Sleep thermal environment control method and system based on wrist skin temperature

Through the sleep thermal environment control method based on wrist skin temperature, the threshold range is determined using slip windows and mixed models, and combined with machine learning algorithms, personalized sleep environment temperature regulation for the elderly is achieved, solving the sleep environment control in the existing technology Inadequate, improving sleep quality and environmental comfort.

CN118981228APending Publication Date: 2024-11-19SHANGHAI JIAOTONG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411057352.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing technology has the risk of multi-point skin temperature testing interfering with sleep environment control, lacks a clear range of skin temperature control, insufficient theoretical basis, and cannot accurately reflect the sleep state of the human body, especially for the elderly, the lack of personalized sleep environment temperature regulation. Effective model.

Method used

The sleep thermal environment control method based on wrist skin temperature is adopted, and the threshold range of individual sleep quality is determined through data collection judgment and slip window and mixed model regression method. The wrist skin temperature prediction model is constructed in combination with machine learning algorithms to monitor and regulate sleep in real time. Ambient temperature, taking into account seasonal and individual habit preferences.

Benefits of technology

It realizes accurate control of the sleep quality of the elderly, improves the comfort and effect of the sleep environment, ensures that the elderly can obtain a comfortable sleep environment in different seasons, provides personalized sleep environment adjustment, and enhances the accuracy and adaptation of temperature adjustment. sex.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981228A_ABST
    Figure CN118981228A_ABST
Patent Text Reader

Abstract

The invention provides a sleep thermal environment control method and system based on wrist skin temperature, and the method comprises the steps: data collection and judgment: judging whether target sleep parameters can be obtained or not, if not, executing a first sleep adjustment step, and if yes, executing a second sleep adjustment step; a first sleep adjustment step: determining a wrist skin temperature threshold range beneficial to the sleep quality of the individual from a pre-stored sleep quality parameter data set, and adjusting the temperature value of the sleep environment to control the skin temperature within the threshold range; and a second sleep adjustment step: acquiring target sleep parameters, determining a wrist skin temperature threshold range beneficial to the individual sleep quality, and adjusting the temperature value of the sleep environment to control the skin temperature within the threshold range. It can be ensured that the old can obtain a comfortable sleep environment in summer and winter through the corresponding season model, and the sleep quality is improved; and the sleep environment can be controlled according to the sleep requirements of different groups / individuals, so that personalized control is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of creating a sleeping environment, and in particular to a method and system for controlling a sleeping thermal environment based on wrist skin temperature. Background Art

[0002] Sleep is an important physiological process of the human body. The quality of human sleep is significantly affected by temperature. High or low temperatures are not conducive to human sleep quality. In particular, the sleep of the elderly is more susceptible to adverse environmental disturbances. Studies have found that the sleep of the elderly is extremely susceptible to heat exposure, and a small heat load will reduce the sleep quality of the elderly. Therefore, considering the fragility of sleep in the elderly, in order to ensure the sleep quality of the elderly, it is necessary to provide a good thermal environment for sleep. Some standards give the indoor temperature of residential buildings. For example, the World Health Organization recommends that the indoor temperature in cold seasons be 18°C, and my country's "Indoor Air Quality Standard" (GB18883-2022) recommends that the indoor temperature in summer be 22-28°C and the indoor temperature in winter be 16-24°C. However, the formulation of these standards does not take into account the needs of the human body during sleep, which leads to the fact that the temperature recommendations of these standard specifications may not necessarily guarantee the sleep quality of the human body. Therefore, it is necessary to establish a set of control methods for the sleep thermal environment for the human body to ensure that the sleep thermal environment does not affect the sleep quality of the human body, especially for the elderly.

