A building comfort evaluation method and device

Abstract

The present invention provides a method and device for evaluating building comfort. The method comprises: obtaining basic data and indoor environment data of a micro-pressurized oxygenated prefabricated building; preprocessing the basic data and indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data; extracting features of the preprocessed basic data and preprocessed indoor environment data to obtain a feature vector; inputting the feature vector and a preset comfort index into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; obtaining a comfort evaluation result according to the comfort score, the comfort prediction result and the preset comfort evaluation condition. The present invention provides a measurement standard for the comfort of micro-pressurized oxygenated prefabricated buildings, which is helpful for the improvement of micro-pressurized oxygenated prefabricated buildings.

Description

Technical Field

[0001] The present invention relates to the technical field of building assessment, and also to a building comfort assessment method and device. Background Art

[0002] Plateau in medicine refers to areas above 3,000 meters above sea level. The low pressure, hypoxia, cold, and strong solar radiation environment in plateau areas can cause various altitude sicknesses. At present, the measures adopted to reduce altitude sickness are mainly oxygenation and pressurization, and the micro-pressurized oxygenated prefabricated building is a new type of prefabricated steel structure building specially developed for the low-pressure and hypoxic environment in plateau areas. Micro-pressurized oxygenated prefabricated buildings integrate prefabricated steel structure systems, sealing systems, air pressurization systems, decorative mechatronics technology, building energy conservation, and new energy utilization technologies to achieve a living space similar to a low-altitude air environment. Studies have shown that micro-pressurized oxygenated prefabricated buildings have an improvement effect on respiratory, cardiovascular, metabolic, hormone and other body function indicators, and can effectively reduce altitude sickness. However, there is currently no detection or evaluation method for the comfort of micro-pressurized oxygenated buildings, and it is impossible to evaluate the comfort of micro-pressurized oxygenated prefabricated buildings. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a building comfort evaluation method and device to achieve comfort evaluation of micro-pressurized oxygenated prefabricated buildings.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] A first aspect of the present invention provides a building comfort evaluation method, comprising:

[0006] Obtain basic data and indoor environment data of micro-pressurized oxygen-enhanced prefabricated buildings;

[0007] Preprocessing the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data;

[0008] Performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector;

[0009] The characteristic vector and the preset comfort index are input into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings;

[0010] A comfort evaluation result is obtained according to the comfort score, the comfort prediction result and the preset comfort evaluation condition.

[0011] Optionally, obtain basic data and indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building, including:

[0012] Obtain structural characteristic data, usage function data, spatial layout data, temperature data, humidity data, light data, oxygen data and pressure data of the micro-pressurized oxygen-enhanced prefabricated building;

[0013] Obtaining basic data according to the structural feature data, the usage function data, and the spatial layout data;

[0014] Indoor environment data is obtained according to the temperature data, the humidity data, the illumination data, the oxygen data and the pressure data.

[0015] Optionally, performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector includes:

[0016] Obtaining a covariance matrix according to the preprocessed basic data and the preprocessed indoor environment data;

[0017] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and principal component vectors;

[0018] The principal component vector is selected according to the eigenvalue to obtain a eigenvector.

[0019] Optionally, the feature vector and the preset comfort index are input into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result, including:

[0020] Inputting the characteristic vector and the preset comfort index into the input layer of the comfort evaluation model to obtain a first output result;

[0021] Inputting the first output result into at least one processing layer of a comfort assessment model to obtain a second output result;

[0022] The second output result is input into the output layer of the comfort evaluation model to obtain a comfort score and a comfort prediction result.

[0023] Optionally, the training process of the comfort evaluation model includes:

[0024] Obtain historical basic data and historical indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building within a preset time period;

[0025] Preprocessing the historical basic data and the historical indoor environment data to obtain preprocessed historical basic data and preprocessed historical indoor environment data;

[0026] Obtaining training samples and test samples according to the preprocessed historical basic data and the preprocessed historical indoor environment data;

[0027] Using the training samples to train the preset network model to obtain a trained preset network model;

[0028] Using a preset activation function and a preset loss function, adjusting the network parameters of the trained preset network model to obtain an adjusted preset network model;

[0029] The adjusted preset network model is tested using the test sample to obtain a comfort evaluation model.

