Sleep intervention optimization method and device, equipment and storage medium

Abstract

The invention discloses a sleep intervention optimization method and device, equipment and a storage medium, and after a user starts a sleep intervention function, an intervention action is executed according to an optimal intervention parameter combination dynamically maintained for the current user. Then, a score reflecting the instant effect of the intervention is quantitatively calculated by comparing user physiological signals collected in a preset time period before and after the intervention action; when the user starts the intervention function next time, the instant effect score and the used parameter combination are stored in a database in an associated mode, the system can utilize the continuously accumulated historical data to conduct learning and updating through an optimization algorithm, and therefore an optimized optimal intervention parameter combination which is more suitable for the user to start the intervention function next time is output. According to the method, the intervention strategy can be continuously and individually adjusted according to the actual physiological response of the user, so that the stability of the sleep aiding and snore stopping effects and the user experience satisfaction degree are remarkably improved. The sleep aid can be widely applied to the technical field of sleep aid.

Description

Sleep intervention optimization methods, devices, equipment and storage media Technical Field

[0001] This application relates to the field of sleep aid technology, and in particular to a sleep intervention optimization method, device, equipment, and storage medium. Background Technology

[0002] With the increasing popularity of smart home and healthy sleep concepts, smart home systems integrating sleep aid and anti-snoring functions, especially smart mattresses, are gradually entering the public eye. These systems, through built-in sensors and actuators, can monitor the user's physiological state and automatically perform interventions such as playing sleep-inducing sounds and adjusting the bed's position, aiming to improve the user's sleep quality.

[0003] In related technologies, the typical workflow of such systems is as follows: when a user enters a sleep state or a specific situation (such as snoring) is detected, corresponding intervention actions are initiated according to a preset program. These intervention actions are often pre-programmed, which lacks the ability to adapt to the individual user's needs. This can easily lead to large fluctuations in the intervention effect between different individuals or in different states of the same user, making it difficult to continuously and stably meet the user's sleep improvement needs.

[0004] In summary, the problems with the relevant technologies urgently need to be addressed. Summary of the Invention

[0005] The purpose of this application is to at least partially solve one of the technical problems existing in the related art.

[0006] Therefore, one objective of the embodiments of this application is to provide a sleep intervention optimization method, apparatus, device, and storage medium.

[0007] To achieve the above-mentioned technical objectives, the technical solution adopted in this application includes: On one hand, this application provides a sleep intervention optimization method, the method comprising: after a user activates a sleep intervention function, performing an intervention action based on the current optimal intervention parameter combination; collecting the user's physiological signals within a preset time period before and after performing the intervention action; determining the immediate effect score corresponding to the intervention action based on the physiological signals; associating the current optimal intervention parameter combination and the immediate effect score with a database for storage, and updating the database using an optimization algorithm to output the optimal intervention parameter combination corresponding to the next time the user activates the sleep intervention function.

[0008] In addition, the sleep intervention optimization method according to the above embodiments of this application may also have the following additional technical features: Further, in one embodiment of this application, the step of performing the intervention action according to the current optimal combination of intervention parameters includes at least one of the following: playing an acoustic signal of a specific mode to the user; wherein the intervention parameters corresponding to the acoustic signal include sound type, frequency content, rhythm and volume; or, controlling the surface structure supporting the user's body to perform a physical movement of a specific mode; wherein the intervention parameters corresponding to the physical movement include movement amplitude, movement frequency and movement mode; or, adjusting the angle of the user's lying posture; wherein the intervention parameters of the angle include adjustment location, adjustment value and adjustment speed.

[0009] Furthermore, in one embodiment of this application, the step of collecting the user's physiological signals during a preset time period before and after performing the intervention includes: collecting the user's heart rate signal, body movement signal, respiratory waveform signal, and snoring signal during the preset time period.

[0010] Furthermore, in one embodiment of this application, determining the immediate effect score corresponding to the intervention action based on the physiological signals includes: determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal; determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal; and performing a weighted summation of the relaxation index score and the ventilation improvement score to obtain the immediate effect score corresponding to the intervention action.