[0003] In a Chinese patent document with publication number CN114259210A, a sleep staging method and control system based on dynamic skin temperature are disclosed, including: a skin temperature monitoring step: monitoring the skin temperature of different parts of the human body; a sleep monitoring step: real-time monitoring of the sleep process being measured; a machine learning step: including a training model and a test model, the training model receives the training set data transmitted by the skin temperature monitoring step and the sleep monitoring step, and continuously adjusts the initial skin temperature threshold; the training model outputs the trained skin temperature threshold and constitutes a test model, and the skin temperature monitoring step and the sleep monitoring step input the test set data into the test model for verification; a sleep staging step: staging the sleep process and determining the current sleep period of the measured person; an environmental monitoring and control step: determining the accurate sleep staging result output by the sleep staging step, and regulating the bedroom environment.

[0004] However, these methods have certain shortcomings in practical applications:

[0005] 1. Testing the skin temperature at multiple points during sleep will disturb sleep and have the risk of falling off, so the number of measurement points should be reduced. Wrist skin temperature can reflect the thermal state of the human body during sleep and can reduce the interference of multiple measurement points on sleep.

[0006] 2. The control range of skin temperature is not clear and the theoretical basis is insufficient. Although some studies have proposed that the thermal environment can be controlled based on skin temperature, they have not given a skin temperature threshold range that is conducive to human sleep.

[0007] 3. The theoretical basis for controlling the sleeping environment temperature is also insufficient. There is no relevant theoretical model for how to accurately control the sleeping environment temperature for different groups of people, especially for the elderly. There is a lack of effective control models to achieve precise control of the sleeping thermal environment and personalized sleeping thermal environment regulation.

[0008] 4. Existing sleep environment control technologies often fail to accurately reflect the actual sleep state of the human body. Considering that in real life, not only temperature, but also relative humidity and residents' living habits, such as the use of fans in summer and electric blankets in winter, will affect the thermal state of the human body during sleep, the current temperature control technology does not take these factors into account, which also leads to the inability to meet personalized sleep needs. Therefore, it is necessary to develop a more accurate and personalized sleep thermal environment control method to improve the sleep quality of the human body. Proposing a sleep thermal environment control method based on wrist skin temperature has become an urgent problem to be solved. Summary of the invention

[0009] In view of the defects in the prior art, an object of the present invention is to provide a method and system for controlling the thermal environment during sleep based on wrist skin temperature.

[0010] A method for controlling a sleeping thermal environment based on wrist skin temperature provided by the present invention includes:

[0011] Data collection judgment step: judging whether the target sleep parameters can be obtained, if not, executing the first sleep adjustment step, if yes, executing the second sleep adjustment step;

[0012] The first sleep adjustment step: determining a wrist skin temperature threshold range that is beneficial to the individual's sleep quality from a pre-stored sleep quality parameter data set, and adjusting the temperature value of the sleep environment so that the skin temperature is controlled within the threshold range;

[0013] The second sleep adjustment step: obtaining the target sleep parameters, using a sliding window and a regression method based on a hybrid model to determine a wrist skin temperature threshold range that is beneficial to the individual's sleep quality, and adjusting the temperature value of the sleeping environment to control the skin temperature within the threshold range.

[0014] Preferably, the first sleep adjustment step includes:

[0015] The determined wrist skin temperature threshold range that is beneficial to the individual's sleep quality is input into the control terminal as a control target;

[0016] According to different seasons, a corresponding control model is established; the control model includes:

[0017] Summer control model, ΔT a =(ΔT sk / 0.067)℃;

[0018] Winter control model, ΔT a =(T sk / 0.031)℃;

[0019] Among them, T a is the sleeping environment temperature, T sk is the wrist skin temperature, ΔT sk Indicates that the real-time monitored skin temperature is greater than the maximum value of the threshold range or less than the minimum value of the threshold range, ΔT a Indicates that the skin temperature ΔT needs to be changed sk When the sleep environment temperature is adjusted, the sleep environment temperature is taken as the execution target;

[0020] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0021] Preferably, the second sleep adjustment step comprises:

[0022] A wrist skin temperature prediction model is constructed using a machine learning algorithm, loss functions under different algorithm models are compared to evaluate the prediction performance of the wrist skin temperature prediction model, and the wrist skin temperature prediction model with the best performance is selected;

[0023] Use the selected wrist skin temperature prediction model to output the temperature SHAP value and establish the relationship between the temperature SHAP value and temperature:

[0024] ΔT a =(ΔT sk / B)℃;

[0025] Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature;

[0026] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0027] Preferably, the sliding window includes determining a wrist skin temperature threshold range T1-T2 that is beneficial to the individual's sleep quality, iterating from the minimum and maximum points of the wrist skin temperature toward the center with a certain step length, establishing an association between sleep quality and wrist skin temperature in each interval [minimum value, T1] and [T2, maximum value], and using the association result as a basis for whether to stop iteration.

