Intelligent health care control method, device and system and storage medium

Abstract

The invention relates to an intelligent health care control method, device and system and a storage medium, and belongs to the field of health care environment control, and the method comprises the steps: obtaining current environment parameters monitored by a plurality of sensors and user physiological data monitored by a physiological data collection device in real time through a data interface; inputting the physiological data of the user into a health assessment model based on deep learning to obtain a health state of the user; determining a target environment parameter according to the health state; generating an environment regulation and control instruction according to the current environment parameter and the target environment parameter; and sending the environment regulation and control instruction to corresponding environment regulation equipment through a control interface so as to drive the environment regulation equipment to operate, so that the health environment reaches the target environment parameters. The method has the effect of improving the regulation precision of the health-care environment.

Description

Technical Field

[0001] This application relates to the technical field of health and wellness environment control, and in particular to an intelligent health and wellness control method, device, system, and storage medium. Background Technology

[0002] With the improvement of people's living standards and the enhancement of health awareness, the demand for health and wellness services is increasing, making it crucial to provide a safe, comfortable, and healthy living environment for this population. Traditional health and wellness environments rely on manual management and simple equipment control, such as caregivers manually adjusting air conditioners and turning on air purifiers. This approach is inefficient, manpower-dependent, and slow to respond.

[0003] Currently, there are some automated environmental control systems that monitor the environment through sensors and apply fixed threshold control to devices such as air conditioners. However, these automated control systems still have technical shortcomings: 1. Existing control systems mostly rely on the regulation of a single dimension of environmental parameters, such as indoor temperature and humidity. However, different users have different individual health conditions and physiological states, and their environmental needs are also different. Therefore, they cannot provide a targeted health and wellness environment.

[0004] 2. Existing environmental control, medical monitoring, and health management systems often operate independently, making it impossible to coordinate and adjust environmental equipment based on the user's physiological data.

[0005] 3. Existing control systems only intervene after environmental parameters exceed the limits, making it difficult to provide precise health and wellness adjustments based on the user's specific situation.

[0006] Therefore, there is an urgent need for an intelligent health and wellness control system that can overcome the aforementioned technical deficiencies. Summary of the Invention

[0007] To improve the precision of health and wellness environment regulation, this application provides an intelligent health and wellness control method, device, system, and storage medium.

[0008] Firstly, this application provides an intelligent health and wellness control method, which adopts the following technical solution: The system acquires real-time environmental parameters monitored by multiple sensors and user physiological data monitored by physiological data acquisition devices through a data interface. The user's physiological data is input into a deep learning-based health assessment model to obtain the user's health status. Determine the target environmental parameters based on the described health status; Generate environmental control instructions based on the current environmental parameters and the target environmental parameters; The environmental control command is sent to the corresponding environmental control equipment through the control interface to drive the environmental control equipment to operate, so that the health and wellness environment reaches the target environmental parameters.

[0009] By adopting the above technical solutions, environmental and physiological data are collected in real time through multiple sensors. With the help of deep learning health assessment models, the user's health status can be scientifically judged, providing a precise basis for environmental regulation. Based on the current and target environmental parameters, instructions are generated and the equipment is driven to operate. The health and wellness environment can be quickly adjusted to the optimal level that suits the user's health status, effectively reducing human intervention errors, improving environmental adaptability, creating a personalized and dynamic health and wellness environment for users, improving the health and wellness experience and health management efficiency, and realizing precise and dynamic regulation of the health and wellness environment and real-time care for the user's health.

[0010] Further, the step of generating environmental control instructions based on the current environmental parameters and the target environmental parameters includes: Determine whether historical adjustment data exists in the database, indicating that the current environmental parameters were adjusted to the target environmental parameters. If it exists, the current activity state is obtained through the user's physiological data, and the historical adjustment data under the same activity state as the current activity state is obtained. The historical adjustment data includes the change curve of the user with time as the independent variable and historical physiological data as the dependent variable when the current environmental parameter is adjusted to the target environmental parameter. The activity state is sleep or activity. Calculate the rate of change of historical physiological data per unit time based on the aforementioned change curve; The time point in which the rate of change of the historical physiological data is greater than a preset value is determined as the first node; Calculate the ratio of the time corresponding to each first node, and divide the process of adjusting from the current environmental parameters to the target environmental parameters according to the ratio to obtain multiple first intermediate nodes; According to the insertion node strategy corresponding to the current activity state, a second intermediate node is inserted into the initial intermediate node, and the first intermediate node and the second intermediate node are determined as intermediate nodes; An environmental control instruction is generated based on the intermediate nodes. The environmental control instruction is as follows: each intermediate node is used as the adjustment amount of the current environmental parameter in sequence, and the adjustment is maintained for a preset time until the target environmental parameter is reached.

[0011] By adopting the above technical solution, utilizing historical adjustment data and physiological change curves, key time nodes in the adjustment process are determined, and the environmental parameter adjustment path is segmented and optimized. By setting intermediate nodes and setting preset dwell times, environmental changes are made smoother, reducing the impact on users' physiology, improving the comfort and adaptability of the health and wellness environment, and achieving precise and personalized dynamic control.

