Sleep quality monitoring and evaluation method combined with user data analysis

Abstract

The application relates to a sleep quality monitoring and evaluation method combined with user data analysis, and belongs to the technical field of sleep monitoring.The application constructs user individual physiological response parameters, dynamically updates real-time data of the user, constructs a multi-scale sleep environment model of the user based on a digital twin technology, and carries out simulation in a virtual space, so that the sleep quality of the user is dynamically evaluated in combination with real-time data of the user and simulation data in the virtual space, sleep quality comfort degree score data of the user is obtained, the sleep quality evaluation result of the user is determined according to the sleep quality comfort degree score data of the user, and the sleep environment is dynamically controlled based on the sleep quality evaluation result of the user.The application fully considers the coupling conditions between environmental parameters and the individual physiological response parameters of the user, so that the environmental parameters can be further optimized, and the sleep environment control is more accurate.

Description

Technical Field

[0001] This invention relates to the field of sleep monitoring technology, and in particular to a method for monitoring and evaluating sleep quality by combining user data analysis. Background Technology

[0002] Sleep is an active process, a necessary rest for restoring energy, beneficial for mental and physical recovery, fundamental to maintaining health and physical strength, and a guarantee for achieving high productivity. Modern medicine generally believes that sleep is a necessary life process for the brain to reorganize information (redistribute and solidify stimuli and their connections to corresponding nerve cells), temporarily shifting the focus of excitation (attention) to nerve cells with lower excitation intensity. These nerve cells then take over most of the body's vital activities, while the more excitable nerve cells that previously processed and responded to internal and external stimuli need to largely shield themselves from their effects. During sleep, a person's active activities decrease, and physical strength is restored accordingly. Compared to the waking state, during sleep, contact with the surroundings ceases, conscious awareness disappears, muscles relax, nerve reflexes weaken, body temperature decreases, heart rate slows, blood pressure slightly decreases, metabolism slows, and gastrointestinal motility is significantly reduced. However, the sleep environment is a crucial factor affecting sleep quality. Current technology often adjusts the sleep environment by controlling environmental control devices, but it does not consider the coupling between parameters, leading to imprecise sleep environment control. Summary of the Invention

[0003] This invention overcomes the shortcomings of existing technologies and provides a method for monitoring and evaluating sleep quality by combining user data analysis.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a method for monitoring and evaluating sleep quality by combining user data analysis, comprising the following steps:

[0006] Collect historical users’ thermal comfort data, acoustic sensitivity data, and light wake-up data to construct personalized physiological response parameters for users and dynamically update users’ real-time data.

[0007] A multi-scale sleep environment model for users is constructed based on digital twin technology, setting up a physical entity layer and a virtual mapping layer, and simulating it in virtual space;

[0008] By combining the user's real-time data and simulation data in the virtual space, the user's sleep quality is dynamically evaluated to obtain the user's sleep quality comfort score data.

[0009] Determine a sleep quality evaluation result of the user according to the sleep quality comfort degree score data of the user, and dynamically control the sleep environment based on the sleep quality evaluation result of the user.

[0010] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the thermal comfort data, sound sensitivity data and light wake-up data of the historical user are collected, the user's personalized physiological response parameters are constructed, and the real-time data of the user is dynamically updated, specifically including:

[0011] Obtain the skin temperature and metabolic rate of the user within a preset time, and construct thermal comfort data according to the skin temperature and metabolic rate of the user within a preset time; obtain the auditory sensitivity data of the user during sleep, and construct sound sensitivity data;

[0012] Obtain the light sensitivity data of the user in each sleep stage during sleep, and construct light wake-up data; construct the user's personalized physiological response parameters according to the thermal comfort data, sound sensitivity data and light wake-up data;

[0013] Intercept the user's personalized physiological response parameters within a preset time, and calculate the user's personalized physiological response parameters in each timestamp, and take the user's personalized physiological response parameters in each timestamp as a state vector;

[0014] Construct a state vector transition matrix according to the state vector, calculate the transition probability value of each state vector in the state vector transition matrix to another state vector, and update the state vector transition matrix when the transition probability value is greater than a preset transition probability value.

