Sleep-aiding music playing method and system based on multi-sensor fusion
By using multi-sensor fusion technology to collect users' sleep sounds, acceleration, and eye movement data, and using machine learning models to accurately extract sleep features, this technology solves the problem of time-consuming, labor-intensive, and untargeted sleep music recommendations in existing technologies. It enables accurate recommendations of personalized sleep music and improves users' sleep quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING GUANGJI XIANGDA MEDIA GROUP CO LTD
- Filing Date
- 2026-03-04
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies rely on manual analysis of polysomnography (PSG) to identify sleep characteristics, which is time-consuming, labor-intensive, and highly subjective. The recommendations for sleep-aid music lack specificity and are difficult to adapt to users' personalized sleep needs.
By using multi-sensor fusion technology, the system collects users' sleep sound signals, acceleration signals, and eye movement data. Using machine learning models and feature extraction algorithms, it accurately extracts users' sleep characteristics and recommends sleep-aiding music based on sleep quality parameters.
It improves the accuracy of sleep feature extraction, enables personalized recommendations of sleep-aid music, and enhances users' sleep quality.
Smart Images
Figure CN122006060A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of sleep management technology, and in particular to a method and system for playing sleep-aiding music based on multi-sensor fusion. Background Technology
[0002] Sleep, an indispensable physiological process for the human body, is directly related to physical and mental health, cognitive function, and daytime behavior. Accurate extraction of sleep characteristics through sleep signals is a core prerequisite for assessing sleep quality parameters and recommending sleep-aiding music to users.
[0003] Existing technologies mainly rely on manual analysis of polysomnography (PSG) to identify sleep signals and extract features. This is time-consuming, labor-intensive, highly subjective, and has low accuracy in feature extraction. Furthermore, the recommendations for sleep-aid music lack specificity and are difficult to meet users' sleep needs. Summary of the Invention
[0004] This invention provides a method and system for playing sleep-aid music based on multi-sensor fusion, which improves the accuracy of user sleep feature extraction.
[0005] On one hand, the present invention provides a method for playing sleep-aid music based on multi-sensor fusion, which includes: The system collects the user's sleep sound signals and determines sound characteristic coefficients based on these signals; it also collects the user's sleep acceleration signals and determines acceleration characteristic coefficients based on these signals; it collects the user's sleep eye movement data and determines the user's sleep characteristics based on this data, along with the sound and acceleration characteristic coefficients; finally, it determines sleep quality parameters based on these sleep characteristics and plays sleep-aid music for the user according to these parameters.
[0006] Further, determining sound characteristic coefficients based on sleep sound signals includes: preprocessing the sleep sound signals; performing spectral analysis on the preprocessed sleep sound signals to obtain a sleep sound signal spectrum; determining the respiratory cycle based on the sleep sound signal spectrum; establishing a preset time window; calculating the standard deviation and average value of the respiratory cycles within the preset time window; calculating the coefficient of variation of the time window based on the standard deviation and average value of the respiratory cycles within the preset time window; establishing a coefficient of variation sequence based on the coefficient of variation of each time window in chronological order; calculating the degree of sleep sound disorder based on the coefficient of variation sequence; and determining sound characteristic coefficients based on the degree of sleep sound disorder and the coefficient of variation.
[0007] Further, the degree of sleep noise disturbance is calculated based on the coefficient of variation sequence, including: obtaining a preset neighborhood, calculating the difference between any coefficient of variation in the coefficient of variation sequence and the average value of the remaining coefficients of variation in the preset neighborhood; and calculating the average value of the differences between all coefficients of variation in the coefficient of variation sequence and the average value of the remaining coefficients of variation in the preset neighborhood to obtain the degree of sleep noise disturbance.
[0008] Furthermore, the sound characteristic coefficients are determined based on the degree of sleep sound disturbance and the coefficient of variation, including: calculating the average coefficient of variation for all time windows, setting correction weights based on the degree of sleep sound disturbance, and correcting the average coefficient of variation based on the correction weights to obtain the sound characteristic coefficients.