[0012] Furthermore, if it does not exist, the method further includes: The adjustment speed of the environmental control equipment from the current environmental parameters to the target environmental parameters is obtained based on big data. Determine the health level corresponding to the user's stated health status; The adjustment speed is adjusted based on the health level, and the level of health is positively correlated with the speed of adjustment.

[0013] By adopting the above technical solution, in the absence of historical data, the adjustment speed is obtained through big data and adjusted in combination with the user's health level. The lower the health level, the slower the adjustment, avoiding discomfort or risk to users caused by sudden changes in environmental parameters, ensuring safety and comfort, realizing personalized and stable environmental regulation based on individual health status, and improving the health and wellness experience and safety.

[0014] Furthermore, before determining the target environmental parameters based on the health status, the method further includes: Acquire the standard target environmental parameters corresponding to the health status and the historical adjustment data of the environmental parameters by the user under the same health status; Calculate the difference between each of the historical adjustment data and the standard target environmental parameter; Calculate the variance of each difference. When the variance is less than a preset variance, determine the mean of each difference as the user's environment preference value. When the variance is greater than or equal to the preset variance, arrange the differences in ascending order to obtain a first sequence. Obtain a first curve based on the first sequence. Extract a local curve in the first curve whose slope is less than a preset slope. Determine the mean of the differences corresponding to the local curve as the user's environment preference value. The correlation between the environmental parameters and the health status is determined based on the big data. If the correlation is less than the first preset value, the environmental preference value will not be modified. If the correlation degree is greater than the first preset value and less than the second preset value, then calculate: environmental preference value × (1 - correlation degree) to obtain a new environmental preference value; If the correlation degree is greater than the second preset value, then the environmental preference value is set to zero; wherein, the first preset value is less than the second preset value, and the correlation degree, the first preset value, and the second preset value are all less than 1; The environmental preference value is added to the value of the target environmental parameter to obtain the corrected target environmental parameter.

[0015] By adopting the above technical solutions and combining user environmental preferences with the correlation with health, the target environmental parameters are personalized and modified. When the correlation is high, health is prioritized and the influence of preferences is reduced or eliminated. When the correlation is moderate, health and preferences are balanced. When the correlation is low, user habits are preserved. This achieves precise environmental regulation that prioritizes health while taking comfort into account, thereby improving health and wellness effects and user satisfaction.

[0016] Furthermore, determining the correlation between each type of environmental parameter and the health status based on the big data includes: Based on big data, keywords of environmental parameters corresponding to the health status are obtained; Obtain the frequency of occurrence of keywords for each of the environmental parameters within a preset time period; The frequency of occurrence of the environmental parameter keywords is determined as the correlation between the corresponding environmental parameter type and the health status.

[0017] By adopting the above technical solutions, keywords related to health status are extracted from big data, their frequency of occurrence is statistically analyzed and used as correlation, and the impact of each environmental parameter on health is quickly quantified. This helps to achieve precise regulation that prioritizes health while taking into account individual preferences, and improves the adaptability and scientific nature of the health and wellness environment.

[0018] Furthermore, the method also includes: The user's physiological data in the time sequence is input into a health prediction model based on a time sequence attention mechanism to obtain the user's future health status. If the future health status is worse than the user's health status, then obtain abnormal physiological data types; The environmental parameter that can improve the abnormal physiological data is determined as the first environmental parameter; Obtain the target value of the first environmental parameter, and increase the first environmental parameter by a preset unit value every preset time interval until it is adjusted to the target value.

[0019] By adopting the above technical solutions, the temporal attention mechanism is used to predict the user's future health status, identify potential deterioration trends in advance, and gradually adjust relevant environmental parameters to target values ​​for abnormal physiological data, thereby achieving proactive intervention. Through gradual adjustment, the impact of sudden environmental changes on users can be avoided, effectively delaying or improving the trend of health deterioration, enhancing the intelligence and preventiveness of the health and wellness environment, and improving the user's health protection and comfort.

[0020] Secondly, this application provides an intelligent health and wellness control device, which adopts the following technical solution: The data acquisition module is used to acquire monitoring data from multiple sensors in real time through a data interface. The monitoring data includes user physiological data and current environmental parameters. The health status assessment module is used to input the user's physiological data into a deep learning-based health assessment model to obtain the user's health status. The target environment parameter determination module is used to determine the target environment parameters based on the health status. An environmental control instruction generation module is used to generate environmental control instructions based on the current environmental parameters and the target environmental parameters; The environmental control module is used to send the environmental control commands to the corresponding environmental control equipment through the control interface, so as to drive the environmental control equipment to operate and make the health and wellness environment reach the target environmental parameters.

[0021] By adopting the above technical solutions, environmental and physiological data are collected in real time through multiple sensors. With the help of deep learning health assessment models, the user's health status can be scientifically judged, providing a precise basis for environmental regulation. Based on the current and target environmental parameters, instructions are generated and the equipment is driven to operate. The health and wellness environment can be quickly adjusted to the optimal level that suits the user's health status, effectively reducing human intervention errors, improving environmental adaptability, creating a personalized and dynamic health and wellness environment for users, improving the health and wellness experience and health management efficiency, and realizing precise and dynamic regulation of the health and wellness environment and real-time care for the user's health.

