Sleep quality adjusting device and method combined with health analysis

Abstract

The invention discloses a sleep quality adjusting device and method combined with health analysis, and relates to the related field of data processing.The device comprises a sleep monitoring module used for obtaining a heart rate monitoring time sequence signal, a respiration rate monitoring time sequence signal, an electroencephalogram rhythm monitoring time sequence signal and a body movement monitoring time sequence signal through a sleep monitoring assembly when a user falls asleep; the coupling analysis module is used for performing coupling analysis on the monitoring time sequence signal in combination with the sleep recording duration to obtain a user sleep quality score; the alpha wave emission optimization module is used for optimizing alpha wave emission through the sleep adjusting component when the score is smaller than or equal to a score threshold value, and alpha wave emission control parameters are obtained; the sleep quality adjusting module is used for adjusting the sleep quality. The technical problems that existing sleep quality adjustment combined with health analysis is insufficient in evaluation accuracy and poor in sleep quality adjustment effect are solved, and the technical effects of improving the evaluation accuracy and achieving accurate adjustment of the sleep quality are achieved.

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a sleep quality adjustment device and method combined with health analysis. Background Art

[0002] With the acceleration of the pace of modern life, sleep disorders are becoming more and more common, seriously affecting people's physical and mental health. In order to improve sleep quality, various sleep quality adjustment technologies and devices have emerged. In traditional sleep quality adjustment methods, they mainly rely on single-dimensional physiological signals for monitoring and analysis. Although these methods can reflect the user's sleep condition to a certain extent, they only start from a single dimension and lack a comprehensive evaluation system, resulting in insufficient evaluation accuracy.

[0003] In the current related technologies, sleep quality adjustment combined with health analysis has technical problems such as insufficient assessment accuracy and poor sleep quality adjustment effect. Summary of the invention

[0004] The present application provides a sleep quality adjustment device and method combined with health analysis, which simultaneously monitors physiological signals in multiple dimensions such as heart rate, respiratory rate, EEG rhythm and body movement, and performs coupling analysis to obtain a comprehensive user sleep quality score. When the score is lower than a preset threshold, the sleep adjustment component is used to optimize the alpha wave emission and other technical means to achieve the technical effect of improving the accuracy of the assessment and realizing precise adjustment of the sleep quality.

[0005] The present application provides a sleep quality adjustment device combined with health analysis, the device comprising a sleep monitoring component and a sleep adjustment component, including: A sleep monitoring module, which is used to obtain a heart rate monitoring timing signal, a respiratory rate monitoring timing signal, an electroencephalogram rhythm monitoring timing signal and a body movement monitoring timing signal through the sleep monitoring component when the user falls asleep; a coupling analysis module, which is used to perform coupling analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the electroencephalogram rhythm monitoring timing signal and the body movement monitoring timing signal in combination with the sleep record duration to obtain a user sleep quality score; an alpha wave emission optimization module, which is used to optimize the alpha wave emission through the sleep adjustment component to obtain an alpha wave emission control parameter when the user sleep quality score is less than or equal to the user sleep quality score threshold corresponding to the sleep record duration; a sleep quality adjustment module, which is used to adjust the user's sleep quality according to the alpha wave emission control parameter.

[0006] In a possible implementation, when the user falls asleep, the sleep monitoring component obtains a heart rate monitoring timing signal, a respiratory rate monitoring timing signal, an electroencephalogram rhythm monitoring timing signal, and a body movement monitoring timing signal, and the sleep monitoring module performs the following processing: Obtain clock information, push forward a preset duration, and construct a preset monitoring time zone; collect the heart rate monitoring timing signal through the heart rate monitor of the sleep monitoring component; collect the respiratory rate monitoring timing signal through the respiratory rate monitor of the sleep monitoring component; collect the EEG rhythm monitoring timing signal through the EEG rhythm monitor of the sleep monitoring component; collect the body movement monitoring timing signal through the body movement monitor of the sleep monitoring component.

[0007] In a possible implementation, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed in combination with the sleeping record duration to obtain a user sleep quality score. The coupling analysis module performs the following processing: A signal coupling model is obtained, and sleep stage analysis is performed on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal to obtain the coupled sleep stage; a target sleep stage is matched according to the sleeping record duration; and a sleep quality assessment is performed according to the target sleep stage and the coupled sleep stage to obtain the user's sleep quality score.