[0030] Optionally, obtaining a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition includes:

[0031] Obtain preset comfort evaluation conditions;

[0032] Processing the comfort score and the comfort prediction result to obtain comfort level data;

[0033] Comparing the comfort level data with the preset comfort evaluation condition to obtain a comparison result;

[0034] A comfort evaluation result is obtained according to the comparison result.

[0035] Optionally, obtain preset comfort evaluation conditions, including:

[0036] Get the user's physical data;

[0037] Inputting the user's physical data into a preset health assessment model to obtain a health assessment result;

[0038] According to the health assessment result, a preset comfort assessment condition is determined.

[0039] A second aspect of the present invention provides a building comfort evaluation device, comprising:

[0040] An acquisition module is used to obtain basic data and indoor environment data of micro-pressurized oxygen-enhanced prefabricated buildings;

[0041] A processing module, used for preprocessing the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data;

[0042] An extraction module, used for performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector;

[0043] A prediction module is used to input the feature vector and the preset comfort index into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings;

[0044] The evaluation module is used to obtain a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition.

[0045] According to a third aspect of the present invention, a computing device is provided, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to the first aspect is executed.

[0046] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the method described in the first aspect.

[0047] The above solution of the present invention includes at least the following beneficial effects:

[0048] The above scheme of the present invention obtains basic data and indoor environment data of the micro-pressurized oxygenated prefabricated building, pre-processes the data and then extracts features to obtain feature vectors, inputs the feature vectors and preset comfort indicators into a trained comfort assessment model to obtain comfort scores and comfort prediction results, and evaluates the comfort of the micro-pressurized oxygenated prefabricated building based on the comfort score, comfort prediction results and preset comfort assessment conditions to obtain comfort assessment results, thereby providing a measurement standard for the comfort of the micro-pressurized oxygenated prefabricated building and contributing to the improvement of the micro-pressurized oxygenated prefabricated building. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a building comfort evaluation method in an embodiment of the present invention;

[0050] Figure 2 Schematic diagram of the structure of the building comfort evaluation device in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0052] like Figure 1As shown, an embodiment of the present invention provides a building comfort evaluation method, comprising the following steps:

[0053] Step 101, obtaining basic data and indoor environment data of a micro-pressurized oxygen-enhanced prefabricated building;

[0054] Step 102, preprocessing the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data;

[0055] Step 103, extracting features from the preprocessed basic data and the preprocessed indoor environment data to obtain feature vectors;

[0056] Step 104, inputting the characteristic vector and the preset comfort index into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings;

[0057] Step 105: Obtain a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition.

[0058] Specifically, micro-pressurized oxygen-enhanced prefabricated buildings change the air pressure and oxygen partial pressure in the building space to make the indoor environment equivalent to the level of low-altitude areas. They can be used for high-altitude housing, medical treatment, snow mountain camping, etc., which can effectively solve the problem of human tissue hypoxia in high-altitude areas, improve the human body's oxygen supply, and promote the improvement of the living environment in high-altitude areas.

[0059] The building comfort assessment method proposed in the embodiment of the present invention obtains basic data and indoor environment data of a micro-pressurized oxygenated prefabricated building, performs feature extraction after preprocessing the data, obtains a feature vector, inputs the feature vector and a preset comfort index into a trained comfort assessment model, obtains a comfort score and a comfort prediction result, and evaluates the comfort of the micro-pressurized oxygenated prefabricated building based on the comfort score, the comfort prediction result and the preset comfort assessment conditions to obtain a comfort assessment result, thereby providing a measurement standard for the comfort of the micro-pressurized oxygenated prefabricated building and contributing to the improvement of the micro-pressurized oxygenated prefabricated building.

