon emission accounting can be performed quickly and accurately for different building types.

[0055] In some exemplary embodiments, after determining the building energy consumption feature clusters, the computer device can construct a building carbon emission accounting channel library based on the building energy consumption feature clusters and the carbon emission data of the target city.

[0056] Specifically, computer equipment can construct multiple carbon emission accounting models based on building energy consumption characteristic clusters and carbon emission data of target cities, and then construct a building carbon emission accounting channel library based on multiple carbon emission accounting models.

[0057] Step 103: Obtain the building energy consumption dataset of the target city, and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data.

[0058] Optionally, the building energy consumption dataset includes, but is not limited to, electricity consumption, heating energy consumption, cooling energy consumption, and gas energy consumption.

[0059] In some exemplary embodiments, a computer device may acquire a dataset of building energy consumption for a target city.

[0060] Specifically, computer equipment can use sensors and metering devices installed in buildings within the target city to monitor the energy consumption of each building in real time. This allows for the continuous collection and processing of building energy consumption data, resulting in a city building energy consumption dataset. The building energy consumption dataset includes energy consumption data for all buildings, typically recorded over time.

[0061] Furthermore, after acquiring the building energy consumption dataset of the target city, the computer equipment can perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data.

[0062] Specifically, computer equipment can perform matching and mapping in the building carbon emission accounting channel library based on the building energy consumption dataset. By matching the energy consumption data of each building with the corresponding carbon emission accounting model, the most suitable carbon emission accounting model for the building is selected for carbon emission accounting.

[0063] For example, if building A belongs to the low-energy-efficiency cluster, building B belongs to the high-energy-efficiency cluster, and building C belongs to the medium-energy-efficiency cluster, then based on the real-time energy consumption data of buildings A, B, and C, the appropriate carbon emission accounting model for low-energy-efficiency buildings, high-energy-efficiency buildings, and medium-energy-efficiency buildings is automatically selected from the building carbon emission accounting channel library to calculate carbon emissions.

[0064] Once the corresponding carbon emission accounting model is determined, carbon emission accounting is performed on each building using the building energy consumption dataset. This involves calculating carbon emissions from building energy consumption data through the corresponding carbon emission accounting channel, resulting in multiple building carbon emission accounting data sets. These data sets can reflect the actual carbon emissions of a building over a specific period, typically expressed in carbon dioxide equivalents (kgCO2e). For example, if building M has a monthly carbon emission of 1250 kgCO2e from electricity, 540 kgCO2e from heating, and 900 kgCO2e from gas, then the total carbon emission is 2690 kgCO2e / month.

[0065] Step 104: Obtain the building carbon emission impact network of the target city, and determine the carbon emission accounting results of the target city based on the building carbon emission impact network and multiple building carbon emission accounting data.

[0066] Among them, the carbon emission accounting results, namely the city-scale carbon emission accounting results, can be used to indicate the carbon emissions of the target city.

[0067] In some exemplary embodiments, a computer device can acquire a network of building carbon emission impacts on a target city.

[0068] Specifically, computer equipment can acquire the building distribution attributes of a target city and determine the building carbon emission impact network of the target city based on the building distribution attributes.

[0069] Furthermore, after acquiring the building carbon emission impact network of the target city, the computer equipment can determine the carbon emission accounting results of the target city based on the building carbon emission impact network and multiple building carbon emission accounting data.

[0070] Specifically, computer equipment can perform impact gain analysis and total value quantification on multiple building carbon emission accounting data according to the building carbon emission impact network to determine the carbon emission accounting results of the target city.

[0071] The aforementioned city-scale carbon emission accounting method integrating building attributes first acquires building attribute information and energy consumption data for the target city. It then performs feature fusion and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters. Next, based on these building energy consumption feature clusters and the target city's carbon emission data, a building carbon emission accounting channel library is constructed. This library contains carbon emission accounting models corresponding to different building energy consumption feature clusters. Then, the target city's building energy consumption dataset is acquired, and carbon emission accounting is performed based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data sets. Finally, a building carbon emission impact network for the target city is obtained, and based on this network and the multiple building carbon emission accounting data sets, the carbon emission accounting result for the target city is determined. This carbon emission accounting result indicates the target city's carbon emissions. The city-scale carbon emission accounting method integrating building attributes provided in this application fully utilizes building attribute information in the process of determining the carbon emission accounting result, effectively improving the accuracy of city-scale carbon emission accounting and thus enhancing the efficiency of carbon emission management.

[0072] In one exemplary embodiment, such as Figure 2 As shown, feature fusion and cluster analysis are performed on building attribute information and energy consumption data to determine building energy consumption feature clusters, including the following steps:

[0073] Step 201: Extract correlation features from building attribute information and energy consumption data to obtain building attribute feature set and energy consumption feature set.

[0074] In some exemplary embodiments, the computer device can perform correlation feature extraction on building attribute information and energy consumption data to obtain a building attribute feature set and an energy consumption feature set.

[0075] Specifically, computer equipment can extract features that have a significant impact on carbon emission accounting from building attribute information and energy consumption data, and obtain building attribute feature sets and energy consumption feature sets.

[0076] For example, building attribute feature set may include building type, age, building area, building materials, etc., and energy consumption features may include electricity consumption, gas consumption, hot water consumption, etc.

[0077] Step 202: Perform principal component analysis and feature screening on the building attribute feature set and energy consumption feature set to obtain the key feature set of building attributes and the key feature set of energy consumption.