[0008] In a possible implementation, a signal coupling model is obtained, and sleep stage analysis is performed on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal to obtain a coupled sleep stage. The coupling analysis module performs the following processing: A signal coupling model is obtained, wherein the signal coupling model includes a first signal coupling channel to an Nth signal coupling channel; the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are input into the first signal coupling channel to obtain a first sleep stage; until the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are input into the Nth signal coupling channel to obtain an Nth sleep stage; the majority sleep stage from the first sleep stage to the Nth sleep stage is extracted and set as a coupled sleep stage.

[0009] In a possible implementation, a signal coupling model is obtained, and the coupling analysis module performs the following processing: Collect heart rate recording timing signals, respiratory rate recording timing signals, EEG rhythm recording timing signals, body movement recording timing signals and sleep stage identification data, and set them as a data set for building a signal coupling model; divide the data set for building a signal coupling model into k parts to obtain k groups of signal coupling model building data; perform k times of extraction with replacement on the k groups of signal coupling model building data to construct a first signal coupling model building data set, set the mean square error as the loss function, take the sleep stage identification data as supervision, and take the heart rate recording timing signals, respiratory rate recording timing signals, EEG rhythm recording timing signals, and body movement recording timing signals as input to train a long short-term memory neural network to obtain the first signal coupling channel; until the Nth signal coupling channel is generated; perform mode full connection on the first signal coupling channel to the Nth signal coupling channel to obtain the signal coupling model.

[0010] In a possible implementation, a sleep quality assessment is performed according to the target sleep stage and the coupled sleep stage to obtain the user sleep quality score, and the coupling analysis module performs the following processing: Construct a sleep quality scoring function: ,in, Characterize the sleep quality score, Characterizing coupled sleep stages, Characterizing a target sleep stage; and performing sleep quality assessment on the target sleep stage and the coupled sleep stage according to the sleep quality scoring function to obtain a sleep quality score of the user.

[0011] In a possible implementation, the alpha wave emission is optimized by the sleep adjustment component to obtain the alpha wave emission control parameters, and the alpha wave emission optimization module performs the following processing: The heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are adjusted to obtain the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal; the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal are coupled and analyzed to obtain the user's updated sleep quality score; when the user's updated sleep quality score is greater than the user's sleep quality score threshold, alpha wave emission optimization is performed with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters.

[0012] In a possible implementation, the alpha wave emission optimization is performed with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters, and the alpha wave emission optimization module performs the following processing: Alpha wave emission samples are collected with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain an alpha wave emission sample set; outlier analysis is performed on the alpha wave emission sample set to obtain an outlier factor set; and the alpha wave emission sample with the minimum outlier factor is extracted and set as the alpha wave emission control parameter.

[0013] The present application also provides a sleep quality adjustment method combined with health analysis, including: When the user falls asleep, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component; in combination with the sleep record duration, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed to obtain the user's sleep quality score; when the user's sleep quality score is less than or equal to the user's sleep quality score threshold corresponding to the sleep record duration, the alpha wave emission is optimized through the sleep adjustment component to obtain the alpha wave emission control parameters; the user's sleep quality is adjusted according to the alpha wave emission control parameters.

[0014] It is intended that through the sleep quality adjustment device and method combined with health analysis proposed in the present application, when the user falls asleep, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component of the sleep monitoring module. In combination with the sleep record duration, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed through the coupling analysis module to obtain the user's sleep quality score. When the user's sleep quality score is less than or equal to the user's sleep quality score threshold corresponding to the sleep record duration, the alpha wave emission is optimized through the sleep adjustment component of the alpha wave emission optimization module to obtain the alpha wave emission control parameters. Finally, the user's sleep quality is adjusted through the sleep quality adjustment module according to the alpha wave emission control parameters, thereby achieving the technical effect of improving the evaluation accuracy and realizing precise adjustment of sleep quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic diagram of the structure of a sleep quality adjustment device combined with health analysis provided in an embodiment of the present application.

[0017] Figure 2 A flowchart of a sleep quality adjustment method combined with health analysis provided in an embodiment of the present application.

[0018] Explanation of reference numerals: sleep monitoring module 10 , coupling analysis module 20 , alpha wave emission optimization module 30 , sleep quality adjustment module 40 . DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0022] The present application embodiment provides a sleep quality adjustment device combined with health analysis, the device includes a sleep monitoring component and a sleep adjustment component, such as Figure 1 As shown, the device comprises: The sleep monitoring module 10 is used to obtain the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal through the sleep monitoring component when the user falls asleep. Specifically, when the user falls asleep, the user's heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component. Among them, the heart rate monitoring timing signal is a heart rate data sequence that varies with time; the respiratory rate monitoring timing signal is a respiratory frequency data sequence that varies with time; the EEG rhythm monitoring timing signal is a brain wave data sequence that varies with time recorded by an electroencephalogram (EEG), reflecting the electrical activity of the brain; the body movement monitoring timing signal is a body movement data sequence that varies with time recorded by a sensor.