[0015] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, a multi-scale sleep environment model of the user is constructed based on digital twin technology, a physical entity layer and a virtual mapping layer are set, and simulation is performed in a virtual space, specifically including:

[0016] Construct a multi-scale sleep environment model of the user based on digital twin technology, set a physical entity layer and a virtual mapping layer in the multi-scale sleep environment model of the user, and generate a 3D point cloud model by deploying a laser radar in the bedroom in the physical entity layer;

[0017] In the 3D point cloud model, mark the positions of doors, windows, heaters and air conditioners, and real-time return temperature and humidity, light data, noise data and air flow data through environmental sensors, and physiological data through wearable devices;

[0018] In the virtual mapping layer, an interactive virtual bedroom is constructed using Unreal Engine, an accurate space model is generated by importing the 3D point cloud model, an air flow model is established based on the air flow data using computational fluid dynamics, and the air flow diffusion path of the air conditioner is simulated.

[0019] calculating a temperature field distribution based on the backhaul temperature and humidity, calculating an illumination distribution in the bedroom based on illumination data, forming a noise distribution based on noise data, and simulating in a virtual space.

[0020] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep quality of the user is dynamically evaluated based on real-time data of the user and simulation data in a virtual space, and sleep quality comfort score data of the user is obtained, specifically including:

[0021] setting user sleep quality comfort evaluation index data, constructing a hierarchical evaluation system based on an analytic hierarchy process, taking the real-time data of the user and the simulation data in the virtual space as independent variables, and introducing the analytic hierarchy process;

[0022] setting sleep quality comfort score data of a plurality of users, dividing the hierarchical evaluation system into a target layer, a criterion layer, and a scheme layer, inputting the sleep quality comfort score data of the user into the target layer, and inputting the independent variables into the scheme layer;

[0023] inputting the user sleep quality comfort evaluation index data into the criterion layer, evaluating based on the hierarchical evaluation system, and obtaining sleep quality comfort score data of the user.

[0024] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep quality evaluation result of the user is determined according to the sleep quality comfort score data of the user, specifically including:

[0025] setting a sleep quality comfort score data threshold of the user, and determining whether the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user;

[0026] when the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, sleep quality score data that does not meet predetermined requirements is generated;

[0027] when the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, sleep quality score data that meets predetermined requirements is generated.

[0028] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep environment is dynamically controlled based on the sleep quality evaluation result of the user, specifically including:

[0029] When the sleep quality evaluation result of the user is sleep quality score data that does not meet predetermined requirements, the environmental parameters of each sleep environment are reinitialized, a mutual information matrix between the environmental parameters of each sleep environment is calculated based on an information theory method, the interaction between the parameters is quantified, and cross mutual information is obtained;

[0030] According to the cross mutual information, the coupling between the environmental parameters of each sleep environment is determined, and the actual environmental parameters of the current sleep environment are estimated based on the cross mutual information and the environmental parameters of each sleep environment;

[0031] The environmental parameters of each sleep environment are dynamically simulated, and the sleep quality evaluation result of the user is obtained, and when the sleep quality evaluation result of the user is sleep quality score data that does not meet predetermined requirements, the environmental parameters of each sleep environment are continuously adjusted.

[0032] When the sleep quality evaluation result of the user is sleep quality score data that meets predetermined requirements, the environmental parameters of each sleep environment are output, and the environmental parameters of each sleep environment are controlled through an environmental parameter device.

[0033] The second aspect of the present application provides a sleep quality monitoring and evaluation system combined with user data analysis, including a memory and a processor, the memory includes a sleep quality monitoring and evaluation method program combined with user data analysis, and the sleep quality monitoring and evaluation method program combined with user data analysis is executed by the processor to realize the steps of any one of the sleep quality monitoring and evaluation method combined with user data analysis.

[0034] The third aspect of the present application provides a computer readable storage medium, including a sleep quality monitoring and evaluation method program combined with user data analysis, and the sleep quality monitoring and evaluation method program combined with user data analysis is executed by the processor to realize the steps of any one of the sleep quality monitoring and evaluation method combined with user data analysis.

