Method for adaptive comfort adjustment of a sleep instrument and sleep instrument

Abstract

The present application relates to the technical field of sleep regulation, in particular to a sleep instrument adaptive comfort adjustment method and a sleep instrument, comprising the following steps: monitoring breathing interval by using Internet of Things sensors, analyzing rhythm trend, identifying breathing response, monitoring skin temperature and body movement coordination, evaluating comfort state deviation, analyzing breathing and heart rate linkage, identifying sleep stage, combining environmental temperature and humidity trend, judging adjustment rhythm, and sending device control instruction set. In the present application, through the synchronous correlation of the real-time physiological state of the user and the environmental factors, the linkage relationship between the continuous breathing interval change trend and the heart rate fluctuation is analyzed, the sleep stage change process is accurately evaluated, and the synchronous fluctuation trend of the skin temperature and the body movement signal is combined to continuously and dynamically track the comfort state, automatically identify the coordination degree of individual physiological and environmental changes in the sleep cycle, optimize the external environmental parameter output rhythm, improve the environmental regulation precision, and ensure the smooth transition of the physiological state during the sleep stage conversion of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sleep regulation, in particular to a sleep instrument adaptive comfort adjustment method and a sleep instrument. BACKGROUND

[0002] The technical field of sleep regulation includes relevant technical systems for monitoring, identifying and intervening in various physiological and environmental parameters during the human sleep process, including controlling or adjusting relevant influencing factors through sleep state perception and determination, assisting or guiding users to enter different depth sleep stages, and systematically integrating physiological signal acquisition, sleep cycle modeling, external stimulus control, human behavior feedback and other sub-directions. The sleep regulation technology specifically covers sub-fields such as electroencephalogram signal recognition and response mechanism research, parameter control of acoustic, light and temperature perception stimulation, human-computer interaction scheme design, etc., aiming to build an intelligent intervention mechanism that adapts to individual characteristics and achieve continuous and dynamic sleep process management. The adaptive comfort adjustment method of the sleep instrument refers to a method of automatically adjusting the stimulation output parameters by collecting data such as skin temperature, body movement amplitude, and respiratory rate of the user during the sleep process, combining with the set threshold to judge the current comfort state. In view of the problem of user perception comfort change during long-term use of the sleep instrument, it covers the use of thermal sensors to collect body surface temperature, the use of piezoelectric film sensors to monitor micro-movement data, and the execution of pre-set rules by the control unit for real-time feedback adjustment. The specific implementation includes building a comfort reference model based on historical use data, comparing current state parameters in real time and identifying deviation range, and dynamically adjusting the working parameters of the thermal stimulation unit and the vibration feedback unit through the drive control module to maintain the stimulation output within the target comfort interval.

[0003] Traditional sleep instrument adjustment technology relies only on fixed threshold and historical data comparison during long-term operation, and does not fully consider the synchronous correlation between dynamic physiological changes and real-time environmental factors. During the transition of sleep stages, the coordination between physiological parameters and external environmental changes is not sufficient, and it is difficult to cope with the continuous fluctuation of comfort state, resulting in delayed comfort adjustment during the sleep period, obvious physiological discomfort during sleep state transition, affecting user sleep continuity and comfort, reducing sleep quality and weakening user long-term use experience. SUMMARY

[0004] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide a sleep instrument adaptive comfort adjustment method and a sleep instrument. The technical solution is as follows:

[0005] In order to achieve the above purpose, the present application adopts the following technical scheme, the adaptive comfort adjustment method of the sleep instrument, comprising the following steps:

[0006] S1: Real-time monitoring and recording of user's breathing interval data using Internet of Things sensors, analyzing the interval change direction and amplitude fluctuation difference of consecutive breathing cycles, identifying the deviation trend in rhythm change, calculating the trend consistency in breathing rhythm conversion path, and generating rhythm trend judgment information;

[0007] S2: According to the rhythm trend judgment information, analyze the amplitude change ratio before and after the breathing interruption node and the difference of continuous breathing recovery form, construct the joint parameter sequence of amplitude change and interruption time, identify the breathing response mode, and generate the breathing response classification label;

[0008] S3: Call the breathing response classification label, monitor and identify the continuous change range of skin temperature and the density of body movement signal, judge the coordination degree of temperature change and body movement density synchronous change trend, divide the deviation occurrence section according to the continuous length of synchronous trend, and generate the comfortable state deviation factor;

[0009] S4: Using the comfortable state deviation factor, real-time analyze the user's breathing fluctuation stable distribution and heart rate continuous difference change amplitude, by comparing the synchronous appearance frequency of breathing fluctuation event and heart rate amplitude change, identify and classify the user's sleep stage state, and generate the sleep stage recognition result.

[0010] As a further scheme of the present application, the rhythm trend judgment information includes frequency turning point distribution characteristics, interval change direction classification information, and rhythm conversion path consistency index, the breathing response classification label includes amplitude recovery type, interruption response characteristics, and periodic fluctuation structure, the comfortable state deviation factor includes skin temperature fluctuation amplitude, body movement density change level, and temperature movement coordination trend length, and the sleep stage recognition result includes breathing and heart rate synchronization ratio, linkage intensity distribution interval, and stage state label identification.

[0011] As a further scheme of the present application, the rhythm trend judgment information includes frequency turning point distribution characteristics, interval change direction classification information, and rhythm conversion path consistency index, the breathing response classification label includes amplitude recovery type, interruption response characteristics, and periodic fluctuation structure, the comfortable state deviation factor includes skin temperature fluctuation amplitude, body movement density change level, and temperature movement coordination trend length, and the sleep stage recognition result includes breathing and heart rate synchronization ratio, linkage intensity distribution interval, and stage state label identification.

[0012] S101: Real-time acquisition of user's breathing interval data using Internet of Things sensors, monitoring the interval change of consecutive breathing cycles, analyzing the fluctuation direction of each interval in the breathing cycle, combining the amplitude change trend, judging the interval fluctuation state, and generating the breathing interval fluctuation trend index;

[0013] S102: Based on the breathing interval fluctuation trend index, identify the frequency turning point distribution in the breathing stage, judge the density and sequence distribution of the turning point in the cycle change trend, establish the distribution characteristics of the frequency turning point, and obtain the frequency turning point deviation interval characteristics;

[0014] S103: Call the frequency turning offset interval feature, calculate the consistency of the continuous change direction of each stage in the respiratory rhythm transition path, analyze the persistence of the trend consistency, and establish rhythm trend judgment information.