[0078] In some exemplary embodiments, after obtaining the building attribute feature set and the energy consumption feature set, the computer device can perform principal component analysis and feature screening on the building attribute feature set and the energy consumption feature set to obtain the key feature set of building attributes and the key feature set of energy consumption.

[0079] Specifically, computer equipment can use principal component analysis (PCA) to transform high-dimensional data from building attribute feature sets and energy consumption feature sets into fewer principal components, thereby reducing the dimensionality of the data. PCA reduces redundant information by finding the directions that best represent the variance of the data, while retaining important information in the data.

[0080] For example, principal component analysis (PCA) identifies building type, age, building area, and building materials as the features with the greatest impact on building attributes, while electricity consumption, gas consumption, and hot water consumption are the features with the greatest impact on energy consumption. Following PCA, features that significantly affect the target variables (e.g., energy efficiency, carbon emissions) are selected from the extracted feature set, while those with less impact on the analysis results are removed, resulting in a key feature set for building attributes and a key feature set for energy consumption.

[0081] Step 203: Perform time-series alignment and correlation fusion processing on the key feature set of building attributes and the key feature set of energy consumption to obtain the building energy consumption fusion feature set.

[0082] In some exemplary embodiments, after obtaining the key feature set of building attributes and the key feature set of energy consumption, the computer device can perform time-series alignment and correlation fusion processing on the key feature set of building attributes and the key feature set of energy consumption to obtain the building energy consumption fusion feature set.

[0083] Specifically, computer equipment can perform time-series alignment of key feature sets for building attributes and key feature sets for energy consumption, ensuring that building attribute information and energy consumption data are consistent over time. For example, if energy consumption data is recorded monthly, while building attribute data is recorded yearly, the building attribute data can be repeated monthly to match the temporal resolution of the energy consumption data. After time-series alignment, the building attribute feature sets and energy consumption feature sets are correlated and fused to obtain a unified building energy consumption fusion feature set, which can contain comprehensive information about both building attributes and energy consumption data.

[0084] For example, suppose we analyze data from three buildings: Building A is a residential building with an area of ​​120 m², facing south, with monthly electricity consumption of 2000 kWh, monthly heating consumption of 1500 kWh, and monthly gas consumption of 500 m³; Building B is a commercial building with an area of ​​500 m², facing east, with monthly electricity consumption of 4000 kWh, monthly heating consumption of 3100 kWh, and monthly gas consumption of 1000 m³; Building C is a residential building with an area of ​​200 m², facing south, with monthly electricity consumption of 2200 kWh, monthly heating consumption of 1600 kWh, and monthly gas consumption of 600 m³. We extract building attribute features (function type, orientation) and energy consumption features (electricity, heating, and gas consumption), resulting in two feature sets: the building attribute feature set and the energy consumption feature set. Inputting the two feature sets into principal component analysis revealed that building type, area, and orientation have a significant impact on energy consumption, while electricity consumption and heating energy consumption have a significant impact on carbon emissions. Building attribute data is collected annually, while energy consumption data is recorded monthly. Therefore, the building attribute data can be repeated monthly to match the time dimension of the energy consumption data. These two feature sets are then correlated and merged to form a comprehensive feature set containing both building attribute and energy consumption information.

[0085] Step 204: Perform cluster analysis based on the building energy consumption fusion feature set to obtain building energy consumption feature clusters.

[0086] In some exemplary embodiments, after obtaining the building energy consumption fusion feature set, the computer device can perform cluster analysis based on the building energy consumption fusion feature set to obtain building energy consumption feature clusters.

[0087] Specifically, computer equipment can perform cluster analysis based on the building energy consumption feature set, and then determine the building energy consumption feature cluster based on the results of the cluster analysis.

[0088] In one exemplary embodiment, such as Figure 3 As shown, cluster analysis is performed based on the building energy consumption fusion feature set to obtain building energy consumption feature clusters, including the following steps:

[0089] Step 301: Perform cluster analysis on the building energy consumption integrated feature set to obtain multiple building energy consumption cluster results.

[0090] Optionally, clustering analysis is an unsupervised learning method that can be used to divide data into different clusters based on some similarity measure, with each cluster containing data points with similar characteristics.

[0091] In some exemplary embodiments, a computer device can perform cluster analysis on a set of building energy consumption features to obtain multiple clusters of building energy consumption clustering results.

[0092] Specifically, the computer equipment can select multiple different numbers of clusters to perform cluster analysis on the building energy consumption fusion feature set. The number of clusters is the preset number of clusters in the cluster analysis. Different numbers of clusters may yield different clustering results; therefore, choosing an appropriate number of clusters is crucial for the clustering effect. The number of clusters is a positive integer greater than or equal to 1. For example, if the number of clusters is 2, then buildings A and C are clustered into one cluster (low energy efficiency cluster), and building B is clustered into a separate cluster (high energy efficiency cluster).

[0093] Step 302: Calculate the intra-cluster sum of squares for multiple building energy consumption clusters to obtain the intra-cluster sum of squares for multiple energy consumption results, and determine the target number of clusters based on the intra-cluster sum of squares for multiple energy consumption results.

[0094] The intra-cluster sum of squares measures the sum of the squares of the distances between each data point within a cluster and the cluster center, indicating the density of the clustering. For example, a smaller intra-cluster sum of squares indicates a more concentrated cluster of data points and better clustering quality.

[0095] In some exemplary embodiments, after obtaining multiple building energy consumption clustering result clusters, the computer device can perform intra-cluster sum of squares calculation on the multiple building energy consumption clustering result clusters to obtain the intra-cluster sum of squares of multiple energy consumption result clusters.