[0060] In an optional embodiment of the present invention, step 101 includes:

[0061] Step 1011, obtaining structural characteristic data, usage function data, spatial layout data, temperature data, humidity data, light data, oxygen data and pressure data of the micro-pressurized oxygen-enhanced prefabricated building;

[0062] Step 1012, obtaining basic data according to the structural feature data, the usage function data, and the spatial layout data;

[0063] Specifically, the basic data of micro-pressurized aeration prefabricated buildings, such as the relevant data of building structure, materials, installation or equipment used, are all basic data. The basic data of micro-pressurized aeration prefabricated buildings can include:

[0064] Structural characteristic data. Such as material data: including the type of building materials (such as concrete, steel, wood, etc.) and specifications, as well as the mechanical performance parameters of the materials such as compression and tension; it can also include construction size data: such as the size and cross-sectional form of the main components such as walls, floor slabs, beams and columns, such as thickness, width, length, etc.; it can also include connection method data: describing the connection method between components, such as welding, bolt connection or riveting structure, as well as the construction and performance parameters of the connection nodes; it can also include the structure of the pressurized oxygen system: such as the specifications, performance parameters, pipeline layout and connection method of the pressurized equipment, as well as the type, distribution and effect evaluation of the oxygen equipment.

[0065] Use functional data. For example, functional zoning data: different functional areas are divided according to usage requirements, such as living areas, office areas, leisure areas, etc., and the size information such as the area and height of each area is described; it can also include ventilation and air conditioning data: such as the layout of the ventilation system, the location and number of air vents, and the type, capacity and distribution of the air conditioning system; it can also include lighting and electrical: including the type, layout and illumination requirements of lighting equipment, as well as the configuration of electrical equipment and power consumption estimates.

[0066] Spatial layout data: Such as the floor plan data of the building, the relative position and spatial relationship of each functional area, and the floor height data of the building.

[0067] Step 1013, obtaining indoor environment data according to the temperature data, the humidity data, the illumination data, the oxygen data and the pressure data.

[0068] Specifically, micro-pressurized oxygenated prefabricated buildings need to achieve constant pressure, constant oxygen, constant temperature, constant humidity, etc. Therefore, it is necessary to collect a variety of indoor environmental data of micro-pressurized oxygenated prefabricated buildings, such as temperature data, humidity data, light data, oxygen data and pressure data, as the basis for subsequent evaluation of building comfort. It should be noted that these indoor environmental data can be obtained through various methods such as on-site measurement, sensor monitoring, and user feedback.

[0069] In an optional embodiment of the present invention, the preprocessing method in step 102 may include data cleaning to remove duplicate, erroneous and invalid data, thereby ensuring the accuracy and completeness of the data; the preprocessing method may also include data normalization, which normalizes data of different dimensions and units to enable the model to better process the data.

[0070] In an optional embodiment of the present invention, step 103 includes:

[0071] Step 1031, obtaining a covariance matrix according to the preprocessed basic data and the preprocessed indoor environment data;

[0072] Specifically, through By calculating the covariance matrix, we can get the correlation between different data features, avoid overfitting, and improve the model processing efficiency. i and i are two random variables in the preprocessed basic data and preprocessed indoor environment data, For x i The corresponding observed data mean, for y i The corresponding observed data mean, n is the total number of preprocessed basic data plus preprocessed indoor environment data.

[0073] Step 1032, performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and principal component vectors;

[0074] Specifically, through eigenvalue decomposition, the preprocessed basic data and the preprocessed indoor environment data can be decomposed into eigenvalues ​​and corresponding principal component vectors. The size of the eigenvalue represents the importance of the corresponding principal component vector, and the principal component vector represents the direction of the original feature in the new feature space.

[0075] Step 1033, selecting the principal component vector according to the eigenvalue to obtain a eigenvector.

[0076] Specifically, after obtaining the eigenvalues ​​and the corresponding principal component vectors, the eigenvalues ​​need to be sorted, generally sorting the eigenvalues ​​from large to small. Since the eigenvalues ​​and the principal component vectors are in a corresponding relationship, the larger the eigenvalue corresponding to the sorted principal component vector, the more important the principal component vector is. According to the sorting results of the eigenvalues, the principal component vectors corresponding to the first M eigenvalues ​​are selected as eigenvectors. These eigenvectors represent the linear combination of the original features in the low-dimensional space. By selecting appropriate eigenvectors, most of the information in the preprocessed basic data and the preprocessed indoor environment data can be retained.