[0009] Furthermore, the acceleration feature coefficients are determined based on the sleep acceleration signal, including: extracting time-domain and frequency-domain features from the sleep acceleration signal to obtain a sleep acceleration feature set; determining body movement events based on the trained machine learning model and the sleep acceleration feature set; statistically analyzing the body movement types of each body movement event; extracting key body movement events based on the body movement types; and determining the acceleration feature coefficients based on the frequency of occurrence of the key body movement events.
[0010] Furthermore, based on sleep eye movement data, sound feature coefficients, and acceleration feature coefficients, the user's sleep characteristics are determined, including: determining sleep characteristic parameters based on sound feature coefficients and acceleration feature coefficients; determining sleep stages based on sleep eye movement data; statistically analyzing the changing trends of sleep characteristic parameters for each sleep stage; setting feature tolerance thresholds based on sleep stages; and determining sleep characteristics based on the changing trends of sleep characteristic parameters for all sleep stages and the corresponding feature tolerance thresholds.
[0011] Furthermore, sleep characteristics are determined based on the changing trends of sleep characteristic parameters across all sleep stages and the corresponding characteristic tolerance thresholds. This includes: plotting sleep characteristic parameter change curves based on the changing trends of sleep characteristic parameters; performing curve fitting on the sleep characteristic parameter change curves to obtain sleep characteristic parameter prediction curves; predicting the time required for sleep characteristic parameters to reach the corresponding characteristic tolerance thresholds based on the sleep characteristic parameter prediction curves; and determining sleep characteristics based on the time required for sleep characteristic parameters to reach the corresponding characteristic tolerance thresholds from the prediction curves of all sleep characteristic parameters.
[0012] Furthermore, based on sleep quality parameters, the system plays sleep-aid music for the user, including: obtaining the user's current sleep stage and determining the basic music category based on the current sleep stage; determining the specific music list within the basic music category based on the sleep quality parameters; and determining the user's sleep-aid music based on the specific music list.
[0013] Furthermore, the specific music list in the basic music category is determined based on sleep quality parameters, including: obtaining the trend of changes in the user's sleep quality parameters when playing sleep-aid music, determining the music suitability based on the trend of changes in the user's sleep quality parameters when playing sleep-aid music; collecting the user's suitability for all sleep-aid music, sorting the sleep-aid music in descending order of suitability; filtering out suitable sleep-aid music with a ranking lower than a preset ranking threshold based on the ranking results, and updating the user's sleep-aid music based on the suitable sleep-aid music.
[0014] On the other hand, the present invention also provides a sleep-aid music playback system based on multi-sensor fusion, comprising: The system includes a sound module for collecting the user's sleep sound signals and determining sound characteristic coefficients based on these signals; an acceleration module for collecting the user's sleep acceleration signals and determining acceleration characteristic coefficients based on these signals; a fusion module for collecting the user's sleep eye movement data and determining the user's sleep characteristics based on the sleep eye movement data, sound characteristic coefficients, and acceleration characteristic coefficients; and a playback module for determining sleep quality parameters based on the user's sleep characteristics and playing sleep-aid music based on these parameters.
[0015] This invention provides a method and system for playing sleep-aid music based on multi-sensor fusion. It collects the user's sleep sound signals and determines sound feature coefficients based on these signals; it also collects the user's sleep acceleration signals and determines acceleration feature coefficients based on these signals; and it collects the user's sleep eye movement data and determines the user's sleep characteristics based on the sleep eye movement data, sound feature coefficients, and acceleration feature coefficients. By extracting multi-dimensional features from the user's sleep signals, more accurate user sleep characteristics can be extracted to achieve precise recommendations of sleep-aid music. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating a sleep-aid music playback method based on multi-sensor fusion provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a sleep-aid music playback system based on multi-sensor fusion provided in an embodiment of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0019] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0020] Figure 1 This is a flowchart illustrating a sleep-aid music playback method based on multi-sensor fusion provided in an embodiment of the present invention.