[0023] In one possible implementation, when the user falls asleep, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component, including: obtaining clock information, pushing forward a preset duration, and constructing a preset monitoring time zone; collecting the heart rate monitoring timing signal through the heart rate monitor of the sleep monitoring component; collecting the respiratory rate monitoring timing signal through the respiratory rate monitor of the sleep monitoring component; collecting the EEG rhythm monitoring timing signal through the EEG rhythm monitor of the sleep monitoring component; collecting the body movement monitoring timing signal through the body movement monitor of the sleep monitoring component.

[0024] Specifically, the current clock information is obtained through the built-in clock module or the synchronous network time protocol (NTP). The clock information is used to determine the specific time when the user falls asleep, and is the basis for the subsequent calculation of the preset monitoring time zone. According to research needs, a preset duration (such as 30 minutes, 1 hour, etc.) is set. This duration is used to determine the preparation time before starting monitoring to ensure that the user is already asleep. This preset duration is pushed forward from the current clock information to construct a time interval, namely the preset monitoring time zone. In this time zone, the device begins to collect various sleep monitoring data.

[0025] Through the heart rate monitor (such as heart rate sensor, heart rate belt, etc.) in the sleep monitoring component, heart rate data is continuously collected while the user is asleep. These data are arranged in time series to form a heart rate monitoring timing signal. Similarly, a respiratory rate monitor (such as a chest strap, respiratory sensor, etc.) is used to collect respiratory rate data while the user is asleep. These data are also arranged in time series to form a respiratory rate monitoring timing signal. Electrodes are placed on the user's head through an electroencephalogram (such as an electroencephalograph EEG) to collect brain wave data. After processing and analysis, the brain wave data identifies different electroencephalogram rhythms (such as alpha waves, beta waves, delta waves, etc.) to form an electroencephalogram rhythm monitoring timing signal. Use a body movement monitor (such as an accelerometer, pressure sensor, etc.) to collect body movement data on parts of the user's body (such as wrists, chest, etc.). These data reflect the user's tiny movements during sleep and form a body movement monitoring timing signal. This implementation method ensures that data collection begins after the user actually falls asleep by building a preset monitoring time zone, avoiding inaccurate data caused by the user not yet falling asleep. By collecting multiple physiological parameters such as heart rate, respiratory rate, EEG rhythm and body movement, the comprehensiveness of data collection is improved, providing comprehensive and accurate data support for user sleep status analysis.

[0026] The coupling analysis module 20 is used to perform coupling analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal in combination with the sleep record duration to obtain the user's sleep quality score. Specifically, in combination with the user's sleep record duration (i.e., the time from the user's attempt to fall asleep to the actual time of falling asleep), the above four monitoring timing signals are coupled and analyzed, that is, a variety of signals are comprehensively analyzed to evaluate the user's sleep quality and give the user's sleep quality score, which is the result of a quantitative evaluation of the user's sleep quality.

[0027] In one possible implementation, in combination with the sleep record duration, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed to obtain a user sleep quality score, including: obtaining a signal coupling model, performing a sleep stage analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain a coupled sleep stage; matching a target sleep stage according to the sleep record duration; performing a sleep quality assessment according to the target sleep stage and the coupled sleep stage to obtain the user sleep quality score.

[0028] Specifically, a signal coupling model is pre-stored inside the device. This model is obtained based on the statistical analysis of a large amount of user sleep data, and can reflect the correlation between different physiological signals (heart rate, respiratory rate, EEG rhythm, body movement) and how they jointly affect the sleep stage. Before performing the coupling analysis, the signal coupling model is loaded, and the loaded signal coupling model is used to synchronously analyze the heart rate monitoring timing signal, respiratory rate monitoring timing signal, EEG rhythm monitoring timing signal, and body movement monitoring timing signal. By analyzing the waveform characteristics, frequency distribution, etc. of these signals, the user's sleep stages in different time periods are identified, such as non-rapid eye movement (NREM, including light sleep and deep sleep) and rapid eye movement (REM). These identified sleep stages are coupled sleep stages.