[0077] Specifically, after selecting the principal component vectors corresponding to the first M eigenvalues ​​as the eigenvectors, the preprocessed basic data and the preprocessed indoor environment data are mapped to the low-dimensional space formed by the eigenvectors, and the projection values ​​of the preprocessed basic data and the preprocessed indoor environment data on the eigenvectors are obtained, and these projection values ​​represent the importance of the preprocessed basic data and the preprocessed indoor environment data projected on the eigenvectors. The preprocessed basic data and the preprocessed indoor environment data whose projection values ​​are greater than the preset feature extraction values ​​are selected as the eigenvectors, and the features related to comfort can be extracted from the original preprocessed basic data and the preprocessed indoor environment data, such as the fluctuation range of indoor temperature, the stability of humidity, and the average value of oxygen content (the fluctuation range of indoor temperature, the stability of humidity, and the average value of oxygen content can be obtained from the original data) as the eigenvectors, which are used as the input of the comfort evaluation model, thereby improving the accuracy of the comfort score and the comfort prediction results.

[0078] In an optional embodiment of the present invention, step 104 includes:

[0079] Step 10411, inputting the feature vector and the preset comfort index into the input layer of the comfort evaluation model to obtain a first output result;

[0080] Specifically, the feature vector and the preset comfort index constitute the input data. The input layer includes multiple neurons, each neuron corresponds to one data in the input data, and the number of neurons in the input layer depends on the number of data in the input data. The function of the input layer is to convert the input data into a format that can be processed inside the comfort assessment model, such as converting the input data into a vector form. The output of the input layer is the first output result, which is the input passed to the neurons in the processing layer.

[0081] Step 10421, inputting the first output result into at least one processing layer of a comfort evaluation model to obtain a second output result;

[0082] Specifically, according to actual needs, the comfort assessment model may include one or more processing layers, which are located between the input layer and the output layer. Its function is to convert the first output result into a higher-level feature representation. The number of neurons and the connection method of each processing layer are different, depending on the specific neural network architecture.

[0083] Specifically, through O t =g(V×S t ) and S t =f(U×X i +W×S t-1 ) to obtain the second output result, wherein O t is the second output result at time t, g is the first conversion function, V is, St is the value of the processing layer at time t, f is the second conversion function, U is the parameter matrix, X i is the i-th vector in the first output result, W is the weight matrix, S t-1 is the value of the processing layer at time t-1. The first conversion function and the second conversion function can be selected according to actual conditions.

[0084] Step 10431, input the second output result into the output layer of the comfort evaluation model to obtain a comfort score and a comfort prediction result.

[0085] Here, after processing by the output layer, a comfort score will be obtained, which is the comfort score at each time point; a comfort prediction result will also be obtained, that is, the comfort prediction result for a period of time in the future.

[0086] In an optional embodiment of the present invention, the training process of the comfort evaluation model in step 104 includes:

[0087] Step 10421, obtaining historical basic data and historical indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building within a preset time period;

[0088] Here, it can be one year, five years, or ten years of historical basic data and historical indoor environment data. The more data, the higher the accuracy of the final model. These data can be obtained according to actual needs. Historical basic data can include data such as building structure, materials, and equipment. Historical indoor environment data can include temperature data, humidity data, oxygen content data, noise data, and other data.

[0089] Step 10422, preprocessing the historical basic data and the historical indoor environment data to obtain preprocessed historical basic data and preprocessed historical indoor environment data;

[0090] Here, preprocessing methods can be deduplication, normalization, etc. to ensure the accuracy and completeness of the data and improve the efficiency of model training.

[0091] Step 10423, obtaining training samples and test samples according to the preprocessed historical basic data and the preprocessed historical indoor environment data;

[0092] Specifically, the data can be divided according to a preset ratio, such as 80% as training samples for training the model, and 20% as test samples for testing the accuracy of the model, thereby optimizing the model.

[0093] Step 10424, training the preset network model using the training samples to obtain a trained preset network model;

[0094] Here, 80% of the training samples are used to train the preset network model, and the preset network model can select a suitable model according to actual needs.

[0095] Step 10425, using a preset activation function and a preset loss function, adjusting the network parameters of the trained preset network model to obtain an adjusted preset network model;

[0096] Here, the training sample can be passed through each layer of the preset network model, and the output result can be obtained through the preset activation function. The output result and the preset loss function are used to calculate the gradient of the parameters of the processing layer and the output layer in the preset network model, and then the gradient of the parameters of each layer in the preset network model is calculated forward in sequence. The calculated gradient is used to update the parameters of each layer to minimize the preset loss function. After these steps, the optimal network parameters of the preset network model can be obtained.

