Immersive sleep scene adjusting method and system based on rhythm planning analysis

Abstract

The invention relates to the technical field of sleep scene adjustment, in particular to an immersive sleep scene adjustment method and system based on rhythm planning analysis. And acquiring real-time physiological feedback data and immersive sleep state data of the target user to construct a real-time sleepiness index curve, and performing mapping planning on saturated and unsaturated sleepiness rhythms in the sliding sub-window to obtain a real-time sleep rhythm phase. And simulating a preset creation control strategy of the immersive sleep scene through simulation software, and determining a response offset analysis scene for the rhythm phase in combination with electroencephalogram signal inversion calculation. And when the analysis result is a rhythm confusion scene, the real-time rhythm phase in the sleep staging mode is used as a driving benchmark to calculate the phase opportunity difference, and an amplitude compensation mechanism is designed to perform parameter adjustment of a chaos scene factor. According to the invention, dynamic and personalized regulation and control of the immersive sleep scene can be realized, the rhythm disorder or inertia problem is effectively improved, and the immersive sleep quality of the user is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sleep scene regulation, and in particular to an immersive sleep scene regulation method and system based on rhythm planning analysis. BACKGROUND

[0002] With the development of immersive technology, multi-modal interaction is widely used in the field of sleep assistance. Existing immersive sleep scene regulation methods usually create a single or multi-factor combination through external factors such as light, sound, smell, or environmental temperature to induce user relaxation and improve sleep. However, human sleep is essentially regulated by the circadian rhythm and sleep homeostasis dual-process mechanism, and the sleep rhythm state of users has highly individualized and dynamic characteristics. Existing regulation techniques lack deep utilization of real-time physiological feedback and sleep state data of users, making it difficult to accurately and timely track the sleepiness changes of users, and thus unable to accurately plan a rhythm phase that conforms to the sleep habits of users; secondly, it fails to establish a dynamic mechanism for planning sleep rhythm phases according to real-time sleepiness concentration, and cannot accurately develop a rhythm phase image that conforms to the sleep habits of users, resulting in lagging scene regulation and ineffective response to rhythm confusion or inertia state. In addition, in the rhythm abnormal scene, existing regulation methods lack fine-tuned regulation strategies for guiding the two different states of confusion and inertia, often leading to extensive regulation and limited effectiveness, which in turn reduces the sleep quality of users. Therefore, there is an urgent need for an immersive sleep scene regulation method that combines real-time rhythm planning analysis to achieve individualized, dynamic, and fine-tuned scene regulation intervention and improve the experience and stability of users enjoying immersive sleep. SUMMARY

[0003] The present application overcomes the shortcomings of the prior art and provides an immersive sleep scene regulation method and system based on rhythm planning analysis.

[0004] To achieve the above purpose, the technical solution adopted by the present application is as follows: The present application provides an immersive sleep scene regulation method based on rhythm planning analysis in the first aspect, comprising the following steps: S102: Obtain real-time physiological feedback data and immersive sleep state data of a target user to track real-time sleepiness, obtain a real-time sleepiness index curve, map and plan the sleepiness rhythm of the saturated state and the unsaturated state within the sleep sliding sub-window based on the real-time sleepiness index curve, and obtain the real-time sleep rhythm phase of the target user; S104: Simulate the preset creation control strategy of the current immersive sleep scene to shake the real-time sleep rhythm phase through simulation software, calculate the response offset of the current immersive sleep scene to the rhythm phase according to the simulation result and the actual electroencephalogram sequence, analyze the current immersive sleep scene according to the phase response drift function between the generated current sleep rhythm phase and the real-time sleep rhythm phase, and obtain the rhythm planning analysis result; S106: If the rhythm planning analysis result shows a rhythm chaos scene, align the real-time sleep rhythm phase based on the sleep staging mode to the rhythm chaos scene mode as a driving benchmark of a guide event, obtain a phase opportunity difference, adjust the creation parameters of different scene factors of the rhythm chaos scene based on the amplitude compensation design of the phase opportunity difference, and generate a first adjustment scheme; S108: If the rhythm planning analysis result shows a rhythm inertia scene, construct a multi-dimensional parameter adjustment polar coordinate model, analyze the adjustment strategy of the scene factor on the multi-dimensional parameter adjustment polar coordinate model based on the inertia delay of the phase response drift of the current rhythm inertia scene, adjust the creation parameters of the rhythm inertia scene, obtain a second adjustment scheme.

[0005] Preferably, the S102 specifically comprises the following steps: Collect real-time physiological feedback data of the target user through the Internet of Things, and synchronously extract immersive sleep state data of the target user at a historical time period when the real-time physiological feedback data is generated through a sleep log; Introduce a biological sleep dynamics mechanism to establish a biological sleep dynamics state equation, evaluate the sleepability of the real-time physiological feedback data along the tangent direction of the immersive sleep state data in the biological sleep dynamics state equation to track and update the real-time sleepiness of the target user, and obtain a real-time sleepiness index curve of the sleep timing; Construct a sleep sliding window field of the current rhythm steady state, formulate a variance weighting criterion for the sleep sliding window field according to a short-time sleep driving mechanism, and divide the sleep sliding window field into a plurality of sleep sliding sub-windows according to the sleep behavior information of the target user; Perform kurtosis weighting calculation and processing on the steepness of the real-time sleepiness index curve in each sleep sliding sub-window based on the variance weighting criterion in the sleep sliding window framework, and obtain a local sleepiness kurtosis decay value of each sleep sliding sub-window; If the local sleepiness kurtosis decay value is greater than a preset threshold, the peak-valley curve span corresponding to the sleep sliding sub-window is marked as a saturated state cutoff section, and if it is less than the preset threshold, it is marked as an unsaturated state cutoff section; Obtain the real-time sleepiness index of the saturated state cutoff section and the unsaturated state cutoff section through the real-time sleepiness index curve, synchronously locate the center point of the saturated state cutoff section, mark it as a first proxy anchor point, and locate the center point of the saturated state cutoff section, mark it as a second proxy anchor point; The average height of the rhythm function corresponding to the real-time sleepiness index of each saturated state cut-off section and unsaturated state cut-off section is calculated on each first proxy anchor point and second proxy anchor point, an explicit Euler method is introduced to time-approximate integrate the average height of the rhythm function, and a rhythm below area model of the real-time sleepiness index curve is generated; The sleep staging rule is obtained, the phase mapping planning of the sleep staging rule is performed according to the proxy interpenetration distribution of the saturated integration-unsaturated integration in the rhythm below area model, and the real-time sleep rhythm phase of the target user is obtained.