[0029] According to the user's sleep record duration and general sleep cycle rules (such as adults experience 4-6 sleep cycles per night, each cycle is about 90 minutes), calculate the target sleep stage (ideal sleep stage) that the user should reach under the current sleep duration. For example, if the user has fallen asleep for 3 hours, according to general rules, they should be in or about to enter the deep sleep stage (NREM stage 3 or stage 4). Compare the coupled sleep stage with the target sleep stage to evaluate the user's sleep quality, including: whether the user has reached the expected target sleep stage; whether the user's physiological signals are stable and normal in the target sleep stage; and whether there are abnormal sleep events (such as apnea, abnormal heart rate, etc.). According to these evaluation criteria, a user's sleep quality score is given, which can be a value or a level. This implementation method avoids the possible misleading of a single physiological signal by integrating the coupling relationship of multiple physiological signals, matches the target sleep stage with the duration of falling asleep and the general sleep cycle rules, and accurately evaluates whether the user's sleep quality meets expectations.

[0030] In one possible implementation, a signal coupling model is obtained, and sleep stage analysis is performed on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal to obtain a coupled sleep stage, including: obtaining a signal coupling model, wherein the signal coupling model includes a first signal coupling channel to an Nth signal coupling channel; inputting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal into the first signal coupling channel to obtain a first sleep stage; until the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal are input into the Nth signal coupling channel to obtain an Nth sleep stage; extracting the majority sleep stage from the first sleep stage to the Nth sleep stage, and setting it as a coupled sleep stage.

[0031] Specifically, the signal coupling model includes multiple signal coupling channels (the first signal coupling channel to the Nth signal coupling channel), and the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are simultaneously input into each signal coupling channel in the signal coupling model. Each channel performs a comprehensive analysis of the four physiological signals input simultaneously according to its own algorithm to extract information related to the sleep stage. After processing each signal coupling channel, multiple sleep stage judgment results based on the comprehensive analysis of the four physiological signals are obtained. The sleep stage judgment results output by all signal coupling channels are counted to find the sleep stage with the most occurrences (the majority sleep stage), and this majority sleep stage is used as the coupled sleep stage obtained based on the coupling analysis of multiple physiological signals, which reflects the most likely sleep state of the user under the current sleep duration. This implementation method introduces a signal coupling model, combines the processing results of multiple signal coupling channels, extracts the majority sleep stage as the coupled sleep stage, reduces the misjudgment caused by individual signal abnormalities or errors, and improves the accuracy of sleep stage analysis.

[0032] In one possible implementation, a signal coupling model is obtained, including: collecting heart rate recording timing signals, respiratory rate recording timing signals, electroencephalogram rhythm recording timing signals, body movement recording timing signals and sleep stage identification data, and setting them as a signal coupling model construction data set; dividing the signal coupling model construction data set into k parts, and obtaining k groups of signal coupling model construction data; performing k times of extraction with replacement on the k groups of signal coupling model construction data, and constructing a first signal coupling model construction data set, setting the mean square error as a loss function, taking the sleep stage identification data as supervision, and taking the heart rate recording timing signals, respiratory rate recording timing signals, electroencephalogram rhythm recording timing signals, and body movement recording timing signals as input to train a long short-term memory neural network, and obtaining the first signal coupling channel; until the Nth signal coupling channel is generated; performing mode full connection on the first signal coupling channel to the Nth signal coupling channel, and obtaining the signal coupling model.

[0033] Specifically, a large number of heart rate recording time series signals, respiratory rate recording time series signals, EEG rhythm recording time series signals, body movement recording time series signals, and corresponding sleep stage identification data (such as through manual labeling or automatic identification by professional equipment) are collected during sleep. These data together constitute the signal coupling model construction data set, which provides a basis for model training. The signal coupling model construction data set is divided into k parts to obtain k groups of signal coupling model construction data.

[0034] The following takes the first signal coupling channel as an example to illustrate the model training process: Perform k-times of extraction with replacement on k groups of signal coupling model construction data to construct the first signal coupling model construction data set. Set the mean squared error (MSE) as the loss function to measure the difference between the model prediction results and the actual sleep stage identification data. Take the heart rate recording time series signal, respiratory rate recording time series signal, EEG rhythm recording time series signal, and body movement recording time series signal as input, and the sleep stage identification data as supervision information to train the Long Short-Term Memory (LSTM) neural network. LSTM is a neural network structure suitable for processing time series data and can capture long-term dependencies in signals. After training, the first signal coupling channel is obtained, which can predict the user's sleep stage based on the input physiological signal.

