Sleep quality analysis method, device and storage medium

Abstract

The present invention discloses a sleep quality analysis method, device, and storage medium. The method includes: obtaining ambient audio features at various time points within a monitoring period; determining a user's sleep quality score at each time point within the monitoring period; and analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score. The technical solution of this application enables sleep quality analysis, and by incorporating ambient audio features into the analysis, an effective assessment of the user's sleep quality is achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a sleep quality analysis method, device and storage medium. Background Art

[0002] A good night's sleep can reduce and relieve stress, ensure normal metabolism, accelerate the healing of damaged tissues, and maintain the function of all organs and the mental state. Therefore, a good night's sleep is extremely important. Currently, sleep quality is easily affected by external environmental sounds. For negative environmental sounds such as roommates' snoring, street noise, vehicles, construction, and other positive white noise such as rain and wind, sleep-inducing music is usually played through headphones to assist sleep. However, this fails to effectively evaluate the factors that affect the user's sleep quality, resulting in poor sleep-aiding effects. Summary of the Invention

[0003] The embodiments of the present application aim to solve the problem of being unable to effectively evaluate a user's sleep quality by providing a sleep quality analysis method, device, and storage medium.

[0004] The present invention provides a sleep quality analysis method, which includes:

[0005] Obtain the ambient audio characteristics at each time point during the monitoring period;

[0006] Determining a user's sleep quality score at each time point during the monitoring period;

[0007] The user's sleep quality is analyzed according to the time-series variation characteristics of the ambient audio characteristics and the time-series variation characteristics of the user's sleep quality score.

[0008] In one embodiment, the step of determining the user's sleep quality score at each time point within the monitoring period includes:

[0009] Obtaining the user's blood oxygen saturation and pulse at various time points during the monitoring period;

[0010] The user's sleep quality score is determined according to the blood oxygen saturation and the pulse.

[0011] In one embodiment, the step of analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score includes:

[0012] Obtaining an influence coefficient of the environmental audio feature;

[0013] Obtaining an influence coefficient of the user's sleep quality score according to an average slope of the user's sleep quality score;

[0014] Based on the influence coefficient of the user's sleep quality score and the influence coefficient of the environmental audio feature, a neural network model is used to fit the time series change characteristics of the environmental audio feature and the time series change characteristics of the user's sleep quality score to analyze the user's sleep quality.

[0015] In one embodiment, after the step of analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio characteristics and the temporal variation characteristics of the user's sleep quality score, the following steps are included:

[0016] When the ambient sound is negative, determine the ambient sound cancellation audio according to the decibel level of the ambient sound, and embed the ambient sound cancellation audio into the audio played during the user's sleep;

[0017] When the ambient sound is positive ambient sound, determining a first control action according to an influence coefficient of the ambient audio feature and an influence coefficient of the user's sleep quality score, and executing the first control action;

[0018] determining whether the user's sleep quality has improved;

[0019] If yes, continue to execute the first control action;

[0020] If not, suspend the execution of the first control action.

[0021] In one embodiment, the step of determining the ambient sound cancellation audio according to the decibel level of the ambient sound includes:

[0022] When the decibel level is greater than the first decibel level, audio with the same frequency, the same amplitude, and the opposite phase as the ambient sound is used as the ambient sound cancellation audio;

[0023] When the decibel number is less than or equal to the first decibel number, audio having the same frequency as the ambient sound is used as the ambient sound cancellation audio, wherein the amplitude of the ambient sound cancellation audio is greater than the amplitude of the ambient sound.

[0024] In one embodiment, the step of determining a first control action based on an influence coefficient of the ambient audio feature and an influence coefficient of the user's sleep quality score, and executing the first control action includes:

[0025] When the influence coefficient of the environmental audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the first control action includes at least one of the following: turning off the noise reduction function; starting the transparency mode; reducing the playback volume of the current audio or turning off the current audio;

[0026] When the influence coefficient of the environmental audio feature is less than the influence coefficient of the user's sleep quality score, the first control action is to maintain the playing state.

[0027] In one embodiment, the sleep quality analysis method further includes:

[0028] determining whether a rate of change of the user's sleep quality score during the monitoring period is less than or equal to a preset rate of change of the user's sleep quality score;

[0029] If so, the amplitude of the positive audio is determined according to the user's sleeping state, and the positive audio is embedded in the audio played during the user's sleeping process.

[0030] In one embodiment, the sleep quality analysis method further includes:

[0031] determining whether a rate of change of the user's blood oxygen saturation during the monitoring period is less than a preset rate of change of blood oxygen saturation;

[0032] If yes, execute a second control action, wherein the second control action includes at least one of the following: triggering an alarm; playing a preset audio; sending the blood oxygen saturation to a terminal;

[0033] If not, when the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both positive growth trends, return to the step of determining whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than the preset blood oxygen saturation change rate; when the growth trends are both negative growth trends, return to the step of determining whether the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset user sleep quality score change rate.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides an electronic device, which includes: a memory, a processor, and a sleep quality analysis program stored in the memory and runnable on the processor, wherein the sleep quality analysis program implements the steps of the above-mentioned sleep quality analysis method when executed by the processor.