[0022] Thirdly, this application provides an intelligent health and wellness control system, which adopts the following technical solution: An intelligent health and wellness control system includes: multiple sensors and environmental control devices installed indoors, wherein the environmental control devices include a fresh air system, a laminar flow hood, an air conditioner, an oxygen generator, and a negative ion generator; It also includes multiple physiological data acquisition devices and electronic devices worn by the user. The sensors, the environmental control devices, and the physiological data acquisition devices are all connected to the electronic devices, which are connected to edge computing devices and cloud servers. The electronic device includes: At least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: perform the method as described in any one of the first aspects.

[0023] By adopting the above technical solutions, environmental and physiological data are collected in real time through multiple sensors. With the help of deep learning health assessment models, the user's health status can be scientifically judged, providing a precise basis for environmental regulation. Based on the current and target environmental parameters, instructions are generated and the equipment is driven to operate. The health and wellness environment can be quickly adjusted to the optimal level that suits the user's health status, effectively reducing human intervention errors, improving environmental adaptability, creating a personalized and dynamic health and wellness environment for users, improving the health and wellness experience and health management efficiency, and realizing precise and dynamic regulation of the health and wellness environment and real-time care for the user's health.

[0024] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method as described in any one of the first aspects.

[0025] In summary, this application includes at least one of the following beneficial technical effects: 1. By collecting environmental and physiological data in real time through multiple sensors and using a deep learning health assessment model, it can scientifically determine the user's health status, provide accurate basis for environmental regulation, generate instructions based on current and target environmental parameters and drive the equipment to operate, and quickly adjust the health and wellness environment to the optimal level that suits the user's health status. 2. To create a personalized and dynamic health and wellness environment for users, improving their health and wellness experience and the efficiency of health management; 3. The environmental parameter adjustment path is segmented and optimized. By setting intermediate nodes and setting preset dwell times, environmental changes are made smoother, reducing the impact on users' physiology, improving the comfort and adaptability of the health and wellness environment, and achieving precise and personalized dynamic control. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the intelligent health and wellness control system in the embodiments of this application.

[0027] Figure 2 This is a flowchart illustrating the intelligent health and wellness control method in the embodiments of this application.

[0028] Figure 3 This is a structural block diagram of the intelligent health and wellness control device in the embodiments of this application.

[0029] Figure 4 This is a structural block diagram of the electronic device in the embodiments of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0032] This application discloses an intelligent health and wellness control system, referring to... Figure 1 It includes multiple sensors installed indoors, such as temperature and humidity sensors, oxygen concentration sensors, air pressure sensors, PM2.5 sensors, etc., as well as environmental control equipment installed indoors, such as fresh air systems, laminar flow hoods, air conditioners, oxygen generators, negative ion generators, etc.

[0033] The fresh air system is responsible for air replacement and features three levels of filtration: pre-filter, medium-efficiency filter, and high-efficiency filter, ensuring the purity of the air supplied to the room. Laminar flow hoods are installed in areas with high cleanliness requirements to maintain the cleanliness of the local space.

[0034] The system also includes various physiological data acquisition devices worn by the user, such as smartwatches, which can measure the user's heart rate, blood pressure, and blood oxygen saturation.

[0035] The system also includes electronic devices, with each sensor, environmental control device, and physiological data acquisition device connected to the electronic devices via wired or wireless communication protocols. The electronic devices can acquire relevant data from the sensors and physiological data acquisition devices through data interfaces. Based on the data from each sensor and the user's physiological data, the system analyzes the user's health status, determines the most suitable environment for the user, and sends control commands to the environmental control devices through a control interface to execute corresponding control logic, adjusting indoor environmental conditions such as starting the humidifier, adjusting the air conditioning mode, and turning on the negative ion generator.

[0036] The electronic devices are also connected to edge computing devices and cloud servers. The edge computing devices can initially process sensor data and improve the computing speed of the electronic devices, while the cloud servers store monitoring data and environmental control data.

[0037] This application discloses an intelligent health and wellness control method. (Refer to...) Figure 1This is performed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, desktop computer, etc., but is not limited to these. (Steps S101 to S105) Step S101: Real-time acquisition of current environmental parameters monitored by multiple sensors and user physiological data monitored by physiological data acquisition devices via data interface.

[0038] Specifically, the electronic device acquires monitoring data from multiple sensors via wired or wireless data interfaces, namely current environmental parameters such as current temperature and humidity, current oxygen concentration, current air pressure, and current PM2.5 concentration, and acquires user physiological data monitored by physiological data acquisition devices via wireless data interfaces, such as heart rate, blood pressure, and blood oxygen saturation.

[0039] Step S102: Input the user's physiological data into the deep learning-based health assessment model to obtain the user's health status.