[0096] Specifically, for each cluster of building energy consumption results, the computer device can calculate the Euclidean distance from each data point to the center of the cluster, and sum the squares of all distances to obtain the sum of squares within the cluster.

[0097] Furthermore, after obtaining the sum of squares within multiple energy consumption result clusters, the computer device can determine the target number of clusters based on the sum of squares within multiple energy consumption result clusters.

[0098] Specifically, as the number of clusters increases, the sum of squares within clusters typically decreases gradually. The rate of decrease slows down as the number of clusters increases. By calculating the changes in the sum of squares within clusters under different numbers of clusters and identifying the elbows where significant changes occur by calculating the rate of decrease, we can determine the optimal target number of clusters. That is, when the number of clusters increases to a certain extent, the rate of decrease in the sum of squares within clusters begins to level off, and further increasing the number of clusters has very limited effect on improving cluster quality.

[0099] The elbow rule is a method for selecting the optimal number of clusters. By calculating the sum of squares within each cluster at different numbers of clusters, it identifies the point where the rate of decrease in the sum of squares within each cluster sharply slows down; this point is called the elbow. The number of clusters corresponding to this point is usually the optimal number, i.e., the target number of clusters. The target number of clusters is the optimal number of clusters determined by the elbow rule, typically located at the point where the rate of decrease in the sum of squares within each cluster sharply slows down. For example, the sum of squares within each cluster is 1200 for a cluster of 2, 900 for a cluster of 3, 600 for a cluster of 4, 450 for a cluster of 5, and 400 for a cluster of 6. The decrease is significant from the number of clusters 2 to 3, while the decrease slows down noticeably from the number of clusters 4 to 5. The elbow point usually appears at the number of clusters 3 or 4, meaning that a cluster number of 3 or 4 is the target number of clusters.

[0100] Step 303: Perform cluster analysis and cluster label assignment on the building energy consumption fusion feature set based on the target cluster number to obtain multiple building energy consumption feature clusters.

[0101] In some exemplary embodiments, after determining the target number of clusters, the computer device can perform cluster analysis and cluster label assignment on the building energy consumption fusion feature set based on the target number of clusters to obtain multiple building energy consumption feature clusters.

[0102] Specifically, if the target number of clusters is 3, then the target number of clusters will be used to perform cluster analysis and cluster label assignment on the building energy consumption fusion feature set to obtain three building energy consumption feature clusters, each of which contains buildings with similar energy efficiency characteristics.

[0103] Multiple building energy consumption characteristic clusters are groups of buildings with similar energy efficiency characteristics. Buildings with similar electricity consumption, heating energy consumption, and other energy consumption characteristics may be grouped into the same cluster. By fully considering the differences in building attributes and energy consumption characteristics, cluster analysis can group buildings with similar energy efficiency characteristics into one category, enabling more accurate carbon emission accounting.

[0104] In one exemplary embodiment, such as Figure 4As shown, based on building energy consumption characteristic clusters and carbon emission data of target cities, a building carbon emission accounting channel library is constructed, including the following steps:

[0105] Step 401: Associate and identify the building energy consumption feature clusters with the carbon emission data of the target city to obtain multiple feature cluster-carbon emission sample sets.

[0106] In some exemplary embodiments, a computer device can associate and identify building energy consumption feature clusters with carbon emission data of a target city to obtain multiple feature cluster-carbon emission sample sets.

[0107] Specifically, computer equipment can first normalize the carbon emission data of the target city to ensure that the carbon emission data of different buildings are within the same standard range. The normalization process can be achieved by subtracting the minimum value from each carbon emission data point and then dividing by the range of carbon emission data (maximum value - minimum value), thus mapping all carbon emission data to the range [0, 1].

[0108] Furthermore, building energy consumption feature clusters are associated with standard carbon emission data. Each building is assigned to a corresponding feature cluster based on its energy consumption characteristics (such as electricity consumption, heating energy consumption, etc.). These feature clusters reflect different levels of building energy efficiency, forming multiple feature cluster-carbon emission sample sets. Each feature cluster-carbon emission sample set includes the building's energy consumption characteristics and the corresponding standard carbon emission value.

[0109] Step 402: Select multiple feature cluster calculation model structures based on the data characteristics and calculation requirements of multiple building energy consumption feature clusters.

[0110] In some exemplary embodiments, after obtaining multiple feature clusters—carbon emission sample sets—the computer device can select multiple feature cluster accounting model structures based on the data characteristics information and accounting requirements of multiple building energy consumption feature clusters.

[0111] Specifically, computer equipment can select an appropriate accounting model structure based on the characteristic data and carbon emission accounting requirements of each building energy consumption characteristic cluster. Since each cluster of buildings has different energy efficiency characteristics, it is necessary to select a suitable characteristic cluster accounting model structure based on the specific cluster's characteristics.

[0112] For example, a linear regression model is chosen for cluster 1 (low energy efficiency), a support vector machine model is chosen for cluster 2 (medium energy efficiency), and a random forest model is chosen for cluster 3 (high energy efficiency).

[0113] Step 403: Based on the multi-feature cluster accounting model structure, perform accounting fitting on multiple feature cluster-carbon emission sample sets to construct a building carbon emission accounting channel library.

[0114] In some exemplary embodiments, after obtaining multiple feature cluster accounting model structures and multiple feature cluster-carbon emission sample sets, the computer device can perform accounting fitting on multiple feature cluster-carbon emission sample sets based on the multiple feature cluster accounting model structures to construct a building carbon emission accounting channel library.

[0115] In some exemplary embodiments, a computer device can perform accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to obtain multiple carbon emission accounting channel sets, and then construct a building carbon emission accounting channel library based on the multiple carbon emission accounting channel sets.

