An outdoor thermal comfort evaluation method based on data collected by a wearable device

Abstract

The present application relates to the field of thermal comfort monitoring, and more particularly to an outdoor thermal comfort evaluation method based on data collected by a wearable device, comprising collecting target data; determining the thermal comfort value of the target collection body according to the individual data of the target collection body through a thermal comfort model, and determining whether to redetermine the thermal comfort value and the thermal comfort value determination method according to the thermal comfort stability of the thermal comfort value of the target collection body; when compensating the target collection body thermal comfort value according to the environmental factor data, determining the optional thermal comfort effective area according to the periodic motion area; determining the allowable influence value range of the environmental factor data according to the interval duration of the R wave in the electrocardiogram; determining the influence degree of the environmental wind speed and the influence degree of the environmental temperature; adjusting the target collection body thermal comfort value according to the environmental influence factor, improving the determination accuracy of the influence degree of the environmental influence factor on the target collection body comfort value, and further improving the determination accuracy of the thermal comfort value.

Description

Technical Field

[0001] This invention relates to the field of thermal comfort monitoring, and more particularly to a method for evaluating outdoor thermal comfort based on data collected by wearable devices. Background Technology

[0002] With the advancement of science and technology, deep learning models are increasingly being used in thermal comfort monitoring technology to monitor and reflect the thermal comfort level of the human body in the current environment in real time. Among these, the prediction and assessment of outdoor thermal comfort is an important research direction. However, since environmental factors affect thermal comfort values ​​and these factors are uncontrollable, it is difficult to obtain accurate user thermal comfort values ​​using only traditional electrocardiogram (ECG) and electroencephalogram (EEG) signals. Therefore, how to determine the degree of influence of environmental factors on user thermal comfort values ​​under different conditions and further adjust thermal comfort values ​​to make them more accurate is a problem that urgently needs to be solved.

[0003] Chinese Patent Publication No. CN113496318A discloses a terminal and method for evaluating the Personalized Thermal Comfort (PMV) value of a user. The method includes: a sensor for acquiring input parameters including user attribute characteristics, indoor air environment parameters, and outdoor air environment parameters; a processor for executing program code and inputting the input parameters acquired by the sensor into a trained PMV model, outputting the PMV value. The trained PMV model is obtained by training a neural network model using standard input parameters including user attribute characteristics, indoor air environment parameters, and outdoor air environment parameters as input and preset standard output data representing the PMV value as output. Therefore, the above technical solution has the following problems: it cannot determine the degree of influence of environmental factors on the user's thermal comfort value under different conditions, thus making it impossible to adjust the thermal comfort value accordingly, resulting in low accuracy of the thermal comfort value. Summary of the Invention

[0004] To address this issue, the present invention provides an outdoor thermal comfort evaluation method based on data collected by wearable devices, which overcomes the problem of low accuracy of thermal comfort values ​​caused by the inability to determine the actual application scenario for corresponding adjustment in the prior art.

[0005] To achieve the above objectives, the present invention provides a method for evaluating outdoor thermal comfort based on data collected by wearable devices, comprising: Collect target data, which includes individual data of the target data subject and environmental factor data; The data analysis unit determines the thermal comfort value of the target acquisition body based on the individual data of the target acquisition body through the thermal comfort model. Under the first data analysis condition, the data analysis unit compensates for the thermal comfort value of the target acquisition body based on environmental factor data. The data analysis unit determines the selectable effective thermal comfort area of ​​the target acquisition body based on the area of ​​the periodic motion region of the target acquisition body; Extract the interval duration of the R wave in the target body's electrocardiogram and determine the allowable range of environmental factor data based on the interval duration of the R wave in the target body's electrocardiogram. The degree of influence of ambient wind speed is determined based on the ambient wind speed and the open area of ​​the selectable thermal comfort effective zone, and the degree of influence of ambient temperature is determined based on the ambient temperature of the selectable thermal comfort effective zone. If the ambient temperature of the selectable effective thermal comfort area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of ambient temperature based on secondary influencing factors. The thermal comfort value of the target acquisition body is adjusted according to the thermal comfort value compensation formula and transmitted to the user terminal; The thermal comfort value of the target acquisition body after compensation adjustment is denoted as Q, and the thermal comfort value before compensation adjustment is denoted as Q0. The thermal comfort value compensation formula is:

[0006] Where V is the ambient wind speed, T is the ambient temperature, V0 is the preset ambient wind speed, T0 is the preset ambient temperature, α1 is the degree of influence of ambient wind speed, and α2 is the degree of influence of ambient temperature. The individual data includes the skin temperature and electrocardiogram signal of the target body, and the environmental factor data includes ambient temperature, ambient wind speed, ambient humidity and the area of ​​the obstructed area. Ambient humidity and the area of ​​the obstructed area are secondary influencing factors. The first data analysis condition is that the thermal comfort stability of the target body is within a second preset stability range. The thermal comfort model is a CNN model.

