Sleep respiration detection method and device, terminal equipment and storage medium

Abstract

The invention discloses a sleep respiration detection method and device, terminal equipment and a storage medium, and belongs to the technical field of terminals. The method is applied to terminal equipment and comprises the steps that corresponding sleep data of a user in the sleep process are obtained, and the sleep data comprise body movement signals collected through an inertial sensor IMU of the terminal equipment; according to the sleep data, extracting sleep feature data; calculating a first apnea hypopnea index AHI according to the sleep feature data; and determining a first risk level corresponding to the sleep apnea hypopnea syndrome SAHS according to the first AHI. According to the method, when the user sleeps, the IMU can be used for collecting the body movement signal of the user on the bed in a non-contact mode, the sleep feature data are extracted based on the collected body movement signal, and the AHI is calculated, so that the risk level corresponding to the SAHS is determined in time, the method does not need to be carried out in a special sleep monitoring room, the measurement process is convenient and simple, and the measurement efficiency is improved. And the efficiency of detecting the SAHS of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a sleep apnea detection method, apparatus, terminal device and storage medium. Background Art

[0002] With the development of science and technology, it is very common to collect and process people's physiological data in biomedical engineering research, such as electrocardiogram signals, respiratory signals, etc.

[0003] Among them, most physiological data need to be collected clinically, that is, the user wears clinical equipment and instruments, and after the medical staff collects the required physiological data through these equipment and instruments, the collected data are sorted out through the process of data analysis and manual labeling by the medical staff to analyze the user's physical condition. For example, at present, the clinical detection process for Sleep Apnea Hypopnea Syndrome (SAHS) not only needs to be carried out in a special sleep monitoring room, but also requires medical staff to manually label all signals after collecting the user's physiological data. The whole process is labor-intensive and costly, and there is a problem of low efficiency in detecting the user's SAHS. Summary of the invention

[0004] In order to improve the efficiency of detecting the user's SAHS, the present application embodiment provides a sleep breathing detection method, apparatus, terminal device and storage medium. The technical solution is as follows:

[0005] In one aspect, the present application provides a sleep breathing detection method, which is applied to a terminal device, and the method includes:

[0006] Acquire sleep data corresponding to the user during sleep, wherein the sleep data includes a body motion signal of the user collected by an inertial sensor IMU of the terminal device;

[0007] Extracting sleep characteristic data according to the sleep data;

[0008] Calculating a first apnea-hypopnea index AHI according to the sleep characteristic data;

[0009] A first risk level corresponding to sleep apnea-hypopnea syndrome (SAHS) is determined according to the first AHI.

[0010] In one aspect, the present application provides a sleep breathing detection device, which is applied to a terminal device, and the device includes:

[0011] A first acquisition module is used to acquire sleep data corresponding to the user during sleep, wherein the sleep data includes a body motion signal of the user collected by an inertial sensor IMU of the terminal device;

[0012] A first extraction module, configured to extract sleep characteristic data according to the sleep data;

[0013] A first calculation module, used for calculating a first apnea-hypopnea index AHI according to the sleep characteristic data;

[0014] The first determination module is used to determine a first risk level corresponding to sleep apnea hypopnea syndrome SAHS according to the first AHI.

[0015] In another aspect, the present application provides a terminal device, which includes a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the sleep breathing detection method as described in one aspect.

[0016] In another aspect, the present application provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the sleep apnea detection method as described in one aspect.

[0017] On the other hand, an embodiment of the present application provides a computer program product. When the computer program product is executed on a computer, the computer is enabled to execute the sleep breathing detection method as described in one aspect above.

[0018] On the other hand, an embodiment of the present application provides an application publishing platform, which is used to publish a computer program product, wherein when the computer program product is run on a computer, the computer executes the sleep breathing detection method as described in one aspect above.

[0019] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0020] The sleep data corresponding to the user during sleep is obtained through the terminal device, and the sleep data includes body motion signals collected by the inertial sensor IMU of the terminal device; based on the sleep data, sleep characteristic data is extracted; based on the sleep characteristic data, a first apnea-hypopnea index AHI is calculated; based on the first AHI, the first risk level corresponding to the sleep apnea-hypopnea syndrome SAHS is determined. In an embodiment of the present application, when the user is sleeping, the terminal device can use the IMU to collect the body motion signals of the user on the bed in a contactless manner, extract the sleep characteristic data based on the obtained sleep data, and calculate the AHI, so as to timely determine the risk level corresponding to the SAHS, without the need to be performed in a special sleep monitoring room, and the measurement process is convenient and concise, which improves the efficiency of detecting the user's SAHS. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a schematic diagram of a scene of a wearable clinical device involved in an exemplary embodiment of the present application;

[0023] Figure 2 is a schematic diagram of an example structure of a terminal device provided in an embodiment of the present application;

[0024] Figure 3 is a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application;

[0025] Figure 4 is a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application;

[0026] Figure 5 is a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application;

[0027] Figure 6 is a structural block diagram of a sleep breathing detection device provided by an exemplary embodiment of the present application;

[0028] Figure 7 It is a structural schematic diagram of another example of a sleep apnea detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0030] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0031] The solution provided by the present application can be used in real-life scenarios in which people use terminal devices in their daily lives to collect users' physiological data through terminal devices. To facilitate understanding, some terms and application scenarios involved in the embodiments of the present application are briefly introduced below.

[0032] SAHS: Sleep Apnea Hypopnea Syndrome (SAHS) refers to a sleep-related respiratory disorder in which apnea and / or hypopnea occur repeatedly during sleep due to various reasons. It is clinically defined as apnea occurring more than 30 times per night during sleep or an apnea-hyponea index (AHI) ≥ 5 times / hour, where AHI refers to the number of apnea plus hypopnea per hour of sleep.

[0033] The above definition of apnea refers to the complete cessation of oral and nasal breathing airflow for more than 10 seconds during sleep; hypopnea refers to a decrease of more than 50% in the intensity of breathing airflow during sleep compared with the baseline level, accompanied by a decrease of ≥4% in blood oxygen saturation compared with the baseline level. Recurrent nocturnal hypoxia and hypercapnia caused by apnea can lead to complications such as hypertension, coronary heart disease, diabetes and cerebrovascular disease, and even sudden death at night. Therefore, SAHS is a potentially fatal sleep breathing disorder. Timely and effective detection of SAHS is of great significance.

[0034] IMU: Inertial measurement unit, is a device that measures the three-axis attitude angle (or angular rate) and acceleration of an object. IMU contains three single-axis accelerometers and three single-axis gyroscopes. The accelerometer detects the acceleration signal of the object in the carrier coordinate system in three independent axes, while the gyroscope detects the angular velocity signal of the carrier relative to the navigation coordinate system, measuring the angular velocity and acceleration of the object in three-dimensional space.

[0035] MIC: Microphone is an energy conversion device that converts sound signals into electrical signals.

[0036] Abnormal breathing events refer to events in which the user's breathing experiences temporary apnea or hypopnea.

[0037] Multimodality in multimodal data refers to the collaborative reasoning of multiple heterogeneous modal data. It usually refers to the recognition technology that integrates or fuses two or more biometric data, using the unique advantages of multiple recognition technology and combining data fusion technology to make the authentication and recognition process more accurate and secure.

