Intelligent bed dynamic regulation method and device based on physiological signals

Abstract

The application discloses a physiological signal-based intelligent bed dynamic regulation method and device, relates to the field of sleep monitoring and regulation, collects physiological signals such as electrocardiogram, respiration and body movement of a user and a head pressure distribution signal, constructs a current state vector of the user according to the physiological signals and the head pressure distribution signal, calculates a control vector according to the state vector, the control vector including a target bed head angle, a target disturbance amplitude, a target disturbance frequency, a target light brightness and a target vibration intensity, adjusts the bed head angle to the target bed head angle by a bed head execution mechanism according to the control vector, applies a swing disturbance to the swing execution mechanism at the target amplitude and the target frequency, adjusts the light brightness to the target light brightness by the light execution mechanism, and outputs the vibration stimulation with the target vibration intensity by the vibration execution mechanism. The angle adjustment, the mechanical disturbance, the light change and the vibration stimulation are cooperatively matched to guide the user to transit to deep sleep, and active regulation based on the physiological state is realized to effectively improve the sleep quality.

Description

Technical Field

[0001] This application relates to the field of sleep monitoring and regulation, and in particular to a method and device for dynamic regulation of a smart bed based on physiological signals. Background Technology

[0002] Existing smart bed systems primarily focus on two aspects: environmental regulation and physiological monitoring. Regarding environmental regulation, they automatically adjust indoor lighting brightness, control audio equipment to play sleep-aiding audio, or adjust the headboard support angle via electromechanical structures to enhance the user's physical comfort while lying down. These adjustments are based on environmental physical parameters or user-preset values, aiming to create suitable external conditions for sleep. In terms of physiological monitoring, existing systems utilize radar or wearable devices to collect physiological characteristic data such as heart rate, respiratory rate, and body movement while the user is in bed. After statistical analysis, they generate a sleep quality report including indicators such as deep sleep duration and sleep efficiency, which is then presented to the user. The core of these systems lies in data collection and information presentation.

[0003] However, in existing smart bed systems, the physiological monitoring and environmental regulation functions operate independently. The physiological data acquired by the physiological monitoring module is only used for post-event statistical analysis and report generation, and is not input as feedback signals into the control logic of the environmental regulation module. Therefore, the environmental regulation module cannot adaptively and dynamically adjust based on the user's current physiological state. This disconnect between monitoring and regulation means the system can only observe and record the user's sleep process, but cannot proactively intervene in the regulation process based on the user's physiological state, making it difficult to effectively improve the user's sleep quality.

[0004] Therefore, how to regulate sleep based on the user's physiological state to effectively improve sleep quality is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method and device for dynamic regulation of a smart bed based on physiological signals, which solves the problem that the monitoring and regulation are separated, resulting in the system only being able to observe and record the user's sleep process, but unable to actively intervene in the regulation process based on the user's physiological state, making it difficult to effectively improve the user's sleep quality.

[0006] To address the aforementioned technical problems, this application provides a method for dynamic control of an intelligent bed based on physiological signals, comprising: Collect the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals, and body movement signals; Construct the user's current state vector based on the physiological signals and the head pressure distribution signal; The current control vector is calculated based on the state vector; wherein the control vector includes at least the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity; The headboard actuator is controlled to adjust the headboard angle to the target headboard angle, the swing actuator is controlled to apply swing disturbance with the target disturbance amplitude and the target disturbance frequency, the lighting actuator is controlled to adjust the lighting brightness to the target lighting brightness, and the vibration actuator is controlled to output vibration stimulation with the target vibration intensity.

[0007] In one optional embodiment, constructing the user's current state vector based on the physiological signals and the head pressure distribution signal includes: Heart rate variability is determined based on the electrocardiogram signal; The respiratory rate is determined based on the respiratory signal; The intensity of body movement is determined based on the body movement signal; Determine the head pressure distribution matrix based on the head pressure distribution signal; The heart rate variability, respiratory rate, body motion intensity, and head pressure distribution matrix constitute the state vector.

[0008] In one optional embodiment, calculating the current control vector based on the state vector includes: Calculate the sleep stability index and cervical spine support deviation index based on the state vector; The target headboard angle is calculated based on the cervical spine support deviation index. The pressure gradient vector is determined based on the head pressure distribution matrix, and the adjustment direction of the target head angle is determined based on the pressure gradient vector. The target disturbance amplitude is calculated based on the sleep stability index, and the target disturbance frequency is calculated based on the respiratory rate; The target respiratory rate is determined based on the heart rate variability, and the target light brightness and the target vibration intensity are determined based on the target respiratory rate.

[0009] In one optional embodiment, calculating the sleep stability index and the cervical spine support deviation index based on the state vector includes: The heart rate variability is normalized to obtain normalized heart rate variability. Calculate the respiratory rate variance based on multiple respiratory rates within a preset time window; The actual pressure center coordinates are determined based on the head pressure distribution matrix. The sleep stability index is calculated based on the normalized heart rate variability, the respiratory rate variance, and the body movement intensity. The cervical spine support deviation index is calculated based on the actual pressure center coordinates and the preset ideal head position coordinates.

[0010] In an optional embodiment, the sleep stability index is calculated based on the normalized heart rate variability, the respiratory rate variance, and the body movement intensity, including: The sleep stability index is calculated based on the first preset formula; The first preset formula is: SSI = w1·HRV_norm + w2·(1 / Var_RR) - w3·Motion; Wherein, SSI is the sleep stability index, HRV_norm is the normalized heart rate variability, Var_RR is the respiratory rate variance, Motion is the body movement intensity, w1 is the first weighting coefficient, w2 is the second weighting coefficient, and w3 is the third weighting coefficient.