[0035] In addition, to achieve the above objectives, the present invention further provides a computer-readable storage medium storing a sleep quality analysis program, which implements the steps of the above sleep quality analysis method when executed by a processor.

[0036] The technical solutions for a sleep quality analysis method, device, and storage medium provided in the embodiments of this application utilize a method for acquiring ambient audio features at various time points within a monitoring period, determining a user's sleep quality score at each time point within the monitoring period, and then analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score. By taking into account the impact of ambient audio features on user sleep quality and monitoring in real time how the user's sleep quality changes with ambient sound, the problem of being unable to effectively assess the user's sleep quality is resolved, and the technical solutions of this application improve the user's sleep quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of the structure of an electronic device involved in an embodiment of the present invention;

[0038] Figure 2 FIG. 1 is a flow chart of the first embodiment of the sleep quality analysis method of the present invention.

[0039] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings are only an embodiment diagram, not the entire invention. DETAILED DESCRIPTION

[0040] This application takes into account the impact of different audio on user sleep based on the characteristics of the ambient audio, combined with the user's physical signs and sleep status, to achieve intelligent adjustment of the played audio, ultimately achieving the beneficial effect of improving the user's sleep.

[0041] To better understand the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0042] like Figure 1 As shown, Figure 1 This is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention.

[0043] It should be noted that Figure 1 This is a structural diagram of the hardware operating environment of the electronic device.

[0044] like Figure 1As shown, the electronic device may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0045] Those skilled in the art will understand that Figure 1 The electronic device structure shown in the figure does not limit the electronic device and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0046] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a sleep quality analysis program. The operating system is a program that manages and controls the hardware and software resources of the electronic device, and the sleep quality analysis program and other software or programs are executed.

[0047] exist Figure 1 In the electronic device shown, the user interface 1003 is mainly used to connect to the terminal and communicate data with the terminal; the network interface 1004 is mainly used to communicate data with the background server; the processor 1001 can be used to call the sleep quality analysis program stored in the memory 1005.

[0048] In this embodiment, the electronic device includes: a memory 1005, a processor 1001, and a sleep quality analysis program stored in the memory and executable on the processor, wherein:

[0049] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it performs the following operations:

[0050] Obtain the ambient audio characteristics at each time point during the monitoring period;

[0051] Determining a user's sleep quality score at each time point during the monitoring period;

[0052] The user's sleep quality is analyzed according to the time-series variation characteristics of the ambient audio characteristics and the time-series variation characteristics of the user's sleep quality score.

[0053] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0054] Obtaining the user's blood oxygen saturation and pulse corresponding to each of the time points during the monitoring period;

[0055] The user's sleep quality score is determined according to the blood oxygen saturation and the pulse.

[0056] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0057] Obtaining an influence coefficient of the environmental audio feature;

[0058] Obtaining an influence coefficient of the user's sleep quality score according to an average slope of the user's sleep quality score;

[0059] Based on the influence coefficient of the user's sleep quality score and the influence coefficient of the environmental audio feature, a neural network model is used to fit the time series change characteristics of the environmental audio feature and the time series change characteristics of the user's sleep quality score to analyze the user's sleep quality.

[0060] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0061] When the ambient sound is negative, determine the ambient sound cancellation audio according to the decibel level of the ambient sound, and embed the ambient sound cancellation audio into the audio played during the user's sleep;

[0062] When the ambient sound is positive ambient sound, determining a first control action according to an influence coefficient of the ambient audio feature and an influence coefficient of the user's sleep quality score, and executing the first control action;

[0063] determining whether the user's sleep quality has improved;

[0064] If yes, continue to execute the first control action;

[0065] If not, suspend the execution of the first control action.

[0066] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0067] When the decibel level is greater than the first decibel level, audio with the same frequency, the same amplitude, and the opposite phase as the ambient sound is used as the ambient sound cancellation audio;

[0068] When the decibel number is less than or equal to the first decibel number, audio having the same frequency as the ambient sound is used as the ambient sound cancellation audio, wherein the amplitude of the ambient sound cancellation audio is greater than the amplitude of the ambient sound.

[0069] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0070] When the influence coefficient of the environmental audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the first control action includes at least one of the following: turning off the noise reduction function; starting the transparency mode; reducing the playback volume of the current audio or turning off the current audio;

[0071] When the influence coefficient of the environmental audio feature is less than the influence coefficient of the user's sleep quality score, the first control action is to maintain the playing state.

[0072] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0073] determining whether a rate of change of the user's sleep quality score during the monitoring period is less than or equal to a preset rate of change of the user's sleep quality score;

[0074] If so, the amplitude of the positive audio is determined according to the user's sleeping state, and the positive audio is embedded in the audio played during the user's sleeping process.