[0015] As a further scheme of the present application, the acquisition step of the respiratory response classification label is:

[0016] S201: According to the rhythm trend judgment information, detect the respiratory interruption node, analyze the respiratory amplitude data before and after the interruption node, compare the amplitude ratio changes of the two sections, establish the amplitude ratio change sequence, and generate the amplitude change ratio sequence;

[0017] S202: Call the amplitude change ratio sequence, analyze the amplitude change and cycle length change in the continuous respiratory recovery period, judge the distribution mode of the respiratory amplitude adjustment frequency and the periodic fluctuation amplitude in the recovery stage, and obtain the recovery fluctuation feature;

[0018] S203: Based on the recovery fluctuation feature, construct a joint parameter sequence of amplitude change and interruption duration, compare the change trajectory of the parameters, identify the user's respiratory response mode, and generate a respiratory response classification label.

[0019] As a further scheme of the present application, the acquisition step of the comfort state offset factor is:

[0020] S301: Call the respiratory response classification label, monitor the continuous change range of skin temperature, detect the body motion signal in the same time period and count the body motion frequency per unit time, analyze the fluctuation amplitude of skin temperature and body motion signal, and generate a physiological fluctuation feature coefficient;

[0021] S302: According to the physiological fluctuation feature coefficient, compare the change curves of the skin temperature change amplitude and the body motion intensity in the same time period, judge the cooperative fluctuation trend of the two data, analyze the synchronous change interval and change direction of the two, and obtain the synchronous trend interval;

[0022] The specific formula for judging the cooperative fluctuation trend of the two data is:

[0023] ;

[0024] Calculate the synchronous trend cooperative coefficient;

[0025] Wherein, is the synchronous trend cooperative coefficient of skin temperature and body motion signal, is the skin temperature change normalized value in the first time window, is the skin temperature change cooperative weight in the first time window, the number of body movements in the first time window, the body movement change coordination weight in the first time window, the total number of windows in a monitoring period, the serial number index of the time window;

[0026] S303: According to the synchronization trend interval, the distribution of the synchronization trend duration in each monitoring period is judged, the offset occurrence section is divided according to the duration of the synchronization trend, the comfort state offset trend of the current period is evaluated, and a comfort state offset factor is generated.

[0027] As a further scheme of the present application, the acquisition step of the sleep stage recognition result is:

[0028] S401: The comfort state offset factor is called to monitor and analyze the respiratory fluctuation event and heart rate amplitude change data, the fluctuation frequency in the respiratory period and the heart rate fluctuation amplitude are counted, and the relative fluctuation mode of the respiratory and heart rate changes is analyzed to generate the respiratory and heart rate fluctuation relationship.

[0029] S402: Based on the respiratory and heart rate fluctuation relationship, the synchronization of the changes is analyzed, the synchronization proportion relationship is calculated, and the duration of the synchronization period is analyzed to judge the synchronization proportion relationship between the respiratory period fluctuation frequency and the heart rate change amplitude, calculate the physiological signal linkage change strength, and obtain the fluctuation linkage strength.

[0030] S403: According to the fluctuation linkage strength, the physiological signal linkage change strength, the sleep stage state of the user is identified and classified in real time according to the physiological signal linkage change strength, and a sleep stage recognition result is generated.

[0031] As a further scheme of the present application, the specific formula for judging the synchronization proportion relationship between the respiratory period fluctuation frequency and the heart rate change amplitude is:

[0032] ;

[0033] The synchronization linkage strength value is calculated;

[0034] wherein, the synchronization linkage strength value, the normalized value of the number of respiratory fluctuations of the user in the kth period, the average value of the respiratory fluctuation normalized values in m periods, the normalized value of the heart rate amplitude change of the user in the kth period, the average value of the heart rate amplitude change normalized values in m periods, The normalized amplitude change modulation factor based on physiological linkage sensitivity is extracted in the kth period, k is the index number of the period, and m is the number of monitoring periods.

[0035] As a further scheme of the present application, the method further comprises:

[0036] S5: using the sleep stage recognition result, analyzing the continuous heart rate variation amplitude and the body movement stable period length in real time, constructing a deep sleep stability index, combining the change direction and rate trend of the real-time environmental temperature and humidity, analyzing the synchronism of the user state and the environmental trend, judging the environmental condition adjustment rhythm, and generating a device control instruction set;

[0037] The device control instruction set comprises a deep sleep stability index scalar, a temperature and humidity adjustment synchronization parameter, and an environmental output rhythm control instruction.

[0038] As a further scheme of the present application, the device control instruction set comprises:

[0039] S501: calling the sleep stage recognition result, monitoring and analyzing the continuous heart rate variation amplitude and the body movement stable period length, analyzing the correlation between heart rate fluctuation and body movement period stability, and constructing a deep sleep stability index;

[0040] S502: based on the deep sleep stability index, combining the change trend of real-time environmental temperature and humidity, calculating the fluctuation direction and rate of temperature and humidity change, analyzing the synchronism of the user state and the environmental parameter, and generating environmental trend synchronism information;

[0041] S503: according to the environmental trend synchronism information, judging the environmental condition adjustment rhythm, combining the user sleep state and the environmental change trend, sending a control instruction to the environmental adjustment device, and generating a device control instruction set.

[0042] On the other hand, a sleep instrument comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps of the adaptive comfort adjustment method of the sleep instrument.

[0043] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0044] By synchronously correlating the real-time physiological state of the user and the environmental factors, analyzing the linkage relationship between the continuous breathing interval change trend and the heart rate fluctuation, accurately evaluating the sleep stage change process, and combining the synchronous fluctuation trend of the skin temperature and the body movement signal, the comfort state is continuously and dynamically tracked, the coordination degree of individual physiological and environmental changes in the sleep period is automatically identified, the output rhythm of external environmental parameters is optimized, the environmental regulation precision is improved, and the physiological state of the user is smoothly transitioned during the sleep stage conversion. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0046] Figure 1 The workflow of the present application is shown in the figure. DETAILED DESCRIPTION

[0047] The technical solutions in the present application will be described below with reference to the drawings.

[0048] In the embodiments of the present application, the words such as "example", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. In fact, the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0049] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. "Of", "corresponding" and "corresponding" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0050] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1. When the distinction is not emphasized, the meanings expressed are consistent.