[0040] Specifically, the electronic device pre-trains a health assessment model. First, it collects various physiological time-series signals from the user through a wearable device, and performs noise reduction, alignment, and standardization on the signals to form a physiological sample dataset. Based on medical diagnostic standards or health questionnaires, it labels the samples in the dataset with health status. It then constructs a deep learning model containing convolutional layers and recurrent neural network layers to automatically extract features from the physiological time-series signals and assess health status. Finally, it trains the model using the labeled dataset, adjusts hyperparameters through cross-validation, and uses early stopping to prevent overfitting, ultimately obtaining the health assessment model.

[0041] After inputting user physiological data into the health assessment model, conclusions about the user's health status can be obtained, such as the user's heart rate being higher than the normal range and blood oxygen saturation being lower than 95%.

[0042] Step S103: Determine the target environmental parameters based on the health status.

[0043] Specifically, the electronic device presets target environmental parameters that need to be adjusted for each health state. For example, if the user is in a health state with blood oxygen saturation below 95%, the corresponding target environmental parameters are an oxygen concentration of 28%, an air pressure of 1.08 standard atmospheres, and a negative ion concentration of 1000 / cm³. This is to increase the indoor oxygen concentration and improve the user's blood oxygen saturation.

[0044] Step S104: Generate environmental control instructions based on current environmental parameters and target environmental parameters.

[0045] Specifically, by comparing the current environmental parameters with the target environmental parameters, environmental control instructions can be obtained. For example, if the current oxygen concentration does not reach the target value, the environmental control instruction is to turn on the oxygen generator and adjust the oxygen concentration to the target value. Environmental control instructions can include instructions for one or more environmental control devices.

[0046] Step S105: Send environmental control commands to the corresponding environmental control equipment through the control interface to drive the environmental control equipment to operate and make the health and wellness environment reach the target environmental parameters.

[0047] Specifically, after receiving environmental control instructions, the environmental control equipment adjusts its operating parameters to bring the health and wellness environment up to the target environmental parameters. This allows the health and wellness environment to be changed according to the user's individual needs, thereby improving the user's health status.

[0048] Furthermore, when the electronic device performs step S104, it includes (steps S1041 to S10410): Step S1041: Determine whether there is historical adjustment data in the database that was adjusted from the current environmental parameters to the target environmental parameters.

[0049] Specifically, electronic devices store historical adjustment data in a local database or a cloud server database. In order to generate environmental control instructions suitable for users, they search the historical data to see if there is historical adjustment data that adjusts the current environmental parameters to the target environmental parameters.

[0050] If it exists, proceed to steps S1042 to S1047. If it does not exist, proceed to steps S1048 to S10410.

[0051] Step S1042: Obtain the current activity state through the user's physiological data, and acquire historical regulation data under the same activity state as the current activity state. The historical regulation data includes the change curve of the user with time as the independent variable and historical physiological data as the dependent variable when adjusting from the current environmental parameters to the target environmental parameters. The activity state is sleep or activity.

[0052] Specifically, electronic devices compare user physiological data with data models corresponding to each activity state to identify the user's current activity state. For example, in the data model for sleep, the user's physiological data has a corresponding range.

[0053] Users experience the same environmental parameters differently under different activity states. Therefore, the historical adjustment data under the same activity state as the current activity state is specifically obtained.

[0054] When the environment changes, users' physiological data will change over time. The change curve can reflect the real-time impact of environmental changes on users' health. Furthermore, due to individual differences, users have different sensitivities to changes in the current type of environment, and the change curve can better reflect the points of rapid change and slow change.

[0055] Step S1043: Calculate the rate of change of historical physiological data per unit time based on the change curve.

[0056] Specifically, if the unit of time is seconds, the electronic device calculates the rate of change of historical physiological data every second.

[0057] Step S1044: Determine the time point where the rate of change of historical physiological data is greater than the preset value as the first node.

[0058] Specifically, users' physiological data may change rapidly in the first few minutes after environmental parameters change, and then stabilize after a few minutes. In order to enable users to gradually adapt to environmental changes and reduce the discomfort caused by sudden environmental changes, electronic devices identify the first point of drastic change based on the rate of change of historical physiological data.

[0059] Step S1045: Calculate the ratio of the time corresponding to each first node, and divide the process of adjusting from the current environmental parameters to the target environmental parameters according to the ratio to obtain multiple first intermediate nodes.

[0060] Specifically, there may be one or more first nodes. If three first nodes are identified in a 5-minute change curve, the ratio of the time corresponding to each first node is obtained. For example, if the time corresponding to the first nodes is 1 minute, 1.5 minutes, and 2.5 minutes, the corresponding ratio is calculated to be 2:3:5. Under normal circumstances, the current environmental parameters can be directly adjusted to the target environmental parameters. However, in order to enable users to adapt to environmental changes, electronic devices adopt a strategy of slowly changing the environment. For example, the process of adjusting the current environmental parameters to the target environmental parameters is to increase the oxygen production of the oxygen concentrator by 5%. The increased oxygen production is divided according to the ratio to obtain 1%, 1.5%, and 2.5%, thus obtaining the first intermediate nodes as 1%, 1.5%, and 2.5%.

[0061] Step S1046: Based on the insertion strategy corresponding to the current activity state, insert a second intermediate node into the initial intermediate nodes, and determine the first and second intermediate nodes as intermediate nodes.