[0021] like Figure 1 As shown in the figure, the execution subject of the sleep-aid music playback method based on multi-sensor fusion provided by the embodiment of the present invention can be an electronic device, and the method mainly includes the following steps: S101, Collect the user's sleep sound signal and determine the sound feature coefficient based on the sleep sound signal; In some embodiments of this application, determining sound characteristic coefficients based on sleep sound signals includes: preprocessing the sleep sound signal; performing spectral analysis on the preprocessed sleep sound signal to obtain a sleep sound signal spectrum; determining the respiratory cycle based on the sleep sound signal spectrum; establishing a preset time window; calculating the standard deviation and average value of the respiratory cycles within the preset time window; calculating the coefficient of variation of the time window based on the standard deviation and average value of the respiratory cycles within the preset time window; establishing a coefficient of variation sequence based on the coefficient of variation of each time window in chronological order; calculating the degree of sleep sound disorder based on the coefficient of variation sequence; and determining sound characteristic coefficients based on the degree of sleep sound disorder and the coefficient of variation.
[0022] In this embodiment, the preprocessing of the sleep sound signal includes filtering, standardization, and noise reduction. Filtering preserves the respiratory frequency band and slightly higher frequency bands that may contain snoring. Standardization eliminates differences in absolute volume values. Noise reduction suppresses steady-state environmental noise. A short-time Fourier transform is performed on the preprocessed sleep sound signal to obtain a sleep sound signal spectrum. The respiratory cycle is extracted by tracking the energy-dominant frequency in the spectrum. The coefficient of variation is calculated by the ratio of the standard deviation to the average value of the respiratory cycle duration within a preset time window. The coefficient of variation sequence is established by the time order of the coefficient of variation, and the degree of sleep sound disorder is calculated to obtain the sound feature coefficients.
[0023] In some embodiments of this application, calculating the degree of sleep noise disorder based on the coefficient of variation sequence includes: obtaining a preset neighborhood; calculating the difference between any coefficient of variation in the coefficient of variation sequence and the average value of the remaining coefficients of variation in the preset neighborhood; and calculating the average value of the differences between all coefficients of variation in the coefficient of variation sequence and the average value of the remaining coefficients of variation in the preset neighborhood to obtain the degree of sleep noise disorder.
[0024] In this embodiment, the degree of disorder of the coefficient of variation sequence is calculated. The higher the degree of disorder, the more inconsistent the respiratory rhythm is within adjacent time periods, which may indicate the presence of irregular breathing.
[0025] In some embodiments of this application, the sound feature coefficient is determined based on the degree of sleep sound disturbance and the coefficient of variation, including: calculating the average coefficient of variation for all time windows, setting a correction weight based on the degree of sleep sound disturbance, and correcting the average coefficient of variation based on the correction weight to obtain the sound feature coefficient.
[0026] In this embodiment, the correction weight is set according to the degree of disorder of sleep sounds. The greater the disorder, the higher the corresponding correction weight. The range of the correction weight is [0, 2]. The average coefficient of variation is corrected by the correction weight to obtain the sound feature coefficient.
[0027] S102, Collect the user's sleep acceleration signal and determine the acceleration characteristic coefficient based on the sleep acceleration signal; In some embodiments of this application, determining acceleration feature coefficients based on sleep acceleration signals includes: extracting time-domain and frequency-domain features from the sleep acceleration signals to obtain a sleep acceleration feature set; determining body movement events based on a trained machine learning model and the sleep acceleration feature set; statistically analyzing the body movement types of each body movement event; extracting key body movement events based on the body movement types; and determining acceleration feature coefficients based on the frequency of occurrence of the key body movement events.
