Control method of intelligent mattress and control system based on intelligent mattress

Abstract

The invention discloses a control method of an intelligent mattress and a control system based on the intelligent mattress, and relates to the technical field of smart home. According to the embodiment of the invention, processing, separation and feature extraction are sequentially carried out on collected original composite signals to obtain heart rate variation features and micro body movement features; calculating a pressure index and a sleep stage according to heart rate variation characteristics and micro body movement characteristics; and finally, the intelligent mattress is controlled based on the processed target composite signal, the heart rate variation characteristics, the pressure index and the sleep stage, so that a complete closed-loop path from'non-sensing 'to'accurate evaluation' and then to'dynamic intervention 'is constructed, and active and intelligent adjustment on the emotion of the monitored object is realized.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of smart home, in particular to a control method of a smart mattress and a control system based on the smart mattress. BACKGROUND

[0002] With the rapid development of smart home technology, smart mattresses have gradually become popular and have functions such as bed posture adjustment, softness adjustment, massage, heating and basic sleep monitoring. However, the existing smart mattresses have obvious limitations in health monitoring and active intervention: the monitoring dimension is relatively single, and it mainly depends on contact sensors or limited data sources (such as only collecting basic physiological parameters such as respiratory rate and turning over frequency). For example, the sensors of some products are easily disturbed by turning over and other actions, or the data dimension is limited, resulting in relatively low accuracy of health monitoring. In terms of intervention means, it mainly focuses on physical layer adjustment, such as mattress hardness adjustment, body position change, etc. SUMMARY

[0003] The embodiment of the present application provides a control method of a smart mattress and a control system based on the smart mattress, which aims to solve the problem that the existing smart mattress cannot actively and intelligently adjust the mood of the monitored object.

[0004] In a first aspect, the embodiment of the present application provides a control method of a smart mattress, comprising: collecting an original composite signal of a monitored object, and processing the original composite signal to obtain a target composite signal; performing signal separation and feature extraction on the target composite signal to obtain a heart rate variability feature and a micro-body movement feature; calculating a stress index and a sleep stage according to the heart rate variability feature and the micro-body movement feature; controlling the smart mattress according to the target composite signal, the heart rate variability feature, the stress index and the sleep stage.

[0005] In a second aspect, the embodiment of the present application further provides a control system based on a smart mattress, comprising: a smart mattress and a smart device, the smart mattress is used for executing the control method of the smart mattress in the first aspect, and the smart device comprises a smart sound box and an aromatherapy machine, the smart sound box and the aromatherapy machine are linked with the smart mattress.

[0006] The embodiment of the present application provides a control method of an intelligent mattress and a control system based on the intelligent mattress, the original composite signal collected is sequentially processed, separated and feature extracted to obtain a heart rate variability feature and a micro body movement feature; then, a stress index and a sleep stage are calculated according to the heart rate variability feature and the micro body movement feature; finally, the intelligent mattress is controlled based on the processed target composite signal, the heart rate variability feature, the stress index and the sleep stage, so that a complete closed loop path from 'unconscious perception' to 'precise evaluation' and then to 'dynamic intervention' is constructed, and active and intelligent adjustment of the emotion of a monitored object is realized. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0008] Figure 1 A block schematic diagram of the control system based on the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 2 A flowchart of the control method of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 3 A sub-flowchart of the control method of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 4 Another sub-flowchart of the control method of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 5 Still another sub-flowchart of the control method of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 6 Still another sub-flowchart of the control method of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 7 A flowchart of the control method of the intelligent mattress provided by another embodiment of the present application is shown in the figure. Figure 8 A schematic block diagram of the control device of the intelligent mattress provided by an embodiment of the present application is shown in the figure. Figure 9 A schematic block diagram of the intelligent mattress provided by an embodiment of the present application is shown in the figure.

[0009] Reference signs: 10, control system based on intelligent mattress; 11, intelligent mattress; 111, piezoelectric film sensor array; 112, signal conditioning circuit; 12, intelligent device; 121, intelligent sound box; 122, aromatherapy machine. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of the present application.

[0011] It should be understood that the terms “comprise” and “include” as used in the specification and the appended claims indicate the presence of the described features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0012] It should also be understood that the terms used in the present application specification are only for the purpose of describing particular embodiments and are not intended to limit the present application. For example, as used in the present application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0013] It should be further understood that the term “and / or” as used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations thereof, and includes these combinations.

