Public building carbon emission prediction method based on multi-source data processing

Abstract

The invention discloses a public building carbon emission prediction method based on multi-source data processing, relates to the technical field of carbon emission prediction, and aims to effectively quantify behavior factors based on a data driving mode and then take the behavior factors as extra multi-source data for prediction model training so as to predict the carbon emission of a public building. Therefore, the prediction model can further learn dynamic behavior factors on the basis of existing static building characteristics, environmental climate data and the like, so that the influence of personnel activities and equipment use conditions in the building on energy consumption can be more comprehensively considered; and the accuracy of predicting the carbon emission of the public building by the prediction model is obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission prediction, and in particular to a method for predicting carbon emissions from public buildings based on multi-source data processing. Background Art

[0002] The public building carbon emission prediction method based on multi-source data processing is a method that combines multiple data sources and technical means to accurately estimate the carbon dioxide and other greenhouse gas emissions generated by public buildings during their use. In order to more accurately predict the carbon emissions of public buildings, existing methods usually follow a series of specific steps. The following is a detailed description of these steps:

[0003] First, data collection is performed, including energy consumption data: by installing smart meters or sensors to monitor the use of different types of energy in the building, including electricity, gas, heat, etc., and ensure that the data can be transmitted to the data center on a regular basis; environmental and climate data: integrating outdoor temperature, humidity, wind speed, sunshine duration and other information from local weather stations or third-party APIs to provide the necessary background conditions for understanding building energy consumption; building characteristic data: recording and collating information about the static properties of the building, such as area, height, orientation, building materials and their insulation performance, construction year and design standards, etc.; operational data: using building automation systems (BAS), Internet of Things (IoT) devices or other monitoring methods to capture dynamic information such as personnel activity patterns (working hours, visitor flow), equipment operation status (start and stop times of air conditioning systems and lighting systems) in the building;

[0004] The collected data is then preprocessed, including cleaning and verification: removing or correcting outliers, erroneous records, and duplicates; confirming that the timestamps of all data points are correct; missing value processing: using interpolation methods to fill in blank data points, such as mean filling, nearest neighbor filling, or model-based estimation; standardization and normalization: converting various types of data into a unified format and unit for subsequent analysis; for numerical variables, standardization or normalization operations can be implemented to improve algorithm efficiency;

[0005] Next, we select the model. We often need to choose the appropriate modeling technology according to the nature of the problem and the characteristics of the data, such as linear regression, decision tree, random forest, support vector machine (SVM), artificial neural network (ANN), long short-term memory network (LSTM), etc. After comparing the performance of different models and considering factors such as their accuracy, computational complexity, training time and interpretability, we select the model that best suits the current task. Usually, the artificial neural network model is used.

[0006] Then, the model training is carried out, including dividing the data set: dividing the collected data into training set, validation set and test set to ensure that the model can perform well on known data and have strong generalization ability on unknown data; hyperparameter tuning: using grid search, random search or Bayesian optimization and other methods to find the optimal hyperparameter combination to achieve the best performance; cross-validation: using methods such as K-fold cross-validation to reduce the risk of overfitting while ensuring model stability and reliability;

[0007] Finally, once the model training is completed and verified, it is deployed in the actual environment to predict carbon emission trends in real time over a period of time in the future.

[0008] Although the above methods provide a comprehensive framework for predicting carbon emissions from public buildings, there are still significant challenges in practice, especially the following aspects:

[0009] Human behavioral habits, such as opening windows for ventilation and temperature settings, have an important impact on building energy consumption. However, this part of unstructured information has been ignored and has not been effectively incorporated into existing prediction models. This has, to a certain extent, reduced the accuracy of existing prediction models for predicting carbon emissions from public buildings.

[0010] Therefore, the prior art urgently needs a technical solution for public building carbon emission prediction method based on multi-source data processing. Summary of the invention

[0011] In order to solve the above technical problems, the present invention provides a method for predicting carbon emissions of public buildings based on multi-source data processing, which specifically includes the following steps:

[0012] Step S1, collecting energy consumption data, environmental climate data, building characteristic data and operation data of public buildings, and defining them as first data, and collecting behavioral factors of public buildings at the same time;

[0013] Step S2, performing quantitative processing on the behavior factors of the public building to obtain second data of the public building;

[0014] Step S2a, calculating a first score of each behavior factor of a public building;

