Intelligent prediction system for sports environment based on internet of things

Abstract

The application relates to the technical field of data processing, in particular to a motion environment intelligent prediction system based on the Internet of Things, which comprises a data acquisition module, which is used for acquiring data of each environment parameter in each time period at different time points in the environment of a motion place; an environment prediction module, which is used for predicting the environment parameters, comprising: determining the environment fluctuation degree, long-term skewness, evaluation coefficient and effective weight of each time period, and predicting each environment parameter by using a neural network model; and an evaluation recommendation module, which is used for evaluating the environment of the motion place and recommending a motion mode for a user, comprising: determining the first suitability, the second suitability and the aerobic recommendation coefficient of the next monitoring period, and evaluating and recommending the motion mode of the user in the motion place. The application can improve the accuracy of environment parameter prediction, thereby evaluating the condition of the environment suitable for aerobic exercise, improving the motion effect of rehabilitation training and reducing motion injury.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a motion environment intelligent prediction system based on Internet of Things. BACKGROUND

[0002] With the rapid development and deep integration of artificial intelligence, Internet of Things and big data technology fields, the medical rehabilitation field is also facing a challenging and transformative change. Under the background of clinical rehabilitation and community health care, scientific rehabilitation training, maximizing the rehabilitation effect and effectively avoiding secondary injury have become the core issues of common concern.

[0003] Traditional motion environment prediction systems can usually only provide static prediction data display, lack intelligent fusion of multi-source heterogeneous data and dynamic prediction ability, and are difficult to capture the instantaneous changes and local microclimate mutation characteristics of environmental parameters, resulting in inaccurate prediction results of the motion environment in the sports place. Secondly, it is unable to provide personalized rehabilitation training motion recommendations and high-value motion decision support for users according to environmental changes, resulting in users exercising in unsuitable environmental conditions, affecting health and exercise effect. SUMMARY

[0004] In order to solve the above technical problems, the motion environment intelligent prediction system based on Internet of Things is provided to solve the existing problems.

[0005] The technical problem solved by the present application is to provide a motion environment intelligent prediction system based on Internet of Things, which comprises:

[0006] A data acquisition module is configured to acquire data of each environmental parameter at different time points in each time period in the environment of the sports place, wherein the environmental parameters include temperature, humidity, wind speed, ultraviolet intensity and PM 2.5 concentration;

[0007] An environment prediction module is configured to predict the environmental parameters, comprising:

[0008] Anomaly detection is performed on the data of each environmental parameter at all time points in each time period, and abnormal time points are obtained. The average difference between the data of different environmental parameters at abnormal time points and other time points is analyzed. The periodic change of the data of humidity and wind speed at abnormal time points is combined to determine the environmental fluctuation degree of each time period.

[0009] The distribution offset and change trend of the data of ultraviolet intensity and PM 2.5 concentration at all time points in each time period are calculated to obtain the long-term skew degree of each time period. The environmental fluctuation degree is combined to obtain the evaluation coefficient of each time period.

[0010] Based on the interval length of each time period in each monitoring period and the evaluation coefficient, the effective weight of each time period is calculated, and based on the effective weight of the time period to which each time is belong, the neural network model is used to predict each environmental parameter in the next monitoring period.

[0011] The evaluation recommendation module is used to evaluate the environment of the sports place and recommend the sports mode for the user, comprising:

[0012] For the next monitoring period, the offset of the predicted values of temperature and humidity and the dispersion degree thereof are analyzed to determine the first suitability of the next monitoring period.

[0013] The difference between the change trend of the predicted values of the wind speed and PM 2.5 concentration, and the average level of the predicted values of PM 2.5 concentration and ultraviolet intensity, to determine the second suitability of the next monitoring period, and combine the first suitability to obtain the aerobic recommendation coefficient of the next monitoring period, to evaluate and recommend the sports mode of the user in the sports place.

[0014] Preferably, the determination of the environmental fluctuation degree of each time period comprises:

[0015] The ratio between the mean value of the data of each environmental parameter at all abnormal time points in each time period and the mean value of the data of all time points except the abnormal time points is calculated as the relative change gradient of each environmental parameter in each time period, and the cumulative sum of the relative change gradients of all environmental parameters in each time period is calculated.

[0016] The autocorrelation function is used to respectively obtain the autocorrelation coefficients corresponding to a plurality of preset lag orders based on the data of all abnormal time points of humidity and wind speed in each time period, and the mode of the autocorrelation coefficients corresponding to all preset lag orders is respectively taken as the first correlation degree and the second correlation degree of each time period; and the average value of the first correlation degree and the second correlation degree is calculated.

[0017] The environmental fluctuation degree is the product of the average value and the cumulative sum.

[0018] Preferably, the calculation of the long-term skewness of each time period comprises:

[0019] The sum of the absolute value of the skewness of the ultraviolet intensity at all time points in each time period and the absolute value of the skewness of PM 2.5 concentration is taken as a first sum value.

