Sleep monitoring method, earphone, earphone control method, and terminal device

Abstract

The present application relates to a sleep monitoring method, an earphone, an earphone control method, and a terminal device. The sleep monitoring method is applied to an earphone, and the earphone comprises a bone voiceprint sensor and a vibration motor. The sleep monitoring method comprises: detecting a sleep state of a target object, wherein the sleep state comprises a non-asleep state and an asleep state; when it is detected that the target object is in the asleep state, determining, on the basis of bone conduction data picked up by the bone voiceprint sensor, whether a breathing state of the target object meets a sleep breathing early warning condition; and if yes, controlling the vibration motor to vibrate, to perform sleep breathing risk early warning. By means of the method, the timeliness of sleep breathing risk early warning can be improved.

Description

Sleep monitoring methods, headphones, headphone control methods, and terminal devices

[0001] Related applications

[0002] This application claims priority to Chinese patent application filed on December 13, 2024, with application number 202411848189X, entitled "Sleep Monitoring Method, Headphones, Headphone Control Method and Terminal Device", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of sound processing technology, and in particular to a sleep monitoring method, headphones, headphone control method, and terminal device. Background Technology

[0004] With the development of sound processing technology, sleep monitoring technology has emerged, which can be used to monitor the sleep quality of a target subject. In traditional technology, devices such as smartwatches or smart bracelets are typically used to monitor the target user's vital signs data, and then sleep breathing detection is performed based on the vital signs data.

[0005] However, on the one hand, after a target subject experiences sleep apnea risk, it takes a period of time for the results to be reflected in the vital signs data. The vital signs data cannot reflect the target subject's breathing status in real time, resulting in poor real-time performance of sleep monitoring. This makes it impossible to promptly alert users to the existence of sleep apnea risk. Summary of the Invention

[0006] Therefore, it is necessary to provide a sleep monitoring method, headphones, headphone control method, and terminal device that can improve the timeliness of sleep apnea risk warning in response to the above-mentioned technical problems.

[0007] In a first aspect, this application provides a sleep monitoring method applied to headphones, the headphones including a bone conduction sensor and a vibration motor; the method includes:

[0008] Detect the sleep state of the target object; the sleep state includes the state of not falling asleep and the state of falling asleep.

[0009] When the target object is detected to be in the sleep state, the bone conduction data picked up by the bone voiceprint sensor is used to confirm whether the target object's breathing state meets the sleep breathing warning conditions.

[0010] If the breathing state of the target object meets the conditions for sleep apnea warning, the vibration motor is controlled to vibrate in order to provide a sleep apnea risk warning.

[0011] In the aforementioned sleep monitoring method, a bone conduction sensor and a vibration motor are installed on the headphones. Once the target is detected to be asleep, the bone conduction sensor can capture bone conduction data. This data is then used to determine if the target's breathing status meets the sleep apnea warning criteria. Because bone conduction data provides real-time feedback on the target's breathing status without delay, the real-time performance of sleep monitoring is improved. Furthermore, if the target's breathing status meets the sleep apnea warning criteria, the vibration motor is activated to promptly alert the user to the sleep apnea risk, thus improving the timeliness of sleep apnea risk warnings.

[0012] Secondly, this application also provides a headphone control method, applied to a terminal device, the method comprising:

[0013] Displays noise reduction control interfaces for multiple sleep noise source types;

[0014] In response to noise reduction enable or disable operations for multiple sleep noise source types on the noise reduction control interface, an active noise reduction control signal is generated.

[0015] The active noise cancellation control signal is sent to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter sleep noise cancellation mode.

[0016] In the aforementioned headphone control method, the terminal device can display a noise cancellation control interface for multiple sleep noise source types. The target user can then select to enable or disable noise cancellation for these multiple sleep noise source types on the noise cancellation control interface. Based on this, the terminal device can generate an active noise cancellation control signal to control the headphones in sleep noise cancellation mode. Thus, the target user in this application can autonomously choose which types of noise to filter and which types to retain during sleep, achieving personalized noise cancellation for sleep scenarios and resulting in better noise cancellation performance.

[0017] Thirdly, this application also provides an earphone, including a memory, a processor, a microphone, and a bone conduction sensor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0018] The sleep state of the target object is detected; the sleep state includes the state of not falling asleep and the state of falling asleep; when the target object is detected to be in the state of falling asleep, the breathing state of the target object is confirmed to meet the conditions for sleep apnea warning based on the bone conduction data picked up by the bone voiceprint sensor; if the breathing state of the target object meets the conditions for sleep apnea warning, the vibration motor is controlled to vibrate to provide a sleep apnea risk warning.

[0019] Fourthly, this application also provides a terminal device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0020] A noise cancellation control interface is displayed for multiple sleep noise source types; in response to noise cancellation enabling or disabling operations for multiple sleep noise source types on the noise cancellation control interface, an active noise cancellation control signal is generated; the active noise cancellation control signal is sent to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter sleep noise cancellation mode. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the disclosed drawings without creative effort.

[0022] Figure 1 is a flowchart illustrating a sleep monitoring method in one embodiment of this application;

[0023] Figure 2 is a flowchart illustrating the process of confirming whether the breathing state of the target object meets the sleep breathing early warning conditions in one embodiment of this application;

[0024] Figure 3 is a schematic diagram of the process for detecting respiratory distress in a target object in one embodiment of this application;

[0025] Figure 4 is a flowchart illustrating the headphone control method in one embodiment of this application;

[0026] Figure 5 is a structural block diagram of a sleep monitoring device in one embodiment of this application;

[0027] Figure 6 is a structural block diagram of an earphone control device in one embodiment of this application;

[0028] Figure 7 is an internal structural diagram of the earphone in one embodiment of this application;

[0029] Figure 8 is an internal structure diagram of a terminal device in one embodiment of this application. Detailed Implementation

[0030] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] In an exemplary embodiment, as shown in FIG1, a sleep monitoring method is provided, which is applied to headphones, the headphones including a bone conduction sensor and a vibration motor, and includes the following steps 202 to 206. Wherein:

[0032] Step 202: Detect the sleep state of the target object; the sleep state includes the state of not falling asleep and the state of falling asleep.

