WO2022247649A1 - Method and apparatus for evaluating respiratory function during sleep - Google Patents

Abstract

An apparatus (1000) for evaluating a respiratory function during sleep. The apparatus comprises a processing unit (1100), a receiving unit (1200) and a sending unit (1300). The processing unit (1100) is used for automatically enabling or disabling, in different detection scenarios and by using different detection modes, the evaluation of respiratory functions of a user during sleep, which functions comprise a sleep cycle staging, hypopnea, sleep apnea, a snoring level risk, etc. In this way, a user does not need to manually click the start or end of sleeping, and the evaluation of respiratory functions during sleep is automatically enabled or disabled, such that the user experience is friendly. Moreover, the accuracy of evaluation is also improved.

Description

Method and device for assessing sleep breathing function

This application claims the priority of a Chinese patent application filed with the State Intellectual Property Office on May 24, 2021, with application number 202110567956.X, and application title "Method and device for evaluating sleep respiratory function", the entire contents of which are incorporated by reference in this application.

technical field

The present application relates to the field of computer technology, and more specifically, to a method and device for evaluating sleep breathing function.

Background technique

With the continuous increase of people's life pressure, the quality of sleep is gradually reduced, and people begin to pay attention to the quality of sleep and the detection of sleep-breathing disease during sleep. Sleep-disordered breathing is a major factor affecting sleep quality. Simple snoring, hypoventilation, and sleep apnea are the most common causes of sleep-disordered breathing. Respiratory diseases during sleep can be fatal. Therefore, effective real-time detection and early warning of abnormal sleep stages, simple snoring, hypoventilation, and sleep apnea during sleep are particularly important for personal health and family care.

At present, technologies such as obtaining respiratory signals through ultrasound for sleep staging, detection of sleep in and out, and division of snoring sounds, breathing sounds, and non-target segments based on recorded data are gradually mature. For example, polysomnography on the market, by recording brain waves, electromyography, electrocardiogram, oronasal airflow, chest and abdomen breathing movements, and sounds during sleep, sums up and analyzes the sleep status and Severity of snoring, hypoventilation, sleep apnea, etc. Polysomnography requires professionals to operate it in a professional place, which is poor in comfort and expensive, and it is difficult to meet the convenience and efficiency requirements of family daily life. In addition, there are some applications (applications, also referred to as apps) for the evaluation of sleep breathing function on the market, and most of these apps set a threshold in the environment where the user (or the subject) sleeps or use a neural network method Identify the sound and breathing sound during sleep, and then evaluate the quality of the user's sleep breathing throughout the night. This evaluation method requires the user to manually click the start and end of sleep, which is extremely unfriendly to the user experience.

Contents of the invention

The present application provides a method and device for evaluating sleep breathing function, which can conveniently evaluate a user's sleep breathing function and improve user experience.

In a first aspect, a method for evaluating sleep breathing function is provided, the method includes: determining a current detection scene, and the current detection scene belongs to one of preset detection scenarios, wherein the preset The detection scene includes a first detection scene and a second detection scene, wherein the first detection scene is that the user is wearing a smart wearable device, and the second detection scene is that the user is not wearing a smart wearable device;

Select a detection method according to the current detection scene,

Using the selected detection method to determine the state of the user, wherein the state of the user includes that the user is in a sleeping state, or that the user is in a non-sleeping state;

According to the state of the user, the evaluation of the sleep breathing function of the user is turned on or off,

Wherein, the evaluation of sleep breathing function includes evaluating one or more of the following: sleep cycle stage, hypopnea, sleep apnea, and risk of snoring grade.

In the technical solution of the present application, firstly, the current detection scene is determined, and a corresponding detection method is selected based on the current detection scene. Different detection methods use different means to determine whether the user is in a sleep state. If it is determined that the user is in a sleep state, the evaluation of the sleep apnea function is automatically started. If it is determined that the user is in a non-sleeping state, the evaluation of the sleep apnea function is not started.

It can be seen that compared with some existing solutions, the user needs to manually click the sleep start or sleep end on the sleep monitoring device to turn on or off the sleep breathing function of the sleep monitoring device, the technical solution of the present application, in different detection scenarios In this case, the user's status is obtained through different detection methods, so that the evaluation of the sleep breathing function can be automatically turned on or off, and the user experience is more friendly.

With reference to the first aspect, in some implementation manners of the first aspect, the selecting a detection method according to the current detection scenario includes:

If the current detection scene is the first detection scene, select a first detection method, wherein the first detection method is to judge the state of the user through the smart wearable device; or,

If the current detection scene is the second detection scene, select the second detection method, wherein the second detection method is to judge the the status of the user;

Wherein, the status of the smart wearable device includes one or more of the following: the duration of the smart wearable device being in a static state within a specified period of time is greater than or equal to the first duration threshold, the duration of the smart wearable device being in a large motion state The duration is greater than or equal to the second duration threshold;

The user's historical sleep information includes one or more of the following: the user's historical sleep time period, the user's preset sleep time, and the user's preset alarm clock time.

In this implementation, in the detection scenario where the user wears the smart wearable device, the smart wearable device is used to judge the user's state in real time, specifically, to judge the user's falling asleep and getting out of sleep. However, when the user is not wearing the smart wearable device, it is necessary to combine the state of the smart wearable device and the user's historical sleep information to determine the user's state. Thus, regardless of whether the user wears the smart wearable device, the user's state can be judged through an appropriate detection method, and then the evaluation can be automatically turned on or off, which improves the user experience.

With reference to the first aspect, in some implementations of the first aspect, after starting the evaluation of the user's sleep breathing function, the method further includes:

acquiring available signals in the first detection scene or the second detection scene;

Evaluate the sleep breathing function of the user according to the available signals, wherein the available signals include one or more of the following:

one or more respiratory indicators, the respiratory indicators include respiratory rate and/or respiratory wave decline;

one or more snore indicators including snore loudness; and

The user's action index, where the action index includes the user's action range and/or frequency of major actions.