[0051] In order to make the technical problems, technical solutions and advantages of the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0052] Please refer to Figure 1 The present application provides a technical solution, a sleep instrument adaptive comfort adjustment method, comprising the following steps:

[0053] S1: using Internet of Things sensors, real-time monitoring and recording user breathing interval data, analyzing interval change direction and amplitude fluctuation difference of continuous breathing cycle, identifying deviation trend in rhythm change, calculating trend consistency in breathing rhythm conversion path, and generating rhythm trend judgment information;

[0054] S2: According to the rhythm trend judgment information, the amplitude change proportion before and after the respiratory interruption node and the difference in continuous respiratory recovery form are analyzed, a joint parameter sequence of amplitude change and interruption time length is constructed, the respiratory response mode is identified, and a respiratory response classification label is generated;

[0055] S3: The respiratory response classification label is called to monitor and identify the continuous change range of skin temperature and the density of body movement signals, judge the coordination degree of temperature change and body movement density synchronous change trend, divide the deviation occurrence section according to the continuous length of synchronous trend, and generate a comfortable state deviation factor;

[0056] S4: Using the comfortable state deviation factor, real-time analysis of user respiratory fluctuation stable distribution and heart rate continuous difference change amplitude, by comparing the synchronous appearance frequency of respiratory fluctuation events and heart rate amplitude change, identifying and classifying the user's sleep stage state, generating sleep stage recognition result;

[0057] S5: Using the sleep stage recognition result, real-time analysis of continuous heart rate change amplitude and body movement stable cycle length, constructing a deep sleep stability index, combining the change direction and rate trend of real-time environmental temperature and humidity, analyzing the synchronization of user state and environmental trend change, judging the environmental condition adjustment rhythm, generating device control instruction set.

[0058] The rhythm trend judgment information includes frequency turning point distribution characteristics, interval change direction classification information, and rhythm conversion path consistency index. The respiratory response classification label includes amplitude recovery type, interruption response feature, and periodic fluctuation structure. The comfortable state deviation factor includes skin temperature fluctuation amplitude, body movement density change level, and temperature movement coordination trend length. The sleep stage recognition result includes respiratory and heart rate synchronization proportion, linkage intensity distribution interval, and stage state label identification. The device control instruction set includes deep sleep stability index scalar, temperature and humidity adjustment synchronization parameter, and environment output rhythm control instruction.

[0059] The acquisition step of the rhythm trend judgment information is:

[0060] S101: Using Internet of Things sensors, real-time collection of user respiratory interval data, monitoring of continuous respiratory cycle interval change, analysis of the fluctuation direction of each interval in the respiratory cycle, combination of amplitude change trend, judgment of interval fluctuation state, and generation of respiratory interval fluctuation trend index;

[0061] Using IoT sensors, real-time data on user breathing intervals is collected. First, airflow signals during breathing are acquired. A high-sensitivity flow sensor records the start and end times of each inhalation and exhalation. By setting the data acquisition frequency to 1Hz, a continuous 10-minute breathing interval sequence is obtained. For example, during the user's sleep preparation phase, the intervals of the first ten breathing cycles recorded are 3.2 seconds, 2.8 seconds, 3.1 seconds, 2.9 seconds, 3.0 seconds, 3.3 seconds, 3.1 seconds, 2.7 seconds, 3.2 seconds, and 3.0 seconds. Changes in the breathing interval for each cycle are detected. The difference between adjacent intervals is calculated and marked as positive or negative. For example, 2.8 seconds minus 3.2 seconds equals -0.4 seconds, indicating a shorter interval. These changes are then arranged sequentially. For subsequent analysis, all respiratory interval changes are sequentially accumulated, and a sliding window is used to determine the trend of the changes in amplitude over consecutive cycles. When determining the trend of amplitude changes, the five most recent respiratory interval changes are selected. If the percentage of positive values ​​exceeds 60%, it is determined that the respiratory interval is continuously lengthening; otherwise, it is determined that it is shortening. Combining the above amplitude change trend, in this example, assuming the changes in the first five cycles are -0.4, 0.3, -0.2, 0.1, and 0.3 seconds, with 3 positive values ​​and 2 negative values, the respiratory interval fluctuation trend is determined to be mainly lengthening. Furthermore, based on the accumulated duration of different fluctuation directions, the respiratory interval fluctuation trend index is calculated using the following formula, where the total duration of positive fluctuations is... The total duration of negative fluctuations is The respiratory interval fluctuation trend index is ,in, This is an indicator of the trend of respiratory interval fluctuations. This represents the total duration of the positive fluctuation. For the total duration of negative fluctuations, the parameter The value ranges from -1 to 1. Positive values ​​indicate a trend of increasing intervals, while negative values ​​indicate a trend of decreasing intervals. For example, if... Second, seconds, then This indicates that the user's current respiratory interval is showing a slightly prolonged trend. (If this occurs within the data collection period...) If the value repeatedly fluctuates above 0.1, the system determines that the interval fluctuation is continuously increasing. If the data collection period is within this range... If the value remains below -0.2, it is determined that the interval fluctuation is continuously shortening. By combining the trend and proportion of amplitude changes, the status of respiratory interval fluctuation is monitored, and the trend index of respiratory interval fluctuation is finally obtained.

[0062] S102: Based on the respiratory interval fluctuation trend index, identify the distribution of frequency inflection points in the respiratory phase, determine the density and sequence distribution of inflection points in the periodic change trend, establish the distribution characteristics of frequency inflection points, and obtain the frequency inflection offset interval characteristics.

[0063] Based on the respiratory interval fluctuation trend index, the frequency turning point distribution in the respiratory stage is further analyzed, the window sliding method is used to detect the extreme points in the continuous respiratory cycle, the position of the maximum value and the minimum value is judged once every 5 cycles, for example, if the interval value between the 3rd, 6th and 9th cycle is the peak value or the valley value, the cycle number of these cycles is recorded as the frequency turning point, then the density of the turning point appearing in the total detection cycle is counted, the density calculation formula is , wherein is the turning point density, is the total number of turning points, is the total number of detection cycles, if 5 turning points are detected in 10 minutes, the density is 5 / 10=0.5, the distribution of these turning points in the cycle sequence is further analyzed, the standard deviation is used to evaluate the uniformity of the interval between the turning points, if the standard deviation is small, it means that the turning point distribution is uniform, if the standard deviation is large, it means that the turning points are concentrated in certain specific cycles, the frequency turning point shift phenomenon is judged combined with the distribution, then the distribution diagram of the turning point appearing is drawn according to the respiratory interval change of different users, the horizontal axis is the cycle number, the vertical axis is the respiratory interval, the turning point is marked with an asterisk, which is convenient for intuitive judgment of the cycle distribution state, if the 3rd, 6th and 9th cycle is the peak value in 10 cycles, the frequency turning point distribution characteristic is periodic shift, finally the shift interval of the frequency turning point is induced according to the distribution characteristic, each shift interval is numbered, for example, shift interval 1 corresponds to 3-4 cycle, shift interval 2 corresponds to 6-7 cycle, shift interval 3 corresponds to 9-10 cycle, the frequency turning point shift interval characteristic is finally obtained.