[0011] In one optional embodiment, the cervical spine support deviation index is calculated based on the actual pressure center coordinates and the preset ideal head position coordinates, including: The cervical spine support deviation index is calculated based on the second preset formula; The second preset formula is: CSI = √((xc-x0)² + (yc-y0)²); Wherein, CSI is the cervical spine support deviation index, (xc, yc) are the coordinates of the actual pressure center, and (x0, y0) are the coordinates of the ideal head position.

[0012] In one optional embodiment, calculating the target headboard angle based on the cervical spine support deviation index includes: The target headboard angle is calculated according to the third preset formula; The third preset formula is: θ_target = θ_base + k·CSI; Wherein, θ_target is the target headboard angle, θ_base is the preset base headboard angle, CSI is the cervical spine support deviation index, and k is the preset adjustment coefficient.

[0013] In one optional embodiment, calculating the target perturbation amplitude based on the sleep stability index and calculating the target perturbation frequency based on the respiratory rate includes: The target disturbance amplitude is calculated according to the fourth preset formula; The fourth preset formula is: A = A0 + α·(1-SSI); Where A is the target perturbation amplitude, A0 is the preset base perturbation amplitude, SSI is the sleep stability index, and α is the gain coefficient; The target disturbance frequency is calculated according to the fifth preset formula; The fifth preset formula is: f = β·RR; Where f is the target disturbance frequency, RR is the breathing frequency, and β is the coupling coefficient.

[0014] In one optional embodiment, determining the target respiratory rate based on the heart rate variability, and determining the target light brightness and the target vibration intensity based on the target respiratory rate, includes: The target respiratory rate is calculated according to the sixth preset formula; The sixth preset formula is: f_target = f0 - γ·(HRV0 - HRV); Where f_target is the target respiratory rate, f0 is the preset baseline respiratory rate, γ is the proportional gain, HRV0 is the heart rate variability baseline, and HRV is the heart rate variability. If the target respiratory rate is greater than the upper limit of the preset respiratory rate range, then the target respiratory rate is taken as the upper limit. If the target respiratory rate is less than the lower limit of the preset respiratory rate range, then the target respiratory rate is taken as the lower limit. If the target respiratory rate is within the preset respiratory rate range, then the target respiratory rate remains unchanged; The brightness of the target light is calculated according to the seventh preset formula; The seventh preset formula is: L(t) = L0 + ΔL·sin(2π·f_target·t); Where L(t) is the target light brightness at time t, L0 is the preset base brightness, ΔL is the preset brightness variation range, f_target is the target breathing frequency, and t is time; The target vibration intensity is calculated according to the eighth preset formula; The eighth preset formula is: V(t) = V0·sin(2π·f_target·t); Where V(t) is the target vibration intensity at time t, V0 is the preset vibration intensity, f_target is the target breathing frequency, and t is time.

[0015] This application also provides a smart bed dynamic control device based on physiological signals, comprising: The acquisition module is used to acquire the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals, and body movement signals; The construction module is used to construct the user's current state vector based on the physiological signals and the head pressure distribution signal; The calculation module is used to calculate the current control vector based on the state vector; wherein the control vector includes at least the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity; The control module is used to control the headboard actuator to adjust the headboard angle to the target headboard angle, control the swing actuator to apply swing disturbance with the target disturbance amplitude and target disturbance frequency, control the lighting actuator to adjust the lighting brightness to the target lighting brightness, and control the vibration actuator to output vibration stimulation with the target vibration intensity.

[0016] This application provides a dynamic control method for a smart bed based on physiological signals. It collects multi-dimensional physiological signals from the user, including electrocardiogram, respiration, and body movement, as well as head pressure distribution signals. Based on these signals, a current state vector is constructed. The current control vector is then calculated from this state vector, specifically including the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity. This control vector is distributed to various actuators to control the headboard actuator to adjust the headboard angle to the target angle, the swing actuator to apply swing disturbances with the target amplitude and frequency, the light actuator to adjust the light brightness to the target brightness, and the vibration actuator to output vibration stimulation with the target vibration intensity. The angle adjustment, mechanical disturbance, light changes, and vibration stimulation work in synergy to guide the user into deep sleep, forming a complete control process. Unlike existing smart beds that only record data without intervention, this application actively controls sleep based on physiological state to effectively improve sleep quality.

[0017] The beneficial effects and methods of the intelligent bed dynamic control device based on physiological signals provided in this application are as described above. Attached Figure Description

[0018] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for dynamic control of an intelligent bed based on physiological signals, provided as an embodiment of this application; Figure 2 A structural diagram of a smart bed dynamic control device based on physiological signals provided in an embodiment of this application; Figure 3 This is a structural diagram of another intelligent bed dynamic control device based on physiological signals provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0021] The core of this application is to provide a method and device for dynamic regulation of a smart bed based on physiological signals, which is used to regulate the user's physiological state to effectively improve sleep quality.

[0022] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] Figure 1 A flowchart illustrating a method for dynamic control of an intelligent bed based on physiological signals, as provided in this application embodiment, is shown below. Figure 1 As shown, a method for dynamic regulation of an intelligent bed based on physiological signals includes: S10: Collect the user's physiological signals and head pressure distribution signals; among which, the physiological signals include at least electrocardiogram signals, respiratory signals and body movement signals.

[0024] S11: Construct the user's current state vector based on physiological signals and head pressure distribution signals.

