State control method, device, equipment, medium and product

Abstract

The invention discloses a state control method, device and equipment, a medium and a product. The method comprises the following steps: acquiring a first ballistocardiogram signal; performing preprocessing and feature extraction on the first ballistocardiogram signal to obtain a first physiological feature parameter contained in the first ballistocardiogram signal; processing the first physiological feature parameter through a sleep staging model to obtain a sleep staging result of the user; when the sleep staging result indicates that the user is in a set sleep period, processing the first physiological feature parameter through a pressure evaluation model to obtain a pressure level of the user; and when the pressure level exceeds a set level, determining that the user is in an abnormal sleep state, and controlling intervention equipment to work according to a working mode indicated by a target intervention strategy. According to the method, the sleep abnormal state can be automatically identified and timely intervention is implemented, so that the sleep quality is improved.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to a state control method, device, equipment, medium, and product. Background Technology

[0002] Nightmares are disturbing dream experiences that occur during sleep, causing awakening, increased heart rate, fear, and severe disruption of sleep structure.

[0003] Currently, some technologies use wearable devices (such as smart bracelets) to monitor heart rate variability (HRV) to infer the occurrence of nightmares. However, such methods are easily affected by the user's movements during sleep, leading to distorted HRV monitoring data and affecting the accuracy of judging sleep abnormalities such as nightmares. In addition, some smart home systems attempt to use sound or light to assist sleep, but these are mostly timed or manually triggered, lacking accurate judgment of the user's sleep cycle and physiological state, making it difficult to identify and intervene in abnormal sleep states in a timely and accurate manner. Summary of the Invention

[0004] This invention provides a state control method, apparatus, device, medium, and product to address the problem of intervention in abnormal sleep states.

[0005] According to one aspect of the present invention, a state control method is provided, comprising:

[0006] Acquire the first cardiac impact signal, which includes cardiac impact signals during the user's sleep on the mattress;

[0007] The first cardiac impact signal is preprocessed and its features are extracted to obtain the first physiological feature parameters contained in the first cardiac impact signal.

[0008] The sleep staging result of the user is obtained by processing the first physiological characteristic parameter through a sleep staging model;

[0009] When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is processed by a stress assessment model to obtain the user's stress level. The set sleep period includes the REM sleep period.

[0010] When the pressure level exceeds a set level, it is determined that the user is in a sleep abnormal state, and the intervention device is controlled to work in accordance with the working mode indicated by the target intervention strategy. The intervention device includes a device for intervening in the user's sleep.

[0011] According to another aspect of the present invention, a state control device is provided, comprising:

[0012] The acquisition module is used to acquire the first cardiac impact signal, which includes the cardiac impact signal during the user's sleep on the mattress.

[0013] The preprocessing module is used to preprocess and extract features from the first cardiac impact signal to obtain the first physiological feature parameters contained in the first cardiac impact signal.

[0014] The first processing module is used to process the first physiological characteristic parameters through a sleep staging model to obtain the sleep staging result of the user.

[0015] The second processing module is used to process the first physiological characteristic parameter through a stress assessment model to obtain the user's stress level when the sleep staging result indicates that the user is in a set sleep period, wherein the set sleep period includes the rapid eye movement (REM) period.

[0016] The determination module is used to determine that the user is in a sleep abnormal state when the pressure level exceeds a set level, and to control the intervention device to work in accordance with the working mode indicated by the target intervention strategy, wherein the intervention device includes a device for intervening in the user's sleep.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the method described in any embodiment of the present invention.

[0023] The technical solution of this invention acquires a first cardiac impact signal, preprocesses and extracts features from the first cardiac impact signal to obtain a first physiological characteristic parameter contained in the first cardiac impact signal. By extracting and quantifying the physiological information contained in the first cardiac impact signal, a first physiological characteristic parameter that can accurately reflect the user's sleep state is obtained, improving the accuracy of judging the user's sleep cycle and physiological state. The first physiological characteristic parameter is processed by a sleep staging model to obtain the user's sleep staging result. By judging whether the user is in a set sleep period, it is further judged whether the user is in an abnormal sleep state, improving the accuracy of judging the user's sleep state. When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is processed by a stress assessment model to obtain the user's stress level. By assessing the user's stress level, the first physiological characteristic parameter is quantified and mapped to the corresponding stress level, facilitating timely intervention. When the stress level exceeds a set level, it is determined that the user is in an abnormal sleep state, and the intervention device is controlled to work according to the working mode indicated by the target intervention strategy. This enables timely judgment of whether the user is in an abnormal sleep state and timely intervention, thereby minimizing the impact of the abnormal sleep state on the user and improving sleep quality.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a scene diagram of a state control method provided in an embodiment of the present invention;

[0027] Figure 2 This is a flowchart of a state control method provided in Embodiment 1 of the present invention;

[0028] Figure 3 This is a flowchart of a state control method provided in Embodiment 2 of the present invention;

[0029] Figure 4 This is a flowchart of a state control method provided in an embodiment of the present invention;

[0030] Figure 5This is a schematic diagram of the structure of a state control device provided in Embodiment 3 of the present invention;

