Control system and method for green building structure capable of reducing carbon emissions

Abstract

The present application relates to the field of intelligent control, and specifically discloses a control system and method for a green building structure that can reduce carbon emissions. The control system uses a neural network model based on deep learning to mine the differential correlation characteristics between indoor temperature and humidity time series coordinated correlation characteristics and outdoor temperature and humidity time series coordinated correlation characteristics, so as to adaptively control the air outlet intensity of the air conditioner based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to a control system and method for a green building structure capable of reducing carbon emissions. Background Art

[0002] With climate change and the acceleration of urbanization, energy consumption and carbon emissions of buildings have become important issues in global environmental protection and sustainable development. Green buildings have become one of the key means to control carbon emissions and improve the ecological environment of buildings. Among them, the efficiency and energy saving of air conditioning systems are particularly important as they are one of the main sources of energy consumption in buildings.

[0003] Traditional air conditioning control methods often rely on artificial sensing of changes in external temperature to adjust the air conditioning accordingly. However, since everyone's body temperature is different, and the ability to perceive the external ambient temperature is also different, there is a great deal of subjectivity in the manual control method, which cannot meet the balance between the efficiency and effect of the air conditioning system and energy saving and environmental protection.

[0004] Therefore, an optimized control system for a green building structure that can reduce carbon emissions is desired, so as to reduce carbon emissions on the basis of improving the working efficiency and effect of air conditioning, making the air conditioning system more efficient and energy-saving. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a control system and method for a green building structure that can reduce carbon emissions, which uses a neural network model based on deep learning to mine the difference correlation characteristics between the indoor temperature and humidity time series coordinated correlation characteristics and the outdoor temperature and humidity time series coordinated correlation characteristics, so as to adaptively control the air outlet intensity of the air conditioner based on the actual indoor and outdoor temperature and humidity changes, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0006] According to one aspect of the present application, a control system for a green building structure capable of reducing carbon emissions is provided, comprising:

[0007] A data acquisition module, used to obtain indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period;

[0008] A data parameter time series distribution module, used for arranging the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the plurality of predetermined time points into an indoor temperature time series input vector, an indoor humidity time series input vector, an outdoor temperature time series input vector and an outdoor humidity time series input vector respectively according to the time dimension;

[0009] A data parameter time series association coding module, used for performing association coding on the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and performing association coding on the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix;

[0010] A bidirectional attention feature extraction module, used to pass the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix;

[0011] An indoor-outdoor transfer correlation module, used to calculate a transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix;

[0012] A feature optimization module, used for performing feature optimization on the transfer matrix to obtain an optimized transfer matrix; and

[0013] The air outlet intensity control module is used to pass the optimized transfer matrix through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label.

[0014] In the control system of the green building structure capable of reducing carbon emissions, the data parameter time series association coding module is used to: perform association coding on the indoor temperature time series input vector and the indoor humidity time series input vector according to the following association formula to obtain an indoor temperature-humidity association matrix; wherein the formula is: Where V1 represents the indoor temperature timing input vector, represents the transposed vector of the indoor temperature time series input vector, V2 represents the indoor humidity time series input vector, M1 represents the indoor temperature-humidity association matrix, Represents vector multiplication; and, the outdoor temperature time series input vector and the outdoor humidity time series input vector are associated and encoded using the following association formula to obtain an outdoor temperature-humidity association matrix; wherein the formula is: Wherein V3 represents the outdoor temperature time series input vector, represents the transposed vector of the outdoor temperature time series input vector, V4 represents the outdoor humidity time series input vector, M2 represents the outdoor temperature-humidity association matrix, Represents vector multiplication.

[0015] In the control system of the green building structure that can reduce carbon emissions, the bidirectional attention feature extraction module is used to: use each layer of the convolutional neural network model including the bidirectional attention mechanism module to perform the following on the input data in the forward transfer of the layer: convolution processing on the input data to obtain a convolution feature map; pooling the convolution feature map along the channel dimension to obtain a pooled feature map; and, nonlinear activation on the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation feature matrix and the outdoor temperature-humidity correlation feature matrix, and the input of the first layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix.

[0016] In the control system of the green building structure capable of reducing carbon emissions, the indoor and outdoor transfer association module is used to calculate the transfer matrix of the indoor temperature-humidity association characteristic matrix relative to the outdoor temperature-humidity association characteristic matrix using the following formula; wherein the formula is:

[0017]

[0018] Where M1 represents the indoor temperature-humidity correlation feature matrix, M2 represents the outdoor temperature-humidity correlation feature matrix, t Denotes the transfer matrix.

[0019] In the control system of the green building structure that can reduce carbon emissions, the feature optimization module is used to perform vector spectrum clustering agent learning fusion optimization on the transfer matrix according to the following optimization formula to obtain the optimized transfer matrix; wherein the optimization formula is:

[0020]

[0021]

[0022] Among them, M t is the transfer matrix, M ′ t is the optimized transfer matrix, V1~V n represents each row eigenvector of the transfer matrix, and D V is a distance matrix composed of the distances between every two corresponding row eigenvectors of the transfer matrix, exp(·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the value of the natural exponential function with the eigenvalues ​​of each position in the matrix raised to the power, ⊙ and Represent positional dot multiplication and matrix addition respectively.