[0033] As an example, one can acquire the vital signs of a target object and, based on those signs, detect the target object's sleep state, i.e., whether it has fallen asleep.

[0034] The aforementioned headphones can be wireless Bluetooth headphones or wired headphones; the type of headphones is not limited in this embodiment.

[0035] Step 204: When the target object is detected to be asleep, the respiratory status of the target object is confirmed to meet the sleep apnea warning conditions based on the bone conduction data picked up by the bone voiceprint sensor.

[0036] Among these risks, when the target is asleep, the target will make breathing sounds, and may even snore; the target may be at risk of sleep apnea when falling asleep, thus posing a sleep risk.

[0037] It should be noted that snoring is usually produced by vibrations in the upper respiratory tract, which can be easily captured by bone conduction sensors to form bone conduction data. Based on this, bone conduction data can clearly characterize the vibrational features of snoring, such as amplitude, frequency, and time.

[0038] As an example, step 204 includes: when the target object is detected to be asleep, converting the bone conduction data from the time domain to the frequency domain to obtain bone conduction frequency domain data; extracting features from the bone conduction frequency domain data to obtain the first snoring feature of the target object; detecting whether the target object has a risk of sleep apnea based on the first snoring feature; if the target object has a risk of sleep apnea, confirming that the target object's breathing state meets the sleep apnea warning conditions; if the target object does not have a risk of sleep apnea, confirming that the target object's breathing state does not meet the sleep apnea warning conditions.

[0039] Step 206: If the target's breathing state meets the sleep apnea warning conditions, then control the vibration motor to vibrate in order to provide a sleep apnea risk warning.

[0040] The earphones are equipped with a vibration motor. When the target's breathing state meets the conditions for sleep apnea warning, a motor control signal is generated. The motor control signal is used to control the vibration motor to vibrate, so as to warn the target of sleep apnea risk and indicate that the target needs to change sleeping position or wear a CPAP machine.

[0041] It should be noted that when the target's breathing state meets the conditions for sleep apnea warning, the headphones can push sleep apnea risk information to the terminal device to alert the user to the existence of breathing risks. In this way, the target can be aware of their own sleep apnea risks in a timely manner and should seek medical attention promptly.

[0042] In the above embodiments, a bone conduction sensor and a vibration motor are installed on the headphones. After detecting that the target is asleep, the bone conduction sensor can pick up the target's bone conduction data. Based on the bone conduction data, it can be determined whether the target's breathing status meets the sleep apnea warning conditions. Since the bone conduction data can provide real-time feedback on the target's breathing status without delay, the real-time performance of sleep monitoring can be improved. Furthermore, if the target's breathing status meets the sleep apnea warning conditions, the vibration motor is controlled to vibrate, which can promptly provide the user with a sleep apnea risk warning, thus improving the timeliness of sleep apnea risk warnings.

[0043] In some embodiments, the headphones further include a microphone, and after detecting the sleep state of the target object, the sleep monitoring method further includes:

[0044] When the target is detected to be awake, the system detects whether there is sleep disturbance noise in the external environment based on the ambient sound data picked up by the microphone. If there is sleep disturbance noise in the external environment, the system controls the headphones to actively reduce noise from the external sound signals. If there is no sleep disturbance noise in the external environment, the system controls the headphones to play sleep-aiding audio.

[0045] Sleep disturbance noise refers to noise that interferes with the target's ability to fall asleep, such as a partner's snoring, construction noise, or a child's crying; sleep aid sound sources refer to sound sources that help the target fall asleep, such as alpha waves, white noise, pink noise, slow-paced music, or ambient audio.

[0046] Specifically, when the target is detected to be awake, the ambient audio features of the ambient sound data picked up by the microphone in each preset frequency band are extracted. By classifying the ambient audio features of each preset frequency band, the presence of sleep disturbance noise in the external environment is detected. If sleep disturbance noise exists in the external environment, the headphones are controlled to enter active noise cancellation mode. This allows the headphones to play a masked sound source corresponding to the sleep disturbance noise, thereby actively reducing noise in the external sound signal. The masked sound source can be the inverse sound signal corresponding to the sleep disturbance noise. If there is no sleep disturbance noise in the external environment, the headphones are controlled to play a sleep aid sound source.

[0047] In this embodiment, when the target is not asleep, the headphones can automatically identify whether there is sleep disturbance noise in the external environment. If sleep disturbance noise exists, the headphones will actively cancel the sleep disturbance noise that the target can hear. If there is no sleep disturbance noise, the headphones will play sleep aid sound sources. This can achieve intelligent selection of ways to help the target fall asleep according to different external environments, thus improving the success rate of helping the target fall asleep quickly.

[0048] In one embodiment, referring to FIG2, the headphones further include a microphone; the step of confirming whether the breathing state of the target object meets the sleep apnea warning conditions based on the bone conduction data picked up by the bone conduction sensor includes:

[0049] Step 302: Based on the bone conduction data picked up by the bone voiceprint sensor, the target object is subjected to apnea state detection to obtain the first state detection result.