[0020] The sum of the Hurst index of the data of all abnormal time points of ultraviolet intensity in each time period and the Hurst index of the data of all abnormal time points of PM 2.5 concentration is taken as a second sum value.

[0021] The long-term skewness is a product of the first sum and the second sum.

[0022] Preferably, the evaluation coefficient is a normalized result of a product of the environmental fluctuation and the long-term skewness.

[0023] Preferably, the effective weight of each time period is calculated, including:

[0024] An initial prediction time is obtained at a first time in a next monitoring period of each monitoring period; and an inverse of a time interval between a last time in each time period and the initial prediction time is taken as a time weight of each time period.

[0025] The effective weight is a product of the time weight and the evaluation coefficient.

[0026] Preferably, the prediction of each environmental parameter in the next monitoring period includes: based on the data of each environmental parameter at all times in each monitoring period, taking the effective weight of the time period to which each time belongs as an attention weight of a neural network model with attention mechanism, and using the neural network model to predict each environmental parameter to obtain a prediction value of each environmental parameter at each time in the next monitoring period.

[0027] Preferably, the determination of the first suitability of the next monitoring period includes:

[0028] A temperature change rate is obtained by taking a change rate between a mean value of the prediction value of the temperature at each time in the next monitoring period and a preset suitable temperature; a humidity change rate is obtained by taking a change rate between a mean value of the prediction value of the humidity at each time in the next monitoring period and a preset suitable humidity; and a temperature and humidity deviation is obtained by taking a sum of the temperature change rate and the humidity change rate.

[0029] A quartile range of the prediction value of the temperature and the humidity at all times in the next monitoring period is calculated respectively, and the quartile range is positively mapped respectively; and a temperature and humidity dispersion is obtained by taking a sum of the positively mapped results of the temperature and the humidity in the next monitoring period.

[0030] The first suitability is a negatively mapped result of a product of the temperature and humidity deviation and the temperature and humidity dispersion.

[0031] Preferably, the determination of the second suitability of the next monitoring period includes:

[0032] The prediction value of the wind speed and the prediction value of the PM 2.5 concentration at each time in the next monitoring period are curve fitted respectively, and a fitting curve corresponding to the wind speed and a fitting curve corresponding to the PM 2.5The predicted value corresponding to the time when the slope of the fitting curve corresponding to the concentration is greater than 0, constitutes a wind speed growth sequence and a concentration growth sequence; the distance between the wind speed growth sequence and the concentration growth sequence is calculated;

[0033] The PM 2.5 The ratio of the average of the predicted values of the concentration at each time to the preset first reference threshold is denoted as a concentration ratio;

[0034] The ratio of the average of the predicted values of the ultraviolet intensity at each time in the next monitoring period to the preset second reference threshold is denoted as an intensity ratio; the sum of the concentration ratio and the intensity ratio is taken as the environmental risk degree;

[0035] The second suitability is the ratio of the distance to the environmental risk degree.

[0036] Preferably, the aerobic recommendation coefficient is the normalized result of the product of the first suitability and the second suitability.

[0037] Preferably, the evaluation and recommendation of the movement mode of the user in the movement place include: if the aerobic recommendation coefficient is greater than or equal to a preset threshold, recommending the user to perform aerobic movement in the movement place, otherwise, recommending the user to perform short-term anaerobic movement in the movement place.

[0038] The present application has at least the following beneficial effects:

[0039] The present application determines the environmental fluctuation degree of each time period by analyzing the abnormal mutation of different environmental parameters, the difference between the average level of abnormal data and non-abnormal data, and the periodic change of humidity and wind speed data at the abnormal time, which has the beneficial effect of considering the drastic change of environmental parameters in the movement place in a short time, and the periodic disturbance caused by the sensitivity of humidity and wind speed to climate mutation, reflecting the significant change of the environment in the time period, and evaluating the environmental instability in the time period; the long-term skew degree of each time period is calculated, which has the beneficial effect of considering the periodic change of the ultraviolet intensity, PM 2.5The distribution offset of the concentration and the long-term change trend reflect the pollution risk of long-term inhalable particulate matters and the exposure risk of ultraviolet rays in the exercise environment in this time period, and evaluate the health risk situation; the evaluation coefficient of each time period is determined, which has the beneficial effect of comprehensively evaluating the change intensity of the environmental parameters and reflecting the instability of the exercise environment; the effective weight of each time period is calculated, and based on the effective weight of the time period to which each time is belong, the neural network model is used to predict each environmental parameter in the next monitoring period, which has the beneficial effect of evaluating the influence on the prediction by the approaching prediction target of different time periods, and combining the influence of the unstable change of the exercise environment in different time periods on the prediction, dynamically adjusting the effective weight, so that the model pays more attention to the data of the time period which has greater influence on the prediction result, and improves the accuracy of the prediction of the environmental parameters; the first suitability of the next monitoring period is determined, which has the beneficial effect of reflecting the deviation and instability of the predicted value of the temperature and humidity in the next monitoring period by the deviation of the predicted value of the temperature and humidity from the temperature and humidity of the body comfort, and the dispersion of the predicted value of the temperature and humidity, and evaluating the environmental condition of the next monitoring period suitable for aerobic training exercise; the second suitability of the next monitoring period is determined, which has the beneficial effect of considering the growth trend of the PM 2.5 concentration caused by the diffusion intensity affected by the wind speed, and the average level of the PM 2.5 concentration and the ultraviolet radiation intensity, reflecting the potential risk of the environmental condition of the next monitoring period to the user's health, and further evaluating the environmental condition suitable for aerobic training exercise; the aerobic recommendation coefficient of the next monitoring period is obtained, which evaluates and recommends the exercise mode of the user in the exercise place, which has the beneficial effect of comprehensively evaluating the environmental condition suitable for aerobic training exercise from multiple aspects, providing scientific and personalized rehabilitation training exercise suggestions for the user, avoiding potential exercise environment risks in advance, ensuring that the user performs rehabilitation exercise in a suitable environment, improving the exercise effect of rehabilitation training and reducing exercise injuries. BRIEF DESCRIPTION OF DRAWINGS