[0028] Preferably, the second sleep adjustment step can be individually controlled by acquiring an individual's habit preference data set; the individual's habit preference data set includes historical / existing sleep environment data, sleep quality data, wrist skin temperature data, and daily habit preference data for adjusting the thermal environment.

[0029] A sleep thermal environment control system based on wrist skin temperature provided by the present invention comprises:

[0030] Data collection judgment module: judge whether the target sleep parameters can be obtained, if not, execute the first sleep adjustment module, if yes, execute the second sleep adjustment module;

[0031] The first sleep adjustment module: determines a wrist skin temperature threshold range that is beneficial to the individual's sleep quality from a pre-stored sleep quality parameter data set, and adjusts the temperature value of the sleep environment so that the skin temperature is controlled within the threshold range;

[0032] The second sleep adjustment module: obtains the target sleep parameters, uses a sliding window and a regression method based on a hybrid model to determine the wrist skin temperature threshold range that is beneficial to the individual's sleep quality, and adjusts the temperature value of the sleeping environment to keep the skin temperature within the threshold range.

[0033] Preferably, the first sleep adjustment module includes:

[0034] The determined wrist skin temperature threshold range that is beneficial to the individual's sleep quality is input into the control terminal as a control target;

[0035] According to different seasons, a corresponding control model is established; the control model includes:

[0036] Summer control model, ΔT a =(ΔT sk / 0.067)℃;

[0037] Winter control model, ΔT a =(T sk / 0.031)℃;

[0038] Among them, T a is the sleeping environment temperature, T sk is the wrist skin temperature, ΔT sk Indicates that the real-time monitored skin temperature is greater than the maximum value of the threshold range or less than the minimum value of the threshold range, ΔT a Indicates that the skin temperature ΔT needs to be changed sk When the sleep environment temperature is adjusted, the sleep environment temperature is taken as the execution target;

[0039] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0040] Preferably, the second sleep adjustment module includes:

[0041] A wrist skin temperature prediction model is constructed using a machine learning algorithm, loss functions under different algorithm models are compared to evaluate the prediction performance of the wrist skin temperature prediction model, and the wrist skin temperature prediction model with the best performance is selected;

[0042] Use the selected wrist skin temperature prediction model to output the temperature SHAP value and establish the relationship between the temperature SHAP value and temperature:

[0043] ΔT a =(ΔT sk / B)℃;

[0044] Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature;

[0045] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0046] Preferably, the sliding window includes determining a wrist skin temperature threshold range T1-T2 that is beneficial to the individual's sleep quality, iterating from the minimum and maximum points of the wrist skin temperature toward the center with a certain step length, establishing an association between sleep quality and wrist skin temperature in each interval [minimum value, T1] and [T2, maximum value], and using the association result as a basis for whether to stop iteration.

[0047] Preferably, the second sleep adjustment module can perform personalized control by acquiring an individual's habit preference data set; the individual's habit preference data set includes historical / existing sleep environment data, sleep quality data, wrist skin temperature data and daily habit preference data for adjusting the thermal environment.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. Based on the analysis of a large number of sleep data sets, the present invention accurately determines the wrist skin temperature threshold range that is beneficial to the sleep quality of the elderly. Temperatures below or above the threshold range are not conducive to the sleep quality of the elderly. Compared with traditional environmental parameter adjustment methods, this method is more accurate and can provide more effective sleep environment control for the elderly: an accurate sleep environment temperature control model is established according to different seasons to ensure that the elderly can obtain a comfortable sleeping environment in both summer and winter and improve their sleep quality.