[0050] As an example, step 302 includes: converting bone conduction data from the time domain to the frequency domain to obtain bone conduction frequency domain data; extracting features from the bone conduction frequency domain data to obtain the first snoring feature of the target object; and detecting the apnea state of the target object based on the first snoring feature to obtain the first state detection result.

[0051] As an example, based on the first snoring sound characteristic, the apnea state of the target object is detected, and the first state detection result is obtained, including:

[0052] According to the preset apnea detection model, the first snoring feature is mapped to the corresponding apnea risk level, and the apnea risk level is used as the first state detection result. The apnea risk level is used to characterize the apnea state of the target object, that is, to characterize the risk or probability of the target object experiencing apnea.

[0053] It should be noted that the aforementioned first snoring feature can characterize the duration, amplitude, and interval of snoring when the target is asleep. Therefore, the first snoring feature can be used to detect the target's sleep apnea state. For example, if the first snoring feature indicates that the target has snoring for more than 10 seconds, it can be considered that the target has sleep apnea. The first state detection result is that there is sleep apnea, or in other words, there is a risk of sleep apnea.

[0054] Step 304: Based on bone conduction data and ambient sound data picked up by the microphone, detect the breathing difficulties of the target object to obtain the second state detection result.

[0055] In addition to the risk of sleep apnea, the target individuals may also face the risk of breathing difficulties due to their sleeping posture. For example, poor sleeping posture may cause the target individual's mouth and nose to be covered by a pillow or blanket, leading to breathing difficulties. If the target individual's breathing condition is already poor, breathing difficulties may also trigger the risk of sleep apnea.

[0056] It should be noted that snoring is usually produced by vibrations in the upper respiratory tract. These vibrations are easily captured by bone conduction sensors, forming bone conduction data. In addition, snoring also transmits sound signals to the outside world, which are picked up by microphones. Similarly, the vibrations caused by breathing sound signals are smaller. Compared to bone conduction data, breathing sound signals are easier for microphones to pick up, forming environmental sound signals together with snoring. Therefore, the environmental sound data picked up by the microphone will include various sound signals such as snoring sound signals, breathing sound signals, and external noise signals. Among them, external noise signals can include car horn sounds, air conditioning sounds, and other people's voices.

[0057] As an example, step 304 includes: converting bone conduction data from the time domain to the frequency domain to obtain bone conduction frequency domain data; converting ambient sound data from the time domain to the frequency domain to obtain acoustic frequency domain data; extracting features from the bone conduction frequency domain data to obtain the first snoring feature of the target object; extracting features from the acoustic frequency domain data to obtain acoustic frequency domain features; and detecting the breathing disorder state of the target object based on the acoustic frequency domain features and the first snoring feature to obtain the second state detection result.

[0058] As an example, based on the acoustic frequency domain features and the first snoring feature, the breathing disorder state of the target object is detected, and the second state detection result is obtained, including:

[0059] The sound frequency domain features are denoised to obtain the denoised sound frequency domain features; the denoised sound frequency domain features are fused with the first snoring sound features to obtain the target fused features; according to the preset breathing difficulty detection model, the target fused features are converted into a breathing difficulty risk level, and the breathing difficulty risk level is used as the second state detection result. The breathing difficulty risk level is used to characterize the breathing difficulty state of the target object, that is, to characterize the risk or probability of the target object experiencing breathing difficulty.

[0060] Step 306: Based on the first state detection result and / or the second state detection result, confirm whether the target's breathing state meets the sleep apnea warning conditions.

[0061] As an example, step 306 includes: if the risk level of sleep apnea is greater than the first preset risk level, or the risk level of breathing difficulties is greater than the second preset risk level, then confirm that the breathing state of the target subject meets the sleep apnea warning conditions; if the risk level of sleep apnea is not greater than the first preset risk level, and the risk level of breathing difficulties is not greater than the second preset risk level, then confirm that the breathing state of the target subject does not meet the sleep apnea warning conditions.

[0062] In the aforementioned sleep monitoring method, a microphone and a bone conduction sensor are installed on the headphones. After detecting that the target is asleep, the microphone can capture ambient sound data, and the bone conduction sensor can capture bone conduction data. Based on the bone conduction data, the target's apnea state is checked, yielding a first-state detection result. Then, based on the bone conduction and ambient sound data, the target's breathing difficulties are detected, yielding a second-state detection result. Finally, based on the first and second-state detection results, it can be confirmed whether the target's breathing state meets the sleep apnea warning conditions. This approach improves the real-time performance of sleep apnea detection because both bone conduction and ambient sound data provide real-time feedback on the target's breathing state without delay. Furthermore, this embodiment utilizes two dimensions of data—bone conduction and ambient sound—for sleep apnea detection, providing a richer data dimension and thus improving accuracy. Therefore, this embodiment enhances both the real-time performance and accuracy of sleep apnea detection.

[0063] In an exemplary embodiment, as shown in Figure 3, the detection of breathing difficulties in a target object is performed based on bone conduction data and ambient sound data picked up by a microphone, including:

[0064] Step 402: Extract snoring features from bone conduction data to obtain the first snoring feature of the target object.

[0065] As an example, step 402 includes: converting bone conduction data from the time domain to the frequency domain to obtain bone conduction frequency domain data; extracting frequency domain features from the bone conduction frequency domain data to obtain the first snoring feature of the target object, wherein the frequency domain feature can be a feature that characterizes the amplitude of snoring as a function of frequency.

[0066] Step 404: Extract features from the environmental sound data to obtain the target sound features.