[0023] In the control system of the green building structure that can reduce carbon emissions, the air outlet intensity control module includes: an expansion unit, used to expand the optimized transfer matrix into a classification feature vector based on a row vector or a column vector; a fully connected encoding unit, used to use multiple fully connected layers of the classifier to fully connect the classification feature vector to obtain an encoded classification feature vector; and a classification result generation unit, used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0024] According to another aspect of the present application, a control method for a green building structure capable of reducing carbon emissions is provided, comprising:

[0025] Obtain indoor temperature values, indoor humidity values, outdoor temperature values, and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period;

[0026] Arrange the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the plurality of predetermined time points into an indoor temperature time series input vector, an indoor humidity time series input vector, an outdoor temperature time series input vector and an outdoor humidity time series input vector respectively according to the time dimension;

[0027] Performing association coding on the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and performing association coding on the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix;

[0028] The indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix are respectively passed through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix;

[0029] Calculating a transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix;

[0030] Performing feature optimization on the transfer matrix to obtain an optimized transfer matrix; and

[0031] The optimized transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label.

[0032] According to another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the control method for the green building structure that can reduce carbon emissions as described above.

[0033] According to another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the control method of the green building structure capable of reducing carbon emissions as described above.

[0034] Compared with the prior art, the present application provides a control system and method for a green building structure that can reduce carbon emissions. The control system adopts a neural network model based on deep learning to mine the differential correlation characteristics between the indoor temperature and humidity time series coordinated correlation characteristics and the outdoor temperature and humidity time series coordinated correlation characteristics, so as to adaptively control the air outlet intensity of the air conditioner based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions and making the air conditioning system more efficient and energy-saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0036] Figure 1 A schematic diagram of a control system for a green building structure capable of reducing carbon emissions according to an embodiment of the present application;

[0037] Figure 2 A block diagram of a control system for a green building structure capable of reducing carbon emissions according to an embodiment of the present application;

[0038] Figure 3 A system architecture diagram of a control system for a green building structure capable of reducing carbon emissions according to an embodiment of the present application;

[0039] Figure 4 A flowchart of a convolutional neural network encoding in a control system of a green building structure that can reduce carbon emissions according to an embodiment of the present application;

[0040] Figure 5 A block diagram of an air flow intensity control module in a control system of a green building structure capable of reducing carbon emissions according to an embodiment of the present application;

[0041] Figure 6 A flow chart of a control method for a green building structure capable of reducing carbon emissions according to an embodiment of the present application;

[0042] Figure 7 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0044] Application Overview

[0045] As mentioned above, the traditional air conditioning control method is often to manually sense the changes in the outside temperature to adjust the air conditioning accordingly. However, since each person's body temperature is different, the perception of the outside environment temperature is also different. Therefore, there is a great deal of subjectivity in the manual control method, which cannot meet the balance between the working efficiency and effect of the air conditioning system and energy conservation and environmental protection. Therefore, an optimized control system for green building structures that can reduce carbon emissions is desired, so as to reduce carbon emissions on the basis of improving the working efficiency and effect of air conditioning, making the air conditioning system more efficient and energy-saving.

[0046] Accordingly, considering that in the actual control process of the air-conditioning system, in order to be able to intelligently perform adaptive control of the air-conditioning operation based on the actual external situation, thereby avoiding the problems of increased carbon emissions and poor working efficiency of the air-conditioning system caused by manual control, in the technical solution of the present application, it is expected to intelligently adjust the air outlet intensity level of the air-conditioning based on the indoor and outdoor temperature and humidity data. However, since the indoor and outdoor temperatures and humidity have their own dynamic change regularity in the time dimension, and the indoor temperature and humidity have a time-series collaborative correlation characteristic, the outdoor temperature and humidity also have a time-series collaborative correlation characteristic. At the same time, in order to be able to accurately and effectively control the air outlet intensity of the air-conditioning system, it is necessary to pay attention to the differential correlation between the indoor temperature and humidity time-series correlation characteristics and the outdoor temperature and humidity time-series correlation characteristics. Therefore, in this process, the difficulty lies in how to fully express the differential correlation feature distribution information between the indoor temperature and humidity time series coordinated correlation features and the outdoor temperature and humidity time series coordinated correlation features, so as to adaptively control the air conditioning air outlet intensity based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0047] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. The development of deep learning and neural networks provides new solutions and solutions for mining the differential correlation feature distribution information between the indoor temperature and humidity time series collaborative correlation features and the outdoor temperature and humidity time series collaborative correlation features. Those of ordinary skill in the art should know that the deep neural network model based on deep learning can be trained through appropriate strategies, such as the back propagation algorithm of gradient descent to adjust the parameters of the deep neural network model so that it can simulate the complex nonlinear associations between things, which is obviously suitable for simulating and establishing the differential correlation relationship between the indoor temperature and humidity time series collaborative correlation features and the outdoor temperature and humidity time series collaborative correlation features.

[0048] Specifically, in the technical solution of the present application, first, the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points within a predetermined time period are obtained. Next, considering that the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value all have dynamic change rules in the time dimension, therefore, in order to be able to fully express the difference correlation feature information between the indoor temperature and humidity time series collaborative correlation feature and the outdoor temperature and humidity time series collaborative correlation feature, it is necessary to first analyze the time series distribution information of the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value in the time dimension. Therefore, in the technical solution of the present application, the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value at the multiple predetermined time points are arranged according to the time dimension as the indoor temperature time series input vector, the indoor humidity time series input vector, the outdoor temperature time series input vector, and the outdoor humidity time series input vector, so as to respectively integrate the distribution information of the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value in the time series.