[0015] Step S2a1: for each behavior factor, define at least two basic features respectively, and construct a feature vector for each behavior factor based on the at least two basic features;

[0016] Among them, the expression of the characteristic vector of each behavioral factor is: ;

[0017] In the formula, The feature vector representing the i-th behavioral factor; represents the kth basic feature of the i-th behavioral factor; k represents the number of basic features in the i-th behavioral factor;

[0018] Step S2a2: Based on historical data, define at least two influencing factors for each basic feature in the feature vector of each behavior factor;

[0019] Among them, the expression of the influencing factor of each basic feature in the feature vector of each behavioral factor is: ;

[0020] In the formula, The set of influencing factors of the kth basic feature in the feature vector representing the i-th behavioral factor; represents the mth influencing factor of the kth basic feature in the feature vector of the i-th behavior factor; m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavior factor, and m≥2k, that is, each basic feature has at least two influencing factors;

[0021] Step S2a3, based on each basic feature in the feature vector of each behavior factor and the influence factor of each basic feature in the feature vector of each behavior factor, calculate the influence value of each basic feature in the feature vector of each behavior factor;

[0022] The calculation formula for the influence value of each basic feature in the feature vector of each behavioral factor is: ;

[0023] In the formula, The influence value of the kth basic feature in the feature vector representing the i-th behavioral factor; Represents based on basic features m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavior factor, and m ≥ 2k, that is, each basic feature has at least two influencing factors;

[0024] Step S2a4: Based on the influence value of each basic feature, a first score of each behavior factor is calculated by weighted summation;

[0025] The calculation formula for the first score of each behavioral factor is: ;

[0026] In the formula, represents the first score of the ith behavioral factor; Represents the weight of the kth basic feature; The influence value of the kth basic feature in the feature vector representing the i-th behavioral factor;

[0027] Step S2b, dividing each behavioral factor into at least two categories according to different dimensions;

[0028] Step S2c, calculating a second score for each type of behavior factor based on the first score of each behavior factor in each type of behavior factor;

[0029] The calculation formula for the second score of each type of behavioral factor is: ;

[0030] In the formula, represents the second score of the qth category behavioral factor; represents the weight of the i-th behavioral factor; represents the first score of the ith behavioral factor; It means that the i-th behavior factor belongs to the q-th type of behavior factor;

[0031] Step S2d, combining the second scores of each type of behavioral factors to obtain a comprehensive score of all behavioral factors;

[0032] The calculation formula for the comprehensive score of all behavioral factors is: ;

[0033] In the formula, represents a composite score of all behavioral factors; represents the weight of the qth type of behavioral factor; represents the second score of the qth category behavioral factor; represents the number of behavioral factor categories;

[0034] Step S2e, counting the first score of each behavior factor, the second score of each type of behavior factor, and the comprehensive score of all behavior factors, and defining them as the second data of the public building;

[0035] Step S3, performing preprocessing on the first data and the second data, wherein the preprocessing includes cleaning, verification, missing value processing, standardization and normalization;

[0036] Step S4: constructing a carbon emission prediction model, and using the preprocessed first data and second data to train the carbon emission prediction model to obtain a trained carbon emission prediction model;

[0037] Step S5: Acquire real-time data to be input, and input the real-time data into the carbon emission prediction model to obtain a carbon emission prediction result.

[0038] The embodiments of the present invention have the following technical effects:

[0039] The present invention aims to effectively quantify behavioral factors in a data-driven manner and use them as an additional multi-source data for predictive model training. This enables the predictive model to further learn dynamic behavioral factors based on existing static building characteristics and environmental climate data, thereby more comprehensively considering the impact of human activities and equipment usage in buildings on energy consumption, thereby significantly improving the accuracy of the predictive model for carbon emissions prediction of public buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of a method for predicting carbon emissions from public buildings based on multi-source data processing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0043] Embodiment 1: Figure 1 As shown, the present invention provides a method for predicting carbon emissions from public buildings based on multi-source data processing, comprising the following steps:

[0044] Step S1, collecting energy consumption data, environmental climate data, building characteristic data and operation data of public buildings, and defining them as first data, and collecting behavioral factors of public buildings at the same time;

[0045] We will not elaborate on the means used to collect energy consumption data, environmental climate data, building feature data and operation data of public buildings. We will focus on how to collect behavioral factors of public buildings. First, behavioral sensors can be deployed in buildings, such as infrared sensors, cameras, access control systems, etc., to record people's activity trajectories, window opening for ventilation, temperature settings and other behaviors; secondly, questionnaires can be regularly distributed to building users to understand their daily behavior patterns, such as working hours, rest time, equipment usage habits, etc.; or mobile applications can be developed, and users can use the application to report their own behaviors, such as turning on and off lights, adjusting air-conditioning temperatures, etc.