[0067] As an example, step 404 includes: converting the ambient sound data from the time domain to the frequency domain to obtain audio-visual domain data; extracting frequency domain features from the audio-visual domain features to obtain target sound features, wherein the frequency domain features can be features that characterize the amplitude of the sound picked up by the microphone as a function of frequency.

[0068] Step 406: Generate the breathing sound features of the target object based on the target sound features and the first snoring sound features.

[0069] As an example, step 406 includes: weighted fusion of the target sound features and the first snoring features to obtain the breathing sound features of the target object. In this way, the breathing sound features include both the bone conduction voiceprint features corresponding to the snoring and the breathing sound features picked up by the microphone, which has richer feature dimensions and helps to improve the accuracy of sleep breathing detection.

[0070] As an example, based on the target sound features and snoring features, the breathing sound features of the target object are generated, including:

[0071] The first snoring feature is converted from bone voiceprint feature to sound feature to obtain the second snoring feature; the target sound feature and the second snoring feature are differentially processed to obtain the breathing sound feature of the target object.

[0072] Specifically, the first snoring feature is converted from bone conduction voiceprint features to audio frequency domain features, resulting in the second snoring feature. The target sound feature is then denoised to obtain the denoised target sound feature. Finally, the denoised target sound feature and the second snoring feature are differentially processed to obtain the target subject's breathing sound feature. This process removes the audio frequency features of the target subject's snoring from the sound signal picked up by the microphone, making the final breathing sound feature purer and more accurate, thus improving the accuracy of simultaneous sleep apnea detection.

[0073] Step 408: Detect breathing difficulties in the target object based on the characteristics of breathing sounds.

[0074] As an example, step 408 includes: converting breathing sound features into a breathing difficulty risk level according to a preset breathing difficulty detection model, wherein the breathing difficulty risk level is used to characterize the breathing difficulty state of the target object, that is, to characterize the risk or probability of the target object experiencing breathing difficulty.

[0075] As an example, the headphones include a vital signs sensor that detects breathing difficulties in a target subject based on the characteristics of breathing sounds, including:

[0076] The system acquires the vital signs signals of the target object picked up by the vital signs signal sensor and extracts the corresponding vital signs signal features; based on the vital signs signal features and breathing sound features, it detects the target object's breathing difficulties.

[0077] Among them, vital signs signals can be electrocardiogram variability signals, blood oxygen saturation signals, heart rate variability signals, and body motion signals, etc., and the vital signs signal sensors can be PPG (Photoplethysmography) sensors and gyroscopes, etc.

[0078] Specifically, the system acquires the vital signs signals of the target object using a vital signs signal sensor, and transforms these signals from the time domain to the frequency domain to obtain the vital signs frequency domain signal. Frequency domain features are extracted from the vital signs frequency domain signal to obtain vital signs signal features. These features are then fused with respiratory sound features to obtain vital signs sound fusion features. Based on a pre-defined respiratory distress detection model, the vital signs sound fusion features are converted into a respiratory distress risk level. This approach combines three dimensions of signal data—vital signs, bone conduction data, and environmental sound data picked up by a microphone—to detect the respiratory status of the target object. The detection criteria are richer and more reliable, improving the accuracy of respiratory status detection.

[0079] In the above embodiments, the bone conduction data picked up by the bone conduction sensor and the ambient sound data picked up by the microphone can be combined to detect the breathing difficulties. This realizes the detection of the breathing difficulties from two dimensions: bone conduction vibration and sound. The detection basis is richer and more reliable, which can improve the accuracy of the breathing difficulties detection.

[0080] In an exemplary embodiment, the first state detection result includes a sleep apnea risk level, and the second state detection result includes a breathing difficulty risk level; based on the first state detection result and / or the second state detection result, confirming whether the target's breathing state meets the sleep apnea warning conditions includes:

[0081] If the risk level of sleep apnea is greater than a first preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the risk level of breathing difficulties is greater than a second preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the risk level of sleep apnea is not greater than the first preset risk level and the risk level of breathing difficulties is not greater than the second preset risk level, the risk levels of sleep apnea and breathing difficulties are weighted and fused to obtain a target risk level; if the target risk level is greater than a third preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the target risk level is not greater than the third preset risk level, the breathing state of the target subject is determined not to meet the sleep apnea warning conditions.

[0082] Specifically, when the risk level of apnea is greater than the first preset risk level, the target subject is considered to have a high risk of apnea, and therefore the target subject's breathing state is determined to meet the sleep apnea warning conditions. When the risk level of breathing difficulties is greater than the second preset risk level, the target subject is considered to have a high risk of breathing difficulties, and therefore the target subject's breathing state is determined to meet the sleep apnea warning conditions. When the risk level of apnea is not greater than the first preset risk level and the risk level of breathing difficulties is not greater than the second preset risk level, the apnea risk level and the breathing difficulties risk level are weighted and summed according to the first preset weight corresponding to the apnea risk level and the second preset weight corresponding to the breathing difficulties risk level to obtain the target risk level, wherein the sum of the first preset weight and the second preset weight is greater than 1. When the target risk level is greater than the third preset risk level, the target subject's breathing state is determined to meet the sleep apnea warning conditions. When the target risk level is not greater than the third preset risk level, the target subject's breathing state is determined to not meet the sleep apnea warning conditions.

[0083] In this embodiment, the respiratory status of the target subject is assessed from two aspects: apnea and dyspnea, to determine whether it meets the conditions for sleep apnea warning. The dimensions of respiratory status assessment are richer, thus improving the accuracy of assessing whether the respiratory status of the target subject meets the conditions for sleep apnea warning.