[0035] The present application solves the defects in the background art, and has the following advantages:

[0036] The application collects the thermal comfort data, sound sensitivity data and light awakening data of historical users, constructs the personalized physiological response parameters of the users, dynamically updates the real-time data of the users, and then constructs a multi-scale sleep environment model of the users based on the digital twin technology, sets a physical entity layer and a virtual mapping layer, and simulates in the virtual space, so as to dynamically evaluate the sleep quality of the users in combination with the real-time data of the users and the simulation data in the virtual space, obtain sleep quality comfort degree score data of the users, finally determine the sleep quality evaluation result of the users according to the sleep quality comfort degree score data of the users, and dynamically control the sleep environment based on the sleep quality evaluation result of the users. The application fully considers the coupling between the environmental parameters and the personalized physiological response parameters of the users, so that the environmental parameters can be further optimized, and the sleep environment control is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0038] Figure 1 The overall flowchart of the sleep quality monitoring and evaluation method combined with user data analysis is shown;

[0039] Figure 2 The system block diagram of the sleep quality monitoring and evaluation system combined with user data analysis is shown. DETAILED DESCRIPTION

[0040] In order to more clearly illustrate the above-mentioned purposes, features and advantages of the present application, the following will further describe the present application in combination with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0041] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the protection scope of the present application is not limited by the specific embodiments disclosed below.

[0042] As Figure 1 shown, the first aspect of the present application provides a sleep quality monitoring and evaluation method combined with user data analysis, including the following steps:

[0043] S102: Collecting thermal comfort data, sound sensitivity data and light wake-up data of historical users, constructing personalized physiological response parameters of users, and dynamically updating real-time data of users;

[0044] S104: Constructing a multi-scale sleep environment model of the user based on digital twin technology, setting a physical entity layer and a virtual mapping layer, and simulating in a virtual space;

[0045] S106: Dynamically evaluating the sleep quality of the user in combination with real-time data of the user and simulation data in the virtual space, and obtaining sleep quality comfort score data of the user;

[0046] S108: Determining the sleep quality evaluation result of the user according to the sleep quality comfort score data of the user, and dynamically controlling the sleep environment based on the sleep quality evaluation result of the user.

[0047] It should be noted that the present application fully considers the coupling between environmental parameters and the personalized physiological response parameters of the user, so as to further optimize the environmental parameters and further make the sleep environment control more accurate.

[0048] Further, in the sleep quality monitoring and evaluation method combining user data analysis, the thermal comfort data, sound sensitivity data and light wake-up data of historical users are collected, the personalized physiological response parameters of users are constructed, and the real-time data of users is dynamically updated, which specifically includes:

[0049] The skin temperature and metabolic rate of the user within a preset time are obtained (which can be obtained through medical health data), the skin temperature and metabolic rate of the user within a preset time are used to constitute thermal comfort data, the auditory sensitivity data of the user during sleep (such as the sound data of waking up the user, different age groups of users have different auditory sensitivity data) is obtained, and the sound sensitivity data is constituted;

[0050] The light sensitivity data of the user in each sleep stage during sleep is obtained, the light wake-up data is constructed, and the personalized physiological response parameters of the user are constructed according to the thermal comfort data, the sound sensitivity data and the light wake-up data;

[0051] The personalized physiological response parameters of the user within a preset time are intercepted, and the personalized physiological response parameters of the user in each timestamp are calculated, and the personalized physiological response parameters of the user in each timestamp are taken as a state vector;

[0052] The state vector transition matrix is constructed according to the state vector, the transition probability value of each state vector in the state vector transition matrix to another state vector is calculated, and when the transition probability value is greater than a preset transition probability value, the state vector transition matrix is updated.

[0053] It should be noted that constructing user personalized physiological response parameters according to thermal comfort data, sound sensitivity data and light awakening data, and updating in time through a state vector matrix, can make the data the physiological parameters of the user at the present stage, so as to improve the control accuracy of the sleep environment. The light awakening data includes light intensity data and light type data (such as visible light and invisible light).