[0097] Step 10426: Use the test sample to test the adjusted preset network model to obtain a comfort evaluation model.

[0098] Specifically, the adjusted preset network model is tested using the test samples, and the performance of the model is optimized by adjusting the model structure or parameters.

[0099] In an optional embodiment of the present invention, step 105 includes:

[0100] Step 1051, obtaining preset comfort evaluation conditions;

[0101] Here, the preset comfort assessment conditions can be set according to factors such as building type, usage function, user needs, etc. For example, the comfort threshold, fluctuation range, change trend and other conditions for different time periods can be set. Different preset comfort assessment conditions can also be set for different users according to the user's health assessment results to meet the user's own physical condition. For example, if the health assessment result of user A is good, the comfort threshold, fluctuation range, change trend and the like in the preset comfort assessment conditions can be set to a larger range; if the health assessment result of user B is poor, the comfort threshold, fluctuation range, change trend and the like in the preset comfort assessment conditions can be set to a relatively small range.

[0102] Step 1052, processing the comfort score and the comfort prediction result to obtain comfort level data;

[0103] Specifically, the comfort scores are counted and analyzed, and the average score, highest score, lowest score, etc. are calculated to fully understand the comfort level of the building at different times or in different areas; the comfort prediction results are analyzed to obtain the comfort change trend and the comfort level that may be achieved in the future.

[0104] Step 1053, comparing the comfort level data with the preset comfort evaluation condition to obtain a comparison result;

[0105] Specifically, if the comfort level data meet or exceed the preset comfort assessment conditions, the comfort assessment result is good comfort, otherwise it is poor comfort. For the poor comfort result, the database of micro-pressurized aeration prefabricated buildings can be searched to find the corresponding improvement plan and give improvement suggestions, which will help further upgrade and improve the micro-pressurized aeration prefabricated buildings.

[0106] Step 1054: Obtain a comfort evaluation result based on the comparison result.

[0107] Specifically, the comfort assessment results may include a comparison conclusion between the comfort level data and the preset comfort assessment conditions, such as if the comfort score and comfort prediction results in the comfort level data do not meet the preset comfort assessment conditions. It may also include improvement suggestions found in the database of micro-pressurized aeration prefabricated buildings.

[0108] Specifically, the comfort evaluation results can be visualized to analyze the change trend of comfort scores over time and the influence of different environmental factors on comfort. According to the comfort evaluation results, targeted improvement measures can be proposed for the building, such as optimizing the building's internal environmental control system (oxygenation, pressure reduction), improving ventilation efficiency, etc., to improve the building's comfort level.

[0109] Specifically, a comfort assessment report can be generated based on the comfort assessment results. The report includes comfort scores, comfort prediction results, comfort assessment results and improvement suggestions to help improve the comfort level of micro-pressurized oxygenated prefabricated buildings.

[0110] In an optional embodiment of the present invention, step 1051 includes:

[0111] Step 10511, obtaining the user's physical data;

[0112] As shown in Table 1 , the user’s age, group, and other physical data can be obtained as a basis for subsequent health assessment.

[0113] Table 1 User's physical data

[0114]

[0115] Specifically, the data in Table 1 are obtained by filling out questionnaires or measuring before the user enters the micro-pressurized oxygen prefabricated building and after staying in the micro-pressurized oxygen prefabricated building for a preset period of time. Among them, the constant can be set in advance manually or generated naturally when using SPSS statistical analysis software (automated statistical product and service software), age refers to the age of the user, the group can be the different pressures when entering the micro-pressurized oxygen prefabricated building, WBC refers to the white blood cells tested by the user, the left atrial diameter - front and back can be obtained by echocardiography, the aortic valve blood flow spectrum can be obtained by echocardiography, SO2 warm-up can be measured by a cardiopulmonary function assessment instrument, 6hSO2 can be measured by a pulse oximeter 6 hours after the user leaves the micro-pressurized oxygen prefabricated building, R 2 It is a fixed value of 89.5%. The adjusted R2, F, DW value, unstandardized coefficient, standardized coefficient, B, and standard error are obtained when using SPSS statistical analysis software (automated statistical products and service software) to do multivariate logistic regression analysis (linear regression analysis). t is the intermediate data obtained when using SPSS statistical analysis software to do multivariate logistic regression analysis. p is the indicator of statistical difference. * represents p<0.05, ** represents p<0.01, and there is a significant statistical difference. VIF is obtained when using SPSS statistical analysis software to do multivariate logistic regression analysis, which is used to analyze the collinearity of data. VIF close to 1 is better. Tolerance is obtained when using SPSS statistical analysis software to do multivariate logistic regression analysis, which is used to analyze the collinearity of data.