[0075] When the processor 1001 calls the sleep quality analysis program stored in the memory 1005, it also performs the following operations:

[0076] determining whether a rate of change of the user's blood oxygen saturation during the monitoring period is less than a preset rate of change of blood oxygen saturation;

[0077] If yes, execute a second control action, wherein the second control action includes at least one of the following: triggering an alarm; playing a preset audio; sending the blood oxygen saturation to a terminal;

[0078] If not, when the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both positive growth trends, return to the step of determining whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than the preset blood oxygen saturation change rate; when the growth trends are both negative growth trends, return to the step of determining whether the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset user sleep quality score change rate.

[0079] The technical solutions of this application will be introduced below in the form of embodiments.

[0080] like Figure 2 As shown, in the first embodiment of the present application, the sleep quality analysis method of the present application includes the following steps:

[0081] Step S110: Acquire the ambient audio features at each time point within the monitoring period.

[0082] In this embodiment, in order to solve the problem of being unable to effectively evaluate the user's sleep quality, the present application adopts a technical solution of obtaining the environmental audio features at each time point within the monitoring period, and determining the user's sleep quality score corresponding to each time point within the monitoring period, and then analyzing the user's sleep quality based on the temporal change characteristics of the environmental audio features and the temporal change characteristics of the user's sleep quality score. Since the impact of the environmental audio features on the user's sleep quality is taken into account and the functional relationship between the environmental audio features and the user's sleep quality is determined, the user's sleep quality can be monitored in real time as the environmental sound changes, thereby achieving an effective evaluation of the user's sleep quality.

[0083] In this embodiment, the user can wear headphones while sleeping. When the headphones play music, the ambient sound is captured by the headphones' microphones to determine the type of ambient sound. Alternatively, when the user is sleeping, they can play audio through an external audio player device, capture the ambient sound through the audio player device's microphones, and then determine the type of ambient sound. Ambient sound types include positive and negative ambient sound. Positive ambient sound is mainly a smooth signal with limited bandwidth that appears evenly on a time scale, such as the sound of rain, waves, waterfalls in nature, and the sound of fans and air conditioners in homes; negative ambient sound is sudden, intermittent, and high-volume sound, such as the roar of cars, construction, industrial production, social life, etc. The system obtains the ambient sound type corresponding to each time point during the monitoring period. In this process, in addition to obtaining the ambient sound type, the decibel level of the ambient sound is also obtained.

[0084] In this embodiment, individual responses to different audio features vary. Therefore, it is necessary to establish an influence function tailored to a specific personality based on the ambient sound and user's physical characteristics. The subjective evaluation of ambient sound is evaluated using the sound level index adopted by international standardization organizations and most countries in recent years. This index can reflect the interference of ambient sound on speech and the psychological annoyance it causes. The audio features of this application primarily include at least one of the following: equivalent continuous sound level, ambient sound pollution level, and narrowband noise sound pressure level. The equivalent continuous sound level is the average energy value of the sound level over a certain period of time; the ambient sound pollution level is the evaluation value of ambient sound that is derived by combining the influence of the average energy value and the variation characteristics (expressed by standard deviation). Furthermore, the degree of annoyance caused by sounds of the same loudness varies. People are particularly annoyed by ambient sounds with a narrow bandwidth, intermittent sounds, high intensity sounds, and sudden sounds. Therefore, the narrowband noise sound pressure level, which represents the noise center frequency of 800Hz, is introduced.

[0085] In this embodiment, at least one of the equivalent continuous sound level, the ambient sound pollution level, and the narrowband noise sound pressure level corresponding to each time point within the monitoring period is obtained. The monitoring period can be determined according to actual conditions.

[0086] Step S120: determining the user's sleep quality score at each time point within the monitoring period.

[0087] In this embodiment, in addition to obtaining the ambient audio features at each time point within the monitoring period, the user's sleep quality score corresponding to each time point within the monitoring period is also obtained to evaluate the impact of each ambient audio feature on the user's sleep quality score. The aforementioned ambient audio features and user sleep quality scores are determined in real time, i.e., each time point has a corresponding ambient audio feature value and a corresponding user sleep quality score.

[0088] Specifically, a common sleep monitoring method involves using a mobile phone app. The system monitors sleep using the phone's built-in sensors. Alternatively, wearable devices such as smartwatches and wristbands can be connected to monitor sleep data. Using CPC (cardiopulmonary coupling) technology, the coupling strength between the heartbeat interval (RR) and the respiratory interval (EDR) is analyzed to quantitatively assess sleep quality and sleep state. Alternatively, non-wearable devices can be used to monitor sleep by attaching sensors to pillows, sheets, or bedside tables. These methods output the user's sleep state and sleep quality score. The user's sleep state can include at least one of deep sleep, light sleep, rapid eye movement (REM), and wakefulness. Each sleep state has a corresponding preset sleep quality score change rate range. After obtaining the user's sleep quality score, the preset sleep quality score change rate range to which the user's sleep quality score falls is determined, and then the sleep state corresponding to the preset sleep quality score change rate range is determined.