[0025] S12: Calculate the current control vector based on the state vector; wherein the control vector includes at least the target head angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity.

[0026] S13: Control the headboard actuator to adjust the headboard angle to the target headboard angle, control the swing actuator to apply swing disturbance with the target disturbance amplitude and target disturbance frequency, control the lighting actuator to adjust the lighting brightness to the target lighting brightness, and control the vibration actuator to output vibration stimulation with the target vibration intensity.

[0027] In step S10, the physiological signals include at least electrocardiogram (ECG) signals, respiratory signals, and body movement signals. The ECG signal is collected by a photoplethysmography (PPG) sensor in the user's watch or wristband, and heart rate and heart rate variability are extracted through signal processing. The respiratory signal is collected by radar sensors installed on both sides of the bed, and respiratory waveforms are extracted by detecting the user's chest and abdominal micro-movements, thereby calculating the respiratory rate. The body movement signal is collected by an inertial measurement unit built into the watch or wristband, and body movement intensity is extracted by analyzing triaxial acceleration data. The head pressure distribution signal is collected by an array-type thin-film pressure sensor under the pillow. This array-type pressure sensor consists of multiple pressure sensing units arranged in rows and columns. When the user's head is placed on the pillow, each sensing unit detects the pressure value at its corresponding position, forming pressure distribution data corresponding to the head contact area.

[0028] In step S11, the user's current state vector S(t) is constructed based on physiological signals and head pressure distribution signals. Specifically, this includes: determining heart rate variability (HRV) based on electrocardiogram (ECG) signals, and also determining heart rate (HR) based on ECG signals; determining respiratory rate (RR) based on respiratory signals; determining body movement intensity (Motion) based on body movement signals; and determining the head pressure distribution matrix P(x,y) based on head pressure distribution signals. Heart rate variability, respiratory rate, body movement intensity, and head pressure distribution matrix constitute the state vector S(t) = {HR, HRV, RR, Motion, P(x,y)}. This state vector constitutes a multi-dimensional quantitative representation of the user's current sleep state, serving as the input basis for subsequent control vector calculation.

[0029] Determining heart rate based on electrocardiogram (ECG) signals includes: identifying the location of R waves based on ECG signals, counting the number of R waves within a preset time window, and dividing the number of R waves by the duration of the preset time window to obtain the heart rate.

[0030] Determining heart rate variability based on electrocardiogram (ECG) signals includes: identifying the R-wave position based on the ECG signal, calculating the time interval between adjacent R-waves to obtain the RR interval sequence; performing time-domain analysis on the RR interval sequence, calculating the root mean square (RMS) of the difference between adjacent RR intervals, and using the RMS as the heart rate variability. The RR interval refers to the time difference between the peak values ​​of the R-waves of two consecutive heartbeats.

[0031] Determining respiratory frequency based on respiratory signals includes: extracting respiratory waveforms from respiratory signals; filtering the respiratory waveforms to remove noise components from the respiratory signals; performing zero-crossing detection on the filtered respiratory waveforms and identifying the zero-crossing points of each rising edge of the respiratory waveform as the starting point of each respiratory cycle; calculating the time interval between adjacent starting points as the respiratory cycle; converting the respiratory cycle into the number of breaths per unit time to obtain the respiratory frequency.

[0032] Determining the intensity of body movement based on body movement signals includes: extracting triaxial acceleration data from the body movement signals; calculating the composite amplitude of the triaxial acceleration data; counting the number of times the composite amplitude exceeds a preset threshold within a preset time window, and using the number of times as the intensity of body movement.

[0033] Determining the head pressure distribution matrix based on the head pressure distribution signal includes: extracting the pressure response values ​​of each sensing unit in the array-type pressure sensor based on the head pressure distribution signal, with each sensing unit arranged in M ​​rows × N columns; performing analog-to-digital conversion and calibration on each pressure response value to obtain the pressure value corresponding to each sensing unit; arranging each pressure value into an M × N two-dimensional matrix according to the row and column positions of each sensing unit to obtain the head pressure distribution matrix P(x,y), where x is the row direction coordinate, y is the column direction coordinate, and P(x,y) represents the pressure value at coordinate (x,y).

[0034] In step S12, the current control vector U(t) is calculated based on the state vector S(t). The control vector U(t) includes at least the target headboard angle θ_target, the target disturbance amplitude A, the target disturbance frequency f, the target light intensity L(t), and the target vibration intensity V(t). The target headboard angle is a vector, including both magnitude and direction. It should be noted that the constraints on each component of the control vector can be within feasible constraint ranges, which include: upper and lower limits of the target disturbance amplitude (e.g., ±0.5° to ±3°), upper and lower limits of the target headboard angle (e.g., 5° to 25°), upper and lower limits of the target light intensity (e.g., 0 to 100 lux), and upper and lower limits of the target vibration intensity (e.g., normalized values ​​0 to 1).

[0035] The current control vector is calculated based on the state vector, including: calculating the sleep stability index and cervical spine support deviation index based on the state vector; calculating the target head angle based on the cervical spine support deviation index; determining the pressure gradient vector based on the head pressure distribution matrix, and determining the adjustment direction of the target head angle based on the pressure gradient vector; calculating the target disturbance amplitude based on the sleep stability index, and calculating the target disturbance frequency based on the respiratory rate; determining the target respiratory rate based on heart rate variability, and determining the target light brightness and target vibration intensity based on the target respiratory rate. It also includes calculating the arousal risk index based on the variance of heart rate and respiratory rate, and body movement intensity.