[0014] For example, as used in the present specification and the appended claims, the term “if’ can be interpreted as meaning “when” or “once” or “in response to a determination” or “in response to detecting” depending on the context. Similarly, the phrases “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “once it is determined” or “in response to the determination” or “once [the described condition or event] is detected” or “in response to detecting [the described condition or event]” depending on the context.

[0015] See Figure 1In the embodiment, the control system based on the smart mattress comprises a smart mattress and a smart device, wherein the smart mattress is provided with a piezoelectric film sensor array and a signal conditioning circuit, the piezoelectric film sensor array is used to collect original composite signals of a monitored object, and the signal conditioning circuit is used to process the original composite signals; the smart device comprises a smart sound box and an aromatherapy machine, and the smart sound box and the aromatherapy machine are linked with the smart mattress. It should be noted that in the embodiment, the piezoelectric film sensor array is a flexible and high-sensitivity sensing device, which can convert mechanical stimuli such as pressure and vibration into electrical signals. Its core feature is to use a row + column electrode structure, which greatly reduces the number of leads and effectively suppresses signal crosstalk, realizing the non-inductive monitoring of small dynamic stress (such as heartbeat and muscle microtremor), that is, the piezoelectric film sensor array can realize non-inductive collection, and the sensitivity is greater than or equal to 50 mV / g, and the signal-to-noise ratio is greater than 20 dB. It should be further noted that in the embodiment, the signal conditioning circuit comprises a charge amplifier, a band-pass filter, an instrument amplifier and an ADC sampling circuit, wherein the charge amplifier is used to process high-impedance charge signals (such as piezoelectric sensor output), converts charge into voltage through capacitive negative feedback, and effectively isolates the influence of cable capacitance; the instrument amplifier is a programmable gain instrument amplifier, which is used to amplify the weak voltage signal with high precision, and the high common-mode rejection ratio can effectively suppress the environmental common-mode noise; the band-pass filter is composed of a high-pass filter and a low-pass filter, which is used to filter out unnecessary low-frequency drift and high-frequency noise in the signal, and retain the effective target frequency band; the ADC sampling circuit is used to convert the analog voltage signal into a digital signal.

[0016] Please refer to Figure 2 , Figure 2 is a flowchart of a control method of a smart mattress provided by an embodiment of the present application. The control method of the smart mattress will be described in detail below. The method is applied to a smart mattress, for example Figure 2 as shown, and the method comprises the following steps S110-S140.

[0017] S110, collect original composite signals of a monitored object, and process the original composite signals to obtain target composite signals.

[0018] In the embodiment, the piezoelectric film sensor array inductively collects the original composite signals of the monitored object, and the signal conditioning circuit processes the original composite signals to obtain the target composite signals. It should be noted that in the embodiment, the original composite signals are the original psychological signals of the monitored object. It should be further noted that step S110 is realized by the sensing module of the smart mattress. Understandably, the sensing module comprises the piezoelectric film sensor array and the signal conditioning circuit.

[0019] For example Figure 3As shown, step S110 includes steps S111-S114: S111. The original composite signal is impedance-transformed to obtain a transformed composite signal; S112. Filter out the noise signal in the converted composite signal to obtain the filtered composite signal; S113. Amplify the filtered composite signal to obtain an amplified composite signal; S114. Perform analog-to-digital conversion on the amplified composite signal to obtain the target composite signal.

[0020] In this embodiment, firstly, impedance conversion is performed. The original composite signal generated by the piezoelectric sensor has high output impedance characteristics, making it easily attenuated and susceptible to interference. Therefore, a charge amplifier is first used as a buffer in the signal conditioning circuit to convert the high-impedance charge signal into a low-impedance voltage signal, thereby ensuring that the signal can be effectively transmitted to subsequent processing stages. Next, the filtering and denoising stage begins. The signal after impedance conversion still contains various noises, mainly including low-frequency drift (baseline drift) caused by slow changes in body temperature and high-frequency noise generated by electrical switches in the environment. This stage uses a bandpass filter, and by setting appropriate high-pass and low-pass cutoff frequencies (e.g., 0.1Hz to 100Hz), these out-of-band noises are precisely filtered out, retaining the effective physiological signal frequency band, thereby significantly improving the signal-to-noise ratio. Then, signal amplification is performed. The filtered composite signal is usually still relatively weak in amplitude, insufficient to be effectively quantized by the subsequent ADC sampling circuit. This stage uses an instrumentation amplifier to amplify the filtered composite signal. This instrumentation amplifier boasts advantages such as high input impedance, high common-mode rejection ratio, and low noise. It can stably and with high gain amplify weak differential signals while effectively suppressing common-mode interference, providing an analog voltage signal with sufficient amplitude for digitization. Finally, analog-to-digital conversion is performed. The amplified composite signal is then fed into the ADC sampling circuit. The ADC discretizes and quantizes the continuous-time analog signal at a set sampling rate (e.g., 500 Hz), converting it into a discrete digital sequence that can be directly processed and recognized—the final target composite signal.