[0064] S103: calling the frequency turning point shift interval characteristic, calculating the consistency of the continuous change direction in each stage of the respiratory rhythm conversion path, analyzing the persistence of the trend consistency, and establishing rhythm trend judgment information;

[0065] The frequency turning point shift interval characteristic is called, the consistency of the continuous change direction of the respiratory rhythm conversion path is analyzed, the interval change direction in each shift interval is collected, which is marked as rising or falling in turn, the proportion of the consistency of the continuous change direction in each stage is calculated, for example, in shift interval 1, if the interval change between the 3rd and 4th cycle is rising, the consistency of the change direction in this interval is 100%, if in shift interval 2, the 6th cycle is rising and the 7th cycle is falling, the consistency is 50%, the length of the period of consistency in each shift interval is further counted, the consistency of the trend is analyzed by using the following formula , wherein is the trend consistency, is the length of the consistency period, For interval total length, for example, interval 1 length is 2 periods, consistency length is 2, then , interval 2 length is 2, consistency length is 1, then , the average of the total interval is obtained, and the overall trend consistency is obtained, if the overall is greater than 0.7, it is judged that the respiratory rhythm conversion path has obvious one-way trend, if the overall is less than 0.3, the trend shows frequent conversion, and finally the rhythm trend judgment information is established through the above analysis.

[0066] The acquisition step of the respiratory response classification label is:

[0067] S201: According to the rhythm trend judgment information, the respiratory interruption node is detected, the respiratory amplitude data before and after the interruption node is analyzed, the amplitude ratio change of the two sections is compared, the amplitude ratio change sequence is established, and the amplitude change ratio sequence is generated;

[0068] According to the rhythm trend judgment information, when the respiratory interruption node is detected, the respiratory signal of the user in the continuous respiratory period is collected, the respiratory flow or chest and abdomen belt sensor signal is recorded, the algorithm is used to identify the node with large interval increase or significant decrease of respiratory intensity in the signal, the 15th period is set as the respiratory interruption node, the respiratory amplitude data of the 5 periods before and after the interruption node is extracted, it is assumed that the amplitudes of the first 5 periods are 0.32, 0.35, 0.36, 0.34 and 0.33 liters, and the amplitudes of the last 5 periods are 0.15, 0.18, 0.22, 0.29 and 0.31 liters, the average values of the two sections are compared, the average value of the first section is 0.34 liters, and the average value of the last section is 0.23 liters, the ratio change of the amplitudes of the two sections is calculated , wherein is the average value of the amplitude of the last section, is the average value of the amplitude of the first section, in this example , if multiple respiratory interruption nodes are continuously detected, the amplitude ratio change is obtained for each node in the same way, the amplitude ratio change of all interruption nodes is arranged in turn, the amplitude ratio change sequence is established, and finally the amplitude change ratio sequence is generated, wherein is the amplitude change ratio, is the average value of the amplitude of the last section, is the average value of the amplitude of the first section.

[0069] S202: The amplitude change ratio sequence is called, the amplitude change and period length change in the continuous respiratory recovery period are analyzed, the distribution mode of the respiratory amplitude adjustment frequency and the periodic fluctuation amplitude in the recovery stage is judged, and the recovery fluctuation characteristics are obtained.

[0070] The amplitude change ratio sequence is called, the amplitude change and the period length change in the continuous breathing recovery period are analyzed, the amplitude and the period length of 10 consecutive breathing periods after the interruption are collected, it is assumed that the amplitudes are 0.15, 0.18, 0.22, 0.29, 0.31, 0.33, 0.34, 0.35, 0.36, 0.37 liters respectively, and the period lengths are 2.5, 2.7, 2.9, 3.0, 3.1, 3.2, 3.1, 3.0, 2.8, 2.6 seconds respectively, for each period, the amplitude change rate is calculated wherein is the amplitude of the i th period, the amplitude adjustment frequency of each period is analyzed, the number of times of positive growth and negative growth of the amplitude is counted, if the number of times of positive growth in the first five periods is more than that of negative growth, it is determined that the amplitude continuously increases at the early stage of recovery, and the amplitude tends to be stable at the later stage, the standard deviation of the period length of each period is calculated, reflecting the fluctuation amplitude, if the standard deviation in the first five periods is greater than that in the last five periods, it is determined that the fluctuation amplitude is large at the early stage and tends to be stable at the later stage, combined with the analysis results above, the amplitude change rate and the period length fluctuation of each period are counted, and the recovery fluctuation characteristics are summarized, wherein is the amplitude change rate, is the amplitude of the i th period.

[0071] S203: based on the recovery fluctuation characteristics, a joint parameter sequence of amplitude change and interruption duration is constructed, the change trajectory of the parameters is compared, the breathing response mode of the user is identified, and a breathing response classification label is generated;

[0072] Based on the recovery fluctuation characteristics, a joint parameter sequence of amplitude change and interruption duration is constructed, the duration of each breathing interruption and the recovery amplitude change rate are recorded, it is assumed that the interruption durations are 4.2 seconds, 5.0 seconds and 3.8 seconds respectively, and the recovery amplitude change rates are 0.50, 0.60 and 0.45 respectively, and the joint parameter sequence is constructed wherein is the interruption duration, is the recovery amplitude change rate, the change trajectory of the parameters is further compared, the joint parameter distribution of each event is displayed in the form of a scatter plot, if the interruption duration of the same user is longer and the amplitude recovery rate is higher, it is classified into the fast recovery type response, if the interruption duration is short and the amplitude recovery rate is low, it is classified into the slow recovery type response, different breathing response modes are identified, and finally a breathing response classification label is generated, wherein is the interruption duration, is the recovery amplitude change rate.