[0084] In one exemplary embodiment, the sleep monitoring method further includes:

[0085] The system detects the number and frequency of sleep apnea risk events when the target subject is asleep. Specifically, when the target subject's breathing state meets the early warning conditions for sleep apnea, a sleep apnea risk event is determined to have occurred. Based on the number and frequency of events, sleep apnea risk information is pushed to the terminal device.

[0086] Specifically, the system detects the number of sleep-related breathing risk events and their frequency within a sleep period for a target individual. The number of events is the cumulative number of times the target individual's breathing status meets the sleep-related breathing warning criteria within a sleep period. The event frequency is the cumulative number of times the target individual's breathing status meets the sleep-related breathing warning criteria within a preset time period within a sleep period. The preset time period can be every hour or every half hour, etc. If the number of events exceeds a preset threshold or the event frequency exceeds a preset frequency threshold, sleep-related breathing risk information is pushed to the terminal device. This sleep-related breathing risk information is used to indicate that the target individual has a high risk of sleep-related breathing. A sleep period can be the target individual's nighttime sleep period or afternoon nap period, etc.

[0087] In this embodiment, the number of sleep breathing risk events and the frequency of occurrence of time events for the target object during a certain period are recorded. Then, based on the number of occurrences and the frequency of occurrence of sleep breathing risk events, the level of sleep breathing risk of the target object during a certain sleep period can be analyzed. When the sleep breathing risk is high, an early warning is issued to avoid causing danger.

[0088] In one exemplary embodiment, the sleep monitoring method further includes:

[0089] The system acquires an active noise cancellation control signal sent by a terminal device. The terminal device displays a noise cancellation control interface for multiple sleep noise source types and generates an active noise cancellation control signal in response to noise cancellation enable or disable operations for multiple sleep noise source types on the noise cancellation control interface. Based on the active noise cancellation control signal, the system controls the headphones to enter sleep noise cancellation mode.

[0090] It should be noted that in this embodiment, the headphones can communicate with a terminal device. The terminal device can display a noise cancellation control interface for multiple sleep noise source types. This noise cancellation control interface includes multiple on / off buttons for sleep noise source types. In response to the on / off noise cancellation operation for multiple sleep noise source types on the noise cancellation control interface, an active noise cancellation control signal is generated. The noise cancellation on operation can be a click operation of the on button, and the noise cancellation off operation can be a click operation of the off button. According to the active noise cancellation control signal, the headphones are controlled to enter sleep noise cancellation mode. When the headphones are in sleep noise cancellation mode, noise from sleep noise source types with noise cancellation on will be filtered by the headphones' active noise cancellation function, while noise from sleep noise source types with noise cancellation off will not be filtered by the headphones' active noise cancellation function.

[0091] In this embodiment, the target user can choose which types of noise to filter and which types of noise to retain during sleep, thus enabling personalized noise reduction for sleep scenarios through the headphones, resulting in better noise reduction performance for sleep scenarios.

[0092] In an exemplary embodiment, as shown in FIG4, a headphone control method is provided, applied to a terminal device, the headphone control method comprising:

[0093] Step 502 displays the noise reduction control interface for multiple sleep noise source types.

[0094] Step 504: In response to noise reduction enable or disable operations for multiple sleep noise source types on the noise reduction control interface, generate an active noise reduction control signal.

[0095] Step 506: Send an active noise cancellation control signal to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter sleep noise cancellation mode.

[0096] As an example, steps 502 to 506 include: the terminal device displaying a noise cancellation control interface for multiple sleep noise source types, the noise cancellation control interface including multiple on / off buttons for sleep noise source types; in response to the noise cancellation on / off operation for multiple sleep noise source types on the noise cancellation control interface, generating an active noise cancellation control signal, wherein the noise cancellation on operation can be a click operation of clicking the on button, and the noise cancellation off operation can be a click operation of clicking the off button; according to the active noise cancellation control signal, controlling the headphones to enter sleep noise cancellation mode, wherein after the headphones are in sleep noise cancellation mode, noise from sleep noise source types with noise cancellation on will be filtered by the headphones' active noise cancellation function, and noise from sleep noise source types with noise cancellation off will not be filtered by the headphones' active noise cancellation function.

[0097] In this embodiment, the terminal device can display a noise reduction control interface for multiple sleep noise source types. The target user can then select to enable or disable noise reduction for these multiple sleep noise source types on the noise reduction control interface. Based on this, the terminal device can generate an active noise reduction control signal to control the headphones in sleep noise reduction mode. Thus, the target user can autonomously choose which types of noise to filter and which types to retain during sleep, achieving personalized noise reduction control for sleep scenarios and resulting in better noise reduction performance for the headphones.

[0098] In one exemplary embodiment, the above-described headphone control method further includes:

[0099] The system acquires the target user's sleep noise habit information, which represents the target user's habit of turning on or off the noise cancellation button for each type of sleep noise source. It also acquires historical ambient sound data picked up by the microphone when the target user is asleep. Based on the historical ambient sound data and sleep noise habit information, it detects the target sleep aid sound source type that is suitable for the target user. Based on the target sleep aid sound source type, it controls the headphones to play the corresponding sleep aid sound source.

[0100] Among them, there are usually a variety of sleep-aid sound sources for headphones, such as white noise, pink noise, slow-paced music, and ambient audio.

[0101] Specifically, the process involves acquiring the sleep noise habit information of the target subject, which represents the target subject's habit of turning on or off noise cancellation buttons for various sleep noise source types; generating sleep noise habit features based on the sleep noise habit information; acquiring historical environmental sound data picked up by the microphone while the target subject is asleep, and converting the historical environmental sound data from the time domain to the frequency domain to obtain historical breathing sound audio domain data; extracting frequency domain features from the historical breathing sound audio domain data to obtain historical breathing sound audio domain features; fusing the sleep noise habit features and the historical breathing sound audio domain features to obtain fused features; inputting the fused features into a preset classifier to output a target sleep aid sound source type identifier suitable for the target subject; and controlling the headphones to play the sleep aid sound source corresponding to the target sleep aid sound source type identifier.