[0021] S120. Perform signal separation and feature extraction on the target composite signal to obtain heart rate variability features and microbody motion features.

[0022] In this embodiment, for example Figure 4As shown, step S120 includes steps S121-S123: S121, separating the target composite signal to obtain a heart rate vibration signal and a microbody motion signal; S122, extracting the heart rate variation features from the heart rate vibration signal; S123, extracting the microbody motion features from the microbody motion signal. Specifically, step S121 includes: performing multi-level wavelet decomposition on the target composite signal to obtain low-frequency coefficients and high-frequency coefficients representing different frequency components of the signal; reconstructing the heart rate vibration signal using the low-frequency coefficients; and reconstructing the microbody motion signal using the high-frequency coefficients. More specifically, in this embodiment, firstly, multi-level wavelet decomposition is performed on the target composite signal, and a wavelet basis with tight support and good symmetry is selected to perform J-level decomposition on the target composite signal (e.g., J=5). Each level of decomposition will generate two sets of coefficients: low-frequency coefficients and high-frequency coefficients. Then, the heart rate vibration signal is reconstructed using the low-frequency coefficients. The heart rate vibration signal is mainly caused by the heartbeat, and its energy is mainly concentrated in the low-frequency range (e.g., 0.5-2 Hz). Therefore, low-frequency coefficients from the lower levels after decomposition are selected for signal reconstruction. This step effectively preserves the rhythmic fluctuations of the heart rate while filtering out most high-frequency noise and micro-movement interference. Finally, high-frequency coefficients are used to reconstruct the micro-movement signal. Micro-movement signals (such as muscle tremors and turning over) typically exhibit high-frequency, low-amplitude characteristics (e.g., 1-10 Hz), so high-frequency coefficients from the decomposition are selected for signal reconstruction.

[0023] Further, step S122 includes: identifying the R-wave peak value of each heartbeat cycle in the heart rate vibration signal and calculating the time interval between adjacent R waves to obtain an RR interval sequence; cleaning the RR interval sequence to obtain a cleaned RR interval sequence; and calculating the heart rate variability features based on the cleaned RR interval sequence, wherein the heart rate variability features include heart rate time-domain features and heart rate frequency-domain features, and the heart rate time-domain features include low-frequency power, high-frequency power, and power ratio. Specifically, the R-wave peak value of each heartbeat cycle is first accurately located from the heart rate vibration signal. The R-wave peak value is the feature point with the highest amplitude and sharpest shape in the electrocardiogram signal, and is usually implemented using a peak detection algorithm based on amplitude and slope. In practical applications, in order to improve the accuracy of detection, the heart rate vibration signal is first preprocessed by differentiation and squaring to enhance the steepness of the R-wave, and then an adaptive dynamic threshold is set to identify the true R-wave peak value and avoid noise interference. After identifying the continuous R-wave peak value positions, the RR interval sequence can be generated by calculating the time interval between adjacent R waves (usually in milliseconds). Because RR interval sequences may contain outliers caused by noise, signal dropout, or ectopic beats, these outliers can severely interfere with the accuracy of heart rate variability analysis. Therefore, RR interval sequences need to be cleaned. The cleaning process mainly includes two steps: first, outlier removal, for example, using thresholding or statistical methods to identify and remove outliers that significantly deviate from the normal range; second, data repair, filling the gaps left after outlier removal using algorithms such as linear interpolation or spline interpolation, thereby obtaining a continuous and regular cleaned RR interval sequence. Heart rate variability (HRV) features are calculated based on the cleaned RR interval sequence. HRV features include time-domain features and frequency-domain features. The time-domain features are obtained through direct statistical calculations, such as the standard deviation of the RR interval sequence. The frequency-domain features are obtained by estimating the power spectral density of the RR interval sequence, decomposing the signal into different frequency ranges and calculating their power values. These include low-frequency power (LF, typically 0.04-0.15 Hz), high-frequency power (HF, typically 0.15-0.4 Hz), and the ratio between the two, i.e., the power ratio (LF / HF).