[0011] Further, in one embodiment of this application, determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal includes: using the heart rate signal of a first time period before the intervention action as a baseline, performing linear regression on the heart rate signal of a second time period after the intervention action, and determining the heart rate decrease rate based on the slope of the obtained regression line; calculating a first energy value of the body movement signal of the first time period and a second energy value of the body movement signal of the second time period, and determining an energy decay rate based on the first energy value and the second energy value; and determining the relaxation index score corresponding to the intervention action based on the heart rate decrease rate and the energy decay rate.

[0012] Further, in one embodiment of this application, determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal includes: extracting the amplitude and period of the respiratory waveform signal, and calculating the coefficient of variation of the amplitude and the period; determining the respiratory stability rate based on the coefficient of variation before and after performing the intervention action; determining a first snoring intensity based on the snoring signal of a first time period before performing the intervention action, and determining a second snoring intensity based on the snoring signal of a second time period after performing the intervention action; determining a snoring intensity attenuation rate based on the first snoring intensity and the second snoring intensity; and determining the ventilation improvement score corresponding to the intervention action based on the respiratory stability rate and the snoring intensity attenuation rate.

[0013] Furthermore, in one embodiment of this application, the updating through an optimization algorithm includes: constructing an optimization model representing the user's personalized response relationship based on the historical records stored in the database, taking the combination of intervention parameters as input and the corresponding immediate effect score as output; and solving the optimization model through Gaussian process regression to obtain the optimal combination of intervention parameters corresponding to the next time the user activates the sleep intervention function.

[0014] On the other hand, this application provides a sleep intervention optimization device, which includes: an execution unit, configured to execute an intervention action according to the current optimal intervention parameter combination after the user activates the sleep intervention function; a collection unit, configured to collect the user's physiological signals within a preset time period before and after the execution of the intervention action; a processing unit, configured to determine the instantaneous effect score corresponding to the intervention action based on the physiological signals; and an update unit, configured to associate the current optimal intervention parameter combination and the instantaneous effect score with a database for storage, and update the database using an optimization algorithm to output the optimal intervention parameter combination corresponding to the next time the user activates the sleep intervention function.

[0015] On the other hand, embodiments of this application provide an electronic device, including: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor implements the above-described sleep intervention optimization method.

[0016] On the other hand, embodiments of this application also provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the aforementioned sleep intervention optimization method.

[0017] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the aforementioned sleep intervention optimization method.

[0018] The advantages and beneficial effects of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application: The sleep intervention optimization method, apparatus, device, and storage medium disclosed in the embodiments of this application, when a user activates the sleep intervention function, does not execute a fixed program, but rather performs intervention actions based on an optimal combination of intervention parameters dynamically maintained for the current user. Subsequently, by comparing the user's physiological signals collected within a preset time period before and after the intervention action, a score reflecting the immediate effect of this intervention is quantitatively calculated. This immediate effect score and the parameter combination used are associated and stored in a database. The system can utilize this continuously accumulated historical data to learn and update through optimization algorithms, thereby outputting an optimized optimal combination of intervention parameters more suitable for the user's next activation of the intervention function. This application can continuously and personally adjust the intervention strategy according to the user's actual physiological response, thereby significantly improving the stability of sleep aid and anti-snoring effects and user experience satisfaction. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following description is provided with accompanying drawings of the relevant technical solutions in the embodiments of this application or the prior art. It should be understood that the accompanying drawings described below are only for the purpose of clearly illustrating some embodiments of the technical solutions in this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0020] Figure 1 is a schematic diagram of the implementation environment of a sleep intervention optimization method provided in the embodiments of this application; Figure 2 is a flowchart of a sleep intervention optimization method provided in the embodiments of this application; Figure 3 is a structural schematic diagram of an electronic device provided in the embodiments of this application. Detailed Implementation

[0021] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0022] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0024] With the increasing popularity of smart home and healthy sleep concepts, smart home systems integrating sleep aid and anti-snoring functions, especially smart mattresses, are gradually entering the public eye. These systems, through built-in sensors and actuators, can monitor the user's physiological state and automatically perform interventions such as playing sleep-inducing sounds and adjusting the bed's position, aiming to improve the user's sleep quality.