[0089] In this embodiment, not only the ambient audio characteristics but also the user's sleeping state can be detected, and the impact of different ambient audio characteristics on the user's sleep can be comprehensively considered.

[0090] In one embodiment, determining the user's sleep quality score at each time point within the monitoring period specifically includes the following steps:

[0091] Step S121, obtaining the user's blood oxygen saturation and pulse corresponding to each time point in the monitoring period;

[0092] Step S122: Determine the user's sleep quality score based on the blood oxygen saturation and the pulse.

[0093] In this embodiment, a user's sleep quality score can be determined by measuring the user's blood oxygen saturation and pulse during sleep. The blood oxygen saturation and pulse represent the user's vital signs described in this application and are directly associated with the user's sleep state. The vital signs directly associated with the user's sleep state are denoted as SaO2, with a unit of 100%, and as H, with a unit of beats / min. The user's sleep quality score corresponding to the blood oxygen saturation and the pulse can be determined separately, and then the user's sleep quality score can be determined based on the weighted values ​​of the two scores. A weighting ratio can also be preset, for example, a weighted ratio of 30% for the blood oxygen saturation and a weighted ratio of 70% for the pulse. The user's sleep quality score can then be determined based on the weighted values ​​of the blood oxygen saturation and pulse scores, and their corresponding weighted ratios.

[0094] In this embodiment, the user's blood oxygen saturation and pulse corresponding to each time point during the monitoring period are obtained, and the user's sleep quality score corresponding to each time point is output at the same time, so as to determine the changes in blood oxygen saturation and pulse with the audio type of the ambient sound.

[0095] In the technical solution of this embodiment, the blood oxygen saturation and pulse of the user corresponding to each time point during the monitoring period are obtained; the user's sleep quality score is obtained based on the blood oxygen saturation and the pulse, thereby determining the impact of the blood oxygen saturation and pulse on the user's sleep quality.

[0096] Step S130 , analyzing the user's sleep quality according to the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score.

[0097] In this embodiment, the ambient audio features and the user's sleep quality score at each time point within the monitoring period are obtained. The time-series variation features of the ambient audio features are obtained based on the ambient audio features corresponding to each time point, and the time-series variation features of the user's sleep quality score are obtained based on the user's sleep quality score corresponding to each time point. The time-series variation features of the ambient audio features and the time-series variation features of the user's sleep quality score are fitted and calculated to obtain the impact of the ambient audio features on the user's sleep quality. Among them, by fitting the ambient audio features corresponding to each time point, a time-series variation curve of the ambient audio features can be obtained, and the time-series variation features of the ambient audio features can be obtained based on the time-series variation curve. Similarly, by fitting the user's sleep quality score corresponding to each time point, a time-series variation curve of the user's sleep quality score can be obtained, and the time-series variation features of the user's sleep quality score can be obtained based on the time-series variation curve.

[0098] In one embodiment, the step of analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score specifically includes:

[0099] Step S131, obtaining the influence coefficient of the environmental audio feature;

[0100] Step S132, obtaining an influence coefficient of the user's sleep quality score according to the average slope of the user's sleep quality score;

[0101] In this embodiment, the influence coefficient of the user's sleep quality score is obtained based on the average slope of the user's sleep quality score during the monitoring period. A positive average slope indicates a positive impact. A negative average slope indicates a negative impact. The absolute value of the average slope indicates the magnitude of the impact on the user's sleep quality. The influence coefficient R of the user's sleep quality score is linearly decomposed into two groups of factors: one group is the ambient sound factor, which includes the equivalent continuous sound level, the ambient sound pollution level, and the narrowband noise sound pressure level; the other group is the user's vital sign factors, which include blood oxygen saturation and pulse.

[0102] The influence coefficient of the user's sleep quality score is:

[0103]

[0104] Where K is the total number of factors, x i Represents the factor value of the ambient sound in the i-th factor, f i represents the influence coefficient of environmental sound on the i-th factor; u represents the factor influence coefficient, w i Represents the influence weight of the i-th factor.

[0105] The aforementioned factors include: user sleep quality score, equivalent continuous sound level, ambient sound pollution level, narrowband noise sound pressure level, blood oxygen saturation, and pulse rate. The impact coefficient of the user's sleep quality score is calculated by taking the average slope of the sleep quality score Q over the sampling period. A positive number represents a positive impact, a negative number represents a negative impact, and the absolute value represents the magnitude of the impact.

[0106] Typical test results and the table of environmental audio impact coefficients for specific users are as follows:

[0107]

[0108] Step S133: Based on the influence coefficient of the user's sleep quality score and the influence coefficient of the environmental audio feature, a neural network model is used to fit the time series change characteristics of the environmental audio feature and the time series change characteristics of the user's sleep quality score to analyze the user's sleep quality.