[0073] The acquisition step of the comfort state offset factor is:

[0074] S301: Call the respiratory response classification label, monitor the continuous change range of skin temperature, detect the body motion signal in the same time period and count the number of body motions per unit time, analyze the fluctuation amplitude of skin temperature and body motion signal, and generate physiological fluctuation characteristic coefficient;

[0075] When calling the respiratory response classification label to monitor the continuous change range of skin temperature, a thermosensitive sensor is attached to the user's wrist skin, and the skin temperature is recorded every 10 seconds. Assuming that the temperature sequence measured in 10 consecutive minutes is 33.1, 33.2, 33.3, 33.5, 33.6, 33.7, 33.5, 33.4, 33.2, and 33.0 degrees Celsius, the body motion signal in the same time period is detected, the acceleration sensor is used to capture the micro-motion changes of the user, and the peak value of the body motion signal per minute is accumulated. For example, the number of body motions per minute is 5, 7, 6, 8, 5, 4, 6, 5, 7, and 6 times, the fluctuation amplitude of skin temperature and body motion signal is analyzed, and the maximum amplitude and mean deviation of each change is calculated respectively. The fluctuation amplitude of skin temperature can be calculated as , The fluctuation amplitude of body motion signal can be calculated as , The two data are normalized, and the skin temperature fluctuation normalization coefficient and the body motion signal fluctuation normalization coefficient are used, for example , where is the average temperature, in this example , , is the average number of body motions, The two normalization coefficients are weighted and calculated, and the weights are 0.4 and 0.6 respectively. The physiological fluctuation characteristic coefficient is substituted into the data , where is the fluctuation amplitude of skin temperature, is the maximum temperature, is the minimum temperature, is the average temperature, is the fluctuation amplitude of body motion signal, is the maximum number of body motions, is the minimum number of body motions, is the average number of body motions, is the skin temperature normalization coefficient, is the body motion normalization coefficient, is the physiological fluctuation characteristic coefficient, and the physiological fluctuation characteristic coefficient is finally generated.

[0076] S302: Based on the physiological fluctuation characteristic coefficient, compare the change curves of skin temperature change amplitude and body movement intensity within the same time period, determine the coordinated fluctuation trend of the two data, analyze the synchronous change range and direction of the two, and obtain the synchronous trend range.

[0077] The specific formula for determining the coordinated fluctuation trend of the two data points is as follows:

[0078] ;

[0079] Calculate the synchronization trend coordination coefficient;

[0080] in, This represents the synchronization trend coefficient between skin temperature and body movement signals. For the first Normalized values ​​of skin temperature changes within a time window For the first Coordinated weighting of skin temperature changes within a time window For the first Normalized value of the change in the number of body movements within a time window For the first Coordination weights of body motion changes within a time window The total number of windows in the monitoring period. This is the index of the time window.

[0081] Using formula Determine the coordinated fluctuation trend of two data points. In this formula, The synchronization trend coefficient between skin temperature and body movement signals represents the strength of the synchronization between normalized temperature and body movement fluctuations; a larger value indicates a more pronounced synchronization trend. The numerator uses a weighted summation method, adding the normalized results of temperature and body movement changes within each monitoring window, with weights... and Used to emphasize the importance of a specific window or the reliability of data, the absolute value sign ensures that both positive and negative fluctuations are counted. The denominator, by summing and square-taking the absolute values ​​of the normalized changes across all windows, serves to normalize, scale, and amplify anomalous fluctuations, thus outputting a dimensionless co-variable parameter that distinguishes the fluctuation characteristics of different individuals and time periods. The detailed definitions of each parameter are as follows: The synchronization trend coefficient between skin temperature and body movement signals (dimensionless). For the first The normalized values ​​of skin temperature changes within a time window, the normalization process is as follows: ,in For the first Temperature measurement values ​​for each window. The standard deviation of skin temperature change over a reference time period. is the normalized value of the body movement number in the first time window, and the normalization process is , wherein is the body movement number in the first window, is the standard deviation of the body movement change in the reference time of the same section, is the normalized change of skin temperature in the first window, is the normalized change of body movement in the first window, is the total number of windows, represents the absolute value, is the window accumulation, is the square root. The acquisition and value calculation of each parameter are as follows: temperature normalized change : Taking the skin temperature data monitored for 10 minutes (1 collection per minute) as an example, the sequence is assumed to be (unit: ℃), and the standard deviation is obtained by the standard deviation calculation formula, ℃, taking the second window as an example: , and the rest are obtained in turn. Body movement normalized change : Assuming that the body movement data collection frequency is 1 per minute, the body movement number sequence is (unit: times), times, and is calculated in the same way. Weight , : If the experiment shows that the contribution weight of temperature change to synchrony is 0.6 and the body movement is 0.4, then the weight in the whole cycle is set to , , the optimal weight can also be obtained through cross-validation or Bayesian optimization experiment, and the reasonable range of the interval is 0.2-0.8. Take 10 windows, and substitute the following (take the first 4 windows as an example):

[0082] Table 1 Skin temperature and body movement signal monitoring and normalized data table

[0083]

[0084] Table 1 lists the actual measurement values and normalized calculation results of skin temperature and body movement signals under some windows. As shown in Table 1, the measurement data has been standardized. Formula actual example:

[0085] molecule;

[0086] ; ; and the weight is substituted

[0087] Window 2: ;

[0088] Window 3: ;

[0089] Window 4: ;

[0090] Summation: ;

[0091] Take the absolute value: ;

[0092] Denominator:

[0093] Window 2: ;

[0094] Window 3: ;

[0095] Window 4: ;

[0096] Summation: ;

[0097] Prescription: ;

[0098] Final result: ;

[0099] If within the entire cycle A value consistently greater than 0.6 is defined as a high synergy trend range, 0.3-0.6 as moderate synergy, and less than 0.3 as weak synergy. This result indicates that the current synchronization trend synergy level is generally moderate. Combining data from other steps can further deduce the level of comfort deviation trend, thereby influencing the output range and mode of regulatory commands. The formula effectively integrates the contributions of different types of physiological signals to the synchronization trend by weighted summation of the normalized values ​​of skin temperature changes and body movement signal changes, significantly improving the sensitivity and stability of cross-signal synergy analysis. This provides a precise data foundation for subsequent comfort range segmentation and adaptive control strategies.

[0100] S303: Based on the synchronization trend interval, determine the distribution of the synchronization trend duration in each monitoring cycle, divide the offset occurrence segment according to the duration of the synchronization trend, evaluate the comfort state offset trend of the current cycle, and generate the comfort state offset factor.

[0101] Based on the aforementioned synchronization trend intervals, the distribution of synchronization trend durations within each monitoring period is determined. The lengths of synchronization trend intervals within each period are statistically analyzed, and the durations of consecutive synchronization intervals are accumulated. A duration distribution histogram is then generated, with the longest synchronization interval length set as... , all interval average duration is , compare the length of each interval with the average duration, if the length of an interval exceeds 1.5 times the average duration, it is determined that the interval is a deviation occurrence section, the distribution of all deviation sections in the period is comprehensively analyzed, the deviation trend of the current period comfort state is evaluated, and the deviation index , for example minutes, minutes, then , wherein is the length of the longest synchronization interval, is the average duration of all intervals, is the deviation index, and finally the comfort state deviation factor is generated.