[0040] The application provides an intelligent exercise environment prediction system based on the Internet of Things.

[0041] Figure 1 The application provides an intelligent exercise environment prediction system based on the Internet of Things.

[0042] Figure 2 The application provides an intelligent exercise environment prediction system based on the Internet of Things.

[0043] Figure 3 The application provides an intelligent exercise environment prediction system based on the Internet of Things. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the present application more clear, the Internet of Things based intelligent prediction system for sports environment is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0046] Please refer to Figure 1 , which shows the block diagram of the Internet of Things based intelligent prediction system for sports environment provided by an embodiment of the present application, which includes a data acquisition module, an environment prediction module and an evaluation recommendation module.

[0047] The data acquisition module is used to acquire the data of each environmental parameter at different time points in each time period in the environment of the sports venue.

[0048] With the development of rehabilitation medicine, users need to recover their functions through sports therapy. During the rehabilitation training process, the training effect and safety not only depend on the physical condition and training intensity of the user, but also are closely related to the sports environment at the time of training. Different sports environments are suitable for different rehabilitation training methods. When the environment is suitable, for example, when the temperature and humidity are in a relatively comfortable condition and the air quality is good, long-time aerobic exercise is recommended to improve the heart and lung function and muscle endurance. On the contrary, when the temperature and humidity are high and the air quality is poor, short-time aerobic exercise is recommended to reduce the probability of health risks and complications.

[0049] Based on the above analysis, through the temperature and humidity sensor, the wind speed sensor, the ultraviolet sensor and the PM 2.5 The detection sensor acquires the temperature, humidity, wind speed, ultraviolet intensity and PM 2.5 concentration of the sports venue at each time point.

[0050] In this embodiment, the frequency of data acquisition is 1 Hz. As other implementation manners, the implementer can set it according to the actual situation.

[0051] Among them, the S12SD ultraviolet sensor outputs an analog voltage signal, and the voltage at each time point is acquired through AD conversion. The calculation formula of the ultraviolet intensity is:

[0052]

[0053]

[0054] Among them, is the light intensity at the time point, is a preset proportion coefficient, is a voltage at a time t, is a preset conversion coefficient, wherein, is 307 Lux / V, is 200 Lux, and Lux represents a unit of illumination intensity.

[0055] The PM sensor outputs a PWM signal of the concentration of inhalable particulate matter, and the concentration of the inhalable particulate matter is measured by the proportion of low levels in the PWM signal. It should be noted that the PM sensor of the GP2Y1023AUOF type is used to obtain the concentration of the inhalable particulate matter. 2.5 2.5 The process of obtaining the concentration of the inhalable particulate matter by the PM sensor of the GP2Y1023AUOF type is a known technology, and will not be described here. 2.5 2.5 The process of obtaining the concentration of the inhalable particulate matter by the PM sensor of the GP2Y1023AUOF type is a known technology, and will not be described here.

[0056] The collected data is filled with missing values and normalized, a plurality of time points are taken as a time period, a plurality of time periods are taken as a monitoring period, and data of each environmental parameter at each time point in each time period in each monitoring period is obtained, wherein the environmental parameters include temperature, humidity, wind speed, ultraviolet intensity, and PM concentration. 2.5

[0057] In this embodiment, the length of the time period is 5 minutes, and the length of the monitoring period is 3 hours. As other embodiments, the implementer can set it according to the actual situation. Secondly, the bilinear interpolation method is used for filling the missing values, and the Z-Score standardization is used for normalization processing. The bilinear interpolation method and the Z-Score standardization are both known technologies, and will not be described here. As other embodiments, the implementer can use other methods of existing technologies, for example, the cubic spline interpolation method is used for filling the missing values, and the maximum and minimum value normalization method is used for normalization processing. As other embodiments, the implementer can set it according to the actual situation.