[0049] Then, since the indoor temperature value and the indoor humidity value have a time series collaborative correlation in the time dimension, that is to say, the indoor temperature and humidity affect each other and jointly determine the working mode of the air conditioner. Similarly, for the time series distribution information of the outdoor temperature value and the outdoor humidity value, there is also a time series correlation between the two. Therefore, in the technical solution of the present application, it is necessary to further associate the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity correlation matrix, and associate the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity correlation matrix, so as to respectively establish the time series distribution correlation between the indoor temperature value and the indoor humidity value, and the time series distribution correlation between the outdoor temperature value and the outdoor humidity value, which is conducive to the subsequent precise control of the air outlet intensity of the air conditioning system.

[0050] Further, a convolutional neural network model with excellent performance in implicit correlation feature extraction is used to perform feature mining of the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix respectively. In particular, considering the complexity of the temporal synergistic correlation features of the indoor temperature and humidity and the temporal synergistic correlation features of the outdoor temperature and humidity, the temporal correlation relationship between indoor and outdoor temperature and humidity cannot be fully and effectively portrayed by the traditional feature extraction method. Therefore, in the technical solution of the present application, the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix are respectively obtained by a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity correlation feature matrix and an outdoor temperature-humidity correlation feature matrix. It should be understood that the bidirectional attention mechanism can better capture the correlation information between temperature and humidity, so that the context information can be fully utilized to enhance the indoor temperature and humidity temporal correlation feature response and the outdoor temperature and humidity temporal correlation feature response, and suppress the background feature response. Specifically, the bidirectional attention module calibrates the attention weights of the entire indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix in the horizontal direction and the vertical direction respectively and obtains complex feature relationships, thereby being able to obtain local feature information from the global features of the space.

[0051] Next, the transfer matrix of the indoor temperature-humidity correlation feature matrix relative to the outdoor temperature-humidity correlation feature matrix is ​​further calculated to represent the differential correlation feature distribution information between the indoor temperature and humidity time series collaborative correlation features and the outdoor temperature and humidity time series collaborative correlation features, so as to more fully and accurately capture the information interaction and information transfer process between the indoor and outdoor temperature and humidity time series correlation features, which is conducive to the subsequent adaptive control of the air outlet intensity of the air conditioner. Then, the transfer matrix is ​​used as a classification feature matrix for classification processing in a classifier to obtain a classification result for representing the recommended air outlet intensity level label. In other words, the classification label of the classifier is the recommended air outlet intensity level label. Therefore, after obtaining the classification result, the air outlet intensity of the air conditioner can be adaptively controlled based on the classification result, thereby optimizing the working efficiency and effect of the air conditioning system and reducing carbon emissions.

[0052] In particular, in the technical solution of the present application, when calculating the transfer matrix of the indoor temperature-humidity correlation feature matrix relative to the outdoor temperature-humidity correlation feature matrix, since the eigenvalues ​​of the corresponding positions of the transfer destination matrix are obtained from the inner product between each row vector of the transfer matrix and each column vector of the transfer source matrix, the transfer matrix can be regarded as a feature matrix obtained by splicing the individual row vectors. Therefore, when the transfer matrix is ​​used as a whole for classification and regression through a classifier, it is expected to improve the classification effect by improving the integrity of the feature distribution of the transfer matrix.

[0053] Based on this, the applicant of the present application denotes the transfer matrix, for example, as M t Perform vector spectrum clustering agent learning fusion optimization to obtain the optimized transfer matrix, for example, denoted as M ′ t , M ′ t Specifically expressed as:

[0054]

[0055]

[0056] Among them, V1~V n Denotes the transfer matrix M t Each row vector of D V is a distance matrix consisting of the distances between corresponding eigenvectors.

[0057] Here, when the row vectors of the transfer matrix are concatenated and classified and regressed by the classifier, the internal class regression semantic features of each row vector will be confused with the synthetic noise features, resulting in ambiguity in the boundary between meaningful class regression semantic features and noise features. The vector spectral clustering agent learning fusion optimization introduces spectral clustering agent learning for representing the spatial layout and semantic similarity between vectors to utilize the conceptual information of the association between class regression semantic features and class regression scenarios, and implicitly supervises and propagates the potential association attributes between the row vectors of the transfer matrix, thereby improving the overall distribution dependence of the transfer matrix as a synthetic feature, thereby improving the classification effect of the transfer matrix through the classifier for classification and regression. In this way, the air outlet intensity of the air conditioner can be adaptively controlled based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0058] Based on this, the present application proposes a control system for a green building structure that can reduce carbon emissions, which includes: a data acquisition module, used to obtain indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period; a data parameter time series distribution module, used to arrange the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the multiple predetermined time points according to the time dimension as indoor temperature time series input vectors, indoor humidity time series input vectors, outdoor temperature time series input vectors, and outdoor humidity time series input vectors; a data parameter time series association coding module, used to association-code the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and to associate the outdoor temperature time series input vector and the outdoor humidity time series input vector with each other. The invention relates to a method for extracting an indoor temperature-humidity correlation matrix from a time series input vector and performing association coding to obtain an outdoor temperature-humidity correlation matrix; a bidirectional attention feature extraction module, which is used to pass the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity correlation feature matrix and an outdoor temperature-humidity correlation feature matrix; an indoor-outdoor transfer association module, which is used to calculate the transfer matrix of the indoor temperature-humidity correlation feature matrix relative to the outdoor temperature-humidity correlation feature matrix; a feature optimization module, which is used to perform feature optimization on the transfer matrix to obtain an optimized transfer matrix; and an air outlet intensity control module, which is used to pass the optimized transfer matrix through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label.