[0006] Preferably, the biological sleep dynamics mechanism is introduced to establish a biological sleep dynamics state equation, the real-time sleepiness of the target user is tracked and updated in the biological sleep dynamics state equation along the tangent direction of the immersed sleep state data according to the sleepiness plasticity of the real-time physiological feedback data, a real-time sleepiness index curve of the sleep time sequence is obtained, and the specific steps include the following steps: Based on the rhythm sleep index system, the biological sleep dynamics mechanism is introduced, the dynamic state control model of the real-time physiological feedback data is built by taking the immersed sleep state data as the state variable input of the biological sleep dynamics mechanism, and a nonlinear biological sleep dynamics state equation is generated; The sleep stability index is extracted from the rhythm sleep index system, the real-time physiological feedback data is evaluated in multiple dimensions by a series of sleep stability indexes, the sleepiness plasticity coefficient of the target user is obtained, and the tracking resolution step is preset based on the sleepiness plasticity coefficient; According to the tangent direction which is linearly approximated, the balance prediction value on the collection time sequence is calculated along the tangent direction based on the tracking resolution step, the balance prediction value is substituted into the biological sleep dynamics state equation to predict the support position of the next dynamic balance point, and the dynamic alternation balance support point is obtained. Based on the dynamic alternation balance support point, a Jacobian matrix is calculated to track and update the tangent direction, the candidate tangent point trajectory eigenvalue in the continuous updating process of the Jacobian matrix is output, the real-time sleepiness index of the target user is determined according to the candidate tangent point trajectory eigenvalue, and the real-time sleepiness index curve on the sleep time sequence is fitted and constructed.

[0007] Preferably, the S104 specifically includes the following steps: The preset creation control strategy of the current immersed sleep scene is called through the Internet of Things, and a dynamic pseudo-real model of the current immersed sleep scene is constructed by using sleep scene simulation software; The preset creation control strategy is injected into the dynamic pseudo-real model as a dithering item, the real-time sleep rhythm phase is simulated by using the dynamic pseudo-real model after injection, the electroencephalogram signal of the target user is recorded in the simulation process, and the simulated electroencephalogram signal sequence is output; An actual electroencephalogram sequence of a target user in a current immersive sleep scene is acquired, a time-frequency domain registration space is constructed, and the time-frequency domain registration space is divided into N sub-registration blocks based on a predetermined stage of sleep staging; A short-time Fourier transform algorithm is introduced to perform rhythm response transformation calculation on the actual electroencephalogram sequence to obtain an actual response spectrum waveform, and a registration operation is performed on the simulated electroencephalogram sequence and the actual electroencephalogram sequence in the time-frequency domain registration space; Only the simulated response spectrum waveform and the corresponding sub-registration block in the simulated electroencephalogram sequence with a similarity greater than a preset similarity threshold to the actual response spectrum waveform are extracted, marked as a response registration block, and the registration overlap rate between the simulated response spectrum waveform and the actual response spectrum waveform is obtained through the response registration block; A response spectrum distortion coefficient of the target user responding to the real-time sleep rhythm phase under the current immersive sleep scene jitter is determined according to the registration overlap rate, and a Hilbert instantaneous phase transformation matrix is constructed based on the response spectrum distortion coefficient; A phase oscillation equation is introduced, and the response shift of the real-time sleep rhythm phase is observed and analyzed for smoothing of scattered points in the phase oscillation equation through the Hilbert instantaneous phase transformation matrix, and an analog sleep rhythm phase is generated; If the phase response drift function between the analog sleep rhythm phase and the real-time sleep rhythm phase is positive, the current immersive sleep scene where the real-time sleep rhythm phase is located is marked as a rhythm chaotic scene; if the phase response drift function between the analog sleep rhythm phase and the real-time sleep rhythm phase is negative, the current immersive sleep scene is marked as a rhythm inert scene, and a rhythm planning analysis result is obtained.

[0008] Preferably, the S106 specifically includes the following steps: If the rhythm planning analysis result shows a rhythm chaotic scene, the immersive sleep scene creation system is used to obtain stage guidance decision information of different scene factors in the rhythm chaotic scene for the target user to enter an immersive sleep mode; The sleep staging rule is embedded as a reference modal scale architecture to construct a heterogeneous modal stage alignment grid, the real-time sleep rhythm phase is set as a guide window event, and a trigger timestamp of the sleep staging rule when the guide window event occurs is obtained; Based on the stage guidance decision information, the rhythm chaotic scene is aligned to the stage alignment grid around the alignment benchmark of the trigger timestamp, and a phase timing difference of the rhythm chaotic scene is obtained by traversing the modal alignment range between the sleep staging and the rhythm chaotic scene during the alignment process. The open-loop transfer function of the immersion sleep scene building system for building the rhythm chaos scene is acquired, a Bode open-loop frequency diagram of the rhythm chaos scene is drawn according to the open-loop transfer function, and a current low-frequency gain amount of the system for building the rhythm chaos scene is identified by analyzing the Bode open-loop frequency diagram. A preset maximum low-frequency gain demand amount is based on a phase time difference, and if the current low-frequency gain amount is less than the maximum low-frequency gain demand amount, then a magnitude tuning compensator is deployed in the immersion sleep scene building system at this time, and a boundary cutoff frequency of the magnitude tuning compensator is constrained based on the maximum low-frequency gain demand amount. A tuning correction value of the rhythm chaos scene is constructed using the magnitude tuning compensator according to the current low-frequency gain amount, a current cutoff frequency is acquired, the tuning correction value is applied to the immersion sleep scene building system to adjust the building parameters of each scene factor in the rhythm chaos scene, until the current cutoff frequency approaches the boundary cutoff frequency, and a first adjustment scheme is obtained.

[0009] Preferably, the S108 specifically includes the following steps: If the rhythm planning analysis result shows a rhythm inert scene, then a plurality of standby building parameters of different scene factors in the rhythm inert scene and an intervention function of each standby building parameter for promoting the immersion sleep are acquired by the immersion sleep scene building system; A tuning polar coordinate branch is established based on different scene factors, a fixed-point coordinate network in which the standby building parameters are deployed is woven and arranged according to the intervention function, a K-means clustering algorithm is introduced to cluster each standby building parameter to a network node of the fixed-point coordinate network, an inert counter is assigned to each fixed-point coordinate, and a multi-dimensional tuning polar coordinate model of the rhythm inert scene is generated; Real-time standby building parameters of the rhythm inert scene in the current working condition are acquired, the fixed-point coordinates of each real-time standby building parameter are found and connected in the multi-dimensional tuning coordinate model, and a real-time tuning polar coordinate layout is obtained; The delay weight of the real-time tuning polar coordinate layout on the phase response drift function is analyzed by the inert accumulation index of the inert counter, and a subsidiary sampling layout is obtained by starting sampling planning from the starting center of the real-time tuning polar coordinate layout according to the delay weight; The tuning polar coordinate branch covered by the subsidiary sampling layout, the fixed-point coordinates and the corresponding standby building parameters are extracted, and are defined as candidate adjustment parameter solutions, and a jitter residual gradient threshold value is preset when the phase response drift function approaches 0; If the jitter residual gradient of the fixed-point coordinate does not exceed the jitter residual gradient threshold value, then the update of the candidate adjustment parameter solution of the fixed-point coordinate is skipped; if the jitter residual gradient of the fixed-point coordinate exceeds the jitter residual gradient threshold value, then the corresponding candidate adjustment parameter solution is updated, and an adjustment strategy of each scene factor is obtained; Based on the adjustment strategy uploaded to the immersive sleep scene building system, the adjustment parameters of each scene factor in the rhythm inertia scene are adjusted to obtain a second adjustment scheme.