With reference to the first aspect, in some implementation manners of the first aspect, the evaluating the sleep breathing function of the user according to the available signal includes:

The available signal is predicted by using the trained light gradient lifting machine GBM model to evaluate the sleep breathing function of the user.

In this implementation, the trained light-weight GBM model is used to predict what is available in the current detection scene. Since the light-weight GBM model is obtained through a large amount of data training in advance, and the data used for training is only reserved for breathing, The frequency bands related to snoring and other signals have high sensitivity, which provides a good basis for the subsequent evaluation of sleep breathing function, and the evaluation accuracy is improved.

With reference to the first aspect, in some implementation manners of the first aspect, before using the trained lightweight GBM prediction model to predict the available signal, the method further includes:

Obtain audio data and ultrasound data of the user;

Preprocessing the audio data and ultrasound data, and performing feature extraction on the preprocessed audio data and ultrasound data to obtain extracted data, wherein the feature extraction process includes processing the preprocessed audio Data and ultrasound data for the extraction of raw features and the aggregation of statistical features;

Using the extracted data, train the lightweight GBM prediction model to obtain the trained lightweight GBM prediction model.

In this implementation, the available signals obtained in the detection scene, such as audio data and ultrasonic data, are preprocessed and feature extracted, and the extracted data thus obtained is used for the training of the lightweight GBM model, which can improve the performance of the lightweight GBM model. For the predictive performance of the model, compared with the existing evaluation scheme of sleep breathing function, the evaluation result of the technical scheme of the present application is more accurate and the sensitivity is higher.

With reference to the first aspect, in some implementation manners of the first aspect, the use of the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user includes:

If the snoring loudness is greater than or equal to the first loudness threshold, and the duration is greater than or equal to the first duration threshold, it is determined that the user's snoring level risk is high risk;

If the loudness of the snoring sound is greater than or equal to the first loudness threshold and the duration is less than the first duration threshold, it is determined that the user's snoring level risk is medium risk;

If the loudness of the snoring sound is greater than or equal to the second loudness threshold and the duration is greater than or equal to the second duration threshold, it is determined that the user's snoring level risk is low risk, wherein the second loudness threshold is smaller than the first loudness threshold a threshold, the second duration threshold is less than the first duration threshold;

Otherwise, it is determined that the user's snoring level risk is normal.

With reference to the first aspect, in some implementation manners of the first aspect, the use of the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user includes:

If the respiratory rate is greater than the first frequency and the slope is greater than the first value, it is determined that the sleep staging stage is REM sleep;

If the breathing frequency is less than or equal to the first frequency and greater than or equal to the second frequency, it is determined that the sleep staging stage is light sleep;

If the breathing frequency is less than or equal to the second frequency, it is determined that the sleep staging stage is deep sleep.

With reference to the first aspect, in some implementation manners of the first aspect, the use of the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user includes:

If the decrease ratio of the amplitude of the respiratory wave is greater than the first percentage, it is judged as hypopnea;

If the decrease ratio of the kurtosis of the respiratory wave is greater than the second percentage, it is determined to be sleep apnea.

In each of the above implementation manners, by setting appropriate judgment rules and thresholds, durations or percentages, the accuracy of sleep apnea function evaluation can be improved.

The second aspect provides a communication device, the communication device has the function of realizing the method in the first aspect or any possible implementation thereof, the function can be realized by hardware, or by executing corresponding software by hardware . The hardware or software includes one or more units corresponding to the above functions.

In a third aspect, a communication device is provided, including a processor and a communication interface, the communication interface is used to receive data and/or information, and transmit the received data and/or information to the processor, the processing The processor processes the data and/or information, so that the communication device executes the method in the first aspect or any possible implementation thereof.

Alternatively, the processor may be a processing circuit.

Optionally, the aforementioned communication interface may be an interface circuit.

Optionally, the communication interface may include an input interface and an output interface. Wherein, the input interface is used to receive data and/or information to be processed, and the output interface is used to output processed data and/or information.

In a fourth aspect, the present application provides a communication device, including at least one processor, the at least one processor is coupled to at least one memory, the at least one memory is used to store computer programs or instructions, and the at least one processor is used to The computer program or instruction is called and executed from the at least one memory, so that the communication device executes the method in the first aspect or any possible implementation manner thereof.

Optionally, the at least one processor is integrated with the at least one memory.

Optionally, the communication devices in the above second to fourth aspects may be a chip or a chip system, for example, a system on a chip (system on a chip, SOC) chip.

In a fifth aspect, the present application provides a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when the computer instructions are run on a computer, as in the first aspect or any possible implementation thereof, method is executed.

In a sixth aspect, the present application provides a computer program product, the computer program product includes computer program code, and when the computer program code is run on a computer, the method in the first aspect or any possible implementation thereof be executed.

In a seventh aspect, the present application provides a smart wearable device, including the communication device as described in the second aspect.

Description of drawings

Fig. 1 is a schematic flowchart of the method for evaluating sleep breathing function provided by the present application.

Fig. 2 is a schematic flowchart of the method for evaluating sleep breathing function provided by the present application.

FIG. 3 is a schematic block diagram of preprocessing and feature extraction performed by the evaluation device.

Fig. 4 is an exemplary flow chart of the method for evaluating sleep breathing function provided by the present application.

FIG. 5 is an evaluation device 500 for evaluating sleep breathing function provided by the present application.

Fig. 6 is a schematic block diagram of the evaluation device provided by the present application.

Fig. 7 is a schematic structural diagram of the evaluation device provided by the present application.

Fig. 8 is a schematic block diagram of a smart wearable device provided by the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

The technical solution of this application can be applied to smart wearable devices, which can automatically detect the user's sleep breathing function (for example, sleep staging, sleep apnea, snoring detection, snoring partial detection, hypoventilation and other sleep breathing related diseases) The evaluation does not require the user to manually enable or disable the evaluation of the sleep breathing function, which improves the user experience. In addition, the accuracy of the assessment has also improved.

