Relaxation control method based on user activity information data, and system using same

Abstract

The present invention relates to a relaxation control method based on user activity information data, and a system using same. Existing mattress systems cannot form a relaxation model on the basis of activity information of users, which affects the relaxation effect. In the present invention, multidimensional activity information of a user is collected to provide data support for a component relaxation model, so as to ensure that the relaxation model can be deeply associated with the multidimensional activity information of the user, and ensure that a relaxation device can apply a personalized relaxation stimulus to the user under the guidance of the relaxation model, thereby meeting the relaxation requirements of the user and realizing a better sleep experience; relaxation parameters of the user are measured, and a relaxation effect of the relaxation model is determined on the basis of a preset relaxation threshold value, so as to adjust conversion parameters on the basis of the effectiveness of conversion between the activity information and the relaxation model, thereby ensuring that the user has a better relaxation effect; and the relaxation model is corrected by means of adjusting the conversion parameters, thereby effectively improving the usage experience.

Description

A relaxation control method based on user activity information data and a system using it Technical Field

[0001] This invention relates to the field of sleep, and more specifically to a relaxation control method based on user activity information data and a system using the same. Background Technology

[0002] Existing smart beds include a control box, an electric frame, a smart mattress, and compatible electrical appliances. The electric frame offers various angle adjustments, and the smart mattress features adjustable airbags and sensors that monitor the user. The control box provides various services to the user by controlling the electric frame and airbags, and monitors the user's state through sensors to provide comfort services via the electric frame and airbags. During use, the user controls the electric frame, smart mattress, and electrical appliances using a pre-set relaxation model. However, because the services provided within the relaxation model cannot be adjusted according to the user's actual situation, or can only be superficially adjusted based on real-time physiological and postural data detected by the sensors, it cannot meet the user's requirement for a deep and personalized relaxation experience. This results in the user not achieving a good relaxation effect, impacting the sleep experience. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a relaxation control method and system based on user activity information data. The method collects multi-dimensional activity information from users and uses it as the basis for forming a relaxation model after conversion and calculation. This allows the relaxation model to be deeply correlated with the user's multi-dimensional activity information, ensuring that the relaxation model can automatically adjust according to the user's differentiated activity information, thereby meeting the user's relaxation requirements and achieving a better sleep experience.

[0004] This invention is achieved through the following method: a relaxation control method based on user activity information data, which is implemented through the following steps:

[0005] The first step is to collect multi-dimensional activity information from users, and then process the activity information from each dimension to obtain the corresponding activity data.

[0006] The second step is to set up multi-dimensional relaxation information, set corresponding conversion parameters between activity data and relaxation information in each dimension, so that activity data in each dimension can be converted into intermediate parameters corresponding to relaxation information in any dimension. The intermediate parameters in the same dimension of relaxation information are accumulated to obtain relaxation data corresponding to that dimension of relaxation information, and the relaxation data in each dimension are combined to form a relaxation model implemented to the user.

[0007] The third step involves the user receiving relaxation stimuli based on the relaxation model, monitoring the user's relaxation parameters, setting a relaxation threshold, adjusting the conversion parameters based on the relationship between the relaxation parameters and the relaxation threshold, and then adjusting the relaxation model to achieve relaxation parameter adjustment so that the relaxation parameters reach the relaxation threshold.

[0008] By collecting multi-dimensional activity information from users, the system provides data support for the component relaxation model. This ensures that the relaxation model can be deeply correlated with the user's multi-dimensional activity information, and that the relaxation device can apply personalized relaxation stimuli to the user under the guidance of the relaxation model. This satisfies the user's relaxation requirements and provides a better sleep experience. After the relaxation stimulation is completed, the system detects the user's relaxation parameters and judges the relaxation effect of the relaxation model based on preset relaxation thresholds. Then, it adjusts the conversion parameters based on the effectiveness of the conversion between activity information and the relaxation model, ensuring that the user has a good relaxation effect after receiving relaxation stimuli based on the relaxation model. By actively judging and correcting the conversion parameters, the relaxation model is modified, effectively improving the user experience.