[0116] In one exemplary embodiment, such as Figure 5 As shown, based on the multi-feature cluster accounting model structure, multiple feature cluster-carbon emission sample sets are calculated and fitted to construct a building carbon emission accounting channel library, including the following steps:

[0117] Step 501: Perform accounting fitting on multiple feature cluster-carbon emission sample sets based on the accounting model structure of multiple feature clusters to generate multiple initial accounting channel sets.

[0118] In some exemplary embodiments, a computer device may perform accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to generate multiple initial accounting channel sets.

[0119] Specifically, computer equipment can use multiple feature cluster calculation model structures to perform calculation fitting training on multiple feature cluster-carbon emission sample sets. Through training, each model can accurately predict or calculate its carbon emissions based on the building's energy consumption data.

[0120] For example, using data from cluster 1 (low-energy-efficiency buildings), a linear regression model is trained. The building's electricity consumption and heating energy consumption are used as input features, and carbon emissions are used as the target variable. A set of model parameters (e.g., regression coefficients) is obtained through training. Using data from cluster 2 (medium-energy-efficiency buildings), a support vector machine model is trained. By optimizing model parameters (e.g., kernel function, penalty parameter C), the model can predict carbon emissions based on electricity consumption and heating energy consumption, with the building's electricity consumption and heating energy consumption as input features and the predicted carbon emissions as output. Using data from cluster 3 (high-energy-efficiency buildings), by optimizing model parameters (e.g., number of trees, tree depth), the model can predict carbon emissions based on electricity consumption and heating energy consumption, with the building's electricity consumption and heating energy consumption as input features and the predicted carbon emissions as output.

[0121] The training process involves optimizing the model's parameters to achieve the best predictive performance on the given training data. After training, multiple initial sets of accounting channels are obtained, which are the preliminary carbon emission accounting models for each feature cluster.

[0122] Step 502: Perform cross-validation and iterative optimization on multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets.

[0123] In some exemplary embodiments, after generating multiple initial accounting channel sets, the computer device can perform cross-validation and iterative optimization on the multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets.

[0124] Specifically, cross-validation is performed for each initial validation channel. The purpose of cross-validation is to evaluate the model's generalization ability, ensuring it can adapt to new data and reducing the risk of overfitting. Through cross-validation, the dataset is divided into multiple subsets, and the model is trained and evaluated on different training and validation sets. After cross-validation, iterative tuning is performed, which involves continuously adjusting the model's parameters (such as learning rate, regularization parameters, etc.) to improve the model's accuracy.

[0125] For example, adjusting the regularization parameter in linear regression, or adjusting the number and depth of trees in a random forest. This process is accomplished using methods such as grid search or random search. After cross-validation and tuning, multiple optimized carbon emission accounting models are obtained, forming multiple sets of carbon emission accounting channels. The carbon emission accounting channel set is a collection of multiple optimized accounting models after cross-validation and iterative tuning, capable of accurately calculating carbon emissions for buildings with different feature clusters.

[0126] Step 503: Integrate multiple carbon emission accounting channel sets according to multiple building energy consumption characteristic clusters to construct a building carbon emission accounting channel library.

[0127] In some exemplary embodiments, after obtaining multiple sets of carbon emission accounting channels, the computer device can integrate and process the multiple sets of carbon emission accounting channels according to multiple building energy consumption characteristic clusters to construct a building carbon emission accounting channel library.

[0128] In one exemplary embodiment, such as Figure 6 As shown, obtaining the building carbon emission impact network of a target city includes the following steps:

[0129] Step 601: Obtain the building distribution attributes of the target city.

[0130] Optionally, building distribution attributes are various spatial distribution information and attribute characteristics of buildings in the target city, such as the functional type, scale, distribution location, and density of buildings. For example, building distribution attributes may include building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions.

[0131] The building-level dimension relates to the building itself and typically includes its function (e.g., residential, commercial, industrial), structure, area, and orientation, directly impacting energy consumption, carbon emissions, and energy-saving potential. The spatial distribution dimension describes the building's location and distribution within the urban space, including building density, geographical location (e.g., proximity to transportation hubs), and distances between buildings. The environmental interaction dimension considers the interaction between the building and its surrounding environment, including climate, surrounding green spaces, and traffic flow; these external factors influence energy efficiency and carbon emissions. For example, the design of green spaces and orientation can reduce the need for heating and air conditioning.

[0132] Step 602: Determine the set of individual buildings based on the building distribution attributes, and identify each individual building in the set of individual buildings as a network node.

[0133] In some exemplary embodiments, after obtaining the building distribution attributes of the target city, the computer device can determine a set of individual buildings based on the building distribution attributes, and identify each individual building in the set of individual buildings as a network node.

[0134] Specifically, computer equipment can extract the set of individual buildings from the building distribution attributes; that is, each individual building is treated as an independent entity, serving as a network node. In graph theory, a network node is the basic unit of a network. In the building carbon emission impact network, each building is considered a node. Nodes are connected by edges, representing the mutual influence between buildings. Through network analysis, the carbon emission relationships and impacts between buildings can be assessed.

[0135] Step 603: Perform edge influence analysis on network nodes according to architectural, spatial distribution, and environmental interaction dimensions to obtain the set of node connection edge influence.

[0136] In some exemplary embodiments, after determining network nodes, the computer device can perform edge influence analysis on the network nodes according to the building-level dimension, spatial distribution dimension, and environmental interaction dimension to obtain the node connection edge influence set.