[0038] Among them, the physiological data mentioned in this application may include the user's electrocardiogram data, heart rate data, blood pressure data, temperature, body movement signals and other data reflecting physiological phenomena.

[0039] Please refer to Figure 1 , which shows a scene schematic diagram of a wearable clinical device involved in the related technology of this application. Figure 1 As shown, it includes a collection device 101, a user 102, and a bed 103.

[0040] In related technologies, when it is necessary to collect some physiological data of user 102, user 102 can lie on bed 103, and medical staff will wear collection device 101 at the corresponding position of user 102 and start collection device 101, and complete the collection of user's physiological data with the cooperation of user 102.

[0041] For example, physiological data may include the heart rate and BCG signal of the user during normal breathing while the user is lying in bed. Medical staff collect these body motion signals through the collection device 101, and confirm the user's physical condition through processes such as data analysis and calibration of the collected body motion signals.

[0042] The above-mentioned acquisition device 101 can be a medical device for analyzing SAHS. At present, the gold standard for analyzing and determining the risk level of SAHS is polysomnography diagnosis, but polysomnography examination needs to be performed in a special sleep monitoring room. By setting a piezoelectric film sensor on the bed to contact the user, the required body movement signal can be collected through the piezoelectric film sensor, and the multi-lead signal can be monitored at the same time. This process not only needs to be carried out in a special sleep monitoring room, but also requires medical staff to manually mark all signals after collecting the user's physiological data. The whole process is labor-intensive and costly, and there is a problem of low efficiency in detecting the user's SAHS.

[0043] In order to improve the efficiency of detecting the user's SAHS and get rid of the dependence on traditional medical equipment, this solution directly detects the user in a non-contact mode. For example, terminal devices can be used in this application, and the device connection and wearing methods are complex, the types of fused data are small, and the operation process is convenient and fast, without the participation of additional professionals, and the flexibility of user self-detection is higher.

[0044] Optionally, the terminal device may be a terminal device including an inertial sensor IMU. For example, the terminal device may include but is not limited to wearable devices (such as smart bracelets, smart watches, smart glasses, etc.), mobile phones, tablet computers, laptops, smart glasses, smart watches, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, desktop computers, laptops, etc.

[0045] Optionally, the terminal device may establish a communication connection, and optionally, the communication connection may be a wired network connection or a wireless network connection.

[0046] Optionally, the wireless network connection or wired network connection described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or a virtual private network. In some embodiments, the data exchanged through the network is represented by technology and / or format including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0047] Please refer to Figure 2 , is a schematic diagram of an example structure of a terminal device provided in an embodiment of the present application. Figure 2 The terminal shown includes components such as a processor 210 , a memory 220 , a transceiver 230 , a display unit 240 , an input unit 250 , a sensor 260 , an audio circuit 270 , and a power module 280 .

[0048] The processor 210 is the control center of the terminal, and uses various interfaces and lines to connect various parts of the entire terminal. By running or executing software programs and / or modules stored in the memory 220, and calling data stored in the memory 220, the processor 210 performs various functions of the terminal and processes data, thereby monitoring the terminal as a whole. Optionally, the processor 210 may include one or more processing units; optionally, the processor 210 may integrate an application processor, which mainly processes operating devices, user interfaces, and application programs, etc. Of course, other processors may also be included, which are not listed here one by one.

[0049] The memory 220 can be used to store software programs and modules. The processor 210 executes various functional applications and data processing of the terminal by running the software programs and modules stored in the memory 220. The memory 220 may mainly include a program storage area and a data storage area, wherein the program storage area may store operating devices, at least one application required for a function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal (such as audio data, a phone book, etc.), etc. In addition, the memory 220 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0050] The transceiver 230 can provide wireless communication solutions applied on the terminal, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) network), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The transceiver 230 can be one or more devices integrating at least one communication processing module, for example, the antenna and the baseband processor are integrated into the transceiver 230, or the antenna and the modem processor are integrated into the transceiver 230, etc., which are not limited here.

[0051] The display unit 240 may be used to display information input by the user or information provided to the user and various menus of the terminal. The display unit 240 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc., which is not limited here.

[0052] The input unit 250 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the terminal. Specifically, the input unit 250 can collect the user's operations on or near it, and drive the corresponding connection device according to a pre-set program. In addition, the input unit 250 may include a touch panel, which can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel, the input unit 250 may also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of function keys (such as volume control keys, switch keys, etc.), trackballs, joysticks, etc.

[0053] The terminal may also include at least one sensor 260, such as a gyroscope sensor, a motion sensor, and other sensors. The motion sensor may include an acceleration sensor for detecting the magnitude of acceleration in all directions, and the magnitude and direction of gravity when stationary, which may be used for applications that identify the posture of the terminal device, such as horizontal and vertical screen switching, related games, magnetometer posture calibration, etc. As for other sensors that may be configured in the terminal device, such as a pressure gauge, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., they will not be described in detail here.

[0054] The audio circuit 270 may include a speaker and a microphone, and may provide an audio interface between the user and the terminal. The audio circuit 270 may transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 270 and converted into audio data, and then the audio data is output to the processor 210 for processing, and then sent to another terminal device through the video circuit, or the audio data is output to the memory 220 for further processing.

[0055] The terminal also includes a power module 280 for supplying power to various components. Optionally, the power module 280 can be logically connected to the processor 210 through a power management device, so that the power management device can manage charging, discharging, power consumption and other functions.

[0056] Although not shown, the terminal device may further include a camera. Optionally, the camera may be located at the front or rear of the terminal device, which is not limited in the embodiment of the present application.

[0057] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the terminal device. In other embodiments of the present application, the terminal device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0058] In order to solve the problems existing in the above-mentioned related technologies and improve the low efficiency and accuracy of detecting the user's SAHS, the present application provides a sleep breathing detection method that can be applied to a terminal device. The terminal device can timely assess the risk level corresponding to the user's SAHS without contacting the user.

[0059] Please refer to Figure 3 , which shows a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application, the sleep breathing detection method can be applied to a terminal device, and the terminal device includes an IMU unit. Figure 3 As shown, the sleep breathing detection method may include the following steps:

[0060] Step 301, obtaining sleep data corresponding to the user during sleep, where the sleep data includes body motion signals of the user collected by an inertial sensor IMU of a terminal device.

[0061] Optionally, the terminal device can collect physiological signals generated by the user's body during the user's sleep, and obtain the user's physiological data during the sleep process, that is, the sleep data corresponding to the user during the sleep process. Among them, the physiological signal can be a signal generated by the user's breathing, a signal generated by the heartbeat, etc. In this application, it is used to detect the user's sleep breathing. Therefore, the terminal device can be used to collect the sleep data generated by the user's breathing, heartbeat, movement, etc. during the sleep process. The sleep data collected here includes vibration data corresponding to the tiny vibrations generated by the user's breathing, heartbeat, movement, etc. during the sleep process, and these vibration data are body motion signals.

[0062] In the embodiment of the present application, the body motion signal can be collected by the IMU of the terminal device. For example, the terminal device includes an IMU unit, and the user can place the terminal device at the head of the bed before sleeping in bed. After the user falls asleep, the terminal device will use its own IMU unit to collect data. The terminal device can collect data including the breathing, heartbeat, movement, etc. generated by the user when sleeping in bed through its own IMU to obtain IMU data.