[0009] Preferably, in the first step, an upper limit value IN_n_max and a lower limit value IN_n_min for each dimension of activity information are set, corresponding one-to-one. The corresponding activity data Xn is then calculated as Xn = (IN_n - IN_n_min) / (IN_n_max - IN_n_min), thus obtaining a dataset X containing n activity data points. The activity information includes n dimensions, and each activity information has its own independent upper and lower limit value. Therefore, it is necessary to record n ​​upper and n lower limit values ​​for each activity information point.

[0010] Preferably, the activity information collected from each dimension is statistically recorded, and the upper limit value IN_n_max and lower limit value IN_n_min of the activity information for each dimension are obtained from the records. During use, the universal upper limit value IN_n_max and lower limit value IN_n_min for each dimension of activity information are pre-stored, and the database is continuously updated through recording in later use to form new upper and lower limits for activity information. This ensures that the activity data fluctuates within a suitable range, preventing large fluctuations in individual data from affecting data accuracy, and also ensures that the activity data matches the user's actual activity information.

[0011] As a preferred approach, multi-dimensional activity information includes the duration of various activities and the differentiated exercise intensities among them. Activity information includes the duration and intensity of different types of activities, such as exercise duration, meeting duration, sitting duration, and walking duration. By collecting the duration and intensity of different types of activities, the user's fatigue level can be assessed, facilitating the later calculation of relaxation information.

[0012] Preferably, in the second step, the activity data includes n dimensions, the relaxation information includes m dimensions, and the transformation parameters include n×m parameters. Each dimension of activity data and each dimension of relaxation information has an independent corresponding transformation parameter W_nm. The activity data of n dimensions within the X dataset can be converted into intermediate parameters within the same dimension of relaxation information using the corresponding transformation parameter W_nm. This process is repeated to obtain m dimensions of relaxation information. Different activity information and different relaxation information have independent corresponding relationships. Transformation calculations are performed by setting one-to-one corresponding transformation parameters between different activity information and different relaxation information, ensuring that each dimension of the user's activity information is reflected in each relaxation information. Specifically, there are m transformation parameters associated with any activity information, allowing the activity information to be converted into intermediate parameters corresponding one-to-one with each of the m dimensions of relaxation information. Similarly, n dimensions of activity information are transformed into m dimensions of relaxation information through n×m transformation parameters, and each dimension of relaxation information has n intermediate parameters corresponding one-to-one with all activity information, creating a relationship between each activity information and each relaxation information, thereby achieving deep association.

[0013] Preferably, each dimension of relaxation information contains n intermediate parameters. Relaxation data for forming a relaxation model is obtained by accumulating the intermediate parameters within each relaxation information. Specifically, when the activity information is conducive to user relaxation, the conversion parameter W_nm is negative; when the activity information hinders user relaxation, the conversion parameter W_nm is positive. By pre-determining the correlation between activity information and relaxation effect in each dimension and setting the corresponding conversion parameter to negative or positive, setting the conversion parameter to positive allows the intermediate parameters to increase the relaxation information during accumulation, while setting the conversion parameter to negative allows the intermediate parameters to decrease the relaxation information during accumulation. This allows the relaxation model to have a larger adjustment range, thereby meeting the user's relaxation needs.

[0014] Preferably, the multi-dimensional relaxation information includes at least two of the following: massage duration, massage height, massage frequency, massage location, music volume, music genre, fragrance concentration, and fragrance type. Massage stimulation is provided to the user by calculating massage duration, massage height, massage frequency, and massage location information; music relaxation services are provided by calculating music volume and music genre information; and fragrance relaxation services are provided by calculating fragrance concentration and fragrance type information. Adding more relaxation devices and detailed relaxation information increases the dimensionality, thereby meeting users' needs for differentiated relaxation models.

[0015] Preferably, in the third step, after implementing the relaxation model, if the relaxation parameter is less than the relaxation threshold, the pre-relaxation difference is calculated and the conversion parameter is increased.

[0016] After implementing the recalculated relaxation model:

[0017] If the relaxation parameter is greater than the relaxation threshold, then record and continue using the current conversion parameter;

[0018] If the relaxation parameter is less than the relaxation threshold, the conversion parameter is adjusted, the post-relaxation difference is calculated and compared with the pre-relaxation difference. When the post-relaxation difference is less than the pre-relaxation difference, the conversion parameter is continuously increased. When the post-relaxation difference is greater than the pre-relaxation difference, the conversion parameter is decreased.