Exemplarily, the smart wearable devices mentioned in this application include, but are not limited to: smart electronic products such as smart bracelets, smart watches, smart phones, and iPads.

Referring to FIG. 1 , FIG. 1 is a schematic flowchart of the method for evaluating sleep breathing function provided by the present application. As shown in FIG. 1 , the method 100 may be performed by an evaluation device. Exemplarily, the evaluation device may be a smart wearable device, or a chip (or chip system) built in the smart wearable device. The method 100 mainly includes steps 110-140.

110. The evaluation device determines a current detection scene, where the current detection scene belongs to one of preset detection scenes.

Exemplarily, the preset detection scenarios may include a first detection scenario and a second detection scenario.

Wherein, the first detection scene is that the user wears the smart wearable device, and the second detection scene is that the user does not wear the smart wearable device.

120. The evaluation device selects a detection mode according to the current detection scenario.

In the present application, the evaluation device may select a detection method suitable for the detection scenario in different detection scenarios, so as to further determine whether the user is in a sleep state.

Specifically, if the current detection scene is the first detection scene, the evaluation device selects the first detection mode. Wherein, the first detection method is that the evaluation device judges the state of the user through the smart wearable device.

If the current detection scene is the second detection scene, the evaluation device selects the second detection method, wherein, if the second detection method is adopted, the evaluation device needs to further obtain the status of the smart wearable device and the user's historical sleep information, and according to the smart wearable The status of the device and the historical sleep information of the user are used to determine the status of the user.

Optionally, the state of the smart wearable device includes one or more of the following:

The duration of the smart wearable device being in a static state within a specified time period is greater than or equal to the first duration threshold, and the duration of the smart wearable device being in a large motion state is greater than or equal to the second duration threshold.

Exemplarily, whether the smart wearable device is in a large motion state can be judged by the motion range of the smart wearable device. For example, set a threshold of motion range, if the motion range of the smart wearable device is greater than the threshold, it indicates that the smart wearable device is in a state of large motion, otherwise it is not in a state of large motion.

Optionally, the user's historical sleep information includes one or more of the following: the user's historical sleep time period, the user's preset sleep time, and the user's preset alarm clock time, and so on.

Exemplarily, the sleep time preset by the user may be a preset time for falling asleep, or a preset time for getting up (that is, time for getting out of sleep), and the like.

130. The evaluation device judges the state of the user by using the selected detection mode.

Wherein, the state of the user includes that the user is in a sleeping state, or the user is in a non-sleeping state.

140. The evaluation device enables or disables the evaluation of the sleep breathing function of the user according to the state of the user.

Specifically, when the user is in a sleeping state, the evaluation of the user's sleep breathing function is started. When the user is in a non-sleeping state, the evaluation of the user's sleep breathing function is not enabled or disabled.

It should be understood that turning off the sleep apnea function evaluation refers to turning off the sleep apnea function evaluation after the sleep apnea function evaluation is turned on by judging the user's state in real time.

Optionally, the assessment of sleep breathing function may include, but is not limited to, assessing one or more of the following: sleep cycle stages, hypopnea, sleep apnea, and risk of snoring grade.

In this application, based on the current detection scenario, the evaluation device can determine whether the user is in a sleep state, and then automatically enable or disable the evaluation of sleep breathing function. Specifically, if the evaluation device determines that the user is in a sleep state, it automatically starts the evaluation of the sleep breathing function. On the contrary, if the evaluation device determines that the user is in a non-sleeping state, the evaluation of the sleep breathing function is not started. Alternatively, after the evaluation device automatically starts the evaluation of the sleep apnea function, it judges the state of the user in real time and determines that the user is out of sleep, and then automatically turns off the evaluation of the sleep apnea function.

It can be seen that, compared with some existing solutions, the user needs to manually click the sleep start or sleep end on the sleep monitoring device to turn on or off the sleep breathing function of the sleep monitoring device, compared with the technical solution of the present application, the evaluation device is In different detection scenarios, the user's status is obtained through different detection methods, so that the evaluation of the sleep breathing function can be automatically turned on or off, and the user experience is more friendly.

The following describes in detail with reference to FIG. 2 , the assessment device performs the sleep breathing function assessment process after it determines that the user is in a sleep state and starts the sleep breathing function assessment.

Referring to FIG. 2 , FIG. 2 is a schematic flowchart of the method for evaluating sleep breathing function provided by the present application. Similar to method 100, method 200 may be performed by an evaluation device. As shown in FIG. 2 , the method 200 mainly includes steps 210-240.

210. The evaluation device determines that the current detection scene is the first detection scene, that is, the user is wearing the smart wearable device.

220. The evaluation device selects a first detection manner corresponding to the first detection scene.

230. The evaluation device judges the state of the user through the smart wearable device, and obtains a judgment result.

240. If it is determined that the user is in a sleep state, the evaluation device starts the evaluation of the sleep breathing function.

After starting the evaluation of the sleep breathing function, the evaluation device continues to perform the following steps.

250. The evaluation device acquires available signals in the current detection scene through the smart wearable device.

Optionally, available signals include one or more of the following:

one or more respiratory indicators, the respiratory indicators include respiratory rate and/or respiratory wave decline;

one or more snore indicators including snore loudness; and

The user's action index, where the action index includes the user's action range and/or frequency of major actions.

Exemplarily, the evaluation device obtains available signals in the current detection scene through a microphone of the smart wearable device, an ultrasonic sending and/or receiving sensor, and the like.

260. The evaluation device uses a pre-trained machine learning prediction model to predict the obtained available signals and output a prediction result.

Specifically, as an example, the machine learning model in this application adopts a lightweight GBM prediction model.

It should be understood that before the light-weight GBM prediction model is used for prediction, a large amount of training is required to improve the accuracy and sensitivity of prediction.