[0063] Step 302: extracting sleep characteristic data based on the sleep data.

[0064] Optionally, the terminal device can extract sleep characteristic data from the sleep data based on the sleep data and a pre-trained machine learning model. Among them, the sleep characteristic data can reflect the functional status of different body organs of the user during sleep. For example, the extracted sleep characteristic data may include heart rate variability data (HRV), etc. Heart rate variability data refers to the reflection of the activity of the autonomic nervous system and the quantitative assessment of the tension and balance of the cardiac sympathetic and vagal nerves, so as to judge its effect on the condition and prevention of cardiovascular diseases, which may be a valuable indicator for predicting sudden cardiac death and arrhythmic events.

[0065] Step 303: Calculate a first apnea-hypopnea index AHI according to the sleep characteristic data.

[0066] Optionally, the terminal device calculates the user's AHI, i.e., a first AHI, based on the sleep characteristic data obtained above according to a preset calculation method, and the first AHI may indicate the number of apnea and hypopnea of ​​the user per hour of sleep. The calculation method may also be similar to the above-mentioned machine learning model, where the sleep characteristic data is input into another trained machine learning model to calculate the first AHI.

[0067] Step 304: Determine a first risk level corresponding to sleep apnea hypopnea syndrome (SAHS) according to the first AHI.

[0068] Generally, AHI is an important parameter for assessing the risk level corresponding to SAHS. For example, if AHI ≥ 5 times / hour, it can be determined that the risk level corresponding to SAHS is medium risk. If AHI < 5 times / hour, it can be determined that the risk level corresponding to SAHS is low risk. If AHI ≥ 8 times / hour, it can be determined that the risk level corresponding to SAHS is high risk. The correspondence between AHI and the risk level corresponding to SAHS can be pre-set in the terminal device. After the terminal device obtains the first AHI, the first risk level corresponding to the user's SAHS is determined through the correspondence.

[0069] In summary, the sleep data corresponding to the user during sleep is obtained through the terminal device, and the sleep data includes the body motion signal collected by the inertial sensor IMU of the terminal device; according to the sleep data, the sleep characteristic data is extracted; according to the sleep characteristic data, the first apnea-hypopnea index AHI is calculated; according to the first AHI, the first risk level corresponding to the sleep apnea-hypopnea syndrome SAHS is determined. In this application, when the user is sleeping, the body motion signal of the user on the bed can be collected in a contactless manner using the IMU, and the sleep characteristic data can be extracted based on the collected body motion signal, and the AHI can be calculated, so as to timely determine the risk level corresponding to the SAHS, without the need to be carried out in a special sleep monitoring room, and the measurement process is convenient and concise, which improves the efficiency of detecting the user's SAHS.

[0070] In one possible implementation, the extracted sleep characteristic data includes multiple types of characteristic data, such as at least one type of characteristic data including heart rate variability data, breathing intensity, specific body movement characteristic data, etc. The terminal device processes and calculates these sleep characteristic data to obtain the user's first AHI, thereby improving the accuracy of obtaining the user's AHI.

[0071] Please refer to Figure 4 , which shows a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application, the sleep breathing detection method can be applied to a terminal device, and the terminal device includes an IMU unit. Figure 4 As shown, the sleep breathing detection method may include the following steps:

[0072] Step 401, start the SAHS monitoring function.

[0073] Optionally, the terminal device of the present application has a monitoring function for monitoring SAHS. When the user needs to monitor his or her own SAHS, the user can turn on this function in the terminal device and place the terminal device at the bedside when resting.

[0074] Step 402: Detect whether the user is in a sleeping state based on data collected by an inertial measurement unit IMU.

[0075] Optionally, after the user turns on the SAHS monitoring function, the terminal device will collect data through its own IMU, and the terminal device will detect whether the user is in a sleeping state based on the collected data. For example, when the user is in a sleeping state, the user's movements are much less than when in a non-sleeping state, and the collected IMU data is smaller and the amplitude changes more smoothly than the IMU data in the non-sleeping state, thereby determining whether the user is in a sleeping state. For example, the terminal device analyzes the IMU data. If the data value of the currently collected IMU data is less than the preset threshold and the amplitude change is less than the amplitude threshold, it can be determined that the current user is in a sleeping state.

[0076] Optionally, since the heart rate variability (HRV) data can indirectly reflect whether the user is asleep, the terminal device can also extract based on the above-mentioned IMU data to obtain the user's HRV data, and determine whether the user is in a sleeping state based on the HRV data. For example, the terminal device can extract the user's ballistocardiogram (BCG) signal according to a pre-set first filtering algorithm, calculate the user's heart rate variability data according to the extracted BCG signal, and further determine whether the user is in a sleeping state according to the heart rate variability data. For example, the heart rate variability data of a general user will be more stable in a sleeping state, that is, the heart rate will remain in a normal changing state. If the result of detecting the heart rate variability data indicates that the user's heart rate changes greatly, the user is not in a sleeping state. If the result of detecting the heart rate variability data indicates that the user's heart rate changes less, the user is in a sleeping state.

[0077] Optionally, the above two processes for detecting user falling asleep can be set as corresponding detection algorithms, which can be pre-edited by developers and set in the terminal device. The terminal device processes and detects the IMU data through the preset detection algorithm to determine whether the user is in a sleeping state. Optionally, the above process for detecting user falling asleep can be detected in real time or periodically, which is not limited by the comparison of this application.

[0078] Step 403: When the user is in a sleeping state, the user's body motion signal is collected through the IMU.

[0079] Optionally, when the terminal device determines that the user is in a sleeping state, it collects data through its own IMU unit, and the collected IMU data will include the user's body motion signals. For example, due to the tiny vibrations generated by breathing, the IMU will collect data generated by the vibration of the bed caused by such tiny vibrations. Among them, when the terminal device collects data through the IMU, it can be collected in real time or within a set fixed time. For example, when the SAHS monitoring function is started as mentioned above, the user can actively select the monitoring time (such as 10 pm to 8 am), and the terminal device collects data through the IMU within the fixed time period.

[0080] Step 404, obtaining sleep data corresponding to the user during sleep, where the sleep data includes body motion signals collected by an inertial sensor IMU of the terminal device.

[0081] Optionally, sleep data is data collected by the terminal device during the user's sleep, including the body motion signals collected by the IMU (i.e., IMU data). In actual applications, the user may need to monitor many body organs during his or her sleep (such as snoring, brain waves, etc.), and the sleep data includes these data obtained through monitoring. In this solution, the sleep data at least includes the body motion signals collected by the inertial sensor IMU of the terminal device.

[0082] Step 405: extracting sleep characteristic data based on the sleep data.

[0083] Optionally, according to actual needs, the terminal device can extract sleep feature data based on the acquired sleep data and the set filtering algorithms, machine learning models, etc. For example, if it is necessary to monitor the heart organ of a sleeping user, a filtering algorithm, machine learning model, etc. related to electrocardiogram data can be pre-set to extract sleep feature data. If it is necessary to monitor the risk level corresponding to the SAHS of a sleeping user, a filtering algorithm, machine learning model, etc. related to the SAHS of the user can be pre-set to extract sleep feature data.