[0010] The second aspect of the present application provides an immersive sleep scene adjustment system based on rhythm planning analysis, which comprises a memory, a processor and a communication interface, the memory comprises an immersive sleep scene adjustment method based on rhythm planning analysis, the communication interface is used for data connection communication between the memory and the processor, and the immersive sleep scene adjustment method based on rhythm planning analysis is executed by the processor to realize the steps of any one of the immersive sleep scene adjustment methods.

[0011] The present application solves the technical defects in the background art, and has the following beneficial technical effects: The present application can accurately locate the sleep rhythm dynamics of the user by obtaining real-time physiological feedback data and immersive sleep state data of the target user, analyzing and tracking the real-time sleepiness index curve and performing rhythm phase mapping planning. The actual response offset of the immersive scene to the rhythm phase can be effectively obtained by simulating the building strategy of the immersive sleep scene by using the simulation software and performing inversion calculation combined with the electroencephalogram signal, so as to realize accurate planning analysis of the rhythm phase. When the rhythm confusion scene occurs, the building parameters of different scene factors can be adjusted in a targeted manner based on the driving benchmark alignment and amplitude compensation mechanism of the real-time rhythm phase, so as to restore the rhythm stability and reduce the rhythm pointing disorder caused by the inappropriate adjustment of the immersive sleep scene building. When the rhythm inertia scene occurs, the inertia delay is analyzed by using the multi-dimensional parameter adjustment polar coordinate model to provide a targeted adjustment strategy, which effectively improves the rhythm response delay and reduces the low adaptability of the real-time rhythm to the current immersive sleep scene. The present application can realize personalized, dynamic and fine adjustment in the immersive sleep scene, and significantly improves the sleep rhythm coordination and the quality of immersive sleep of the user. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings of embodiments according to these drawings without creative labor.

[0013] Figure 1 A first method flowchart of the immersive sleep scene adjustment method based on rhythm planning analysis is shown; Figure 2 A second method flowchart of the immersive sleep scene adjustment method based on rhythm planning analysis is shown; Figure 3A system framework diagram of an immersive sleep scene adjustment system based on rhythm planning analysis is shown. DETAILED DESCRIPTION

[0014] In order to enable a more clear understanding of the above-mentioned objects, features and advantages of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, and therefore, the protection scope of the present application is not limited by the specific embodiments disclosed below.

[0016] The first aspect of the present application provides a method for adjusting an immersive sleep scene based on rhythm planning analysis, as shown in the formula (I), comprising the following steps: Figure 1 As shown in the formula (I), comprising the following steps: S102: Real-time physiological feedback data and immersive sleep state data of a target user are acquired to track real-time sleepiness, a real-time sleepiness index curve is obtained, a saturated state and an unsaturated state sleepiness rhythm in a sleep sliding sub-window is mapped and planned based on the real-time sleepiness index curve, and a real-time sleep rhythm phase of the target user is obtained; S104: The preset creation control strategy of the current immersive sleep scene is simulated by simulation software to shake the real-time sleep rhythm phase, a response offset of the current immersive sleep scene to the rhythm phase is calculated according to a simulation result and an actual electroencephalogram signal sequence, the current immersive sleep scene is analyzed according to a phase response drift function between a generated current sleep rhythm phase and the real-time sleep rhythm phase, and a rhythm planning analysis result is obtained; S106: If the rhythm planning analysis result shows a rhythm chaos scene, a real-time sleep rhythm phase based on a sleep staging mode is used as a driving benchmark to align to a rhythm chaos scene mode, a phase opportunity difference is obtained, and an adjustment parameter of a different scene factor of the rhythm chaos scene is adjusted based on an amplitude compensation design of the phase opportunity difference, and a first adjustment scheme is generated; S108: If the rhythm planning analysis result shows a rhythm inertia scene, a multi-dimensional parameter adjustment polar coordinate model is constructed, an adjustment strategy of a scene factor is analyzed on the multi-dimensional parameter adjustment polar coordinate model based on an inertia delay of a phase response drift of the current rhythm inertia scene, an adjustment parameter of the rhythm inertia scene is adjusted, a second adjustment scheme is obtained.

[0017] It should be noted that different scene factors include light (blue light), background sound (white noise, natural sound and breathing guide sound), temperature (air conditioner, air heater), humidity (humidifier), bed vibration (mattress, pillow) and sleep aid release (fragrance).

[0018] Preferably, the S102 specifically comprises the following steps: Collect real-time physiological feedback data of the target user through the Internet of Things, and synchronously extract immersive sleep state data of the target user at a historical time period when the real-time physiological feedback data is generated through a sleep log; Introduce a biological sleep dynamics mechanism to establish a biological sleep dynamics state equation, and track and update real-time sleepiness of the target user in the biological sleep dynamics state equation along the tangent direction of the immersive sleep state data according to sleep steady state evaluation of sleepiness plasticity of the real-time physiological feedback data, to obtain a real-time sleepiness index curve of sleep timing; Construct a sleep sliding window field of present circadian steady state, formulate a variance weighted criterion of the sleep sliding window field according to a short sleep driving mechanism, and divide the sleep sliding window field into a plurality of sleep sliding sub-windows according to sleep behavior information of the target user; Perform kurtosis weighted calculation and processing on steepness of a slope of the real-time sleepiness index curve in each sleep sliding sub-window based on the variance weighted criterion in the sleep sliding window framework, to obtain a local sleepiness kurtosis decay value of each sleep sliding sub-window; If the local sleepiness kurtosis decay value is greater than a preset threshold, the peak-valley curve span corresponding to the sleep sliding sub-window is marked as a saturated state cutoff section, and if the local sleepiness kurtosis decay value is less than the preset threshold, the peak-valley curve span is marked as an unsaturated state cutoff section; Obtain real-time sleepiness indexes of the saturated state cutoff section and the unsaturated state cutoff section through the real-time sleepiness index curve, synchronously locate a center point of the saturated state cutoff section, mark as a first proxy anchor point, and locate a center point of the saturated state cutoff section, mark as a second proxy anchor point; Calculate a circadian function average height of the real-time sleepiness index corresponding to each saturated state cutoff section and unsaturated state cutoff section at each first proxy anchor point and second proxy anchor point, introduce an explicit Euler method to perform time series approximate integration on the circadian function average height, and generate a circadian lower area model of the real-time sleepiness index curve; Obtain a sleep staging rule, perform phase mapping planning of the sleep staging rule according to proxy interleaved distribution of sleepiness saturated integral-unsaturated integral in the circadian lower area model, and obtain a real-time sleep rhythm phase of the target user.