[0035] Repeat the above model training process, and perform k-times of extraction with replacement on k groups of signal coupling model construction data each time to generate the second signal coupling channel, the third signal coupling channel, and the Nth signal coupling channel. The output results of the first signal coupling channel to the Nth signal coupling channel are comprehensively analyzed. Since each channel may give different sleep stage judgment results, the method of extracting the majority sleep stage is adopted, that is, the sleep stage with the most occurrences in the judgment results of each channel is counted and set as the coupling sleep stage. That is, the majority full connection refers to connecting the output results of multiple channels by statistical voting to obtain the final judgment result. In this implementation method, the training data of each signal coupling channel is randomly extracted from the k groups of signal coupling model construction data, and is replaced. Therefore, the training data of each channel may contain different parts from the original data set. This diversity helps the model learn a wider range of data features, thereby improving its generalization ability. Although the training data of each channel comes from the same original data set, due to the randomness of the extraction process, the training data of different channels are independent to some extent. This independence helps to reduce the correlation between models, so that each channel can learn different data features independently. Finally, the output results of multiple signal coupling channels are combined by means of mode full connection, which reduces the overall judgment errors caused by individual channel judgment errors and improves the robustness and accuracy of the model. At the same time, since the changes in physiological signals during sleep are often continuous and periodic, the LSTM neural network can handle the characteristics of this time series data well, thereby further improving the accuracy of sleep stage judgment.

[0036] In a possible implementation, performing a sleep quality assessment according to the target sleep stage and the coupled sleep stage to obtain the user sleep quality score includes: constructing a sleep quality score function: ,in, Characterize the sleep quality score, Characterizing coupled sleep stages, Characterizing a target sleep stage; and performing sleep quality assessment on the target sleep stage and the coupled sleep stage according to the sleep quality scoring function to obtain a sleep quality score of the user.

[0037] Specifically, the sleep quality scoring function is used to quantify the difference or degree of match between the coupled sleep stage and the target sleep stage, wherein the coupled sleep stage is a representation of the user's actual sleep stage obtained through signal coupling model analysis, which can be a vector, matrix or other mathematical form, and the target sleep stage is a representation of the expected sleep stage determined based on the length of sleep record and knowledge of sleep cycles. The representations of the coupled sleep stage and the target sleep stage are input into the sleep quality scoring function for calculation, and the output of the function is the user's sleep quality score. This implementation method quantifies the user's sleep quality into a specific value by constructing a sleep quality scoring function, which is convenient for comparison and analysis, and helps to intuitively understand the user's sleep condition, providing a basis for subsequent sleep quality adjustments.

[0038] The alpha wave emission optimization module 30 is used to optimize the alpha wave emission through the sleep adjustment component to obtain the alpha wave emission control parameters when the user's sleep quality score is less than or equal to the user's sleep quality score threshold corresponding to the sleeping record duration. Specifically, when the user's sleep quality score is lower than or equal to the preset sleep quality score threshold, the alpha wave (a brain wave with a frequency between 8 and 12 Hz associated with relaxation and wakefulness) emission is optimized through the sleep adjustment component (such as a sound device, a light device, a vibration device, etc.) to obtain the best alpha wave emission control parameters (including sound frequency, light intensity, etc.).

[0039] In a possible implementation, the alpha wave emission is optimized by a sleep adjustment component to obtain the alpha wave emission control parameters, including: adjusting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the electroencephalogram rhythm monitoring timing signal and the body movement monitoring timing signal to obtain the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal; coupling analysis is performed on the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal to obtain the user's updated sleep quality score; when the user's updated sleep quality score is greater than the user's sleep quality score threshold, optimizing the alpha wave emission with the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters.

[0040] Specifically, based on historical data or a machine learning model, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal are adjusted to obtain a heart rate update timing signal, a respiratory rate update timing signal, an EEG rhythm update timing signal, and a body movement update timing signal, which represent the desired physiological state associated with higher sleep quality. The adjusted heart rate update timing signal, respiratory rate update timing signal, EEG rhythm update timing signal, and body movement update timing signal are input into the coupling analysis module 20 for a new coupling analysis. Combined with the duration of falling asleep, the adjusted physiological signal is evaluated to see whether it helps to improve sleep quality, and the user's updated sleep quality score is obtained. If the user's updated sleep quality score is greater than the user's sleep quality score threshold, it means that the adjustment measures are effective and alpha wave emission optimization can be performed. Taking the heart rate update timing signal, respiratory rate update timing signal, EEG rhythm update timing signal and body movement update timing signal as the update target, by adjusting the parameters of the sleep adjustment component (such as sound frequency, light intensity, etc.), the user's sleeping environment is actually adjusted or the user's senses are stimulated to guide the user's heart rate, respiratory rate, EEG rhythm and body movement to the state represented by the update timing signal, and finally obtain the alpha wave emission control parameters to guide the subsequent sleep quality adjustment process. This implementation method obtains the update timing signal in advance and performs simulation analysis to evaluate the potential impact of these signals on sleep quality without actually disturbing the user's sleep, avoiding unnecessary adjustment attempts and improving the efficiency and accuracy of the adjustment.