[0084] Optionally, in this solution, the sleep characteristic data used to determine the risk level corresponding to the SAHS of the user is extracted as an example. The sleep characteristic data obtained above may include at least one type of characteristic data among heart rate variability data, breathing intensity, and specific body movement characteristic data, wherein the specific body movement characteristic data is used to indicate the specific body movement corresponding to the abnormal breathing event of the user, for example, the specific body movement characteristic data is the specific body movement caused by the user waking up at the end of apnea. That is, based on the sleep data obtained above, the terminal device can extract data such as heart rate variability data, breathing intensity, and specific body movement characteristic data, and then determine the risk level corresponding to the SAHS of the user.

[0085] Among them, since the sleep data can be the body motion signal collected by the above-mentioned IMU (also called IMU data), the terminal device can extract sleep characteristic data based on the sleep data as follows: extract the ballistocardiogram BCG signal according to the first filtering algorithm and the body motion signal, and calculate the heart rate variability data according to the BCG signal; and / or, extract the breathing intensity according to the second filtering algorithm and the body motion signal; and / or, obtain specific body motion characteristic data according to the frequency domain characteristics of the body motion signal.

[0086] Optionally, both the first filtering algorithm and the second filtering algorithm can be pre-set in the terminal device by the developer. For example, after the terminal device collects IMU data (i.e., body motion signal) through the IMU, the IMU data is extracted by the pre-set first filtering algorithm to obtain the user's BCG signal, and then the heart rate variability is calculated to obtain the heart rate variability data. In addition, after the IMU collects the IMU data, the terminal device can also extract the IMU data through the pre-set second filtering algorithm to obtain the user's respiratory waveform data, and extract the corresponding respiratory intensity based on the respiratory waveform data. In addition, after the IMU collects the IMU data, the terminal device can also transform the IMU data in the frequency domain to obtain the frequency domain characteristics of the IMU data, and obtain specific body motion feature data by detecting the frequency domain characteristics of the IMU data, thereby detecting whether the user has generated data due to body motion caused by awakening, and subsequently the specific body motion feature data can be used to know the specific pattern of micro-body motion caused by awakening at the end of apnea, and then identify apnea events.

[0087] It should be noted that the steps for obtaining the above-mentioned sleep characteristic data can be obtained simultaneously or step by step, and various sleep characteristic data are extracted according to actual needs. The number of types in actual applications can be less or more, and can also include other different types of characteristic data, which will not be repeated here.

[0088] Step 406: Calculate a first apnea-hypopnea index AHI according to the sleep characteristic data.

[0089] Optionally, the terminal device may independently calculate the user's first AHI based on the sleep characteristic data obtained above.

[0090] In one possible implementation, each type of characteristic data contained in the sleep characteristic data corresponding to the preset time window is fused to generate multimodal data, and the sleep characteristic data corresponding to the preset time window is extracted based on the sleep data corresponding to the preset time window; and the first AHI is calculated based on the multimodal data. For example, the sleep characteristic data obtained above includes heart rate variability data, respiratory intensity, and specific body movement characteristic data. The terminal device fuses these three types of sleep characteristic data within the preset time window to generate multimodal data. Among them, the preset time window can be pre-set by the developer or user. For example, after the terminal device collects the IMU data and extracts different types of sleep characteristic data according to the IMU data, it is necessary to align these sleep characteristic data on the time axis and fuse the corresponding sleep characteristic data within the preset time window. For example, the preset time window is from 10 pm to 8 am, and the sleep characteristic data within the preset time window is fused, and various types of sleep characteristic data are aligned on the time axis to generate multimodal data. Optionally, the size and number of the preset time windows can be flexibly set.

[0091] Optionally, the terminal device calculates the first AHI based on the generated multimodal data. The calculation process can be calculated by a machine learning model preset in the terminal device, whose input is the generated multimodal data and output is the calculated first AHI. The machine learning model can also be pre-trained by the developer and set in the terminal device. For example, the terminal device can comprehensively determine whether an abnormal breathing event occurs in the time period based on the heart rate variability, respiratory waveform, body movement characteristics and snoring characteristics in the same preset time window, summarize the number of abnormal breathing events and calculate the AHI.

[0092] In a possible implementation, the terminal device of the present solution can also calculate the AHI corresponding to each type of characteristic data and the credibility corresponding to each type of characteristic data according to the multiple types of characteristic data included in the above-mentioned sleep characteristic data, and calculate the first AHI according to the AHI corresponding to each type of characteristic data and the corresponding credibility. For example, when the terminal device calculates the first AHI according to the sleep characteristic data, it can be as follows: according to each type of characteristic data included in the sleep characteristic data, calculate the AHI corresponding to each type of characteristic data; according to each type of characteristic data included in the sleep characteristic data and the standard characteristic data corresponding to each type of characteristic data, obtain the data quality corresponding to each type of characteristic data, and calculate the credibility corresponding to each type of characteristic data according to the data quality corresponding to each type of characteristic data; according to the AHI corresponding to each type of characteristic data and the corresponding credibility, calculate the first AHI.

[0093] Optionally, the terminal device calculates the AHI corresponding to each type of characteristic data based on each type of characteristic data contained in the sleep characteristic data as follows: based on each type of characteristic data contained in the sleep characteristic data, detect abnormal breathing events occurring in each type of characteristic data; based on the detection results, obtain the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event; calculate the AHI corresponding to each type of characteristic data based on the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event.

[0094] For example, still taking the extracted sleep characteristic data including three types of characteristic data, namely heart rate variability data, breathing intensity, and specific body movement characteristic data, as an example, the terminal device can perform model recognition based on the heart rate variability data, detect the number of abnormal breathing events that indicate the user's sleep in the heart rate variability data, and calculate the AHI corresponding to the heart rate variability data based on the number of abnormal breathing events that appear in the heart rate variability data and the start and end time of each abnormal breathing event. The terminal device can also detect the breathing intensity through model recognition based on the extracted breathing intensity, detect the number of abnormal breathing events that indicate the user's sleep in the breathing intensity, and calculate the AHI corresponding to the breathing intensity based on the number of abnormal breathing events and the start and end time of each abnormal breathing event. The terminal device can also detect special body movements in the specific body movement feature data by performing model recognition on the specific body movement feature data. The special body movement can indicate abnormal breathing events that occur during the user's sleep, thereby detecting the number of abnormal breathing events that occur during the user's sleep indicated in the specific body movement feature data, and calculating the AHI corresponding to the specific body movement feature data based on the number of abnormal breathing events that occur in the specific body movement feature data and the start and end time of each abnormal breathing event. Among them, the machine learning model used in the above model recognition can also be pre-set in the terminal device by the developer, which will not be repeated here.

[0095] Optionally, in the process of obtaining the data quality corresponding to each type of feature data according to each type of feature data contained in the sleep feature data and the standard feature data corresponding to each type of feature data, the standard feature data corresponding to each type of feature data may be obtained in advance in a noise-free state when collecting data from the user through model simulation, that is, the standard feature data is assumed to be collected in a noise-free and interference-free state. The terminal device compares each type of feature data contained in the sleep feature data actually extracted with the corresponding standard feature data to determine the difference between the two and obtain the data quality corresponding to each type of feature data. The larger the difference between each type of feature data contained in the sleep feature data actually extracted and the corresponding standard feature data, the worse the data quality and the lower the credibility. The smaller the difference between each type of feature data contained in the sleep feature data actually extracted and the corresponding standard feature data, the better the data quality and the higher the credibility.