[0059] Figure 1 Schematic diagram of a control system for a green building structure that can reduce carbon emissions according to an embodiment of the present application. Figure 1 As shown, in this application scenario, a temperature sensor (e.g. Figure 1 V1) in the figure obtains the indoor temperature values ​​at multiple predetermined time points within a predetermined time period, and uses a temperature sensor (for example, Figure 1 V2) in the figure obtains the indoor humidity values ​​at multiple predetermined time points within a predetermined time period, and uses a temperature sensor (for example, Figure 1 V3) in the figure obtains the outdoor temperature values ​​at multiple predetermined time points within a predetermined time period, and, through a temperature sensor (for example, Figure 1 V4 shown in the figure) obtains the outdoor humidity values ​​at multiple predetermined time points within a predetermined time period. Then, the above data is input into a server (for example, Figure 1 In S), wherein the server is capable of processing the above-mentioned input data with the control algorithm of the green building structure that can reduce carbon emissions to generate a classification result for representing a recommended air outlet intensity level label.

[0060] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0061] Exemplary Systems

[0062] Figure 2 FIG. 1 is a block diagram of a control system for a green building structure that can reduce carbon emissions according to an embodiment of the present application. Figure 2 As shown, the control system 300 of the green building structure that can reduce carbon emissions according to the embodiment of the present application includes: a data acquisition module 310; a data parameter time series distribution module 320; a data parameter time series association encoding module 330; a two-way attention feature extraction module 340; an indoor and outdoor transfer association module 350; a feature optimization module 360; and an air outlet intensity control module 370.

[0063] Among them, the data acquisition module 310 is used to obtain the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points within a predetermined time period; the data parameter time series distribution module 320 is used to arrange the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at the multiple predetermined time points into an indoor temperature time series input vector, an indoor humidity time series input vector, an outdoor temperature time series input vector and an outdoor humidity time series input vector according to the time dimension; the data parameter time series association coding module 330 is used to associate and code the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and associate and code the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity correlation matrix; the bidirectional attention feature extraction module 340 is used to pass the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity correlation feature matrix and an outdoor temperature-humidity correlation feature matrix respectively; the indoor-outdoor transfer correlation module 350 is used to calculate the transfer matrix of the indoor temperature-humidity correlation feature matrix relative to the outdoor temperature-humidity correlation feature matrix; the feature optimization module 360 ​​is used to perform feature optimization on the transfer matrix to obtain an optimized transfer matrix; and the air outlet intensity control module 370 is used to pass the optimized transfer matrix through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label.

[0064] Figure 3 FIG. 1 is a system architecture diagram of a control system for a green building structure that can reduce carbon emissions according to an embodiment of the present application. Figure 3As shown, in the network architecture, the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points within a predetermined time period are first obtained by the data acquisition module 310; then, the data parameter time series distribution module 320 arranges the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points obtained by the data acquisition module 310 into indoor temperature time series input vector, indoor humidity time series input vector, outdoor temperature time series input vector and outdoor humidity time series input vector according to the time dimension; the data parameter time series association coding module 330 performs association coding on the indoor temperature time series input vector and the indoor humidity time series input vector obtained by the data parameter time series distribution module 320 to obtain an indoor temperature-humidity association matrix, and performs association coding on the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix. association matrix; the bidirectional attention feature extraction module 340 passes the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix obtained by the data parameter temporal association encoding module 330 through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix; then, the indoor-outdoor transfer association module 350 calculates the transfer matrix of the indoor temperature-humidity association feature matrix obtained by the bidirectional attention feature extraction module 340 relative to the outdoor temperature-humidity association feature matrix; the feature optimization module 360 ​​performs feature optimization on the transfer matrix calculated by the indoor-outdoor transfer association module 350 to obtain an optimized transfer matrix; further, the air outlet intensity control module 370 passes the optimized transfer matrix through a classifier to obtain a classification result, and the classification result is used to represent the recommended air outlet intensity level label.

[0065] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the data acquisition module 310 is used to obtain the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points within a predetermined time period. It should be understood that, considering that in the actual control process of the air-conditioning system, in order to be able to intelligently perform adaptive control of the air-conditioning work based on the actual external situation, thereby avoiding the problems of increased carbon emissions and poor working efficiency of the air-conditioning system caused by manual control, therefore, in the technical solution of the present application, the air outlet intensity level of the air conditioner can be intelligently adjusted based on indoor and outdoor temperature and humidity data. Therefore, in a specific example of the present application, first, the indoor temperature value, indoor humidity value, outdoor temperature value and outdoor humidity value at multiple predetermined time points within a predetermined time period are obtained by a temperature sensor.

[0066] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the data parameter time series distribution module 320 is used to arrange the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the multiple predetermined time points into indoor temperature time series input vectors, indoor humidity time series input vectors, outdoor temperature time series input vectors and outdoor humidity time series input vectors according to the time dimension. Considering that the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value all have dynamic change rules in the time dimension, in order to fully express the differential correlation feature information between the indoor temperature and humidity time series collaborative correlation features and the outdoor temperature and humidity time series collaborative correlation features, it is necessary to first analyze the time series distribution information of the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value in the time dimension. Therefore, in the technical solution of the present application, the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the multiple predetermined time points are arranged according to the time dimension as indoor temperature time series input vector, indoor humidity time series input vector, outdoor temperature time series input vector and outdoor humidity time series input vector, so as to respectively integrate the distribution information of the indoor temperature value, the indoor humidity value, the outdoor temperature value and the outdoor humidity value in time series.