[0036] The sleep stability index and cervical spine support deviation index are calculated based on the state vector, including: normalizing the heart rate variability to obtain normalized heart rate variability; calculating the respiratory rate variance based on multiple respiratory rates within a preset time window; determining the actual pressure center coordinates based on the head pressure distribution matrix; calculating the sleep stability index based on the normalized heart rate variability, respiratory rate variance, and body movement intensity; and calculating the cervical spine support deviation index based on the actual pressure center coordinates and the preset ideal head position coordinates.

[0037] The actual pressure center coordinates (xc, yc) are determined based on the head pressure distribution matrix; xc = Σ(x·P(x,y)) / ΣP(x,y); yc = Σ(y·P(x,y)) / ΣP(x,y); where P(x,y) is the pressure value at coordinate (x,y), x is the row coordinate, and y is the column coordinate.

[0038] The sleep stability index (SSI) is calculated based on normalized heart rate variability, respiratory rate variance, and body movement intensity. This includes: calculating the SSI using a first preset formula: SSI = w1·HRV_norm + w2·(1 / Var_RR) - w3·Motion; where SSI is the sleep stability index, HRV_norm is the normalized heart rate variability, Var_RR is the respiratory rate variance, Motion is body movement intensity, w1 is the first weighting coefficient, w2 is the second weighting coefficient, and w3 is the third weighting coefficient. A higher HRV_norm indicates greater relaxation; a larger 1 / Var_RR value (the smaller the Var_RR) indicates greater stability; more Motion indicates instability; high SSI indicates deep sleep, and low SSI indicates light sleep / instability.

[0039] The cervical spine support deviation index is calculated based on the actual pressure center coordinates and the preset ideal head position coordinates. This includes: calculating the cervical spine support deviation index based on a second preset formula; the second preset formula is: CSI=√((xc-x0)²+(yc-y0)²); where CSI is the cervical spine support deviation index, (xc, yc) are the actual pressure center coordinates, and (x0, y0) are the ideal head position coordinates. The ideal head position coordinates can be the center of the pillow or the optimal support point calibrated based on the user's body shape. A larger CSI indicates that the head is tilted, the pillow support is incorrect, and the cervical spine is under abnormal pressure. This is used to control the adjustment of the headboard angle.

[0040] The arousal risk index is calculated based on heart rate, respiratory rate variance, and body movement intensity. This includes: calculating the arousal risk index based on the ninth pre-set formula; the ninth pre-set formula is: ARI = k1·HR + k2·Var_RR + k3·Motion; where ARI is the arousal risk index, HR is heart rate, Var_RR is respiratory rate variance, Motion is body movement intensity, k1 is the fourth weighting coefficient, k2 is the fifth weighting coefficient, and k3 is the sixth weighting coefficient. An increase in HR indicates a rapid heartbeat (tension / awakening), and an increase in Var_RR indicates arousal. ARI is used to determine whether to awaken the individual or whether strong intervention is necessary.

[0041] The purpose of adjusting the headboard angle, disturbance amplitude, disturbance frequency, light brightness, and vibration intensity in this embodiment is to maximize SSI and minimize the sum of ARI and CSI.

[0042] The target head angle is calculated based on the cervical spine support deviation index, including: calculating the target head angle according to the third preset formula; the third preset formula is: θ_target=θ_base+k·CSI; where θ_target is the target head angle, θ_base is the preset base head angle, CSI is the cervical spine support deviation index, and k is the preset adjustment coefficient.

[0043] The pressure gradient vector is determined based on the head pressure distribution matrix, and the adjustment direction of the target head angle is determined based on the pressure gradient vector. This includes: obtaining the pressure gradient vector by taking the partial derivatives of the head pressure distribution matrix in the row and column directions respectively; if the row direction component of the pressure gradient vector indicates that the head is deviating to the left, the target head angle is adjusted to the right; if the row direction component of the pressure gradient vector indicates that the head is deviating to the right, the target head angle is adjusted to the left; if the column direction component of the pressure gradient vector indicates that the head is deviating to the downward, the target head angle is adjusted upward.

[0044] P=( P / x, P / y); where, P is the pressure gradient vector. P / x is the partial derivative in the horizontal direction (left-right direction), representing the rate of change of pressure in the horizontal direction. P / y is the partial derivative in the column direction (head-to-toe direction), representing the rate of change of pressure in the vertical direction. If P points to the left, indicating greater pressure on the left side. The head is tilted to the left, so the bed should be adjusted to the right. If... P points to the right, indicating greater pressure on the right side; the head is tilted to the right, so the head of the bed is adjusted to the left. If... P points upwards, indicating greater pressure above, causing the head to tilt upwards and the head of the bed to lower; if P points downwards, indicating greater downward pressure, causing the head to tilt downwards and the headboard to rise.

[0045] The target perturbation amplitude is calculated based on the sleep stability index, and the target perturbation frequency is calculated based on the respiratory rate. This includes: calculating the target perturbation amplitude according to the fourth preset formula; the fourth preset formula is: A=A0+α·(1-SSI); where A is the target perturbation amplitude, A0 is the preset base perturbation amplitude, SSI is the sleep stability index, and α is the gain coefficient (unit: degree), which controls the amplification factor of SSI change on A; and calculating the target perturbation frequency according to the fifth preset formula; the fifth preset formula is: f=β·RR; where f is the target perturbation frequency, RR is the respiratory rate, and β is the coupling coefficient (dimensionless), which is the scaling factor that maps the respiratory rate to the perturbation frequency.