[0019] It should be noted that the real-time physiological feedback data includes heart rate, heart rate variability parameters, respiratory rate, adenosine level, body motion parameters and skin temperature parameters. Immersive sleep state data includes neural activity data, electrodermal activity data, electromyography data, eye movement data and body motion data. Since the sleep rhythm of the target user is not a fixed regular form, but is determined by a variety of external factors, for example, the target user has a certain brain movement or body movement before sleep, the adenosine level quickly rises from low level to high level, so that the actual sleepiness after exercise appears a sharp increasing condition, so the real-time sleep rhythm of the user may be advanced. However, the existing adjustment method is difficult to reasonably speculate and plan the rhythm according to the sleepiness of the user, resulting in inaccurate individual rhythm adjustment of the immersive sleep scene for different users. Therefore, the biological sleep dynamic state equation established by the biological sleep dynamic mechanism is used to analyze the sleep plasticity of the real-time physiological feedback data and the immersive sleep state data generated by the target user in the historical time period, so as to further track the real-time sleepiness trend of the target user entering the sleep timing stage, that is, the real-time sleepiness index curve. The longer the wake-up time is, the more the brain needs sleep, and the sleepiness pressure gradually accumulates, and these sleepiness pressure will gradually release after entering the sleep stage. It can be seen that the real-time sleepiness is driven by its sleep steady state, so the method further formulates a variance weighted criterion about the sleep sliding window field based on the short-time sleep driving mechanism. The variance weighted criterion can effectively remove the local deviation of the kurtosis calculation of the real-time sleepiness index curve in each subsequent sleep sliding sub-window, and improve the accuracy of the curve in reflecting the sleepiness decay peak state distribution. The method can quantify the tail thickness and abnormal value tendency of the window sleepiness pressure concentration of the target user under the gradient advancement of the time by the peak weighted real-time sleepiness index curve of the micro window, which can more sensitively capture the timing pulse of the rhythm cut-in, and significantly improve the accuracy of the subsequent real-time planning of the individual sleep rhythm according to the sleepiness concentration gradient of the user.

[0020] It should be noted that if the local sleepiness peak degree attenuation value is greater than the preset threshold value, it indicates that the peak-valley curve span depicted by the real-time sleepiness index curve at this moment is large, indicating that the sleepiness concentration of the target user at this moment has reached an extreme saturation state and tends to be unsaturated, representing that the target user has a strong sleepiness, and therefore the peak-valley curve span corresponding to the sleep sliding sub-window is marked as a saturated state cutoff section. Otherwise, it indicates that the peak-valley curve span is large, indicating that the target user has a low level of sleepiness at this moment, and therefore it is marked as an unsaturated state cutoff section. The first proxy anchor point and the second proxy anchor point are respectively the representative base points of the saturated state cutoff section and the unsaturated state cutoff section. Approximate estimation of the rhythm phase based on the anchor point can balance the integral values of the left end point and the right end point of the curve span, effectively offset the partial accumulation deviation of the two ends of the interval, and improve the credibility of the rhythm planning based on the sleepiness gradient change. The average height of the rhythm function is the function height value that can best represent the average sleepiness concentration of the saturated state cutoff section and the unsaturated state cutoff section. It should be noted that the sleep rhythm planned by the method is based on the turning point of the sleep staging rule, such as the cut-in timing of jumping from N1 light sleep to N2 light sleep in the sleep-onset leading rhythm. Through this method, the real-time sleepiness of the user can be tracked, and the sleep rhythm phase can be planned with high precision based on the sleep steady state mechanism as the key rule, so as to formulate a unique rhythm positioning for users with different sleep habits, provide personalized adjustment basis for subsequent immersive sleep scenes, and meet the sleep assistance needs of different user groups.

[0021] Preferably, the introduction of the biological sleep dynamics mechanism establishes a biological sleep dynamics state equation, and the sleep-onset plasticity of the real-time physiological feedback data is tracked and updated in the biological sleep dynamics state equation along the tangent direction of the immersive sleep state data to obtain the real-time sleepiness of the sleep timing, and the real-time sleepiness index curve of the sleep timing is obtained, specifically including the following steps: Based on the rhythm sleep index system, the biological sleep dynamics mechanism is introduced, and the dynamic state control modeling of the real-time physiological feedback data is performed by inputting the immersive sleep state data as the state variable through the biological sleep dynamics mechanism, to generate a nonlinear biological sleep dynamics state equation; The sleep steady state index is extracted through the rhythm sleep index system, the real-time physiological feedback data is evaluated in multiple dimensions by a series of sleep steady state indexes, the sleep-onset plasticity coefficient of the target user is obtained, and the tracking resolution step is preset based on the sleep-onset plasticity coefficient; According to the linear approximate tangent direction of the immersive sleep state data, the balance prediction value on the collection timing is calculated along the tangent direction based on the tracking resolution step, the balance prediction value is substituted into the biological sleep dynamics state equation to predict the support position of the next dynamic balance point, and the dynamic alternation balance branch point is obtained; A Jacobian matrix is ​​calculated based on the dynamic change equilibrium pivot to track and update the tangent direction. The candidate tangent trajectory feature values ​​are output during the continuous update process of the Jacobian matrix. The real-time sleepiness index of the target user is determined based on the candidate tangent trajectory feature values, and a real-time sleepiness index curve on the sleep time series is constructed by fitting.

[0022] It should be noted that for real-time sleepiness tracking of different target users, this method uses sleep homeostasis indicators to independently and jointly evaluate the real-time physiological feedback data generated by the target users based on different dimensional benchmarks. For example, it assesses the brain's sleepiness pressure tendency when the user has abnormal heart rate variability parameters, and the adenosine accumulation level when heart rate variability parameters and respiratory rate fluctuations occur simultaneously. This allows for plasticity analysis of the user's intention to fall asleep, and a sleep plasticity coefficient is used to quantify this. Based on the preset resolution step size, the real-time sleepiness tracking path can be effectively determined. Immersive sleep state data provides tracking guidance. Using this tracking guidance, the balance prediction value of the collected real-time data is calculated on the predetermined tracking path. This balance prediction value is a "candidate orientation" close to the actual sleep balance threshold. By substituting the balance prediction value back into the biological sleep dynamic state equation, the support point that drives the user to reach sleep homeostasis at different short moments can be predicted, namely the dynamic change balance fulcrum. This is the key point for locking in whether the user experiences a sleepiness jump. Subsequently, at the new equilibrium point, the Jacobian matrix is ​​calculated to track and update the tangent direction, determining the extension direction for the next short time step. This ensures the continuity of sleepiness perception, prevents sleepiness from deviating or diverging, and achieves a real-time, continuous sleepiness characterization effect. Finally, the candidate tangent trajectory feature values ​​recorded by the Jacobian matrix during the update process reveal the real-time sleepiness dynamic threshold at which the target user reaches sleep homeostasis. This method can track real-time sleepiness during the sleep process of different users, thus providing a personalized reference template for rhythm planning. This makes rhythm positioning more reliable for different users and improves the accuracy of subsequent immersive sleep scene guidance.