[0067] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the data parameter time series association coding module 330 is used to associate the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and associate the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix. Since the indoor temperature value and the indoor humidity value have a time series collaborative association relationship in the time dimension, that is, the indoor temperature and humidity affect each other and jointly determine the working mode of the air conditioner. Similarly, for the distribution information of the outdoor temperature value and the outdoor humidity value in the time series, there is also a time series association relationship between the two. Therefore, in the technical solution of the present application, it is necessary to further associate and encode the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and to associate and encode the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix, so as to respectively establish the time series distribution association relationship between the indoor temperature value and the indoor humidity value, and the time series distribution association relationship between the outdoor temperature value and the outdoor humidity value, which is conducive to the subsequent precise control of the air outlet intensity of the air conditioning system. In a specific example of the present application, the indoor temperature time series input vector and the indoor humidity time series input vector are associated and encoded with the following association formula to obtain an indoor temperature-humidity association matrix; wherein, the formula is: Where V1 represents the indoor temperature timing input vector, represents the transposed vector of the indoor temperature time series input vector, V2 represents the indoor humidity time series input vector, M1 represents the indoor temperature-humidity association matrix, Represents vector multiplication; and, the outdoor temperature time series input vector and the outdoor humidity time series input vector are associated and encoded using the following association formula to obtain an outdoor temperature-humidity association matrix; wherein the formula is:

[0068]

[0069] Wherein V3 represents the outdoor temperature time series input vector, represents the transposed vector of the outdoor temperature time series input vector, V4 represents the outdoor humidity time series input vector, M2 represents the outdoor temperature-humidity association matrix, Represents vector multiplication.

[0070] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the bidirectional attention feature extraction module 340 is used to pass the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix. That is, in the technical solution of the present application, the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix are passed through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix. It should be understood that the bidirectional attention mechanism can better capture the correlation information between temperature and humidity, so that the context information can be fully utilized to enhance the indoor temperature and humidity temporal correlation feature response and the outdoor temperature and humidity temporal correlation feature response, and suppress the background feature response. Specifically, the bidirectional attention module calibrates the attention weights of the entire indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix from the horizontal direction and the vertical direction respectively and obtains complex feature relationships, so that local feature information can be obtained from the global features of the space. In a specific example, the convolutional neural network includes a plurality of neural network layers cascaded to each other, wherein each neural network layer includes a convolution layer, a pooling layer, and an activation layer. In the encoding process of the convolutional neural network, each layer of the convolutional neural network uses the convolution layer to perform convolution processing based on a convolution kernel on the input data during the forward transmission process of the layer, uses the pooling layer to perform pooling processing on the convolution feature map output by the convolution layer, and uses the activation layer to perform activation processing on the pooling feature map output by the pooling layer.

[0071] Figure 4 The flowchart of convolutional neural network coding in the control system of the green building structure that can reduce carbon emissions according to the embodiment of the present application is shown in FIG. Figure 4 As shown, in the convolutional neural network encoding process, it includes: using each layer of the convolutional neural network model including the bidirectional attention mechanism module to perform the following on the input data in the forward transfer of the layer: S210, convolution processing on the input data to obtain a convolution feature map; S220, pooling the convolution feature map along the channel dimension to obtain a pooled feature map; and, S230, nonlinear activation on the pooled feature map to obtain an activation feature map; wherein, the output of the last layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity association feature matrix and the outdoor temperature-humidity association feature matrix, and the input of the first layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix.

[0072] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the indoor and outdoor transfer association module 350 is used to calculate the transfer matrix of the indoor temperature-humidity association feature matrix relative to the outdoor temperature-humidity association feature matrix. That is, after obtaining the indoor temperature-humidity association feature matrix and the outdoor temperature-humidity association feature matrix, the transfer matrix of the indoor temperature-humidity association feature matrix relative to the outdoor temperature-humidity association feature matrix is ​​further calculated to represent the differential association feature distribution information between the indoor temperature and humidity time series collaborative association features and the outdoor temperature and humidity time series collaborative association features, so as to more fully and accurately capture the information interaction and information transfer process between the indoor and outdoor temperature and humidity time series association features, which is conducive to the subsequent adaptive control of the air conditioning outlet intensity. In a specific example of the present application, the transfer matrix of the indoor temperature-humidity association feature matrix relative to the outdoor temperature-humidity association feature matrix is ​​calculated by the following formula; wherein, the formula is:

[0073]

[0074] Where M1 represents the indoor temperature-humidity correlation feature matrix, M2 represents the outdoor temperature-humidity correlation feature matrix, t Denotes the transfer matrix.

[0075] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the feature optimization module 360 ​​is used to perform feature optimization on the transfer matrix to obtain an optimized transfer matrix. It should be understood that when calculating the transfer matrix of the indoor temperature-humidity correlation feature matrix relative to the outdoor temperature-humidity correlation feature matrix, since the eigenvalues ​​of the corresponding positions of the transfer destination matrix are obtained from the inner product between each row vector of the transfer matrix and each column vector of the transfer source matrix, the transfer matrix can be regarded as a feature matrix obtained by splicing the individual row vectors. Therefore, when the transfer matrix is ​​used as a whole for classification and regression through a classifier, it is expected to improve the classification effect by improving the integrity of the feature distribution of the transfer matrix. Based on this, the applicant of the present application optimizes the transfer matrix, for example, denoted as M t Perform vector spectrum clustering agent learning fusion optimization to obtain the optimized transfer matrix, for example, denoted as M ′ t , M ′ t Specifically expressed as:

[0076]

[0077]