[0041] In a possible implementation, alpha wave emission optimization is performed with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters, including: collecting alpha wave emission samples with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain an alpha wave emission sample set; performing outlier analysis on the alpha wave emission sample set to obtain an outlier factor set; extracting the alpha wave emission sample with the minimum outlier factor and setting it as the alpha wave emission control parameter.

[0042] Specifically, after the user's heart rate, breathing rate, EEG rhythm, body movement and other physiological signals are adjusted and updated, these updated timing signals are used as a reference to collect alpha wave emission samples through relevant equipment in the sleep monitoring component (such as an electroencephalogram, a heart rate monitor, etc.). The collected alpha wave emission samples are sorted to form a set containing multiple samples, each of which contains alpha wave activity data in a specific time period and physiological signal data related thereto. Statistical methods or machine learning algorithms are used to perform outlier analysis on the alpha wave emission sample set to identify abnormal samples that are significantly different from most samples. These abnormal samples reflect abnormal fluctuations or instability in the user's physiological state. In the outlier analysis results, the outlier factor of each sample is calculated, that is, the degree of difference between the sample and other samples in the set. The sample with the smallest outlier factor is extracted, that is, the sample is closest to most samples in the set, reflecting the most stable and typical alpha wave activity state of the user. The extracted alpha wave emission samples with the minimum outlier factor are used as alpha wave emission control parameters. These parameters include the frequency, intensity, and emission duration of alpha waves, which are used to adjust the user's sleep quality through the sleep adjustment component. This implementation method uses outlier analysis to identify and exclude abnormal samples, ensuring that the final extracted control parameters can reflect the user's most stable and typical alpha wave activity state, and act on the user through the sleep adjustment component to guide the user's brain electrical activity to a more stable and relaxed state, thereby achieving the technical effect of effectively adjusting the user's sleep quality and promoting the user's deep sleep and relaxation state.

[0043] The sleep quality adjustment module 40 is used to adjust the sleep quality of the user according to the alpha wave emission control parameters. Specifically, according to the alpha wave emission control parameters, the sleep quality of the user is adjusted through the sleep adjustment component, such as adjusting the environmental sound, light, etc., to improve the sleep quality of the user. The embodiment of the present application adopts simultaneous monitoring of physiological signals of multiple dimensions such as heart rate, respiratory rate, EEG rhythm and body movement, and performs coupling analysis to obtain a comprehensive user sleep quality score. When the score is lower than the preset threshold, the sleep adjustment component is used to optimize the alpha wave emission and other technical means, thereby achieving the technical effect of improving the evaluation accuracy and realizing precise adjustment of sleep quality.

[0044] In the above, refer to Figure 1 The sleep quality adjustment device combined with health analysis according to an embodiment of the present invention is described in detail. Figure 2 A sleep quality adjustment method combined with health analysis according to an embodiment of the present invention is described.

[0045] The sleep quality adjustment method combined with health analysis according to an embodiment of the present invention is used to solve the technical problems of insufficient evaluation accuracy and poor sleep quality adjustment effect in the existing sleep quality adjustment combined with health analysis, so as to achieve the technical effect of improving evaluation accuracy and realizing precise adjustment of sleep quality.

[0046] The sleep quality adjustment method combined with health analysis includes: when the user falls asleep, obtaining the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal through the sleep monitoring component; in combination with the sleep record duration, coupling analysis is performed on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain the user's sleep quality score; when the user's sleep quality score is less than or equal to the user's sleep quality score threshold corresponding to the sleep record duration, optimizing the alpha wave emission through the sleep adjustment component to obtain the alpha wave emission control parameters; and adjusting the user's sleep quality according to the alpha wave emission control parameters.

[0047] Among them, when the user falls asleep, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component, which can further include: obtaining clock information, pushing forward a preset duration, and constructing a preset monitoring time zone; collecting the heart rate monitoring timing signal through the heart rate monitor of the sleep monitoring component; collecting the respiratory rate monitoring timing signal through the respiratory rate monitor of the sleep monitoring component; collecting the EEG rhythm monitoring timing signal through the EEG rhythm monitor of the sleep monitoring component; collecting the body movement monitoring timing signal through the body movement monitor of the sleep monitoring component.