[0023] Preferably, S104, as Figure 2 As shown, the specific steps include: By retrieving the preset creation and control strategies of the current immersive sleep scene through the Internet of Things, a dynamic simulation model of the current immersive sleep scene is constructed using sleep scene simulation software. A preset control strategy is used to inject jitter into a dynamic simulation model. The real-time sleep rhythm phase is simulated by the injected dynamic simulation model. During the simulation, the target user's EEG signal is recorded and the simulated EEG signal sequence is output. The actual EEG signal sequence of the target user in the current immersive sleep scenario is obtained, a time-frequency domain registration space is constructed, and the time-frequency domain registration space is divided into N sub-registration blocks based on the predetermined stage of sleep stage. The short-time Fourier transform algorithm is introduced to transform and calculate the rhythm response of the actual electroencephalogram signal sequence to obtain an actual response spectrum waveform, and the registration operation is performed on the simulated electroencephalogram signal sequence and the actual electroencephalogram signal sequence in the time-frequency domain registration space; Only the simulated response spectrum waveform and the corresponding sub-registration block in the simulated electroencephalogram signal sequence with a similarity greater than a preset similarity threshold to the actual response spectrum waveform are extracted, and are marked as a response registration block, and the registration superposition rate between the simulated response spectrum waveform and the actual response spectrum waveform is obtained through the response registration block; The response spectrum distortion coefficient of the target user responding to the real-time sleep rhythm phase under the current immersive sleep scene jitter is determined according to the registration superposition rate, and the Hilbert instantaneous phase transformation matrix is constructed based on the response spectrum distortion coefficient; The phase oscillation equation is introduced, the response shift of the real-time sleep rhythm phase is observed and analyzed by the Hilbert instantaneous phase transformation matrix in the phase oscillation equation, and the simulated sleep rhythm phase is inversely calculated; If the phase response drift function between the simulated sleep rhythm phase and the real-time sleep rhythm phase is positive, the current immersive sleep scene where the real-time sleep rhythm phase is located is marked as a rhythm chaotic scene; if the phase response drift function between the simulated sleep rhythm phase and the real-time sleep rhythm phase is negative, the current immersive sleep scene is marked as a rhythm inert scene, and the rhythm planning analysis result is obtained.

[0024] It should be noted that the dynamic pseudo-real model is constructed to evaluate the response performance of the target user in the current immersive sleep scene jitter environment to the planned real-time sleep rhythm phase, which can replace the tedious steps of artificial field testing, save a lot of scene adjustment cost output of manpower and material resources, and greatly improve the adjustment efficiency. The time-frequency domain registration space is divided into N sub-registration blocks based on the sleep staging stages, which can make the rhythm response spectrum analysis between the simulated electroencephalogram signal and the actual electroencephalogram signal more refined, avoid the omission and misplacement phenomenon of traditional spectrum unified rough matching, and significantly improve the positioning accuracy of the response node. The actual response spectrum waveform reveals the known trigger node of the target user responding to the rhythm phase in the actual sleep process in the current immersive sleep scene. The response spectrum distortion coefficient quantifies the degree of deviation of the simulated response characteristics of the triggered real-time sleep rhythm phase from the known response characteristics in the jitter environment, and visualizes the sensitivity of the current immersive sleep scene to the real-time sleep rhythm phase through the construction of the Hilbert instantaneous phase transformation matrix, and finally inversely calculates the simulated sleep rhythm phase through the phase oscillation equation. The phase response drift function reflects the phase drift amplitude of the simulated sleep rhythm phase (in the current immersive sleep scene) compared with the real-time sleep rhythm phase (standard).

[0025] It should be noted that the immersive sleep scene is generated according to the real-time sleep rhythm phase, including a leading scene (T0-T1, 30-60 min), a sleep-in scene (T1-T2, 0-30 min), a maintenance scene (T2-T3, in sleep), and a pre-awakening scene (T3-T4, 15-30 min before awakening). If the phase response drift function between the simulated sleep rhythm phase and the real-time sleep rhythm phase is positive, it indicates that the simulated sleep rhythm phase is in advance of the real-time sleep rhythm phase, indicating that the current immersive sleep scene has caused incorrect guidance or interference to the target user in the sleep staging, resulting in confusion in the direction of the real-time sleep rhythm phase. For example, the target user is currently in the key sleep-in rhythm from the N1 light sleep period to the N2 light sleep period, but the high-frequency white noise and the gradual brightening of the light generated by the current immersive sleep scene are adjusted to high light, causing the target user to fail to enter the planned rhythm, so the scene is a rhythm chaos scene. Conversely, if the phase response drift function is negative, it indicates that the current immersive sleep scene cannot respond to the real-time sleep rhythm phase, in other words, the real-time sleep rhythm phase is not suitable for the current immersive sleep scene, resulting in phase inertia, so the scene is an inappropriate scene that makes the rhythm phase inert. Through the method, the response characteristics and phase offset of the real-time sleep rhythm phase can be calculated in a simulated manner by the current immersive sleep scene, so as to analyze the correctness and rationality of the guidance of the current scene to the planned rhythm phase, and improve the adjustment accuracy of the immersive sleep scene for different user rhythms.

[0026] Preferably, the S106 specifically comprises the following steps: If the rhythm planning analysis result shows a rhythm chaos scene, the immersive sleep scene creation system is used to obtain the staging guidance decision information of different scene factors in the rhythm chaos scene for the target user to enter the immersive sleep mode; The sleep staging rule is embedded as a reference modal scale architecture to construct a heterogeneous modal phase alignment grid, the real-time sleep rhythm phase is set as a guide window event, and the trigger timestamp of the guide window event is obtained; Based on the staging guidance decision information, the rhythm chaos scene is aligned to the phase alignment grid around the trigger timestamp as an alignment benchmark, and the modal alignment range between the sleep staging and the rhythm chaos scene is traversed during the alignment process to obtain the phase timing difference of the rhythm chaos scene; An open-loop transfer function of the immersive sleep scene creation system for creating the rhythm chaos scene is obtained, a Bode open-loop frequency diagram of the rhythm chaos scene is constructed according to the open-loop transfer function, and the current low-frequency gain of the system for creating the rhythm chaos scene is identified by analyzing the Bode open-loop frequency diagram; If the current low-frequency gain amount is less than the maximum low-frequency gain demand amount, a magnitude adjustment compensator is deployed in the immersive sleep scene creation system, and the boundary cutoff frequency of the magnitude adjustment compensator is constrained based on the maximum low-frequency gain demand amount; The adjustment correction value of the rhythm chaos scene is constructed using the magnitude adjustment compensator according to the current low-frequency gain amount, the current cutoff frequency is obtained, the adjustment correction value is applied to the immersive sleep scene creation system to adjust the creation parameters of each scene factor in the rhythm chaos scene, until the current cutoff frequency approaches the boundary cutoff frequency, and a first adjustment scheme is obtained.

