Wearable devices and methods for assessing respiratory infections
The wearable device uses audio and physiological parameter sensors to assess respiratory infection risk by calculating respiratory rates and adapting to user posture, enabling early detection and accurate reporting.
Patent Information
- Application Number
- JP2024528619
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2021-12-08
- Filing Date
- 2022-11-23
- Publication Date
- 2024-12-04
- Estimated Expiration
- 2042-11-23
AI Technical Summary
Existing wearable devices are unable to assess a user's risk of suffering from respiratory infections based on multiple physiological parameters, making it difficult to detect these infections at an early stage.
A wearable device equipped with sensors to obtain audio and physiological parameter signals, such as PPG and ACC, processes these signals to calculate respiratory rates and generate assessment reports, adapting measurement schemes based on user posture to improve accuracy.
Enables early detection of respiratory infections, facilitating timely intervention and treatment, and providing accurate respiratory infection assessment reports.
Smart Images

Figure 2024544756000001_ABST
Abstract
Description
[Technical field]
[0001] This application claims priority to Chinese Patent Application No. 202111489780.7, entitled "Wearable Device and Method for Assessing Respiratory Infection," filed with the State Intellectual Property Office of the People's Republic of China on December 8, 2021. The Chinese patent application is hereby incorporated by reference in its entirety.
[0002] The present application relates to the technical field of wearable devices, and in particular to a wearable device and a method for assessing respiratory infection. [Background technology]
[0003] Currently, wearable devices on the market have the function of detecting physiological parameters such as heart rate, blood oxygen concentration, and body temperature, etc. However, wearable devices on the market cannot evaluate the risk of a user suffering from a disease, such as a respiratory infection, which involves multiple physiological parameters, based on the detected physiological parameters. Summary of the Invention
[0004] In view of this, the present application provides a wearable device and a method for assessing respiratory infection to solve the problem that existing wearable devices are unable to assess a user's risk of contracting a disease.
[0005] According to a first aspect, the present application provides a wearable device. The wearable device may include a first sensor, a second sensor, and a processor. The first sensor is configured to acquire an audio signal of the user. The second sensor is configured to acquire a physiological parameter signal of the user. The processor is configured to acquire a respiration rate of the user based on the physiological parameter signal, and acquire a respiratory infection assessment report of the user based on the audio signal and the respiratory rate. It should be understood that since the wearable device has characteristics such as portability and portability, the wearable device can help the user to perform a respiratory infection assessment as needed. The risk of the user suffering from a respiratory infection can be evaluated based on the respiratory infection assessment report. Furthermore, by using the wearable device, a respiratory infection can be detected at an early stage, so that confirmation, intervention and treatment can be performed as early as possible to prevent the respiratory infection from worsening.
[0006] In some implementations, the second sensor may include a PPG sensor. The PPG sensor is configured to acquire a PPG signal of the user. The processor is configured to acquire a first respiratory rate of the user based on the PPG signal. In some cases, the wearable device may acquire a respiratory infection assessment report of the user based on the first respiratory rate and the audio signal.
[0007] In some implementations, the second sensor may further include an ACC sensor. The ACC sensor is configured to acquire an ACC signal of the user. The processor is configured to acquire a second respiratory rate of the user based on the ACC signal. In some cases, the wearable device may acquire a respiratory infection assessment report of the user based on the second respiratory rate and the audio signal.
[0008] In some implementations, the processor is further configured to perform filtering and fusion on the first respiratory rate and the second respiratory rate to obtain a third respiratory rate of the user. It should be understood that since the third respiratory rate is obtained based on the first respiratory rate and the second respiratory rate, the accuracy of the measured respiratory rate may be improved. Based on this, the accuracy of the respiratory infection assessment report may be improved.
[0009] In some implementations, the processor is further configured to obtain a user posture classification result based on the ACC signal, and the posture classification result includes a first posture and a second posture, the first posture includes a state in which the user's wearing position is stressed for support, and the second posture includes a state in which the user's wearing position is naturally placed. It should be understood that due to the detection of the user's posture, the corresponding respiratory rate is used to obtain a respiratory infection assessment report, thereby improving the accuracy of the assessment report.
[0010] In some implementations, when the user is in the first position, the processor is configured to obtain a respiratory infection assessment report based on the first respiratory rate and the audio signal. It should be understood that when the user is in the first position, the PPG sensor may obtain a PPG signal with a relatively high signal-to-noise ratio. Based on this, the first respiratory rate may be obtained based on the PPG signal, and the respiratory infection assessment report may further be obtained.