[0007] Furthermore, the data analysis unit determines whether to re-determine the thermal comfort value of the target acquisition body and the method for determining the thermal comfort value based on the thermal comfort stability of the target acquisition body; If the thermal comfort stability is within the first preset stability range, the data analysis unit determines the waiting time for stabilization and re-determines the thermal comfort value of the target acquisition body when the stabilization time ends. If the thermal comfort stability is within the second preset stability range, the data analysis unit determines to re-determine the thermal comfort value of the target acquisition body and compensates the thermal comfort value of the target acquisition body based on environmental factor data. If the thermal comfort stability of the target acquisition body is within the third preset stability range, the data analysis unit determines that there is no need to re-determine the thermal comfort value of the target acquisition body. The thermal comfort stability is related to the change in the thermal comfort value of the target sample within a preset detection time.

[0008] Furthermore, under the first data analysis conditions, the data analysis unit extracts and determines the selectable thermal comfort effective area of ​​the target acquisition body based on the area of ​​the periodic motion region within the most recent single detection cycle of the target acquisition body; The area of ​​the selectable thermal comfort effective region is positively correlated with the area of ​​the periodic motion region. The selectable thermal comfort effective region is a circular region with the center being the current position of the target acquisition body.

[0009] Furthermore, under the second data analysis condition, the data analysis unit calculates the interval duration difference between the first and second interval durations of the R wave in the target acquisition body's electrocardiogram, and determines the allowable influence range of environmental factor data based on the interval duration difference; If the interval duration difference is within the first preset interval duration difference range, the data analysis unit determines the allowable impact value range of the environmental factor data based on the interval duration difference, and the allowable impact value range of the environmental factor data is the preset allowable impact value range; If the interval duration difference is within the second preset interval duration difference range, the data analysis unit determines the allowable impact range of the environmental factor data based on the interval duration difference, and the allowable impact range of the environmental factor data is negatively correlated with the interval duration difference. The second data analysis condition is that the effective area for selectable thermal comfort has been determined.

[0010] Furthermore, under the third data analysis condition, the data analysis unit determines the degree of influence of the ambient wind speed based on the ambient wind speed in the selectable effective thermal comfort area; If the ambient wind speed in the selectable effective thermal comfort area is less than or equal to the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed as the preset degree of influence of the ambient wind speed. If the ambient wind speed in the selectable effective thermal comfort area is greater than the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed based on the open area of ​​the selectable effective thermal comfort area. The third data analysis condition is that the preset allowable influence value range has been determined.

[0011] Furthermore, the data analysis unit determines the degree of influence of ambient wind speed based on the open area of ​​the selectable thermal comfort effective region; The open area of ​​the optional thermal comfort effective zone is negatively correlated with the degree of influence of the ambient wind speed.

[0012] The data analysis unit extracts the ambient temperature of the selectable effective thermal comfort zone under the fourth data analysis condition. If the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature based on secondary influencing factors. If the ambient temperature of the selectable thermal comfort effective area is less than or equal to the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature to be the preset degree of influence of the ambient temperature. The fourth data analysis condition is the completion of determining the degree of influence of environmental wind speed.

[0013] Furthermore, the data analysis unit extracts the ambient humidity of the selectable effective thermal comfort area under the fifth data analysis condition and determines the first sub-influence coefficient based on the ambient humidity. If the ambient humidity is less than or equal to the preset ambient humidity, the data analysis unit determines that the first sub-influence coefficient is the preset humidity sub-influence coefficient; If the ambient humidity is greater than the preset ambient humidity, the data analysis unit determines a first sub-influence coefficient based on the humidity difference between the ambient humidity and the preset ambient humidity. The first sub-influence coefficient is positively correlated with the humidity difference. The fifth data analysis condition is that the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature.

[0014] Furthermore, under the sixth data analysis condition, the data analysis unit extracts the heat absorption capacity of the relevant shading objects in the shading area of ​​the selectable thermal comfort effective area. If the heat absorption capacity is less than the preset heat absorption capacity threshold, the data analysis unit determines the second sub-influence coefficient for determining the area of ​​the shielded region based on the heat absorption capacity of the relevant shielding object. The second sub-influence coefficient is negatively correlated with the heat absorption capacity. The sixth data analysis condition is that the determination of the first sub-influence coefficient is completed.

[0015] Furthermore, the data analysis unit determines the degree of influence of ambient temperature based on the first sub-influence coefficient and the second sub-influence coefficient.