[0046] Furthermore, θ(t) = θ0 + A·sin(2πft + ); where θ(t) represents the swing angle at time t, θ0 represents the base angle (e.g., 10°), A is the target perturbation amplitude, and 2πf is the angular frequency, The instantaneous phase of breathing (extracted by Hilbert transform) is used to realize perturbation and breathing.

[0047] The target respiratory rate is determined based on heart rate variability, and the target light brightness and target vibration intensity are determined based on the target respiratory rate, including: calculating the target respiratory rate according to the sixth preset formula; the sixth preset formula is: f_target=f0-γ·(HRV0-HRV); where f_target is the target respiratory rate, f0 is the preset baseline respiratory rate, γ is the proportional gain, HRV0 is the baseline of heart rate variability, and HRV is the heart rate variability; if the target respiratory rate is greater than the upper limit of the preset respiratory rate range, the target respiratory rate is taken as the upper limit; if the target respiratory rate is less than the lower limit of the preset respiratory rate range, the target respiratory rate is taken as the lower limit; if the target respiratory rate is within the preset respiratory rate range... Within the frequency range, the target breathing frequency remains unchanged; the target light brightness is calculated according to the seventh preset formula; the seventh preset formula is: L(t)=L0+ΔL·sin(2π·f_target·t); where L(t) is the target light brightness at time t, L0 is the preset base brightness, ΔL is the preset brightness variation range, f_target is the target breathing frequency, and t is time; the target vibration intensity is calculated according to the eighth preset formula; the eighth preset formula is: V(t)=V0·sin(2π·f_target·t); where V(t) is the target vibration intensity at time t, V0 is the preset vibration intensity, f_target is the target breathing frequency, and t is time.

[0048] It should be noted that the preset respiratory rate range is 0.1Hz to 0.25Hz. The baseline heart rate variability is the average heart rate variability over the 5 minutes prior to sleep. Heart rate variability is obtained by taking the ECG signal approximately 1 minute from the current moment.

[0049] In step S13, the calculated control vector U(t) is distributed to each actuator for execution: The headboard actuator is controlled to adjust the headboard angle to the target headboard angle; the headboard actuator can be driven by an electric actuator or a linear motor to change the tilt angle of the headboard. The swing actuator is controlled to apply a swing disturbance with the target disturbance amplitude and frequency; the swing actuator is installed between the bed frame and the bed board and can generate periodic micro-displacements relative to the bed frame in the horizontal or vertical direction, thereby forming a mechanical swing stimulus acting on the user; the swing actuator includes a motor and an eccentric transmission mechanism, which generates periodic swing by driving the eccentric wheel to rotate. The lighting actuator is controlled to adjust the lighting brightness to the target lighting brightness; the lighting actuator can be a variable brightness LED (light-emitting diode) light strip or light group installed on both sides of the headboard or above the bed frame as an ambient lighting device. The vibration actuator is controlled to output a vibration stimulus with the target vibration intensity; the vibration actuator can be a motor or an oscillator array installed inside the headboard or mattress.

[0050] After step S13, return to step S10 to collect new physiological signals and head pressure distribution signals in real time, reconstruct the state vector and solve the new control vector to achieve closed-loop dynamic correction of the control vector, and continuously follow the changes in the user's physiological state for adaptive regulation.

[0051] Based on the above embodiments, this application also provides an abnormal state monitoring and alarm mechanism, specifically: when any of the following conditions are met, the user is determined to be in an abnormal state and an alarm is triggered.

[0052] If the respiratory rate (RR) falls below the preset lower limit, it is considered apnea or respiratory depression; if the heart rate (HR) rises above the preset upper limit, it is considered tachycardia or a stress state; if the body movement intensity (Motion) changes drastically within a short period, it is considered awakening, startle reflex, or discomfort. Alarms include: immediately stopping swaying disturbances, vibration stimulation, and light guidance to avoid aggravating user discomfort; emitting warning signals through the smart bed's built-in speakers or lights to alert the user or caregiver; sending alarm information wirelessly to the user terminal, nursing station, or remote server; and storing the time, type, and related physiological data of abnormal events locally or in the cloud for subsequent analysis.

[0053] Furthermore, it also includes: periodically calculating the arousal risk index in units of preset time windows; when the arousal risk index exceeds the preset threshold for M consecutive preset time windows, it is determined that the user is in a state of continuous high arousal risk and an early warning signal is output, where M is a preset positive integer.

[0054] By periodically calculating the arousal risk index in preset time windows, and only outputting a warning signal when the ARI exceeds the preset threshold for M consecutive time windows, the system avoids single false triggers caused by instantaneous physiological fluctuations, effectively improves the accuracy and reliability of abnormal state judgment, reduces false alarms caused by normal physiological changes such as users briefly turning over or temporary fluctuations in breathing rhythm, and enhances the user experience.

[0055] This application provides a dynamic control method for a smart bed based on physiological signals. It collects multi-dimensional physiological signals from the user, including electrocardiogram, respiration, and body movement, as well as head pressure distribution signals. Based on these signals, a current state vector is constructed. The current control vector is then calculated from this state vector, specifically including the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity. This control vector is distributed to various actuators to control the headboard actuator to adjust the headboard angle to the target angle, the swing actuator to apply swing disturbances with the target amplitude and frequency, the light actuator to adjust the light brightness to the target brightness, and the vibration actuator to output vibration stimulation with the target vibration intensity. The angle adjustment, mechanical disturbance, light changes, and vibration stimulation work in synergy to guide the user into deep sleep, forming a complete control process. Unlike existing smart beds that only record data without intervention, this application actively controls sleep based on physiological state to effectively improve sleep quality.