[0054] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, a multi-scale sleep environment model of the user is constructed based on digital twin technology, a physical entity layer and a virtual mapping layer are set, and simulation is performed in a virtual space. Specifically:

[0055] A multi-scale sleep environment model of the user is constructed based on digital twin technology, and a physical entity layer and a virtual mapping layer are set in the multi-scale sleep environment model of the user. In the physical entity layer, a 3D point cloud model is generated by deploying a laser radar in the bedroom.

[0056] In the 3D point cloud model, the positions of doors, windows, heaters and air conditioners are labeled, and temperature and humidity, light data, noise data and air flow data are returned in real time through environmental sensors, and physiological data is uploaded through wearable devices.

[0057] In the virtual mapping layer, an interactive virtual bedroom is constructed using Unreal Engine software, an accurate space model is generated by importing the 3D point cloud model, an air flow model is established based on the air flow data using computational fluid dynamics, and the air flow diffusion path of the air conditioner is simulated.

[0058] The temperature field distribution is calculated based on the returned temperature and humidity using thermodynamic equations, the light distribution in the bedroom is calculated using light data, and the noise distribution is formed based on noise data, and simulation is performed in the virtual space.

[0059] It should be noted that Unreal Engine can be used to develop various games from two-dimensional mobile platform games to large-scale host platform games, and is suitable for global independent game developers. It can also be used in non-game fields such as car configurators, marketing assets, model building and other projects. Through the method, a multi-scale sleep environment model of the user can be constructed, and the sleep environment can be simulated in a virtual space.

[0060] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep quality of the user is dynamically evaluated based on real-time data of the user and simulation data in the virtual space, and sleep quality comfort score data of the user is obtained. Specifically, it includes:

[0061] The user sleep quality comfort evaluation index data is set, the hierarchical structure evaluation system is constructed based on the analytic hierarchy process, the real-time data of the user and the simulation data in the virtual space are taken as independent variables, and the analytic hierarchy process is introduced;

[0062] The sleep quality comfort score data of a plurality of users (such as the score data range being 0-100) is set, the hierarchical structure evaluation system is divided into a target layer, a criterion layer and a scheme layer, the sleep quality comfort score data of the user is input into the target layer, and the independent variables are input into the scheme layer;

[0063] The user sleep quality comfort evaluation index data is input into the criterion layer, evaluation is performed based on the hierarchical structure evaluation system, and the sleep quality comfort score data of the user is obtained.

[0064] It should be noted that the score range of the sleep quality comfort score data of the user is 0-100, and the higher the score, the higher the sleep quality. The sleep quality comfort score data of the user can be obtained by the method, so that the sleep quality of the user is evaluated.

[0065] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep quality evaluation result of the user is determined according to the sleep quality comfort score data of the user, and specifically:

[0066] The sleep quality comfort score data threshold of the user is set, and it is judged whether the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user;

[0067] When the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, the sleep quality score data that does not meet the predetermined requirement is generated;

[0068] When the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, the sleep quality score data that meets the predetermined requirement is generated.

[0069] Further, in the sleep quality monitoring and evaluation method combined with user data analysis, the sleep environment is dynamically controlled based on the sleep quality evaluation result of the user, and specifically includes:

[0070] When the sleep quality evaluation result of the user is the sleep quality score data that does not meet the predetermined requirement, the environmental parameters of each sleep environment are reinitialized, the mutual information matrix between the environmental parameters of each sleep environment is calculated based on the information theory method, the interaction between the parameters is quantified, and the cross mutual information is obtained;

[0071] It should be noted that the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment can be determined by the cross mutual information, and the actual environmental parameters of the current sleep environment can be estimated based on the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment.

[0072] According to the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment, the actual environmental parameters of the current sleep environment can be estimated based on the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment and the environmental parameters of each sleep environment.

[0073] It should be noted that the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment can be determined by the cross mutual information, and the actual environmental parameters of the current sleep environment can be estimated based on the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment.

[0074] The environmental parameters of each sleep environment are dynamically simulated to obtain the sleep quality evaluation result of the user, and when the sleep quality evaluation result of the user is sleep quality score data that does not meet the predetermined requirements, the environmental parameters of each sleep environment are continuously adjusted.