[0028] In this embodiment, a user's sleep acceleration signal is collected using a triaxial accelerometer. The sleep acceleration signal's time-domain and frequency-domain features are extracted. The time-domain features include signal amplitude area, root mean square, zero-crossing rate, and interquartile range. The frequency-domain features include dominant frequencies of each axis, band power ratio, and spectral entropy. This establishes a sleep acceleration feature set. A training sample set is built using labeled body movement event data. The trained machine learning model is a random forest algorithm model. The random forest algorithm model is trained using the training sample set. The current sleep acceleration feature set is input into the trained machine learning model to obtain body movement events. The body movement types of all body movement events within a monitoring period are statistically analyzed. Specific body movement types include: turning over, limb tremors, and no significant body movement. Body movement events of the turning over and limb tremors types are identified as key body movement events. The frequency of occurrence of these key body movement events is then determined as the acceleration feature coefficient.
[0029] S103, Collect the user's sleep eye movement data, and determine the user's sleep characteristics based on the sleep eye movement data, sound feature coefficients, and acceleration feature coefficients; In some embodiments of this application, the sleep characteristics of a user are determined based on sleep eye movement data, sound feature coefficients, and acceleration feature coefficients, including: determining sleep characteristic parameters based on sound feature coefficients and acceleration feature coefficients; determining sleep stages based on sleep eye movement data; statistically analyzing the changing trends of sleep characteristic parameters for each sleep stage; setting feature tolerance thresholds based on sleep stages; and determining sleep characteristics based on the changing trends of sleep characteristic parameters for all sleep stages and the corresponding feature tolerance thresholds.
[0030] In this embodiment, sleep characteristic parameters are obtained by weighted summation of sound characteristic coefficients and acceleration characteristic coefficients. Sleep stages are divided into wakefulness, REM sleep, and non-REM sleep stages using the user's eye movement data. The characteristic tolerance threshold gradually decreases as the sleep stage progresses. Sleep characteristics are obtained by the degree of convergence between the trend of sleep characteristic parameters and the characteristic tolerance threshold.
[0031] In some embodiments of this application, sleep characteristics are determined based on the changing trends of sleep characteristic parameters across all sleep stages and the corresponding feature tolerance thresholds. This includes: plotting a sleep characteristic parameter change curve based on the changing trends of the sleep characteristic parameters; performing curve fitting on the sleep characteristic parameter change curve to obtain a sleep characteristic parameter prediction curve; predicting the time required for the sleep characteristic parameter to reach the corresponding feature tolerance threshold based on the sleep characteristic parameter prediction curve; and determining the sleep characteristics based on the time required for the sleep characteristic parameter to reach the corresponding feature tolerance threshold from the prediction curves of all sleep characteristic parameters.
[0032] In this embodiment, the change curve of sleep characteristic parameters is fitted by polynomial fitting, and the time required for the sleep characteristic parameters to reach the corresponding characteristic tolerance threshold is standardized to obtain the sleep characteristics of the corresponding sleep stage. The average value of the sleep characteristics of all sleep stages is determined as the sleep characteristic.
[0033] S104 determines sleep quality parameters based on the user's sleep characteristics and plays sleep-aid music based on the sleep quality parameters.
[0034] In this embodiment, standard sleep characteristics are set, and the difference between the user's sleep characteristics and the permissible sleep characteristics is determined as a sleep quality parameter. The higher the difference, the better the user's sleep quality.
[0035] In some embodiments of this application, playing sleep-aid music for the user based on sleep quality parameters includes: obtaining the user's current sleep stage, determining a basic music category based on the current sleep stage; determining a specific music list within the basic music category based on the sleep quality parameters, and determining the user's sleep-aid music based on the specific music list.
[0036] In this embodiment, each sleep stage corresponds to a different basic music category. The basic music category for the waking stage is slow-paced instrumental music, the basic music category for non-REM sleep is minimalist melody music, and the basic music category for REM sleep is ambient music. The volume of the sleep-aid music gradually decreases in each sleep stage until it reaches zero at a preset time. Specific music is selected from the basic music categories based on sleep quality parameters to form a specific music list, which is then used as the user's sleep-aid music.