[0116] Step 10512, inputting the user's physical data into a preset health assessment model to obtain a health assessment result;

[0117] Specifically, the preset health assessment model used in this embodiment is:

[0118] Health assessment results = -0.28×age-0.269×group+0.252×white blood cell count+0.264×left atrial diameter+0.277×aortic valve blood flow spectrum+0.173×SO2 during the cardiopulmonary function warm-up period+0.176×6hSO2.

[0119] Step 10513: Determine preset comfort assessment conditions based on the health assessment results.

[0120] Specifically, different preset comfort assessment conditions can be set for different users according to the user's health assessment results to meet the user's own physical condition and adapt to individual differences. For example, if the health assessment result of user A is good, the comfort threshold, fluctuation range, change trend, etc. in the preset comfort assessment conditions can be set to a larger range; if the health assessment result of user B is poor, the comfort threshold, fluctuation range, change trend, etc. in the preset comfort assessment conditions can be set to a relatively small range.

[0121] like Figure 2 As shown, an embodiment of the present invention provides a building comfort evaluation device 200, comprising:

[0122] Acquisition module 201, used to acquire basic data and indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building;

[0123] A processing module 202 is used to preprocess the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data;

[0124] An extraction module 203 is used to extract features from the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector;

[0125] Prediction module 204, used for inputting the feature vector and the preset comfort index into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings;

[0126] The evaluation module 205 is used to obtain a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition.

[0127] Optionally, obtain basic data and indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building, including:

[0128] Obtain structural characteristic data, usage function data, spatial layout data, temperature data, humidity data, light data, oxygen data and pressure data of the micro-pressurized oxygen-enhanced prefabricated building;

[0129] Obtaining basic data according to the structural feature data, the usage function data, and the spatial layout data;

[0130] Indoor environment data is obtained according to the temperature data, the humidity data, the illumination data, the oxygen data and the pressure data.

[0131] Optionally, performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector includes:

[0132] Obtaining a covariance matrix according to the preprocessed basic data and the preprocessed indoor environment data;

[0133] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and principal component vectors;

[0134] The principal component vector is selected according to the eigenvalue to obtain a eigenvector.

[0135] Optionally, the feature vector and the preset comfort index are input into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result, including:

[0136] Inputting the characteristic vector and the preset comfort index into the input layer of the comfort evaluation model to obtain a first output result;

[0137] Inputting the first output result into at least one processing layer of a comfort assessment model to obtain a second output result;

[0138] The second output result is input into the output layer of the comfort evaluation model to obtain a comfort score and a comfort prediction result.

[0139] Optionally, the training process of the comfort evaluation model includes:

[0140] Obtain historical basic data and historical indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building within a preset time period;

[0141] Preprocessing the historical basic data and the historical indoor environment data to obtain preprocessed historical basic data and preprocessed historical indoor environment data;

[0142] Obtaining training samples and test samples according to the preprocessed historical basic data and the preprocessed historical indoor environment data;

[0143] Using the training samples to train the preset network model to obtain a trained preset network model;

[0144] Using a preset activation function and a preset loss function, adjusting the network parameters of the trained preset network model to obtain an adjusted preset network model;

[0145] The adjusted preset network model is tested using the test sample to obtain a comfort evaluation model.

[0146] Optionally, obtaining a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition includes:

[0147] Obtain preset comfort evaluation conditions;

[0148] Processing the comfort score and the comfort prediction result to obtain comfort level data;

[0149] Comparing the comfort level data with the preset comfort evaluation condition to obtain a comparison result;

[0150] A comfort evaluation result is obtained according to the comparison result.