[0031] Figure 6 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Figure 1 This is a scene diagram of a state control method provided in an embodiment of the present invention. For example... Figure 1As shown, the built-in sensor array in the smart mattress (i.e., the mattress itself) first collects the user's original Ballistocardiogram (BCG) signal, i.e., the first cardiac impact signal, and sends it to the signal conditioning circuit in the electronic device for preprocessing (such as filtering) to obtain the BCG signal. Subsequently, the algorithm module in the microprocessor processes the BCG signal: the feature extraction module extracts the first physiological characteristic parameters; the sleep cycle recognition module identifies the user's sleep cycle based on the first physiological characteristic parameters. The sleep cycle can include: wakefulness, non-rapid eye movement (NREM) sleep (including sleep onset (N1 stage), light sleep (N2 stage), and deep sleep (N3 stage)), and rapid eye movement (REM) sleep. When the user is in a set sleep cycle, i.e., a set sleep period, the stress assessment module assesses the user's stress level based on the first physiological characteristic parameters. If the stress level exceeds the set level, it is determined that the user is in an abnormal sleep state. The microprocessor issues an intervention command, which, according to the user's preset configuration through the user terminal application software, calls upon the corresponding smart home devices to perform sleep intervention on the user and execute the intervention operation. An abnormal sleep state can be an abnormal physiological state that occurs during the user's sleep. Abnormal sleep states can manifest as, for example, a sudden increase in heart rate over a certain period of time, or an abnormally elevated ratio of low-frequency power to high-frequency power in heart rate variability. Intervention actions can be operations performed by intervention devices according to instructions sent by electronic devices. Intervention actions include, but are not limited to, actions that improve the user's sleep quality, such as brightening lights, turning on a smart speaker, or having the mattress vibrate.

[0035] The acquisition, storage, use, and processing of data in the technical solution of this invention all comply with the relevant provisions of relevant laws and regulations.

[0036] Example 1

[0037] Figure 2 This is a flowchart of a state control method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where intervention is needed for users in abnormal sleep states. The method can be executed by a state control device, which can be implemented in hardware and / or software and can be configured in an electronic device. The electronic device can be, for example, a mattress control box. Figure 2 As shown, the method includes:

[0038] S110. Acquire the first cardiac impact signal, which includes the cardiac impact signal during the user's sleep on the mattress.

[0039] In this embodiment, the first cardiac impact signal can be a cardiac impact signal collected during the user's sleep. The first cardiac impact signal can be collected by a sensor array mounted in the mattress, without requiring the user to wear a sensor device. The first cardiac impact signal reflects the minute vibrations of the body caused by heartbeat and blood flow, containing rich physiological information such as heart rate, respiratory rate, and cardiac impact force.

[0040] Specifically, the sensor array in the mattress collects the user's first cardiac impact signal during sleep in real time and sends it to electronic devices for further processing via methods such as Bluetooth.

[0041] S120. The first cardiac impact signal is preprocessed and its features are extracted to obtain the first physiological feature parameters contained in the first cardiac impact signal.

[0042] In this embodiment, the first physiological characteristic parameter can be a physiological characteristic parameter of the user during sleep. The first physiological characteristic parameter is extracted from the first cardiac impact signal and includes, but is not limited to, at least one of: heart rate, heart rate variability, respiratory rate, respiratory pattern, and body movement signal.

[0043] In this embodiment, the breathing pattern can be a specific manner and rhythm exhibited by the human body during gas exchange. The breathing pattern reflects characteristics such as the depth, frequency, and rhythm of breathing. Body movement signals can be signals generated by human activity. The amplitude of body movement signals is much greater than the vibrations generated by basic life activities such as heartbeat and breathing.

[0044] Specifically, physiological characteristics include one or more of the following: heart rate, heart rate variability, respiratory rate, respiratory pattern, and body movement signals.

[0045] Specifically, the first cardiac impact signal is preprocessed, including but not limited to noise reduction and filtering (such as using a low-pass filter). Feature extraction is performed on the preprocessed first cardiac impact signal to separate waveforms representing different physiological characteristic parameters. The peaks, troughs, and periods of the separated signals are calculated, or these are used as the first physiological characteristic parameters.

[0046] For example, feature extraction of the first cardiac impact signal can be performed by: using variational mode decomposition to separate the components corresponding to the first physiological characteristic parameter from the mixed BCG signal. Then, peaks and troughs are detected in the time domain, or the dominant frequency is analyzed using fast Fourier transform in the frequency domain to determine the first physiological characteristic parameter.

[0047] S130. The first physiological characteristic parameter is processed by the sleep staging model to obtain the sleep staging result of the user.

[0048] In this embodiment, the sleep staging model can be a model used to determine the user's current sleep cycle. The sleep staging model can be built into the microprocessor of an electronic device, determining the user's sleep cycle by analyzing the input first cardiac impulse signal. The sleep staging model can be a machine learning model, such as a support vector machine, random forest, or deep learning model. The sleep staging result can be an indication of the user's current sleep cycle. The sleep staging result is output by the sleep staging model, and can be mapped to a string of values ​​for output, for example, REM sleep can be mapped to 00.

[0049] Specifically, all or a selection of primary physiological characteristic parameters are input into the sleep staging model. The sleep staging model analyzes the primary physiological characteristic parameters and, based on the correspondence between the primary physiological characteristic parameters and sleep cycles, obtains the user's current sleep cycle and determines the sleep staging result.

[0050] For example, the sleep staging model first sorts the first physiological characteristic parameters according to time sequence, and uses its built-in classification algorithm (such as support vector machine, trained neural network or specific clustering model) to perform in-depth analysis on these characteristic sequences, identify the feature combinations and change patterns related to different sleep cycles, and calculate the probability that the user's current sleep cycle is one of each sleep cycle, and determines the sleep cycle with the highest probability as the sleep cycle indicated by the sleep staging result.

[0051] S140. When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is processed by a stress assessment model to obtain the user's stress level. The set sleep period includes the REM sleep period.