[0016] Compared with the prior art, the beneficial effects of this invention are as follows: the technical solution of this invention determines whether to re-determine the thermal comfort value and the method for determining the thermal comfort value based on the thermal comfort stability of the target acquisition body, avoiding instability of the thermal comfort value caused by environmental factors and individual behavior of the target acquisition body, thereby improving the accuracy of thermal comfort value determination. Furthermore, when compensating for the thermal comfort value of the target acquisition body based on environmental factor data, the area of ​​the periodic motion region within the most recent single detection cycle of the target acquisition body is extracted to determine the selectable effective thermal comfort region of the target acquisition body, avoiding the problem of low determination accuracy caused by an excessively large collection range of environmental factor data. At the same time, the allowable influence range of environmental factor data is determined based on the interval duration of the R wave in the electrocardiogram of the target acquisition body. The interval duration of the R wave reflects the heart rate of the target acquisition body, thereby reflecting the influence of individual movement factors and physical differences of the target acquisition body on the determination of thermal comfort value, thus making the determined allowable influence range of environmental factor data more consistent with the actual working scenario.

[0017] In this invention, if the ambient wind speed in the selectable effective thermal comfort area is greater than the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed based on the open area of ​​the selectable effective thermal comfort area. This makes the determination of the degree of influence of the ambient wind speed more consistent with the actual working scenario and further improves the accuracy of the determination of the degree of influence of the ambient wind speed.

[0018] In this invention, the data analysis unit determines the degree of influence of ambient temperature based on the first sub-influence coefficient and the second sub-influence coefficient, making the determination of the degree of influence of ambient temperature more consistent with the actual working scenario and further improving the accuracy of the determination of the degree of influence of ambient wind speed. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of an outdoor thermal comfort evaluation method based on data collected by wearable devices, according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating how the thermal comfort value of the target acquisition body is determined based on its thermal comfort stability, and the method for determining the thermal comfort value, as described in this embodiment of the invention. Figure 3 This is a flowchart illustrating how to determine the permissible range of environmental factor data based on the time interval difference, as per an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0021] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0023] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0024] Please see Figure 1 The diagram illustrates an outdoor thermal comfort evaluation method based on data collected by wearable devices, as described in an embodiment of the present invention. The present invention provides an outdoor thermal comfort evaluation method based on data collected by wearable devices, comprising: Collect target data, which includes individual data of the target data subject and environmental factor data; The data analysis unit determines the thermal comfort value of the target acquisition body based on the individual data of the target acquisition body through the thermal comfort model. Under the first data analysis condition, the data analysis unit compensates for the thermal comfort value of the target acquisition body based on environmental factor data. The data analysis unit determines the selectable effective thermal comfort area of ​​the target acquisition body based on the area of ​​the periodic motion region of the target acquisition body; Extract the interval duration of the R wave in the target body's electrocardiogram and determine the allowable range of environmental factor data based on the interval duration of the R wave in the target body's electrocardiogram. The degree of influence of ambient wind speed is determined based on the ambient wind speed and the open area of ​​the selectable thermal comfort effective zone, and the degree of influence of ambient temperature is determined based on the ambient temperature of the selectable thermal comfort effective zone. If the ambient temperature of the selectable effective thermal comfort area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of ambient temperature based on secondary influencing factors. The thermal comfort value of the target acquisition body is adjusted according to the thermal comfort value compensation formula and transmitted to the user terminal; The thermal comfort value of the target acquisition body after compensation adjustment is denoted as Q, and the thermal comfort value before compensation adjustment is denoted as Q0. The thermal comfort value compensation formula is:

[0025] Where V is the ambient wind speed, T is the ambient temperature, V0 is the preset ambient wind speed, T0 is the preset ambient temperature, α1 is the degree of influence of ambient wind speed, and α2 is the degree of influence of ambient temperature. The individual data includes the skin temperature and electrocardiogram signal of the target body, and the environmental factor data includes ambient temperature, ambient wind speed, ambient humidity and the area of ​​the obstructed area. Ambient humidity and the area of ​​the obstructed area are secondary influencing factors. The first data analysis condition is that the thermal comfort stability of the target body is within a second preset stability range. The thermal comfort model is a CNN model.

[0026] Specifically, the individual data can be collected through wearable devices, which need to have heart rate sensors and skin temperature sensors. The environmental factor data can be collected using temperature sensors, anemometers, and humidity sensors to collect the corresponding information to be collected. It is worth noting that the shading area is the sum of the shading areas within the selectable thermal comfort effective area where the shadow area is greater than the preset shadow area. The shading area can be collected using an image acquisition and transmission device or a drone.

[0027] Specifically, the thermal comfort model employs a CNN model, where human skin temperature, ambient temperature, and electrocardiogram (ECG) signals are used as input data to train and build the CNN model. The steps for building the CNN model include: input data acquisition, data preprocessing, CNN model training and prediction, and model evaluation. This is easily understood by those skilled in the art. However, it is worth noting that data preprocessing is crucial because it can reduce noise and eliminate outliers, thereby improving the model's training and prediction capabilities. Specifically, data preprocessing can include the following sub-steps: Numericalization: Input data needs to be converted into numerical signals before it can be processed by a computer. This is done by using an analog-to-digital converter (ADC) to sample the signals and convert them into digital signals. An ADC is a device that converts continuous signals into discrete signals; it converts the signal amplitude at each sampling moment into a corresponding digital code.