[0096] Optionally, the terminal device can calculate the credibility corresponding to each type of feature data based on the acquired data quality as follows: the data quality can be indicated by a specific numerical value, and the terminal device pre-stores a calculation formula between different data qualities and credibility, and the specific numerical value of the data quality is substituted into the calculation formula to calculate the credibility corresponding to each type of feature data. Alternatively, the terminal device can also pre-store a correspondence table between different data qualities and credibility, and after acquiring the data quality, the credibility corresponding to the corresponding feature data is obtained by querying the correspondence table between the data quality and credibility.

[0097] Optionally, the terminal device may calculate the first AHI according to the AHI corresponding to each type of feature data and the corresponding credibility as follows: according to the credibility corresponding to each type of feature data, obtain the weight corresponding to each type of feature data; according to the AHI corresponding to each type of feature data and the corresponding weight, obtain the first AHI according to a preset calculation method. For example, the terminal device may directly use the credibility corresponding to each type of feature data as the weight corresponding to each type of feature data, and obtain the first AHI by multiplying the AHI corresponding to each type of feature data by the corresponding weight and dividing by the sum of the weights.

[0098] For example, still taking the extracted sleep characteristic data including three types of characteristic data, namely heart rate variability data, breathing intensity, and specific body movement characteristic data as an example, after executing the above-mentioned calculation of the AHI and credibility of the three types of characteristic data, namely heart rate variability data, breathing intensity, and specific body movement characteristic data, the terminal device can obtain the following data: the AHI calculated by the heart rate variability data is X, and the credibility is 90%, the AHI calculated by the breathing intensity is Y, and the credibility is 95%, and the AHI calculated by the specific body movement characteristic data is Z, and the credibility is 85%. The terminal device calculates the AHI and credibility corresponding to each type of characteristic data according to a preset calculation method, multiplies the AHI corresponding to each type of characteristic data by the corresponding weight and divides it by the sum of the weights, and obtains the first AHI=(X*90%+Y*95%+Z*85%) / (90%+95%+85%).

[0099] In a possible implementation, the sleep data also includes snoring data collected by a voice collection device, and the sleep feature data also includes at least one type of feature data in the snoring interval and snoring energy data obtained based on the snoring data. In the above steps, obtaining the sleep data corresponding to the user during sleep also includes: collecting ambient sound data through a voice collection device; detecting the endpoints of the sound segments in the ambient sound data to extract the sound segments in the ambient sound data; and performing snoring recognition on each sound segment to obtain snoring data.

[0100] That is to say, in this solution, the sleep data collected by the terminal device also includes snoring data collected by its own voice collection device. By processing the snoring data, the snoring interval and snoring energy data are extracted as the type data in the above sleep characteristic data. Optionally, the voice collection device can be a MIC device of the terminal device. For example, after detecting that the user is in a sleeping state, the terminal device can also turn on its own MIC device to collect ambient sound data. In the process of extracting sleep characteristic data according to the sleep data, in addition to extracting sleep characteristic data based on IMU data in the manner of step 405, the ambient sound data in the sleep data can also be detected, and the endpoints of the sound segments in the ambient sound data can be detected to extract the sound segments in the ambient sound data; snoring recognition is performed on each sound segment through a pre-trained snoring recognition model to obtain snoring data, and snoring intervals and snoring energy data are obtained according to the snoring data. The snoring intervals and snoring energy data obtained here are also used as one of the above sleep characteristic data, and the steps of generating multimodal data or calculating AHI and credibility separately are performed, which will not be repeated here.

[0101] Step 407: Determine a first risk level corresponding to sleep apnea hypopnea syndrome SAHS according to the first AHI.

[0102] Optionally, the terminal device determines the first risk level corresponding to the SAHS of the user according to the AHI obtained above. For example, a correspondence between the range of AHI and the SAHS risk level of the user is set in the terminal device. After obtaining the first AHI, the range of the first AHI is determined, and the corresponding correspondence is queried to determine the first risk level corresponding to the SAHS of the user. For example, please refer to Table 1, which shows a correspondence table between the range of AHI and the risk level involved in an exemplary embodiment of the present application.

[0103] Range of AHI Risk Level Scope 1 Level 1 Scope 2 Level 2 Scope 3 Level 3 …… ……

[0104] Table 1

[0105] As shown in Table 1, different AHI ranges correspond to different risk levels. If the range of the first AHI obtained above is range one, by querying Table 1, it is determined that the first risk level corresponding to the user's SAHS is level one.

[0106] In one possible implementation, in order to more accurately reflect the risk level corresponding to the SAHS of the user, in this solution, the terminal device can further determine the risk level corresponding to the SAHS of the user based on the first AHI, combined with the user information of the user and / or the risk level corresponding to the SAHS determined based on the snoring. For example, the terminal device can also obtain the snoring feature variability based on the snoring data; obtain the second risk level corresponding to the SAHS based on the snoring feature variability; when executing step 407, determine the first risk level based on one or more of the first AHI and the second risk level, the user's personal information, and the user's user disease information.

[0107] Optionally, the process of the terminal device obtaining the second risk level corresponding to SAHS based on the snoring characteristic variability can be as follows: the terminal device is set with a correspondence between the snoring characteristic variability data and the user's SAHS risk level. After obtaining the snoring characteristic variability, the corresponding correspondence can be queried to determine the second risk level corresponding to SAHS.

[0108] Optionally, taking the above-mentioned fusion of the first AHI, the second risk level, and the user's personal information and user disease information to determine the first risk level as an example, the fusion process can be done by a fusion machine learning model, which is pre-trained by the developer and set in the terminal device. After obtaining the first AHI, the second risk level, and the user's personal information and user disease information, the first AHI, the second risk level, and the user's personal information and user disease information are input into the fusion model to calculate the fused risk level. The final fused risk level is the first risk level of the sleep breathing detection result.

[0109] In a possible implementation, the terminal device may also perform the following steps to calculate: determine the level correspondence according to the user's disease information, the level correspondence includes the correspondence between different AHI ranges and different risk levels of SAHS; determine a new first AHI according to the first AHI and the second risk level; determine the first risk level according to the AHI range and the level correspondence in which the new first AHI is located. Optionally, the user's disease information can be pre-collected and set in the terminal device. For example, the user's disease information may include: whether there has been sleep apnea and (or) hypopnea, sleep respiratory diseases, asthma, coronary heart disease and other diseases. For the same AHI range, when the user has more diseases, the risk level corresponding to the AHI range is higher, thereby determining the level correspondence that meets the current user.

[0110] Optionally, after determining the above-mentioned level correspondence, when determining the first risk level, the terminal device can also determine a new first AHI based on the first AHI and the second risk level, wherein the higher the second risk level determined above, the larger the new first AHI determined here will be, that is, the second risk level is used as a parameter to adjust the first AHI. If the second risk level is higher, the actually calculated first AHI can be expanded accordingly to avoid the risk level determined by the calculated first AHI being too small to be lower than the second risk level. For example, the terminal device obtains the second risk level corresponding to SAHS as level 2 based on the variability of snoring characteristics. The value of the first AHI calculated based on the sleep characteristic data is 5. If only the first AHI is used to determine the risk level, the determined risk level is only level 1. In order to improve the reliability of the data, the value of the first AHI can be adaptively increased in combination with the second risk level to determine a new first AHI (5+0.5*level 2=6), and the final first risk level is determined in the above-mentioned determined level correspondence according to the new first AHI.