[0046] Step S2, performing quantitative processing on the behavior factors of the public building to obtain second data of the public building;

[0047] Step S2a, calculating a first score of each behavior factor of a public building;

[0048] Step S2a1: for each behavior factor, define at least two basic features respectively, and construct a feature vector for each behavior factor based on the at least two basic features;

[0049] It is worth noting that the means of defining the basic characteristics of behavioral factors include but are not limited to: 1. Analyzing existing data using cluster analysis to identify characteristics that are highly correlated with energy consumption as the basic characteristics of behavioral factors; 2. Using traditional questionnaire surveys to understand the behavioral patterns of building users, so as to extract common behavioral characteristics and use them as the basic characteristics of behavioral factors.

[0050] For common behavioral factors in public buildings, the following basic characteristics can be defined but are not limited to:

[0051] 1. Timestamp: records the specific time when the behavior occurs, including date, hour, minute, etc. The main function is that behaviors in different time periods have different effects on energy consumption, such as weekdays and weekends, daytime and nighttime, etc.; 2. Frequency: the frequency of behavior, such as several times a day, several times a week, etc. The main function is that high-frequency behaviors may have a greater impact on energy consumption than low-frequency behaviors, such as frequently turning on and off lights or adjusting air-conditioning temperature; 3. Duration: the duration of each behavior, such as the time of opening windows for ventilation each time, the time of using equipment each time, etc. The main function is that long-term behaviors usually consume more energy, such as turning on air conditioning or lighting for a long time; 4. Intensity: the intensity or strength of the behavior, such as the range of changes in the air-conditioning temperature setting value, the brightness of the light, etc. The main function is that high-intensity behaviors may lead to higher energy consumption, such as quickly adjusting the air-conditioning temperature or using high-power equipment.

[0052] Among them, the expression of the characteristic vector of each behavioral factor is: ;

[0053] In the formula, The feature vector representing the i-th behavioral factor; represents the kth basic feature of the i-th behavioral factor; k represents the number of basic features in the i-th behavioral factor;

[0054] Step S2a2: Based on historical data, define at least two influencing factors for each basic feature in the feature vector of each behavior factor;

[0055] It is worth noting that the means of defining influencing factors based on historical data mainly involves analyzing historical data through regression models to find out the quantitative relationship between each basic feature and energy consumption, thereby determining the influencing factors;

[0056] For the above basic characteristics, the following influencing factors can be defined:

[0057] Influencing factors of timestamp: Influencing factor 1: time period of the day, morning, afternoon, evening, because energy consumption patterns are different in different time periods; Influencing factor 2: the difference between working days and weekends, because people's behavior patterns are quite different on working days and weekends;

[0058] Frequency influencing factors: Influence factor 1: The frequency of the behavior, such as several times a day, high-frequency behavior may lead to higher energy consumption; Influence factor 2: The cumulative number of behaviors. In the long run, the more cumulative times, the higher the total energy consumption;

[0059] Influencing factors of duration: Influencing factor 1: the duration of a single behavior. Long-term behavior usually consumes more energy; Influencing factor 2: the cumulative duration of the behavior, that is, the cumulative duration of the behavior over a period of time;

[0060] Influencing factors of intensity: Influencing factor 1: The intensity of the behavior, such as the amplitude of change in the temperature setting value. High-intensity behavior may lead to higher energy consumption. Influencing factor 2: The intensity of the behavior, such as the difference between quickly adjusting the temperature and slowly adjusting the temperature. Intense behavior may lead to higher instantaneous energy consumption.