[0028] Filtering: After the input data is quantified, it needs to be filtered to eliminate noise and improve signal quality. This filtering process removes high-frequency or low-frequency components from the signal, thereby improving signal quality and accuracy. Because ECG signals contain a significant amount of high-frequency and low-frequency noise, low-pass and high-pass filters are typically used. Low-pass filters remove high-frequency noise while retaining low-frequency components, while high-pass filters remove low-frequency noise while retaining high-frequency components. The specific filtering method is determined by the user based on the actual working scenario to improve signal quality and accuracy, thus providing a more reliable data foundation for subsequent thermal comfort evaluation.

[0029] Baseline drift removal: Baseline drift refers to the slow drift of a signal along the time axis, usually caused by factors such as the measuring equipment itself or the external environment. If not removed, baseline drift affects the shape and characteristics of the signal, thus impacting subsequent thermal comfort evaluation results. This paper provides a feasible method to eliminate baseline drift, employing curve fitting technology. Curve fitting involves finding a curve equation that best approximates the coordinates of existing data points, using this curve equation to describe the relationship between these data points. First, a baseline model needs to be constructed, which is a function model of the baseline changing over time. Commonly used baseline models include linear models, polynomial models, and spline models. The user determines the appropriate baseline model based on the signal characteristics and data distribution. The baseline model is then fitted using sampled data to obtain its parameters. Common fitting methods include least squares, least squares support vector regression, and locally weighted linear regression. Finally, the fitted baseline model is used to correct the original signal, eliminating baseline drift. Specifically, the fitted baseline model is applied to the original signal to obtain the corrected signal. By removing baseline drift to eliminate unnecessary noise and interference in the signal, the accuracy and stability of the signal are improved, providing a more reliable data foundation for subsequent thermal comfort assessment.

[0030] Segmentation: The input data is divided into several segments of equal length to facilitate the analysis of signals within different time periods.

[0031] Standardization: Standardization is applied to each segment to eliminate the influence of signal amplitude differences on the result. Standardization ensures that the signal mean is 0 and the standard deviation is 1, thus eliminating amplitude differences. A standardization method is provided using Z-score standardization, which involves subtracting the mean from the signal value of each segment and then dividing by its standard deviation. Specifically, for a segment of length N, its signal value sequence is {x1, x2, ..., x...}. N Given that the mean is μ and the standard deviation is σ, the standardized signal sequence is:

[0032] Standardization can eliminate amplitude differences in signals, making the morphological characteristics of the signals more prominent.

[0033] These data preprocessing steps can yield more accurate data, thereby improving the training and prediction capabilities of the model. This is something that is easily understood by those skilled in the art and will not be elaborated upon here.

[0034] Specifically, the range of thermal comfort values ​​is related to the thermal comfort model. In this embodiment of the invention, the range of thermal comfort values ​​is [0,1]. A method is provided to map all thermal comfort values ​​to the [0,1] interval. Processed skin temperature and electrocardiogram signals are used as datasets, and all data are normalized using a Z-score model. The dataset is then divided into two sets: a training set (80% of the dataset) and a validation set (20% of the dataset). The training set is used as the input layer to train the CNN model to improve its prediction accuracy. After converting the input layer into a matrix, multiple appropriate convolution kernels are selected to perform convolution operations on the input signal matrix, thereby extracting the local features of the input layer matrix. During this process, the positional relationships of the features are also determined; therefore, this layer can be called either a convolutional layer or a feature mapping layer. Each computational layer of the entire neural network consists of multiple feature mapping planes, and all neurons on each plane have equal weights.

[0035] After the convolutional layer is completed, the output data of the convolution is passed to the batch normalization layer to standardize the output data. Specifically, for the input data {x1, x2, ..., xn}, we first use formula (1) to calculate the mean µ of its n samples, and then use formula (2) to calculate its variance σ. Then, the n input sample data are demeaned and divided by the standard deviation using formula (3). A constant ε is added to the variance estimate to ensure that the denominator is not zero and ε > 0. Finally, the standardized data is obtained. Parameters γ and β are introduced to scale and shift the standardized data to better maintain the diversity of data distribution and nonlinear fitting ability. The value range of γ is [0.1, 10] and the value range of β is [-10, 10]. Users can determine the values ​​of γ and β according to the characteristics of the dataset and the structure of the neural network to achieve the best standardization effect. If the distribution of the dataset is relatively concentrated, the value of γ can be smaller to narrow the range of standardized data. If the distribution of the dataset is relatively dispersed, the value of γ can be larger to expand the range of standardized data. This is easy for those in the field to understand and will not be elaborated here.