[0052] In this embodiment, the set sleep period can be a preset sleep cycle for stress assessment of the user. The set sleep period can be, for example, the REM sleep cycle. The stress assessment model can be a model used to assess the user's current emotional stress state. The stress assessment model compares the variation of the first physiological characteristic parameter with a preset threshold based on the input first physiological characteristic parameter to determine the user's stress level, and can be built into the microprocessor of an electronic device. The stress level can be a grading index quantified from the first physiological characteristic parameter. The stress level reflects the level of the user's emotional stress state. Stress levels include, but are not limited to, high stress levels and normal stress levels. When the stress level is high, the user is in an abnormal sleep state, that is, the user is experiencing a nightmare.

[0053] Specifically, when the sleep staging results indicate that the user is in a set sleep period, the first physiological characteristic parameter is input into the stress assessment model. The stress assessment model calculates the range of change of the first physiological characteristic parameter over a period of time, and determines the stress level based on the range of values ​​that the range of change falls into.

[0054] For example, when the ratio of low-frequency power to high-frequency power in heart rate variability, or when the heart rate increases significantly within a set period, such as half an hour, and the magnitude of the change exceeds a preset threshold, the user is determined to be in a high stress level.

[0055] S150. When the pressure level exceeds a set level, determine that the user is in an abnormal sleep state, and control the intervention device to work in accordance with the working mode indicated by the target intervention strategy. The intervention device includes a device for intervening in the user's sleep.

[0056] In this embodiment, the set pressure level can be a pressure threshold level. When the pressure level exceeds the set level (such as the normal pressure level), it is determined that the user is in an abnormal sleep state, and intervention is then initiated. The intervention device can be any device that intervenes on the user. Intervention devices include, but are not limited to, smart mattresses, smart curtains, smart speakers, smart lights, or mobile phones. The target intervention strategy can be a set of pre-designed intervention operations. The target intervention strategy can be set by the user in advance on a mobile application and implemented by calling different intervention devices.

[0057] Specifically, if the pressure level exceeds a set level, the microprocessor determines that the user is currently in an abnormal sleep state and sends a command to the intervention device. This command instructs the intervention device to intervene on the user according to the target intervention strategy. The intervention device receives the command from the electronic device and intervenes on the user accordingly. The purpose of the intervention is to gently awaken the user from the nightmare state, but not to the point of complete wakefulness, minimizing the impact of the abnormal sleep state on the user and improving sleep quality.

[0058] In this embodiment, there can be multiple intervention devices. The electronic device can send instructions to the intervention devices according to the intervention timing of each device. Alternatively, the electronic device can immediately send instructions to the intervention devices after determining that the user is in an abnormal sleep state, to control the intervention devices to operate according to the target intervention strategy. The instructions can specify the intervention timing, such as when the intervention device should operate according to the target intervention strategy, or the intervention device can directly operate according to the target intervention strategy immediately after receiving the instructions.

[0059] For example, the process of an intervention device intervening in a user according to a target intervention strategy can be as follows: after receiving an instruction, the intervention device operates according to the working method indicated by the instruction. When the intervention device is a smart light, the instruction can trigger the smart light to operate according to the target intervention strategy, such as controlling the brightness and color of the light. When the intervention device is a smart speaker, the instruction can trigger the smart speaker to operate according to the target intervention strategy, such as controlling the music played and the decibel level.

[0060] Optionally, the target intervention strategy includes one or more of the following: intervention timing, target intensity, and target intervention mode; wherein the intervention timing is related to the length of the set time window used by the stress assessment model.

[0061] In this embodiment, the intervention timing can be the time when the intervention operation is executed. The intervention timing could be, for example, when the user is in a state of abnormal sleep, or when the user exhibits signs of an abnormal sleep state but is not actually in a state of abnormal sleep. The target intensity can be the intensity at which the intervention device performs the intervention operation. The target intensity can be expressed as the decibel level of a smart speaker, the vibration intensity of a smart mattress, or the brightness of a smart light. The target intensity and intervention timing can be determined by the user or fine-tuned by an algorithm based on the execution effects of previous intervention operations. The target intervention mode can be the execution mode of the intervention operation. Target intervention modes include, but are not limited to, sound and light intervention modes and vibration intervention modes. Different target intervention modes invoke different intervention devices; in the sound and light intervention mode, the smart light and smart speaker are invoked respectively, and in the vibration intervention mode, the smart mattress is invoked.

[0062] Setting a time window allows for the effective time period used for stress assessment. The length of the time window determines the timing of intervention. If the time window is shorter than a preset threshold, the stress assessment results better reflect short-term changes in stress levels; that is, intervention occurs as soon as the user is detected to be in a sleep disturbance state, meaning intervention happens while the user is already in a sleep disturbance state. If the time window is longer than the preset threshold, the stress assessment results reflect the persistent state of stress and can identify early signs of sleep disturbances; intervention occurs when these signs appear.

[0063] Specifically, the target intervention strategy includes at least one of the following: intervention timing, target intensity, and target intervention mode. All of these can be set by the user or adjusted by the algorithm based on previous intervention results.

[0064] For example, electronic devices continuously record each executed target intervention strategy and its corresponding actual effects (e.g., the rate of decrease in the user's stress level, whether the rate of decrease reaches the expected target, and user feedback). Based on this, methods such as Bessel functions are used to adjust the timing and intensity of intervention in the target intervention strategy.

[0065] Optionally, the determination of the target intervention strategy includes:

[0066] In response to the user's selection of an intervention mode in the intervention settings interface, the selected intervention mode is taken as the target intervention mode;

[0067] In response to the user's selection of intervention intensity in the intervention settings interface, the selected intervention intensity is taken as the target intensity.