[0025] In related technologies, the typical workflow of such systems is as follows: when a user enters a sleep state or a specific situation (such as snoring) is detected, corresponding intervention actions are initiated according to a preset program. These intervention actions are often pre-programmed, which lacks the ability to adapt to the individual user's needs. This can easily lead to large fluctuations in the intervention effect between different individuals or in different states of the same user, making it difficult to continuously and stably meet the user's sleep improvement needs.

[0026] In view of this, this application provides a sleep intervention optimization method, apparatus, device, and storage medium. When a user activates the sleep intervention function, the system does not execute a fixed program, but instead performs intervention actions based on an optimal combination of intervention parameters dynamically maintained for the current user. Subsequently, by comparing the user's physiological signals collected within a preset time period before and after the intervention action, a score reflecting the immediate effect of the intervention is quantitatively calculated. This immediate effect score and the parameter combination used are associated and stored in a database. The system can utilize this continuously accumulated historical data to learn and update through optimization algorithms, thereby outputting an optimized optimal combination of intervention parameters more suitable for the user's next activation of the intervention function. This application can continuously and personally adjust the intervention strategy according to the user's actual physiological response, thereby significantly improving the stability of sleep aid and anti-snoring effects and user experience satisfaction.

[0027] Please refer to Figure 1, which shows a schematic diagram of the implementation environment of a sleep intervention optimization method provided in this embodiment. In this implementation environment, the main hardware and software components involved include an electronic device 110 and a backend server 120. The electronic device 110 and the backend server 120 are connected by communication.

[0028] Specifically, the sleep intervention optimization method provided in this application embodiment can be executed independently on the electronic device 110 or based on data interaction between the electronic device 110 and the backend server 120. The electronic device 110 can be a dedicated control unit integrated inside the mattress, such as an ARM-based processor, which directly connects to various sensors (such as heart rate, breathing, and pressure sensors) and actuators inside the mattress; the backend server 120 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0029] The electronic device 110 and the backend server 120 can establish a communication connection via a wireless network or a wired network. This wireless or wired network uses standard communication technologies and / or protocols. The network can be the Internet or any other network, including but not limited to any combination of Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, wired or wireless networks, private networks, or virtual private networks.

[0030] Of course, it is understood that the implementation environment in Figure 1 is only one of the optional application scenarios of the sleep intervention optimization method provided in the embodiments of this application, and the actual application is not fixed to the hardware and software environment shown in Figure 1.

[0031] Below, in conjunction with the aforementioned description of the implementation environment, a sleep intervention optimization method provided in the embodiments of this application will be introduced and explained.

[0032] Please refer to Figure 2, which is a schematic diagram of a sleep intervention optimization method provided in an embodiment of this application. The sleep intervention optimization method includes, but is not limited to: step 210, after the user activates the sleep intervention function, performing an intervention action according to the current optimal intervention parameter combination; step 220, collecting the user's physiological signals within a preset time period before and after performing the intervention action; step 230, determining the immediate effect score corresponding to the intervention action based on the physiological signals; step 240, associating the current optimal intervention parameter combination and the immediate effect score with the database for storage, and updating it through an optimization algorithm to output the optimal intervention parameter combination corresponding to the next time the user activates the sleep intervention function.

[0033] This application provides a sleep intervention optimization method. This method constructs a closed-loop adaptive optimization system, the process of which can be summarized as follows: After performing an intervention, the system collects and analyzes changes in the user's physiological signals to quantitatively evaluate the immediate effect of the intervention; then, the effect score is associated with and stored with the parameters used, and the data is learned and updated using an optimization algorithm, thereby dynamically outputting the optimal parameter combination suitable for the user's next intervention. This method realizes the transformation from fixed-procedure intervention to continuous personalized optimization based on physiological feedback, significantly improving the accuracy and adaptability of sleep intervention.

[0034] The following describes and explains a sleep intervention optimization method provided in the embodiments of this application, with specific steps and procedures.