[0062] Specifically, since users experience the same environmental parameters differently under different activity states, for the sake of user health, corresponding insertion node strategies can be adopted for different activity states.

[0063] For example, if the current activity state is sleep, the environmental parameter adjustment process needs to be slowed down. Calculate the difference between the first intermediate node and the initial value, the difference between two adjacent first intermediate nodes, and the difference between the last first intermediate node and the final value. Insert a second intermediate node during the time period when the difference is greater than a preset value. The preset value can be the average of the calculated differences. Insert the second intermediate node so that the difference between the second intermediate node and the preceding intermediate node is the preset value.

[0064] As in the example above, the calculated differences are 1, 0.5, 1, and 2.5. The preset value is 1.25. Therefore, since the difference 2.5 > 1.25, a second intermediate node of 3.75% is inserted between the first intermediate node of 2.5% and the final value of 5%. Thus, the intermediate nodes are 1%, 1.5%, 2.5%, and 3.75%.

[0065] If the current activity status is active, there is no need to insert a second intermediate node, and the original environment adjustment speed is maintained.

[0066] Step S1047: Generate an environmental control instruction based on the intermediate nodes. The environmental control instruction is as follows: sequentially use each of the intermediate nodes as the adjustment amount of the current environmental parameter and stay for a preset time until the target environmental parameter is reached.

[0067] For example, the current oxygen concentration of 23% is first increased by 1% to 24% and maintained for 2 minutes. Then the oxygen concentration adjustment is changed to 1.5% to 24.5% and maintained for 2 minutes. The adjustment is further changed to 2.5% to 25.5% and maintained for 2 minutes. Finally, the adjustment is 3.75% until it is adjusted to 28%.

[0068] During this process, the indoor oxygen concentration rises slowly, providing users with a buffer time to adapt to environmental changes. Furthermore, the environmental changes and the individual's adaptation to the environment follow the same stepwise pattern, allowing users to adapt to the new environment silently.

[0069] If there is no historical adjustment data for adjusting from the current environmental parameters to the target environmental parameters, then: Step S1048: Based on big data, obtain the adjustment speed of the environmental control equipment from the current environmental parameters to the target environmental parameters.

[0070] Specifically, the adjustment speed from the current environmental parameter to the target environmental parameter is related to the characteristics of the environmental control equipment itself. The electronic equipment obtains the adjustment speed of the environmental control equipment when adjusting the corresponding value based on big data.

[0071] Step S1049: Determine the health level corresponding to the user's health status.

[0072] Specifically, each parameter in the user's health status is compared with the preset health level of the corresponding parameter. After comparing each parameter, the lowest level is selected as the overall health level. For example, if the heart rate is within the normal range, it is level one; if the blood pressure is high, it is level two. Therefore, the health level is determined to be level two.

[0073] Step S10410: Adjust the adjustment speed according to the health level. The level of health is positively correlated with the speed of adjustment.

[0074] Specifically, the lower the health level, the slower the adjustment speed. The first level is higher than the second level. The electronic device obtains the preset multiplier corresponding to the second level, multiplies the adjustment speed by the multiplier, and obtains the slower adjustment speed.

[0075] Furthermore, before executing step S103, the electronic device analyzes the user's historical data to determine the user's environmental preferences, thereby obtaining the target environmental parameters suitable for the user, including (steps S11 to S15).

[0076] Step S11: Obtain the standard target environmental parameters corresponding to the health status and the user's historical adjustment data for the environmental parameters under the same health status.

[0077] Specifically, electronic devices preset standard target environmental parameters corresponding to each health state. These standard target environmental parameters are suitable for most people, while historical adjustment data can reflect the user's personal preferences.

[0078] Step S12: Obtain the difference between each historical adjustment data and the standard target environmental parameter.

[0079] Step S13: Calculate the variance of each difference. When the variance is less than the preset variance, determine the mean of each difference as the user's environment preference value. When the variance is greater than or equal to the preset variance, arrange the differences in ascending order to obtain a first sequence. Obtain a first curve based on the first sequence. Extract local curves in the first curve whose slope is less than the preset slope. Determine the mean of the differences corresponding to the local curves as the user's environment preference value.

[0080] Specifically, for each environmental parameter, there are multiple sets of historical adjustment data. The difference between each set of historical adjustment data is calculated, and then the variance of the difference is calculated. The magnitude of the variance reflects the fluctuation of the historical adjustment data compared to the standard target environmental parameter.

[0081] When the variance is less than the preset variance, the difference between the historical adjustment data and the standard environmental parameters is stable, and the mean of the difference can be used as the environmental preference value.

[0082] For example, if there are 10 historical adjustment data points for oxygen content, after calculating the difference between each historical adjustment data point and the standard target environmental parameter, the mean of the difference is -2%, which means that the environmental preference value for oxygen content is -2%, and users prefer to lower the standard target environmental parameter by 2%.

[0083] If the variance is greater than or equal to the preset variance, the difference between the historical adjustment data and the standard environmental parameters is unstable. In the first sequence obtained after sorting the differences, the local curves with a slope less than the preset slope retain relatively consistent stable data, while the data corresponding to the first curve with a slope greater than or equal to the preset slope are prominent abnormal data. Therefore, the mean of the differences (stable data) corresponding to the local curves is used as the user's environmental preference value. Step S13: Determine the correlation between each environmental parameter and health status based on big data.