[0109] In this embodiment, after obtaining the temporal variation characteristics of the ambient audio features and the user's sleep quality score, these characteristics are input into a pre-set neural network model. The pre-set neural network model receives two inputs: real-world ambient data and system-generated audio data. By inputting these data into the pre-set neural network model, the relationship between the impact of different ambient sound types and ambient audio parameters on user sleep quality is determined.

[0110] In this embodiment, the preset neural network model combines the influence coefficient of the audio feature and the influence coefficient of the user's sleep quality score to fit the temporal change characteristics of the environmental audio feature and the temporal change characteristics of the user's sleep quality score, thereby obtaining the influence function of the environmental audio feature on the user's sleep quality.

[0111] In the technical solution of this embodiment, the influence coefficient of the environmental audio characteristics and the user's sleep quality score is determined, and then the influence function of the environmental audio characteristics on the user's sleep quality is determined according to the influence coefficient.

[0112] In a second embodiment of the present application, the sleep quality analysis method of the present application includes the following steps:

[0113] Step S110, obtaining the ambient audio features at each time point within the monitoring period;

[0114] Step S121, obtaining the user's blood oxygen saturation and pulse at each time point during the monitoring period;

[0115] Step S122, determining the user's sleep quality score based on the blood oxygen saturation and the pulse;

[0116] Step S131, obtaining the influence coefficient of the environmental audio feature;

[0117] Step S132, obtaining an influence coefficient of the user's sleep quality score according to the average slope of the user's sleep quality score;

[0118] Step S133, based on the influence coefficient of the user's sleep quality score and the influence coefficient of the environmental audio feature, a neural network model is used to fit the time series change characteristics of the environmental audio feature and the time series change characteristics of the user's sleep quality score to analyze the user's sleep quality;

[0119] Step S140 : When the ambient sound is negative ambient sound, determine ambient sound cancellation audio according to the decibel level of the ambient sound, and embed the ambient sound cancellation audio into the audio played during the user's sleep.

[0120] In this embodiment, multiple ambient sound cancellation audio tracks are prepared based on the type of ambient sound. Each audio track corresponds to a different sound category, loudness, and frequency characteristics. For example, thunder corresponds to high loudness and low frequency, rain corresponds to medium loudness and medium frequency, and birdsong and cicada chirping correspond to running water. Furthermore, each track corresponds to a different impact factor on the user's sleep quality score. After determining the ambient sound type, the ambient sound cancellation audio track is determined based on the decibel level. This audio track is then used to adjust the audio played during the user's sleep.

[0121] Specifically, after analyzing the user's sleep quality, the current ambient sound will also be obtained in real time. Under different ambient sound types, there are corresponding ambient sound elimination audios for different decibel levels of ambient sound; the ambient sound elimination audios are used to eliminate the impact of ambient sound on the user's sleep. Optionally, a sound detection device can be installed on the device that plays audio, and the decibel level of the ambient sound can be detected by the sound detection device. At least one sound detection device can also be set in the area where the user sleeps, and the decibel level of the ambient sound collected by the sound detection device can be transmitted to the device that plays audio. At the same time, the decibel level of the ambient sound can also be displayed on the display screen of the device that plays audio.

[0122] After determining the ambient sound cancellation audio according to the decibel level of the ambient sound, the ambient sound cancellation audio is embedded into the audio played during the user's sleep, so that the audio played during the user's sleep is adjusted.

[0123] In one embodiment, the first control is performed based on the real-time ambient sound. This process determines different control methods according to the decibel level of the ambient sound under different ambient sound types. Specifically, determining the ambient sound cancellation audio according to the decibel level of the ambient sound specifically includes:

[0124] Step S141: When the decibel level is greater than the first decibel level, audio having the same frequency, the same amplitude, and the opposite phase as the ambient sound is used as the ambient sound cancellation audio.

[0125] In this embodiment, if the ambient sound is detected as negative ambient sound in the first step, the decibel level of the ambient sound is read. If the decibel level of the ambient sound is greater than the first decibel level, an audio with the same frequency, same amplitude, and opposite phase as the ambient sound is used as the ambient sound cancellation audio.

[0126] For example, if D > 25dB, the system performs noise reduction. Specifically, the noise reduction process generates ambient sound cancellation audio with the same frequency and amplitude as the current ambient sound, but opposite phase, and embeds it into the audio played during the user's sleep to offset some of the ambient noise.

[0127] Step S142: When the decibel level is less than or equal to the first decibel level, use audio having the same frequency as the ambient sound as the ambient sound cancellation audio, wherein the amplitude of the ambient sound cancellation audio is greater than the amplitude of the ambient sound.

[0128] In this embodiment, if the ambient sound is detected as negative in the first step, the decibel level of the ambient sound is read. If the decibel level of the ambient sound is less than or equal to a first decibel level, audio having the same frequency as the ambient sound is used as the ambient sound cancellation audio. The amplitude of the ambient sound cancellation audio is greater than the amplitude of the ambient sound.