[0019] After each relaxation model implementation, the relaxation effect on the user is monitored, and relaxation parameters are obtained. The relaxation effect is evaluated by comparing the relaxation parameters with a relaxation threshold, and the conversion parameters are then adjusted accordingly. Furthermore, the direction of adjustment of the conversion parameters is judged by statistically analyzing the difference between two consecutive relaxation parameters and the relaxation threshold. This ensures that the conversion parameters, after a limited number of adjustments, guarantee that the user achieves a good relaxation effect after experiencing the relaxation stimulus. In use, conversion parameters can be adjusted individually to improve the accuracy of adjustments, or all conversion parameters can be adjusted in batches using preset adjustment rules, reducing the number of adjustments and improving adjustment efficiency.

[0020] Preferably, heart rate variability parameters are obtained by monitoring user heart rate data, and respiratory variability parameters are obtained by monitoring respiratory data. These heart rate variability parameters and respiratory variability parameters are then used to calculate relaxation parameters using a preset weighting ratio. By monitoring the user's heart rate and respiratory data after relaxation stimulation, these relaxation parameters are obtained, providing a basis for subsequent evaluation and adjustment of conversion parameters. Setting weighting ratios adjusts the proportion of heart rate and respiratory data in the relaxation parameters, thereby improving the accuracy of the relaxation parameters in reflecting the user's relaxation effect.

[0021] Preferably, the heart rate variability parameter is obtained through the following steps: First, heart rate data is measured within a preset time period while the user is at rest. Then, the time intervals between adjacent heartbeats are statistically analyzed to form a heart rate dataset. Finally, the heart rate dataset is processed sequentially by averaging, calculating variance, and calculating standard deviation to obtain the heart rate variability parameter. Monitoring the user's heart rate data within the preset time period serves as the basis for the calculation. A larger variation in the time intervals between adjacent heartbeats indicates greater heart rate variability, suggesting a more relaxed user. The heart rate variability parameter is obtained by sequentially averaging, calculating variance, and calculating standard deviation from the base data, effectively eliminating the impact of individual data deviations on accuracy.

[0022] The respiratory variability parameter is obtained through the following steps: First, respiratory data is measured within a preset time period while the user is at rest. Then, the number of breaths per minute is counted to form a respiratory dataset. Finally, the respiratory dataset is calculated by sequentially performing cumulative averaging, variance calculation, and standard deviation calculation to obtain the respiratory variability parameter. Monitoring the user's respiratory data within the preset time period serves as the basis for the calculation. A greater variation in respiratory rate indicates a higher respiratory variability parameter, suggesting greater user relaxation. The respiratory variability parameter is obtained by sequentially performing cumulative averaging, variance calculation, and standard deviation calculation on the base data, effectively eliminating the impact of individual data deviations on accuracy.

[0023] A system using the relaxation control method includes:

[0024] The activity data acquisition module is used to collect multi-dimensional activity information from users and transmit it to the processing module;

[0025] The physiological data acquisition module is used to collect the user's physiological data and transmit it to the processing module. The physiological data includes heart rate data and respiratory data.

[0026] The relaxation module, including massage, music, and aromatherapy components, controls the independent operation of these components by receiving a relaxation model from the processing module, in order to apply differentiated relaxation stimuli to the user.

[0027] The data storage module is used to store the transformation parameters, relaxation information of each dimension, activity information of each dimension, relaxation threshold, and relaxation parameters obtained from each detection required for the operation of the processing module.

[0028] The processing module normalizes the multi-dimensional activity information from the activity data acquisition module and calculates a relaxation model to guide the operation of the relaxation module by combining the transformation parameters. It calculates relaxation parameters from the physiological data acquisition module and adjusts the transformation parameters after comparing them with the relaxation threshold.

[0029] The system obtains multi-dimensional activity information through the activity data acquisition module, calculates a relaxation model through the processing module, controls the relaxation module to apply relaxation stimuli to the user, and monitors the user's physiological data and evaluates the relaxation effect through the physiological data acquisition module. It also adjusts the stored conversion parameters to effectively improve the matching between the relaxation model and the user's activity information, thereby ensuring that the user achieves the relaxation effect in a shorter time under the action of the relaxation model.