Exemplarily, the evaluation device acquires audio data and ultrasound data of the user, and preprocesses the audio data and ultrasound data. Further, the evaluation device performs feature extraction on the preprocessed audio data and ultrasound data. Specifically, feature extraction may mainly include extraction of original features and aggregation of statistical features. For the convenience of description, hereinafter, the data obtained through feature extraction will be referred to as extracted data.

The evaluation device uses the extracted data to train the light GBM prediction model, and obtains the trained light GBM prediction model, which provides a good guarantee for the accuracy and sensitivity of the subsequent evaluation of sleep breathing function.

Exemplarily, the detailed flow of preprocessing and feature extraction performed by the evaluation device may be as shown in FIG. 3 .

Referring to FIG. 3 , FIG. 3 is a schematic block diagram of preprocessing and feature extraction performed by the evaluation device. As shown in FIG. 3 , the evaluation device obtains target audio data and/or ultrasonic data in the current detection scene through silent detection, judgment of sound segments and silent segments, and collection of audio data and ultrasonic data. Further, the evaluation device performs preprocessing on the obtained target audio data and/or ultrasound data, so as to eliminate the influence of the magnitude of the data and its own local fluctuations.

Exemplarily, the preprocessing may include performing amplitude normalization, median filtering, and bandpass filtering on the target audio data and/or ultrasound data, so as to retain the frequency bands of the respiratory signal and the snoring signal as much as possible, so as to improve the sensitivity of the evaluation .

In addition, the evaluation device performs feature extraction on the preprocessed signal to obtain extracted data. Exemplarily, the process of feature extraction includes extraction of original features of target audio data and/or ultrasound data and aggregation of statistical features.

Exemplarily, the original features include, but are not limited to: Mel-frequency cepstral coefficients, differential features, and spectral flatness. Statistical features include, but are not limited to: mean, variance, peak, skewness, and distance features.

Further, the machine learning model pair is trained by using the extracted data. Exemplarily, the machine learning model may adopt a light gradient boosting machine (light gradient boosting machine, light GBM) model. In the process of training the model, the light GBM model analyzes the input signal to obtain the probability and label of the respiratory signal, snoring signal and non-snoring signal in the input signal, and statistics and caches them for subsequent predictions .

When the evaluation device obtains available signals in the current detection scene, the obtained available signals are input into the lightweight GBM model, and prediction results are obtained to complete the evaluation of the user's sleep breathing function.

Some examples of prediction results are given below.

Exemplarily, the risk of snoring is evaluated through the user's, breathing index, snoring sound index, motion index, and the like.

For example, if the loudness of snoring is greater than or equal to the first loudness threshold (denoted as DB1), and the duration is greater than or equal to the first duration threshold (denoted as T1), it is determined that the user's snoring risk level is high risk;

If the snoring loudness is greater than or equal to the first loudness threshold and the duration is less than the first duration threshold, it is determined that the user's snoring level risk is medium risk;

If the snoring loudness is greater than or equal to the second loudness threshold (denoted as DB2), and the duration is greater than or equal to the second duration threshold (denoted as T2), it is determined that the user's snoring level risk is low risk;

In other cases, it is determined that the user's snoring level risk is normal;

Wherein, the second loudness threshold is smaller than the first loudness threshold, and the second duration threshold is smaller than the first duration threshold.

Exemplarily, the user's sleep staging stage is identified according to the user's breathing rate feature.

For example, if the respiratory rate is greater than the first frequency (for example, X1) and the slope is greater than the first value (for example, Y1), it is determined that the user's sleep staging stage is rapid eye movement sleep (rapid eye movement sleep, REM);

If the breathing frequency is less than or equal to the first frequency (for example, X1) and greater than or equal to the second frequency (for example, X2), it is determined that the user's sleep stage is light sleep;

If the breathing frequency is less than or equal to the second frequency (for example, X2), it is determined that the user's sleep staging stage is deep sleep;

Wherein, X2 is smaller than X1.

Exemplarily, the user's sleep apnea or hypopnea is judged according to the magnitude of the decrease of the user's respiratory wave.

For example, if the decrease ratio of the amplitude of the user's respiratory wave is greater than a first percentage (for example, X%), it is determined to be hypopnea;

If the decrease ratio of the kurtosis of the respiratory wave is greater than the second percentage (for example, Y%), it is determined to be sleep apnea.

An example description of the workflow of the evaluation device is given below with reference to FIG. 4 .

Referring to FIG. 4 , FIG. 4 is an exemplary flowchart of a method 400 for evaluating sleep breathing function provided by the present application. It should be understood that the method 400 may be performed by an evaluation device. The evaluation device may be executed by a smart wearable device or a module (for example, a chip or a chip system, etc.) with corresponding functions in the smart wearable device, which is not limited. Exemplarily, the chip may be a system on a chip (system on a chip, SOC).

401. Determine whether the user wears the smart wearable device.

It should be understood that judging whether the user wears the smart wearable device is to determine whether the current detection scene is specifically the first detection scene or the second detection scene.

If yes, go to step 402 . If not, go to step 403 .

402. Determine whether the user falls asleep by using the smart wearable device.

That is, it is determined whether the user is in a sleep state or a non-sleep state.

If not, go to step 404 .

If yes, go to step 405.

404. The evaluation of the sleep breathing function is not started.

405. Automatically start the evaluation of the sleep breathing function.

404. Determine whether the duration of the smart wearable device being in the static state is equal to or greater than the first duration threshold.

If not, go to step 406 .

If yes, go to step 407.

406. The evaluation of the sleep breathing function is not started.

407. Automatically start the evaluation of the sleep breathing function.

After the evaluation of sleep breathing function is initiated, step 408 is performed.

408. Real-time statistics and analysis of breathing indicators and snoring indicators.

Optionally, respiration indicators may include one or more, for example, the rate of respiration.

Optionally, the snoring indicator may include one or more, for example, the loudness of the snoring.

409. While performing the sleep breathing assessment, judge whether the user is asleep through the smart wearable device.

If yes, go to step 410.

If not, go to step 408 .