[0129] For example: If D≤25dB, the masking process is carried out. Specifically, the masking process is: generate ambient sound cancellation audio with the same frequency as the ambient sound, set the loudness to D+15dB, where D is the decibel number of the ambient sound. The generated ambient sound cancellation audio is embedded in the audio played during the user's sleep. The above masking process is based on the principle of masking effect. For sounds with similar frequencies, the stronger one will cover the weaker one; in addition, a sound difference of less than 15dB is additive, and a sound difference greater than 15dB is masking, and only the louder sound can be heard. Among them, the above-mentioned first decibel number can be determined according to actual conditions. For example, the first decibel number is 25dB.

[0130] Optionally, if D≤25dB after processing, the above masking process is performed again.

[0131] Step S150 : When the ambient sound is positive ambient sound, a first control action is determined according to an influence coefficient of the ambient audio feature and an influence coefficient of the user's sleep quality score, and the first control action is executed.

[0132] In one embodiment, determining a first control action based on the influence coefficient of the ambient audio feature and the influence coefficient of the user's sleep quality score, and executing the first control action specifically includes the following steps:

[0133] Step S151, when the influence coefficient of the environmental audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the first control action includes at least one of the following: turning off the noise reduction function; starting the transparency mode; reducing the playback volume of the current audio or turning off the currently playing audio.

[0134] In this embodiment, if the ambient sound is detected as positive ambient sound in the first step, the relationship between the influence coefficient of the ambient audio feature and the influence coefficient of the user's sleep quality score is determined. When the influence coefficient of the ambient audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the corresponding first control action is performed. For example, if the influence coefficient R of the user's sleep quality score is positive, and the influence coefficient of the ambient audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the system linearly reduces the volume of the audio played during the user's sleep. And perform at least one of the following first control actions: including turning off the noise reduction function, switching to transparency mode or turning off playback, using natural ambient sound, and reducing health risks;

[0135] Step S152: When the influence coefficient of the environmental audio feature is less than the influence coefficient of the user's sleep quality score, the first control action is to maintain the playing state.

[0136] In this embodiment, when the influence coefficient of the ambient audio feature is less than the influence coefficient of the user's sleep quality score, the first control action is determined to be maintaining the playing state.

[0137] Optionally, if the impact coefficient of the user's sleep quality score is negative, the negative ambient sound process is used. Specifically, when the decibel level is greater than a first decibel level, audio with the same frequency, amplitude, and opposite phase as the ambient sound is used as the ambient sound cancellation audio. When the decibel level is less than or equal to the first decibel level, audio with the same frequency as the ambient sound is used as the ambient sound cancellation audio. This ambient sound cancellation audio is then embedded in the audio played during the user's sleep.

[0138] Optionally, when the ambient sound is positive ambient sound and the decibel level is greater than the second decibel level, the noise reduction process is executed, and after reducing the current ambient sound level to the second decibel level, the execution is returned to when the influence coefficient of the ambient audio feature is greater than or equal to the influence coefficient of the user's sleep quality score. The first control action includes at least one of the following: turning off the noise reduction function; starting the transparency mode; reducing the playback volume of the current audio or turning off the judgment step of the currently playing audio.

[0139] In the technical solution of this embodiment, playback can be controlled based on ambient sound, and playback of played files can be controlled and modified according to multiple conditions, thereby improving sleeping environment sound conditions, achieving the effect of improving sleep quality and assisting work and study.

[0140] Step S160, determining whether the user's sleep quality is improved; if so, continuing to execute the first control action; if not, pausing execution of the first control action.

[0141] In this embodiment, after adjusting the audio played during the user's sleep, it is further determined whether the user's sleep quality has improved. Whether the user's sleep quality has improved can be reflected in whether the user's pulse and the user's blood oxygen saturation have reached preset values. When the preset values ​​are reached, the user's sleep quality is determined to have improved. When the user's sleep quality has improved, it indicates that the first control action is effective, and the first control action will continue to be executed. If the user's sleep quality has not improved, it indicates that the first control action has little effect on the user's sleep quality and may cause the user's sleep quality to deteriorate, and the execution of the first control action will be suspended. A more optimal processing method can be found and implemented to improve the user's sleep quality.

[0142] In this embodiment, the playback of audio files can be controlled based on the ambient sound and the user's sleep state, and the playback of the played files can be controlled and modified according to multiple conditions, thereby improving the sleeping environment sound conditions, achieving the effect of improving sleep quality and assisting work and study.

[0143] Based on the second embodiment, in a third embodiment of the present application, the sleep quality analysis method further includes the following steps:

[0144] Step S210, determining whether the change rate of the user's sleep quality score during the monitoring period is less than or equal to a preset user's sleep quality score change rate;

[0145] If so, step S210 is executed to determine the amplitude of the positive audio according to the user's sleeping state, and embed the positive audio into the audio played during the user's sleeping process.