[0027] It should be noted that the stage guidance decision information proposes a switching decision for the rhythm chaos scene to guide the entry into the immersive sleep mode, for example, in the sleep-in scene (T1-T2, 0-30 min), the target user is guided to jump from the N2 light sleep stage to the N3 deep sleep stage by introducing low-frequency band breathing sound and low light wave less than or equal to 10lx. Since the rhythm chaos scene can cause real-time sleep rhythm phase response disorder, and the real-time sleep rhythm phase is based on the sleep staging rule, there is a heterogeneous misalignment between the appropriate trigger time of the real-time sleep rhythm phase in the sleep staging mode and the actual trigger time of the rhythm chaos scene stage mode, which leads to the error guidance of the real-time sleep rhythm phase by the rhythm chaos scene. Therefore, the method first constructs a heterogeneous stage alignment grid based on the sleep staging rule, which is used to interface the trigger time scale of the real-time sleep rhythm phase in the sleep staging stage and the rhythm chaos scene stage. Further, the real-time sleep rhythm phase is set as a guidance window event to detect its location in the trigger timestamp of the sleep staging rule, which is an alignment reference point or anchor point in the time sequence, which can guide the accurate alignment of the rhythm chaos scene stage mode to the sleep staging mode. The range of the two from the original trigger time point to the time alignment is the degree of heterogeneous misalignment, i.e., the phase time difference. The phase time difference materializes the guidance error of the rhythm chaos scene, indicates the adjustment interval and range of the scene creation parameters, and is the key adjustment prerequisite for correcting the guidance of the real-time sleep rhythm phase by the rhythm chaos scene.

[0028] It should be noted that the immersion sleep scene building system controls the open-loop transfer function of the rhythm chaos scene to draw a Bode open-loop frequency diagram for analyzing the phase margin and amplitude characteristics of the current system, so as to determine whether the low-frequency gain of the current system is sufficient to compensate for the phase opportunity difference, and directly indicate the necessary chaos compensation direction. Among them, the maximum low-frequency gain requirement is the open-loop compensation required by the phase opportunity difference caused by the modified rhythm chaos scene. If the current low-frequency gain is not sufficient for the maximum low-frequency gain requirement, it means that the immersion sleep scene building system cannot meet the adaptive compensation ability of the open-loop compensation amount, so the method deploys the amplitude adjustment compensator to perform compensation calculation effect on the open-loop compensation amount. Among them, the boundary cutoff frequency is the constraint threshold that meets the maximum low-frequency gain requirement. By making the current cutoff frequency approach the boundary cutoff frequency in the process of constructing the adjustment correction value, the current low-frequency gain can be effectively located in the low-frequency interval, ensuring that the compensator can be in the low-frequency band to improve the adjustment gain of different scene factors, without significantly affecting the nearby rhythm phase margin, and improving the reasonable adjustment and adjustment accuracy of the corresponding building parameters of each scene factor according to the rhythm chaos scene to generate the trigger opportunity. Through this method, the unreasonable sleep guidance of the real-time sleep rhythm phase caused by the phased rhythm chaos scene can be analyzed and modified by heterogeneous misalignment compensation, so as to realize the adjustment of the rhythm chaos scene, eliminate the phenomenon of rhythm phase trigger chaos, improve the immersive sleep quality of the target user, and avoid sleep guidance negative optimization.

[0029] Preferably, the S108 specifically comprises the following steps: If the rhythm planning analysis result shows a rhythm inert scene, the immersion sleep scene building system obtains a number of standby building parameters of different scene factors in the rhythm inert scene and the intervention function of each standby building parameter to promote immersion sleep; Based on different scene factors, a parameter adjustment polar coordinate branch is established, the standby building parameters are deployed in the fixed point coordinate network of the parameter adjustment polar coordinate branch according to the intervention function, a K-means clustering algorithm is introduced to cluster each standby building parameter to the network node of the fixed point coordinate network, and an inert counter is assigned to each fixed point coordinate to generate a multi-dimensional parameter adjustment polar coordinate model of the rhythm inert scene; The real-time standby building parameters of the rhythm inert scene in the current working condition are obtained, and the fixed point coordinates of each real-time standby building parameter are found and connected in the multi-dimensional adjustment coordinate model to obtain a real-time parameter adjustment polar coordinate map; The delay weight of the real-time parameter adjustment polar coordinate map on the phase response drift function is analyzed by the inert accumulation index of the inert counter, and the sampling planning is performed from the starting center according to the delay weight to obtain an attached sampling map; Extract the parametric polar coordinate branch attached to the sampling map coverage, the fixed point coordinate belonging to it, and the corresponding reserve construction parameter, define it as the candidate adjustment parameter solution, and preset the jitter residual gradient threshold value approaching 0 when the phase response drift function approaches 0; If the jitter residual gradient of the fixed point coordinate does not exceed the jitter residual gradient threshold value, skip the update of the candidate adjustment parameter solution of the fixed point coordinate; if the jitter residual gradient of the fixed point coordinate exceeds the jitter residual gradient threshold value, apply the update of the corresponding candidate adjustment parameter solution to obtain the adjustment strategy of each scene factor; Based on the adjustment strategy, upload to the immersive sleep scene construction system to adjust the construction parameters of each scene factor in the rhythm inertia scene to obtain a second adjustment scheme.

[0030] It should be noted that the reserve construction parameter is a reasonable preset adjustment parameter planned by the immersive sleep scene construction system in advance for different scene factors in the rhythm inertia scene. Since the accurate response of the real-time sleep rhythm phase cannot adapt to the rhythm inertia scene, the method establishes a polar coordinate model, wherein the angle dimension of the polar coordinate model is the parametric polar coordinate branch, representing different scene factors, forming a multi-dimensional parametric polar coordinate model. Compared with the traditional polar coordinate model, the multi-dimensional parametric polar coordinate model of the method embeds a fixed point coordinate network in each scene factor angle field, which is clustered by the corresponding reserve construction parameter, representing and storing the candidate parameters in the polar coordinate dimension of the scene factor that can be used to adjust the rhythm inertia scene, realizing the synchronous adjustment of different scene factors, reducing the one-by-one adjustment operation steps and debugging links compared with the traditional adjustment method, and greatly improving the adjustment efficiency and accuracy of the immersive sleep scene. In addition, an inertia counter is deployed on each fixed point coordinate, which can weightedly measure the delay of the phase response drift function in the current rhythm inertia scene. The reserve construction parameter provides a sampling reference for candidate adjustment to alleviate or eliminate the inertia of the scene, obtaining an attached sampling map. The real-time parametric polar coordinate map is a polar coordinate radius pattern constructed by parametric adjustment of the current rhythm inertia scene, and the polar coordinate radius represents the parametric adjustment vector (size and direction). The attached sampling map is the polar coordinate radius pattern required to eliminate the scene inertia by adjusting the scene factor. The jitter residual gradient reflects the gradient contribution of the reserve construction parameter on the fixed point coordinate to the maximum extent to eliminate the scene inertia, and reveals the optimality and appropriateness of each candidate adjustment parameter solution for the rhythm inertia scene adjustment.