[0102] The acquisition step of the sleep stage recognition result is:

[0103] S401: Call the comfort state deviation factor, monitor and analyze the respiratory fluctuation event and heart rate amplitude change data, count the fluctuation times and heart rate fluctuation amplitude in the respiratory period, and analyze the synchronous appearance frequency, identify the relative fluctuation mode of respiratory and heart rate change, and generate the respiratory and heart rate fluctuation relationship;

[0104] When calling the comfort state deviation factor to monitor and analyze the respiratory fluctuation event and heart rate amplitude change data, first call the respiratory signal monitoring result, count the respiratory fluctuation event frequency in the continuous monitoring period, and use the threshold method to determine that the amplitude fluctuation in the respiratory signal exceeding 10% of the average amplitude is counted as a fluctuation event. Assuming that 18 fluctuation events are detected in 10 minutes, then get the heart rate data in the same period, get each R-R interval through photoplethysmography or electrocardiogram signal, calculate the difference between the maximum and minimum values of heart rate in each respiratory period, and record it as the heart rate fluctuation amplitude. Assuming that the heart rate fluctuation amplitudes of the first to tenth periods are 6, 8, 5, 7, 9, 6, 5, 8, 7, and 6 times per minute, respectively, the respiratory fluctuation event and the heart rate fluctuation amplitude are compared one by one, if the respiratory fluctuation event occurs and the heart rate fluctuation amplitude exceeds 6 times per minute in a certain period, it is considered as a synchronous event, the number of synchronous events in 10 periods is counted, assuming that there are 7 periods in the synchronous state, the synchronous appearance frequency is 7 / 10=0.7, further analyze the relationship between the respiratory fluctuation and the heart rate change in each period, if they appear at the same time and the change direction is consistent in most periods, it is identified as the positive relative fluctuation mode of respiratory and heart rate change, if the respiratory fluctuation increases and the heart rate fluctuation amplitude decreases, it is the reverse fluctuation, according to the above standard, the fluctuation mode of each period is marked respectively, the proportion of positive mode is counted, and the positive proportion is greater than 0.6 is set as the dominant positive, otherwise it is the reverse, and finally the respiratory and heart rate fluctuation relationship is generated.

[0105] S402: Based on the relationship between respiration and heart rate fluctuations, analyze the synchronicity of changes, calculate the synchronicity ratio and analyze the duration of the synchronicity cycle, determine the synchronicity ratio between the number of respiratory cycle fluctuations and the amplitude of heart rate changes, calculate the intensity of physiological signal linkage changes, and obtain the intensity of fluctuation linkage.

[0106] The specific formula for determining the synchronous proportional relationship between the number of respiratory cycle fluctuations and the amplitude of heart rate changes is as follows:

[0107] ;

[0108] Calculate the synchronization intensity value, determine the synchronization ratio between the number of respiratory cycle fluctuations and the amplitude of heart rate changes, calculate the intensity of physiological signal linkage changes, and obtain the fluctuation linkage intensity.

[0109] in, This is the synchronous linkage intensity value. This is the normalized value of the number of user breathing fluctuations in the k-th cycle. This represents the normalized average of the number of respiratory fluctuations over m cycles. This represents the normalized value of the user's heart rate amplitude change during the k-th cycle. This represents the average of the normalized values ​​of the heart rate amplitude variation over m cycles. is the normalized amplitude change modulation factor extracted based on physiological linkage sensitivity within the k-th cycle, where k is the index number of the cycle and m is the number of monitoring cycles.

[0110] To quantify the degree of physiological signal linkage when calculating the synchronization ratio and analyzing the duration of the synchronization cycle, the following formula is used: In the above formula, This represents the synchronization strength value with modulation weights, is dimensionless, and ranges from 0 to 1. A value closer to 1 indicates a stronger synchronization between the respiratory cycle and heart rate changes; Parameter Indicates the first The normalized value of the number of breaths per minute for a given period is obtained by collecting the user's respiratory rate per minute from an IoT sensor. Normalization is performed by subtracting the minimum value of the period from the measured frequency and then dividing by the maximum-minimum difference. For example, if the monitored data is a respiratory rate group within a period {16 breaths / min, 17 breaths / min, 19 breaths / min, 20 breaths / min}, then the first normalized value is calculated as follows: And so on; parameters For all The average of the normalized respiratory rate fluctuations within each cycle, that is, the normalized value of each cycle. Add them together and then divide by the total number of cycles. If the above data, after normalization, becomes {0, 0.25, 0.75, 1}, then... ; parameter is the normalized value of the amplitude of the heart rate of the user in the first period, which is calculated by collecting the difference between the maximum and minimum heart rate changes in the period and using the same normalization method as the number of respiratory fluctuations. For example, the heart rate changes in the period are {8 times / min, 9 times / min, 10 times / min, 12 times / min}, and the first value is normalized to ; parameter is the average value of the normalized amplitude of the heart rate of the user in all periods, which is calculated in the same way as . For example, the normalized data are {0, 0.25, 0.5, 1}, and ; parameter represents the normalized amplitude change modulation factor based on the physiological linkage sensitivity extracted in the first period, which is obtained by normalizing the ratio of the amplitude of the body motion signal intensity change in the period to the user-set comfortable body motion amplitude reference value. For example, the comfortable body motion amplitude reference value is set to 5 mm, and the actual body motion amplitude is {4 mm, 5 mm, 6 mm, 7 mm}, and the first period modulation factor is calculated as , and the normalization processing method is to standardize the ratio of the above result to the maximum value 7 mm / 5 mm = 1.4, i.e. , and the normalized ;

[0111] The actual monitoring data are taken as an example, as shown in Table 2:

[0112] Table 2 User respiratory, heart rate, and body motion amplitude monitoring data table

[0113]

[0114] According to the data in Table 2, the normalized values of the parameters in each period are calculated as follows:

[0115] , respectively, i.e. ;

[0116] , respectively, i.e. ;

[0117] , respectively, i.e.

[0118] The actual operation is carried out by inputting the formula:

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] The results show that the physiological signal synchronization linkage strength between the number of user breathing fluctuations and the heart rate change amplitude is 0.699, indicating that there is a high linkage level between the two. After using the linkage synchronization degree calculation method of the body motion amplitude modulation factor, the formula can dynamically identify the cooperative change mode of the user's breathing, heart rate and body motion multi-parameters, breaking through the limitations of single signal linkage discrimination. In the actual sleep cycle, when the user has a short-time body motion disturbance or physiological parameter mutation, the cooperative response level of the physiological signal is fed back in time, improving the ability to capture the fluctuation of the stage sleep state, enhancing the adaptability of the sleep instrument adjustment strategy to complex sleep environment and individual differences, ensuring the real-time and multi-dimensional consistency of the comfort regulation decision, and further promoting the continuity and depth recovery of the user's sleep process.