[0024] Furthermore, step S123 includes: calculating a threshold for the micro-body motion signal to obtain a micro-body motion threshold; using a peak detection algorithm to identify all pulse peak points in the micro-body motion signal that exceed the micro-body motion threshold and their position sequences to obtain a pulse peak sequence; and calculating the micro-body motion feature based on the pulse peak sequence, wherein the micro-body motion feature includes the micro-body motion frequency and the micro-body motion detection pulse. Specifically, firstly, a dynamic threshold for the micro-body motion signal needs to be calculated to obtain the micro-body motion threshold, which is usually adaptively determined based on the statistical characteristics of the signal (e.g., median and absolute median difference); then, a peak detection algorithm is used to scan the entire micro-body motion signal, identify all pulse peak points whose amplitude exceeds the aforementioned micro-body motion threshold, and record their corresponding time positions to form a pulse peak sequence. It should be noted that by setting a reasonable minimum peak interval (e.g., 20 sampling points), duplicate counting caused by signal jitter can be avoided, ensuring that each detected peak represents an independent and valid micro-motion event. Based on the obtained pulse peak sequence, the micro-motion frequency and micro-motion detection pulse are calculated. The micro-motion frequency is usually quantified by calculating the number of pulses per unit time (e.g., per minute), which directly reflects the activity or frequency of micro-motion events. The micro-motion detection pulse includes the pulse count, average amplitude, duration, and statistical characteristics of the pulse interval (e.g., mean, standard deviation). These features help to more precisely distinguish different types of micro-motion patterns, such as subtle tremors caused by anxiety or normal rolling over movements.

[0025] S130. Calculate the stress index and sleep stage based on the heart rate variability characteristics and the micro-body movement characteristics.

[0026] In this embodiment, for example Figure 5As shown, step S130 includes steps S131-S132: S131, calculating the stress index by weighting the heart rate variability and the microbody movement characteristics; S132, determining the sleep stage based on the power ratio, the microbody movement frequency, and the microbody movement detection pulse. Specifically, step S132 includes: if the power ratio is within a first preset ratio range and the microbody movement frequency is less than a first preset microbody movement frequency, then the sleep stage is determined to be deep sleep; if the power ratio is within a second preset ratio range and the microbody movement detection pulse is a preset pulse duration, then the sleep stage is determined to be REM sleep; if the power ratio is within a third preset ratio range and the microbody movement frequency is greater than a second preset microbody movement frequency, then the sleep stage is determined to be awake sleep, wherein the second preset microbody movement frequency is greater than the first preset microbody movement frequency. It should be noted that in this embodiment, the stress index = (heart rate variability × heart rate weight) + (micro-body movement characteristics × micro-body movement weight), where the heart rate weight and micro-body movement weight are determined according to the actual situation. It should also be noted that in this embodiment, the power ratio is LF / HF, with a first preset ratio range of less than 1, a first preset micro-body movement frequency of 2 times / minute, a second preset ratio range of 0.8~1.2, a preset pulse time of 0.1s, a third preset ratio range of greater than 3, and a second preset micro-body movement frequency of 10 times / minute. Understandably, if LF / HF < 1 and the micro-body movement frequency < 2 times / minute, it is determined to be deep sleep; if LF / HF is between 0.8 and 1.2 and the micro-body movement detection pulse is 0.1s, it is determined to be REM sleep, where REM sleep is a unique and active stage in the sleep cycle; if LF / HF > 3 and the micro-body movement characteristic frequency > 10 times / minute, it is determined to be wakefulness. It should be noted that steps S120 and S130 are implemented by the computing module in the smart mattress, which includes the main control chip.

[0027] S140. Control the smart mattress based on the target composite signal, the heart rate variability characteristics, the pressure index, and the sleep stage.