[0151] Optionally, obtain preset comfort evaluation conditions, including:

[0152] Get the user's physical data;

[0153] Inputting the user's physical data into a preset health assessment model to obtain a health assessment result;

[0154] According to the health assessment result, a preset comfort assessment condition is determined.

[0155] The building comfort assessment device proposed in the embodiment of the present invention obtains the basic data and indoor environment data of the micro-pressurized oxygenated prefabricated building, performs feature extraction after pre-processing the data, obtains a feature vector, inputs the feature vector and the preset comfort index into the trained comfort assessment model, obtains the comfort score and the comfort prediction result, and evaluates the comfort of the micro-pressurized oxygenated prefabricated building according to the comfort score, the comfort prediction result and the preset comfort assessment condition to obtain the comfort assessment result, which provides a measurement standard for the comfort of the micro-pressurized oxygenated prefabricated building and helps to improve the micro-pressurized oxygenated prefabricated building. It should be noted that the device is a device corresponding to the above method, and all the implementation methods in the above method embodiment are applicable to the embodiment of the device, and can also achieve the same technical effect. It will not be repeated in this embodiment.

[0156] The embodiment of the present invention further provides a computing device, comprising: a processor, and a memory storing a computer program, wherein when the computer program is executed by the processor, the method described in any one of the above embodiments is executed. All implementations in the above method embodiments are applicable to the embodiments of the device, and can achieve the same technical effects. They will not be described in detail in this embodiment.

[0157] The embodiment of the present invention further provides a computer-readable storage medium on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects. They will not be described in detail in this embodiment.

[0158] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A building comfort evaluation method, characterized in that: include: Obtain basic data and indoor environment data of micro-pressurized oxygen-enhanced prefabricated buildings; Preprocessing the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data; Performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector; The characteristic vector and the preset comfort index are input into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings; Obtaining a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition; Among them, the basic data and indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building are obtained, including: Obtaining structural characteristic data, functional data, spatial layout data, temperature data, humidity data, lighting data, oxygen data and pressure data of the micro-pressurized oxygenated prefabricated building; wherein the structural characteristic data includes material data, connection method data, pressurized oxygenated system structure; the functional data includes: different functional areas, ventilation and air conditioning data, lighting and electricity; the spatial layout data includes: the floor plan data of the building, the relative position and spatial relationship of each functional area, and the floor height data of the building; Obtaining basic data according to the structural feature data, the usage function data, and the spatial layout data; Obtaining indoor environment data according to the temperature data, the humidity data, the light data, the oxygen data and the pressure data; The process of extracting features from the preprocessed basic data and the preprocessed indoor environment data to obtain feature vectors includes: According to the preprocessed basic data and the preprocessed indoor environment data, a covariance matrix is ​​obtained; wherein, The covariance matrix is ​​calculated, where σ(x,y) is the covariance matrix, x i and i are two random variables in the preprocessed basic data and preprocessed indoor environment data, For x i The corresponding observed data mean, for y i The corresponding observed data mean, n is the total number of preprocessed basic data plus preprocessed indoor environment data; Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and principal component vectors; Selecting the principal component vector according to the eigenvalue to obtain a eigenvector; Wherein, the comfort evaluation result is obtained according to the comfort score, the comfort prediction result and the preset comfort evaluation condition, including: Obtain preset comfort evaluation conditions; Processing the comfort score and the comfort prediction result to obtain comfort level data; Comparing the comfort level data with the preset comfort evaluation condition to obtain a comparison result; According to the comparison result, a comfort evaluation result is obtained; Among them, obtaining the preset comfort evaluation conditions includes: Get the user's physical data; The user's physical data is input into a preset health assessment model to obtain a health assessment result; wherein the preset health assessment model is: Health assessment result = -0.28×age-0.269×group+0.252×white blood cell count+0.264×left atrial diameter+0.277×aortic valve blood flow spectrum+0.173×SO2 during the warm-up period of cardiopulmonary function+0.176×6hSO2; According to the health assessment result, a preset comfort assessment condition is determined.