[0050] 2. The present invention has the corresponding functions of target monitoring, feedback and adjustment. By real-time monitoring of wrist skin temperature and feedback adjustment of the sleeping environment temperature, it ensures that the elderly are always within a suitable temperature range during sleep and guarantees their sleep quality.

[0051] 3. The method provided by the present invention is not only suitable for the elderly group, but also can realize personalized sleep environment control according to the individual's historical data and preferences. Through this personalized method, each user can be provided with a sleep environment that best meets their needs: the wrist skin temperature threshold range suitable for the individual's sleep quality is accurately determined according to the individual's data set, and the skin temperature is predicted according to the individual's actual life data set, accurately predicting and responding to changes in the sleep environment, reflecting the actual life status, making the wrist skin temperature prediction model more adaptable and accurate.

[0052] 4. The present invention establishes a sleeping environment temperature control model through the SHAP value method, which can comprehensively consider the influence of other factors and characteristics on wrist skin temperature, and then accurately adjust the temperature regulation and optimize the temperature regulation strategy; according to the real-time monitoring and feedback adjustment system of individual wrist skin temperature, it can ensure that the individual is always within the wrist skin temperature range suitable for his sleep quality during sleep. This personalized real-time adjustment method significantly improves the comfort and effect of the sleeping environment.

[0053] Other beneficial effects of the present invention will be explained in the specific implementation manner through the introduction of specific technical features and technical solutions. Through the introduction of these technical features and technical solutions, those skilled in the art should be able to understand the beneficial technical effects brought about by the technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0055] Figure 1 This is a flow chart of controlling the sleeping environment temperature based on wrist skin temperature of the present invention.

[0056] Figure 2 This is a flow chart of the method for determining a wrist skin temperature threshold range that is beneficial to human sleep quality in the present invention. DETAILED DESCRIPTION

[0057] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0058] Example 1

[0059] The present invention determines whether the target parameters can be obtained by collecting data sets such as the target's sleep parameters, skin temperature parameters, indoor environmental parameters, etc. within a period of time, and determines the skin temperature control range and room temperature control model required for this individual during sleep.

[0060] In the early stage, when determining the wrist skin temperature threshold range that is conducive to sleep, it is necessary to obtain sleep parameters and corresponding skin temperature parameters, but in the later stage of the sleep environment temperature control period, it is necessary to control according to the wrist skin temperature, so it is necessary to monitor the wrist skin temperature in real time; and during the control period, it is no longer necessary to monitor the sleep data. This embodiment will be described by taking the elderly as an example.

[0061] Reference Figure 1 and Figure 2 As shown, a method for controlling the thermal environment during sleep based on wrist skin temperature comprises the following steps:

[0062] Step 1: Obtain the sleep quality and other parameter data sets of the elderly. Figure 2 The wrist skin temperature threshold range that is beneficial to the sleep quality of the elderly is determined to be 34.0-34.9°C, which is input into the control terminal as the control target;

[0063] Step 2: For different seasons, the precise control model of sleeping environment temperature based on wrist skin temperature is established as follows:

[0064] Summer: ΔT a =(ΔT sk / 0.067)℃;

[0065] Winter: ΔT a =(T sk / 0.031)℃;

[0066] Among them, T a is the sleeping environment temperature, T sk is the wrist skin temperature, ΔT sk Indicates the difference between the real-time monitored skin temperature greater than 34.9℃ or less than 34.0℃, ΔT a Indicates that the skin temperature ΔT needs to be changed sk The degree of adjustment of the sleeping environment temperature; the sleeping environment temperature is taken as the execution target. (This embodiment selects summer and winter, two relatively typical seasons, for illustration, at which time, there is often a need to control the temperature.)

[0067] Step 3: Monitor the wrist skin temperature of the elderly during sleep in real time as a feedback signal, and adjust the temperature of the sleeping environment to ensure that the wrist skin temperature is within the temperature range of step 1.