[0084] Specifically, the magnitude of environmental parameters is closely related to user health. However, some environmental parameters play an auxiliary role, such as humidity, which helps relax the mind and body, while others can directly change the user's physiological data, such as oxygen content, which helps increase blood oxygen. Therefore, electronic devices acquire the correlation between various environmental parameters and health status.

[0085] When obtaining correlation, keywords for environmental parameters corresponding to health status are obtained based on big data; the frequency of occurrence of each environmental parameter keyword within a preset time period is obtained; and the frequency of occurrence of environmental parameter keywords is determined as the correlation between the corresponding environmental parameter type and health status.

[0086] Specifically, electronic devices obtain environmental adjustment instructions corresponding to health status based on big data, and obtain environmental parameter keywords from the environmental adjustment instructions. The higher the frequency of the keyword, the stronger the correlation between the environmental parameter and the health status, that is, when it is necessary to improve the current health status, it is necessary to adjust the environmental parameter to the standard target environmental parameter.

[0087] Step S14: If the correlation is less than the first preset value, the environmental preference value is not modified; if the correlation is greater than the first preset value and less than the second preset value, the environmental preference value is calculated as: environmental preference value × (1 - correlation) to obtain a new environmental preference value; if the correlation is greater than the second preset value, the environmental preference value is set to zero; wherein, the first preset value is less than the second preset value, and the correlation, the first preset value and the second preset value are all less than 1.

[0088] Specifically, if the correlation is less than the first preset value, the correlation between the environmental parameters and the health status is weak, allowing the user to appropriately modify the target environmental parameters without changing the environmental preference value. If the correlation is between the first and second preset values, the user can appropriately modify the target environmental parameters, and the updated environmental preference value is calculated and controlled. If the correlation is greater than the second preset value, the correlation is strong; if the user adjusts the environmental parameters without authorization, it may affect the user's health status, therefore the environmental preference value is set to zero.

[0089] Step S15: Add the environmental preference value to the target environmental parameter value to obtain the corrected target environmental parameter.

[0090] Specifically, the environmental preference value can be positive, negative, or 0. It is added to the value of the target environmental parameter to obtain the corrected target environmental parameter, which is more in line with the user's preferences.

[0091] Furthermore, the above method also includes (steps S21 to S24): Step S21: Input the user's physiological data in the time sequence into the health prediction model based on the time sequence attention mechanism to obtain the user's future health status and health level.

[0092] Specifically, electronic devices can pre-train a health prediction model based on a temporal attention mechanism, which can identify a user's future health status and health level based on the user's temporal physiological data.

[0093] When training a health prediction model, electronic devices collect historical user physiological time-series data and label the data with corresponding health status tags based on medical diagnostic results or health standards. A neural network model is constructed, which includes at least convolutional layers for extracting local features, recurrent neural network layers for modeling long-term dependencies, and a temporal attention mechanism layer for weighted focusing of key temporal information. The labeled time-series data is input into the model for training with health status prediction as the task, and the model parameters are optimized through backpropagation using a loss function. Cross-validation is used to evaluate the model performance, and hyperparameters are adjusted according to the evaluation metrics to finally obtain the optimized health prediction model.

[0094] Step S22: If the future health status is worse than the user's health status, then obtain the abnormal physiological data type.

[0095] Step S23: Determine the environmental parameter that can improve abnormal physiological data as the first environmental parameter.

[0096] Step S24: Determine the single-adjustment value of the environmental parameter based on the health level, and adjust the single-adjustment value of the first environmental parameter every preset time interval.

[0097] Specifically, if the health status deteriorates in the future, the single-adjustment value of the environmental parameter is determined according to the health level. The lower the health level, the larger the single-adjustment value, and the first environmental parameter needs to be adjusted in advance. This adjustment is carried out every preset time so that the environmental parameter can be quickly adjusted to meet the standard in the future.

[0098] To better implement the above method, this application also provides an intelligent health and wellness control device, referring to... Figure 3 The intelligent health and wellness control device 200 includes: The data acquisition module 201 is used to acquire monitoring data from multiple sensors in real time through a data interface. The monitoring data includes user physiological data and current environmental parameters. The health status assessment module 202 is used to input user physiological data into a deep learning-based health assessment model to obtain the user's health status. The target environment parameter determination module 203 is used to determine the target environment parameters based on the health status. The environmental control instruction generation module 204 is used to generate environmental control instructions based on the current environmental parameters and the target environmental parameters. The environmental control module 205 is used to send environmental control commands to the corresponding environmental control equipment through the control interface, so as to drive the environmental control equipment to operate and make the health and wellness environment reach the target environmental parameters.