[0056] Furthermore, this application uses physiological signals and head pressure distribution signals as regulatory inputs to construct a complete closed-loop link from perception to execution to feedback. It collects multi-dimensional signals such as electrocardiogram, respiration, body movement, and head pressure distribution, and calculates control vectors including bed head angle, swing amplitude and frequency, light brightness, and vibration intensity. After execution, it continuously collects new data to dynamically correct the control vectors, enabling it to proactively intervene in the regulation process based on the user's physiological state, thereby effectively improving sleep quality.

[0057] This application introduces mechanical disturbance as an intervention method, which, in conjunction with light and vibration, forms a multimodal regulation. The oscillating actuator applies oscillation with a target amplitude and frequency, providing rhythmic mechanical stimulation; the light actuator changes sinusoidally according to the target breathing frequency; and the vibration actuator outputs synchronous somatosensory stimulation at the same frequency. These three elements work synergistically from three dimensions: mechanical stimulation, visual guidance, and somatosensory feedback, breaking through the limitations of single intervention modes that rely solely on sound or light.

[0058] This application specifically collects head pressure distribution signals, constructs a head pressure distribution matrix, calculates the cervical spine support deviation index based on this matrix, and dynamically adjusts the head angle to optimize the cervical spine stress state, thereby achieving effective intervention in the regulation of the head and neck region.

[0059] In this application, all control parameters are dynamically driven by the user's physiological state. The disturbance amplitude is adaptively adjusted according to the sleep stability index, the disturbance frequency is synchronized in real time with the breathing rhythm, the head of the bed angle is continuously adjusted according to the head pressure distribution, and the light and vibration also change dynamically with the target breathing frequency, thereby realizing adaptive dynamic control based on real-time physiological state.

[0060] The above embodiments have described in detail the method for dynamic control of an intelligent bed based on physiological signals. This application also provides embodiments of a device for dynamic control of an intelligent bed based on physiological signals. It should be noted that this application describes the embodiments of the device from two perspectives: one is based on functional modules, and the other is based on hardware.

[0061] Figure 2 A structural diagram of a smart bed dynamic control device based on physiological signals provided in this application embodiment is shown below. Figure 2 As shown, a smart bed dynamic control device based on physiological signals includes: The acquisition module 10 is used to acquire the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals and body movement signals; Module 11 is used to construct the user's current state vector based on physiological signals and head pressure distribution signals; The calculation module 12 is used to calculate the current control vector based on the state vector; wherein the control vector includes at least the target head angle, the target disturbance amplitude, the target disturbance frequency, the target light brightness, and the target vibration intensity; The control module 13 is used to control the headboard actuator to adjust the headboard angle to the target headboard angle, control the swing actuator to apply swing disturbance with the target disturbance amplitude and the target disturbance frequency, control the lighting actuator to adjust the lighting brightness to the target lighting brightness, and control the vibration actuator to output vibration stimulation with the target vibration intensity.

[0062] Based on the above embodiments, in one optional embodiment, the building module includes: The first determination submodule is used to determine heart rate variability based on electrocardiogram signals; The second determining submodule is used to determine the respiratory rate based on the respiratory signal; The third determination submodule is used to determine the intensity of body movement based on the body movement signal; The fourth determination submodule is used to determine the head pressure distribution matrix based on the head pressure distribution signal; Construct submodules to form state vectors from the distribution matrices of heart rate variability, respiratory rate, body motion intensity, and head pressure.

[0063] Based on the above embodiments, in one optional embodiment, the solution module includes: The first calculation submodule is used to calculate the sleep stability index and the cervical spine support deviation index based on the state vector. The second calculation submodule is used to calculate the target head angle based on the cervical spine support deviation index. The third calculation submodule is used to determine the pressure gradient vector based on the head pressure distribution matrix, and to determine the adjustment direction of the target head angle based on the pressure gradient vector; The fourth calculation submodule is used to calculate the target perturbation amplitude based on the sleep stability index and the target perturbation frequency based on the respiratory rate; The fifth calculation submodule is used to determine the target respiratory rate based on heart rate variability, and to determine the target light brightness and target vibration intensity based on the target respiratory rate.

[0064] Based on the above embodiments, in an optional embodiment, the first computing submodule includes: The normalization unit is used to normalize the heart rate variability to obtain normalized heart rate variability. The first calculation unit is used to calculate the respiratory rate variance based on multiple respiratory rates within a preset time window. The second calculation unit is used to determine the actual pressure center coordinates based on the head pressure distribution matrix. The third calculation unit is used to calculate the sleep stability index based on normalized heart rate variability, respiratory rate variance and body movement intensity. The fourth calculation unit is used to calculate the cervical spine support deviation index based on the actual pressure center coordinates and the preset ideal head position coordinates.

[0065] Based on the above embodiments, in an optional embodiment, the third computing unit includes: The first calculation subunit is used to calculate the sleep stability index based on the first preset formula; The first preset formula is: SSI = w1·HRV_norm + w2·(1 / Var_RR) - w3·Motion; Among them, SSI is the sleep stability index, HRV_norm is the normalized heart rate variability, Var_RR is the respiratory rate variance, Motion is the body movement intensity, w1 is the first weighting coefficient, w2 is the second weighting coefficient, and w3 is the third weighting coefficient.

[0066] Based on the above embodiments, in an optional embodiment, the fourth computing unit includes: The second calculation subunit is used to calculate the cervical spine support deviation index based on the second preset formula; The second preset formula is: CSI = √((xc-x0)² + (yc-y0)²); Wherein, CSI is the cervical spine support deviation index, (xc, yc) are the actual pressure center coordinates, and (x0, y0) are the ideal head position coordinates.