410. Automatically shut down the sleep breathing evaluation function.

In step 405, step 411 is executed after the sleep breathing assessment function is automatically enabled.

411. Real-time statistics and analysis of breathing indicators and snoring indicators.

412. Acquiring the status of the smart wearable device in real time while performing the sleep breathing assessment, and judging whether the duration of the smart wearable device being in the state of major motion exceeds the second duration threshold.

If yes, go to step 413.

If not, go to step 411.

413. Automatically shut down the sleep breathing evaluation function.

A schematic block diagram of the evaluation device provided by this application is given below.

Referring to FIG. 5 , FIG. 5 is an evaluation device 500 for evaluating sleep breathing function provided by the present application. The evaluation device 500 may include an automatic detection module 510 , a data collection and preprocessing module 520 , a feature extraction and statistics module 530 , and a sleep breathing evaluation function module 540 .

The automatic detection module 510 is mainly used to automatically activate or deactivate the microphone, the ultrasonic receiving device and/or the ultrasonic transmitting device under different detection scenarios, and activate or deactivate the evaluation of sleep breathing function.

The data collection and preprocessing module 520 is mainly used for the collection of audio data and/or ultrasound data, the collection of available signals, and preprocessing such as judging the audio segment and the silent segment. Exemplarily, the audio data includes common recording data.

The feature extraction and statistics module 530 is used to perform feature extraction and statistics on the user's actions, breathing and snoring features.

The sleep breathing function evaluation module 540 is used to evaluate the sleep breathing function of the user according to the data completely extracted and counted by the feature extraction and statistics module 530 .

The sleep breathing method provided by this application has been described in detail above, and the evaluation device provided by this application will be introduced below.

Referring to FIG. 6 , FIG. 6 is a schematic block diagram of the evaluation device provided by the present application. As shown in FIG. 6 , the evaluation device 1000 includes a processing unit 1100 , a receiving unit 1200 and a sending unit 1300 .

The processing unit 1100 is configured to determine a current detection scene, where the current detection scene belongs to one of preset detection scenarios, wherein the preset detection scenarios include a first detection scene and a second detection scene, Wherein, the first detection scene is that the user is wearing a smart wearable device, and the second detection scene is that the user is not wearing a smart wearable device;

And, according to the current detection scene, select a detection method;

And, using the selected detection method to determine the state of the user, wherein the state of the user includes that the user is in a sleeping state, or that the user is in a non-sleeping state;

According to the state of the user, the evaluation of the sleep breathing function of the user is turned on or off,

Wherein, the evaluation of sleep breathing function includes evaluating one or more of the following: sleep cycle stage, hypopnea, sleep apnea, and risk of snoring grade.

The sending unit 1300 is configured to output the evaluation result.

Optionally, as an embodiment, the processing unit 1100 is further configured to:

judging the current detection scene, and selecting a first detection mode when it is determined that the current detection scene is the first detection scene, wherein the first detection mode is to judge the the user's status; or,

In the case where it is determined that the current detection scene is the second detection scene, select the second detection method, wherein the second detection method is determined by the state of the smart wearable device and the historical sleep information of the user. the status of the user;

Wherein, the status of the smart wearable device includes one or more of the following: the duration of the smart wearable device being in a static state within a specified period of time is greater than or equal to the first duration threshold, the duration of the smart wearable device being in a large motion state The duration is greater than or equal to the second duration threshold;

The user's historical sleep information includes one or more of the following: the user's historical sleep time period, the user's preset sleep time, and the user's preset alarm clock time.

Optionally, as an embodiment, the receiving unit 1200 is configured to acquire available signals in the first detection scene or the second detection scene;

And, the processing unit 1100 is configured to evaluate the sleep breathing function of the user according to the available signals, wherein the available signals include one or more of the following:

one or more respiratory indicators, the respiratory indicators include respiratory rate and/or respiratory wave decline;

one or more snore indicators including snore loudness; and

The user's action index, where the action index includes the user's action range and/or frequency of major actions.

Optionally, as an embodiment, the processing unit 1100 is further configured to use a trained light-weight gradient boosting machine GBM model to predict the available signal, so as to evaluate the sleep breathing function of the user.

Optionally, as an embodiment, the receiving unit 1200 is configured to acquire audio data and ultrasound data of the user;

And, the processing unit 1100 is further configured to preprocess the audio data and ultrasound data, and perform feature extraction on the preprocessed audio data and ultrasound data to obtain extracted data, wherein the feature extraction The processing includes performing extraction of original features and aggregation of statistical features on the preprocessed audio data and ultrasound data;

Using the extracted data, train the lightweight GBM prediction model to obtain the trained lightweight GBM prediction model.

Optionally, as an embodiment, the processing unit 100 is specifically configured to:

If the snoring loudness is greater than or equal to the first loudness threshold, and the duration is greater than or equal to the first duration threshold, it is determined that the user's snoring level risk is high risk;

If the loudness of the snoring sound is greater than or equal to the first loudness threshold and the duration is less than the first duration threshold, it is determined that the user's snoring level risk is medium risk;

If the loudness of the snoring sound is greater than or equal to the second loudness threshold and the duration is greater than or equal to the second duration threshold, it is determined that the user's snoring level risk is low risk, wherein the second loudness threshold is smaller than the first loudness threshold a threshold, the second duration threshold is less than the first duration threshold;

Otherwise, it is determined that the user's snoring level risk is normal.

Optionally, as an embodiment, if the respiratory rate is greater than the first frequency and the slope is greater than the first value, it is determined that the sleep staging stage is REM sleep;

If the breathing frequency is less than or equal to the first frequency and greater than or equal to the second frequency, it is determined that the sleep staging stage is light sleep;

If the breathing frequency is less than or equal to the second frequency, it is determined that the sleep staging stage is deep sleep.

Optionally, as an embodiment, the trained lightweight GBM prediction model is used to predict the available signals to evaluate the sleep breathing function of the user, including:

If the decrease ratio of the amplitude of the respiratory wave is greater than the first percentage, it is judged as hypopnea;

If the decrease ratio of the kurtosis of the respiratory wave is greater than the second percentage, it is determined to be sleep apnea.