[0068] Step 4: For different groups / individuals, including the elderly, if the individual's historical / current sleep environment, sleep quality, wrist skin temperature, daily habitual preferences for adjusting the thermal environment and other data sets can be obtained, personalized control can be achieved and these data sets for the individual can be obtained. The data set acquisition includes but is not limited to information such as the individual's historical / current sleep environment, sleep quality, wrist skin temperature, daily habitual preferences for adjusting the thermal environment, and other information, and may also include other factors that may affect sleep or wrist skin temperature, such as gender, age, BMI, number of people in the bedroom, etc.

[0069] Step 5: Reference Figure 2 As shown, a sliding window and a regression method based on a hybrid model are used to determine the wrist skin temperature threshold range (T1, T2) that is beneficial to individual sleep quality; the step size can be determined based on the actual data volume and measurement accuracy.

[0070] Step 6: Use machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting machine, support vector machine, and neural network to build a wrist skin temperature prediction model. The features included include but are not limited to the temperature of the sleeping environment, relative humidity, thermal environment adjustment behavior, season, etc. The prediction performance of the model is evaluated by comparing the loss function under different algorithm models, that is, the mean square error (MSE). The smaller the value, the better the prediction performance. Finally, the optimal skin temperature prediction model is determined.

[0071] When a machine learning algorithm is used to construct a wrist skin temperature prediction model, the included features include, but are not limited to, the temperature of the sleeping environment, relative humidity, thermal environment regulation behavior, season, etc., and may also include information features collected in step 4 such as gender, age, BMI, number of people in the bedroom, etc. that may affect the skin temperature.

[0072] Step 7: Based on the optimal wrist skin temperature prediction model determined by machine learning, output the marginal contribution of temperature, i.e., SHAP value (SHapley Additive exPlanations), and establish the relationship between temperature SHAP value and temperature:

[0073] ΔT a =(ΔT sk / B)℃.

[0074] Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature;

[0075] Step 8: Monitor the wrist skin temperature of the individual during sleep in real time (for example, a miniature wearable sensor can be directly used for real-time monitoring) as a feedback signal, and adjust the temperature of the sleeping environment to ensure that the wrist skin temperature of the individual is within the temperature range in step 5.

[0076] Based on the analysis of a large number of sleep data sets, the present invention accurately determines the wrist skin temperature threshold range that is beneficial to the sleep quality of the elderly. Temperatures below or above the threshold range are not conducive to the sleep quality of the elderly. Compared with traditional environmental parameter adjustment methods, this method is more accurate and can provide more effective sleep environment control for the elderly: an accurate sleep environment temperature control model is established according to different seasons to ensure that the elderly can obtain a comfortable sleeping environment in both summer and winter and improve their sleep quality.

[0077] Example 2

[0078] This embodiment still targets the elderly. First, this method obtains a large amount of information data sets in the actual life of the elderly, including sleep quality, wrist skin temperature, sleeping environment temperature, relative humidity, thermal environment adjustment behavior, etc. Figure 2 The method for determining the wrist skin temperature threshold range that is beneficial to human sleep quality determines that the wrist skin temperature threshold range that is beneficial to the sleep quality of the elderly is (34.0~34.9℃).

[0079] This method uses a sliding window and a regression analysis method based on a mixed model. It iterates from the minimum and maximum points of wrist skin temperature to the center with a step size of 0.2°C. In each interval [minimum value, T1] and [T2, maximum value], it establishes the association between sleep quality and wrist skin temperature. Whether there is a significant result (P≤0.05) is used as the basis for continuing / stopping the iteration. This method can determine the wrist skin temperature threshold range that is beneficial to their sleep quality for different groups or individuals.

[0080] Reference Figure 1 As shown, further, for the elderly who cannot obtain individual daily data information, a systematic control method can be adopted, that is, the wrist skin temperature of the elderly during sleep is controlled within the threshold range (34.0-34.9°C) recommended by the present invention. To ensure that the wrist skin temperature of the elderly is controlled within this range, the degree of control of the sleeping environment temperature is different in different seasons, and the skin temperature exceeds the threshold range ΔT sk , increase / lower the sleeping environment temperature ΔT in summer sk / 0.067, increase / decrease sleeping environment temperature ΔT in winter sk / 0.031.