[0111] Optionally, in the present application, the terminal device may continuously detect the user. If it is found that the first risk level corresponding to the user's SAHS is at medium or high risk for more than N days, a prompt message may be generated and displayed on the terminal device, prompting the user to go to the hospital for treatment or examination, thereby achieving the effect of flexible monitoring by the user in daily life.

[0112] It should be noted that in this solution, the IMU or MIC and other hardware of the terminal device can also be replaced by other hardware that can collect the user's sleep data. For example, the IMU can be replaced by piezoelectric film sensors, UWB ultra-wideband, mmw Radar, WIFI module and other sensors, which will not be repeated here.

[0113] In summary, the sleep data corresponding to the user during sleep is obtained through the terminal device, and the sleep data includes the body motion signal collected by the inertial sensor IMU of the terminal device; according to the sleep data, the sleep characteristic data is extracted; according to the sleep characteristic data, the first apnea-hypopnea index AHI is calculated; according to the first AHI, the first risk level corresponding to the sleep apnea-hypopnea syndrome SAHS is determined. In this application, when the user is sleeping, the body motion signal of the user on the bed can be collected in a contactless manner using the IMU, and the sleep characteristic data can be extracted based on the collected body motion signal, and the AHI can be calculated, so as to timely determine the risk level corresponding to the SAHS, without the need to be carried out in a special sleep monitoring room, and the measurement process is convenient and concise, which improves the efficiency of detecting the user's SAHS.

[0114] In addition, in the process of calculating sleep characteristic data, the present application calculates a variety of sleep characteristic data including the user's sleep, heart rate variability, respiratory waveform and snoring, and can also calculate the user's SAHS risk level in combination with the user's personal information and medical history, thereby improving the accuracy of the final determination of the user's SAHS risk level. By using it in the terminal device, it is convenient for users to monitor SAHS risks for a long time without feeling, and it is easier to promote it as a screening tool. Moreover, the variability of snoring characteristics is used to classify individual users to obtain different second risk levels of SAHS, which can also increase the accuracy of detecting the user's SAHS risk level.

[0115] Next, a mobile phone is used as an example to detect the user's sleep breathing. Figure 3 and Figure 4 The illustrated embodiments are presented by way of example.

[0116] Please refer to Figure 5 , which shows a method flow chart of a sleep breathing detection method provided by an exemplary embodiment of the present application, the sleep breathing detection method can be applied to a mobile phone, and the mobile phone includes an IMU unit and a MIC unit. Figure 5As shown, the sleep breathing detection method may include the following steps:

[0117] Step 501: The user turns on the SAHS monitoring function and places the mobile phone next to the pillow on the bed.

[0118] Step 502: The mobile phone determines whether the user is in a sleeping state based on the data collected by the IMU.

[0119] Step 503: The mobile phone determines whether the user is in a sleeping state based on the HRV.

[0120] Step 504: The mobile phone performs windowing and enhancement processing on the IMU data.

[0121] Step 505: extracting BCG signals.

[0122] Step 506, calculating heart rate variability.

[0123] Step 507: The model identifies abnormal breathing events.

[0124] Optionally, steps 505 to 507 may refer to the process of extracting BCG signals based on IMU data and calculating heart rate variability data, and calculating AHI corresponding to the heart rate variability data in the above steps 405 to 406, which will not be repeated here.

[0125] Step 508: extract the breathing waveform.

[0126] Step 509, calculating the breathing intensity.

[0127] Step 510, identifying abnormal breathing events.

[0128] Optionally, steps 505 to 507 may refer to the process of extracting the respiratory intensity based on the IMU data and calculating the AHI corresponding to the respiratory intensity in the above steps 405 to 406, which will not be repeated here.

[0129] Step 511, detecting micro-body movement.

[0130] Step 512, determining an abnormal breathing event by identifying body movements associated with the abnormal breathing event.

[0131] Optionally, steps 505 to 507 may refer to the process of extracting specific body motion feature data based on IMU data and calculating the AHI corresponding to the specific body motion feature data in the above steps 405 to 406, which will not be repeated here.

[0132] Step 513: Fusing multimodal data within the time window to determine abnormal breathing events.

[0133] Step 514, calculate AHI.

[0134] Optionally, during the process from step 501 to step 514, the mobile phone uses IMU data to extract the user's BCG signal through an appropriate first filtering algorithm, calculates heart rate variability and extracts features to determine whether an abnormal breathing event occurs; uses IMU data to extract the user's breathing waveform and identify abnormal breathing events through an appropriate second filtering algorithm; this helps the IMU data detect tiny body movements caused by awakening at the end of an abnormal breathing event; for each of the above types of data, AHI (number of events / sleep duration) can be calculated separately and weights and credibility can be calculated based on the signal quality of the IMU data; in step 513, for the heart rate variability, breathing waveform, body movement features and snoring features in the same time window, it is also possible to comprehensively determine whether an abnormal breathing event occurs, summarize the number of events and calculate AHI, and calculate weights and credibility based on the signal quality with the AHI calculated separately for each type of data, and obtain the final fused AHI through a pre-trained machine learning model.

[0135] Step 515, the mobile phone turns on the MIC.

[0136] Step 516: Perform voice segment endpoint detection on the ambient sound data collected by the MIC.

[0137] Step 517: extract snoring data.

[0138] Step 518: Calculate the snoring interval and snoring energy.

[0139] Step 519: determine abnormal breathing events based on the snoring interval and snoring energy.

[0140] Step 520: Count the variability of snoring characteristics throughout the night.

[0141] Step 521 : determining the risk level of SAHS of the user based on the variability of the snoring characteristics.

[0142] Step 522 , calculate the final SAHS risk level according to the AHI, the user's personal information and medical history, and the SAHS risk level determined based on the variability of the snoring characteristics.

[0143] That is, the terminal device also detects whether the user is snoring through audio signals, and analyzes the intervals between each snoring sound of the user and the characteristics of the snoring throughout the night to determine whether the user has an abnormal breathing event and the probability of being a SAHS patient and the corresponding SAHS risk level. In the final step 522, the final SAHS risk level is calculated through the fusion model combined with the user's personal information and medical history. If the user is at medium or high risk for many consecutive days, it is recommended to go to the hospital for further examination, thereby achieving the effect of SAHS initial screening.

[0144] In summary, based on this technical solution, a portable smart phone can be used to seamlessly screen whether a user has SAHS risk. The entire solution does not require any additional equipment except the mobile phone. It is portable and seamless, and can evaluate the risk level from more dimensions through multimodal data, thereby obtaining more accurate results.