[0075] When the sleep quality evaluation result of the user is sleep quality score data that meets the predetermined requirements, the environmental parameters of each sleep environment are output, and the environmental parameters of each sleep environment are controlled by the environmental parameter device.

[0076] It should be noted that the coupling between the environmental parameters of each sleep environment and the environmental parameters of each sleep environment and the individual physiological response parameters of the user are fully considered, so that the environmental parameters can be further optimized, and the sleep environment control is more accurate.

[0077] In addition, the method further comprises:

[0078] The real-time sound energy data information in the target area is acquired by a sound energy data acquisition device, a sound energy simulation penetration scene is constructed, and the sound absorption coefficient of the type of sound barrier in the target area is collected; the type of sound barrier in the target area and the real-time sound energy data information in the target area under the coverage data condition are input into the sound energy simulation penetration scene, and sound energy penetration simulation is performed in combination with the sound absorption coefficient of the type of sound barrier in the target area; through sound energy penetration simulation, the sound energy absorbed by the material and the sound energy reflected by the material are acquired, and the sound energy data penetrating the material is calculated according to the sound energy absorbed by the material and the sound energy reflected by the material; the sound energy data penetrating the material is subjected to attenuation analysis under the environmental data information (such as temperature data, humidity data) in the house, the actual sound energy data of the house within the preset range is acquired, the actual sound energy data of the house within the preset range is analyzed according to the sound sensitivity data of the user (due to changes in the environment, the propagation medium will change to a certain extent, which can be determined by the attenuation degree of sound energy in different environments), and it is determined whether there is noise data, and the noise data is output when there is noise data.

[0079] It should be noted that the sound energy data includes sound size data, sound direction data, etc. In fact, the real-time sound energy data information in the target area under different conditions such as the type of sound barrier, the coverage area of the sound barrier, and the thickness data of the sound barrier is different. Through this method, a sound energy simulation penetration scene can be constructed by virtual reality technology or digital twin technology, so that the real-time sound energy data information in the target area under the condition of the type of sound barrier and the coverage data in the target area is input into the sound energy simulation penetration scene, and sound energy penetration simulation is performed in combination with the sound absorption coefficient of the type of sound barrier in the target area, so that the noise data in the house can be more accurately estimated, and the control accuracy of the sleep environment control device can be improved.

[0080] In addition, the method further comprises:

[0081] A Markov decision model is constructed, the sleep state and the environmental parameter are taken as dynamic parameters, the working parameter of the device is taken as a to-be-optimized parameter, the increase of deep sleep time is taken as a positive reward, and the increase of wake-up times is taken as a negative reward;

[0082] The dynamic parameters are input into the Markov decision model, the state transition probability of the dynamic parameters being transferred to another dynamic parameter within a preset time is calculated, and a state transition probability threshold is set;

[0083] When the state transition probability is greater than the state transition probability threshold, another dynamic parameter is updated, a proximal policy optimization (PPO) algorithm is used to train an intelligent agent, a virtual environment is constructed by digital twin technology, and a preset number of operations are performed in the virtual environment to search for the number of positive rewards and the number of negative rewards of the current to-be-optimized parameter;

[0084] The ratio between the number of positive rewards and the number of negative rewards of the current parameter to be optimized is calculated, when the ratio is greater than a preset ratio, the parameter to be optimized is maintained unchanged, when the ratio is not greater than the preset ratio, the parameter to be optimized is adjusted until it is greater than the preset ratio.

[0085] It should be noted that when the state transition probability is greater than the state transition probability threshold, the other dynamic parameter is updated, and the parameter is updated in real time, when the ratio is greater than the preset ratio, it is estimated that the sleep quality of the user is high, otherwise, it is easy to wake up. Through the method, the sleep state and the sleep environment parameter of the user can be updated in time, so as to further search the parameter to be optimized, thereby improving the sleep quality of the user.