[0061] Among them, the expression of the influencing factor of each basic feature in the feature vector of each behavioral factor is: ;

[0062] In the formula, The set of influencing factors of the kth basic feature in the feature vector representing the i-th behavioral factor; represents the mth influencing factor of the kth basic feature in the feature vector of the i-th behavior factor; m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavior factor, and m≥2k, that is, each basic feature has at least two influencing factors;

[0063] Step S2a3, based on each basic feature in the feature vector of each behavior factor and the influence factor of each basic feature in the feature vector of each behavior factor, calculate the influence value of each basic feature in the feature vector of each behavior factor;

[0064] The calculation formula for the influence value of each basic feature in the feature vector of each behavioral factor is: ;

[0065] In the formula, The influence value of the kth basic feature in the feature vector representing the i-th behavioral factor; Represents based on basic features m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavior factor, and m ≥ 2k, that is, each basic feature has at least two influencing factors;

[0066] Step S2a4: Based on the influence value of each basic feature, a first score of each behavior factor is calculated by weighted summation;

[0067] The calculation formula for the first score of each behavioral factor is: ;

[0068] In the formula, represents the first score of the ith behavioral factor; Represents the weight of the kth basic feature; The influence value of the kth basic feature in the feature vector representing the i-th behavioral factor;

[0069] Step S2b, dividing each behavioral factor into at least two categories according to different dimensions;

[0070] It is worth noting that the different dimensions can be divided according to the temporal nature of behavioral factors such as working days / rest days, spatial nature such as different rooms or areas, and types such as office, meeting, leisure, etc.

[0071] Step S2c, calculating a second score for each type of behavior factor based on the first score of each behavior factor in each type of behavior factor;

[0072] The calculation formula for the second score of each type of behavioral factor is: ;

[0073] In the formula, represents the second score of the qth category behavioral factor; represents the weight of the i-th behavioral factor; represents the first score of the ith behavioral factor; It means that the i-th behavior factor belongs to the q-th type of behavior factor;

[0074] Step S2d, combining the second scores of each type of behavioral factors to obtain a comprehensive score of all behavioral factors;

[0075] The calculation formula for the comprehensive score of all behavioral factors is: ;

[0076] In the formula, represents a composite score of all behavioral factors; represents the weight of the qth type of behavioral factor; represents the second score of the qth category behavioral factor; represents the number of behavioral factor categories;

[0077] It is worth noting that, in the above, the methods for determining the weight of each basic feature, the weight of each behavioral factor, and the weight of each type of behavioral factor are the same. Taking the method for determining the weight of the kth basic feature as an example, the influence value of the kth basic feature is first called, and then the influence values ​​of all basic features in the feature vector of the ith behavioral factor are counted and accumulated to obtain the total influence value, and then the influence value of the kth basic feature is ratioed to the total influence value to obtain the weight of the kth basic feature. By analogy, the method for determining the weight of each behavioral factor and the weight of each type of behavioral factor is consistent with the method for determining the weight of each basic feature mentioned above.

[0078] Step S2e, counting the first score of each behavior factor, the second score of each type of behavior factor, and the comprehensive score of all behavior factors, and defining them as the second data of the public building;

[0079] It is worth noting that the reason why the present application needs to classify the behavioral factors after calculating the first score of each behavioral factor, and further calculate the second score of each type of behavioral factor and the comprehensive score of all behavioral factors is that the behavioral factors are complex and multidimensional. Directly inputting the first score into the model may lose some important structural information. However, by classifying the behavioral factors and calculating the second score and the comprehensive score, a richer hierarchical representation can be provided for the model. The data at each level reflects the behavioral characteristics of different granularities. The first score reflects the influence of a single behavioral factor, the second score reflects the comprehensive influence of multiple behavioral factors in the same category, and the comprehensive score effectively reflects the overall influence of all behavioral factors. This multi-level data representation helps the model to more comprehensively understand the influence of behavioral factors on energy consumption, thereby effectively improving the accuracy of carbon emission prediction.

[0080] In addition, due to the diversity and dynamics of behavioral factors in public buildings, directly using the first score cannot fully capture these characteristics. However, by classifying and calculating the second score and the comprehensive score, the model can learn the associations and patterns between different categories of behavioral factors. This not only enhances the generalization ability of the model, enabling it to better cope with unseen data, but also improves the adaptability of the model in different scenarios. For example, the activity patterns of people in office buildings vary greatly on weekdays and weekends. Classification processing can ensure that the model can distinguish between these two situations, thereby more accurately predicting changes in carbon emissions in different time periods.