[0102] In this embodiment, the sleep noise habit information and historical environmental sound data of the target object are first obtained. Based on the sleep noise habit information and historical environmental sound data, the target sleep aid sound source type suitable for the target object is detected. This realizes the detection of the target sleep aid sound source type suitable for the target object from two dimensions: the sleep noise habit and breathing pattern of the target object. The detection basis is rich and reliable, and the detection accuracy of the target sleep aid sound source type suitable for the target object is higher, which helps to indicate the sleep aid effect of the headphones playing sleep aid sound sources.

[0103] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0104] Based on the same inventive concept, this application also provides a sleep monitoring device for implementing the sleep monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more sleep monitoring device embodiments provided below can be found in the limitations of the sleep monitoring method described above, and will not be repeated here.

[0105] In an exemplary embodiment, as shown in FIG5, a sleep monitoring device is provided for use with headphones. The headphones include a bone conduction sensor and a vibration motor. The sleep monitoring device includes: a detection module 602, a confirmation module 604, and an alarm module 606, wherein:

[0106] The detection module 602 is used to detect the sleep state of the target object; the sleep state includes the state of not falling asleep and the state of falling asleep.

[0107] The confirmation module 604 is used to confirm whether the breathing state of the target object meets the sleep breathing warning conditions based on the bone conduction data picked up by the bone voiceprint sensor when the target object is detected to be in the sleep state.

[0108] The early warning module 606 is used to control the vibration motor to vibrate if the breathing state of the target object meets the early warning conditions for sleep apnea, so as to provide an early warning of sleep apnea risk.

[0109] In one embodiment, the earphone further includes a microphone; the confirmation module is also used for:

[0110] Based on the bone conduction data picked up by the bone conduction sensor, the target object is subjected to sleep apnea detection to obtain a first state detection result; based on the bone conduction data and the ambient sound data picked up by the microphone, the target object is subjected to breathing difficulties detection to obtain a second state detection result; based on the first state detection result and / or the second state detection result, it is confirmed whether the breathing state of the target object meets the sleep apnea warning conditions.

[0111] In one embodiment, the confirmation module is further configured to:

[0112] The bone conduction data is used to extract snoring features to obtain the first snoring feature of the target object; the environmental sound data is used to extract features to obtain the target sound feature; the target sound feature and the first snoring feature are used to generate the breathing sound feature of the target object; and the breathing sound feature is used to detect the breathing difficulties of the target object.

[0113] In one embodiment, the confirmation module is further configured to:

[0114] The first snoring feature is converted from bone voiceprint feature to sound feature to obtain the second snoring feature; the target sound feature and the second snoring feature are differentially processed to obtain the breathing sound feature of the target object.

[0115] In one embodiment, the earphone includes a vital sign sensor; the confirmation module is further configured to:

[0116] The system acquires the vital signs signals of the target object picked up by the vital signs signal sensor and extracts the vital signs signal features corresponding to the vital signs signals; based on the vital signs signal features and the breathing sound features, it detects the breathing difficulties of the target object.

[0117] In one embodiment, the first state detection result includes a sleep apnea risk level, and the second state detection result includes a breathing difficulty risk level; the confirmation module is further configured to:

[0118] If the risk level of sleep apnea is greater than a first preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the risk level of breathing difficulties is greater than a second preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the risk level of sleep apnea is not greater than the first preset risk level and the risk level of breathing difficulties is not greater than the second preset risk level, the risk levels of sleep apnea and breathing difficulties are weighted and fused to obtain a target risk level; if the target risk level is greater than a third preset risk level, the breathing state of the target subject is determined to meet the sleep apnea warning conditions; if the target risk level is not greater than the third preset risk level, the breathing state of the target subject is determined not to meet the sleep apnea warning conditions.

[0119] In one embodiment, the sleep monitoring device further includes:

[0120] The risk information push module is used to detect the number of occurrences and frequency of sleep apnea risk events when the target object is asleep. Specifically, when it is confirmed that the breathing state of the target object meets the sleep apnea warning conditions, it is determined that the target object has experienced a sleep apnea risk event; and sleep apnea risk information is pushed to the terminal device based on the number of occurrences and the frequency of occurrences.

[0121] In one embodiment, the sleep monitoring device further includes:

[0122] The sleep aid module is used to detect whether there is sleep disturbance noise in the external environment based on the ambient sound data picked up by the microphone when the target object is detected to be in an awake state; if there is sleep disturbance noise in the external environment, the module controls the headphones to actively reduce noise of the external sound signals; if there is no sleep disturbance noise in the external environment, the module controls the headphones to play sleep aid sound sources.

[0123] In one embodiment, the sleep monitoring device further includes:

[0124] The noise cancellation control module is used to acquire the active noise cancellation control signal sent by the terminal device. The terminal device is used to display a noise cancellation control interface for multiple sleep noise source types, and generate the active noise cancellation control signal in response to the noise cancellation on or off operation for the multiple sleep noise source types on the noise cancellation control interface. According to the active noise cancellation control signal, the device controls the headphones to enter the sleep noise cancellation mode.

[0125] The modules in the aforementioned sleep monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor within the earphone in hardware form or stored in the earphone's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0126] Based on the same inventive concept, this application also provides an earphone control device for implementing the earphone control method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more earphone control device embodiments provided below can be found in the limitations of the earphone control method described above, and will not be repeated here.