[0146] In this embodiment, the second control process is performed simultaneously with the first control process. The second control process is to obtain a user sleep quality score based on the user's real-time sleep state, and to perform higher priority error correction and real-time processing based on the user's sleep quality score.

[0147] The rate of change of the user's sleep quality score within the preset period is recorded as x.

[0148] (1) The user's sleep state is deep sleep, light sleep, or rapid eye movement.

[0149] If the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset rate of change of the user's sleep quality score, it indicates that the user's sleep quality is not good. Determine the amplitude of the positive audio according to the user's sleep state, and embed the positive audio in the audio played during the user's sleep process. The preset rate of change of the user's sleep quality score can be set according to actual conditions. The preset rate of change of the user's sleep quality score in this application is set to -5%. Specifically, when the rate of change of the user's sleep quality score during the monitoring period is 5% ≥ x ≥ -5%, that is, the rate of change of the user's sleep quality score fluctuates within the range of +-5%, it is considered that the audio control strategy played during the user's sleep process is valid, and the processing logic is maintained;

[0150] If the change rate x of the user's sleep quality score during the monitoring period is less than -5%, that is, the user's sleep quality score drops by more than 5% during the sampling period, the audio control strategy for the user's sleep is considered invalid. Select audio with a positive influence coefficient R+2x on the user's sleep quality score.

[0151] (2) The user's sleep state is awake.

[0152] If the change rate x of the user's sleep quality score during the monitoring period is ≥ 5%, the audio control strategy played during the user's sleep is considered effective and the processing logic is maintained;

[0153] If the change rate x of the user's sleep quality score during the monitoring period is ≤ 5%, the audio control strategy played during the user's sleep is considered invalid, and a positive audio with an influence coefficient R+3x of the user's sleep quality score is selected, where the amplitude of the positive audio with R+3x is greater than the amplitude of the positive audio with R+2x.

[0154] This step is to collect and correct real-time user sleep data on top of historical test data, so as to more accurately understand the impact of audio on the user's sleep at the current time and provide a more user-friendly audio playback sleep-aiding experience.

[0155] According to the above technical solution, this embodiment can control the playback of audio played during the user's sleep based on the user's sleep quality score, thereby improving the sleeping environment sound conditions and achieving the effect of improving sleep quality.

[0156] Based on the third embodiment, in a fourth embodiment of the present application, the sleep quality analysis method further includes the following steps:

[0157] Step S310, determining whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than a preset rate of change of blood oxygen saturation;

[0158] If yes, step S320, executing a second control action, wherein the second control action includes at least one of the following: triggering an alarm; playing a preset audio; sending the blood oxygen saturation to the terminal;

[0159] If not, execute step S330. When the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both positive growth trends, return to execute step S310 to determine whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than the preset blood oxygen saturation change rate. When the growth trends are both negative growth trends, return to execute step S210 to determine whether the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset user sleep quality score change rate.

[0160] In this embodiment, in addition to the first and second controls, a third control is also performed. The third control process auxiliary adjusts and modifies the audio according to changes in the user's physical sign factor, namely, blood oxygen saturation.

[0161] If the rate of change of blood oxygen saturation during the monitoring period is less than the preset rate of change of blood oxygen saturation of 60%, the second control action is executed, that is, the health alarm is directly triggered. The system directly calls the alarm process, uses the preset audio to wake up the user, and pushes the relevant data to the bound terminal device to prompt the health risk of respiratory failure.

[0162] Optionally, if the rate of change of the blood oxygen saturation during the monitoring period is greater than or equal to 95%, the system does not perform any processing.

[0163] Optionally, if the rate of change of the blood oxygen saturation during the monitoring period fluctuates between 60% and 95%, that is, it is determined to be greater than the preset rate of change of the blood oxygen saturation, the system calculates the rate of change of the blood oxygen saturation and compares its effectiveness with the control strategy of the second control process. When the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both positive, it indicates that the current control strategy is valid, and the step of determining whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than the preset rate of change of the blood oxygen saturation is continued, and the system maintains the audio processing logic. When the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both negative, it indicates that the current control strategy is invalid, and the second control process is re-executed, that is, the step of determining whether the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset rate of change of the user's sleep quality score.

[0164] In one embodiment, when a user needs to wake up from a sleeping state, the system selects audio playback with a negative impact coefficient a and a relatively smooth transition curve to wake up the user and provide a better experience.

[0165] According to the above technical solution, this embodiment can control the playback of audio played during the user's sleep based on the changes in the user's blood oxygen saturation, thereby improving the sleeping environment sound conditions and achieving the effect of improving sleep quality.

[0166] The embodiments of the present invention provide embodiments of a sleep quality analysis method. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that shown here.