[0058] Thus, the data of each environmental parameter at each time point in each time period in each monitoring period is obtained.

[0059] The environment prediction module is used for predicting the environmental parameters.

[0060] Further, the step flow chart of the environment prediction module provided by the present application is shown in Figure 2

[0061] ​​​​​Step 1, perform anomaly detection on the data of each environmental parameter at all time points in each time period to obtain abnormal time points, analyze the average difference between the data of different environmental parameters at abnormal time points and the data at other time points, and determine the environmental fluctuation degree of each time period in combination with the periodic change of the data of humidity and wind speed at abnormal time points.

[0062] Further, the mass of environmental parameters in the sports place are difficult to directly provide valuable information for users, and also increase the complexity of the sports environment intelligent prediction system; secondly, under normal circumstances, environmental parameters with high gradient dynamic change can reflect the instantaneous environmental evolution trend and local microclimate mutation characteristics of the sports place, and should have a higher weight in the prediction process, so as to more accurately predict and provide data support for the sports needs of users.

[0063] Secondly, the more obvious the instantaneous environmental evolution trend and local microclimate mutation of the sports place, the more obvious the gradient mutation of temperature and humidity, and the more sensitive humidity and wind speed are to air pressure change, so that the mutation is often accompanied by periodic disturbance, so that humidity and wind speed both show high autocorrelation. At the same time, the intensity of ultraviolet light and the concentration of PM 2.5 in the sports place will deviate from the normal distribution, and the mutation of the intensity of ultraviolet light and the concentration of PM 2.5 has a more significant long-term trend.

[0064] Based on the above analysis, the environmental anomaly degree is calculated based on the mutation of each environmental parameter in each time period, specifically:

[0065] Anomaly detection is performed on the data of each environmental parameter at all time points in each time period to obtain the abnormal time points corresponding to each environmental parameter in each time period;

[0066] In this embodiment, the BG (Bernaola Galvan) segmentation algorithm is used for anomaly detection, wherein the BG segmentation algorithm is a known technology and will not be described here. As other embodiments, the implementer can use other methods of prior art, for example, Bayesian mutation point detection algorithm, and this embodiment does not make special restrictions.

[0067] The mean value of the data of each environmental parameter at all time points except the abnormal time points in each time period is calculated, denoted as the first mean value;

[0068] The mean value of the data of each environmental parameter at all abnormal time points in each time period is calculated, denoted as the second mean value;

[0069] The ratio of the second mean value to the first mean value is taken as the relative change gradient of each environmental parameter in each time period;

[0070] Calculate the cumulative sum of the relative change gradient of all environmental parameters in each time period;

[0071] It should be noted that the greater the relative change gradient, the more dramatic the change in the sports venue for that environmental parameter in a short period of time, and the greater the cumulative sum, the more unstable the microclimate or local environment changes in this time period.

[0072] Using the autocorrelation function, based on the data of all abnormal times corresponding to humidity in each time period, the autocorrelation coefficients corresponding to a plurality of preset lag orders are obtained, and the mode of the autocorrelation coefficients corresponding to all preset lag orders is taken as the first correlation degree of each time period;

[0073] Based on the data of all abnormal times corresponding to wind speed in each time period, the autocorrelation coefficients corresponding to a plurality of preset lag orders are obtained, and the mode of the autocorrelation coefficients corresponding to all preset lag orders is taken as the second correlation degree of each time period;

[0074] In this embodiment, the autocorrelation function is a known technology, which will not be described here. In addition, the lag order takes an integer between 1 and 30, and as an alternative, the implementer can set it according to the actual situation.

[0075] Calculate the average of the first correlation degree and the second correlation degree, and take the product of the average and the cumulative sum as the environmental fluctuation degree of each time period;

[0076] It should be noted that the greater the first correlation degree and the second correlation degree, the more obvious the periodic disturbance change of humidity and wind speed in this time period, and the more likely it is to be affected by local microclimate mutation; secondly, the greater the environmental fluctuation degree, the more significant the dynamic change of the environmental parameter in this time period, and there may be periodic disturbance, reflecting the instability of the environmental change in the time period.

[0077] Step 2, by analyzing the distribution deviation and change trend of the data of ultraviolet intensity, PM 2.5 concentration at all times in each time period, calculating the long-term skewness of each time period, and combining the environmental fluctuation degree to obtain the evaluation coefficient of each time period.

[0078] Secondly, analyze the distribution deviation and change trend of the data of ultraviolet intensity, PM 2.5 concentration in each time period, calculate the long-term skewness, specifically:

[0079] Take the sum of the absolute value of the skewness of ultraviolet intensity and the absolute value of the skewness of PM 2.5 concentration at all times in each time period as the first sum value;

[0080] Hurst index of data of all abnormal time points corresponding to the UV intensity in each time period and PM 2.5 The sum of the Hurst indexes of data of all abnormal time points corresponding to the UV intensity and the PM

[0081] It should be noted that the calculation of skewness and the calculation of Hurst index are known technologies, which will not be described here.