[0137] Specifically, computer equipment can extract carbon emission impact features from the building-level dimension, spatial distribution dimension, and environmental interaction dimension to obtain building-level impact feature sets, spatial distribution impact feature sets, and environmental interaction impact feature sets.

[0138] This involves extracting carbon emission impact features at the building level, which means extracting carbon emission-related characteristics from the building's basic features. For example, a building's function type, area, age, and building materials all affect its energy efficiency and carbon emission levels. Residential and commercial buildings may have different energy efficiency requirements and carbon emission patterns, and the building's age also affects its energy efficiency (older buildings may have lower insulation performance, leading to higher heating energy consumption). For example, building A is a residential building with a floor area of ​​200m². 2 Built in 1990, this building has high heating energy consumption; therefore, its building-level impact characteristics include: residential function type, building year (1990), and building area (200m²). 2 The building-level impact feature set is a set of all features that affect building carbon emissions extracted from the building-level dimension, including the building's function type, area, structure, etc.

[0139] Extracting carbon emission impact features from the spatial distribution dimension involves extracting features affecting carbon emissions from the spatial distribution characteristics of buildings. For example, a building's geographical location, proximity to transportation hubs, surrounding building density, and the presence of surrounding greenery all influence a building's energy demand and carbon emissions. High-density building clusters may reduce car use due to convenient public transportation, thereby reducing carbon emissions. For instance, building B, located in the city center with convenient transportation and high green coverage, can effectively reduce carbon emissions. Therefore, the spatial distribution impact features of building B include: geographical location (city center), transportation convenience (proximity to bus stops), and surrounding greenery. The spatial distribution impact feature set is the set of features affecting carbon emissions extracted from the spatial distribution dimension, typically including the building's geographical location, density, transportation convenience, and surrounding facilities.

[0140] Extracting carbon emission impact features from the environmental interaction dimension involves identifying the interactive effects between a building and its surrounding environment. For example, a building's orientation, surrounding climate conditions, the impact of greenbelts, and urban wind conditions can all affect a building's energy consumption and carbon emissions. South-facing buildings may be more energy efficient than north-facing buildings, and warmer climates may require less heating energy. The environmental interaction impact feature set is a set of features extracted from the environmental interaction dimension, reflecting the relationship between a building and its surrounding environment (such as climate, green spaces, and the impact of surrounding buildings).

[0141] Furthermore, computer equipment can use measurement algorithms to correlate the various impact features in the building-level impact feature set, the spatial distribution impact feature set, and the environmental interaction impact feature set to obtain a set of carbon emission impact feature measurement algorithms. In other words, mathematical algorithms are used to quantitatively measure the impact features in dimensions such as building-level, spatial distribution, and environmental interaction, and to assess the degree of impact of each feature on carbon emissions.

[0142] For example, linear regression models are used to assess how features such as building area and building age affect carbon emissions; support vector machines are used to assess the nonlinear impact of features such as spatial location and green space ratio on carbon emissions; and random forests are used to handle complex nonlinear relationships between features, making them suitable for multi-feature carbon emission prediction. For each dimension's impact feature, an appropriate metric algorithm is selected to quantify it. For example, regression analysis is used to assess how building area (building-level feature) affects carbon emissions, or support vector machines are used to assess the impact of building location (spatial distribution feature) on carbon emissions. A metric is generated for each feature, representing the degree of its impact on carbon emissions. For example, building area may be positively correlated with carbon emissions, while building age may be negatively correlated with carbon emissions.

[0143] After performing measurement analysis on each feature, a set of carbon emission impact feature measurement algorithms is obtained. This set of algorithms includes the measurement results of the impact of different features (such as building area, geographical location, climate, etc.) on carbon emissions. The measurement result of each feature reflects its contribution to carbon emissions. For example, through regression analysis, it is found that for every 10m² increase in building area... 2 Carbon emissions increase by 10 kg CO2e / month. Support vector machine analysis revealed that buildings located in city centers emit 20% more carbon than those in suburban areas.

[0144] Furthermore, edge influence analysis is performed on network nodes based on a set of carbon emission impact feature measurement algorithms to obtain a set of node connection edge influence degrees. That is, edge influence analysis is performed on network nodes based on a set of carbon emission impact feature measurement algorithms to obtain a basic network edge influence degree set; influence weights are assigned to the building-level influence feature set, spatial distribution influence feature set, and environmental interaction influence feature set to determine carbon emission impact feature weight factors; and the basic network edge influence degree set is weighted and quantized according to the carbon emission impact feature weight factors to obtain the set of node connection edge influence degrees.

[0145] Edge influence reflects the degree to which carbon emissions between two buildings influence each other. It can be understood as the degree to which buildings influence each other due to similarities or connections in factors such as geographical location, functional type, building area, and environmental interaction. For example, buildings located in the same area may share energy supply and transportation networks, resulting in a certain correlation in their carbon emissions. In graph theory, an edge represents the connection between two nodes. In a carbon emission impact network, edge influence refers to the degree to which carbon emissions between buildings influence each other. The purpose of edge influence analysis is to quantify the carbon emission impact between different buildings. Edge influence analysis is performed on network nodes using a set of carbon emission impact feature measurement algorithms, that is, the influence analysis is performed on the edges between all buildings, resulting in a basic network edge influence set containing the influence values ​​of all edges between buildings. The basic network edge influence set demonstrates the mutual influence relationships between buildings, that is, the degree of interaction between carbon emissions between each pair of buildings.