[0028] In this embodiment, for example Figure 6As shown, step S140 includes steps S141-S143: S141, if the pressure index is greater than a preset pressure index and the duration is greater than a preset duration, then the vibration module in the smart mattress is activated, and the vibration module vibrates at a first vibration frequency; S142, if the sleep stage is deep sleep and the body movement pressure change value of the monitored object is less than a preset pressure change value within a preset time, then the deep sleep mode is entered; S143, if the power ratio in the heart rate variability feature is greater than a preset power ratio and the micro-body movement time is greater than a preset micro-body movement time, then the vibration module is activated, and the vibration module vibrates at a second vibration frequency, wherein the second vibration frequency is greater than the first vibration frequency, and the micro-body movement time is calculated based on the micro-body movement signal in the target composite signal. In practical applications, after separating the micro-movement signals from the target composite signal, a dynamic threshold algorithm is used to detect the pulse events and record the peak point and time position of each pulse. A trained LSTM classification model is then used to analyze the detected pulse sequences, identifying and filtering out valid pulse events belonging to "anxiety-related micro-movements," excluding interference from other irrelevant movements (such as turning over). The duration of all valid pulses classified as anxiety-related micro-movements is accumulated to obtain a quantitative indicator representing the duration of anxiety in the monitored subject—the micro-movement time. Specifically, when the monitored subject's stress index continuously exceeds a preset threshold (e.g., stress index > 70 for more than 5 minutes), the monitored subject is determined to be in a state of mild stress or anxiety, making it difficult to fall asleep. At this time, a mild stress relief mode is activated. This mode activates the vibration module built into the smart mattress and instructs it to vibrate gently and soothingly at a first vibration frequency (e.g., a low-frequency sine wave of 0.5-1 Hz). This low-frequency vibration simulates a soothing rhythm, aiming to guide the monitored subject's breathing rate to slow down through physical stimulation, promoting parasympathetic nerve excitation, thereby helping the monitored subject relax and creating conditions for falling asleep. This intervention is a preventative, low-intensity regulation. When the monitored subject has entered deep sleep and the piezoelectric film sensor array of the smart mattress detects that the change in body motion pressure within a preset time (e.g., 10 minutes) is less than a preset pressure change value, it indicates that the monitored subject's body posture is extremely stable. At this time, the deep sleep protection mode will be automatically activated. In this mode, all unnecessary active intervention functions (such as vibration, aromatherapy, and music) will be suspended to minimize environmental interference and ensure that the monitored subject is not easily awakened, thereby protecting and extending precious deep sleep time. When a more significant stress response is detected in the monitored subject's physiological indicators, a stronger intervention will be initiated. Specifically, for example, if the LF / HF ratio in heart rate variability is greater than a preset power ratio, and the micro-body movement time is greater than a preset micro-body movement time, it indicates that the monitored subject is in a state of high stress or anxiety, and may even be in a restless period of wakefulness or light sleep.At this point, a high-intensity anxiety intervention mode will be activated. This mode will also activate the vibration module, but will use a second vibration frequency (e.g., 2-3 Hz pulsed vibration), which is significantly higher than the first vibration frequency. This stronger, more rhythmic tactile stimulation aims to more proactively interrupt the monitored subject's anxiety physiological cycle, diverting attention through stronger sensory input, helping the nervous system "reset," and thus more quickly alleviating acute anxiety symptoms. It should be noted that step S140 is implemented by the settlement control module in the smart mattress.

[0029] Figure 7 This is a flowchart illustrating a control method for a smart mattress according to another embodiment of the present invention, for example... Figure 7 As shown, in this embodiment, the method includes steps S110-S150. That is, in this embodiment, the method further includes step S150 after step S140 in the above embodiment.

[0030] S150, Linking intelligent devices to cooperate with the vibration module to alleviate the pressure on the monitored object.

[0031] In this embodiment, the smart device includes a smart speaker and an aromatherapy diffuser. Step S150 specifically includes: acquiring the heart rate of the monitored subject and generating audio beat white noise synchronized with the heart rate; controlling the smart speaker to play the audio beat white noise; calculating the atomization amount based on the pressure index; and controlling the aromatherapy diffuser based on the atomization amount, thereby achieving proactive and intelligent regulation of the monitored subject's emotions. Specifically, the heart rate data of the monitored subject is acquired in real time, and synchronized audio beat white noise is generated based on this heart rate. For example, if the monitored subject's heart rate is 62 BPM, the program will calculate and generate a periodic audio beat white noise with a fundamental frequency of 62 / 60 = 1.033 Hz. This audio beat white noise will be immediately sent to the smart speaker and played, guiding the monitored subject's breathing and heart rate rhythm to become smoother through hearing, thereby achieving a relaxation effect; at the same time, the required atomization amount is calculated based on the calculated real-time pressure index using a preset algorithm model. A common control strategy is to use the PID (Proportional-Integral-Derivative) algorithm, whose calculation formula can be simplified to: Atomization volume = Kp × e(t) + Ki × ∫e(t)dt + Kd × de(t) / dt, where e(t) represents the deviation between the pressure index and the set safety threshold. The calculated atomization volume command is sent to the aromatherapy diffuser, which precisely controls the operation of the ultrasonic atomizing plate and other components to release a fixed amount of soothing plant essential oil molecules into the environment. It should be noted that step S150 is implemented by the execution intervention module in the smart mattress.