[0082] The product of the first sum value and the second sum value is the long-term skewness of each time period.

[0083] It should be noted that the larger the first sum value, the more asymmetric the distribution of the UV intensity, the PM 2.5 The concentration has a high skewness distribution; the larger the second sum value, the stronger the long-term dependence of the mutation of the UV intensity, the PM 2.5 The concentration has a strong long-term dependence, and the persistence of the change trend is more significant; the higher the long-term skewness, the higher the health risk of the exercise environment in this time period.

[0084] Further, based on the environmental fluctuation degree and the long-term skewness, an evaluation coefficient is determined, specifically:

[0085] The normalized result of the product of the environmental fluctuation degree and the long-term skewness is the evaluation coefficient of each time period.

[0086] In this embodiment, sigmoid function is used for normalization processing, wherein the sigmoid function is a known technology, which will not be described here. As other embodiments, the implementer can use other methods of existing technologies, such as softmax function, tanh function, etc. This embodiment does not make special restrictions.

[0087] It should be noted that the larger the evaluation coefficient, the more intense the change of the environmental parameters in this time period, the higher the possibility of microclimate mutation, and the more unstable the exercise environment.

[0088] Thus, the evaluation coefficient of each time period is obtained.

[0089] Step 3, based on the interval length of each time period in each monitoring period and the evaluation coefficient, the effective weight of each time period is calculated, and based on the effective weight of the time period to which each time point belongs, the neural network model is used to predict each environmental parameter in the next monitoring period.

[0090] Further, when using the environmental parameters of each monitoring period for prediction, the data closer to the prediction target has higher reference value, therefore, based on the last time point in different time periods in each monitoring period and the evaluation coefficient, the effective weight of each time period is obtained, specifically:

[0091] obtaining a first time point in a next monitoring period as an initial prediction time point;

[0092] taking the reciprocal of the time interval between the last time point in each time period and the initial prediction time point as a time weight of each time period;

[0093] taking the product of the time weight and the evaluation coefficient as an effective weight of each time period;

[0094] collecting data of each environmental parameter at each time point in all time periods in a historical period, and calculating the effective weights of each time period in the historical period by using the above method to form a training set, and training the neural network model with attention mechanism;

[0095] In this embodiment, an Attention-LSTM (Long Short-term Memory Networks) model is used for training, wherein the Attention-LSTM refers to a combination of attention mechanism and LSTM model, and Adam is used as an optimization algorithm and MSE is used as a loss function in the LSTM model, wherein the Attention-LSTM model is a known technology and will not be described here, and as other embodiments, the implementer can use other methods of prior art, for example, Attention-CNN model, and this embodiment does not specially limit this.

[0096] Based on the data of each environmental parameter at all time points in each monitoring period, the effective weight of the time period to which each time point belongs is taken as the attention weight of the neural network model with attention mechanism, and the neural network model is used to predict each environmental parameter to obtain the predicted value of each environmental parameter at each time point in the next monitoring period;

[0097] It should be noted that the greater the time weight, the closer the time period to the prediction target, and the greater the influence on the prediction; the greater the evaluation coefficient, the more significant the environmental change in the time period, and the greater the influence on the prediction; the greater the effective weight, the closer the environmental parameter in the time period to the prediction target, and the more significant the environmental change, and the higher the influence on the prediction result; the attention mechanism dynamically allocates different attention weights to different parts of the input data, so that the model can more effectively capture key features and time steps, and improve the prediction accuracy.

[0098] The evaluation recommendation module is configured to evaluate the environment of the sports place and recommend a sports mode to the user.

[0099] Step 1, for the next monitoring period, analyze the offset and dispersion degree of the predicted values of temperature and humidity, and determine the first suitability of the next monitoring period.

[0100] Further, only through the prediction results of each environmental parameter cannot intuitively provide personalized suggestions for users to meet their rehabilitation training needs, cannot directly translate into user rehabilitation exercise training decision recommendations, and lack of correlation analysis of user exercise demand state and environmental parameter change characteristics. For example, for the way of rehabilitation training exercise, the user's rehabilitation exercise demand can be divided into anaerobic exercise and aerobic exercise. In aerobic exercise, the stability of temperature and humidity is crucial to the user's body temperature regulation. When the temperature and humidity are within the comfortable range of body feeling and change smoothly, it means that the environment is suitable for aerobic exercise, which is conducive to improving aerobic endurance. If the temperature and humidity change too much during exercise, it may cause the user to feel uncomfortable and affect the exercise effect. Secondly, the intensity of ultraviolet and the concentration of PM 2.5 will directly affect the user's health. For example, too high ultraviolet intensity may cause skin damage, and too high PM 2.5 concentration may cause respiratory diseases. Therefore, when the intensity of ultraviolet and the concentration of PM 2.5 are low, it means that the environment has low health risks and is suitable for aerobic exercise.