[0030] The beneficial effects of this invention are as follows: By collecting multi-dimensional activity information from users to provide data support for the component relaxation model, the relaxation model can be deeply correlated with the user's multi-dimensional activity information. This ensures that the relaxation device can apply personalized relaxation stimulation to the user under the guidance of the relaxation model, thereby meeting the user's relaxation requirements and achieving a better sleep experience. After completing the relaxation stimulation, the user's relaxation parameters are detected, and the relaxation effect of the relaxation model is judged according to the preset relaxation threshold. Then, the conversion parameters are adjusted according to the conversion effectiveness between activity information and the relaxation model, ensuring that the user has a better relaxation effect after receiving relaxation stimulation based on the relaxation model. By actively judging and correcting the conversion parameters, the relaxation model is modified, effectively improving the user experience. Attached Figure Description

[0031] Figure 1 is a logical schematic diagram of the relaxation control method described in Embodiment 1;

[0032] Figure 2 is a flowchart illustrating the relaxation control method described in Example 1;

[0033] Figure 3 is a schematic diagram of the system described in Embodiment 2; Embodiments of the present invention

[0034] The essential features of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0035] Example 1:

[0036] This embodiment provides a relaxation control method.

[0037] Figure 1 illustrates a relaxation control method based on user activity information data, which is implemented through the following steps:

[0038] The first step is to collect multi-dimensional activity information from users, and then process the activity information from each dimension to obtain the corresponding activity data.

[0039] Specifically, the activity information collected in each dimension is statistically recorded, and the upper limit value IN_n_max and lower limit value IN_n_min of the activity information for each dimension are obtained from the records. Multi-dimensional activity information of users is collected through wearable smart devices or human-computer interaction devices, and the activity information for each dimension is numbered sequentially from 1 to n and recorded in the corresponding data group in the database in order to obtain the upper limit value and lower limit value of the activity information.

[0040] Specifically, an upper limit value IN_n_max and a lower limit value IN_n_min for activity information are set, corresponding one-to-one with the activity information IN_n of each dimension. The activity data Xn for the corresponding dimension is calculated as Xn = (IN_n - IN_n_min) / (IN_n_max - IN_n_min), thus obtaining a dataset X containing n activity data. The collected activity information is normalized to obtain the corresponding activity data Xn. The n activity data corresponding to the activity information of each dimension are then aggregated to form the dataset X.

[0041] Specifically, the multi-dimensional activity information includes the duration of various activities, with differentiated exercise intensities among them. This activity information is multi-dimensional, encompassing various types of exercise with different intensities, such as standing work time, sitting work time, walking time, running time, sitting reading time, basketball play time, etc. By refining and categorizing all of a user's daily activities, a personalized relaxation model is created, ensuring effective relaxation for the user. Furthermore, the number of dimensions in the activity information can be refined and increased or decreased as needed, and all such adjustments should be considered specific implementation methods of this embodiment.

[0042] The second step is to set up multi-dimensional relaxation information, and set corresponding transformation parameters between activity data and relaxation information in each dimension, so that activity data in each dimension can be transformed into intermediate parameters corresponding to relaxation information in any dimension. The intermediate parameters in the same dimension of relaxation information are accumulated to obtain relaxation data corresponding to that dimension of relaxation information, and the relaxation data in each dimension are combined to form a relaxation model implemented to the user.

[0043] Specifically, the multi-dimensional relaxation information includes at least two of the following: massage duration, massage height, massage frequency, massage location, music volume, music genre, fragrance concentration, and fragrance type. This multi-dimensional relaxation information is then used by a corresponding relaxation device to create a relaxation stimulus applied to the user, thereby achieving relaxation. The number and types of the relaxation information dimensions are associated with the relaxation device, and the device can be modified or adjusted as needed; all of these modifications should be considered specific implementation methods of this embodiment.