[0078] Among them, M t is the transfer matrix, M ′ t is the optimized transfer matrix, V1~V n represents each row eigenvector of the transfer matrix, and D V is a distance matrix composed of the distances between every two corresponding row eigenvectors of the transfer matrix, exp(·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the value of the natural exponential function with the eigenvalues ​​of each position in the matrix raised to the power, ⊙ and Represent positional point multiplication and matrix addition, respectively. Here, when the row vectors of the transfer matrix are concatenated and classified and regressed through the classifier, the internal class regression semantic features of each row vector will be confused with the synthetic noise features, resulting in ambiguity in the boundary between meaningful class regression semantic features and noise features. The vector spectral clustering agent learning fusion optimization introduces spectral clustering agent learning for representing the spatial layout and semantic similarity between vectors to utilize the conceptual information of the association between class regression semantic features and class regression scenarios, and implicitly supervises and propagates the potential association attributes between the row vectors of the transfer matrix, thereby improving the overall distribution dependence of the transfer matrix as a synthetic feature, thereby improving the classification effect of the transfer matrix through the classifier for classification and regression. In this way, the air outlet intensity of the air conditioner can be adaptively controlled based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0079] Specifically, during the operation of the control system 300 of the green building structure that can reduce carbon emissions, the air outlet intensity control module 370 is used to pass the optimized transfer matrix through a classifier to obtain a classification result, and the classification result is used to represent the recommended air outlet intensity level label. In the technical solution of the present application, after obtaining the optimized transfer matrix, it is further used as a classification feature matrix to pass through a classifier to obtain a classification result for representing the recommended air outlet intensity level label. In other words, the classification label of the classifier is the recommended air outlet intensity level label. Therefore, after obtaining the classification result, the air outlet intensity of the air conditioner can be adaptively controlled based on the classification result, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions. Specifically, the classifier includes a plurality of fully connected layers and a Softmax layer cascaded with the last fully connected layer of the plurality of fully connected layers. Among them, in the classification processing of the classifier, the optimized transfer matrix is ​​first projected into a vector. For example, in a specific example, the optimized transfer matrix is ​​expanded along the row vector or column vector into a classification feature vector; then, the classification feature vector is fully connected encoded multiple times using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and then, the encoded classification feature vector is input into the Softmax layer of the classifier, that is, the encoded classification feature vector is classified using the Softmax classification function to obtain a classification label.

[0080] Figure 5 FIG. 1 is a block diagram of an air flow intensity control module in a control system of a green building structure that can reduce carbon emissions according to an embodiment of the present application. Figure 5 As shown, the air outlet intensity control module 370 includes: an expansion unit 371, used to expand the optimized transfer matrix into a classification feature vector based on a row vector or a column vector; a fully connected encoding unit 372, used to use multiple fully connected layers of the classifier to fully connect the classification feature vector to obtain an encoded classification feature vector; and a classification result generation unit 373, used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0081] In summary, according to the embodiment of the present application, a control system 300 for a green building structure that can reduce carbon emissions is explained. It uses a neural network model based on deep learning to mine the differential correlation characteristics between the indoor temperature and humidity time series coordinated correlation characteristics and the outdoor temperature and humidity time series coordinated correlation characteristics, so as to adaptively control the air outlet intensity of the air conditioner based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0082] As described above, the control system of the green building structure that can reduce carbon emissions according to the embodiment of the present application can be implemented in various terminal devices. In one example, the control system 300 of the green building structure that can reduce carbon emissions according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the control system 300 of the green building structure that can reduce carbon emissions can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the control system 300 of the green building structure that can reduce carbon emissions can also be one of the many hardware modules of the terminal device.

[0083] Alternatively, in another example, the control system 300 of the green building structure that can reduce carbon emissions and the terminal device can also be separate devices, and the control system 300 of the green building structure that can reduce carbon emissions can be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0084] Exemplary Methods

[0085] Figure 6 Flow chart of a control method for a green building structure that can reduce carbon emissions according to an embodiment of the present application. Figure 6 As shown, according to the control method of the green building structure that can reduce carbon emissions according to the embodiment of the present application, the steps include: S110, obtaining indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period; S120, arranging the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the multiple predetermined time points into indoor temperature time series input vectors, indoor humidity time series input vectors, outdoor temperature time series input vectors and outdoor humidity time series input vectors according to the time dimension; S130, associating and encoding the indoor temperature time series input vectors and the indoor humidity time series input vectors to obtain an indoor temperature-humidity association matrix, and encoding the outdoor temperature time series input vectors and the outdoor humidity time series input vectors. The outdoor humidity time series input vector is associated encoded to obtain an outdoor temperature-humidity association matrix; S140, the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix are respectively passed through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix; S150, the transfer matrix of the indoor temperature-humidity association feature matrix relative to the outdoor temperature-humidity association feature matrix is ​​calculated; S160, the transfer matrix is ​​feature optimized to obtain an optimized transfer matrix; and, S170, the optimized transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label.

[0086] In one example, in the control method of the green building structure capable of reducing carbon emissions, the step S130 includes: associating and encoding the indoor temperature time series input vector and the indoor humidity time series input vector using the following association formula to obtain an indoor temperature-humidity association matrix; wherein the formula is: Where V1 represents the indoor temperature time series input vector, V1 T represents the transposed vector of the indoor temperature time series input vector, V2 represents the indoor humidity time series input vector, M1 represents the indoor temperature-humidity association matrix, Represents vector multiplication; and, the outdoor temperature time series input vector and the outdoor humidity time series input vector are associated and encoded using the following association formula to obtain an outdoor temperature-humidity association matrix; wherein the formula is: Wherein V3 represents the outdoor temperature time series input vector, represents the transposed vector of the outdoor temperature time series input vector, V4 represents the outdoor humidity time series input vector, M2 represents the outdoor temperature-humidity association matrix, Represents vector multiplication.