[0101] Firstly, by analyzing the change of the predicted values of temperature and humidity at each time in the next monitoring period, the first suitability is calculated, specifically:

[0102] The average of the predicted values of temperature at each time in the next monitoring period is denoted as the average predicted temperature;

[0103] The average of the predicted values of humidity at each time in the next monitoring period is denoted as the average predicted humidity;

[0104] The change rate between the average predicted temperature and the preset suitable temperature is calculated, denoted as the temperature change rate;

[0105] The change rate between the average predicted humidity and the preset suitable humidity is calculated, denoted as the humidity change rate;

[0106] In this embodiment, since the suitable temperature range for human movement is 17 ~24 , and the suitable humidity range is 30%~50%, the preset suitable temperature is 22 , and the preset suitable humidity is 40%. As other implementation manners, the implementer can set it according to the actual situation. Secondly, the calculation process of the temperature change rate is: wherein, represents the average predicted temperature, The preset suitable temperature is represented, and the humidity change rate is calculated by the same method The change rate is calculated by a known technique, which is not described herein.

[0107] The sum of the temperature change rate and the humidity change rate is taken as the temperature and humidity deviation degree;

[0108] The interquartile range of the predicted value of the temperature at all times in the next monitoring period is calculated, and the interquartile range is positively mapped;

[0109] The interquartile range of the predicted value of the humidity at all times in the next monitoring period is calculated, and the interquartile range is positively mapped;

[0110] The sum of the positively mapped results of the temperature and the humidity in the next monitoring period is taken as the temperature and humidity dispersion degree;

[0111] In this embodiment, the calculation of the interquartile range is a known technique, which is not described herein. In addition, the specific process of positive mapping is as follows: the interquartile range is denoted as IQR, and the result of is taken as the positively mapped result, where is a logarithmic function with a natural constant as the base number. Through the process of positive mapping, the dimensional problem between the temperature and the humidity is eliminated.

[0112] The product of the temperature and humidity deviation degree and the temperature and humidity dispersion degree is negatively mapped as the first suitability degree of the next monitoring period;

[0113] In this embodiment, the specific process of negative mapping is as follows: the reciprocal of the product of the temperature and humidity deviation degree and the temperature and humidity dispersion degree is taken as the negatively mapped result. As another implementation manner, the implementer can use an exponential function to perform negative mapping. It is assumed that the product of the temperature and humidity deviation degree and the temperature and humidity dispersion degree is denoted as , and the result of is taken as the negatively mapped result, where is an exponential function with a natural constant as the base number.

[0114] It should be noted that the greater the temperature and humidity deviation degree, the higher the degree of deviation of the predicted temperature and humidity in the next monitoring period from the human body comfortable temperature and humidity, and the more unsuitable it is to perform aerobic exercise. The greater the temperature and humidity dispersion degree, the more dispersed the distribution of the predicted temperature and humidity in the next monitoring period, the more unstable the change, and the more unsuitable it is to perform aerobic training. The smaller the first suitability degree, the more unsuitable the environmental conditions in the next monitoring period for performing aerobic training. Conversely, the greater the first suitability degree, the more suitable the environmental conditions in the next monitoring period for performing aerobic training.

[0115] Step 2, the wind speed and PM2.5 the difference between the concentration and the change trend of the corresponding predicted value, and PM 2.5 the average level of the concentration and the ultraviolet intensity corresponding to the predicted value, determine the second suitability of the next monitoring period, combine the first suitability to obtain the aerobic recommended coefficient of the next monitoring period, evaluate and recommend the exercise mode of the user in the exercise place.

[0116] Secondly, analyze the PM 2.5 the diffusion of the concentration under the change of the wind speed, and PM 2.5 the average level of the concentration and the ultraviolet intensity, calculate the second suitability, specifically:

[0117] curve fitting is performed on the predicted value of the wind speed at each time in the next monitoring period, the slope of the fitting curve corresponding to the wind speed at each time is calculated, and the predicted value corresponding to all time points with a slope greater than 0 is combined to form a wind speed growth sequence;

[0118] curve fitting is performed on the predicted value of the PM 2.5 concentration at each time in the next monitoring period, the slope of the fitting curve corresponding to the PM 2.5 concentration at each time is calculated, and the predicted value corresponding to all time points with a slope greater than 0 is combined to form a concentration growth sequence;

[0119] It should be noted that the least square method is used for curve fitting, wherein the least square method and the calculation of the slope are known technologies, and will not be described here.

[0120] the distance between the wind speed growth sequence and the concentration growth sequence is calculated;

[0121] In this embodiment, the distance is measured by calculating the DTW distance between the wind speed growth sequence and the concentration growth sequence, wherein the DTW distance is a known technology, and will not be described here. As other embodiments, the implementer can use other methods of prior art, for example, Euclidean distance, etc., and this embodiment does not make special restrictions.