[0146] The impact weights of the building-level impact feature set, spatial distribution impact feature set, and environmental interaction impact feature set are calibrated to determine the weight factors for carbon emission impact features, quantifying the relative importance of each feature's impact on carbon emissions. In other words, a weight factor is assigned to each impact feature. For example, through calibration, the weight factor for building area is 0.5 (indicating that building area has a significant impact on carbon emissions), the weight factor for building age is 0.3 (older buildings may have lower energy efficiency and a greater impact), the weight factor for location (city center and suburbs) is 0.1, and the weight factor for green coverage is 0.1 (green coverage has some impact on carbon emissions).

[0147] After obtaining the weighting factors for carbon emission impact features, these factors are applied to the edge influence set of the basic network for weighted quantization calculation. The edge influence between buildings is weighted according to the weight of each feature to obtain the final carbon emission impact between any two buildings. The weighted quantization calculation process essentially involves weighting the connections (edges) between buildings based on their similarity and weighting factors, thereby quantifying the magnitude of mutual carbon emission influence. For example, assuming the initial edge influence between building A and building B is 0.8, the building area weighting factor for building A is 0.5, and the building area weighting factor for building B is 0.4, then the final weighted influence is 0.28. The node connection edge influence set is the set of influence between building nodes obtained after weighted quantization calculation, reflecting the degree of mutual carbon emission influence between each building node and other building nodes.

[0148] Step 604: Based on the set of influence degrees of node connection edges, perform directed topological connections on network nodes to obtain the building carbon emission impact network.

[0149] In some exemplary embodiments, after obtaining the set of node connection edge influence degrees, the computer device can perform directed topological connections between network nodes based on the set of node connection edge influence degrees to obtain the building carbon emission impact network.

[0150] Specifically, computer equipment can utilize the set of influence values ​​of node connection edges to construct directed topological connections based on the strength of the mutual influence of carbon emissions between buildings. Each pair of building connections represents the mutual influence of their carbon emissions, and the direction of the edge indicates the direction of the influence. For example, the carbon emissions of building A may affect building B, or the energy efficiency level of building B may affect the carbon emissions of building A. The connection edges between each building are weighted according to their influence values; the higher the influence value, the stronger the mutual influence of carbon emissions.

[0151] Specifically, for each pair of building nodes, such as A, B, and C, the carbon emission impact degree between them is checked, for example, 0.8, 0.5, etc. Based on the impact degree value, a directed edge is added between each pair of buildings, where the direction and weight of the edge represent the carbon emission impact relationship. If the impact degree of building A on building B is greater than 0, an edge is added from A to B, and vice versa.

[0152] The building carbon emissions impact network consists of all building nodes and the edges connecting them. Through the network's topology, it can reveal which buildings have a strong carbon emissions impact and which buildings contribute significantly to the overall city's carbon emissions. In the building carbon emissions impact network, each building is connected to other buildings through edges, and the influence of these edges quantifies the carbon emissions relationships between them.

[0153] For example, building A has a strong impact on the carbon emissions of building B, building B also affects the carbon emissions of building C, and building A has a certain impact on building C. By constructing a building carbon emission impact network, the role of each building in the carbon emission network can be analyzed. For example, building A may be a key influencer of carbon emissions in the entire region because it has strong influence relationships with other buildings.

[0154] In some exemplary embodiments, computer equipment can perform impact gain analysis and total value quantification on multiple building carbon emission accounting data according to the building carbon emission impact network to determine the carbon emission accounting results of a target city.

[0155] Specifically, impact gain refers to how the interactions between buildings in a building carbon emission impact network lead to changes in carbon emissions. For example, the carbon emissions of building A may affect building B, and building B, in turn, affects building C; these interactions collectively influence the city's overall carbon emissions. The gain of these mutual carbon emission influences is calculated by analyzing the edge influence degree between every two buildings in the building carbon emission impact network, based on the influence degree of each building, its carbon emissions, and the influence relationships between buildings. Impact gain analysis examines how the interactions between buildings in the building carbon emission impact network increase or decrease carbon emissions. Impact gain analysis can reveal the dependencies and interactions between buildings, helping to understand how overall carbon emission levels change due to these connections. The carbon emission gains between all buildings can be calculated in a similar manner, yielding city-scale carbon emission gains based on the interrelationships between buildings.

[0156] Based on impact-gain analysis, total value quantification is performed. This involves aggregating the carbon emission data of all buildings and their interactions to obtain the total carbon emissions for the entire city or region. The contribution of each building to overall carbon emissions is calculated by weighting the impact between buildings. Each building's carbon emissions are affected not only by its own characteristics but also by its interactions with other buildings. By calculating the carbon emissions of all buildings and the impact gains between them, the overall carbon emission accounting result for the city is obtained. Total value quantification involves weighting and aggregating the carbon emissions of all buildings and calculating the total overall carbon emissions. The interactions between buildings are considered during total value quantification to make the calculation results more accurate.

[0157] The carbon emission accounting results for a target city can be obtained by summing the carbon emissions and impact gains of each building. The carbon emission accounting results reflect the total carbon emission level of the target city within a certain time frame and serve as an important basis for urban carbon emission management and policy formulation. Through impact gain analysis and total value quantification, the overall carbon emissions of the city can be calculated more accurately, taking into account the mutual influence between buildings and avoiding rough estimates based solely on the energy efficiency data of individual buildings. Quantifying the impact gains and total values ​​of carbon emissions helps to adjust carbon emission management strategies and measures in a timely manner.