[0031] It should be noted that if the jitter residual gradient of the fixed-point coordinate does not exceed the jitter residual gradient threshold, it means that the candidate adjustment parameter solution to the jitter phase response drift function has a smaller amplitude and limited contribution, so it is not considered as a suitable parameter for adjusting the rhythm inertia scene, and therefore the update of the candidate adjustment parameter solution of the fixed-point coordinate is skipped. On the contrary, it means that the candidate adjustment parameter solution eliminates the gradient contribution of the scene inertia, which can guarantee the accurate triggering of the real-time sleep rhythm phase in the rhythm inertia scene, so the update of the candidate adjustment parameter solution at the fixed-point coordinate is applied to constitute the adjustment strategy of each scene factor of the rhythm inertia scene. Through this method, the phase trigger inertia phenomenon caused by the rhythm inertia scene can be eliminated, ensuring that the real-time sleep rhythm phase can have high adaptability in the current immersive sleep scene stage, improving the guiding stability and reliability of immersive sleep, and improving the comfort and satisfaction of immersive sleep scene feedback to the target user.

[0032] The second aspect of the method provides an immersive sleep scene adjustment system based on rhythm planning analysis, as shown in the figure, the system comprises a memory 301, a processor 302 and a communication interface 303, the memory 301 comprises an immersive sleep scene adjustment method based on rhythm planning analysis, the communication interface 303 is used for data connection communication between the memory 301 and the processor 302, and the immersive sleep scene adjustment method based on rhythm planning analysis is executed by the processor 302 to realize the steps of any one of the immersive sleep scene adjustment methods. Figure 3

[0033] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any skilled person in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.​

Claims

1. A method for adjusting an immersive sleep scenario based on a rhythm planning analysis, characterized in that, The method comprises the following steps: S102: obtaining real-time physiological feedback data and immersive sleep state data of a target user to track real-time sleepiness, obtaining a real-time sleepiness index curve, mapping and planning the sleepiness rhythm of the saturated state and the unsaturated state in the sleep sliding sub-window based on the real-time sleepiness index curve, and obtaining the real-time sleep rhythm phase of the target user; S104: simulating a preset creation control strategy of the current immersive sleep scene by using simulation software to shake the real-time sleep rhythm phase, calculating the response offset of the current immersive sleep scene to the rhythm phase according to the simulation result and the actual electroencephalogram sequence, analyzing the current immersive sleep scene according to the phase response drift function between the generated current sleep rhythm phase and the real-time sleep rhythm phase, and obtaining the rhythm planning analysis result; S106: if the rhythm planning analysis result shows a rhythm chaos scene, the real-time sleep rhythm phase based on the sleep staging mode is used as a driving benchmark to align to the rhythm chaos scene mode, the phase time opportunity difference is obtained, the amplitude compensation design based on the phase time opportunity difference is used to adjust the creation parameters of different scene factors of the rhythm chaos scene, and the first adjustment scheme is generated; S108: if the rhythm planning analysis result shows a rhythm inertia scene, a multi-dimensional parameter adjustment polar coordinate model is constructed, the adjustment strategy of the scene factor is analyzed on the multi-dimensional parameter adjustment polar coordinate model based on the inertia delay of the phase response drift of the current rhythm inertia scene, the creation parameters of the rhythm inertia scene are adjusted, and the second adjustment scheme is obtained.

2. The rhythm planning analysis-based immersive sleep scenario adjustment method according to claim 1, characterized in that, The S102 specifically comprises the following steps: The real-time physiological feedback data of the target user is collected through the Internet of Things, and the immersive sleep state data of the target user when the real-time physiological feedback data is generated in the historical time period is extracted through the sleep log; The biological sleep dynamics mechanism is introduced to establish a biological sleep dynamics state equation, the sleepability of the real-time physiological feedback data is evaluated according to the sleep steady state, the real-time sleepiness of the target user is tracked and updated along the tangent direction of the immersive sleep state data in the biological sleep dynamics state equation, and the real-time sleepiness index curve of the sleep time sequence is obtained; A sleep sliding window field of the current rhythm steady state is constructed, the variance weighting criterion of the sleep sliding window field is formulated according to the short-time sleep driving mechanism, and the sleep sliding window field is divided into a plurality of sleep sliding sub-windows according to the sleep behavior information of the target user; The steepness of the slope of the real-time sleepiness index curve in each sleep sliding sub-window is processed by peak degree weighting calculation based on the variance weighting criterion in the sleep sliding window frame, and the local sleepiness peak degree attenuation value of each sleep sliding sub-window is obtained; If the local sleepiness peak degree attenuation value is greater than a preset threshold, the peak-valley curve span corresponding to the sleep sliding sub-window is marked as a saturated state cutoff section, and if the local sleepiness peak degree attenuation value is less than the preset threshold, the peak-valley curve span is marked as an unsaturated state cutoff section; The real-time sleepiness index of the saturated state cutoff section and the unsaturated state cutoff section is obtained through the real-time sleepiness index curve, the center point of the saturated state cutoff section is located and labeled as a first proxy anchor point, and the center point of the saturated state cutoff section is located and labeled as a second proxy anchor point; The average height of the rhythm function of each saturated state cut-off section and unsaturated state cut-off section corresponding to the real-time sleepiness index is calculated on each first proxy anchor point and second proxy anchor point, an explicit Euler method is introduced to time-sequentially approximate integrate the average height of the rhythm function, and a rhythm below area model of the real-time sleepiness index curve is generated; A sleep staging rule is acquired, a phase mapping plan of the sleep staging rule is performed according to the proxy intercalation distribution of the saturated integration-unsaturated integration in the rhythm below area model, and a real-time sleep rhythm phase of the target user is obtained.

3. The rhythm planning analysis-based immersive sleep scenario adjustment method according to claim 2, characterized in that, The biological sleep dynamics mechanism is introduced to establish a biological sleep dynamics state equation, the real-time sleepiness of the target user is tracked and updated in the biological sleep dynamics state equation along the tangent direction of the immersed sleep state data according to the sleep steady state evaluation of the sleepiness plasticity of the real-time physiological feedback data, and a real-time sleepiness index curve of the sleep time sequence is obtained, specifically including the following steps: Based on big data retrieval, a rhythm sleep index system is acquired, the biological sleep dynamics mechanism is introduced, the real-time physiological feedback data is modeled by taking the immersed sleep state data as a state variable input for power state control, and a nonlinear biological sleep dynamics state equation is generated; The sleep steady state index is extracted from the rhythm sleep index system, the real-time physiological feedback data is evaluated in multiple dimensions by a series of sleep steady state indexes, the sleepiness plasticity coefficient of the target user is acquired, and the tracking resolution step is preset based on the sleepiness plasticity coefficient; According to the tangent direction of the immersed sleep state data which is linearly approximated, the balance prediction value on the collection time sequence is calculated along the tangent direction based on the tracking resolution step, the balance prediction value is substituted into the biological sleep dynamics state equation to predict the support position of the next power balance point, and a power alternation balance fulcrum is obtained. A Jacobian matrix is calculated based on the power alternation balance fulcrum to track and update the tangent direction, the candidate tangent point trajectory eigenvalue in the continuous updating process of the Jacobian matrix is output, the real-time sleepiness index of the target user is determined according to the candidate tangent point trajectory eigenvalue, and a real-time sleepiness index curve on the sleep time sequence is fitted and constructed.