[0068] In this embodiment, the intervention settings interface can be an interactive interface for users to intervene in relevant settings. The intervention settings interface can be displayed on a mobile terminal such as a smartphone. After the settings are completed, the mobile terminal sends the user-set intervention settings to the electronic device. Alternatively, the intervention settings interface can be displayed on an electronic device. The intervention mode and intensity can be set via the electronic device.

[0069] The intervention mode can be the intervention method specified by the user in the intervention settings interface. Intervention modes include, but are not limited to, vibration modes and sound and light modes. The intervention intensity can be the intensity at which the intervention device performs its operation, specified by the user in the intervention settings interface. Intervention intensity can be expressed as light intensity, decibels, or vibration intensity. After the settings are completed, the terminal device sends the intervention-related settings, including the intervention mode and intervention intensity, to the electronic device. The electronic device reads the settings, determines the intervention mode as the target intervention mode, and sets the intervention intensity as the target intensity.

[0070] The selection of intervention modes can be a human-computer interaction operation on the interface. There are no restrictions on the operation method; it can be voice control or inputting or selecting options in the intervention settings interface.

[0071] Specifically, users select the intervention mode and intensity in the intervention settings interface and send them to the electronic device via their mobile terminal. After receiving the data, the electronic device sets the intervention mode and intensity as the target intervention mode and target intensity, respectively.

[0072] The technical solution of this invention acquires a first cardiac impact signal, preprocesses and extracts features from the first cardiac impact signal to obtain a first physiological characteristic parameter contained in the first cardiac impact signal. By extracting and quantifying the physiological information contained in the first cardiac impact signal, a first physiological characteristic parameter that can accurately reflect the user's sleep state is obtained, improving the accuracy of judging the user's sleep cycle and physiological state. The first physiological characteristic parameter is processed by a sleep staging model to obtain the user's sleep staging result. By judging whether the user is in a set sleep period, it is further judged whether the user is in an abnormal sleep state, improving the accuracy of judging the user's sleep state. When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is processed by a stress assessment model to obtain the user's stress level. By assessing the user's stress level, the first physiological characteristic parameter is quantified and mapped to the corresponding stress level, facilitating timely intervention. When the stress level exceeds a set level, it is determined that the user is in an abnormal sleep state, and the intervention device is controlled to work according to the working mode indicated by the target intervention strategy. This enables timely judgment of whether the user is in an abnormal sleep state and timely intervention, thereby minimizing the impact of the abnormal sleep state on the user and improving sleep quality.

[0073] Example 2

[0074] Figure 3 This is a flowchart of a state control method provided in Embodiment 2 of the present invention. This embodiment is an optimization based on any of the above embodiments, and mainly includes: a detailed description of the process of determining the pressure level, determining the pressure level based on the heart rate variability within a set time window, and optimizing the target intervention strategy based on the effect of the intervention after intervention. It should be noted that technical details not described in detail in this embodiment can be found in any of the above embodiments. Figure 3 As shown, the method includes:

[0075] S210. Acquire the first cardiac impact signal, which includes the cardiac impact signal during the user's sleep on the mattress.

[0076] S220. The first cardiac impact signal is preprocessed and its features are extracted to obtain the first physiological feature parameters contained in the first cardiac impact signal.

[0077] S230. The first physiological characteristic parameter is processed by the sleep staging model to obtain the sleep staging result of the user.

[0078] S240. When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is input into the stress assessment model. The stress assessment model determines whether the first physiological characteristic parameter exceeds a set stress threshold. If so, the user's stress level is determined to be a first level; otherwise, the user's stress level is determined to be a second level. Wherein, the first level is greater than the second level, and the second level is the set level.

[0079] In this embodiment, the pressure threshold can be a critical value used to determine whether the user's primary physiological characteristic parameter is abnormal. The pressure threshold can be set empirically or determined based on historical data with added redundancy; this invention does not impose any restrictions on this. The first level is the high pressure level, at which point the user is in an abnormal sleep state and intervention is required. The second level is the normal pressure level. The first level is greater than the second level; when the user's pressure level is the second level, the user's primary physiological characteristic parameter is normal.

[0080] Specifically, the stress assessment model maps the first physiological characteristic parameter to a stress level based on whether the change in the first physiological characteristic parameter exceeds a set stress threshold, and determines the stress level as either Level 1 or Level 2.

[0081] Optionally, the step of inputting the first physiological characteristic parameter into the stress assessment model and determining whether the first physiological characteristic parameter exceeds a set stress threshold through the stress assessment model includes: inputting the heart rate variability in the first physiological characteristic parameter into the stress assessment model and determining whether the heart rate variability within a set time window exceeds a set stress threshold through the stress assessment model.

[0082] Specifically, the heart rate variability (HRV) within the first physiological characteristic parameter of a set time window can be used to determine whether it exceeds a set stress threshold. For example, the ratio of low-frequency power to high-frequency power in HRV is calculated. If the change exceeds the set stress threshold within half an hour, the user is judged to be in level one. Judging by calculating the magnitude of HRV changes within a set time window can effectively smooth out transient interference caused by brief body movements or signal noise, enhancing the system's anti-interference capability. Furthermore, HRV-based judgment accurately reflects the user's true and continuous stress accumulation, improving the accuracy of stress assessment results.

[0083] S250. When the pressure level exceeds a set level, determine that the user is in an abnormal sleep state, and control the intervention device to work in accordance with the working mode indicated by the target intervention strategy, wherein the intervention device includes a device for intervening in the user's sleep.