[0127] In an exemplary embodiment, as shown in FIG6, a headphone control device is provided, applied to a terminal device. The headphone control device includes: a display module 702, a signal generation module 704, and a signal transmission module 706, wherein:

[0128] Display module 702 is used to display the noise reduction control interface for multiple sleep noise source types.

[0129] The signal generation module 704 is used to generate an active noise reduction control signal in response to the noise reduction control interface for noise reduction on or off operations for multiple sleep noise source types.

[0130] The signal transmitting module 706 is used to send the active noise cancellation control signal to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter the sleep noise cancellation mode.

[0131] In one embodiment, the headphone control device further includes:

[0132] The sleep aid control module is used to acquire sleep noise habit information of the target object, wherein the sleep noise habit information represents the target object's habit of turning on or off the noise cancellation button for each of the sleep noise sound source types; acquire historical ambient sound data picked up by the microphone of the target object when it is asleep; detect the target sleep aid sound source type suitable for the target object based on the historical ambient sound data and the sleep noise habit information; and control the headphones to play the corresponding sleep aid sound source based on the target sleep aid sound source type.

[0133] Each module in the aforementioned headphone control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor within the headphone in hardware form or independent of it, or stored in the headphone's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0134] In an exemplary embodiment, an earphone is provided, the internal structure of which can be shown in Figure 7. The earphone includes a bone conduction sensor, a vibration motor, a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The earphone's processor provides computing and control capabilities. The earphone's memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The earphone's input / output interface is used for exchanging information between the processor and external devices. The earphone's communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a sleep monitoring method.

[0135] Those skilled in the art will understand that the structure shown in Figure 7 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the headphones to which the present application is applied. Specific headphones may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0136] In an exemplary embodiment, a terminal device is provided, the internal structure of which can be shown in Figure 8. The terminal device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the headset provides computing and control capabilities. The headset's memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The headset's input / output interface is used for exchanging information between the processor and external devices. The headset's communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a headset control method.

[0137] Those skilled in the art will understand that the structure shown in Figure 8 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the headphones to which the present application is applied. Specific headphones may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one embodiment, an earphone is also provided, including a bone conduction sensor, a vibration motor, a memory, and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described sleep monitoring method embodiment.

[0139] In one embodiment, a terminal device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described headphone control method embodiment.

[0140] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0141] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0144] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A sleep monitoring method, characterized in that, Applied to headphones, the headphones including a bone conduction sensor and a vibration motor; the method includes: Detect the sleep state of the target object; the sleep state includes the state of not falling asleep and the state of falling asleep. When the target object is detected to be in the sleep state, the bone conduction data picked up by the bone voiceprint sensor is used to confirm whether the target object's breathing state meets the sleep breathing warning conditions. If the breathing state of the target object meets the conditions for sleep apnea warning, the vibration motor is controlled to vibrate in order to provide a sleep apnea risk warning.

2. The method according to claim 1, characterized in that, The headphones also include a microphone; the step of confirming whether the target's breathing state meets the sleep apnea warning conditions based on the bone conduction data picked up by the bone conduction sensor includes: Based on the bone conduction data picked up by the bone voiceprint sensor, the target object is subjected to sleep apnea detection to obtain a first state detection result; Based on the bone conduction data and the ambient sound data picked up by the microphone, the target object is detected to have a breathing difficulty state, and a second state detection result is obtained. Based on the first state detection result and / or the second state detection result, confirm whether the breathing state of the target object meets the sleep apnea warning conditions.

3. The method according to claim 2, characterized in that, The step of detecting breathing difficulties in the target object based on the bone conduction data and the ambient sound data picked up by the microphone includes: Snoring features are extracted from the bone conduction data to obtain the first snoring feature of the target object; Feature extraction is performed on the environmental sound data to obtain the target sound features; Based on the target sound features and the first snoring feature, the breathing sound features of the target object are generated; Based on the characteristics of the breathing sounds, the target object is detected to have difficulty breathing.

4. The method according to claim 3, characterized in that, The step of generating the breathing sound features of the target object based on the target sound features and the snoring features includes: The first snoring feature is converted from bone voiceprint feature to sound feature to obtain the second snoring feature; The target sound features and the second snoring features are differentially processed to obtain the breathing sound features of the target object.

5. The method according to claim 3, characterized in that, The earphone includes a vital sign signal sensor; the step of detecting the breathing difficulties of the target object based on the breathing sound characteristics includes: Acquire the vital signs signals of the target object picked up by the vital signs signal sensor, and extract the vital signs signal features corresponding to the vital signs signals; Based on the vital signs and breathing sounds, the respiratory distress of the target object is detected.

6. The method according to claim 2, characterized in that, The first state detection result includes the risk level of sleep apnea, and the second state detection result includes the risk level of breathing difficulties; the step of confirming whether the breathing state of the target subject meets the sleep apnea warning conditions based on the first state detection result and / or the second state detection result includes: If the risk level of sleep apnea is greater than the first preset risk level, it is determined that the breathing state of the target object meets the conditions for sleep apnea warning. If the risk level of breathing difficulties is greater than the second preset risk level, it is determined that the breathing state of the target object meets the conditions for sleep apnea warning. If the risk level of sleep apnea is not greater than the first preset risk level and the risk level of breathing difficulties is not greater than the second preset risk level, the risk level of sleep apnea and the risk level of breathing difficulties are weighted and fused to obtain the target risk level. If the target risk level is greater than the third preset risk level, the respiratory state of the target object is determined to meet the sleep apnea warning conditions.