[0032] In summary, in this embodiment, the stress index and sleep stage are obtained by sequentially processing, separating, and calculating the collected raw composite signals. Based on the processed target composite signal, heart rate variability characteristics, stress index, and sleep stage, the smart mattress is controlled, thereby constructing a complete closed-loop pathway from "imperceptible perception" to "precise assessment" and then to "dynamic intervention." This enables proactive and intelligent regulation of the monitored subject's emotions, that is, it achieves regulation of the monitored subject's emotions from the physical level to the psychological level.

[0033] Figure 8 This is a schematic block diagram of a control device 200 for a smart mattress provided in an embodiment of the present invention. For example... Figure 8 As shown, corresponding to the above-described control method for a smart mattress, the present invention also provides a control device 200 for a smart mattress. This control device 200 includes a unit for executing the above-described control method for a smart mattress, and the device can be configured in a smart mattress. Specifically, please refer to... Figure 8 The control device 200 of the smart mattress includes a data acquisition and processing unit 201, a separation and extraction unit 202, a calculation unit 203, and a control unit 204. Detailed descriptions of each functional module are as follows: The acquisition and processing unit 201 is used to acquire the original composite signal of the monitored object and process the original composite signal to obtain the target composite signal; The separation and extraction unit 202 is used to perform signal separation and feature extraction on the target composite signal to obtain heart rate variability features and microbody motion features; Calculation unit 203 is used to calculate stress index and sleep stage based on the heart rate variability characteristics and the microbody movement characteristics; Control unit 204 is used to control the smart mattress based on the target composite signal, the heart rate variability characteristics, the pressure index, and the sleep stage.

[0034] In one embodiment, the acquisition and processing unit 201 is specifically used for: The original composite signal is impedance-transformed to obtain the transformed composite signal. The noise signal in the converted composite signal is filtered out to obtain the filtered composite signal; The filtered composite signal is amplified to obtain an amplified composite signal; The amplified composite signal is converted from analog to digital to obtain the target composite signal.

[0035] In one embodiment, the separation and extraction unit 202 is specifically used for: The target composite signal is separated to obtain heart rate vibration signal and microbody motion signal; Extract the heart rate variability features from the heart rate vibration signal; Extract the micro-body motion features from the micro-body motion signal.

[0036] In one embodiment, the separation and extraction unit 202 is further configured to: The target composite signal is subjected to multi-level wavelet decomposition to obtain low-frequency coefficients and high-frequency coefficients representing different frequency components of the signal; The heart rate vibration signal is reconstructed using the low-frequency coefficients; The micro-body motion signal is reconstructed using the high-frequency coefficients.

[0037] In one embodiment, the separation and extraction unit 202 is further configured to: The peak value of the R wave in each heartbeat cycle of the heart rate vibration signal is identified, and the time interval between adjacent R waves is calculated to obtain the RR interval sequence; The RR interval sequence is cleaned to obtain a cleaned RR interval sequence; The heart rate variability features are calculated based on the cleaned RR interval sequence, wherein the heart rate variability features include heart rate time-domain features and heart rate frequency-domain features, and the heart rate time-domain features include low-frequency power, high-frequency power, and power ratio.

[0038] In one embodiment, the separation and extraction unit 202 is further configured to: The threshold of the microbody motion signal is calculated to obtain the microbody motion threshold; A peak detection algorithm is used to identify all pulse peak points and their position sequences in the micro-body motion signal that exceed the micro-body motion threshold, thereby obtaining a pulse peak sequence. The micro-movement characteristics are calculated based on the pulse peak sequence, wherein the micro-movement characteristics include the micro-movement frequency and the micro-movement detection pulse.

[0039] In one embodiment, the calculation unit 203 is specifically used for: The stress index is obtained by weighting the heart rate variability and the microbody movement characteristics. The sleep stage is determined based on the power ratio, the microbody movement frequency, and the microbody movement detection pulse.

[0040] In one embodiment, the computing unit 203 is further configured to: If the power ratio is within the range of the first preset ratio and the microbody movement frequency is less than the first preset microbody movement frequency, then the sleep stage is determined to be the deep sleep stage. If the power ratio is within the range of the second preset ratio and the micro-body movement detection pulse is the preset pulse duration, then the sleep stage is determined to be REM sleep. If the power ratio is within the range of the third preset ratio and the micro-body movement frequency is greater than the second preset micro-body movement frequency, then the sleep stage is determined to be the waking period, wherein the second preset micro-body movement frequency is greater than the first preset micro-body movement frequency.