[0084] S260. Obtain the second cardiac impact signal after the intervention device operates according to the target intervention strategy.

[0085] In this embodiment, the second cardiac impact signal can be the cardiac impact signal of the user collected after the intervention. The second cardiac impact signal reflects the execution result of the intervention operation, is collected by a sensor array in the mattress, and sent to an electronic device.

[0086] Specifically, after the intervention is completed, the electronic device acquires the second impact signal transmitted by the mattress.

[0087] S270. The second cardiac impact signal is preprocessed and its features are extracted to obtain the second physiological feature parameters.

[0088] In this embodiment, the second physiological characteristic parameter can be the physiological characteristic parameter of the user after the intervention operation is performed. The second physiological characteristic parameter can be extracted from the second cardiac impact signal.

[0089] Specifically, the second cardiac impact signal is preprocessed, such as by noise reduction and filtering. The preprocessed second cardiac impact signal is then separated into different sub-signals corresponding to different second physiological characteristic parameters, and its peaks, troughs and periods are calculated to obtain the second physiological characteristic parameters.

[0090] Optionally, the physiological characteristics include one or more of the following:

[0091] Heart rate; heart rate variability; respiratory rate; respiratory pattern; body movement signals.

[0092] Specifically, the physiological characteristics of the user described by the first and second physiological characteristic parameters may include: heart rate, heart rate variability, respiratory rate, respiratory pattern and / or body movement signals.

[0093] S280. Determine whether the user's sleep state is a set state based on the second physiological characteristic parameter, wherein the set state indicates that the user is in a stable sleep state; if not, adjust the target intervention strategy; wherein, in the set state, one or more of the following conditions are met: the second physiological characteristic parameter is within a set range within a set duration, and the change in the second physiological characteristic parameter is less than a set threshold; the user is in a light sleep stage or a deep sleep stage in the sleep cycle; the pressure level corresponding to the second physiological characteristic parameter is less than or equal to the set level.

[0094] In this embodiment, the set state can indicate that the user is in a non-abnormal sleep state during sleep, i.e., a stable sleep state. When the user is in the set state, no external intervention is required. The set state can be, for example, a heart rate change within a set duration that is less than a set threshold, or the user being in stage N2 or N3 of a sleep cycle. The set range can be a numerical interval representing that the user is not in an abnormal sleep state. The set range can be set based on experience or determined by a deep learning model based on the user's historical physiological characteristics; this invention does not impose any limitations on this.

[0095] Specifically, when the second physiological characteristic parameter determines that the user is in the set state, it indicates that the user is in stable sleep and has recovered from the abnormal sleep state, and the intervention is successful. When the user is not in the set state, the intervention fails. The electronic device records the timing and intensity of the intervention at this time, and adjusts the timing and intensity of the intervention in the target intervention strategy using methods such as Bessel functions, so that the adjusted target intervention strategy can achieve better intervention effects in subsequent applications.

[0096] The set duration can be a pre-defined duration that reflects whether the second physiological characteristic parameter is stable. If the second physiological characteristic parameter is within a set range within the set duration, and the change in the second physiological characteristic parameter is less than a set threshold, it can be considered a physiological indicator of the user, such as a gradually stabilizing heart rate.

[0097] The technical solution of this invention involves acquiring a first cardiac impact signal; preprocessing and extracting features from the first cardiac impact signal to obtain a first physiological characteristic parameter contained in the first cardiac impact signal; processing the first physiological characteristic parameter through a sleep staging model to obtain the user's sleep staging result; when the sleep staging result indicates that the user is in a set sleep stage, inputting the first physiological characteristic parameter into a stress assessment model, determining whether the stress level is level one or level two based on a set stress threshold, and using the set stress threshold to determine the user's current stress level, thereby achieving standardized and quantitative assessment of the user's stress state and ensuring consistency in stress assessment results; when the stress level exceeds the set level, determining that the user is in an abnormal sleep state, and controlling the intervention device to work according to the working mode indicated by the target intervention strategy; continuously monitoring the user's second BCG signal after intervention and extracting the second physiological characteristic parameter to determine whether the user's sleep state is in the set state; if not, adjusting the target intervention strategy; and adjusting the target intervention strategy based on the feedback of the intervention results to achieve adaptive optimization of the target intervention strategy and improve the effectiveness of the intervention.

[0098] In another embodiment, Figure 4This is a flowchart of a state control method provided by an embodiment of the present invention. First, the electronic device is powered on, and the mattress continuously collects a first BCG signal. A first physiological characteristic parameter is extracted based on the first BCG signal. The first physiological characteristic parameter is input into a sleep staging model. If the output sleep staging result indicates that the user is not in the REM stage, the first BCG signal continues to be collected. If the user is currently in the REM stage, the user's stress level is determined based on the first physiological characteristic parameter. If the user's stress level does not exceed a set level, the first BCG signal continues to be collected. If the user's stress level exceeds the set level, intervention is performed on the user according to the target intervention strategy. After the intervention is completed, the user's second BCG signal is continuously monitored and the second physiological characteristic parameter is extracted to determine the current stress level. If several interventions are unsuccessful, the timing and intensity of the intervention are recorded, and the target intervention strategy is optimized.

[0099] The present invention is described below by way of example, where “BCG raw signal” represents “first cardiac impact signal”:

[0100] Nightmares are disturbing dream experiences that occur during REM sleep, causing awakening, increased heart rate, fear, and severe disruption of sleep structure.