7. The method according to claim 6, characterized in that, The method further includes: The number of occurrences and frequency of sleep apnea risk events are detected when the target object is asleep. Specifically, when the breathing state of the target object meets the sleep apnea warning conditions, it is determined that the target object has experienced a sleep apnea risk event. Based on the number of times the event occurs and the frequency of the event, sleep apnea risk information is pushed to the terminal device.

8. The method according to claim 1, characterized in that, The headphones also include a microphone, and after detecting the sleep state of the target object, the method further includes: When the target is detected to be awake, the system detects whether there is sleep disturbance noise in the external environment based on the ambient sound data picked up by the microphone. If there is sleep disturbance noise in the external environment, the headphones are controlled to actively reduce noise from external sound signals; If there is no sleep-disrupting noise in the external environment, the headphones will play sleep-aiding audio.

9. The method according to claim 1, characterized in that, The method further includes: The active noise cancellation control signal sent by the terminal device is obtained, wherein the terminal device is used to display a noise cancellation control interface for multiple sleep noise source types, and generates the active noise cancellation control signal in response to the noise cancellation control interface for noise cancellation on or off for multiple sleep noise source types. Based on the active noise cancellation control signal, the headphones are controlled to enter sleep noise cancellation mode.

10. A headphone control method, characterized in that, Applied to terminal devices; the method includes: Displays noise reduction control interfaces for multiple sleep noise source types; In response to noise reduction enable or disable operations for multiple sleep noise source types on the noise reduction control interface, an active noise reduction control signal is generated. The active noise cancellation control signal is sent to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter sleep noise cancellation mode.

11. The method according to claim 10, characterized in that, The method further includes: Acquire sleep noise habit information of the target object, wherein the sleep noise habit information represents the target object's habit of turning on or off the noise reduction button for each of the sleep noise source types; The system acquires historical ambient sound data picked up by the microphone when the target object is asleep, and detects the target sleep aid sound source type suitable for the target object based on the historical ambient sound data and the sleep noise habit information. Based on the target sleep aid sound source type, control the headphones to play the corresponding sleep aid sound source.

12. A sleep monitoring device, characterized in that, Applied to headphones, the headphones include a bone conduction sensor and a vibration motor; the headphone control device includes: The detection module is used to detect the sleep state of the target object; the sleep state includes the state of not falling asleep and the state of falling asleep. The confirmation module is used to confirm whether the breathing state of the target object meets the sleep breathing warning conditions based on the bone conduction data picked up by the bone voiceprint sensor when the target object is detected to be in the sleep state. The early warning module is used to control the vibration motor to vibrate if the breathing state of the target object meets the early warning conditions for sleep apnea, so as to provide an early warning of sleep apnea risk.

13. The apparatus according to claim 12, characterized in that, The earphone also includes a microphone; the confirmation module is further used for: Based on the bone conduction data picked up by the bone voiceprint sensor, the target object is subjected to sleep apnea detection to obtain a first state detection result; Based on the bone conduction data and the ambient sound data picked up by the microphone, the target object is detected to have a breathing difficulty state, and a second state detection result is obtained. Based on the first state detection result and / or the second state detection result, confirm whether the breathing state of the target object meets the sleep apnea warning conditions.

14. The apparatus according to claim 13, characterized in that, The confirmation module is also used for: Snoring features are extracted from the bone conduction data to obtain the first snoring feature of the target object; Feature extraction is performed on the environmental sound data to obtain the target sound features; Based on the target sound features and the first snoring feature, the breathing sound features of the target object are generated; Based on the characteristics of the breathing sounds, the target object is detected to have difficulty breathing.

15. The apparatus according to claim 14, characterized in that, The confirmation module is also used for: The first snoring feature is converted from bone voiceprint feature to sound feature to obtain the second snoring feature; The target sound features and the second snoring features are differentially processed to obtain the breathing sound features of the target object.

16. The apparatus according to claim 13, characterized in that, The first state detection result includes the risk level of sleep apnea, and the second state detection result includes the risk level of shortness of breath; the confirmation module is further used for: If the risk level of sleep apnea is greater than the first preset risk level, it is determined that the breathing state of the target object meets the conditions for sleep apnea warning. If the risk level of breathing difficulties is greater than the second preset risk level, it is determined that the breathing state of the target object meets the conditions for sleep apnea warning. If the risk level of sleep apnea is not greater than the first preset risk level and the risk level of breathing difficulties is not greater than the second preset risk level, the risk level of sleep apnea and the risk level of breathing difficulties are weighted and fused to obtain the target risk level. If the target risk level is greater than the third preset risk level, the respiratory state of the target object is determined to meet the sleep apnea warning conditions.

17. The apparatus according to claim 16, characterized in that, The device further includes: The risk information push module is used to detect the number of occurrences and frequency of sleep apnea risk events when the target object is asleep. Specifically, when it is confirmed that the target object's breathing state meets the sleep apnea warning conditions, it is determined that the target object has experienced a sleep apnea risk event. Based on the number of occurrences and the frequency of occurrences, sleep apnea risk information is pushed to the terminal device.

18. A headphone control device, characterized in that, Applied to a terminal device, the device includes: The display module showcases the noise reduction control interface for multiple sleep noise source types. The signal generation module is used to generate an active noise reduction control signal in response to noise reduction enable or disable operations for multiple sleep noise source types on the noise reduction control interface. A signal transmitting module is used to send the active noise cancellation control signal to the headphones, wherein the active noise cancellation control signal is used to control the headphones to enter sleep noise cancellation mode.

19. An earphone comprising a memory, a processor, and a bone conduction sensor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

20. A terminal device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 10 to 11.

Images