[0158] In one exemplary embodiment, such as Figure 7 As shown, another method for calculating urban-scale carbon emissions that integrates building attributes is provided. This method includes the following steps:

[0159] Step 701: Obtain building attribute information and energy consumption data of the target city; extract correlation features from the building attribute information and energy consumption data to obtain building attribute feature sets and energy consumption feature sets; perform principal component analysis and feature filtering on the building attribute feature sets and energy consumption feature sets to obtain key feature sets of building attributes and key feature sets of energy consumption; perform time-series alignment and correlation fusion on the key feature sets of building attributes and key feature sets of energy consumption to obtain a fused feature set of building energy consumption.

[0160] Step 702: Perform cluster analysis on the building energy consumption fusion feature set to obtain multiple building energy consumption cluster result clusters; calculate the intra-cluster sum of squares for the multiple building energy consumption cluster result clusters to obtain multiple energy consumption result cluster intra-cluster sums of squares, and determine the target number of clusters based on the multiple energy consumption result cluster intra-cluster sums of squares; perform cluster analysis and cluster label assignment on the building energy consumption fusion feature set based on the target number of clusters to obtain multiple building energy consumption feature clusters;

[0161] Step 703: Associate and identify building energy consumption feature clusters with carbon emission data of target cities to obtain multiple feature cluster-carbon emission sample sets; select multiple feature cluster accounting model structures based on the data characteristics and accounting requirements of multiple building energy consumption feature clusters; perform accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to generate multiple initial accounting channel sets.

[0162] Step 704: Perform cross-validation and iterative optimization on multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets; integrate the multiple carbon emission accounting channel sets according to multiple building energy consumption feature clusters to construct a building carbon emission accounting channel library, which contains carbon emission accounting models corresponding to different building energy consumption feature clusters; obtain the building energy consumption dataset of the target city, and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data;

[0163] Step 705: Obtain the building distribution attributes of the target city, including building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions; determine the set of individual buildings based on the building distribution attributes, and identify each individual building in the set of individual buildings as a network node; perform edge influence analysis on the network nodes according to the building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions to obtain the node connection edge influence set; connect the network nodes in a directed topology based on the node connection edge influence set to obtain the building carbon emission impact network; and determine the carbon emission accounting result of the target city based on the building carbon emission impact network and multiple building carbon emission accounting data. The carbon emission accounting result is used to indicate the carbon emissions of the target city.

[0164] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0165] Based on the same inventive concept, this application also provides an urban-scale carbon emission accounting device that integrates building attributes for implementing the urban-scale carbon emission accounting method that integrates building attributes as described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more urban-scale carbon emission accounting device embodiments that integrate building attributes provided below can be found in the limitations of the urban-scale carbon emission accounting method that integrates building attributes described above, and will not be repeated here.

[0166] In one exemplary embodiment, such as Figure 8 As shown, a city-scale carbon emission accounting device 800 integrating building attributes is provided, comprising: a first acquisition module 801, an execution module 802, a second acquisition module 803, and a determination module 804, wherein:

[0167] The first acquisition module 801 is used to acquire building attribute information and energy consumption data of the target city, and to perform feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters.

[0168] Execution module 802 is used to construct a building carbon emission accounting channel library based on building energy consumption feature clusters and carbon emission data of target cities. The building carbon emission accounting channel library contains carbon emission accounting models corresponding to different building energy consumption feature clusters.

[0169] The second acquisition module 803 is used to acquire the building energy consumption dataset of the target city and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data.

[0170] The determination module 804 is used to obtain the building carbon emission impact network of the target city, and based on the building carbon emission impact network and multiple building carbon emission accounting data, determine the carbon emission accounting result of the target city. The carbon emission accounting result is used to indicate the carbon emission of the target city.

[0171] In one embodiment, the first acquisition module 801 is specifically used to extract correlation features from building attribute information and energy consumption data to obtain a building attribute feature set and an energy consumption feature set; to perform principal component analysis and feature screening on the building attribute feature set and energy consumption feature set to obtain a key feature set of building attributes and a key feature set of energy consumption; to perform time-series alignment and correlation fusion on the key feature set of building attributes and the key feature set of energy consumption to obtain a fused feature set of building energy consumption; and to perform cluster analysis based on the fused feature set of building energy consumption to obtain a cluster of building energy consumption features.

[0172] In one embodiment, the first acquisition module 801 is specifically used to perform cluster analysis on the building energy consumption fusion feature set to obtain multiple building energy consumption cluster result clusters; calculate the intra-cluster sum of squares on the multiple building energy consumption cluster result clusters to obtain multiple intra-cluster sums of squares of energy consumption result clusters, and determine the target number of clusters based on the multiple intra-cluster sums of squares of energy consumption result clusters; and perform cluster analysis and cluster label assignment on the building energy consumption fusion feature set based on the target number of clusters to obtain multiple building energy consumption feature clusters.

[0173] In one embodiment, the execution module 802 is specifically used to associate and identify building energy consumption feature clusters and carbon emission data of target cities to obtain multiple feature cluster-carbon emission sample sets; select multiple feature cluster accounting model structures according to the data characteristic information and accounting requirements of multiple building energy consumption feature clusters; and perform accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to construct a building carbon emission accounting channel library.

[0174] In one embodiment, the execution module 802 is specifically used to perform accounting fitting on multiple feature cluster-carbon emission sample sets based on multiple feature cluster accounting model structures to generate multiple initial accounting channel sets; to perform cross-validation and iterative optimization on the multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets; and to integrate the multiple carbon emission accounting channel sets according to multiple building energy consumption feature clusters to construct a building carbon emission accounting channel library.