[0086] In addition, the method further comprises:

[0087] A cascaded deep learning architecture is constructed according to the user individualized physiological response parameter, wherein the first layer is a double-flow Temporal CNN processing time sequence physiological signal (such as a breathing parameter);

[0088] The second layer is a graph convolution network (GCN) modeling the topological relationship between signals (such as a heart-brain coupling effect), and the third layer introduces a Transformer encoder to capture long-time dependence relationship, and the model input is a sliding serial data, and the user individualized physiological response parameter is learned individually;

[0089] A federated learning framework is deployed, the terminal device retains a user individualized lightweight model, and a cloud aggregates a global model, and the change feature data of the user individualized physiological response parameter within a preset time is calculated;

[0090] A change feature data threshold of the user individualized physiological response parameter is set, when the change feature data of the user individualized physiological response parameter within the preset time is greater than the change feature data threshold of the user individualized physiological response parameter, the user individualized lightweight model is triggered to be updated.

[0091] It should be noted that by adopting the transfer learning + domain adaptation strategy, when the change feature data of the user individualized physiological response parameter within the preset time is greater than the change feature data threshold of the user individualized physiological response parameter, the user individualized lightweight model is triggered to be updated, which can further deeply integrate the individualized physiological parameters of the user and optimize the control accuracy of the sleep environment.

[0092] As Figure 2As shown, the second aspect of the present application provides a sleep quality monitoring and evaluation combined with user data analysis 4, comprising a memory 41 and a processor 42, the memory 41 comprising a sleep quality monitoring and evaluation combined with user data analysis method program, the sleep quality monitoring and evaluation combined with user data analysis method program being executed by the processor 42 to realize the steps of any one of the sleep quality monitoring and evaluation combined with user data analysis method.

[0093] The third aspect of the present application provides a computer readable storage medium comprising a sleep quality monitoring and evaluation combined with user data analysis method program, the sleep quality monitoring and evaluation combined with user data analysis method program being executed by the processor to realize the steps of any one of the sleep quality monitoring and evaluation combined with user data analysis method.

[0094] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0095] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on a plurality of network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0096] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional unit.

[0097] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0098] Alternatively, the integrated unit of the present application can be stored in a computer readable storage medium if it is realized in the form of a software function module and sold or used as an independent product. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the method of the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a RAM, a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0099] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A sleep quality monitoring and evaluation method incorporating user data analysis, characterized in that, The method comprises the following steps: Collecting thermal comfort data, sound sensitivity data and light awakening data of historical users, constructing personalized physiological response parameters of users, and dynamically updating real-time data of users; Based on digital twin technology, a multi-scale sleep environment model of the user is constructed, a physical entity layer and a virtual mapping layer are set, and simulation is performed in the virtual space; The sleep quality of the user is dynamically evaluated by combining the real-time data of the user and the simulation data in the virtual space, and sleep quality comfort score data of the user is obtained; According to the sleep quality comfort score data of the user, the sleep quality evaluation result of the user is determined, and the sleep environment is dynamically controlled based on the sleep quality evaluation result of the user; Based on digital twin technology, a multi-scale sleep environment model of the user is constructed, a physical entity layer and a virtual mapping layer are set, and simulation is performed in the virtual space, specifically: Based on digital twin technology, a multi-scale sleep environment model of the user is constructed, a physical entity layer and a virtual mapping layer are set in the multi-scale sleep environment model of the user, in the physical entity layer, a 3D point cloud model is generated by deploying a laser radar in the bedroom; In the 3D point cloud model, the positions of doors, windows, heaters and air conditioners are labeled, and real-time temperature and humidity, light data, noise data and air flow data are returned through environmental sensors, and physiological data is uploaded through wearable devices; In the virtual mapping layer, an interactive virtual bedroom is constructed using Unreal Engine, an accurate space model is generated by importing the 3D point cloud model, an air flow model is established based on the air flow data using computational fluid dynamics to simulate the air flow diffusion path of the air conditioner; The temperature field distribution is calculated based on the returned temperature and humidity using thermodynamic equations, the light distribution in the bedroom is calculated using light data, and the noise distribution is formed based on noise data, and simulation is performed in the virtual space; Combining the real-time data of the user and the simulation data in the virtual space, the sleep quality of the user is dynamically evaluated, and sleep quality comfort score data of the user is obtained, specifically including: Setting user sleep quality comfort evaluation index data, constructing a hierarchical evaluation system based on the analytic hierarchy process, taking the real-time data of the user and the simulation data in the virtual space as independent variables, and introducing the analytic hierarchy process; A plurality of sleep quality comfort score data of the user is set, the hierarchical evaluation system is divided into a target layer, a criterion layer and a scheme layer, the sleep quality comfort score data of the user is input into the target layer, and the independent variables are input into the scheme layer; The user sleep quality comfort evaluation index data is input into the criterion layer, the evaluation is performed based on the hierarchical evaluation system, and the sleep quality comfort score data of the user is obtained.