[0011] In some implementations, when the user is in the second position, the processor is configured to obtain a respiratory infection assessment report based on the third respiratory rate and the audio signal. It should be understood that when the user is in the second position, the PPG sensor may obtain a PPG signal with a relatively high signal-to-noise ratio, and similarly, the ACC sensor may obtain an ACC signal with a relatively high signal-to-noise ratio. Based on this, a third respiratory rate can be obtained based on the first respiratory rate and the second respiratory rate, and a respiratory infection assessment report can be further obtained.
[0012] In some implementations, the wearable device may further include a low-pass filter. The low-pass filter is configured to perform low-pass filtering on the ACC signal. The cutoff frequency of the low-pass filter is 1 Hz. The processor is configured to calculate a mean value and a standard deviation of the ACC signal, and calculate a power spectrum based on the low-pass filtered ACC signal to obtain a position and an amplitude of a peak point of the power spectrum. The processor is further configured to input the mean value and the standard deviation of the ACC signal and the position and the amplitude of the peak point of the power spectrum into a classification model to obtain a posture classification result.
[0013] In some implementations, the processor may be further configured to prompt the user to switch to the second position when the user is in the first position and the first respiratory rate exceeds a preset range; and in response to an operation for switching to the second position being performed by the user, to obtain a third respiratory rate based on the PPG signal and the ACC signal; and to obtain a respiratory infection assessment report based on the third respiratory rate and the audio signal.
[0014] In some implementations, the wearable device may be an electronic device such as a wearable watch, a wearable blanket, or a wearable monitor. The wearable monitor may be a multi-parameter monitor.
[0015] In some implementations, the wearable device may further include a first bandpass filter and a second bandpass filter. The first bandpass filter is configured to perform bandpass filtering on the PPG signal to obtain positions of peak points and valley points of the PPG signal. The second bandpass filter is configured to perform bandpass filtering on the PPG signal to obtain amplitudes of peak points and valley points of the PPG signal. The processor is further configured to obtain a first respiratory rate of the user based on the positions and amplitudes of the peak points and valley points of the PPG signal. It should be understood that the waveform of the PPG signal may be obtained by using the second bandpass filter, and the amplitudes of the peak points and valley points of the PPG signal may be obtained based on the positions of the peak points and valley points of the PPG signal.
[0016] In some implementations, the frequency band of signals allowed to pass through the first bandpass filter is from 0.5 Hz to 10 Hz, and the frequency band of signals allowed to pass through the second bandpass filter is from 0.1 Hz to 10 Hz.
[0017] In some implementations, the wearable device may further include a third bandpass filter configured to perform bandpass filtering on the baseline-removed ACC signal, and the processor is further configured to obtain a second respiration rate of the user based on the bandpass filtered ACC signal.
[0018] In some implementations, the frequency band of the signal allowed to pass through the third bandpass filter is from 0.1 Hz to 0.5 Hz.
[0019] According to a second aspect, the present application provides a method for assessing a respiratory infection based on a wearable device. The method may include obtaining an audio signal of a user; obtaining a physiological parameter signal of the user; obtaining a respiratory rate of the user based on the physiological parameter signal; and obtaining a respiratory infection assessment report of the user based on the audio signal and the respiratory rate. It should be understood that the risk of the user suffering from a respiratory infection may be assessed based on the respiratory infection assessment report. Furthermore, according to the method, a respiratory infection can be detected at an early stage, which helps medical personnel to perform confirmation, intervention and treatment to prevent the respiratory infection from worsening.
[0020] In some implementations, obtaining the physiological parameter signal of the user specifically includes obtaining a PPG signal of the user, the PPG signal including the physiological parameter signal. Obtaining a respiration rate of the user based on the physiological parameter signal specifically includes obtaining a first respiration rate of the user based on the PPG signal. In some cases, a respiratory infection assessment report of the user may be obtained based on the first respiration rate and the audio signal.
[0021] In some implementations, obtaining a physiological parameter signal of the user specifically includes obtaining a PPG signal and an ACC signal of the user, and each of the PPG signal and the ACC signal includes a physiological parameter signal. Obtaining a respiration rate of the user based on the physiological parameter signal specifically includes obtaining a first respiration rate of the user based on the PPG signal; obtaining a second respiration rate of the user based on the ACC signal; and performing filtering and fusion on the first respiration rate and the second respiration rate to obtain a third respiration rate of the user. It should be understood that since the third respiration rate is obtained based on the first respiration rate and the second respiration rate, the accuracy of the measured respiration rate may be improved. Based on this, the accuracy of the respiratory infection assessment report may be improved.