[0048] Among them, in combination with the sleep record duration, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed to obtain the user's sleep quality score, which can further include: obtaining a signal coupling model, performing sleep stage analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain the coupled sleep stage; matching the target sleep stage according to the sleep record duration; performing sleep quality assessment according to the target sleep stage and the coupled sleep stage to obtain the user's sleep quality score.

[0049] Among them, obtaining a signal coupling model, performing sleep stage analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain a coupled sleep stage can further include: obtaining a signal coupling model, wherein the signal coupling model includes a first signal coupling channel to an Nth signal coupling channel; inputting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal into the first signal coupling channel to obtain a first sleep stage; until the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are input into the Nth signal coupling channel to obtain an Nth sleep stage; extracting the majority sleep stage from the first sleep stage to the Nth sleep stage, and setting it as a coupled sleep stage.

[0050] Among them, obtaining the signal coupling model can further include: collecting heart rate recording timing signals, respiratory rate recording timing signals, EEG rhythm recording timing signals, body movement recording timing signals and sleep stage identification data, and setting them as a signal coupling model construction data set; dividing the signal coupling model construction data set into k parts to obtain k groups of signal coupling model construction data; performing k times of extraction with replacement on the k groups of signal coupling model construction data to construct a first signal coupling model construction data set, setting the mean square error as the loss function, taking the sleep stage identification data as supervision, and taking the heart rate recording timing signals, respiratory rate recording timing signals, EEG rhythm recording timing signals, and body movement recording timing signals as input to train a long short-term memory neural network to obtain the first signal coupling channel; until the Nth signal coupling channel is generated; performing mode full connection on the first signal coupling channel to the Nth signal coupling channel to obtain the signal coupling model.

[0051] Among them, performing sleep quality assessment according to the target sleep stage and the coupled sleep stage to obtain the user sleep quality score may further include: constructing a sleep quality score function: ,in, Characterize the sleep quality score, Characterizing coupled sleep stages, Characterizing a target sleep stage; and performing sleep quality assessment on the target sleep stage and the coupled sleep stage according to the sleep quality scoring function to obtain a sleep quality score of the user.

[0052] Among them, optimizing the alpha wave emission through the sleep adjustment component to obtain the alpha wave emission control parameters can further include: adjusting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the electroencephalogram rhythm monitoring timing signal and the body movement monitoring timing signal to obtain the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal; coupling analysis of the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal to obtain the user's updated sleep quality score; when the user's updated sleep quality score is greater than the user's sleep quality score threshold, optimizing the alpha wave emission with the heart rate update timing signal, the respiratory rate update timing signal, the electroencephalogram rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters.

[0053] Among them, taking the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to optimize alpha wave emission and obtain the alpha wave emission control parameters can further include: collecting alpha wave emission samples with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain an alpha wave emission sample set; performing outlier analysis on the alpha wave emission sample set to obtain an outlier factor set; extracting the alpha wave emission sample with the minimum outlier factor and setting it as the alpha wave emission control parameter.

[0054] The sleep quality adjustment device combined with health analysis provided in the embodiment of the present invention can execute the sleep quality adjustment method combined with health analysis provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0055] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0056] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A sleep quality adjustment device combined with health analysis, characterized in that: The device comprises a sleep monitoring component and a sleep regulation component, including: A sleep monitoring module, wherein the sleep monitoring module is used to obtain a heart rate monitoring timing signal, a respiratory rate monitoring timing signal, an electroencephalogram rhythm monitoring timing signal, and a body movement monitoring timing signal through the sleep monitoring component when the user falls asleep; A coupling analysis module, wherein the coupling analysis module is used to perform coupling analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal in combination with the sleeping record duration, so as to obtain a user sleep quality score; An alpha wave emission optimization module, wherein when the user's sleep quality score is less than or equal to the user's sleep quality score threshold corresponding to the sleeping record duration, the alpha wave emission is optimized through a sleep adjustment component to obtain an alpha wave emission control parameter; A sleep quality adjustment module is used to adjust the sleep quality of the user according to the alpha wave emission control parameter.

2. The sleep quality adjustment device combined with health analysis as claimed in claim 1, characterized in that: When the user falls asleep, the sleep monitoring component obtains a heart rate monitoring timing signal, a respiratory rate monitoring timing signal, an EEG rhythm monitoring timing signal, and a body movement monitoring timing signal, including: Obtain clock information, push forward the preset duration, and build a preset monitoring time zone; Collecting the heart rate monitoring timing signal through the heart rate monitor of the sleep monitoring component; Collecting the respiratory rate monitoring timing signal through the respiratory rate monitor of the sleep monitoring component; Collecting the EEG rhythm monitoring timing signal through the EEG rhythm monitor of the sleep monitoring component; The body movement monitoring timing signal is collected by the body movement monitor of the sleep monitoring component.