2. The sleep quality monitoring and evaluation method in conjunction with user data analysis according to claim 1, characterized in that, Collecting thermal comfort data, sound sensitivity data and light awakening data of historical users, constructing personalized physiological response parameters of users, and dynamically updating real-time data of users, specifically including: Obtaining skin temperature and metabolic rate of the user within a preset time, constructing thermal comfort data according to the skin temperature and metabolic rate of the user within a preset time, obtaining auditory sensitivity data of the user during sleep, and constructing sound sensitivity data; Obtaining light sensitivity data of a user in each sleep stage when sleeping, constructing light wake-up data, constructing user individual physiological response parameters according to the thermal comfort data, sound sensitivity data and light wake-up data; Truncating the user individual physiological response parameters within a preset time, and calculating the user individual physiological response parameters in each timestamp, taking the user individual physiological response parameters in each timestamp as a state vector; Constructing a state vector transition matrix according to the state vector, calculating a transition probability value of each state vector in the state vector transition matrix to another state vector, and updating the state vector transition matrix when the transition probability value is greater than a preset transition probability value.

3. The sleep quality monitoring and evaluation method in conjunction with user data analysis according to claim 1, characterized in that, Determining a sleep quality evaluation result of the user according to the sleep quality comfort score data of the user, specifically: Setting a sleep quality comfort score data threshold of the user, and determining whether the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user; When the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, generating sleep quality score data that does not meet predetermined requirements; When the sleep quality comfort score data of the user is greater than the sleep quality comfort score data threshold of the user, generating sleep quality score data that meets predetermined requirements.

4. The sleep quality monitoring and evaluation method in conjunction with user data analysis according to claim 1, characterized in that, Dynamically controlling the sleep environment based on the sleep quality evaluation result of the user, specifically including: When the sleep quality evaluation result of the user is sleep quality score data that does not meet predetermined requirements, reinitializing the environment parameters of each sleep environment, calculating a mutual information matrix between the environment parameters of each sleep environment based on an information theory method, quantifying the interaction between the parameters, and obtaining cross mutual information; According to the cross mutual information, determining the coupling between the environment parameters of each sleep environment, and estimating the actual environment parameters of the current sleep environment based on the coupling between the environment parameters of each sleep environment and the environment parameters of each sleep environment; Dynamically simulating the environment parameters of each sleep environment, obtaining the sleep quality evaluation result of the user, and continuing to adjust the environment parameters of each sleep environment when the sleep quality evaluation result of the user is sleep quality score data that does not meet predetermined requirements; When the sleep quality evaluation result of the user is sleep quality score data that meets predetermined requirements, outputting the environment parameters of each sleep environment, and controlling through the environment parameter equipment according to the environment parameters of each sleep environment.

5. A sleep quality monitoring and assessment system incorporating user data analysis, characterized by, A memory and a processor are included, the memory includes a sleep quality monitoring and evaluation method combined with user data analysis program, and the sleep quality monitoring and evaluation method combined with user data analysis program is executed by the processor to realize the steps of the sleep quality monitoring and evaluation method combined with user data analysis of any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, A sleep quality monitoring and evaluation method program including the sleep quality monitoring and evaluation method with user data analysis, when executed by a processor, implements the steps of the sleep quality monitoring and evaluation method with user data analysis as claimed in any one of claims 1-4.

Images