[0041] In one embodiment, the control unit 204 is specifically used for: If the pressure index is greater than the preset pressure index and the duration is greater than the preset duration, then the vibration module in the smart mattress is activated and the vibration module vibrates at the first vibration frequency. If the sleep stage is deep sleep and the change in body pressure of the monitored object is less than the preset pressure change value within a preset time, then the deep sleep mode is entered. If the power ratio in the heart rate variability feature is greater than a preset power ratio and the microbody movement time is greater than a preset microbody movement time, then the vibration module is activated and the vibration module vibrates at a second vibration frequency, wherein the second vibration frequency is greater than the first vibration frequency, and the microbody movement time is calculated based on the microbody movement signal in the target composite signal.

[0042] In one embodiment, such as this embodiment, the control device 200 for the smart mattress further includes a linkage unit.

[0043] The linkage unit is used to link with intelligent devices to cooperate with the vibration module to relieve the pressure on the monitored object.

[0044] In one embodiment, the linkage unit is specifically used for: The heart rate of the monitored object is acquired, and white noise with an audio beat synchronized with the heart rate is generated; Control the smart speaker to play the audio beat white noise; The atomization amount is calculated based on the pressure index; The aroma diffuser is controlled according to the amount of atomization.

[0045] The control device for the aforementioned smart mattress can be implemented as a computer program, which can, for example... Figure 9 It runs on the smart mattress shown.

[0046] Please see Figure 9 , Figure 9 This is a schematic block diagram of a smart mattress provided in an embodiment of the present invention. The smart mattress 300 is a device capable of actively and intelligently adjusting the emotions of the monitored subject.

[0047] See Figure 9The smart mattress 300 includes a processor 302, a memory, and a network interface 305 connected via a system bus 301. The memory may include a non-volatile storage medium 303 and internal memory 304.

[0048] The non-volatile storage medium 303 may store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, it causes the processor 302 to execute a control method for a smart mattress.

[0049] The processor 302 provides computing and control capabilities to support the operation of the entire smart mattress 300.

[0050] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute a control method for a smart mattress.

[0051] This network interface 305 is used for network communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the smart mattress 300 to which the present invention is applied. The specific smart mattress 300 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0052] The processor 302 is used to run a computer program 3032 stored in a memory to implement any embodiment of the above-described control method for the smart mattress.

[0053] It should be understood that, in this embodiment of the invention, the processor 302 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0054] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0055] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform any embodiment of the control method for the smart mattress described above.

[0056] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0057] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0058] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0059] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0060] If the integrated unit example is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, 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 includes several instructions to cause a smart mattress to perform all or part of the steps of the methods described in the various embodiments of the present invention.

[0061] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0062] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0063] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A control method for a smart mattress, characterized in that, include: The original composite signal of the monitored object is acquired, and the original composite signal is processed to obtain the target composite signal; The target composite signal is subjected to signal separation and feature extraction to obtain heart rate variability features and microbody motion features; The stress index and sleep stage are calculated based on the heart rate variability and microbody movement characteristics. The smart mattress is controlled based on the target composite signal, the heart rate variability characteristics, the stress index, and the sleep stage.

2. The control method for the smart mattress according to claim 1, characterized in that, The step of processing the original composite signal to obtain the target composite signal includes: The original composite signal is impedance-transformed to obtain the transformed composite signal. The noise signal in the converted composite signal is filtered out to obtain the filtered composite signal; The filtered composite signal is amplified to obtain an amplified composite signal; The amplified composite signal is converted from analog to digital to obtain the target composite signal.

3. The control method for the smart mattress according to claim 1, characterized in that, The steps of performing signal separation and feature extraction on the target composite signal to obtain heart rate variability features and microbody motion features include: The target composite signal is separated to obtain heart rate vibration signal and microbody motion signal; Extract the heart rate variability features from the heart rate vibration signal; Extract the micro-body motion features from the micro-body motion signal.

4. The control method for the smart mattress according to claim 3, characterized in that, The step of separating the target composite signal to obtain the heart rate vibration signal and the microbody motion signal includes: The target composite signal is subjected to multi-level wavelet decomposition to obtain low-frequency coefficients and high-frequency coefficients representing different frequency components of the signal; The heart rate vibration signal is reconstructed using the low-frequency coefficients; The micro-body motion signal is reconstructed using the high-frequency coefficients.