[0167] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a sleep quality analysis program. When the sleep quality analysis program is executed by a processor, it implements the various steps of the sleep quality analysis method described above and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0168] Since the storage medium provided in the embodiments of this application is the storage medium used to implement the method of the embodiments of this application, those skilled in the art will be able to understand the specific structure and variations of the storage medium based on the method described in the embodiments of this application, and therefore will not be described in detail here. All storage media used in the method of the embodiments of this application fall within the scope of protection to be provided by this application.

[0169] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0173] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third etc. does not indicate any order. These words may be interpreted as names.

[0174] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0175] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A sleep quality analysis method, characterized in that: The sleep quality analysis method comprises: Obtain the ambient audio characteristics at each time point during the monitoring period; Determining a user's sleep quality score at each time point during the monitoring period; analyzing the user's sleep quality according to the temporal variation characteristics of the ambient audio features and the temporal variation characteristics of the user's sleep quality score; When the ambient sound is positive ambient sound, a first control action is determined based on the influence coefficient of the ambient audio feature and the influence coefficient of the user's sleep quality score, and the first control action is executed, wherein when the influence coefficient of the ambient audio feature is greater than or equal to the influence coefficient of the user's sleep quality score, the first control action includes at least one of the following: turning off the noise reduction function; starting the transparency mode; reducing the playback volume of the current audio or turning off the current audio; determining whether the user's sleep quality has improved; If yes, continue to execute the first control action; If not, suspend the execution of the first control action.

2. The sleep quality analysis method according to claim 1, wherein: The step of determining the user's sleep quality score at each time point within the monitoring period includes: Obtaining the user's blood oxygen saturation and pulse at various time points during the monitoring period; The user's sleep quality score is determined according to the blood oxygen saturation and the pulse.

3. The sleep quality analysis method according to claim 2, wherein: The step of analyzing the user's sleep quality according to the temporal variation characteristics of the ambient audio characteristics and the temporal variation characteristics of the user's sleep quality score includes: Obtaining an influence coefficient of the environmental audio feature; Obtaining an influence coefficient of the user's sleep quality score according to an average slope of the user's sleep quality score; Based on the influence coefficient of the user's sleep quality score and the influence coefficient of the environmental audio feature, a neural network model is used to fit the time series change characteristics of the environmental audio feature and the time series change characteristics of the user's sleep quality score to analyze the user's sleep quality.

4. The sleep quality analysis method according to claim 1, wherein: After the step of analyzing the user's sleep quality based on the temporal variation characteristics of the ambient audio characteristics and the temporal variation characteristics of the user's sleep quality score, the method further includes: When the ambient sound is negative ambient sound, the ambient sound cancellation audio is determined according to the decibel level of the ambient sound, and the ambient sound cancellation audio is embedded in the audio played during the user's sleep.

5. The sleep quality analysis method according to claim 4, wherein: The step of determining the ambient sound cancellation audio according to the decibel level of the ambient sound comprises: When the decibel level is greater than the first decibel level, audio with the same frequency, the same amplitude, and the opposite phase as the ambient sound is used as the ambient sound cancellation audio; When the decibel number is less than or equal to the first decibel number, audio having the same frequency as the ambient sound is used as the ambient sound cancellation audio, wherein the amplitude of the ambient sound cancellation audio is greater than the amplitude of the ambient sound.

6. The sleep quality analysis method according to claim 1, wherein: The step of determining a first control action according to the influence coefficient of the ambient audio feature and the influence coefficient of the user's sleep quality score, and executing the first control action includes: When the influence coefficient of the environmental audio feature is less than the influence coefficient of the user's sleep quality score, the first control action is to maintain the playing state.

7. The sleep quality analysis method according to claim 4, wherein: The sleep quality analysis method further includes: determining whether a rate of change of the user's sleep quality score during the monitoring period is less than or equal to a preset rate of change of the user's sleep quality score; If so, the amplitude of the positive audio is determined according to the user's sleeping state, and the positive audio is embedded in the audio played during the user's sleeping process.

8. The sleep quality analysis method according to claim 7, wherein: The sleep quality analysis method further includes: determining whether a rate of change of the user's blood oxygen saturation during the monitoring period is less than a preset rate of change of blood oxygen saturation; If yes, execute a second control action, wherein the second control action includes at least one of the following: triggering an alarm; playing a preset audio; sending the blood oxygen saturation to a terminal; If not, when the growth trends of the rate of change of the blood oxygen saturation and the rate of change of the user's sleep quality score are both positive growth trends, return to the step of determining whether the rate of change of the user's blood oxygen saturation during the monitoring period is less than the preset blood oxygen saturation change rate; when the growth trends are both negative growth trends, return to the step of determining whether the rate of change of the user's sleep quality score during the monitoring period is less than or equal to the preset user sleep quality score change rate.

9. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a sleep quality analysis program stored in the memory and executable on the processor. When the sleep quality analysis program is executed by the processor, the steps of the sleep quality analysis method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a sleep quality analysis program, which, when executed by a processor, implements the steps of the sleep quality analysis method according to any one of claims 1 to 8.

Images