4. The rhythm planning analysis-based immersive sleep scenario adjustment method according to claim 1, characterized in that, The S104 specifically includes the following steps: The preset creation control strategy of the current immersive sleep scene is called through the Internet of Things, and a dynamic pseudo-real model of the current immersive sleep scene is constructed by using a sleep scene simulation software; The preset creation control strategy is injected into the dynamic pseudo-real model as a dithering item, the real-time sleep rhythm phase is simulated by using the dynamic pseudo-real model after injection, the electroencephalogram signal of the target user is recorded in the simulation process, and a simulated electroencephalogram signal sequence is output; The actual electroencephalogram signal sequence of the target user in the current immersive sleep scene is acquired, a time-frequency domain registration space is constructed, and the time-frequency domain registration space is divided into N sub-registration blocks based on the given stage of sleep staging; A short-time Fourier transform algorithm is introduced to perform rhythm response transform calculation on the actual electroencephalogram signal sequence, so as to acquire an actual response frequency spectrum waveform, and a registration operation is performed on the simulated electroencephalogram signal sequence and the actual electroencephalogram signal sequence in the time-frequency domain registration space. Only extract the simulated response spectrum waveform and the corresponding sub-registration block in the simulated brain electrical signal sequence which has a similarity greater than a preset similarity threshold to the actual response spectrum waveform, and mark it as a response registration block, and obtain the registration overlap rate between the simulated response spectrum waveform and the actual response spectrum waveform through the response registration block; Determine the response spectrum distortion coefficient of the target user's response real-time sleep rhythm phase under the current immersive sleep scene jitter according to the registration overlap rate, and construct a Hilbert instantaneous phase transformation matrix based on the response spectrum distortion coefficient; Introduce a phase oscillation equation, and use the Hilbert instantaneous phase transformation matrix to observe and analyze the smooth scattered points of the response shift of the real-time sleep rhythm phase in the phase oscillation equation and inverse solve, to generate a simulated sleep rhythm phase; If the phase response drift function between the simulated sleep rhythm phase and the real-time sleep rhythm phase is positive, mark the current immersive sleep scene where the real-time sleep rhythm phase is located as a rhythm chaotic scene; if the phase response drift function between the simulated sleep rhythm phase and the real-time sleep rhythm phase is negative, mark the current immersive sleep scene as a rhythm inert scene, and obtain a rhythm planning analysis result.

5. The rhythm planning analysis-based immersive sleep scenario adjustment method according to claim 1, characterized in that, The S106 specifically includes the following steps: If the rhythm planning analysis result shows a rhythm chaotic scene, obtain the staging guidance decision information of different scene factors in the rhythm chaotic scene for the target user to enter the immersive sleep mode through an immersive sleep scene creation system; Embed the sleep staging rule as a benchmark modal scale architecture into a heterogeneous modal stage alignment grid, set the real-time sleep rhythm phase as a guide window event, and obtain the trigger timestamp of the sleep staging rule when the guide window event occurs; Align the rhythm chaotic scene to the stage alignment grid around the trigger timestamp as an alignment benchmark based on the staging guidance decision information, and traverse the modal alignment range between the sleep staging and the rhythm chaotic scene during the alignment process to obtain a phase timing difference of the rhythm chaotic scene; Obtain the open-loop transfer function of the immersive sleep scene creation system for creating the rhythm chaotic scene, draw and construct a Bode open-loop frequency diagram of the rhythm chaotic scene according to the open-loop transfer function, and identify the current low-frequency gain amount of the system for creating the rhythm chaotic scene by analyzing the Bode open-loop frequency diagram; Based on the preset maximum low-frequency gain demand amount, if the current low-frequency gain amount is insufficient, deploy and construct an amplitude tuning compensator in the immersive sleep scene creation system at this time, and constrain the boundary cutoff frequency of the amplitude tuning compensator based on the maximum low-frequency gain demand amount; According to the current low-frequency gain amount, use the amplitude tuning compensator to construct a tuning correction value of the rhythm chaotic scene, obtain the current cutoff frequency, and apply the tuning correction value to the immersive sleep scene creation system to adjust the creation parameters of each scene factor in the rhythm chaotic scene, until the current cutoff frequency approaches the boundary cutoff frequency, to obtain a first adjustment scheme. 6.The rhythm planning analysis-based immersive sleep scenario adjustment method according to claim 1, characterized in that, The S108 specifically includes the following steps: If the rhythm planning analysis result shows a rhythm inert scenario, the system obtains a number of prepared role creation parameters of different scene factors in the rhythm inert scenario and the intervention function of each prepared role creation parameter promoting the immersed sleep through the immersed sleep scenario creation system; Based on different scene factors, a polar coordinate branch is established, the prepared role creation parameters are deployed in the fixed point coordinate network of the polar coordinate branch, the K-means clustering algorithm is introduced to cluster the prepared role creation parameters to the network nodes of the fixed point coordinate network, an inert counter is assigned to each fixed point coordinate, and a multi-dimensional polar coordinate model of the rhythm inert scenario is generated; The real-time prepared role creation parameters of the rhythm inert scenario in the current working condition are obtained, the fixed point coordinates of each real-time prepared role creation parameter are searched and connected in the multi-dimensional polar coordinate model, and a real-time polar coordinate map is obtained; The delay weight of the real-time polar coordinate map on the phase response drift function is analyzed by the inert accumulation index of the inert counter, the starting center is sampled and planned from the real-time polar coordinate map according to the delay weight, and an auxiliary sampling map is obtained; The polar coordinate branch covered by the auxiliary sampling map, the fixed point coordinates and the corresponding prepared role creation parameters are extracted and defined as the candidate adjustment parameter solution, and the jitter residual gradient threshold value of the phase response drift function approaching 0 is preset; If the jitter residual gradient of the fixed point coordinate does not exceed the jitter residual gradient threshold value, the update of the candidate adjustment parameter solution of the fixed point coordinate is skipped; if the jitter residual gradient of the fixed point coordinate exceeds the jitter residual gradient threshold value, the corresponding candidate adjustment parameter solution is updated, and the adjustment strategy of each scene factor is obtained; Based on the adjustment strategy, the creation parameters of each scene factor in the rhythm inert scenario are adjusted by uploading to the immersed sleep scenario creation system, and a second adjustment scheme is obtained.

7. A system for adjusting an immersive sleep scenario based on a rhythm planning analysis, characterized in that, The system includes a memory, a processor, and a communication interface, the memory includes an immersed sleep scenario adjustment method program based on rhythm planning analysis, the communication interface is used for data connection communication between the memory and the processor, and the immersed sleep scenario adjustment method program based on rhythm planning analysis is executed by the processor to realize the immersed sleep scenario adjustment method steps of any one of claims 1-6.

Images