3. The sleep quality adjustment device combined with health analysis as claimed in claim 1, characterized in that: Combined with the sleeping record duration, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are coupled and analyzed to obtain a user sleep quality score, including: Obtain a signal coupling model, perform sleep stage analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal to obtain a coupled sleep stage; Matching the target sleep stage according to the recorded duration of falling asleep; A sleep quality assessment is performed according to the target sleep stage and the coupled sleep stage to obtain a sleep quality score of the user.

4. The sleep quality adjustment device combined with health analysis as claimed in claim 3, characterized in that: Obtaining a signal coupling model, performing sleep stage analysis on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal, and the body movement monitoring timing signal to obtain a coupled sleep stage, including: Obtaining a signal coupling model, wherein the signal coupling model includes a first signal coupling channel to an Nth signal coupling channel; Inputting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal into the first signal coupling channel to obtain a first sleep stage; Until the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are input into the Nth signal coupling channel to obtain the Nth sleep stage; The majority sleep stage from the first sleep stage to the Nth sleep stage is extracted and set as a coupled sleep stage.

5. The sleep quality adjustment device combined with health analysis as claimed in claim 4, characterized in that: Obtain signal coupling models, including: Collect heart rate recording timing signals, respiratory rate recording timing signals, EEG rhythm recording timing signals, body movement recording timing signals and sleep stage identification data, and set them as the data set for signal coupling model construction; Dividing the signal coupling model construction data set into k equal parts to obtain k groups of signal coupling model construction data; Perform k extractions with replacement on the k groups of signal coupling model construction data to construct a first signal coupling model construction data set, set the mean square error as a loss function, use the sleep stage identification data as supervision, and use the heart rate recording time series signal, the respiratory rate recording time series signal, the EEG rhythm recording time series signal, and the body movement recording time series signal as input to train a long short-term memory neural network to obtain the first signal coupling channel; Until the Nth signal coupling channel is generated; Performing mode full connection on the first signal coupling channel to the Nth signal coupling channel to obtain the signal coupling model.

6. The sleep quality adjustment device combined with health analysis as claimed in claim 3, characterized in that: Performing a sleep quality assessment according to the target sleep stage and the coupled sleep stage to obtain the user's sleep quality score includes: Construct a sleep quality scoring function: ， in, Characterize the sleep quality score, Characterizing coupled sleep stages, Characterizing target sleep stages; The target sleep stage and the coupled sleep stage are evaluated for sleep quality according to the sleep quality scoring function to obtain the user sleep quality score.

7. The sleep quality adjustment device combined with health analysis as claimed in claim 1, characterized in that: The alpha wave emission is optimized by the sleep regulation component to obtain the alpha wave emission control parameters, including: Adjusting the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain a heart rate update timing signal, a respiratory rate update timing signal, an EEG rhythm update timing signal and a body movement update timing signal; Performing coupling analysis on the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal to obtain a user updated sleep quality score; When the user updated sleep quality score is greater than the user sleep quality score threshold, alpha wave emission optimization is performed with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters.

8. The sleep quality adjustment device combined with health analysis according to claim 7, characterized in that: The alpha wave emission optimization is performed with the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets to obtain the alpha wave emission control parameters, including: Acquiring alpha wave emission samples by taking the heart rate update timing signal, the respiratory rate update timing signal, the EEG rhythm update timing signal and the body movement update timing signal as update targets, and obtaining an alpha wave emission sample set; performing outlier analysis on the alpha wave emission sample set to obtain an outlier factor set; The alpha wave emission sample with the minimum outlier factor is extracted and set as the alpha wave emission control parameter.

9. A sleep quality adjustment method combined with health analysis, characterized in that: The method is applied to the sleep quality adjustment device combined with health analysis according to any one of claims 1 to 8, comprising: When the user falls asleep, the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal are obtained through the sleep monitoring component; Combined with the sleeping record duration, coupling analysis is performed on the heart rate monitoring timing signal, the respiratory rate monitoring timing signal, the EEG rhythm monitoring timing signal and the body movement monitoring timing signal to obtain a user sleep quality score; When the user sleep quality score is less than or equal to the user sleep quality score threshold corresponding to the sleeping record duration, optimizing the alpha wave emission through the sleep adjustment component to obtain the alpha wave emission control parameter; The sleep quality of the user is adjusted according to the alpha wave emission control parameters.

Images