In each of the above implementation manners, the receiving unit 1200 and the sending unit 1300 may also be integrated into a transceiver unit, which has the functions of receiving and sending at the same time, which is not limited here.

In addition, in various embodiments, the processing unit 1100 is configured to perform processing and/or operations implemented internally by the communication device 1000 except for the actions of sending and receiving. The receiving unit 1200 is configured to perform an action of receiving, and the sending unit 1300 is configured to perform an action of sending.

Exemplarily, as an implementation, the functions of the automatic detection module 510, data collection and preprocessing module 520, feature extraction and statistics module 530 and sleep breathing function evaluation module 540 shown in Figure 5 can be integrated in the In the processing unit 1100.

Optionally, in an implementation manner, the evaluation device 500 may further include a display unit 1400, configured to display (that is, present to the user) the evaluation result.

Referring to FIG. 7, FIG. 7 is a schematic structural diagram of the evaluation device provided by the present application. As shown in FIG. 7 , the communication device 10 includes: one or more processors 11 , one or more memories 12 and one or more communication interfaces 13 . The processor 11 is used to control the communication interface 13 to send and receive signals, the memory 12 is used to store a computer program, and the processor 11 is used to call and run the computer program from the memory 12, so that the communication device 10 executes the method described in each method embodiment of the present application. Processes and/or operations performed by the evaluation device.

For example, the processor 11 may have the functions of the processing unit 1100 shown in FIG. 6 , and the communication interface 13 may have the functions of the receiving unit 1200 and/or the sending unit 1300 shown in FIG. 6 . Specifically, the processor 11 can be used to execute the processing and/or operations performed internally by the evaluation device in each method embodiment, and the communication interface 13 is used to execute the sending and/or receiving operations performed by the evaluation device in each method embodiment. action.

Exemplarily, in the method 100 shown in FIG. 1 , the processor 11 is configured to execute steps 110-140. Alternatively, in FIG. 2 , the processor 11 is used to perform steps 210 - 240 , step 260 ; the receiving unit 1200 is used to perform step 250 ; and the sending unit 1300 is used to perform step 270 . Alternatively, in FIG. 4, the processor 11 is configured to execute steps 401-411.

In addition, the communication device 10 can also include one or more memories 14, which can be used to store available signals obtained from detection scenarios, store data of the lightweight GBM model, and store intermediate processing results ,Wait.

In an implementation manner, the communication device 10 may be a smart wearable device.

In another implementation, the communication device 10 may be a chip or a chip system installed in a smart wearable device. In this implementation manner, the communication interface 13 may be an interface circuit or an input/output interface.

Wherein, the dotted box behind the device (for example, processor, memory or communication interface) in FIG. 7 indicates that there may be more than one device.

Fig. 8 is a schematic block diagram of a smart wearable device provided by the present application. Referring to FIG. 8 , the smart wearable device 30 may include a processor 310 , a memory 320 , a wireless communication module 330 , a display screen 340 , a camera 350 , an audio module 360 and a sensor module 370 , and so on. Wherein, the audio module 360 may include a speaker 360A, a receiver 360B, a microphone 360C and the like. Optionally, there may be one or more of the above-mentioned devices.

It can be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the smart wearable device 30 . In other embodiments of the present application, the smart wearable device 30 may include more or fewer components than shown in the illustration, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.

Exemplarily, the processor 310 may correspond to the processing unit 1100 in FIG. 6 , and is configured to execute the steps performed by the processing unit 1100 . Alternatively, the processor 310 has the functions of the processor 11 in FIG. 7 .

Optionally, the processor 310 may include one or more processing units, for example: the processor 310 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), Image signal processor (image signal processor, ISP), controller, memory, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The memory 320 may be used to store computer executable program codes, and the executable program codes include instructions. The processor 310 executes various functional applications and data processing of the smart wearable device 30 by executing instructions stored in the memory 320 . The internal memory 320 may include an area for storing programs and an area for storing data. Wherein, the stored program area can store an operating system, at least one application program required by a function (for example, such as a sound playing function, an image playing function, etc.) and the like. The data storage area can store data created during the use of the smart wearable device 30 (for example, audio data, phonebook, etc.) and the like. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (universal flash storage, UFS) and the like. Exemplarily, the memory 320 has the function of the memory 12 in FIG. 7 .

The wireless communication module 330 can provide wireless local area networks (wireless local area networks, WLAN) such as wireless fidelity (Wireless fidelity, Wi-Fi) networks, bluetooth (bluetooth, BT), global navigation satellites, etc. System (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 360 may be one or more devices integrating at least one communication processing module.

Exemplarily, the wireless communication module 330 may perform information exchange with other devices, modules or devices through the communication interface 13 as shown in FIG. 7 .

The display screen 340 is used for displaying images, videos, text information and the like. Exemplarily, the display screen 340 includes a display panel. The display panel can adopt liquid crystal display (liquid crystal display, LCD), organic light-emitting diode (organic light-emitting diode, OLED), active-matrix organic light-emitting diode or active-matrix organic light-emitting diode (active-matrix organic light emitting diode, AMOLED), flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light emitting diodes (quantum dot light emitting diodes, QLED), etc. Optionally, the smart wearable device 30 may include one or more display screens 340 .

Exemplarily, the display screen 340 is used to display the evaluation result of the sleep apnea function, and may also display prompt information such as the evaluation of the sleep apnea function being in progress or in a closed state.

Camera 350 for capturing still images or video. The object generates an optical image through the lens and projects it to the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other image signals. In some embodiments, the smart wearable device 30 may include one or more cameras 350 .

In addition, the smart wearable device 30 can implement audio functions through the audio module 370 , the speaker 370A, the receiver 370B, the microphone 370C, and the application processor. For example, recording etc.