[0145] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0146] Please refer to Figure 6 , which shows a structural block diagram of a sleep breathing detection device provided by an exemplary embodiment of the present application. The sleep breathing detection device 600 can be used in a terminal device. Figure 3 , Figure 4 or Figure 5 All or part of the steps in the method provided by the illustrated embodiment are performed by the terminal device. The sleep breathing detection device 600 includes:

[0147] A first acquisition module 601 is used to acquire sleep data corresponding to the user during sleep, wherein the sleep data includes a body motion signal of the user collected by an inertial sensor IMU of the terminal device;

[0148] A first extraction module 602, configured to extract sleep characteristic data according to the sleep data;

[0149] A first calculation module 603, used for calculating a first apnea-hypopnea index AHI according to the sleep characteristic data;

[0150] The first determination module 604 is configured to determine a first risk level corresponding to sleep apnea hypopnea syndrome (SAHS) according to the first AHI.

[0151] In summary, the sleep data corresponding to the user during sleep is obtained through the terminal device, and the sleep data includes the body motion signal collected by the inertial sensor IMU of the terminal device; according to the sleep data, the sleep characteristic data is extracted; according to the sleep characteristic data, the first apnea-hypopnea index AHI is calculated; according to the first AHI, the first risk level corresponding to the sleep apnea-hypopnea syndrome SAHS is determined. In this application, when the user is sleeping, the body motion signal of the user on the bed can be collected in a contactless manner using the IMU, and the sleep characteristic data can be extracted based on the collected body motion signal, and the AHI can be calculated, so as to timely determine the risk level corresponding to the SAHS, without the need to be carried out in a special sleep monitoring room, and the measurement process is convenient and concise, which improves the efficiency of detecting the user's SAHS.

[0152] Optionally, the sleep characteristic data includes multiple types of characteristic data, and the first calculation module includes: a first generation unit and a first calculation unit;

[0153] The first generating unit is used to fuse each type of characteristic data included in the sleep characteristic data corresponding to the preset time window to generate multimodal data, wherein the sleep characteristic data corresponding to the preset time window is extracted based on the sleep data corresponding to the preset time window;

[0154] The first calculation unit is configured to calculate the first AHI according to the multimodal data.

[0155] Optionally, the sleep characteristic data includes multiple types of characteristic data, and the first calculation unit includes: a first calculation subunit, a second calculation subunit and a third calculation subunit;

[0156] The first calculation subunit is used to calculate the AHI corresponding to each type of characteristic data included in the sleep characteristic data according to each type of characteristic data included in the sleep characteristic data;

[0157] The second calculation subunit is used to obtain the data quality corresponding to each type of characteristic data according to each type of characteristic data included in the sleep characteristic data and the standard characteristic data corresponding to each type of characteristic data, and calculate the credibility corresponding to each type of characteristic data according to the data quality corresponding to each type of characteristic data;

[0158] The third calculation subunit is configured to calculate the first AHI according to the AHI corresponding to each type of feature data and the corresponding credibility.

[0159] Optionally, the first computing subunit is further configured to:

[0160] Based on each type of characteristic data included in the sleep characteristic data, detecting abnormal breathing events occurring in each type of characteristic data;

[0161] According to the detection results, the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event are obtained;

[0162] According to the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event, the AHI corresponding to each type of characteristic data is calculated.

[0163] Optionally, the third computing subunit is further configured to:

[0164] Obtaining a weight corresponding to each type of feature data according to the credibility corresponding to each type of feature data;

[0165] According to the AHI corresponding to each type of feature data and the corresponding weight, a weighted average is performed on the AHI corresponding to each type of feature data to obtain the first AHI.

[0166] Optionally, the sleep characteristic data includes at least one type of characteristic data of heart rate variability data, breathing intensity, and specific body movement characteristic data, wherein the specific body movement characteristic data is used to indicate a specific body movement corresponding to an abnormal breathing event of the user;

[0167] The first extraction module includes: a first extraction unit, and / or a second extraction unit, and / or a first acquisition unit;

[0168] The first extraction unit is used to extract the ballistocardiogram (BCG) signal according to the first filtering algorithm and the body motion signal, and calculate the heart rate variability data according to the BCG signal;

[0169] The second extraction unit is used to extract the breathing intensity according to a second filtering algorithm and the body motion signal;

[0170] The first acquisition unit is used to acquire the specific body motion feature data according to the frequency domain characteristics of the body motion signal.

[0171] Optionally, the sleep data further includes snoring data collected by a voice collection device, and the sleep characteristic data further includes at least one type of characteristic data of snoring interval and snoring energy data obtained according to the snoring data.

[0172] Optionally, the first acquisition module includes: a first acquisition unit, a third extraction unit, and a second acquisition unit;

[0173] The first acquisition unit is used to collect environmental sound data through the voice acquisition device;

[0174] The third extraction unit is used to detect the endpoints of the voiced segments in the ambient sound data and extract the voiced segments in the ambient sound data;

[0175] The second acquisition unit is used to perform snoring recognition on each sound segment to acquire the snoring data.

[0176] Optionally, the device further comprises:

[0177] A second acquisition module, configured to acquire snoring characteristic variability according to the snoring data;

[0178] A third acquisition module is used to acquire a second risk level corresponding to SAHS according to the snoring characteristic variability;

[0179] The first determination module is further used to determine the first risk level according to the first AHI, the second risk level, and the user disease information of the user.

[0180] Optionally, the first determining module is further configured to:

[0181] Determining a level correspondence relationship according to the user disease information of the user, wherein the level correspondence relationship includes a correspondence relationship between different AHI ranges and different risk levels of SAHS;

[0182] determining a new first AHI according to the first AHI and the second risk level, wherein the higher the second risk level is, the greater the new first AHI is;

[0183] The first risk level is determined according to the AHI range in which the new first AHI is located and the level correspondence.

[0184] Optionally, the device further comprises:

[0185] A first starting module, used for starting the SAHS monitoring function before obtaining the sleep data corresponding to the user during the sleep process;

[0186] A first detection module, used to detect whether the user is in a sleeping state based on data collected by an inertial measurement unit IMU;

[0187] The first acquisition module is used to acquire the user's body motion signal through the IMU when the user is in a sleeping state.

[0188] Please refer to Figure 7 , which is a structural diagram of another example of a sleep breathing detection device provided in an embodiment of the present application. Among them, the sleep breathing detection device 700 can be a terminal device, which can implement the functions of the method provided in an embodiment of the present application. Among them, the sleep breathing detection device 700 can be a chip system. In the embodiment of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0189] In terms of hardware implementation, the communication module 702 may be a transceiver, which is integrated into the sleep apnea detection device 700 to form a communication interface 703 .

[0190] The sleep breathing detection device 700 includes at least one processor 720, which is used to implement or support the sleep breathing detection device 700 to implement the functions of the terminal device in the method provided in the embodiment of the present application. Exemplarily, the processor 720 can obtain the sleep data corresponding to the user during sleep, extract the sleep characteristic data according to the sleep data; calculate the first AHI according to the sleep characteristic data; determine the first risk level corresponding to the SAHS according to the first AHI, please refer to the detailed description in the method example for details, which will not be repeated here.

[0191] The sleep breathing detection device 700 may also include at least one memory 730 for storing program instructions and / or data. The memory 730 is coupled to the processor 720. The coupling in the embodiment of the present application is an indirect coupling or communication connection between devices, units or modules, which may be electrical, mechanical or other forms, and is used for information exchange between devices, units or modules. The processor 720 may operate in coordination with the memory 730. The processor 720 may execute program instructions stored in the memory 730. At least one of the at least one memory may be included in the processor.