[0035] In step 210, after the user activates the sleep intervention function, the system executes the intervention action based on the current optimal combination of intervention parameters. This step is the starting point for the system to implement the intervention. It should be noted that the "optimal combination of intervention parameters" in this embodiment is a dynamic concept. It is not fixed, but rather a set of parameters that the system calculates based on the user's historical data on intervention effects and is considered to be the most effective for the user at the current moment.

[0036] Specifically, the intervention parameter combination defines the execution characteristics of the intervention action, and its specific content can be determined according to the type of intervention action. For example, if several pre-actions involve playing white noise, the parameters may include the center frequency, bandwidth, and volume of the sound; if several pre-actions involve bed body rhythm, the parameters may include the amplitude, frequency, and waveform of the rhythm. In this embodiment, the system can precisely execute the intervention by calling the corresponding actuator (such as a speaker or motor) and according to the settings of this parameter combination, ensuring that each intervention is highly targeted and customizable.

[0037] In step 220, physiological signals of the user are collected during a preset time period before and after the intervention. This provides an objective and quantitative data basis for subsequent effect evaluation.

[0038] In this embodiment, to accurately capture the physiological changes brought about by the intervention, the system needs to establish a physiological baseline before the intervention is performed and continuously monitor the trend of physiological signal changes after the intervention. Specifically, during a short period (e.g., 1-2 minutes) before the intervention begins, the system can simultaneously collect raw physiological signals such as the user's heart rate, body movement, respiratory waveform, and snoring through various sensors built into or integrated into the mattress (e.g., ECG sensors, bio-radar, pressure distribution sensors, microphone arrays, etc.). Furthermore, during a specific period (e.g., 3-5 minutes) after the intervention begins, the system will continue to collect these signals. This before-and-after data collection strategy allows the system to effectively separate the physiological effects produced by the intervention itself, creating conditions for subsequent precise quantitative evaluation.

[0039] In step 230, the immediate effect score corresponding to the intervention action is determined based on the collected physiological signals. In this embodiment, the purpose of determining the immediate effect score is to transform the multidimensional, raw physiological signals collected in step 220 into a single quantitative indicator that can comprehensively and intuitively reflect the immediate effect of the intervention, so as to facilitate the evaluation of the effect of the intervention action.

[0040] Specifically, the system can compare and analyze physiological signals before and after intervention using built-in signal processing algorithms and evaluation models to extract key feature changes that characterize a shift in physiological state towards relaxation or improved ventilation. Finally, the system standardizes these extracted physiological feature changes and inputs them into a weighted fusion model, outputting a scalar value within a predetermined range (e.g., 0-100 points), known as the "immediate effect score." A higher score indicates a more significant positive physiological effect of the intervention parameter combination on the user in the current environment. Of course, in this embodiment, the specific range of the immediate effect score is not limited and can be flexibly set according to actual needs.

[0041] In step 240, the current optimal combination of intervention parameters and the immediate effect score generated by this intervention action are linked together and stored as a complete record in the user's personalized database. The stored data is then learned and updated through an optimization algorithm to output the optimal combination of intervention parameters for the next time the user activates the sleep intervention function.

[0042] In this embodiment, each sleep intervention task and its effect for a user constitutes a data point, which is added to the user's personalized database. This database, maintained by the system, essentially constructs a personalized response function mapping from the "intervention parameter space" to the "effect score." Based on this, relevant optimization algorithms (such as Bayesian optimization) can be used to model and learn this mapping. The algorithm intelligently analyzes existing data, weighing the use of (selecting the best-performing parameters from historical records) against exploration (trying new parameters with potential), thereby recommending a new parameter combination most likely to improve the effect score for the next intervention. Through this continuous "execution-evaluation-learning" cycle, the system can gradually adapt to the user's unique physiological response pattern, causing the intervention strategy to continuously tend towards a personalized optimal solution.