[0036] (1) (2) (3) (4) The convolutional layer connects to the ReLU layer, processing the convolutional data by converting negative numbers to 0 and retaining positive numbers to increase the significance of the input features. After processing, the data is passed to the pooling layer for pooling, which includes two pooling methods: average pooling and max pooling. Average pooling calculates the average value of feature points in the neighborhood, which can reduce the variance of the estimate caused by neighborhood limitations; max pooling takes the maximum value of feature points in the neighborhood, which can reduce the shift in the estimated mean caused by the parameter errors of the convolutional layer.

[0037] After two convolutional pooling processes, a fully connected layer is applied to the final feature matrix. This maps the feature space obtained from the previous two convolutional pooling processes to the sample label space. Specifically, the fully connected layer integrates the feature matrix into a vector representation for classification or regression tasks, reducing the influence of feature spatial location on the classification result and improving the robustness of the entire network. Finally, classification is performed using the softmax layer, mapping all thermal comfort values ​​to the [0,1] interval. The thermal comfort of the target body is quantified by the magnitude of the thermal comfort value; the larger the thermal comfort value, the more comfortable the target body feels thermally.

[0038] Specifically, the data analysis unit determines whether to re-determine the thermal comfort value of the target acquisition body and the method for determining the thermal comfort value based on the thermal comfort stability of the target acquisition body; If the thermal comfort stability is within the first preset stability range, the data analysis unit determines the waiting time for stabilization and re-determines the thermal comfort value of the target acquisition body when the stabilization time ends. If the thermal comfort stability is within the second preset stability range, the data analysis unit determines to re-determine the thermal comfort value of the target acquisition body and compensates the thermal comfort value of the target acquisition body based on environmental factor data. If the thermal comfort stability of the target acquisition body is within the third preset stability range, the data analysis unit determines that there is no need to re-determine the thermal comfort value of the target acquisition body. The thermal comfort stability is related to the change in the thermal comfort value of the target sample within a preset detection time.

[0039] Specifically, the thermal comfort stability is calculated by calculating the absolute value of the difference between the maximum and minimum thermal comfort values ​​of the target acquisition body within a preset detection time of 1 minute. The reciprocal of this absolute value is taken as the thermal comfort stability. The greater the thermal comfort stability, the more stable the thermal comfort value of the target acquisition body. The preset stability range can be determined by the user through experiments with a large number of users to determine the thermal comfort stability of different target acquisition bodies under different levels of exercise. The degree of exercise can be quantified by the user's heart rate. According to the thermal comfort stability corresponding to different levels of exercise, the minimum thermal comfort stability corresponding to a heart rate range of less than 100 beats / minute is recorded as the minimum value of the third preset stability range. The maximum thermal comfort stability corresponding to a heart rate range of 100-150 beats / minute is recorded as the maximum value of the second preset stability range. The maximum thermal comfort stability corresponding to a heart rate range of 100-150 beats / minute is recorded as the minimum value of the second preset stability range. The maximum thermal comfort stability corresponding to a heart rate range of greater than 150 beats / minute is recorded as the maximum value of the first preset stability range.

[0040] Specifically, under the first data analysis condition, the data analysis unit extracts the area of ​​the periodic motion region of the target acquisition body in the most recent single detection cycle to determine the selectable thermal comfort effective area of ​​the target acquisition body; The area of ​​the optional thermal comfort effective region is positively correlated with the area of ​​the periodic motion region. The optional thermal comfort effective region is a circular region with the center of the circle being the current position of the target acquisition body. The periodic motion region is the motion trajectory of the target acquisition body within the most recent complete trajectory detection cycle.

[0041] Specifically, the selectable thermal comfort effective area has a minimum area, which is the area of ​​the periodic motion area. The method for calculating the area of ​​the periodic motion area is to project the motion trajectory of the target acquisition body within a single trajectory detection cycle onto a two-dimensional coordinate system, establish a minimum circle containing the motion trajectory, and record the area corresponding to the minimum circle as the area of ​​the periodic motion area.

[0042] Specifically, under the second data analysis condition, the data analysis unit calculates the interval difference between the first and second interval durations of the R wave in the target acquisition body's electrocardiogram, and determines the allowable influence range of environmental factor data based on the interval duration difference. If the interval duration difference is within the first preset interval duration difference range, the data analysis unit determines the allowable impact value range of the environmental factor data based on the interval duration difference. The allowable impact value range of the environmental factor data is a preset allowable impact value range, which is [0, 0.3]. If the interval duration difference is within the second preset interval duration difference range, the data analysis unit determines the allowable impact range of the environmental factor data based on the interval duration difference. The allowable impact range of the environmental factor data is negatively correlated with the interval duration difference. The maximum value of the allowable impact range of the environmental factor data determined based on the interval duration difference is less than the maximum value of the preset allowable impact range, and the minimum value of the allowable impact range of the environmental factor data determined based on the interval duration difference is equal to the minimum value of the preset allowable impact range. The second data analysis condition is that the effective area for selectable thermal comfort has been determined.