[0044] Specifically, as shown in Figure 2, the activity data includes n dimensions, the relaxation information includes m dimensions, and the transformation parameters include n×m. Each dimension of activity data and each dimension of relaxation information has an independent corresponding transformation parameter W_nm. The activity data of n dimensions in the X dataset can be converted into intermediate parameters in the same dimension of relaxation information through the corresponding transformation parameter W_nm. The relaxation information of m dimensions can be obtained by repeating the operation. For example, if n=8 and m=7, then the number of conversion parameters is n×m=56. During the conversion, the activity information where n is 1 is the standing work time. Corresponding conversion parameters are set between this activity information and the relaxation information of the 7 dimensions. Thus, intermediate parameters corresponding to the relaxation information of each dimension can be obtained by calculating the standing work time. By converting the activity information of each dimension in turn, the relaxation information of each dimension can obtain 8 intermediate parameters converted from the activity information of each dimension through the corresponding conversion parameters. By accumulating the 8 intermediate parameters, the relaxation information of that dimension is formed. This ensures that the relaxation information of each dimension is deeply related to the activity information of each dimension. Different activity information of users each day can form differentiated relaxation information, thereby forming a relaxation model that matches the user's activities of the day.

[0045] Specifically, each dimension of relaxation information contains n intermediate parameters. Relaxation data for forming a relaxation model is obtained by accumulating the intermediate parameters within each relaxation information. When the activity information is beneficial to user relaxation, the conversion parameter W_nm is negative; when the activity information hinders user relaxation, the conversion parameter W_nm is positive. Since different activity information may have both positive and negative effects on relaxation, the conversion parameter's value range is expanded to include both positive and negative numbers. By adjusting the absolute value of the value, the conversion ratio between activity information and relaxation information is controlled, allowing activity information beneficial to relaxation and activity information detrimental to relaxation to cancel each other out during the accumulation process. The conversion parameters configured for each dimension of activity information can be adjusted between positive and negative numbers based on the user's individual circumstances and the corresponding relaxation information. They are not limited to pre-set positive or negative numbers, but can meet the differentiated needs of users and should be considered a specific implementation method of this embodiment.

[0046] The third step involves the user receiving relaxation stimuli according to the relaxation model, monitoring their relaxation parameters, setting a relaxation threshold, and adjusting the conversion parameters based on the relationship between the relaxation parameters and the threshold. This adjustment of the relaxation model ultimately aims to bring the relaxation parameters to the relaxation threshold. After receiving the relaxation stimuli, the user undergoes a relaxation effect evaluation. This evaluation determines the effectiveness of the relaxation model, allowing for the assessment and correction of the conversion parameter matching to improve the relaxation effect. The effect evaluation includes both subjective and objective evaluations.

[0047] Objective effect evaluation refers to: after implementing the relaxation model, monitoring and obtaining users' relaxation parameters and comparing them with a relaxation threshold. When the relaxation parameter is less than the relaxation threshold, the pre-relaxation difference is calculated, and the conversion parameter is increased.

[0048] After implementing the recalculated relaxation model:

[0049] If the relaxation parameter is greater than the relaxation threshold, then record and continue using the current conversion parameter;

[0050] If the relaxation parameter is less than the relaxation threshold, the conversion parameter is adjusted, the post-relaxation difference is calculated and compared with the pre-relaxation difference. When the post-relaxation difference is less than the pre-relaxation difference, the conversion parameter is continuously increased. When the post-relaxation difference is greater than the pre-relaxation difference, the conversion parameter is decreased.

[0051] The transformation parameters were adjusted by repeatedly implementing the relaxation model and monitoring the relaxation parameters.

[0052] After the first relaxation stimulus is applied, the rationality of the current switching parameter is judged by comparing the size between the relaxation parameter and the relaxation threshold. When the relaxation parameter reaches the relaxation threshold, it is recorded and the switching parameter is continued to be used in subsequent use. When the relaxation parameter cannot reach the relaxation threshold, the switching parameter is increased.

[0053] After calculating a new relaxation model based on the revised conversion parameters, a second relaxation stimulus is applied to the user. The rationality of the revised conversion parameters is judged by comparing the magnitude between the relaxation parameters and the relaxation threshold. When the relaxation parameters reach the relaxation threshold, the conversion parameters are recorded and used in subsequent applications. When the relaxation parameters fail to reach the relaxation threshold, the relaxation difference between the relaxation parameters and the relaxation threshold after the first and second relaxation stimuli is calculated, and the conversion parameter data is adjusted according to the following rules:

[0054] If the second relaxation difference is less than the first relaxation difference, it indicates that the correction direction of the conversion parameter is correct, and the conversion parameter should be increased further. If the second relaxation difference is greater than the first relaxation difference, it indicates that the correction direction of the conversion parameter is incorrect, and the conversion parameter should be decreased. In the above process, increasing the conversion parameter means that the absolute value of the conversion parameter becomes larger.