In some embodiments, the audio module 370 can be set in the processor 310 , or some functional modules of the audio module 370 can be set in the processor 310 .

Exemplarily, the microphone 370C on the smart wearable device 30 is used to collect sound signals, reduce noise, and can also implement a directional recording function, etc., so as to realize the collection of sound signals in the detection scene.

The sensor module 380 may include various sensors such as a pressure sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, an ambient light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, and a bone conduction sensor. ,Wait. Some or all of these sensors can be used in the solution of the present application to assist the evaluation device in judging the detection scene and signal acquisition during sleep breathing function evaluation. In addition, the smart wearable device 30 may also include other sensors, which are not limited.

Optionally, the memory and the processor in the foregoing apparatus embodiments may be physically independent units, or the memory and the processor may also be integrated together, which is not limited herein.

In addition, the present application also provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and when the computer instructions are run on the computer, the operations performed by the evaluation device in each method embodiment of the present application are and/or processing is performed.

In addition, the present application also provides a computer program product. The computer program product includes computer program codes or instructions. When the computer program codes or instructions are run on the computer, the operations performed by the evaluation device in each method embodiment of the present application and/or or processing is performed.

In addition, the present application also provides a chip, the chip includes a processor, a memory for storing computer programs is provided independently of the chip, and the processor is used for executing the computer programs stored in the memory, so that the device installed with the chip executes Operations and/or processing performed by the evaluation device in any one method embodiment.

Further, the chip may further include a communication interface. The communication interface may be an input/output interface, or an interface circuit or the like. Further, the chip may further include the memory.

Optionally, there may be one or more processors, one or more memories, and one or more memories.

Optionally, the processor may also be a processing circuit or the like.

In addition, the present application also provides a communication device (for example, it may be a chip or a chip system), including a processor and a communication interface, the communication interface is used to receive (or be referred to as input) data and/or information, and will receive The received data and/or information are transmitted to the processor, and the processor processes the data and/or information, and the communication interface is also used to output (or be referred to as output) the data and/or processed by the processor or information, so that the operations and/or processing performed by the evaluation device in any one method embodiment are performed.

In addition, the present application also provides a communication device, including at least one processor, the at least one processor is coupled to at least one memory, and the at least one processor is configured to execute computer programs or instructions stored in the at least one memory, The communication device is made to perform the operation and/or processing performed by the evaluation device in any one method embodiment.

In addition, the present application also provides a communication device, including a processor and a memory. Optionally, a transceiver may also be included. Wherein, the memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory, and control the transceiver to send and receive signals, so that the communication device performs the operation and/or processing performed by the evaluation device in any method embodiment .

The memory in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the non-volatile memory can be read-only memory (read-only memory, ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically programmable Erases programmable read-only memory (electrically EPROM, EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available such as static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (synchlink DRAM, SLDRAM ) and direct memory bus random access memory (direct rambus RAM, DRRAM). It should be noted that the memory of the systems and methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims (20)

1. A method for evaluating sleep apnea function, comprising:

   Determine the current detection scene, the current detection scene belongs to one of the preset detection scenes, wherein the preset detection scene includes a first detection scene and a second detection scene, the first detection scene The user is wearing a smart wearable device, and the second detection scene is that the user is not wearing a smart wearable device;

   Select a detection method according to the current detection scene,

   Using the selected detection method to determine the state of the user, wherein the state of the user includes that the user is in a sleeping state, or that the user is in a non-sleeping state;

   According to the state of the user, enable or disable the evaluation of the sleep breathing function of the user,

   Wherein, the evaluation of sleep breathing function includes evaluating one or more of the following: sleep cycle stage, hypopnea, sleep apnea, and risk of snoring grade.
2. The method according to claim 1, wherein said selecting a detection method according to said current detection scene comprises:

   If the current detection scene is the first detection scene, select a first detection method, wherein the first detection method is to judge the state of the user through the smart wearable device; or,

   If the current detection scene is the second detection scene, select the second detection method, wherein the second detection method is to judge the the status of the user;

   Wherein, the status of the smart wearable device includes one or more of the following: the duration of the smart wearable device being in a static state within a specified period of time is greater than or equal to the first duration threshold, the duration of the smart wearable device being in a large motion state The duration is greater than or equal to the second duration threshold;

   The user's historical sleep information includes one or more of the following: the user's historical sleep time period, the user's preset sleep time, and the user's preset alarm clock time.
3. The method according to claim 1 or 2, wherein after starting the evaluation of the sleep breathing function of the user, the method further comprises:

   acquiring available signals in the first detection scene or the second detection scene;

   evaluating sleep breathing function of the user based on the available signals,

   Wherein, the available signals include one or more of the following:

   one or more respiratory indicators, the respiratory indicators include respiratory rate and/or respiratory wave decline;

   one or more snore indicators including snore loudness; and

   The user's action index, where the action index includes the user's action range and/or frequency of major actions.
4. The method according to claim 3, wherein the evaluating the sleep breathing function of the user according to the available signal comprises:

   The trained light-weight gradient boosting machine GBM model is used to predict the available signal, so as to evaluate the sleep breathing function of the user.
5. The method according to claim 4, characterized in that, before using the trained lightweight GBM prediction model to predict the available signal, the method further comprises:

   Obtain audio data and ultrasound data of the user;

   Preprocessing the audio data and ultrasound data, and performing feature extraction on the preprocessed audio data and ultrasound data to obtain extracted data, wherein the feature extraction process includes processing the preprocessed audio Data and ultrasound data for the extraction of raw features and the aggregation of statistical features;

   Using the extracted data, train the lightweight GBM prediction model to obtain the trained lightweight GBM prediction model.
6. The method according to claim 4 or 5, wherein said using the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user, including:

   If the snoring loudness is greater than or equal to the first loudness threshold, and the duration is greater than or equal to the first duration threshold, it is determined that the user's snoring level risk is high risk;

   If the snoring loudness is greater than or equal to the first loudness threshold and the duration is less than the first duration threshold, it is determined that the user's snoring level risk is medium risk;