[0043] Specifically, the heart rate of the target acquisition subject can be obtained based on the occurrence time of the R wave. The R wave is the highest peak in the QRS complex of an electrocardiogram (ECG), representing the electrical signal released by the heart during ventricular contraction. In an ECG, the time interval between the occurrence of the R wave is the time interval between two adjacent ventricular contractions, i.e., the heart rate. The first interval duration is the minimum interval duration Tmin between two adjacent R wave occurrences within a single detection cycle, and the second interval duration is the maximum interval duration Tmax between two adjacent R wave occurrences within a single detection cycle. The values ​​within the first preset interval duration difference range are all less than or equal to the preset interval duration difference, and the values ​​within the second preset interval duration difference range are all greater than the preset interval duration difference. The preset interval duration difference is calculated as follows: preset interval duration difference ΔT = [(Tmax - Tmin)] / 2.

[0044] Specifically, the data analysis unit determines the degree of influence of the ambient wind speed based on the ambient wind speed in the selectable effective thermal comfort area under the third data analysis condition; If the ambient wind speed in the selectable effective thermal comfort area is less than or equal to the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed α1 to be the degree of influence of the preset ambient wind speed, and the degree of influence of the preset ambient wind speed is α10, α10 = 0.15; If the ambient wind speed in the selectable effective thermal comfort area is greater than the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed based on the open area of ​​the selectable effective thermal comfort area. In this case, α1≤α10. The third data analysis condition is that the preset allowable influence value range has been determined.

[0045] The preset ambient wind speed is related to the sweat evaporation rate of the target sample. That is, the user can monitor and determine the sweat evaporation rate of the target sample under different wind speeds, place the skin area to be tested on a heat flow meter, measure the heat flow change of the tested area, and thus calculate the amount of sweat evaporation per unit time. The amount of sweat evaporation in each experiment is recorded, and the average value is calculated. The wind speed corresponding to the average value is recorded as the preset ambient wind speed.

[0046] Specifically, the data analysis unit determines the degree of influence of ambient wind speed based on the open area of ​​the selectable effective thermal comfort zone; The open area of ​​the selectable thermal comfort effective zone is negatively correlated with the degree of influence of the ambient wind speed.

[0047] Specifically, the open area refers to the road area within the selectable effective thermal comfort area. Wider roads generally result in higher outdoor air temperatures because increased road width exacerbates the urban heat island effect, which refers to the phenomenon of higher temperatures within a city compared to its surrounding areas. Buildings, roads, and vehicles in a city absorb solar radiation and convert it into heat. Furthermore, wider roads also mean lower building density and more opportunities for ventilation and air convection, further contributing to higher outdoor air temperatures. Therefore, wider roads lead to higher outdoor air temperatures, thus reducing the positive impact of ambient wind speed on thermal comfort values.

[0048] Specifically, the data analysis unit extracts the ambient temperature of the selectable effective thermal comfort area under the fourth data analysis condition. If the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature α2 based on secondary influencing factors, where α2≤α20; If the ambient temperature of the selectable thermal comfort effective area is less than or equal to the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature as the preset ambient temperature influence degree α20, where α20 = 0.15; The fourth data analysis condition is the completion of determining the degree of influence of environmental wind speed.

[0049] Specifically, the preset ambient temperature is related to the thermal comfort value of the target sample. Users can determine the preset ambient temperature of the target sample based on the thermal comfort value of the target sample at different temperatures under controlled temperature conditions in the laboratory. The preset ambient temperature is the temperature corresponding to the average value of the thermal comfort value of the target sample at different temperatures.

[0050] Specifically, the data analysis unit extracts the ambient humidity of the selectable effective thermal comfort area under the fifth data analysis condition and determines the first sub-influence coefficient based on the ambient humidity. If the ambient humidity is less than or equal to the preset ambient humidity, the data analysis unit determines that the first sub-influence coefficient ζ1 is the preset humidity sub-influence coefficient ζ10, where ζ10 = 0.5; If the ambient humidity is greater than the preset ambient humidity, the data analysis unit determines a first sub-influence coefficient ζ1 based on the humidity difference between the ambient humidity and the preset ambient humidity. The first sub-influence coefficient is positively correlated with the humidity difference, and the ζ1 determined based on the humidity difference between the ambient humidity and the preset ambient humidity is less than 0.5. The fifth data analysis condition is that the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature.