[0055] Specifically, heart rate variability parameters are obtained by monitoring user heart rate data, and respiratory variability parameters are obtained by monitoring respiratory data. These heart rate variability parameters and respiratory variability parameters are then used to calculate relaxation parameters through a preset weighting ratio. Since heart rate variability parameters and respiratory variability parameters are different types of data, they need to be converted into relaxation parameters through weighting ratios to ensure that the relaxation parameters are correlated with the user's heart rate and breathing.

[0056] In this embodiment, the main reason for the increased heart rate variability (HRV) in a relaxed state is based on the regulatory mechanisms of the autonomic nervous system, particularly the activity of the parasympathetic nervous system. HRV refers to the degree of variation in the interval between heartbeats, reflecting the heart's responsiveness to environmental and internal bodily changes. In a relaxed state, the parasympathetic nervous system dominates, releasing signals that help lower the heart rate, making cardiac activity smoother and gentler. This smoothness is not constant but rather manifests as a rhythmic, natural fluctuation. This fluctuation causes the heart rate interval to vary within a certain time period, and the differences in these variations are relatively large, thus increasing HRV. To illustrate with a numerical example, suppose a person in a state of stress might maintain a heart rate of 90 beats per minute with a relatively fixed heart rate interval. However, in a relaxed state, although the average heart rate may still be close to 90 beats per minute, the heart rate interval will fluctuate significantly, for example, sometimes 0.65 seconds, sometimes 0.7 seconds, sometimes 0.6 seconds, etc. This fluctuation leads to an increase in HRV. Respiratory variability parameters also have the same functional orientation as heart rate variability parameters. By combining heart rate variability parameters and respiratory variability parameters, the user's relaxation state can be more accurately represented.

[0057] Heart rate variability parameters are obtained through the following steps:

[0058] First, heart rate data is measured within a preset time period while the user is at rest. The preset time period is preferably 2-5 minutes. This data is used as the raw data for calculating heart rate variability parameters.

[0059] Next, the time interval between adjacent heartbeats is statistically analyzed to form a heart rate dataset. This heart rate dataset includes the time interval between consecutive adjacent heartbeats within a preset duration. This not only improves accuracy by statistically analyzing continuous heart rate data, but also allows for timely detection of physiological changes in the user after receiving relaxation stimuli, thereby improving the reliability of relaxation parameters.

[0060] Finally, the heart rate variability parameters are obtained by sequentially calculating the cumulative average, variance, and standard deviation of the data in the heart rate dataset. The average of each data in the heart rate dataset is first obtained by accumulating the average, then the variance is calculated by combining each data and the average, and finally the standard deviation is calculated using the variance to form the heart rate variability parameters.

[0061] Specifically:

[0062] First, the preset duration is preferably 3 minutes;

[0063] Then, the time intervals between adjacent heartbeats within a preset duration are monitored to obtain a heart rate dataset including R1, R2...Rx;

[0064] Finally, calculate the average value M = (R1 + R2 + R3 + ... + Rx) / x;

[0065] Calculate the variance V = [(R1-M)² + (R2-M)² + (R3-M)² + (R4-M)² + ... + (Rx-M)²] / x;

[0066] The standard deviation is S, which is calculated using the formula S²=V;

[0067] The standard deviation S is obtained through the above calculation, and the standard deviation S is set as the heart rate variability parameter used to calculate the relaxation parameters.

[0068] The respiratory variability parameters are obtained through the following steps:

[0069] First, respiratory data are measured within a preset time period while the user is at rest. The preset time period is preferably 2-5 minutes. This data is used as the raw data for calculating respiratory variability parameters.

[0070] Next, the number of breaths per minute is counted to form a breathing dataset, which includes the number of breaths per minute within a preset duration. This not only improves accuracy by statistically analyzing breathing data, but also allows for timely detection of physiological changes in the user after receiving relaxation stimuli, thereby enhancing the reliability of relaxation parameters.