[0192] The sleep apnea detection device 700 may further include a communication interface 703 for communicating with other devices via a transmission medium, so that the device in the sleep apnea detection device 700 can communicate with other devices. Exemplarily, the other device may be a network side device. The processor 720 may use the communication interface 703 to send and receive data. The communication interface 703 may specifically be a transceiver.

[0193] The specific connection medium between the communication interface 703, the processor 720 and the memory 730 is not limited in the embodiment of the present application. Figure 7 The memory 730, the processor 720 and the communication interface 703 are connected via a bus 740. Figure 7 The connections between the other components are shown in bold lines, which are only for illustration and are not intended to be limiting. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0194] In the embodiment of the present application, the processor 720 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiment of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0195] In the embodiment of the present application, the memory 730 can be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., and can also be a volatile memory (volatile memory), such as a random access memory (RAM). The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0196] Optionally, an embodiment of the present application further provides a terminal device, the terminal device includes a processor and a memory, the memory stores a computer program, and the computer program is executed by the processor to implement all or part of the steps performed by the terminal device in the sleep breathing detection method described in the above embodiments.

[0197] Optionally, an embodiment of the present application further provides a computer-readable medium storing a computer program, which is executed by a processor to implement all or part of the steps performed by a terminal device in the sleep breathing detection method described in the above embodiments.

[0198] Optionally, an embodiment of the present application also provides a computer program product, which stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the sleep breathing detection method described in the above embodiments, and all or part of the steps executed by the terminal device.

[0199] It should be noted that: when the device provided in the above embodiment performs the control of the terminal device, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0200] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0201] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0202] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting sleep breathing, characterized in that: Applied to a terminal device, the method comprises: Acquire sleep data corresponding to the user during sleep, wherein the sleep data includes a body motion signal collected by an inertial sensor IMU of the terminal device; Extracting sleep characteristic data according to the sleep data; Calculating a first apnea-hypopnea index AHI according to the sleep characteristic data; A first risk level corresponding to sleep apnea-hypopnea syndrome (SAHS) is determined according to the first AHI.

2. The method according to claim 1, characterized in that The sleep characteristic data includes multiple types of characteristic data, and the calculation of the first apnea-hypopnea index AHI according to the sleep characteristic data includes: fusing each type of characteristic data contained in the sleep characteristic data corresponding to the preset time window to generate multimodal data, wherein the sleep characteristic data corresponding to the preset time window is extracted based on the sleep data corresponding to the preset time window; The first AHI is calculated based on the multimodal data.

3. The method according to claim 1, characterized in that The sleep characteristic data includes multiple types of characteristic data, and the calculation of the first apnea-hypopnea index AHI according to the sleep characteristic data includes: According to each type of characteristic data included in the sleep characteristic data, calculating the AHI corresponding to each type of characteristic data; According to each type of characteristic data included in the sleep characteristic data and the standard characteristic data corresponding to each type of characteristic data, obtaining the data quality corresponding to each type of characteristic data, and calculating the credibility corresponding to each type of characteristic data according to the data quality corresponding to each type of characteristic data; The first AHI is calculated according to the AHI corresponding to each type of feature data and the corresponding credibility.

4. The method according to claim 3, characterized in that The calculating, according to each type of characteristic data included in the sleep characteristic data, the AHI corresponding to each type of characteristic data includes: Based on each type of characteristic data included in the sleep characteristic data, detecting abnormal breathing events occurring in each type of characteristic data; According to the detection result of the abnormal breathing events occurring in each type of characteristic data, the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event are obtained; According to the number of abnormal breathing events occurring in each type of characteristic data and the start and end time of each abnormal breathing event, the AHI corresponding to each type of characteristic data is calculated.

5. The method according to claim 3, characterized in that: The calculating the first AHI according to the AHI corresponding to each type of feature data and the corresponding credibility includes: Obtaining a weight corresponding to each type of feature data according to the credibility corresponding to each type of feature data; According to the AHI corresponding to each type of feature data and the corresponding weight, a weighted average is performed on the AHI corresponding to each type of feature data to obtain the first AHI.

6. The method according to any one of claims 1 to 5, characterized in that: The sleep characteristic data includes at least one type of characteristic data among heart rate variability data, breathing intensity, and specific body movement characteristic data, wherein the specific body movement characteristic data is used to indicate the specific body movement corresponding to the abnormal breathing event of the user; The step of extracting sleep characteristic data according to the sleep data includes: Extracting a ballistocardiogram (BCG) signal according to the first filtering algorithm and the body motion signal, and calculating the heart rate variability data according to the BCG signal; and / or, extracting the breathing intensity according to a second filtering algorithm and the body motion signal; and / or, The specific body motion feature data is acquired according to the frequency domain features of the body motion signal.

7. The method according to any one of claims 1 to 5, characterized in that: The sleep data further includes snoring data collected by a voice collection device, and the sleep characteristic data further includes at least one type of characteristic data of snoring interval and snoring energy data obtained according to the snoring data.

8. The method according to claim 7, characterized in that The step of obtaining sleep data corresponding to the user during sleep includes: Collecting environmental sound data through the voice collection device; Detecting the endpoints of the voiced segments in the ambient sound data to extract the voiced segments in the ambient sound data; Snoring is recognized for each sound segment to obtain the snoring data.

9. The method according to claim 7, characterized in that: The method further comprises: Acquiring snoring characteristic variability according to the snoring data; Obtaining a second risk level corresponding to SAHS according to the snoring characteristic variability; Determining a first risk level corresponding to sleep apnea-hypopnea syndrome (SAHS) according to the first AHI includes: The first risk level is determined according to one or more of the first AHI and the second risk level, the personal information of the user, and the user disease information of the user.

10. The method according to claim 9, characterized in that The determining the first risk level according to the first AHI, the second risk level, and the user disease information of the user includes: Determining a level correspondence relationship according to the user disease information of the user, wherein the level correspondence relationship includes a correspondence relationship between different AHI ranges and different risk levels of SAHS; determining a new first AHI according to the first AHI and the second risk level, wherein the higher the second risk level is, the greater the new first AHI is; The first risk level is determined according to the AHI range in which the new first AHI is located and the level correspondence.

11. The method according to any one of claims 1 to 5, characterized in that: Before obtaining the sleep data corresponding to the user during the sleep process, the method further includes: Start the SAHS monitoring function; Detect whether the user is in a sleeping state based on the data collected by the inertial measurement unit (IMU); When the user is in a sleeping state, the body motion signal of the user is collected through the IMU.

12. A sleep breathing detection device, characterized in that: Applied to a terminal device, the device comprises: A first acquisition module is used to acquire sleep data corresponding to the user during sleep, wherein the sleep data includes a body motion signal of the user collected by an inertial sensor IMU of the terminal device; A first extraction module, configured to extract sleep characteristic data according to the sleep data; A first calculation module, used for calculating a first apnea-hypopnea index AHI according to the sleep characteristic data; The first determination module is used to determine a first risk level corresponding to sleep apnea hypopnea syndrome SAHS according to the first AHI.

13. A terminal device, characterized in that: The terminal device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is executed by the processor to implement the sleep breathing detection method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is executed by a processor to implement the sleep apnea detection method according to any one of claims 1 to 11.

Images