[0087] In one example, in the above-mentioned control method of the green building structure that can reduce carbon emissions, the step S140 includes: using each layer of the convolutional neural network model including the bidirectional attention mechanism module to perform the following on the input data in the forward pass of the layer: convolution processing on the input data to obtain a convolution feature map; pooling the convolution feature map along the channel dimension to obtain a pooled feature map; and, nonlinear activation on the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation feature matrix and the outdoor temperature-humidity correlation feature matrix, and the input of the first layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix.

[0088] In one example, in the control method of the green building structure capable of reducing carbon emissions, the step S150 includes: calculating the transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix by the following formula; wherein the formula is:

[0089]

[0090] Where M1 represents the indoor temperature-humidity correlation feature matrix, M2 represents the outdoor temperature-humidity correlation feature matrix, t Denotes the transfer matrix.

[0091] In one example, in the control method of the green building structure capable of reducing carbon emissions, the step S160 includes: performing vector spectrum clustering agent learning fusion optimization on the transfer matrix according to the following optimization formula to obtain the optimized transfer matrix; wherein the optimization formula is:

[0092]

[0093]

[0094] Among them, M t is the transfer matrix, M ′ t is the optimized transfer matrix, V1~V n represents each row eigenvector of the transfer matrix, and D V is a distance matrix composed of the distances between every two corresponding row eigenvectors of the transfer matrix, exp(·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the value of the natural exponential function with the eigenvalues ​​of each position in the matrix raised to the power, ⊙ and Represent positional dot multiplication and matrix addition respectively.

[0095] In one example, in the above-mentioned control method of the green building structure that can reduce carbon emissions, the step S170 includes: expanding the optimized transfer matrix into a classification feature vector based on a row vector or a column vector; using multiple fully connected layers of the classifier to fully connect encode the classification feature vector to obtain an encoded classification feature vector; and passing the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0096] In summary, according to the embodiment of the present application, a control method for a green building structure that can reduce carbon emissions is explained. It uses a neural network model based on deep learning to mine the differential correlation characteristics between the indoor temperature and humidity time series coordinated correlation characteristics and the outdoor temperature and humidity time series coordinated correlation characteristics, so as to adaptively control the air outlet intensity of the air conditioner based on the actual temperature and humidity changes indoors and outdoors, thereby optimizing the working efficiency and effect of the air conditioning system, while reducing carbon emissions, making the air conditioning system more efficient and energy-saving.

[0097] Exemplary Electronic Devices

[0098] Below, reference Figure 7 To describe an electronic device according to an embodiment of the present application.

[0099] Figure 7 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0100] like Figure 7As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0101] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0102] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the functions in the control system of the green building structure that can reduce carbon emissions of the various embodiments of the present application described above and / or other desired functions. Various contents such as transfer matrices may also be stored in the computer-readable storage medium.

[0103] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0104] The input device 13 may include, for example, a keyboard, a mouse, etc.

[0105] The output device 14 can output various information to the outside, including classification results, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0106] Of course, to simplify, Figure 7 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0107] Exemplary computer program products and computer-readable storage media

[0108] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to perform the steps in the functions of the control method of a green building structure that can reduce carbon emissions according to various embodiments of the present application described in the above "Exemplary System" section of this specification.

[0109] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0110] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to perform the steps in the functions of the control method for a green building structure that can reduce carbon emissions according to various embodiments of the present application described in the above "Exemplary System" section of this specification.

[0111] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0112] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0113] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0114] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0115] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0116] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A control system for a green building structure that can reduce carbon emissions, characterized in that: include: A data acquisition module, used to obtain indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period; A data parameter time series distribution module, used for arranging the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the plurality of predetermined time points into an indoor temperature time series input vector, an indoor humidity time series input vector, an outdoor temperature time series input vector and an outdoor humidity time series input vector respectively according to the time dimension; A data parameter time series association coding module, used for performing association coding on the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and performing association coding on the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix; A bidirectional attention feature extraction module, used to pass the indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix; An indoor-outdoor transfer correlation module, used to calculate a transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix; A feature optimization module, used for performing feature optimization on the transfer matrix to obtain an optimized transfer matrix; as well as An air outlet intensity control module, used for passing the optimized transfer matrix through a classifier to obtain a classification result, wherein the classification result is used to represent a recommended air outlet intensity level label; The feature optimization module is used to: perform vector spectrum clustering agent learning fusion optimization on the transfer matrix according to the following optimization formula to obtain the optimized transfer matrix; Wherein, the optimization formula is: Among them, M t is the transfer matrix, M′ t is the optimized transfer matrix, V1~V n represents each row eigenvector of the transfer matrix, and D V is a distance matrix composed of the distances between every two corresponding row eigenvectors of the transfer matrix, exp(·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the value of the natural exponential function with the eigenvalues ​​of each position in the matrix raised to the power, ⊙ and Respectively represent positional dot multiplication and matrix addition; The vector spectral clustering agent learning fusion optimization introduces spectral clustering agent learning for representing the spatial layout and semantic similarity between vectors, utilizes the conceptual information of the association between regression-like semantic features and regression-like scenarios, and performs implicit supervision propagation on the potential association attributes between each row vector of the transfer matrix to improve the overall distribution dependency of the transfer matrix as a synthetic feature.