[0081] Due to individual differences, their sensitivity to the thermal environment and the degree to which it is affected during sleep vary. Therefore, a method for controlling the thermal environment during sleep can be established for each individual to meet individual needs.

[0082] First, obtain the individual's historical sleep environment, sleep quality, wrist skin temperature, adjustment behavior and other information data sets, or obtain the data information of the last n days through monitoring, and use Figure 2The wrist skin temperature threshold range (T1, T2) that is beneficial to individual sleep quality is determined by the method. After determining the wrist skin temperature threshold range, it is necessary to establish an accurate control model for the sleep thermal environment. The wrist skin temperature prediction model is constructed using multiple machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting machine, support vector machine, and neural network. The input features include but are not limited to the temperature, relative humidity, thermal environment adjustment behavior, bedding thermal resistance, season and other characteristics of the sleeping environment. The prediction performance of the model is evaluated according to the loss function, that is, the mean square error; by comparing the loss functions under different algorithm models, the smaller the value, the better the prediction performance, and finally the optimal skin temperature prediction model is determined. Based on the optimal wrist skin temperature prediction model determined by machine learning, the marginal contribution of temperature, that is, the temperature SHAP value, is output, and the relationship between the temperature SHAP value and temperature is constructed.

[0083] This relationship comprehensively considers the impact of other included features such as relative humidity, thermal environment regulation behavior, bedding thermal resistance, season, etc. on skin temperature, that is, the model is applicable to all cases of other features. Finally, the wrist skin temperature is controlled within the range of (T1, T2) by adjusting the sleeping environment temperature.

[0084] The method provided by the present invention is not only suitable for the elderly group, but also can realize personalized sleep environment control according to the individual's historical data and preferences. Through this personalized method, each user can be provided with a sleep environment that best meets their needs: the wrist skin temperature threshold range suitable for the individual's sleep quality is accurately determined according to the individual's data set, and the skin temperature is predicted according to the individual's data set in real life, and the changes in the sleep environment are accurately predicted and responded to, reflecting the actual life status, so that the wrist skin temperature prediction model is more adaptable and accurate; the sleep environment temperature control model is established by the SHAP value method, which can comprehensively consider the influence of other factors and characteristics on the wrist skin temperature, and then accurately adjust the temperature regulation and optimize the temperature regulation strategy; according to the real-time monitoring and feedback regulation system of the individual's wrist skin temperature, it can ensure that the individual is always in the wrist skin temperature range suitable for his sleep quality during sleep, and this personalized real-time regulation method significantly improves the comfort and effect of the sleep environment.

[0085] The present invention also provides a sleep thermal environment control system based on wrist skin temperature. The sleep thermal environment control system based on wrist skin temperature can be realized by executing the process steps of the sleep thermal environment control method based on wrist skin temperature, that is, those skilled in the art can understand the sleep thermal environment control method based on wrist skin temperature as a preferred implementation of the sleep thermal environment control system based on wrist skin temperature.

[0086] Specifically, a sleep thermal environment control system based on wrist skin temperature includes:

[0087] Data collection judgment module: judge whether the target sleep parameters can be obtained, if not, execute the first sleep adjustment module, if yes, execute the second sleep adjustment module;

[0088] The first sleep adjustment module: determines a wrist skin temperature threshold range that is beneficial to the individual's sleep quality from a pre-stored sleep quality parameter data set, and adjusts the temperature value of the sleep environment so that the skin temperature is controlled within the threshold range;

[0089] The second sleep adjustment module: obtains the target sleep parameters, uses a sliding window and a regression method based on a hybrid model to determine the wrist skin temperature threshold range that is beneficial to the individual's sleep quality, and adjusts the temperature value of the sleeping environment to keep the skin temperature within the threshold range.