[0124] S403: According to the fluctuation linkage strength, the sleep stage state of the user is identified and classified in real time according to the physiological signal linkage change strength, and a sleep stage identification result is generated;

[0125] When the fluctuation linkage strength is used to identify and classify the sleep stage state of the user in real time according to the physiological signal linkage change strength, the fluctuation linkage strength is divided into intervals, such as 0.7 or more for deep sleep period, 0.4-0.7 for light sleep period, and less than 0.4 for rapid eye movement period. The continuous monitoring obtained According to the period, different partitions are classified, for example, if there are 6 periods of 10 monitoring periods 0.75, 3 periods of 0.5, and 1 period of 0.35, then 6 periods correspond to the deep sleep period, 3 periods correspond to the light sleep period, and 1 period corresponds to the rapid eye movement period. The number of periods in each partition is counted, and the overall sleep stage type is determined according to the majority of periods, and finally a sleep stage identification result table is generated according to the period number, recording the sleep stage to which each period belongs.

[0126] The acquisition step of the device control instruction set is:

[0127] S501: Call the sleep stage identification result, monitor and analyze the continuous heart rate change amplitude and body motion stable period length, analyze the correlation between heart rate fluctuation and body motion period stability, and construct a deep sleep stability index;

[0128] The sleep stage recognition result is called to monitor and analyze the continuous heart rate variation amplitude and body movement stable period length, first, the photoplethysmography continuous recording heart rate signal is acquired, every 5 minutes is selected as a group, the difference between the maximum heart rate and the minimum heart rate in the group is calculated to obtain the heart rate fluctuation amplitude sequence, for example, the heart rate fluctuations of 10 groups are 8, 7, 6, 7, 9, 8, 7, 6, 8, 7 times / min, at the same time, the body movement signal stable duration in each group period is counted through the body movement sensor, assuming that the body movement stable periods are 15, 18, 16, 20, 17, 18, 15, 19, 16, 18 minutes, after normalization processing of the two groups of data, the correlation between the heart rate fluctuation change and the body movement stable period is analyzed, the heart rate fluctuation standard deviation is , the body movement period standard deviation is , the correlation coefficient of the two is calculated , wherein, is the heart rate fluctuation of the ith group, is the mean of the heart rate fluctuation, is the body movement period of the ith group, is the mean of the body movement period, if the correlation coefficient is greater than 0.6, it is determined as high correlation, otherwise, it is low correlation, the correlation and the body movement period are combined to give weight, the deep sleep stability index is set as , for example, if , , , then , the deep sleep stability index is finally constructed.

[0129] S502: Based on the deep sleep stability index, the change trend of real-time environmental temperature and humidity is combined to calculate the fluctuation direction and rate of temperature and humidity change, analyze the synchronicity of user state and environmental parameters, and generate environmental trend synchronicity information;

[0130] Based on the deep sleep stability index, the change trend of real-time environmental temperature and humidity is combined, a temperature and humidity sensor is called to continuously record room temperature and humidity data at every 10 second interval, the temperature change rate and the humidity change rate in the same period are extracted, the difference formula is used, , wherein, and are the end and start temperatures in the period, and are the humidity data, for example, if the temperature rises from 24.0 to 24.7 degrees Celsius and the humidity decreases from 60% to 57%, then , , the temperature and humidity change direction and rate are normalized respectively, the normalized rate , Final synchronism information index The smaller the value is, the higher the synchronism between the user state and the environment parameter is. Take an example: , , Finally, the environment trend synchronism information is generated.

[0131] S503: According to the environment trend synchronism information, the environment condition adjustment rhythm is judged, and the control instruction set of the device is generated by combining the user sleep state and the environment change trend, and sending the control instruction to the environment adjustment device.

[0132] When judging the environment condition adjustment rhythm according to the environment trend synchronism information, the synchronism adjustment reference value is set. If the synchronism information is greater than 0.1, it is determined that the difference between the environment change and the user state rhythm is obvious, the system automatically delays the temperature and humidity adjustment device output for 2 minutes, and reduces the fan and heating power by 30%. If the synchronism information is in the interval of 0.05-0.1, only delay 1 minute, and reduce the power by 10%. If it is lower than 0.05, the current device output state is maintained unchanged. Three groups of instruction parameters are generated by combining the sleep stage identification and the synchronism information result, which are device output delay time, output power adjustment ratio and current output mode number. In the example, if the environment synchronism is 0.12, the output is delayed for 2 minutes, the power is reduced by 30%, and the number is "mode 3". Through the system, the device control instruction set is finally generated and sent to the environment adjustment device interface.

[0133] The above embodiments can be realized by software, hardware (such as circuit), firmware or any combination thereof, in whole or in part. When software is used, the above embodiments can be realized in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the flow or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD), or semiconductor medium. The semiconductor medium can be a solid state disk.

[0134] It should be understood that the term "and / or" in this document is merely used to describe associated objects, and it is possible that there are three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, B exists alone, and A, B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood according to the context before and after.

[0135] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including single item or any combination of multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be singular or plural.