[0071] Finally, the respiratory variability parameters are obtained by sequentially calculating the cumulative average, variance, and standard deviation of the data in the respiratory dataset. The average of each data in the respiratory dataset is first obtained by averaging, then the variance is calculated by combining each data and the average, and finally the standard deviation is calculated using the variance to form the respiratory variability parameters.

[0072] The method for calculating respiratory variability parameters is the same as that for calculating respiratory variability parameters. The original data for calculating respiratory variability parameters is the respiratory frequency within a preset time period, from which the respiratory variability parameters are calculated.

[0073] In this embodiment, the preset duration for obtaining respiratory variability parameters and heart rate variability parameters is the same, so that respiratory variability parameters and heart rate variability parameters can be obtained simultaneously.

[0074] In this embodiment, the relaxation model's effect on the user can also be subjectively evaluated by the user based on their subjective feelings, and the conversion parameters can be manually adjusted. This should also be considered a specific implementation method of this embodiment.

[0075] Example 2:

[0076] Compared to Embodiment 1, this embodiment provides a system.

[0077] The system shown in Figure 3 consists of an activity data acquisition module, a physiological data acquisition module, a relaxation module, a processing module, and a data storage module.

[0078] In this embodiment, the activity data acquisition module is used to collect multi-dimensional activity information of users and transmit it to the processing module. This includes wearable smart acquisition devices and human-computer interaction devices. By combining active and passive methods, the module obtains multi-dimensional activity information of users, providing accurate data support for forming a relaxation model that matches the user.

[0079] In this embodiment, the physiological data acquisition module is used to collect the user's physiological data and transmit it to the processing module. The physiological data includes heart rate data and respiratory data. The physiological data acquisition module can be a wearable smart acquisition device or a sensor strip installed on the mattress; both should be considered as specific implementations of this embodiment.

[0080] In this embodiment, the relaxation module includes a massage component, a music component, and an aromatherapy component. By receiving a relaxation model from the processing module, the massage component, music component, and aromatherapy component are controlled to operate independently, thereby applying differentiated relaxation stimuli to the user. Furthermore, the relaxation module can also be a slatted frame, a massage pillow, a humidifier, etc., all of which should be considered specific implementations of this embodiment.

[0081] In this embodiment, the data storage module is used to store the transformation parameters required for the operation of the processing module, relaxation information of each dimension, activity information of each dimension, relaxation threshold, and relaxation parameters obtained from previous detections.

[0082] In this embodiment, the processing module normalizes the multi-dimensional activity information from the activity data acquisition module and calculates a relaxation model to guide the relaxation module's operation by combining the transformation parameters. It also calculates relaxation parameters from the physiological data acquisition module and adjusts these parameters after comparing them with relaxation thresholds. The activity information and relaxation information of each dimension are correlated through cross-setting transformation parameters, ensuring direct correlation and transformation between them, effectively improving the tightness of the correlation.

Claims

1. A relaxation control method based on user activity information data, characterized in that, The method is implemented through the following steps: The first step is to collect multi-dimensional activity information from users, and then process the activity information from each dimension to obtain the corresponding activity data. The second step is to set up multi-dimensional relaxation information, set corresponding conversion parameters between activity data and relaxation information in each dimension, so that activity data in each dimension can be converted into intermediate parameters corresponding to relaxation information in any dimension. The intermediate parameters in the same dimension of relaxation information are accumulated to obtain relaxation data corresponding to that dimension of relaxation information, and the relaxation data in each dimension are combined to form a relaxation model implemented to the user. The third step involves the user receiving relaxation stimuli based on the relaxation model, monitoring the user's relaxation parameters, setting a relaxation threshold, adjusting the conversion parameters based on the relationship between the relaxation parameters and the relaxation threshold, and then adjusting the relaxation model to achieve relaxation parameter adjustment so that the relaxation parameters reach the relaxation threshold.

2. The relaxation control method based on user activity information data according to claim 1, characterized in that, In the first step, set the upper limit value IN_n_max and the lower limit value IN_n_min of the activity information corresponding to each dimension of activity information IN_n, and calculate the activity data Xn of the corresponding dimension, Xn=(IN_n-IN_n_min) / (IN_n_max-IN_n_min), so as to obtain the X dataset containing n activity data.