[0101] Existing technologies include methods that use wearable devices (such as smart bracelets) to monitor heart rate variability (HRV) to infer the occurrence of nightmares. However, these devices require users to wear them, which may cause discomfort, disrupt sleep, and the signal is easily lost when turning over in sleep. Furthermore, some smart home systems attempt to use sound or light for sleep assistance, but these are mostly timed or manually triggered, lacking accurate judgment of the user's sleep stage and physiological state, and thus unable to provide effective and timely intervention at the critical moment when nightmares occur.

[0102] Therefore, there is an urgent need in this field for a non-invasive, high-precision technical solution that can automatically identify potential nightmares and implement personalized interventions.

[0103] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a non-invasive, wear-free nightmare recognition and intervention system and method based on mattress-embedded sensors. This system can accurately identify REM sleep patterns and, combined with BCG signal analysis of emotional stress levels, implement gentle intervention before nightmares cause complete awakening, thereby minimizing sleep disturbances and improving sleep quality.

[0104] This invention relates to the fields of smart home, medical health and sleep assistance technology, and can automatically identify when a user is in REM sleep and accompanied by high emotional stress (i.e. potential nightmares) and activate a user-defined intervention program to improve sleep quality.

[0105] To achieve the above objectives, the present invention mainly includes the following parts:

[0106] Signal acquisition module: A high-sensitivity pressure sensor array integrated into the mattress for continuous, non-contact acquisition of the user's BCG signals. BCG signals are the subtle vibrations of the body caused by heartbeats and blood flow, containing rich physiological information such as heart rate, respiratory rate, and cardiac impact force.

[0107] Signal processing and feature extraction module: Connected to the sensor, it is used to denoise and filter the raw BCG signal and extract key physiological features from it, including but not limited to:

[0108] (1) Heart rate and heart rate variability: especially the low frequency (LF), high frequency (HF) power and their ratio (LF / HF) in HRV, which are core indicators for assessing autonomic nervous system activity and emotional stress.

[0109] (2) Respiratory rate and respiratory pattern: Irregular changes in respiratory rhythm can be used as an auxiliary judgment of stress response.

[0110] (3) Body movement signals: used to help determine the sleep stage and the time of awakening.

[0111] Sleep Stage and Stress Recognition Module: This is the core computing unit (such as a microprocessor) with a built-in algorithm model. This module receives data from the feature extraction module and performs the following judgments:

[0112] (1) Sleep stage segmentation: Based on features such as HRV, breathing (i.e., respiratory rate and breathing pattern), and body movement (i.e. body movement signal), machine learning algorithms (such as support vector machine SVM, random forest or deep learning model) are used to automatically divide sleep into wakefulness, non-rapid eye movement (N1 stage, N2 stage, N3 stage) and rapid eye movement (REM stage).

[0113] (2) Emotional stress assessment: Establish a stress assessment model based on HRV characteristics (such as a significant increase in the LF / HF ratio and a sudden acceleration of heart rate). When these characteristic values ​​exceed the preset personalized threshold during the REM period, it is determined that the user is in a state of high emotional stress and is likely experiencing a nightmare.

[0114] User Configuration and Interaction Module: Provides users with a terminal application. Users can access this application through:

[0115] (1) Select intervention mode: Choose the preferred intervention mode from "vibration wake-up", "light wake-up", "music wake-up" or a combination of modes.

[0116] (2) Set the intervention intensity: such as vibration intensity, light brightness / color temperature, music volume / type.

[0117] (3) Review the sleep report: review the sleep structure, potential nightmare events and intervention records for each night.

[0118] Intelligent intervention execution module: Receives instructions from the recognition module and user configuration preferences, and activates the corresponding intervention device.

[0119] (1) Vibration unit: The built-in miniature linear motor of the mattress can generate a variety of vibration modes from weak to strong.

[0120] (2) Sound and light unit: Smart lamps (such as bedside lamps) and speakers that are linked with the system can emit gradually changing soft light or play soothing music / natural sounds.

[0121] Data storage and communication module: Used to store users' physiological data, sleep models, personalized thresholds and intervention history, and supports data synchronization with users' mobile apps and cloud servers via Wi-Fi / Bluetooth.

[0122] The method described in this invention includes the following steps:

[0123] 1. Continuous signal acquisition: The user's raw BCG signal is continuously and imperceptibly acquired through mattress sensors.

[0124] 2. Signal processing and feature extraction: The signal is preprocessed and physiological parameters such as heart rate, HRV, and respiratory rate (i.e., the first physiological characteristic parameters) are calculated in real time.

[0125] 3. Real-time sleep staging: Using an algorithm model (i.e., sleep staging model), the current sleep stage is determined in real time, with a focus on identifying the REM stage (i.e., the set sleep stage).

[0126] 4. Stress Status Assessment: When the system confirms that the user is in the REM period, it activates a high-precision stress monitoring algorithm (i.e., stress assessment model). It analyzes short-term (i.e., set time window) changes in indicators such as HRV. If the stress level is determined to exceed the threshold (i.e., set stress threshold), the "potential nightmare event" flag is triggered.

[0127] 5. Intervention Decision: The system generates intervention instructions and calls the user's preset intervention mode preferences (i.e., target intervention strategies).

[0128] 6. Implement personalized interventions:

[0129] (1) If the user selects vibration intervention, the motor is started and vibrates with a preset intensity and pattern (such as short pulses that gradually increase in intensity) sufficient to slightly wake the user from the dream but not to make them fully awake.

[0130] (2) If the user selects sound and light intervention, the smart home device will be linked to slowly turn on the lights (such as starting with dark red warm light) or play soothing music that gradually increases in volume.