[0122] the ratio of the mean value of the predicted value of the PM 2.5 concentration at each time in the next monitoring period to the preset first reference threshold is calculated, and is recorded as the concentration ratio;

[0123] the ratio of the mean value of the predicted value of the ultraviolet intensity at each time in the next monitoring period to the preset second reference threshold is calculated, and is recorded as the intensity ratio;

[0124] the sum of the concentration ratio and the intensity ratio is taken as the environmental risk degree;

[0125] In this embodiment, since the PM 2.5When the concentration does not exceed 35 micrograms per cubic meter, the air quality is excellent and the ultraviolet index does not exceed 3, making it safe to carry out outdoor activities. Therefore, the preset first reference threshold value is 35 and the preset second reference threshold value is 3. As other implementation methods, implementers can set them according to the actual situation.

[0126] The ratio of the distance to the environmental risk level is used as the second suitability for the next monitoring cycle;

[0127] It should be noted that the greater the distance, the closer the predicted wind speed is to the PM2.5 concentration in the next monitoring period. 2.5 The predicted concentration trends vary considerably, reflecting the diverse trends in PM2.5 concentrations. 2.5 The less the diffusion intensity is affected by wind speed, the more suitable the environmental conditions are for aerobic exercise; the lower the environmental risk level, the better the PM2.5 concentration. 2.5 Lower average concentrations and UV intensities indicate lower potential health risks to users and are more suitable for aerobic exercise; a higher second suitability indicates more suitable environmental conditions for aerobic exercise.

[0128] Furthermore, based on the first fitness level and the second fitness level, an aerobic recommendation coefficient is determined, specifically as follows:

[0129] The normalized result of the product of the first fitness level and the second fitness level is used as the aerobic recommendation coefficient for the next monitoring cycle.

[0130] In this embodiment, the sigmoid function is used for normalization. The sigmoid function is a well-known technique and will not be described in detail here. As other implementation methods, implementers may use other methods of the prior art, such as the softmax function, tanh function, etc. This embodiment does not impose any special restrictions on this.

[0131] It should be noted that the higher the aerobic recommendation coefficient, the more recommended aerobic rehabilitation training should be for the user. The flowchart of the method for obtaining the aerobic recommendation coefficient provided in this application is as follows: Figure 3 As shown.

[0132] Furthermore, based on the aforementioned aerobic recommendation coefficient, the user's exercise methods are evaluated and recommended, specifically as follows:

[0133] If the aerobic recommendation coefficient is greater than or equal to the preset threshold, the user is recommended to do aerobic exercise in this sports venue; otherwise, the user is recommended to do short-term anaerobic exercise in this sports venue.

[0134] In this embodiment, the preset threshold value is 0.6. As for other implementation methods, the implementer can set it according to the actual situation.

[0135] It should be noted that the greater the aerobic recommended coefficient, the more suitable the temperature and humidity of the exercise place in the next monitoring period is stable, and the health risk of long-term aerobic exercise of the ultraviolet intensity and the concentration of inhalable particulate matter is lower; on the contrary, the temperature and humidity environment of the exercise place in the next monitoring period is not suitable for aerobic exercise, and the user may have higher pressure on the user's body temperature regulation mechanism by using aerobic exercise for training, and the health risk of long-term aerobic exercise of the ultraviolet intensity and the concentration of inhalable particulate matter of the exercise place is higher.

[0136] Therefore, the Internet of Things realizes real-time collection, transmission and processing of data by connecting sensors, devices and networks, the data collection module transmits the collected data to the Internet of Things platform for storage through TCP / IP protocol, the environment prediction module predicts by calling data, and the evaluation recommendation module evaluates and recommends by the prediction result, so as to upload the recommended result of the exercise mode to the Internet of Things platform, and the user accesses the Internet of Things platform through a communication device to obtain the recommended result.

[0137] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0138] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, therefore, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present application, which does not deviate from the technical scheme of the present application, belongs to the protection scope of the present application.

Claims

1. A motion environment intelligent prediction system based on the Internet of Things, characterized in that, The system includes: The data acquisition module is used to collect data on each environmental parameter at different times within each monitoring period of the sports venue. These environmental parameters include temperature, humidity, wind speed, ultraviolet intensity, and PM2.

5. 2.5 concentration; The environmental prediction module is used to predict environmental parameters, including: Anomaly detection was performed on the data of each environmental parameter at all times within each time period to obtain the abnormal times. The average difference between the data of different environmental parameters at the abnormal times and other times was analyzed. Combined with the periodic changes of humidity and wind speed at the abnormal times, the environmental fluctuation of each time period was determined. Through ultraviolet intensity, PM 2.5 The distribution shift and trend of concentration data at all times within each time period are analyzed. The long-term bias of each time period is calculated, and the evaluation coefficient of each time period is obtained by combining the environmental fluctuation. Based on the interval between each time period in each monitoring cycle and the next monitoring cycle, and the evaluation coefficient, the effective weight of each time period is calculated. Based on the effective weight of the time period to which each moment belongs, a neural network model is used to predict each environmental parameter in the next monitoring cycle. The assessment and recommendation module is used to evaluate the environment of sports venues and recommend exercise methods to users, including: For the next monitoring cycle, analyze the deviation and dispersion of the predicted values ​​for temperature and humidity, and determine the first suitability for the next monitoring cycle; By wind speed and PM 2.5 The differences in the trends of predicted values ​​between concentrations, and PM2.5 concentrations. 2.5 The average level of the predicted values ​​for concentration and ultraviolet intensity is used to determine the second fitness level for the next monitoring period. Combined with the first fitness level, the aerobic recommendation coefficient for the next monitoring period is obtained, and the exercise methods of users in sports venues are evaluated and recommended.

2. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, Determining the environmental fluctuations for each time period includes: Calculate the ratio between the mean of the data at all abnormal times in each time period and the mean of the data at all other times except for abnormal times for each environmental parameter. Use this ratio as the relative change gradient of each environmental parameter in each time period. Calculate the sum of the relative change gradients of all environmental parameters in each time period. Using the autocorrelation function, based on the data of all abnormal moments corresponding to humidity and wind speed in each time period, the autocorrelation coefficients corresponding to multiple preset lag orders are obtained respectively. The mode of the autocorrelation coefficients corresponding to all preset lag orders is used as the first correlation and the second correlation for each time period. The average value of the first correlation and the second correlation is calculated. The environmental volatility is the product of the average value and the summation.

3. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The calculation of long-term biases for each time period includes: The absolute value of the skewness of the ultraviolet intensity at all times within each time period is compared with the PM... 2.5 The sum of the absolute values ​​of the skewness of the concentration is denoted as the first sum. Calculate the Hurst index and PM2.5 for all anomalous times corresponding to ultraviolet intensity within each time period. 2.5 The sum of the Hurst exponents of the data at all anomalous times corresponding to the concentration is denoted as the second sum. The long-term bias is the product of the first sum and the second sum.

4. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The evaluation coefficient is the normalized result of the product of the environmental volatility and the long-term bias.

5. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The calculation of the effective weights for each time period includes: Obtain the first moment of the next monitoring cycle within each monitoring cycle and record it as the initial prediction moment; use the reciprocal of the time interval between the last moment of each time period within each monitoring cycle and the initial prediction moment as the time weight of each time period. The effective weight is the product of the time weight and the evaluation coefficient.

6. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The prediction of each environmental parameter in the next monitoring period includes: based on the data of each environmental parameter at all times in each monitoring period, using the effective weight of the time period to which each time belongs as the attention weight of the neural network model with the attention mechanism, using the neural network model to predict each environmental parameter, and obtaining the predicted value of each environmental parameter at each time in the next monitoring period.

7. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The determination of the first suitability for the next monitoring cycle includes: The rate of change between the average predicted temperature at each moment in the next monitoring period and the preset suitable temperature is recorded as the temperature change rate; the rate of change between the average predicted humidity at each moment in the next monitoring period and the preset suitable humidity is recorded as the humidity change rate; the sum of the temperature change rate and the humidity change rate is used as the temperature-humidity deviation. Calculate the interquartile range of the predicted values ​​of temperature and humidity at all times in the next monitoring period, and perform positive mapping on the interquartile ranges respectively; the sum of the positive mapping results of temperature and humidity in the next monitoring period is taken as the temperature and humidity dispersion. The first suitability is the result of negative mapping of the product of the temperature and humidity deviation and the temperature and humidity dispersion.

8. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The determination of the second suitability for the next monitoring cycle includes: Wind speed and PM2.5 in the next monitoring period 2.5 The predicted concentration values ​​at each time point were curve-fitted, and the fitted curves corresponding to wind speed and PM2.5 were plotted separately. 2.5 The predicted values ​​corresponding to the moments when the slope of the fitted curve corresponding to the concentration is greater than 0 are used to form the wind speed growth sequence and the concentration growth sequence; the distance between the wind speed growth sequence and the concentration growth sequence is calculated. Calculate PM2.5 for the next monitoring period 2.5 The ratio of the average predicted concentration at each time point to a preset first reference threshold is denoted as the concentration ratio. The ratio of the average predicted value of ultraviolet intensity at each moment in the next monitoring cycle to a preset second reference threshold is calculated and denoted as the intensity ratio; the sum of the concentration ratio and the intensity ratio is taken as the environmental risk level. The second suitability is the ratio of the distance to the environmental risk level.

9. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The aerobic recommendation coefficient is the normalized result of the product of the first fitness level and the second fitness level.

10. The IoT-based intelligent motion environment prediction system as described in claim 1, characterized in that, The evaluation and recommendation of users' exercise methods in sports venues includes: if the aerobic recommendation coefficient is greater than or equal to a preset threshold, recommending users to perform aerobic exercise in the sports venue; otherwise, recommending users to perform short-term anaerobic exercise in the sports venue.

Images