[0067] Based on the above embodiments, in one optional embodiment, the second computing submodule includes: The fifth calculation unit is used to calculate the target head angle according to the third preset formula; The third preset formula is: θ_target = θ_base + k·CSI; Where θ_target is the target headboard angle, θ_base is the preset base headboard angle, CSI is the cervical spine support deviation index, and k is the preset adjustment coefficient.

[0068] Based on the above embodiments, in an optional embodiment, the fourth computing submodule includes: The sixth calculation unit is used to calculate the target disturbance amplitude according to the fourth preset formula; The fourth preset formula is: A = A0 + α·(1-SSI); Where A is the target perturbation amplitude, A0 is the preset base perturbation amplitude, SSI is the sleep stability index, and α is the gain coefficient; The seventh calculation unit is used to calculate the target disturbance frequency according to the fifth preset formula; The fifth preset formula is: f = β·RR; Where f is the target disturbance frequency, RR is the breathing frequency, and β is the coupling coefficient.

[0069] Based on the above embodiments, in an optional embodiment, the fifth calculation submodule includes: The eighth calculation unit is used to calculate the target respiratory rate according to the sixth preset formula; The sixth preset formula is: f_target = f0 - γ·(HRV0 - HRV); Where f_target is the target respiratory rate, f0 is the preset baseline respiratory rate, γ is the proportional gain, HRV0 is the baseline heart rate variability, and HRV is the heart rate variability. The first value unit is used to set the target respiratory rate as the upper limit if the target respiratory rate is greater than the upper limit of the preset respiratory rate range. The second value unit is used to set the target respiratory rate as the lower limit if the target respiratory rate is less than the lower limit of the preset respiratory rate range. The third value unit is used to keep the target respiratory rate unchanged if the target respiratory rate is within the preset respiratory rate range; The ninth calculation unit is used to calculate the target light brightness according to the seventh preset formula; The seventh preset formula is: L(t) = L0 + ΔL·sin(2π·f_target·t); Where L(t) is the target light brightness at time t, L0 is the preset base brightness, ΔL is the preset brightness variation range, f_target is the target breathing frequency, and t is time; The tenth calculation unit is used to calculate the target vibration intensity according to the eighth preset formula; The eighth preset formula is: V(t) = V0·sin(2π·f_target·t); Where V(t) is the target vibration intensity at time t, V0 is the preset vibration intensity, f_target is the target breathing frequency, and t is time.

[0070] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0071] Figure 3 A structural diagram of another intelligent bed dynamic control device based on physiological signals provided in this application embodiment is shown below. Figure 3 As shown, the intelligent bed dynamic control device based on physiological signals includes: a memory 20 for storing computer programs; The processor 21 is used to execute computer programs to implement the steps of the above embodiment (the method for dynamic control of an intelligent bed based on physiological signals).

[0072] The intelligent bed dynamic control device based on physiological signals provided in this embodiment can include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0073] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0074] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the intelligent bed dynamic control method based on physiological signals disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, physiological signals and head pressure distribution signals.

[0075] In some embodiments, the intelligent bed dynamic control device based on physiological signals may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0076] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the intelligent bed dynamic control device based on physiological signals, and may include more or fewer components than shown.

[0077] The intelligent bed dynamic control device based on physiological signals provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can perform the following methods: collecting the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals, and body movement signals; constructing the user's current state vector based on the physiological signals and head pressure distribution signals; calculating the current control vector based on the state vector; wherein, the control vector includes at least the target head angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity; controlling the head actuator to adjust the head angle to the target head angle, controlling the swing actuator to apply swing disturbance with the target disturbance amplitude and target disturbance frequency, controlling the light actuator to adjust the light brightness to the target light brightness, and controlling the vibration actuator to output vibration stimulation with the target vibration intensity.

[0078] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above-described method embodiment for the dynamic control method of an intelligent bed based on physiological signals.

[0079] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they 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 all or 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 executes all or part of the steps of the methods described in 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.

[0080] The foregoing provides a detailed description of a method and apparatus for dynamic control of an intelligent bed based on physiological signals, as provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0081] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for dynamic control of an intelligent bed based on physiological signals, characterized in that, include: Collect the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals, and body movement signals; Construct the user's current state vector based on the physiological signals and the head pressure distribution signal; The current control vector is calculated based on the state vector; wherein the control vector includes at least the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity; The headboard actuator is controlled to adjust the headboard angle to the target headboard angle, the swing actuator is controlled to apply swing disturbance with the target disturbance amplitude and the target disturbance frequency, the lighting actuator is controlled to adjust the lighting brightness to the target lighting brightness, and the vibration actuator is controlled to output vibration stimulation with the target vibration intensity.

2. The method for dynamic control of an intelligent bed based on physiological signals according to claim 1, characterized in that, Based on the physiological signals and the head pressure distribution signals, a current state vector of the user is constructed, including: Heart rate variability is determined based on the electrocardiogram signal; The respiratory rate is determined based on the respiratory signal; The intensity of body movement is determined based on the body movement signal; Determine the head pressure distribution matrix based on the head pressure distribution signal; The heart rate variability, respiratory rate, body motion intensity, and head pressure distribution matrix constitute the state vector.