[0131] 7. Intervention Feedback and Learning: The system monitors BCG signals after intervention. If the user's physiological indicators (such as heart rate) gradually stabilize and the user re-enters stable sleep, the intervention is recorded as successful. If the user is fully awakened or the stress persists, the intervention parameters (i.e., intervention timing and intensity) are recorded. In the future, the intervention timing or intensity can be fine-tuned through algorithms to achieve adaptive optimization.

[0132] The present invention has the following beneficial effects:

[0133] 1. Seamless monitoring: Based on the built-in sensors in the mattress, users do not need to wear any devices to experience natural comfort, making it suitable for long-term home use.

[0134] 2. Accurate identification: Combining the judgment of "REM phase" and "high emotional stress", the accuracy of nightmare identification is greatly improved and false intervention is avoided.

[0135] 3. Personalized and humanized intervention: Provides a variety of intervention options, allowing users to choose the most acceptable method according to their own preferences. The intensity of intervention is adjustable to minimize disruption to sleep continuity.

[0136] 4. Proactive prevention: Gentle interruptions before nightmares cause intense awakenings and distress minimize sleep disruption, helping to break the vicious cycle of nightmares and improve sleep quality and mental health in the long term.

[0137] 5. Self-learning ability: The system can record the intervention effect and gradually optimize the intervention strategy, becoming more and more in line with the user's personalized needs.

[0138] Example 3

[0139] Figure 5 This is a schematic diagram of a state control device provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes:

[0140] The acquisition module 310 is used to acquire a first cardiac impact signal, which includes cardiac impact signals during the user's sleep on the mattress.

[0141] Preprocessing module 320 is used to preprocess and extract features from the first cardiac impact signal to obtain the first physiological feature parameters contained in the first cardiac impact signal.

[0142] The first processing module 330 is used to process the first physiological characteristic parameters through a sleep staging model to obtain the sleep staging result of the user.

[0143] The second processing module 340 is used to process the first physiological characteristic parameter through a stress assessment model to obtain the user's stress level when the sleep staging result indicates that the user is in a set sleep period, wherein the set sleep period includes the rapid eye movement (REM) period.

[0144] The determination module 350 is used to determine that the user is in an abnormal sleep state when the pressure level exceeds a set level, and to control the intervention device to work in accordance with the working mode indicated by the target intervention strategy, wherein the intervention device includes a device for intervening in the user's sleep.

[0145] The technical solution of this invention involves an acquisition module acquiring a first cardiac impact signal, a preprocessing module preprocessing and extracting features from the first cardiac impact signal to obtain a first physiological characteristic parameter contained in the first cardiac impact signal, and extracting and quantifying the physiological information contained in the first cardiac impact signal to obtain a first physiological characteristic parameter that accurately reflects the user's sleep state, thereby improving the accuracy of judging the user's sleep cycle and physiological state. A first processing module processes the first physiological characteristic parameter through a sleep staging model to obtain the user's sleep staging result. By judging whether the user is in a set sleep period, it further judges whether the user is in an abnormal sleep state, thereby improving the accuracy of judging the user's sleep state. When the sleep staging result indicates that the user is in a set sleep period, a second processing module processes the first physiological characteristic parameter through a stress assessment model to obtain the user's stress level. By assessing the user's stress level, the first physiological characteristic parameter is quantified and mapped to the corresponding stress level for timely intervention. When the stress level exceeds a set level, a determination module determines that the user is in an abnormal sleep state and controls the intervention device to work according to the working mode indicated by the target intervention strategy. This enables timely judgment of whether the user is in an abnormal sleep state and timely intervention, thereby minimizing the impact of the abnormal sleep state on the user and improving sleep quality.

[0146] In another embodiment, the second processing module 340 further includes:

[0147] The input unit is configured to input a first physiological characteristic parameter into a stress assessment model when the sleep staging result indicates that the user is in a set sleep period, and determine whether the first physiological characteristic parameter exceeds a set stress threshold through the stress assessment model. If so, the user's stress level is determined to be a first level; otherwise, the user's stress level is determined to be a second level.

[0148] Wherein, the first level is greater than the second level, and the second level is the set level.

[0149] In another embodiment, the input unit is specifically used for:

[0150] The heart rate variability in the first physiological characteristic parameter is input into the stress assessment model, and the stress assessment model determines whether the heart rate variability within a set time window exceeds a set stress threshold.

[0151] In another embodiment, the device further includes:

[0152] An intervention acquisition module is used to acquire the second cardiac impact signal after the intervention device operates according to the target intervention strategy;

[0153] The extraction module is used to preprocess and extract features from the second cardiac impact signal to obtain the second physiological feature parameters;

[0154] The adjustment module is used to determine whether the user's sleep state is a set state based on the second physiological characteristic parameter, wherein the set state indicates that the user is in a stable sleep state;

[0155] If not, adjust the target intervention strategy;

[0156] In the specified state, one or more of the following conditions are met: the second physiological characteristic parameter is within a specified range for a specified duration, and the change in the second physiological characteristic parameter is less than a specified threshold; the user is in a light sleep or deep sleep phase of a sleep cycle; and the pressure level corresponding to the second physiological characteristic parameter is less than or equal to the specified level.

[0157] In another embodiment, the target intervention strategy includes one or more of the following: intervention timing, target intensity, and target intervention mode; wherein the intervention timing is related to the length of the set time window used by the stress assessment model.