[0037] In some embodiments of this application, determining a specific music list in a basic music category based on sleep quality parameters includes: acquiring the trend of changes in the user's sleep quality parameters while the sleep-aid music is playing; determining the music suitability based on the trend of changes in the user's sleep quality parameters while the sleep-aid music is playing; collecting the user's suitability for all sleep-aid music; sorting the sleep-aid music in descending order of suitability; filtering out suitable sleep-aid music with a ranking lower than a preset ranking threshold based on the sorting results; and determining the suitable sleep-aid music as a specific music list.
[0038] In this embodiment, the trend of change is determined by calculating the slope of the sleep quality parameters. The larger the slope, the higher the music suitability. Thus, suitable sleep-aid music with a suitability ranking lower than a preset ranking threshold is selected as a specific music list.
[0039] Based on the same general inventive concept, this invention also protects a sleep-aid music playback system based on multi-sensor fusion. The sleep-aid music playback system based on multi-sensor fusion provided by this invention will be described below. The sleep-aid music playback system based on multi-sensor fusion described below and the sleep-aid music playback method based on multi-sensor fusion described above can be referred to in correspondence.
[0040] Figure 2 This is a schematic diagram of a sleep-aid music playback system based on multi-sensor fusion provided in an embodiment of the present invention, as shown below. Figure 2 As shown, it includes: The sound module is used to collect the user's sleep sound signals and determine the sound feature coefficients based on the sleep sound signals; The acceleration module is used to collect the user's sleep acceleration signal and determine the acceleration characteristic coefficient based on the sleep acceleration signal; The fusion module is used to collect the user's sleep eye movement data and determine the user's sleep characteristics based on the sleep eye movement data, sound feature coefficients, and acceleration feature coefficients. The playback module is used to determine sleep quality parameters based on the user's sleep characteristics and then play sleep-aid music based on those parameters.
[0041] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for playing sleep-aid music based on multi-sensor fusion, characterized in that, include: Collect users' sleep sound signals and determine sound characteristic coefficients based on the sleep sound signals; Collect the user's sleep acceleration signal and determine the acceleration characteristic coefficient based on the sleep acceleration signal; Collect users' sleep eye movement data, and determine users' sleep characteristics based on sleep eye movement data, sound feature coefficients, and acceleration feature coefficients; Sleep quality parameters are determined based on the user's sleep characteristics, and sleep-aid music is played based on these parameters.
2. The sleep-aid music playback method based on multi-sensor fusion according to claim 1, characterized in that, Determining sound characteristic coefficients based on sleep sound signals includes: The sleep sound signal is preprocessed, and the preprocessed sleep sound signal is subjected to spectrum analysis to obtain the sleep sound signal spectrum. The respiratory cycle is determined based on the spectrogram of sleep sound signals. A preset time window is established, and the standard deviation and mean of the respiratory cycles within the preset time window are calculated. The coefficient of variation of the time window is calculated based on the standard deviation and mean of the respiratory cycles within the preset time window. A coefficient of variation sequence is established based on the coefficient of variation of each time window in chronological order, and the degree of sleep sound disturbance is calculated based on the coefficient of variation sequence. The sound characteristic coefficient is determined based on the degree of disturbance of sleep sounds and the coefficient of variation.
3. The sleep-aid music playback method based on multi-sensor fusion according to claim 2, characterized in that, The degree of sleep sound disturbance is calculated based on the coefficient of variation sequence, including: Obtain a preset neighborhood and calculate the difference between any coefficient of variation in the coefficient of variation sequence and the average value of the remaining coefficients of variation in the preset neighborhood. The level of sleep sound disturbance is obtained by averaging the differences between all coefficients of variation in the statistical coefficient of variation sequence and the average of the remaining coefficients of variation in the preset neighborhood.