[0051] Specifically, the preset ambient humidity value is determined by the user under controlled humidity conditions in a laboratory setting, based on the skin temperature of the target sample at a preset ambient temperature and humidity. The average of all skin temperatures obtained in the experiment is calculated, and the corresponding ambient humidity is recorded as the preset ambient humidity. The effect of ambient humidity on skin temperature is that higher ambient humidity results in higher skin temperature. This is because heat dissipation from the human body is achieved through the evaporation of sweat. Higher ambient humidity means higher moisture content in the air, which reduces the evaporation rate of sweat, thus affecting the body's heat dissipation and increasing skin temperature. Therefore, if the ambient humidity is higher than the preset ambient humidity, the data analysis unit determines a first sub-influence coefficient based on the humidity difference between the ambient humidity and the preset ambient humidity. This first sub-influence coefficient is positively correlated with the humidity difference.

[0052] Specifically, under the sixth data analysis condition, the data analysis unit extracts the heat absorption capacity of the relevant shading objects in the shading area of ​​the selectable thermal comfort effective area. If the heat absorption capacity is less than the preset heat absorption capacity threshold, the data analysis unit determines the second sub-influence coefficient ζ2 based on the heat absorption capacity of the relevant obstruction to determine the area of ​​the obstruction area. The second sub-influence coefficient is negatively correlated with the heat absorption capacity, and ζ2≤0.5. The sixth data analysis condition is that the determination of the first sub-influence coefficient is completed.

[0053] Specifically, the heat absorption capacity of the shading object is preset and stored in the data analysis unit. The heat absorption capacity of the shading object is related to the material and type of the shading object. The heat absorption capacity of the shading object is the ability to absorb solar radiation. The heat absorption capacity of the shading object can be simulated by using the finite element analysis software ANSYS to simulate the heat transfer process of different materials or objects under different environmental conditions. The increase in surface temperature of the shading object per unit time under different radiation intensities is calculated and its average value is recorded as the heat absorption capacity of the shading object, with the unit being ℃ / min. The preset heat absorption capacity threshold value allows the user to statistically analyze the heat absorption capacity of each shading object in the actual application scenario of this invention and calculate the average value of the heat absorption capacity of all shading objects as the preset heat absorption capacity threshold value.

[0054] Specifically, the data analysis unit determines the degree of influence of ambient temperature based on the first sub-influence coefficient and the second sub-influence coefficient, α2=α20×[(ζ1×B / B0)+(ζ2×K / K0)], where B0 is the preset ambient humidity and K0 is the preset heat absorption capacity threshold.

[0055] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0056] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating outdoor thermal comfort based on data collected by wearable devices, characterized in that, include: Collect target data, which includes individual data of the target data subject and environmental factor data; The data analysis unit determines the thermal comfort value of the target acquisition body based on the individual data of the target acquisition body through the thermal comfort model. Under the first data analysis condition, the data analysis unit compensates for the thermal comfort value of the target acquisition body based on environmental factor data. The data analysis unit determines the selectable effective thermal comfort area of ​​the target acquisition body based on the area of ​​the periodic motion region of the target acquisition body; The periodic motion region is the motion trajectory of the target acquisition body within the most recent complete trajectory detection cycle; The method for calculating the area of ​​the periodic motion region is as follows: project the motion trajectory of the target acquisition body within a single trajectory detection cycle onto a two-dimensional coordinate system, establish a minimum circle containing the motion trajectory, and record the area corresponding to the minimum circle as the area of ​​the periodic motion region. Extract the interval duration of the R wave in the target body's electrocardiogram and determine the allowable range of environmental factor data based on the interval duration of the R wave in the target body's electrocardiogram. The degree of influence of ambient wind speed is determined based on the ambient wind speed and the open area of ​​the selectable thermal comfort effective zone, and the degree of influence of ambient temperature is determined based on the ambient temperature of the selectable thermal comfort effective zone. If the ambient temperature of the selectable effective thermal comfort area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of ambient temperature based on secondary influencing factors. The thermal comfort value of the target acquisition body is adjusted according to the thermal comfort value compensation formula and transmitted to the user terminal; The thermal comfort value of the target acquisition body after compensation adjustment is denoted as Q, and the thermal comfort value before compensation adjustment is denoted as Q0. The thermal comfort value compensation formula is: ； Where V is the ambient wind speed, T is the ambient temperature, V0 is the preset ambient wind speed, T0 is the preset ambient temperature, α1 is the degree of influence of ambient wind speed, and α2 is the degree of influence of ambient temperature. The individual data includes the skin temperature and electrocardiogram signal of the target body, and the environmental factor data includes ambient temperature, ambient wind speed, ambient humidity and the area of ​​the obstructed area. Ambient humidity and the area of ​​the obstructed area are secondary influencing factors. The first data analysis condition is that the thermal comfort stability of the target body is within a second preset stability range. The thermal comfort model is a CNN model.

2. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 1, characterized in that, The data analysis unit determines whether to re-determine the thermal comfort value of the target acquisition body and the method for determining the thermal comfort value based on the thermal comfort stability of the target acquisition body. If the thermal comfort stability is within the first preset stability range, the data analysis unit determines the waiting time for stabilization and re-determines the thermal comfort value of the target acquisition body when the stabilization time ends. If the thermal comfort stability is within the second preset stability range, the data analysis unit determines to re-determine the thermal comfort value of the target acquisition body and compensates the thermal comfort value of the target acquisition body based on environmental factor data. If the thermal comfort stability of the target acquisition body is within the third preset stability range, the data analysis unit determines that there is no need to re-determine the thermal comfort value of the target acquisition body. The thermal comfort stability is related to the change in the thermal comfort value of the target sample within a preset detection time.

3. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 2, characterized in that, The data analysis unit extracts and determines the selectable thermal comfort effective area of ​​the target acquisition body based on the area of ​​the periodic motion region within the most recent single detection cycle of the target acquisition body under the first data analysis conditions. The area of ​​the selectable thermal comfort effective region is positively correlated with the area of ​​the periodic motion region. The selectable thermal comfort effective region is a circular region with the center being the current position of the target acquisition body.

4. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 3, characterized in that, The data analysis unit calculates the interval difference between the first and second interval durations of the R wave in the target acquisition body's electrocardiogram under the second data analysis condition, and determines the allowable influence range of environmental factor data based on the interval duration difference. If the interval duration difference is within the first preset interval duration difference range, the data analysis unit determines the allowable impact value range of the environmental factor data based on the interval duration difference, and the allowable impact value range of the environmental factor is the preset allowable impact value range; If the interval duration difference is within the second preset interval duration difference range, the data analysis unit determines the allowable impact range of the environmental factor data based on the interval duration difference, and the allowable impact range of the environmental factor data is negatively correlated with the interval duration difference. The second data analysis condition is that the effective area for selectable thermal comfort has been determined.

5. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 4, characterized in that, The data analysis unit determines the degree of influence of the ambient wind speed based on the ambient wind speed in the selectable effective thermal comfort area under the third data analysis condition. If the ambient wind speed in the selectable effective thermal comfort area is less than or equal to the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed as the preset degree of influence of the ambient wind speed. If the ambient wind speed in the selectable effective thermal comfort area is greater than the preset ambient wind speed, the data analysis unit determines the degree of influence of the ambient wind speed based on the open area of ​​the selectable effective thermal comfort area. The third data analysis condition is that the preset allowable influence value range has been determined.

6. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 5, characterized in that, The data analysis unit determines the degree of influence of environmental wind speed based on the open area of ​​the selectable effective thermal comfort zone. The open area of ​​the selectable thermal comfort effective zone is negatively correlated with the degree of influence of the ambient wind speed.

7. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 6, characterized in that, The data analysis unit extracts the ambient temperature of the selectable effective thermal comfort zone under the fourth data analysis condition. If the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature based on secondary influencing factors. If the ambient temperature of the selectable thermal comfort effective area is less than or equal to the preset ambient temperature, the data analysis unit determines the degree of influence of the ambient temperature to be the preset degree of influence of the ambient temperature. The fourth data analysis condition is the completion of determining the degree of influence of environmental wind speed.

8. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 7, characterized in that, The data analysis unit extracts the ambient humidity of the selectable effective thermal comfort area under the fifth data analysis condition and determines the first sub-influence coefficient based on the ambient humidity. If the ambient humidity is less than or equal to the preset ambient humidity, the data analysis unit determines that the first sub-influence coefficient is the preset humidity sub-influence coefficient; If the ambient humidity is greater than the preset ambient humidity, the data analysis unit determines a first sub-influence coefficient based on the humidity difference between the ambient humidity and the preset ambient humidity. The first sub-influence coefficient is positively correlated with the humidity difference. The fifth data analysis condition is that the ambient temperature of the selectable thermal comfort effective area is greater than the preset ambient temperature.

9. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 8, characterized in that, The data analysis unit extracts the heat absorption capacity of the relevant shielding objects in the shielding area of ​​the selectable thermal comfort effective area under the sixth data analysis condition. If the heat absorption capacity is less than the preset heat absorption capacity threshold, the data analysis unit determines the second sub-influence coefficient for determining the area of ​​the shielded region based on the heat absorption capacity of the relevant shielding object. The second sub-influence coefficient is negatively correlated with the heat absorption capacity of the relevant shielding object. The sixth data analysis condition is that the determination of the first sub-influence coefficient is completed.

10. The outdoor thermal comfort evaluation method based on wearable device data as described in claim 9, characterized in that, The data analysis unit determines the degree of influence of ambient temperature based on the first sub-influence coefficient and the second sub-influence coefficient.

Images