   If the loudness of the snoring sound is greater than or equal to the second loudness threshold and the duration is greater than or equal to the second duration threshold, it is determined that the user's snoring level risk is low risk, wherein the second loudness threshold is smaller than the first loudness threshold a threshold, the second duration threshold is less than the first duration threshold;

   Otherwise, it is determined that the user's snoring level risk is normal.
7. The method according to any one of claims 4-6, wherein said using the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user, including :

   If the respiratory rate is greater than the first frequency and the slope is greater than the first value, it is determined that the sleep staging stage is REM sleep;

   If the breathing frequency is less than or equal to the first frequency and greater than or equal to the second frequency, it is determined that the sleep staging stage is light sleep;

   If the breathing frequency is less than or equal to the second frequency, it is determined that the sleep staging stage is deep sleep.
8. The method according to any one of claims 4-7, wherein said using the trained lightweight GBM prediction model to predict the available signal to evaluate the sleep breathing function of the user, including :

   If the decrease ratio of the amplitude of the respiratory wave is greater than the first percentage, it is judged as hypopnea;

   If the decrease ratio of the kurtosis of the respiratory wave is greater than the second percentage, it is determined to be sleep apnea.
9. A device for evaluating sleep apnea function, comprising:

   A processing unit, configured to determine a current detection scene, where the current detection scene belongs to one of preset detection scenes, wherein the preset detection scene includes a first detection scene and a second detection scene, the The first detection scene is that the user is wearing a smart wearable device, and the second detection scene is that the user is not wearing a smart wearable device;

   Selecting a detection method according to the current detection scenario;

   Using the selected detection method to determine the state of the user, wherein the state of the user includes that the user is in a sleeping state, or that the user is in a non-sleeping state;

   And, according to the state of the user, enable or disable the evaluation of the sleep breathing function of the user,

   Wherein, the evaluation of sleep breathing function includes evaluating one or more of the following: sleep cycle stage, hypopnea, sleep apnea, and risk of snoring grade.
10. The device according to claim 9, wherein the processing unit is specifically used for:

    If the current detection scene is the first detection scene, select the first detection method, wherein the first detection method is to judge the state of the user through the smart wearable device; or,

    If the current detection scene is the second detection scene, select the second detection method, wherein the second detection method is to judge the the user's status;

    Wherein, the state of the smart wearable device includes one or more of the following: the user's historical sleep time period, the user's preset sleep time, and the user's preset alarm clock time.
11. The device according to claim 9 or 10, wherein the device further comprises:

    a communication interface, configured to acquire available signals in the first detection scene or the second detection scene;

    The processing unit is further configured to evaluate the sleep breathing function of the user according to the available signal,

    Wherein, the available signals include one or more of the following:

    one or more respiratory indicators, the respiratory indicators include respiratory rate and/or respiratory wave decline;

    one or more snore indicators including snore loudness; and

    The user's action index, where the action index includes the user's action range and/or frequency of major actions.
12. The device according to claim 11, wherein the processing unit is specifically used for:

    The trained light GBM model is used to predict the available signals, so as to evaluate the sleep breathing function of the user.
13. The device according to claim 12, wherein the communication interface is also used for:

    Obtain audio data and ultrasound data of the user;

    And, the processing unit is also used for:

    Preprocessing the audio data and ultrasound data, and performing feature extraction on the preprocessed audio data and ultrasound data to obtain extracted data, wherein the feature extraction process includes processing the preprocessed audio Data and ultrasound data for the extraction of raw features and the aggregation of statistical features;

    Using the extracted data, train the lightweight GBM prediction model to obtain the trained lightweight GBM prediction model.
14. The device according to claim 12 or 13, wherein the processing unit is specifically used for:

    If the snoring loudness is greater than or equal to the first loudness threshold, and the duration is greater than or equal to the first duration threshold, it is determined that the user's snoring level risk is high risk;

    If the loudness of the snoring sound is greater than or equal to the first loudness threshold and the duration is less than the first duration threshold, it is determined that the user's snoring level risk is medium risk;

    If the loudness of the snoring sound is greater than or equal to the second loudness threshold and the duration is greater than or equal to the second duration threshold, it is determined that the user's snoring level risk is low risk, wherein the second loudness threshold is smaller than the first loudness threshold a threshold, the second duration threshold is less than the first duration threshold;

    Otherwise, it is determined that the user's snoring level risk is normal.
15. The device according to any one of claims 12-14, wherein the processing unit is specifically configured to:

    If the respiratory rate is greater than the first frequency and the slope is greater than the first value, it is determined that the sleep staging stage is REM sleep;

    If the breathing frequency is less than or equal to the first frequency and greater than or equal to the second frequency, it is determined that the sleep staging stage is light sleep;

    If the breathing frequency is less than or equal to the second frequency, it is determined that the sleep staging stage is deep sleep.
16. The device according to any one of claims 12-15, wherein the processing unit is specifically configured to:

    If the decrease ratio of the amplitude of the respiratory wave is greater than the first percentage, it is judged as hypopnea;

    If the decrease ratio of the kurtosis of the respiratory wave is greater than the second percentage, it is determined to be sleep apnea.
17. A communication device, characterized in that it includes at least one processor, the at least one processor is coupled to at least one memory, and the at least one processor is configured to execute a computer program or instructions stored in the at least one memory, so that The communication device executes the method according to any one of claims 1-8.
18. A chip, characterized in that it includes a processor and a communication interface, the communication interface is used to receive data and/or information, and transmit the received data and/or information to the processor, and the processor processes Said data and/or information to perform the method according to any one of claims 1-8.
19. A computer-readable storage medium, characterized in that computer instructions are stored in the computer-readable storage medium, and when the computer instructions are run on a computer, the method according to any one of claims 1-8 is executed accomplish.
20. A computer program product, characterized in that the computer program product includes computer program code, and when the computer program code is run on a computer, the method according to any one of claims 1-8 is implemented.

Images