[0090] The first sleep adjustment module includes:

[0091] The determined wrist skin temperature threshold range that is beneficial to the individual's sleep quality is input into the control terminal as a control target;

[0092] According to different seasons, a corresponding control model is established; the control model includes:

[0093] Summer control model, ΔT a =(ΔT sk / 0.067)℃;

[0094] Winter control model, ΔT a =(T sk / 0.031)℃;

[0095] Among them, T a is the sleeping environment temperature, T sk is the wrist skin temperature, ΔT sk Indicates that the real-time monitored skin temperature is greater than the maximum value of the threshold range or less than the minimum value of the threshold range, ΔT a Indicates that the skin temperature ΔT needs to be changed sk When the sleep environment temperature is adjusted, the sleep environment temperature is taken as the execution target;

[0096] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0097] The second sleep adjustment module includes:

[0098] A wrist skin temperature prediction model is constructed using a machine learning algorithm, loss functions under different algorithm models are compared to evaluate the prediction performance of the wrist skin temperature prediction model, and the wrist skin temperature prediction model with the best performance is selected;

[0099] Use the selected wrist skin temperature prediction model to output the temperature SHAP value and establish the relationship between the temperature SHAP value and temperature:

[0100] ΔT a =(ΔT sk / B)℃;

[0101] Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature;

[0102] The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

[0103] The sliding window includes determining a wrist skin temperature threshold range T1-T2 that is beneficial to the individual's sleep quality, iterating from the minimum and maximum points of the wrist skin temperature toward the center with a certain step length, establishing an association between sleep quality and wrist skin temperature in each interval [minimum value, T1] and [T2, maximum value], and using the association result as a basis for whether to stop iteration.

[0104] The second sleep adjustment module can perform personalized control by acquiring an individual's habit preference data set; the individual's habit preference data set includes historical / current sleep environment data, sleep quality data, wrist skin temperature data, and daily habit preference data for adjusting the thermal environment.

[0105] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0106] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0107] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for controlling the thermal environment during sleep based on wrist skin temperature, characterized in that: include: Data collection judgment step: judging whether the target sleep parameters can be obtained, if not, executing the first sleep adjustment step, if yes, executing the second sleep adjustment step; The first sleep adjustment step: determining a wrist skin temperature threshold range that is beneficial to the individual's sleep quality from a pre-stored sleep quality parameter data set, and adjusting the temperature value of the sleep environment so that the skin temperature is controlled within the threshold range; The second sleep adjustment step: obtaining the target sleep parameters, using a sliding window and a regression method based on a hybrid model to determine a wrist skin temperature threshold range that is beneficial to the individual's sleep quality, and adjusting the temperature value of the sleeping environment to control the skin temperature within the threshold range.

2. The method for controlling the thermal environment during sleep based on wrist skin temperature according to claim 1, characterized in that: The first sleep adjustment step comprises: The determined wrist skin temperature threshold range that is beneficial to the individual's sleep quality is input into the control terminal as a control target; According to different seasons, a corresponding control model is established; the control model includes: Summer control model, ΔT a =(ΔT sk / 0.067)℃; Winter control model, AT a =(T sk / 0.031)℃; Among them, T a is the sleeping environment temperature, T ak is the wrist skin temperature, ΔT sk Indicates that the real-time monitored skin temperature is greater than the maximum value of the threshold range or less than the minimum value of the threshold range, ΔT a Indicates that the skin temperature ΔT needs to be changed sk When the sleep environment temperature is adjusted, the sleep environment temperature is taken as the execution target; The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

3. The method for controlling the thermal environment during sleep based on wrist skin temperature according to claim 2, characterized in that: The second sleep adjustment step comprises: A wrist skin temperature prediction model is constructed using a machine learning algorithm, loss functions under different algorithm models are compared to evaluate the prediction performance of the wrist skin temperature prediction model, and the wrist skin temperature prediction model with the best performance is selected; Use the selected wrist skin temperature prediction model to output the temperature SHAP value and establish the relationship between the temperature SHAP value and temperature: AT a =(ΔT sk / B)℃; Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature; The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

4. The method for controlling the thermal environment during sleep based on wrist skin temperature according to claim 1, characterized in that: The sliding window includes determining a wrist skin temperature threshold range T1-T2 that is beneficial to the individual's sleep quality, iterating from the minimum and maximum points of the wrist skin temperature toward the center with a certain step length, establishing an association between sleep quality and wrist skin temperature in each interval [minimum value, T1] and [T2, maximum value], and using the association result as a basis for whether to stop iteration.