2. The building comfort evaluation method according to claim 1, characterized in that: The feature vector and the preset comfort index are input into the trained comfort evaluation model to obtain the comfort score and comfort prediction results, including: Inputting the characteristic vector and the preset comfort index into the input layer of the comfort evaluation model to obtain a first output result; Inputting the first output result into at least one processing layer of a comfort assessment model to obtain a second output result; The second output result is input into the output layer of the comfort evaluation model to obtain a comfort score and a comfort prediction result.

3. The building comfort evaluation method according to claim 1, characterized in that: The training process of the comfort evaluation model includes: Obtain historical basic data and historical indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building within a preset time period; Preprocessing the historical basic data and the historical indoor environment data to obtain preprocessed historical basic data and preprocessed historical indoor environment data; Obtaining training samples and test samples according to the preprocessed historical basic data and the preprocessed historical indoor environment data; Using the training samples to train the preset network model to obtain a trained preset network model; Using a preset activation function and a preset loss function, adjusting the network parameters of the trained preset network model to obtain an adjusted preset network model; The adjusted preset network model is tested using the test sample to obtain a comfort evaluation model.

4. A building comfort evaluation device, characterized in that: include: An acquisition module is used to obtain basic data and indoor environment data of micro-pressurized oxygen-enhanced prefabricated buildings; A processing module, used for preprocessing the basic data and the indoor environment data to obtain preprocessed basic data and preprocessed indoor environment data; An extraction module, used for performing feature extraction on the preprocessed basic data and the preprocessed indoor environment data to obtain a feature vector; A prediction module is used to input the feature vector and the preset comfort index into a trained comfort evaluation model to obtain a comfort score and a comfort prediction result; the comfort evaluation model is obtained by training a preset network model using historical basic data and historical indoor environment data of micro-pressurized oxygenated prefabricated buildings; An evaluation module, used for obtaining a comfort evaluation result according to the comfort score, the comfort prediction result and a preset comfort evaluation condition; Among them, the basic data and indoor environment data of the micro-pressurized oxygen-enhanced prefabricated building are obtained, including: Obtaining structural characteristic data, functional data, spatial layout data, temperature data, humidity data, lighting data, oxygen data and pressure data of the micro-pressurized oxygenated prefabricated building; wherein the structural characteristic data includes material data, connection method data, pressurized oxygenated system structure; the functional data includes: different functional areas, ventilation and air conditioning data, lighting and electricity; the spatial layout data includes: the floor plan data of the building, the relative position and spatial relationship of each functional area, and the floor height data of the building; Obtaining basic data according to the structural feature data, the usage function data, and the spatial layout data; Obtaining indoor environment data according to the temperature data, the humidity data, the illumination data, the oxygen data and the pressure data; The process of extracting features from the preprocessed basic data and the preprocessed indoor environment data to obtain feature vectors includes: According to the preprocessed basic data and the preprocessed indoor environment data, a covariance matrix is ​​obtained; wherein, The covariance matrix is ​​calculated, where σ(x,y) is the covariance matrix, x i and i are two random variables in the preprocessed basic data and preprocessed indoor environment data, For x i The corresponding observed data mean, for y i The corresponding observed data mean, n is the total number of preprocessed basic data plus preprocessed indoor environment data; Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and principal component vectors; Selecting the principal component vector according to the eigenvalue to obtain a eigenvector; Wherein, the comfort evaluation result is obtained according to the comfort score, the comfort prediction result and the preset comfort evaluation condition, including: Obtain preset comfort evaluation conditions; Processing the comfort score and the comfort prediction result to obtain comfort level data; Comparing the comfort level data with the preset comfort evaluation condition to obtain a comparison result; According to the comparison result, a comfort evaluation result is obtained; Among them, obtaining the preset comfort evaluation conditions includes: Get the user's physical data; The user's physical data is input into a preset health assessment model to obtain a health assessment result; wherein the preset health assessment model is: Health assessment result = -0.28×age-0.269×group+0.252×white blood cell count+0.264×left atrial diameter+0.277×aortic valve blood flow spectrum+0.173×SO2 during the warm-up period of cardiopulmonary function+0.176×6hSO2; According to the health assessment result, a preset comfort assessment condition is determined.

5. A computing device, characterized in that: include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 3 is performed.

6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 3.

Images