[0081] Step S3, performing preprocessing on the first data and the second data, wherein the preprocessing includes cleaning, verification, missing value processing, standardization and normalization;

[0082] Step S4: constructing a carbon emission prediction model, and using the preprocessed first data and second data to train the carbon emission prediction model to obtain a trained carbon emission prediction model;

[0083] It is worth noting that in the training stage of the carbon emission prediction model, its training process is basically the same as the training process of the existing model. The main difference is that a quantified behavioral factor, i.e., the second data, is added. Therefore, the training process of the carbon emission prediction model will not be described in detail here. In the specific training process, the long short-term memory network model is first selected as the main model architecture because it can effectively process time series data and has good dynamic behavior capture capabilities. Then, data preparation is performed, including first data composed of energy consumption data, environmental climate data, building feature data and operation data, and a method based on multi-source data processing to perform quantitative processing on the behavioral factors of public buildings, and obtain the first score of each behavioral factor, the second score of each type of behavioral factor and the second data composed of the comprehensive score of all behavioral factors. Since the first and second data have been pre-processed in step S3, Next, the first and second data need to be divided into three parts for model training, etc. The three parts include the training set: the first part is 70% of the data for training the model, including: energy consumption data, environmental climate data, building feature data, operation data, and behavioral factor data, that is, the second data; the second part is the validation set, that is, 15% of the data is used to adjust hyperparameters and monitor model performance, the data type is the same as above; the third part is the test set, that is, 15% of the data is used to finally evaluate the model performance, the data type is the same as above; then the model is initialized. The process should first define the number of layers and units. For example, define a model with two layers of LSTM units, each layer contains 64 LSTM units, and then initialize the weights, that is, use the Xavier or He initialization method to initialize the model weights to ensure a good distribution of the initial state, and then define the loss function used to measure the difference between the model prediction value and the true value. The calculation formula is: In the formula, Represents the difference between the model prediction value and the true value; Represents the total number of samples, that is, the number of samples in the data set; Represents the true value of the bth sample; Represents the predicted value of the b-th sample.

[0084] This loss function is the core objective function of model training. The smaller its value is, the closer the model prediction value is to the true value.

[0085] Then, hyperparameter tuning is performed. The specific method is to use the grid search method to try different hyperparameter combinations, such as learning rate (0.001, 0.01, 0.1), batch size (32, 64, 128), number of hidden layer units (32, 64, 128), etc., or to use the random search method to randomly select hyperparameter combinations in a large range for testing. The purpose of hyperparameter tuning is to find the optimal model configuration, thereby improving the prediction accuracy and generalization ability of the model. Common hyperparameters include learning rate, batch size, number of hidden layer units, regularization parameters, etc.; then, model training is performed. Specifically, the training data is first input into the model in batches, and the model parameters are gradually updated until the set number of iterations or convergence conditions are reached. The size of each batch should be adjusted according to the hardware resources, such as 32 or 64. Then, the loss value and the performance indicators on the validation set should be recorded regularly to ensure that the model does not overfit or underfit. Specifically, the learning process of the model should be intuitively displayed by drawing the loss curve and the accuracy curve. Finally, when the loss function value on the training set and the validation set tends to be stable, that is, the change amplitude is less than a certain threshold, such as 0.001, the model is considered to have converged. If the model has not fully converged but has reached the preset maximum number of iterations, such as 1000, the training is stopped, that is, the model training is completed, and then K-fold cross-validation is required to reduce the contingency caused by data partitioning and improve the generalization ability and stability of the model. Specifically, the data set is divided into K parts, K-1 parts are used as training sets each time, and the remaining part is used as a validation set, repeated K times, and the average result is used as the final evaluation index. The commonly used K value is 5 or 10. The evaluation indicators used in the validation include but are not limited to the mean absolute error, determination coefficient, etc.; finally, when the model performs well on the validation set and the test set, it is saved in a file format such as .h5 or .pkl for subsequent loading and deployment. At the same time, this newly added data type provides the model with richer dynamic information, enhances the model's expressiveness and generalization ability, reduces noise and redundancy, and makes the prediction results more accurate and reliable.

[0086] Step S5: Acquire real-time data to be input, and input the real-time data into the carbon emission prediction model to obtain a carbon emission prediction result.