[0043] It is understood that the sleep intervention optimization method provided in this application does not execute a fixed program when the user activates the sleep intervention function. Instead, it executes the intervention action based on the optimal combination of intervention parameters dynamically maintained for the current user. Subsequently, by comparing the user's physiological signals collected within a preset time period before and after the intervention action, a score reflecting the immediate effect of this intervention is quantitatively calculated. This immediate effect score and the parameter combination used will be associated and stored in a database. The system can use this continuously accumulated historical data to learn and update through optimization algorithms, thereby outputting an optimized optimal combination of intervention parameters that is more suitable for the user's next activation of the intervention function. This application can continuously and personally adjust the intervention strategy according to the user's actual physiological response, thereby significantly improving the stability of sleep aid and anti-snoring effects and user experience satisfaction.

[0044] Specifically, in some embodiments, the step of performing the intervention action according to the current optimal combination of intervention parameters includes at least one of the following: playing an acoustic signal of a specific pattern to the user; wherein the intervention parameters corresponding to the acoustic signal include sound type, frequency content, rhythm, and volume; or controlling the surface structure supporting the user's body to perform a physical movement of a specific pattern; wherein the intervention parameters corresponding to the physical movement include movement amplitude, movement frequency, and movement pattern; or adjusting the angle of the user's lying posture; wherein the intervention parameters of the angle include the adjustment location, adjustment value, and adjustment.

[0045] In this embodiment, the specific implementation of the intervention action can include multiple methods, and correspondingly, the intervention parameters that can be set for each intervention action can also include multiple methods. In this way, different types of execution units can be flexibly driven to implement the intervention based on the determined optimal combination of intervention parameters.

[0046] For example, in some embodiments, the intervention may manifest as playing a specially designed acoustic signal to the user, the properties of which are defined by a set of intervention parameters, such as the type of sound used (e.g., white noise, pink noise, or natural soundscape), the core distribution of its frequency content, the playback tempo, and the output volume. In some embodiments, the intervention may manifest as controlling a surface structure supporting the user's body (e.g., a mattress) to produce a specific pattern of physical movement, characterized by intervention parameters such as the amplitude, frequency, and pattern of movement (e.g., uniform fluctuation or simulated breathing). Specifically, this function can be achieved through a mattress with airbags, for example, a mattress with multiple independently inflatable and deflated airbag units. By precisely adjusting the air pressure and timing of changes in different airbag units through a control system, the desired overall movement pattern can be synthesized to gently and smoothly facilitate the user's body movement. In other embodiments, the intervention may also manifest as the automated adjustment of the user's lying posture angle, such as changing the user's posture by raising the back or legs. The adjustment behavior is precisely controlled by intervention parameters such as the specific adjustment location, the required angle value, and the speed at which the adjustment is completed. Specifically, this function can be achieved through an electric bed. For example, the bed surface of such an electric bed consists of multiple independently movable bed boards, each of which is connected to an electric actuator as a drive unit. By controlling the extension and retraction of the corresponding electric actuator, a specific bed board (such as the back or leg bed board) can be smoothly flipped or raised, thereby achieving precise and automated posture adjustment.

[0047] It should be noted that the above intervention actions can be applied individually or in combination. In this embodiment, the system can call the corresponding audio playback module, motor drive module or posture adjustment mechanism to accurately execute the intervention instructions defined by the combination of intervention parameters, thereby achieving multi-dimensional and refined adjustment of the user's sleep state.

[0048] Specifically, in some embodiments, determining the immediate effect score corresponding to the intervention action based on the physiological signals includes: determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal; determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal; and performing a weighted summation of the relaxation index score and the ventilation improvement score to obtain the immediate effect score corresponding to the intervention action.

[0049] As described above, in the embodiments of this application, the collected physiological signals may include, but are not limited to, the user's heart rate signal, body movement signal, respiratory waveform signal, and snoring signal. Therefore, when determining the immediate effect score corresponding to the intervention action based on physiological signal analysis, targeted scores can be calculated by analyzing the specific state changes reflected by different physiological signals, and then information fusion can be performed to obtain a comprehensive immediate effect score.