[0136] It should be understood that the size of the sequence number of the above-mentioned processes in various embodiments of the application does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0137] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-mentioned devices, apparatuses and units can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0139] In several embodiments provided by the application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0141] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0142] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0143] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled 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 of adaptive comfort adjustment of a sleep apparatus, characterized in that, The method comprises: S1: using an Internet of Things sensor to monitor and record the breathing interval data of a user in real time, analyze the interval change direction and amplitude fluctuation difference of consecutive breathing cycles, identify the deviation trend in rhythm change, calculate the consistency of the trend in the breathing rhythm conversion path, and generate rhythm trend judgment information; The rhythm trend judgment information acquisition step is: S101: using an Internet of Things sensor to collect the breathing interval data of a user in real time, monitor the interval change of consecutive breathing cycles, analyze the fluctuation direction of each interval in the breathing cycle, judge the interval fluctuation state in combination with the amplitude change trend, and generate a breathing interval fluctuation trend index; S102: based on the breathing interval fluctuation trend index, identifying the frequency turning point distribution in the breathing stage, judging the density and sequence distribution of the turning points in the cycle change trend, establishing the distribution characteristics of the frequency turning points, and obtaining the frequency turning deviation interval characteristics; S103: calling the frequency turning deviation interval characteristics, calculating the consistency of the continuous change direction of each stage in the breathing rhythm conversion path, analyzing the persistence of the trend consistency, and establishing rhythm trend judgment information; S2: according to the rhythm trend judgment information, analyzing the amplitude change proportion before and after the breathing interruption node and the difference in the recovery form of consecutive breathing, constructing a joint parameter sequence of amplitude change and interruption duration, identifying the breathing response mode, and generating a breathing response classification label; The breathing response classification label acquisition step is: S201: according to the rhythm trend judgment information, detecting the breathing interruption node, analyzing the breathing amplitude data before and after the interruption node, comparing the amplitude proportion change of the two sections, establishing an amplitude proportion change sequence, and generating an amplitude proportion change sequence; S202: calling the amplitude proportion change sequence, analyzing the amplitude change and cycle length change in the continuous breathing recovery cycle, judging the distribution mode of the breathing amplitude adjustment frequency and the periodic fluctuation amplitude in the recovery stage, and obtaining a recovery fluctuation feature; S203: based on the recovery fluctuation feature, constructing a joint parameter sequence of amplitude change and interruption duration, comparing the change trajectories of the parameters, identifying the breathing response mode of the user, and generating a breathing response classification label; S3: calling the breathing response classification label, monitoring and identifying the continuous change range of skin temperature and the density of body motion signals, judging the coordination degree of the synchronous change trend of temperature change and body motion density, dividing the deviation occurrence section according to the duration of the synchronous trend, and generating a comfortable state deviation factor; The comfortable state deviation factor acquisition step is: S301: calling the breathing response classification label, monitoring the continuous change range of skin temperature, detecting the body motion signals in the same time period and counting the number of body motions per unit time, analyzing the fluctuation amplitude of skin temperature and body motion signals, and generating a physiological fluctuation feature coefficient; S302: according to the physiological fluctuation feature coefficient, comparing the change curves of the skin temperature change amplitude and the body motion density in the same time period, judging the collaborative fluctuation trend of the two data, analyzing the synchronous change interval and change direction of the two, and obtaining a synchronous trend interval; The specific formula for judging the collaborative fluctuation trend of the two data is: ； Calculate the synchronization trend coordination coefficient; wherein, is a synchronization trend coefficient of the skin temperature and the body motion signal, is a normalized value of the skin temperature change in the first time window, is a synchronization weight of the skin temperature change in the first time window, is a normalized value of the body motion frequency change in the first time window, is a synchronization weight of the body motion change in the first time window, is a total number of windows of a monitoring period, is a serial index of a time window; S303: Based on the synchronization trend interval, determine the distribution of the synchronization trend duration in each monitoring cycle, divide the offset occurrence segment according to the duration of the synchronization trend, evaluate the comfort state offset trend of the current cycle, and generate the comfort state offset factor. S4: Using the aforementioned comfort state offset factor, analyze in real time the stable distribution of the user's respiratory fluctuations and the amplitude of continuous differences in heart rate changes. By comparing the synchronous occurrence frequency of respiratory fluctuation events and heart rate amplitude changes, identify and classify the user's sleep stage states, and generate sleep stage identification results.

2. The adaptive comfort adjustment method of a sleep apparatus according to claim 1, wherein, The rhythm trend judgment information includes frequency inflection point distribution characteristics, interval change direction classification information, and rhythm transition path consistency index. The respiratory response classification label includes amplitude recovery type, interruption response characteristics, and periodic fluctuation structure. The comfort state offset factor includes skin temperature fluctuation amplitude, body motion density change level, and temperature-motion coordination trend length. The sleep stage identification result includes the synchronization ratio of breathing and heart rate, linkage intensity distribution range, and stage state label identifier.

3. The adaptive comfort adjustment method of a sleep apparatus according to claim 1, wherein, The steps for obtaining the sleep stage identification results are as follows: S401: Call the comfort state offset factor, monitor and analyze respiratory fluctuation events and heart rate amplitude change data, count the number of fluctuations and heart rate fluctuation amplitudes within the respiratory cycle, analyze the frequency of synchronous occurrence, identify the relative fluctuation pattern of respiratory and heart rate changes, and generate the relationship between respiratory and heart rate fluctuations. S402: Based on the relationship between respiration and heart rate fluctuations, analyze the synchronicity of changes, calculate the synchronicity ratio and analyze the duration of the synchronicity cycle, determine the synchronicity ratio between the number of respiratory cycle fluctuations and the amplitude of heart rate changes, calculate the intensity of physiological signal linkage changes, and obtain the intensity of fluctuation linkage. S403: Based on the intensity of the fluctuation linkage and the intensity of the physiological signal linkage change, identify and classify the user's sleep stage state in real time, and generate sleep stage identification results.

4. The adaptive comfort adjustment method of a sleep apparatus according to claim 3, wherein, The specific formula for determining the synchronous proportional relationship between the number of respiratory cycle fluctuations and the amplitude of heart rate changes is as follows: ； Calculate the synchronization linkage strength value; wherein, is a synchronization linkage intensity value, is a normalized value of the number of respiratory fluctuations of the user in the kth period, is an average value of the normalized values of the number of respiratory fluctuations in m periods, is a normalized value of the amplitude variation of the heart rate of the user in the kth period, is an average value of the normalized values of the amplitude variation of the heart rate in m periods, is a normalized amplitude variation modulation factor extracted based on the physiological linkage sensitivity in the kth period, k is an index number of the period, and m is a number of monitoring periods.

5. The adaptive comfort adjustment method of a sleep apparatus of claim 1, wherein, The method further includes: S5: Using the sleep stage recognition results, analyze the amplitude of continuous heart rate changes and the length of body movement stability cycle in real time, construct a deep sleep stability index, combine the direction and rate trend of real-time ambient temperature and humidity changes, analyze the synchronicity of changes in user status and environmental trends, determine the rhythm of environmental condition adjustment, and generate a set of device control instructions. The device control instruction set includes a deep sleep stability index scalar, temperature and humidity regulation synchronization parameters, and environmental output rhythm control instructions.

6. The method of adaptive comfort adjustment of a sleep instrument of claim 5, wherein, The steps for obtaining the device control instruction set are as follows: S501: Call the sleep stage recognition results, monitor and analyze the continuous heart rate change amplitude and body motion stability cycle length, analyze the correlation between heart rate fluctuation and body motion cycle stability, and construct a deep sleep stability index; S502: Based on the deep sleep stability index, combined with the real-time ambient temperature and humidity change trends, calculate the fluctuation direction and rate of temperature and humidity changes, analyze the synchronization between user status and environmental parameters, and generate environmental trend synchronization information. S503: According to the environmental trend synchronism information, judge the environmental condition adjustment rhythm, combine the user sleep state and the environmental change trend, send the control instruction to the environmental adjustment device, and generate the device control instruction set.

7. A sleep device comprising a memory and a processor, wherein, The memory stores a computer program, and the processor executes the computer program to realize the steps of the adaptive comfort adjustment method of the sleep instrument in any one of claims 1 to 6.

Images