[0087] It is worth noting that when real-time data is input into the carbon emission prediction model, it is necessary to first perform quantitative processing on the real-time behavior factors therein, and then the quantified real-time behavior factors can be combined with other real-time data to form input data, and input into the carbon emission prediction model. The carbon emission prediction model will then make predictions and obtain carbon emission prediction results, where other real-time data refers to newly acquired energy consumption data, environmental climate data, etc.; carbon emission prediction results can be carbon emission trends in future time periods, such as predicting the changing trend of carbon dioxide emissions from buildings in the next 24 hours, 7 days or a month; and specific numerical predictions, that is, providing specific carbon emission values, such as expected emissions per hour, day or month.

[0088] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0089] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting carbon emissions from public buildings based on multi-source data processing, characterized in that: The following steps are involved: Step S1, collecting energy consumption data, environmental climate data, building characteristic data and operation data of public buildings, and defining them as first data, and collecting behavioral factors of public buildings at the same time; Step S2, performing quantitative processing on the behavior factors of the public building to obtain second data of the public building; Step S2a, calculating a first score of each behavior factor of a public building; Step S2b, dividing each behavioral factor into at least two categories according to different dimensions; Step S2c, calculating a second score for each type of behavior factor based on the first score of each behavior factor in each type of behavior factor; Step S2d, combining the second scores of each type of behavioral factors to obtain a comprehensive score of all behavioral factors; Step S2e, counting the first score of each behavior factor, the second score of each type of behavior factor, and the comprehensive score of all behavior factors, and defining them as the second data of the public building; Step S3, performing preprocessing on the first data and the second data, wherein the preprocessing includes cleaning, verification, missing value processing, standardization and normalization; Step S4: constructing a carbon emission prediction model, and using the preprocessed first data and second data to train the carbon emission prediction model to obtain a trained carbon emission prediction model; Step S5: Acquire real-time data to be input, and input the real-time data into the carbon emission prediction model to obtain a carbon emission prediction result.

2. According to claim 1, a method for predicting carbon emissions from public buildings based on multi-source data processing is characterized in that: The first score of each behavioral factor of the public building is calculated, including: Step S2a1: for each behavior factor, define at least two basic features respectively, and construct a feature vector for each behavior factor based on the at least two basic features; Step S2a2: Based on historical data, define at least two influencing factors for each basic feature in the feature vector of each behavior factor; Step S2a3, based on each basic feature in the feature vector of each behavior factor and the influence factor of each basic feature in the feature vector of each behavior factor, calculate the influence value of each basic feature in the feature vector of each behavior factor; Step S2a4: Based on the influence value of each basic feature, a first score of each behavior factor is calculated by weighted summation.

3. The method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 2 is characterized in that: The expression of the characteristic vector of each behavioral factor is: ； In the formula, The feature vector representing the i-th behavioral factor; represents the kth basic feature of the ith behavioral factor; k represents the number of basic features in the ith behavioral factor.

4. The method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 3 is characterized in that: The expression of the influencing factor of each basic feature in the feature vector of each behavioral factor is: ； In the formula, The set of influencing factors of the kth basic feature in the feature vector representing the i-th behavioral factor; Represents the mth influencing factor of the kth basic feature in the feature vector of the i-th behavioral factor; m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavioral factor, and m≥2k, that is, each basic feature has at least two influencing factors.

5. The method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 4 is characterized in that: The calculation formula for the influence value of each basic feature in the feature vector of each behavioral factor is: ； In the formula, The influence value of the kth basic feature in the feature vector representing the i-th behavioral factor; Represents based on basic features The function of the jth impact factor; m represents the number of influencing factors of the kth basic feature in the feature vector of the i-th behavioral factor, and m≥2k, that is, each basic feature has at least two influencing factors.

6. A method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 5, characterized in that: The calculation formula for the first score of each behavioral factor is: ； In the formula, represents the first score of the ith behavioral factor; Represents the weight of the kth basic feature; Represents the influence value of the kth basic feature in the feature vector of the i-th behavioral factor.

7. The method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 6 is characterized in that: The calculation formula for the second score of each type of behavioral factor is: ； In the formula, represents the second score of the qth category behavioral factor; represents the weight of the i-th behavioral factor; represents the first score of the ith behavioral factor; It means that the i-th behavioral factor belongs to the q-th type of behavioral factor.

8. The method for predicting carbon emissions from public buildings based on multi-source data processing according to claim 7 is characterized in that: The calculation formula for the comprehensive score of all the behavioral factors is: ； In the formula, represents a composite score of all behavioral factors; represents the weight of the qth type of behavioral factor; represents the second score of the qth category behavioral factor; Represents the number of behavioral factor categories.

Images