[0050] Specifically, in this embodiment, the sedative and relaxation effects of the intervention can be evaluated. By analyzing the decreasing trend of heart rate in the heart rate signal and the attenuation of physical activity level reflected in the body movement signal, a relaxation index score is calculated to characterize the user's transition from tension to relaxation. Simultaneously, the improvement effect of the intervention on airway patency can be evaluated in parallel. By analyzing the stability changes of the respiratory waveform signal and the intensity attenuation characteristics of the snoring signal, a ventilation improvement score is calculated to characterize the reduction of upper airway resistance and the optimization of ventilation. Finally, the system integrates the two scores, respectively from the perspectives of the autonomic nervous system state and the airway physical state, through a preset weighted summation model to generate a unified quantitative score that comprehensively reflects the overall immediate effect of the intervention. This score serves as the core feedback signal, providing a precise and reliable basis for subsequent parameter optimization algorithms.

[0051] Specifically, in some embodiments, determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal includes: using the heart rate signal of a first time period before the intervention action as a baseline, performing linear regression on the heart rate signal of a second time period after the intervention action, and determining the heart rate decrease rate based on the slope of the obtained regression line; calculating a first energy value of the body movement signal in the first time period and a second energy value of the body movement signal in the second time period, and determining the energy decay rate based on the first energy value and the second energy value; and determining the relaxation index score corresponding to the intervention action based on the heart rate decrease rate and the energy decay rate.

[0052] In this application embodiment, a process for calculating a relaxation index score is provided, which embodies a precise method for dynamic trend analysis and quantitative comparison of physiological signals.

[0053] Specifically, in this embodiment, a slope analysis technique based on regression is introduced for processing heart rate signals. Heart rate data from the first time period before the intervention is used as a baseline reflecting the user's initial state. Then, linear regression analysis is performed on the heart rate data from the second time period after the intervention. The slope of the resulting regression line represents the rate of heart rate decline. A negative slope with a larger absolute value indicates a faster and more pronounced transition of the heart rate towards a relaxed state. Simultaneously, the system processes body movement signals in parallel, using energy analysis to calculate the total energy or specific frequency band energy of the body movement signals in the first time period before and the second time period after the intervention. The energy decay rate is calculated by comparing these two energy values, which directly reflects the extent of the decrease in the user's muscle activity level.

[0054] Finally, the two key quantitative indicators extracted from the cardiovascular system and the somatic motor system respectively—the rate of heart rate decline and the rate of body energy decay—can be input into a pre-set evaluation model. This model combines these two heterogeneous but related physiological trend indicators into a single, standardized relaxation index score through standardization and weighted fusion steps, thereby achieving an objective and repeatable quantitative evaluation of the relaxation effect induced by the intervention.

[0055] Specifically, in some embodiments, determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal includes: extracting the amplitude and period of the respiratory waveform signal, and calculating the coefficient of variation of the amplitude and the period; determining the respiratory stability rate based on the coefficient of variation before and after performing the intervention action; determining a first snoring intensity based on the snoring signal of a first time period before performing the intervention action, and determining a second snoring intensity based on the snoring signal of a second time period after performing the intervention action; determining the snoring intensity attenuation rate based on the first snoring intensity and the second snoring intensity; and determining the ventilation improvement score corresponding to the intervention action based on the respiratory stability rate and the snoring intensity attenuation rate.

[0056] In this embodiment of the application, a process for determining a ventilation improvement score is also provided, which embodies a strategy for comprehensively assessing the upper respiratory tract status from two physical dimensions: respiratory rhythm regularity and airway ventilation noise.

[0057] Specifically, in this embodiment, the respiratory waveform signal is first subjected to in-depth feature extraction and stability analysis. By calculating the amplitude variation coefficient and period variation coefficient of the respiratory waveform in the first time period before intervention, the degree of respiratory irregularity caused by partial airway obstruction is quantified. After intervention, the system also calculates the corresponding variation coefficient in the second time period, and accurately calculates the respiratory stability rate by comparing the changes of these two variation coefficients before and after intervention. The increase in this ratio directly reflects the good trend of the respiratory pattern changing from disordered and irregular to stable and uniform. At the same time, acoustic energy analysis can be performed on the snoring signal. The acoustic energy of specific low-frequency bands characterizing snoring features in the first time period before intervention and the second time period after intervention are extracted and defined as the first snoring intensity and the second snoring intensity, respectively. Then, the snoring intensity attenuation rate is calculated. This ratio effectively characterizes the degree of reduction of noise generated by airway tissue vibration.