5. The control method for the smart mattress according to claim 3, characterized in that, The step of extracting heart rate variability features from the heart rate vibration signal includes: The peak value of the R wave in each heartbeat cycle of the heart rate vibration signal is identified, and the time interval between adjacent R waves is calculated to obtain the RR interval sequence; The RR interval sequence is cleaned to obtain a cleaned RR interval sequence; The heart rate variability features are calculated based on the cleaned RR interval sequence, wherein the heart rate variability features include heart rate time-domain features and heart rate frequency-domain features, and the heart rate time-domain features include low-frequency power, high-frequency power, and power ratio.

6. The control method for the smart mattress according to claim 5, characterized in that, The step of extracting the micro-body motion features from the micro-body motion signal includes: The threshold of the microbody motion signal is calculated to obtain the microbody motion threshold; A peak detection algorithm is used to identify all pulse peak points and their position sequences in the micro-body motion signal that exceed the micro-body motion threshold, thereby obtaining a pulse peak sequence. The micro-movement characteristics are calculated based on the pulse peak sequence, wherein the micro-movement characteristics include the micro-movement frequency and the micro-movement detection pulse.

7. The control method for the smart mattress according to claim 6, characterized in that, The steps of calculating the stress index and sleep stage based on the heart rate variability and the microbody movement characteristics include: The stress index is obtained by weighting the heart rate variability and the microbody movement characteristics. The sleep stage is determined based on the power ratio, the microbody movement frequency, and the microbody movement detection pulse.

8. The control method for the smart mattress according to claim 7, characterized in that, The step of determining the sleep stage based on the power ratio, the microbody movement frequency, and the microbody movement detection pulse includes: If the power ratio is within the range of the first preset ratio and the microbody movement frequency is less than the first preset microbody movement frequency, then the sleep stage is determined to be the deep sleep stage. If the power ratio is within the range of the second preset ratio and the micro-body movement detection pulse is the preset pulse duration, then the sleep stage is determined to be REM sleep. If the power ratio is within the range of the third preset ratio and the micro-body movement frequency is greater than the second preset micro-body movement frequency, then the sleep stage is determined to be the waking period, wherein the second preset micro-body movement frequency is greater than the first preset micro-body movement frequency.

9. The control method for the smart mattress according to claim 1, characterized in that, The step of controlling the smart mattress based on the target composite signal, the heart rate variability characteristics, the pressure index, and the sleep stage includes: If the pressure index is greater than the preset pressure index and the duration is greater than the preset duration, then the vibration module in the smart mattress is activated and the vibration module vibrates at the first vibration frequency. If the sleep stage is deep sleep and the change in body pressure of the monitored object is less than the preset pressure change value within a preset time, then the deep sleep mode is entered. If the power ratio in the heart rate variability feature is greater than a preset power ratio and the microbody movement time is greater than a preset microbody movement time, then the vibration module is activated and the vibration module vibrates at a second vibration frequency, wherein the second vibration frequency is greater than the first vibration frequency, and the microbody movement time is calculated based on the microbody movement signal in the target composite signal.

10. The control method for the smart mattress according to claim 9, characterized in that, After the step of activating the vibration module and causing the vibration module to vibrate at the second vibration frequency if the power ratio in the heart rate variability feature is greater than a preset power ratio and the microbody movement time is greater than a preset microbody movement time, the method further includes: The intelligent device is linked to work with the vibration module to relieve the pressure on the monitored object.

11. The control method for the smart mattress according to claim 10, characterized in that, The smart device includes a smart speaker, and the step of linking the smart device to cooperate with the vibration module to relieve the pressure on the monitored object includes: The heart rate of the monitored object is acquired, and white noise with an audio beat synchronized with the heart rate is generated; Control the smart speaker to play the audio beat white noise.

12. The control method for the smart mattress according to claim 10, characterized in that, The smart device also includes an aromatherapy diffuser, and the step of linking the smart device to work with the vibration module to relieve the pressure on the monitored object includes: The atomization amount is calculated based on the pressure index; The aroma diffuser is controlled according to the amount of atomization.

13. A control system based on a smart mattress, comprising a smart mattress and a smart device, wherein the smart mattress is used to execute, for example, the control method of the smart mattress according to any one of claims 1-12, and the smart device comprises a smart speaker and an aromatherapy diffuser, wherein the smart speaker and the aromatherapy diffuser are linked with the smart mattress.

14. The control system based on a smart mattress according to claim 13, wherein the smart mattress is provided with a piezoelectric thin film sensor array and a signal conditioning circuit, the piezoelectric thin film sensor array is used to collect the original composite signal of the monitored object, and the signal conditioning circuit is used to process the original composite signal.

Images