[0099] The environmental control instruction generation module 204 is specifically used for: Determine if historical adjustment data exists in the database, showing the adjustment from the current environmental parameters to the target environmental parameters; If it exists, the current activity state is obtained through the user's physiological data, and historical regulation data under the same activity state as the current activity state is obtained. The historical regulation data includes the change curve of the user with time as the independent variable and historical physiological data as the dependent variable when the current environmental parameters are adjusted to the target environmental parameters. The activity state is sleep or activity. Calculate the rate of change of historical physiological data per unit time based on the change curve; The time point where the rate of change in historical physiological data exceeds a preset value is defined as the first node; Calculate the ratio of the time corresponding to each first node, and divide the process of adjusting from the current environmental parameters to the target environmental parameters according to the ratio to obtain multiple first intermediate nodes; Based on the node insertion strategy corresponding to the current activity state, insert the second intermediate node into the initial intermediate nodes, and determine the first and second intermediate nodes as intermediate nodes; The environmental control instructions are generated based on the intermediate nodes. The environmental control instructions are as follows: each intermediate node is used as the adjustment amount of the current environmental parameter in sequence, and the adjustment is held for a preset time until the target environmental parameter is reached.

[0100] If it does not exist, it also includes: Based on big data, the adjustment speed of environmental control equipment from current environmental parameters to target environmental parameters is obtained; Determine the health level corresponding to the user's health status; The adjustment speed is adjusted based on the health level, and the level of health is positively correlated with the speed of adjustment.

[0101] The intelligent health and wellness control device 200 also includes: The historical adjustment data acquisition module is used to acquire the standard target environmental parameters corresponding to the health status and the user's historical adjustment data for the environmental parameters under the same health status. The difference calculation module is used to obtain the difference between each historical adjustment data and the standard target environmental parameter; The environment preference value calculation module is used to calculate the variance of each difference. When the variance is less than the preset variance, the mean of each difference is determined as the user's environment preference value. When the variance is greater than or equal to the preset variance, the differences are arranged in ascending order to obtain the first sequence. The first curve is obtained based on the first sequence. Local curves with slopes less than the preset slope are extracted from the first curve, and the mean of the differences corresponding to the local curves is determined as the user's environment preference value. The correlation determination module is used to determine the correlation between each environmental parameter and health status based on big data. The environment preference value modification module is used for: If the correlation is less than the first preset value, the environment preference value will not be modified. If the correlation is greater than the first preset value and less than the second preset value, then calculate: Environmental preference value × (1 - correlation) to obtain a new environmental preference value; If the correlation is greater than the second preset value, the environmental preference value is set to zero; wherein, the first preset value is less than the second preset value, and the correlation, the first preset value, and the second preset value are all less than 1; The target environment parameter correction module is used to add the environmental preference value to the target environment parameter value to obtain the corrected target environment parameter.

[0102] The correlation determination module is specifically used for: Based on big data, keywords related to environmental parameters and health status are obtained; Obtain the frequency of occurrence of keywords for various environmental parameters within a preset time period; The frequency of occurrence of environmental parameter keywords is used to determine the correlation between the corresponding environmental parameter type and health status.

[0103] The intelligent health and wellness control device 200 also includes: The module for determining the user's future health status is used to input time-series user physiological data into a health prediction model based on a time-series attention mechanism to obtain the user's future health status. The abnormal physiological data acquisition module is used to acquire abnormal physiological data if the future health status is worse than the user's health status. The first environmental parameter determination module is used to determine the environmental parameters that can improve abnormal physiological data as the first environmental parameters; The first environmental parameter adjustment module is used to obtain the target value of the first environmental parameter and increase the first environmental parameter by a preset unit value every preset time until it is adjusted to the target value.

[0104] The various variations and specific examples of the methods in the foregoing embodiments are also applicable to the intelligent health and wellness control device of this embodiment. Through the foregoing detailed description of the intelligent health and wellness control method, those skilled in the art can clearly understand the implementation method of the intelligent health and wellness control device in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0105] To better implement the above methods, embodiments of this application provide an electronic device, referring to... Figure 4 The electronic device 300 includes a processor 301, a memory 303, and a display screen 305. The memory 303 and the display screen 305 are both connected to the processor 301, such as via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0106] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0107] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 may be divided into address bus, data bus, control bus, etc.

[0108] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0109] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0110] Figure 4 The electronic device 300 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0111] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the program implements the intelligent health and wellness control method provided in the above embodiments. By collecting environmental and physiological data in real time through multiple sensors and using a deep learning health assessment model, it can scientifically determine the user's health status, providing a precise basis for environmental regulation. Based on current and target environmental parameters, it generates instructions and drives the device to operate, which can quickly adjust the health and wellness environment to the optimal level suitable for the user's health status. This effectively reduces human intervention errors, improves environmental adaptability, creates a personalized and dynamic health and wellness environment for users, improves the health and wellness experience and health management efficiency, and achieves precise and dynamic regulation of the health and wellness environment and real-time care for the user's health.

[0112] In this embodiment, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0113] The computer program in this embodiment includes program code for performing all the aforementioned methods. The program code may include instructions corresponding to the method steps provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed entirely on the user's computer as a standalone software package.