[0058] Ultimately, the improvement in respiratory mechanics represented by the respiratory stability rate and the improvement in airway patency represented by the snoring intensity attenuation rate—two physiologically closely related and mutually reinforcing indicators—can be fused together. A specific computational model can then be used to generate a ventilation improvement score, thereby providing an objective quantitative measure of the immediate effect of anti-snoring interventions on restoring airway patency.

[0059] Specifically, in some embodiments, the updating through optimization algorithms includes: constructing an optimization model representing the user's personalized response relationship based on historical records stored in the database, taking the combination of intervention parameters as input and the corresponding immediate effect score as output; and solving the optimization model through Gaussian process regression to obtain the optimal combination of intervention parameters corresponding to the next time the user activates the sleep intervention function.

[0060] In this embodiment, each historical record stored in the database can be considered as a set of observation sample points. Each observation sample point consists of a specific combination of intervention parameters (input) and its resulting immediate effect score (output). Based on these observation sample points, a surrogate model characterizing the user's unique physiological response characteristics can be constructed using Gaussian process regression. This model can not only fit the effect of known parameter points, but more importantly, it can predict the effect of parameter points in unknown regions with an uncertainty measure, that is, it simultaneously provides the mean of the predicted effect score and the degree of confidence (variance) in the prediction. When it is necessary to determine parameters for the next intervention, the optimization algorithm does not simply select the parameters corresponding to the highest historical score, but rather solves for recommended parameters by maximizing the acquisition function (e.g., the expected improvement function) based on this Gaussian process model. The value of this acquisition function increases in regions with good predicted effects (encouraging the use of known good parameters) and high uncertainty (encouraging the exploration of untried regions), thereby intelligently balancing the contradiction between using existing parameter combinations and exploring unknown parameter combinations. The parameter combination recommended through this process is the new attempt that is most likely to improve the intervention effect under the current understanding, and can be used as the optimal intervention parameter combination for the next initiation of the sleep intervention function. By repeating this process, we can gradually approach the optimal intervention strategy for the user, which can effectively improve the personalized experience of sleep intervention.

[0061] This application embodiment also provides a sleep intervention optimization device, the device comprising: an execution unit, configured to execute an intervention action according to the current optimal intervention parameter combination after the user activates the sleep intervention function; a collection unit, configured to collect the user's physiological signals within a preset time period before and after the execution of the intervention action; a processing unit, configured to determine the instantaneous effect score corresponding to the intervention action based on the physiological signals; and an update unit, configured to associate the current optimal intervention parameter combination and the instantaneous effect score with a database for storage, and update the database using an optimization algorithm to output the optimal intervention parameter combination corresponding to the next time the user activates the sleep intervention function.

[0062] Referring to FIG3, an embodiment of this application provides an electronic device, including: at least one processor 310; at least one memory 320 for storing at least one program; when the at least one program is executed by the at least one processor 310, the at least one processor 310 implements the above-described sleep intervention optimization method.

[0063] Similarly, the content of the above method embodiments is applicable to the embodiments of this electronic device. The specific functions implemented by the embodiments of this electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0064] This application embodiment also provides a computer-readable storage medium storing a program executable by a processor 310, which, when executed by the processor 310, is used to perform the aforementioned sleep intervention optimization method.

[0065] Similarly, the content of the above method embodiments is applicable to the present computer-readable storage medium embodiments. The specific functions implemented by the present computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0066] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the above-described sleep intervention optimization method.