5. The method for controlling the thermal environment during sleep based on wrist skin temperature according to claim 1, characterized in that: The second sleep adjustment step can be individually controlled by acquiring an individual's habit preference data set; the individual's habit preference data set includes historical / current sleep environment data, sleep quality data, wrist skin temperature data, and daily habit preference data for adjusting the thermal environment.

6. A sleep thermal environment control system based on wrist skin temperature, characterized in that: include: Data collection judgment module: judge whether the target sleep parameters can be obtained, if not, execute the first sleep adjustment module, if yes, execute the second sleep adjustment module; The first sleep adjustment module: determines a wrist skin temperature threshold range that is beneficial to the individual's sleep quality from a pre-stored sleep quality parameter data set, and adjusts the temperature value of the sleep environment so that the skin temperature is controlled within the threshold range; The second sleep adjustment module: obtains the target sleep parameters, uses a sliding window and a regression method based on a hybrid model to determine the wrist skin temperature threshold range that is beneficial to the individual's sleep quality, and adjusts the temperature value of the sleeping environment to keep the skin temperature within the threshold range.

7. The sleep thermal environment control system based on wrist skin temperature according to claim 6, characterized in that: The first sleep adjustment module includes: The determined wrist skin temperature threshold range that is beneficial to the individual's sleep quality is input into the control terminal as a control target; According to different seasons, a corresponding control model is established; the control model includes: Summer control model, ΔT a =(ΔT sk / 0.067)℃; Winter control model, ΔT a =(T sk / 0.031)℃; Among them, T a is the sleeping environment temperature, T sk is the wrist skin temperature, ΔT sk Indicates that the real-time monitored skin temperature is greater than the maximum value of the threshold range or less than the minimum value of the threshold range, ΔT a Indicates that the skin temperature ΔT needs to be changed sk When the sleep environment temperature is adjusted, the sleep environment temperature is taken as the execution target; The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

8. The sleep thermal environment control system based on wrist skin temperature according to claim 7, characterized in that: The second sleep adjustment module includes: A wrist skin temperature prediction model is constructed using a machine learning algorithm, loss functions under different algorithm models are compared to evaluate the prediction performance of the wrist skin temperature prediction model, and the wrist skin temperature prediction model with the best performance is selected; Use the selected wrist skin temperature prediction model to output the temperature SHAP value and establish the relationship between the temperature SHAP value and temperature: AT a =(ΔT sk / B)℃; Among them, B is the linear regression coefficient of the sleeping environment temperature SHAP value and temperature; The target's wrist skin temperature during sleep is monitored in real time and used as a feedback signal; the temperature of the sleeping environment is adjusted so that the target's wrist skin temperature is within the wrist skin temperature threshold range that is beneficial to the individual's sleep quality.

9. The sleep thermal environment control system based on wrist skin temperature according to claim 6, characterized in that: The sliding window includes determining a wrist skin temperature threshold range T1-T2 that is beneficial to the individual's sleep quality, iterating from the minimum and maximum points of the wrist skin temperature toward the center with a certain step length, establishing an association between sleep quality and wrist skin temperature in each interval [minimum value, T1] and [T2, maximum value], and using the association result as a basis for whether to stop iteration.

10. The sleep thermal environment control system based on wrist skin temperature according to claim 6, characterized in that: The second sleep adjustment module can perform personalized control by acquiring an individual's habit preference data set; the individual's habit preference data set includes historical / current sleep environment data, sleep quality data, wrist skin temperature data, and daily habit preference data for adjusting the thermal environment.