3. The relaxation control method based on user activity information data according to claim 2, characterized in that, The activity information collected in each dimension is statistically recorded, and the upper limit value IN_n_max and the lower limit value IN_n_min of the activity information for each dimension are obtained from the records; or, the multi-dimensional activity information includes the duration of multiple activities and the exercise intensity that varies among the multiple activities.

4. The relaxation control method based on user activity information data according to claim 1, characterized in that, In the second step, the activity data includes n dimensions, the relaxation information includes m dimensions, and the transformation parameters include n×m. Each dimension of activity data and each dimension of relaxation information has an independent corresponding transformation parameter W_nm. The activity data of n dimensions in the X dataset can be converted into intermediate parameters in the same dimension of relaxation information through the corresponding transformation parameter W_nm. The relaxation information of m dimensions is obtained by repeating the operation.

5. The relaxation control method based on user activity information data according to claim 4, characterized in that, The relaxation information in the same dimension contains n intermediate parameters. The relaxation data used to form the relaxation model is obtained by accumulating the intermediate parameters in each relaxation information. Alternatively, when the activity information is conducive to user relaxation, the conversion parameter W_nm is a negative number; or when the activity information hinders user relaxation, the conversion parameter W_nm is a positive number.

6. The relaxation control method based on user activity information data according to claim 4, characterized in that, The multi-dimensional relaxation information includes at least two of the following: massage duration, massage height, massage frequency, massage location, music volume, music genre, fragrance concentration, and fragrance type.

7. The relaxation control method based on user activity information data according to claim 1, characterized in that, In the third step, after implementing the relaxation model, if the relaxation parameter is less than the relaxation threshold, the pre-relaxation difference is calculated and the conversion parameter is increased. After implementing the recalculated relaxation model: If the relaxation parameter is greater than the relaxation threshold, then record and continue using the current conversion parameter; If the relaxation parameter is less than the relaxation threshold, the conversion parameter is adjusted, the post-relaxation difference is calculated and compared with the pre-relaxation difference. When the post-relaxation difference is less than the pre-relaxation difference, the conversion parameter is continuously increased. When the post-relaxation difference is greater than the pre-relaxation difference, the conversion parameter is decreased.

8. The relaxation control method based on user activity information data according to claim 7, characterized in that, Heart rate variability parameters are obtained by monitoring user heart rate data, and respiratory variability parameters are obtained by monitoring respiratory data. Relaxation parameters are calculated by using the heart rate variability parameters and respiratory variability parameters with preset weight ratios.

9. The relaxation control method based on user activity information data according to claim 8, characterized in that, Heart rate variability parameters can be obtained through the following steps: First, heart rate data is measured within a preset time period while the user is at rest. Then, the time interval between adjacent heartbeats is counted to form a heart rate dataset. Finally, the heart rate dataset is calculated by performing cumulative average, variance, and standard deviation calculations sequentially to obtain the heart rate variability parameters. Alternatively, respiratory variability parameters can be obtained through the following steps: First, respiratory data is measured within a preset time period while the user is at rest. Then, the number of breaths per minute is counted to form a respiratory dataset. Finally, the respiratory dataset is calculated by performing cumulative average, variance, and standard deviation calculations sequentially to obtain the respiratory variability parameters.

10. A system using the relaxation control method according to any one of claims 1-9, characterized in that, include: The activity data acquisition module is used to collect multi-dimensional activity information from users and transmit it to the processing module; The physiological data acquisition module is used to collect the user's physiological data and transmit it to the processing module. The physiological data includes heart rate data and respiratory data. The relaxation module, including massage, music, and aromatherapy components, controls the independent operation of these components by receiving a relaxation model from the processing module, in order to apply differentiated relaxation stimuli to the user. The data storage module is used to store the transformation parameters, relaxation information of each dimension, activity information of each dimension, relaxation threshold, and relaxation parameters obtained from each detection required for the operation of the processing module. The processing module normalizes the multi-dimensional activity information from the activity data acquisition module and calculates a relaxation model to guide the operation of the relaxation module by combining the transformation parameters. It calculates relaxation parameters from the physiological data acquisition module and adjusts the transformation parameters after comparing them with the relaxation threshold.

Images