[0114] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

[0115] Additionally, it should be understood that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A smart health and wellness control method, characterized in that, The method is executed by an electronic device, and comprises: obtaining, in real time, current environmental parameters monitored by a plurality of sensors and user physiological data monitored by a physiological data acquisition device through a data interface; inputting the user physiological data into a health assessment model based on deep learning to obtain a health status of the user; determining a target environmental parameter according to the health status; generating an environmental regulation instruction according to the current environmental parameter and the target environmental parameter; sending the environmental regulation instruction to a corresponding environmental regulation device through a control interface to drive the environmental regulation device to operate, so that a health-care environment reaches the target environmental parameter.

2. The method of claim 1, wherein, The method further comprises: determining whether historical regulation data of adjustment from the current environmental parameter to the target environmental parameter exists in a database; if the historical regulation data exists, obtaining a current activity state through the user physiological data, obtaining the historical regulation data in the same activity state as the current activity state, the historical regulation data comprising a change curve of historical physiological data with time as an independent variable and the user as a dependent variable when the current environmental parameter is adjusted to the target environmental parameter, the activity state being sleep or activity, and calculating a historical physiological data change rate per unit time according to the change curve; determining a time node at which the historical physiological data change rate is greater than a preset value as a first node; calculating a ratio of time corresponding to each first node, dividing a process of adjustment from the current environmental parameter to the target environmental parameter according to the ratio to obtain a plurality of first intermediate nodes; inserting a second intermediate node into the preliminary intermediate nodes according to an insertion node strategy corresponding to the current activity state, and determining the first intermediate nodes and the second intermediate nodes as intermediate nodes; generating an environmental regulation instruction according to the intermediate nodes, the environmental regulation instruction being: taking each intermediate node as a regulation amount of the current environmental parameter in turn and staying for a preset time until the target environmental parameter is reached.

3. The method of claim 2, wherein, if the historical regulation data does not exist, the method further comprises: obtaining an adjustment speed of an environmental regulation device from the current environmental parameter to the target environmental parameter based on big data; determining a health level corresponding to the health status of the user; correcting the adjustment speed according to the health level, the health level being positively correlated with the adjustment speed.

4. The method of claim 1, wherein, Before the step of determining the target environmental parameter according to the health status, the method further comprises: obtaining a standard target environmental parameter corresponding to the health status and historical regulation data of environmental parameters of the user in the same health status; calculating a difference between each historical regulation data and the standard target environmental parameter; computing a variance of each of the difference values, when the variance is less than a preset variance, determining a mean value of each of the difference values as the environmental preference value of the user; when the variance is greater than or equal to the preset variance, arranging the difference values in ascending order to obtain a first sequence, obtaining a first curve according to the first sequence, intercepting a local curve with a slope less than a preset slope in the first curve, and determining a mean value of the difference values corresponding to the local curve as the environmental preference value of the user; determining the correlation degree between the environmental parameter and the health state based on the big data; if the correlation degree is less than a first preset value, the environmental preference value is not modified; if the correlation degree is greater than the first preset value and less than a second preset value, a new environmental preference value is obtained by calculating: environmental preference value x (1-correlation degree); if the correlation degree is greater than the second preset value, the environmental preference value is set to zero; wherein the first preset value is less than the second preset value, and the correlation degree, the first preset value and the second preset value are all less than 1; adding the environmental preference value to the value of the target environmental parameter to obtain a modified target environmental parameter.

5. The method of claim 4, wherein, The method further comprises: inputting the user physiological data of the time sequence state into a health prediction model based on a time sequence attention mechanism to obtain a future health state of the user; if the future health state is worse than the user health state, an abnormal physiological data type is obtained; determining an environmental parameter that can improve the abnormal physiological data as a first environmental parameter; 6. The method of claim 1, wherein, obtaining a target value of the first environmental parameter, and increasing the first environmental parameter by a preset unit value every preset time until adjusting to the target value. It comprises: a data acquisition module for acquiring monitoring data of multiple sensors in real time through a data interface, wherein the monitoring data includes user physiological data and current environmental parameters; a health state evaluation module for inputting the user physiological data into a health evaluation model based on deep learning to obtain the health state of the user; a target environmental parameter determination module for determining a target environmental parameter according to the health state; 7. A smart health and wellness control device, characterized in that, an environmental control instruction generation module for generating an environmental control instruction according to the current environmental parameter and the target environmental parameter; an environmental adjustment module for sending the environmental control instruction to the corresponding environmental adjustment device through a control interface to drive the environmental adjustment device to operate, so that the health-care environment reaches the target environmental parameter. It comprises: a plurality of sensors and environmental adjustment devices arranged in the room, wherein the environmental adjustment devices include a fresh air system, a laminar flow hood, an air conditioner, an oxygen generator, and a negative ion generator; ​ ​ 8. A smart health and wellness control system, characterized in that, ​ ​ The application also discloses a user-worn physiological data acquisition device and an electronic device, wherein the sensor, the environment adjusting device and the physiological data acquisition device are connected with the electronic device, and the electronic device is connected with an edge computing device and a cloud server. The electronic device comprises: at least one processor; a memory; at least one computer program, wherein the at least one computer program is stored in the memory and is configured to be executed by the at least one processor, and the at least one computer program is configured to execute the method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer program stored in the memory can be loaded by the processor and executed to execute the method in any one of claims 1 to 6.

Images