[0067] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0068] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0069] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0071] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0072] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0073] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0074] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0075] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for optimizing sleep intervention, characterized in that, The method includes: after a user activates the sleep intervention function, performing an intervention action based on the current optimal combination of intervention parameters; collecting the user's physiological signals within a preset time period before and after the intervention action; determining the immediate effect score corresponding to the intervention action based on the physiological signals; associating the current optimal combination of intervention parameters and the immediate effect score with a database for storage, and updating the database using an optimization algorithm to output the optimal combination of intervention parameters for the next time the user activates the sleep intervention function.

2. The sleep intervention optimization method according to claim 1, characterized in that, The intervention action performed according to the current optimal combination of intervention parameters includes at least one of the following: playing an acoustic signal of a specific pattern to the user; wherein the intervention parameters corresponding to the acoustic signal include sound type, frequency content, rhythm, and volume; or controlling the surface structure supporting the user's body to perform a physical movement of a specific pattern; wherein the intervention parameters corresponding to the physical movement include movement amplitude, movement frequency, and movement pattern; or adjusting the angle of the user's lying posture; wherein the intervention parameters of the angle include the adjustment location, adjustment value, and adjustment speed.

3. The sleep intervention optimization method according to claim 1, characterized in that, The process of collecting the user's physiological signals during a preset time period before and after the intervention includes collecting the user's heart rate signal, body movement signal, respiratory waveform signal, and snoring signal during the preset time period.

4. The sleep intervention optimization method according to claim 3, characterized in that, The step of determining the immediate effect score corresponding to the intervention action based on the physiological signals includes: determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal; determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal; and performing a weighted summation of the relaxation index score and the ventilation improvement score to obtain the immediate effect score corresponding to the intervention action.

5. The sleep intervention optimization method according to claim 4, characterized in that, The step of determining the relaxation index score corresponding to the intervention action based on the heart rate signal and the body movement signal includes: using the heart rate signal of a first time period before the intervention action as a baseline, performing linear regression on the heart rate signal of a second time period after the intervention action, and determining the heart rate decrease rate based on the slope of the obtained regression line; calculating a first energy value of the body movement signal of the first time period and a second energy value of the body movement signal of the second time period, and determining the energy decay rate based on the first energy value and the second energy value; and determining the relaxation index score corresponding to the intervention action based on the heart rate decrease rate and the energy decay rate.

6. The sleep intervention optimization method according to claim 4, characterized in that, The step of determining the ventilation improvement score corresponding to the intervention action based on the respiratory waveform signal and the snoring signal includes: extracting the amplitude and period of the respiratory waveform signal, and calculating the coefficient of variation of the amplitude and the period; determining the respiratory stability rate based on the coefficient of variation before and after the intervention action; determining the first snoring intensity based on the snoring signal of the first time period before the intervention action, and determining the second snoring intensity based on the snoring signal of the second time period after the intervention action; determining the snoring intensity attenuation rate based on the first snoring intensity and the second snoring intensity; and determining the ventilation improvement score corresponding to the intervention action based on the respiratory stability rate and the snoring intensity attenuation rate.

7. A sleep intervention optimization method according to any one of claims 1-6, characterized in that, The update via optimization algorithm includes: constructing an optimization model representing the user's personalized response relationship based on the historical records stored in the database, taking the combination of intervention parameters as input and the corresponding instant effect score as output; and solving the optimization model through Gaussian process regression to obtain the optimal combination of intervention parameters for the next time the user activates the sleep intervention function.

8. A sleep intervention and optimization device, characterized in that, The device includes: an execution unit, configured to execute an intervention action based on the current optimal combination of intervention parameters after the user activates the sleep intervention function; a data acquisition unit, configured to acquire the user's physiological signals within a preset time period before and after the execution of the intervention action; a processing unit, configured to determine the immediate effect score corresponding to the intervention action based on the physiological signals; and an update unit, configured to associate the current optimal combination of intervention parameters and the immediate effect score with a database for storage, and update the database using an optimization algorithm to output the optimal combination of intervention parameters for the next time the user activates the sleep intervention function.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; when said at least one program is executed by said at least one processor, said at least one processor implements a sleep intervention optimization method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to implement a sleep intervention optimization method as described in any one of claims 1-7.

Images