2. The control system of a green building structure capable of reducing carbon emissions according to claim 1, characterized in that: The data parameter timing association encoding module is used to: The indoor temperature time series input vector and the indoor humidity time series input vector are associated and encoded using the following association formula to obtain an indoor temperature-humidity association matrix; Wherein, the formula is: Where V1 represents the indoor temperature timing input vector, represents the transposed vector of the indoor temperature time series input vector, V2 represents the indoor humidity time series input vector, M1 represents the indoor temperature-humidity association matrix, represents vector multiplication; and The outdoor temperature time series input vector and the outdoor humidity time series input vector are associated and encoded using the following association formula to obtain an outdoor temperature-humidity association matrix; Wherein, the formula is: Wherein V3 represents the outdoor temperature time series input vector, represents the transposed vector of the outdoor temperature time series input vector, V4 represents the outdoor humidity time series input vector, M2 represents the outdoor temperature-humidity association matrix, Represents vector multiplication.

3. The control system of a green building structure capable of reducing carbon emissions according to claim 2, characterized in that: The bidirectional attention feature extraction module is used to: use each layer of the convolutional neural network model including the bidirectional attention mechanism module to perform the following on the input data in the forward pass of the layer: Perform convolution on the input data to obtain a convolution feature map; Pooling the convolutional feature map along the channel dimension to obtain a pooled feature map; as well as Performing nonlinear activation on the pooled feature map to obtain an activated feature map; Among them, the output of the last layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation feature matrix and the outdoor temperature-humidity correlation feature matrix, and the input of the first layer of the convolutional neural network including the bidirectional attention mechanism module is the indoor temperature-humidity correlation matrix and the outdoor temperature-humidity correlation matrix.

4. The control system of a green building structure capable of reducing carbon emissions according to claim 3, characterized in that: The indoor and outdoor transfer association module is used to: calculate the transfer matrix of the indoor temperature-humidity association characteristic matrix relative to the outdoor temperature-humidity association characteristic matrix using the following formula; Wherein, the formula is: Where M1 represents the indoor temperature-humidity correlation feature matrix, M2 represents the outdoor temperature-humidity correlation feature matrix, t Denotes the transfer matrix.

5. The control system of a green building structure capable of reducing carbon emissions according to claim 4, characterized in that: The air outlet intensity control module comprises: An expansion unit, used for expanding the optimized transfer matrix into a classification feature vector based on a row vector or a column vector; a fully connected encoding unit, configured to perform fully connected encoding on the classification feature vector using a plurality of fully connected layers of the classifier to obtain an encoded classification feature vector; and The classification result generating unit is used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

6. A control method for a green building structure capable of reducing carbon emissions, characterized in that: include: Obtain indoor temperature values, indoor humidity values, outdoor temperature values, and outdoor humidity values ​​at multiple predetermined time points within a predetermined time period; Arrange the indoor temperature values, indoor humidity values, outdoor temperature values ​​and outdoor humidity values ​​at the plurality of predetermined time points into an indoor temperature time series input vector, an indoor humidity time series input vector, an outdoor temperature time series input vector and an outdoor humidity time series input vector respectively according to the time dimension; Performing association coding on the indoor temperature time series input vector and the indoor humidity time series input vector to obtain an indoor temperature-humidity association matrix, and performing association coding on the outdoor temperature time series input vector and the outdoor humidity time series input vector to obtain an outdoor temperature-humidity association matrix; The indoor temperature-humidity association matrix and the outdoor temperature-humidity association matrix are respectively passed through a convolutional neural network model including a bidirectional attention mechanism module to obtain an indoor temperature-humidity association feature matrix and an outdoor temperature-humidity association feature matrix; Calculating a transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix; Performing feature optimization on the transfer matrix to obtain an optimized transfer matrix; as well as Passing the optimized transfer matrix through a classifier to obtain a classification result, wherein the classification result is used to represent a recommended air outlet intensity level label; Performing feature optimization on the transfer matrix to obtain an optimized transfer matrix, including: performing vector spectrum clustering agent learning fusion optimization on the transfer matrix according to the following optimization formula to obtain the optimized transfer matrix; Wherein, the optimization formula is: Among them, M t is the transfer matrix, M′ t is the optimized transfer matrix, V1~V n represents each row eigenvector of the transfer matrix, and D V is a distance matrix composed of the distances between every two corresponding row eigenvectors of the transfer matrix, exp(·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the value of the natural exponential function with the eigenvalues ​​of each position in the matrix raised to the power, ⊙ and Respectively represent positional dot multiplication and matrix addition; The vector spectral clustering agent learning fusion optimization introduces spectral clustering agent learning for representing the spatial layout and semantic similarity between vectors, utilizes the conceptual information of the association between regression-like semantic features and regression-like scenarios, and performs implicit supervision propagation on the potential association attributes between each row vector of the transfer matrix to improve the overall distribution dependency of the transfer matrix as a synthetic feature.

7. A control method for a green building structure capable of reducing carbon emissions according to claim 6, characterized in that: Calculating the transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix, comprising: calculating the transfer matrix of the indoor temperature-humidity correlation characteristic matrix relative to the outdoor temperature-humidity correlation characteristic matrix using the following formula; Wherein, the formula is: Where M1 represents the indoor temperature-humidity correlation feature matrix, M2 represents the outdoor temperature-humidity correlation feature matrix, t Denotes the transfer matrix.

8. A control method for a green building structure capable of reducing carbon emissions according to claim 7, characterized in that: The optimized transfer matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to represent a recommended air outlet intensity level label, including: Expanding the optimized transfer matrix into a classification feature vector based on a row vector or a column vector; Performing full connection encoding on the classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and The encoded classification feature vector is passed through the Softmax classification function of the classifier to obtain the classification result.

Images