4. The sleep-aid music playback method based on multi-sensor fusion according to claim 2, characterized in that, Sound characteristic coefficients are determined based on the degree of disturbance of sleep sounds and the coefficient of variation, including: The average coefficient of variation for all time windows is calculated. A correction weight is set according to the degree of disturbance of sleep sounds. The average coefficient of variation is then corrected according to the correction weight to obtain the sound feature coefficient.
5. The sleep-aid music playback method based on multi-sensor fusion according to claim 1, characterized in that, Acceleration characteristic coefficients are determined based on sleep acceleration signals, including: Time-domain and frequency-domain features of sleep acceleration signals are extracted to obtain a sleep acceleration feature set; Based on a trained machine learning model and a sleep acceleration feature set, body movement events are determined. The types of body movements in each physical event are statistically analyzed. Key physical events are extracted based on the types of physical movements, and acceleration characteristic coefficients are determined based on the frequency of occurrence of key physical events.
6. The sleep-aid music playback method based on multi-sensor fusion according to claim 1, characterized in that, Based on sleep eye movement data, sound characteristic coefficients, and acceleration characteristic coefficients, the user's sleep characteristics are determined, including: Sleep characteristic parameters are determined based on sound characteristic coefficients and acceleration characteristic coefficients, sleep stages are determined based on sleep eye movement data, and the changing trends of sleep characteristic parameters in each sleep stage are statistically analyzed. The sleep characteristics are determined by setting a feature tolerance threshold based on the sleep stage and by determining the sleep characteristic parameters change trend and corresponding feature tolerance threshold for all sleep stages.
7. The sleep-aid music playback method based on multi-sensor fusion according to claim 6, characterized in that, Sleep characteristics are determined based on the changing trends of sleep characteristic parameters across all sleep stages and the corresponding characteristic tolerance thresholds, including: Based on the changing trends of sleep characteristic parameters, a curve of sleep characteristic parameter change is plotted, and curve fitting is performed on the curve of sleep characteristic parameter change to obtain a predicted curve of sleep characteristic parameters; The time required for sleep characteristic parameters to reach their corresponding tolerance thresholds is predicted based on the sleep characteristic parameter prediction curves. The sleep characteristics are then determined based on the time required for all sleep characteristic parameter prediction curves to reach their corresponding tolerance thresholds.
8. The sleep-aid music playback method based on multi-sensor fusion according to claim 7, characterized in that, Play sleep-aid music based on sleep quality parameters, including: Obtain the user's current sleep stage and determine the basic music category based on the current sleep stage; Based on sleep quality parameters, a specific music list is determined within the basic music category, and then sleep-aid music is selected for the user based on this specific music list.
9. The sleep-aid music playback method based on multi-sensor fusion according to claim 8, characterized in that, Based on sleep quality parameters, a specific music list is determined within the basic music category, including: Acquire the trend of changes in users' sleep quality parameters when playing sleep-aid music, and determine the degree of music suitability based on the trend of changes in users' sleep quality parameters when playing sleep-aid music. Collect user feedback on the compatibility of all sleep-aid music and sort the sleep-aid music in descending order of compatibility. Based on the sorting results, suitable sleep-aid music with a ranking lower than the preset ranking threshold is selected and the suitable sleep-aid music is determined as a specific music list.
10. A sleep-aid music playback system based on multi-sensor fusion, characterized in that, include: The sound module is used to collect the user's sleep sound signals and determine the sound feature coefficients based on the sleep sound signals; The acceleration module is used to collect the user's sleep acceleration signal and determine the acceleration characteristic coefficient based on the sleep acceleration signal; The fusion module is used to collect the user's sleep eye movement data and determine the user's sleep characteristics based on the sleep eye movement data, sound feature coefficients, and acceleration feature coefficients. The playback module is used to determine sleep quality parameters based on the user's sleep characteristics and then play sleep-aid music based on those parameters.