[0158] In another embodiment, the device further includes:

[0159] The target intervention strategy determination module, for determining the target intervention strategy, includes:

[0160] In response to the user's selection of an intervention mode in the intervention settings interface, the selected intervention mode is taken as the target intervention mode;

[0161] In response to the user's selection of intervention intensity in the intervention settings interface, the selected intervention intensity is taken as the target intensity.

[0162] In another embodiment, the physiological characteristics include one or more of the following:

[0163] Heart rate; heart rate variability; respiratory rate; respiratory pattern; body movement signals.

[0164] The state control device provided in this embodiment of the invention can execute a state control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0165] Example 4

[0166] Figure 6 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention, as shown below. Figure 6 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0167] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor 11, and the computer program is executed by the at least one processor 11 to enable the at least one processor 11 to perform the method provided by the present invention.

[0168] The processor 11 can perform various appropriate actions and processes based on a computer program stored in the read-only memory (ROM) 12 or a computer program loaded from the storage unit 18 into the random access memory (RAM) 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0169] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0170] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the methods provided in this invention.

[0171] In some embodiments, the methods provided herein may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the methods by any other suitable means (e.g., by means of firmware).

[0172] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0174] In the context of this invention, a computer-readable storage medium stores computer instructions that are used to cause a processor to execute and implement the method provided by this invention.

[0175] The present invention also provides a computer program product comprising a computer program that, when executed by a processor, implements the method provided according to embodiments of the present invention. A computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0176] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0177] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0178] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0179] This invention also provides a computer program product, including a computer program that, when executed by a processor, can implement the methods provided in any embodiment of this application.

[0180] In the implementation of the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0181] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0182] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A state control method, characterized in that, include: Acquire the first cardiac impact signal, which includes cardiac impact signals during the user's sleep on the mattress; The first cardiac impact signal is preprocessed and its features are extracted to obtain the first physiological feature parameters contained in the first cardiac impact signal. The sleep staging result of the user is obtained by processing the first physiological characteristic parameter through a sleep staging model; When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is processed by a stress assessment model to obtain the user's stress level. The set sleep period includes the REM sleep period. When the pressure level exceeds a set level, it is determined that the user is in a sleep abnormal state, and the intervention device is controlled to work in accordance with the working mode indicated by the target intervention strategy. The intervention device includes a device for intervening in the user's sleep.

2. The method according to claim 1, characterized in that, When the sleep staging result indicates that the user is in a set sleep stage, the stress level of the user is obtained by processing the first physiological characteristic parameter through a stress assessment model, including: When the sleep staging result indicates that the user is in a set sleep period, the first physiological characteristic parameter is input into the stress assessment model. The stress assessment model determines whether the first physiological characteristic parameter exceeds a set stress threshold. If so, the user's stress level is determined to be level one; otherwise, the user's stress level is determined to be level two. Wherein, the first level is greater than the second level, and the second level is the set level.

3. The method according to claim 2, characterized in that, The step of inputting the first physiological characteristic parameter into the stress assessment model and determining whether the first physiological characteristic parameter exceeds a set stress threshold through the stress assessment model includes: The heart rate variability in the first physiological characteristic parameter is input into the stress assessment model, and the stress assessment model determines whether the heart rate variability within a set time window exceeds a set stress threshold.

4. The method according to claim 3, characterized in that, After determining that the user is in an abnormal sleep state when the pressure level exceeds a set level, and controlling the intervention device to operate according to the working mode indicated by the target intervention strategy, the method further includes: Acquire the second cardiac impact signal after the intervention device operates according to the target intervention strategy; The second cardiac impact signal is preprocessed and its features are extracted to obtain the second physiological feature parameters. Based on the second physiological characteristic parameter, it is determined whether the user's sleep state is a set state, wherein the set state indicates that the user is in a stable sleep state; If not, adjust the target intervention strategy; In the specified state, one or more of the following conditions are met: the second physiological characteristic parameter is within a specified range within a specified duration, and the change in the second physiological characteristic parameter is less than a specified threshold; the user is in a light sleep or deep sleep phase of a sleep cycle; and the pressure level corresponding to the second physiological characteristic parameter is less than or equal to the specified level.

5. The method according to claim 1, characterized in that, The targeted intervention strategies include one or more of the following: Intervention timing, target intensity, and target intervention mode; The timing of the intervention is related to the length of the set time window used by the stress assessment model.

6. The method according to claim 5, characterized in that, The steps for determining the target intervention strategy include: In response to the user's selection of an intervention mode in the intervention settings interface, the selected intervention mode is taken as the target intervention mode; In response to the user's selection of intervention intensity in the intervention settings interface, the selected intervention intensity is taken as the target intensity.

7. The method according to any one of claims 1-5, characterized in that, The physiological characteristics include one or more of the following: Heart rate; heart rate variability; respiratory rate; respiratory pattern; body movement signals.

8. A state control device, characterized in that, include: The acquisition module is used to acquire the first cardiac impact signal, which includes the cardiac impact signal during the user's sleep on the mattress. The preprocessing module is used to preprocess and extract features from the first cardiac impact signal to obtain the first physiological feature parameters contained in the first cardiac impact signal. The first processing module is used to process the first physiological characteristic parameters through a sleep staging model to obtain the sleep staging result of the user. The second processing module is used to process the first physiological characteristic parameter through a stress assessment model to obtain the user's stress level when the sleep staging result indicates that the user is in a set sleep period, wherein the set sleep period includes the rapid eye movement (REM) period. The determination module is used to determine that the user is in a sleep abnormal state when the pressure level exceeds a set level, and to control the intervention device to work in accordance with the working mode indicated by the target intervention strategy, wherein the intervention device includes a device for intervening in the user's sleep.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method of any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images