[0175] In one embodiment, the second acquisition module 803 is specifically used to acquire the building distribution attributes of the target city, including building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions; determine a set of individual buildings based on the building distribution attributes, and identify each individual building in the set of individual buildings as a network node; perform edge influence degree analysis on the network nodes according to the building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions to obtain a set of node connection edge influence degrees; and perform directed topological connections on the network nodes based on the set of node connection edge influence degrees to obtain the building carbon emission impact network.

[0176] The modules in the aforementioned urban-scale carbon emission accounting device that integrates building attributes can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0177] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores XX data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a city-scale carbon emission accounting method that integrates building attributes.

[0178] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a city-scale carbon emission accounting method that integrates building attributes.

[0179] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0180] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the above embodiments.

[0181] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0182] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0183] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data that have been fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0184] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0185] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0186] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A city-scale carbon emission accounting method that integrates building attributes, characterized in that, The method includes: Obtain building attribute information and energy consumption data of the target city, and perform feature fusion processing and cluster analysis on the building attribute information and energy consumption data to determine building energy consumption feature clusters; Based on the building energy consumption feature clusters and the carbon emission data of the target city, a building carbon emission accounting channel library is constructed, which contains carbon emission accounting models corresponding to different building energy consumption feature clusters. Obtain the building energy consumption dataset of the target city, and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data; Obtain the building carbon emission impact network of the target city, and based on the building carbon emission impact network and the multiple building carbon emission accounting data, determine the carbon emission accounting result of the target city. The carbon emission accounting result is used to indicate the carbon emission amount of the target city.

2. The method according to claim 1, characterized in that, The process of performing feature fusion and cluster analysis on the building attribute information and the energy consumption data to determine building energy consumption feature clusters includes: The building attribute information and the energy consumption data are correlated with feature extraction to obtain a building attribute feature set and an energy consumption feature set. Principal component analysis and feature filtering are performed on the building attribute feature set and energy consumption feature set to obtain the key feature set of building attributes and the key feature set of energy consumption. The key feature set of building attributes and the key feature set of energy consumption are subjected to time-series alignment and correlation fusion processing to obtain the building energy consumption fusion feature set. Cluster analysis is performed based on the building energy consumption fusion feature set to obtain the building energy consumption feature cluster.

3. The method according to claim 2, characterized in that, The clustering analysis based on the building energy consumption fusion feature set to obtain the building energy consumption feature cluster includes: Cluster analysis is performed on the building energy consumption integrated feature set to obtain multiple building energy consumption clusters; The sum of squares within each cluster of the multiple building energy consumption clusters is calculated to obtain the sum of squares within each energy consumption cluster, and the target number of clusters is determined based on the sum of squares within each energy consumption cluster. Based on the target number of clusters, cluster analysis and cluster label assignment are performed on the building energy consumption fusion feature set to obtain the multiple building energy consumption feature clusters.

4. The method according to any one of claims 1 to 3, characterized in that, The construction of a building carbon emission accounting channel library based on the building energy consumption characteristic cluster and the carbon emission data of the target city includes: The building energy consumption feature clusters and the carbon emission data of the target city are associated and identified to obtain multiple feature cluster-carbon emission sample sets; Based on the data characteristics and accounting requirements of the multiple building energy consumption feature clusters, select multiple feature cluster accounting model structures; Based on the aforementioned multiple feature cluster accounting model structure, the multiple feature clusters-carbon emission sample sets are calculated and fitted to construct the building carbon emission accounting channel library.

5. The method according to claim 4, characterized in that, The method of performing calculation and fitting on the multiple feature clusters-carbon emission sample sets based on the multiple feature cluster calculation model structure to construct the building carbon emission calculation channel library includes: Based on the aforementioned multiple feature cluster accounting model structure, the multiple feature clusters-carbon emission sample sets are calculated and fitted to generate multiple initial accounting channel sets; Cross-validation and iterative optimization are performed on the multiple initial accounting channel sets to obtain multiple carbon emission accounting channel sets; The multiple carbon emission accounting channel sets are integrated and processed according to the multiple building energy consumption characteristic clusters to construct the building carbon emission accounting channel library.

6. The method according to any one of claims 1 to 3, characterized in that, The process of obtaining the building carbon emission impact network of the target city includes: Obtain the building distribution attributes of the target city, including building-level dimensions, spatial distribution dimensions, and environmental interaction dimensions; Based on the building distribution attributes, a set of individual buildings is determined, and each individual building in the set of individual buildings is identified as a network node. The network nodes are analyzed for edge influence based on the architectural dimension, spatial distribution dimension, and environmental interaction dimension to obtain a set of node connection edge influence. The network nodes are connected in a directed topology based on the set of influence degrees of the node connection edges to obtain the building carbon emission impact network.

7. A city-scale carbon emission accounting device integrating building attributes, characterized in that, The device includes: The first acquisition module is used to acquire building attribute information and energy consumption data of the target city, and to perform feature fusion processing and cluster analysis processing on the building attribute information and energy consumption data to determine building energy consumption feature clusters. The execution module is used to construct a building carbon emission accounting channel library based on the building energy consumption feature clusters and the carbon emission data of the target city. The building carbon emission accounting channel library contains carbon emission accounting models corresponding to different building energy consumption feature clusters. The second acquisition module is used to acquire the building energy consumption dataset of the target city, and perform carbon emission accounting based on the building carbon emission accounting channel library and the building energy consumption dataset to obtain multiple building carbon emission accounting data. The determination module is used to obtain the building carbon emission impact network of the target city, and based on the building carbon emission impact network and the multiple building carbon emission accounting data, determine the carbon emission accounting result of the target city, wherein the carbon emission accounting result is used to indicate the carbon emission of the target city.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images