3. The method for dynamic control of an intelligent bed based on physiological signals according to claim 2, characterized in that, The current control vector is calculated based on the state vector, including: Calculate the sleep stability index and cervical spine support deviation index based on the state vector; The target headboard angle is calculated based on the cervical spine support deviation index. The pressure gradient vector is determined based on the head pressure distribution matrix, and the adjustment direction of the target head angle is determined based on the pressure gradient vector. The target disturbance amplitude is calculated based on the sleep stability index, and the target disturbance frequency is calculated based on the respiratory rate; The target respiratory rate is determined based on the heart rate variability, and the target light brightness and the target vibration intensity are determined based on the target respiratory rate.

4. The method for dynamic control of an intelligent bed based on physiological signals according to claim 3, characterized in that, The sleep stability index and cervical spine support deviation index are calculated based on the state vector, including: The heart rate variability is normalized to obtain normalized heart rate variability. Calculate the respiratory rate variance based on multiple respiratory rates within a preset time window; The actual pressure center coordinates are determined based on the head pressure distribution matrix. The sleep stability index is calculated based on the normalized heart rate variability, the respiratory rate variance, and the body movement intensity. The cervical spine support deviation index is calculated based on the actual pressure center coordinates and the preset ideal head position coordinates.

5. The method for dynamic control of an intelligent bed based on physiological signals according to claim 4, characterized in that, The sleep stability index is calculated based on the normalized heart rate variability, the respiratory rate variance, and the body movement intensity, including: The sleep stability index is calculated based on the first preset formula; The first preset formula is: SSI = w1·HRV_norm + w2·(1 / Var_RR) - w3·Motion; Wherein, SSI is the sleep stability index, HRV_norm is the normalized heart rate variability, Var_RR is the respiratory rate variance, Motion is the body movement intensity, w1 is the first weighting coefficient, w2 is the second weighting coefficient, and w3 is the third weighting coefficient.

6. The method for dynamic control of an intelligent bed based on physiological signals according to claim 4, characterized in that, The cervical spine support deviation index is calculated based on the actual pressure center coordinates and the preset ideal head position coordinates, including: The cervical spine support deviation index is calculated based on the second preset formula; The second preset formula is: CSI = √((xc-x0)² + (yc-y0)²); Wherein, CSI is the cervical spine support deviation index, (xc, yc) are the coordinates of the actual pressure center, and (x0, y0) are the coordinates of the ideal head position.

7. The method for dynamic control of an intelligent bed based on physiological signals according to claim 3, characterized in that, The target headboard angle is calculated based on the cervical spine support deviation index, including: The target headboard angle is calculated according to the third preset formula; The third preset formula is: θ_target = θ_base + k·CSI; Wherein, θ_target is the target headboard angle, θ_base is the preset base headboard angle, CSI is the cervical spine support deviation index, and k is the preset adjustment coefficient.

8. The method for dynamic control of an intelligent bed based on physiological signals according to claim 3, characterized in that, The target perturbation amplitude is calculated based on the sleep stability index, and the target perturbation frequency is calculated based on the respiratory rate, including: The target disturbance amplitude is calculated according to the fourth preset formula; The fourth preset formula is: A = A0 + α·(1-SSI); Where A is the target perturbation amplitude, A0 is the preset base perturbation amplitude, SSI is the sleep stability index, and α is the gain coefficient; The target disturbance frequency is calculated according to the fifth preset formula; The fifth preset formula is: f = β·RR; Where f is the target disturbance frequency, RR is the breathing frequency, and β is the coupling coefficient.

9. The method for dynamic control of an intelligent bed based on physiological signals according to claim 3, characterized in that, Determining the target respiratory rate based on the heart rate variability, and determining the target light brightness and the target vibration intensity based on the target respiratory rate, includes: The target respiratory rate is calculated according to the sixth preset formula; The sixth preset formula is: f_target = f0 - γ·(HRV0 - HRV); Where f_target is the target respiratory rate, f0 is the preset baseline respiratory rate, γ is the proportional gain, HRV0 is the heart rate variability baseline, and HRV is the heart rate variability. If the target respiratory rate is greater than the upper limit of the preset respiratory rate range, then the target respiratory rate is taken as the upper limit. If the target respiratory rate is less than the lower limit of the preset respiratory rate range, then the target respiratory rate is taken as the lower limit. If the target respiratory rate is within the preset respiratory rate range, then the target respiratory rate remains unchanged; The brightness of the target light is calculated according to the seventh preset formula; The seventh preset formula is: L(t) = L0 + ΔL·sin(2π·f_target·t); Where L(t) is the target light brightness at time t, L0 is the preset base brightness, ΔL is the preset brightness variation range, f_target is the target breathing frequency, and t is time; The target vibration intensity is calculated according to the eighth preset formula; The eighth preset formula is: V(t) = V0·sin(2π·f_target·t); Where V(t) is the target vibration intensity at time t, V0 is the preset vibration intensity, f_target is the target breathing frequency, and t is time.

10. A smart bed dynamic control device based on physiological signals, characterized in that, include: The acquisition module is used to acquire the user's physiological signals and head pressure distribution signals; wherein, the physiological signals include at least electrocardiogram signals, respiratory signals, and body movement signals; The construction module is used to construct the user's current state vector based on the physiological signals and the head pressure distribution signal; The calculation module is used to calculate the current control vector based on the state vector; wherein the control vector includes at least the target headboard angle, target disturbance amplitude, target disturbance frequency, target light brightness, and target vibration intensity; The control module is used to control the headboard actuator to adjust the headboard angle to the target headboard angle, control the swing actuator to apply swing disturbance with the target disturbance amplitude and target disturbance frequency, control the lighting actuator to adjust the lighting brightness to the target lighting brightness, and control the vibration actuator to output vibration stimulation with the target vibration intensity.

Images