[0022] In some implementations, before the step of acquiring the user's physiological parameter signal, the method further includes: acquiring the user's ACC signal; acquiring the user's posture classification result based on the ACC signal, where the posture classification result includes a first posture and a second posture, the first posture includes a state in which the user's wearing position is stressed for support, and the second posture includes a state in which the user's wearing position is naturally placed. It should be understood that due to the detection of the user's posture, the corresponding respiratory rate is used to acquire the respiratory infection assessment report, thereby improving the accuracy of the assessment report.
[0023] In some implementations, the step of obtaining a user posture classification result based on the ACC signal specifically includes the steps of calculating the average value and standard deviation of the ACC signal; performing low-pass filtering on the ACC signal and calculating the power spectrum of the ACC signal to obtain the position and amplitude of the peak point of the power spectrum, where the cutoff frequency of the low-pass filtering is 1 Hz; and inputting the average value and standard deviation of the ACC signal and the position and amplitude of the peak point of the power spectrum into a classification model to obtain a posture classification result.
[0024] In some implementations, obtaining a respiratory infection assessment report of the user based on the audio signal and the respiratory rate specifically includes obtaining a respiratory infection assessment report based on a first respiratory rate and the audio signal when the user is in a first position; or obtaining a respiratory infection assessment report based on a third respiratory rate and the audio signal when the user is in a second position. It should be understood that when the user is in the first position, the PPG sensor may obtain a PPG signal having a relatively high signal-to-noise ratio. Based on this, a first respiratory rate may be obtained based on the PPG signal, and a respiratory infection assessment report may be further obtained. When the user is in the second position, in addition to the PPG signal, the ACC sensor may also obtain an ACC signal having a relatively high signal-to-noise ratio. Based on this, a third respiratory rate may be obtained based on the first respiratory rate and the second respiratory rate, and a respiratory infection assessment report may be further obtained.
[0025] In some implementations, the method may further include prompting the user to switch to a second position when the user is in the first position and the first breathing rate exceeds a preset range; and obtaining a third breathing rate based on the PPG signal and the ACC signal in response to the user performing an operation to switch to the second position.
[0026] According to a third aspect, the present application further provides a wearable device. The wearable device may include a processor, an ACC sensor, and a PPG sensor. The ACC sensor is configured to acquire an ACC signal of a user. The PPG sensor is configured to acquire a PPG signal of a user. The processor is configured to acquire a posture classification result of the user based on the ACC signal, the posture classification result including a first posture and a second posture, the first posture including a state in which the user's wearing position is stressed for support, and the second posture including a state in which the user's wearing position is naturally placed. When the user is in the first posture, the processor is further configured to acquire a first respiratory rate of the user based on the PPG signal. When the user is in the second state, the processor is further configured to acquire a first respiratory rate of the user based on the PPG signal, acquire a second respiratory rate of the user based on the ACC signal, and perform filtering and fusion on the first respiratory rate and the second respiratory rate to acquire a third respiratory rate of the user. It should be understood that the wearable device may acquire a posture classification result based on the detection of the user's posture. In addition, the wearable device can improve the accuracy of the measured respiration rate by acquiring the user's respiration rate in a manner that corresponds to the posture classification result.
[0027] According to a fourth aspect, the present application further provides a method for measuring a respiration rate based on a wearable device. The method may include: acquiring an ACC signal and a PPG signal of a user; acquiring a posture classification result of the user based on the ACC signal, where the posture classification result includes a first posture and a second posture, the first posture includes a state in which the user's wearing position is stressed for support, and the second posture includes a state in which the user's wearing position is naturally placed; acquiring a first respiration rate of the user based on the PPG signal when the user is in the first posture; or acquiring a first respiration rate of the user based on the PPG signal, acquiring a second respiration rate of the user based on the ACC signal, and performing filtering and fusion on the first respiration rate and the second respiration rate to obtain a third respiration rate of the user when the user is in the second state. It should be understood that the posture classification result may be acquired based on the detection of the posture of the user. In addition, the accuracy of the measured respiration rate may be improved by acquiring the user's respiration rate in a manner corresponding to the posture classification result.
[0028] According to the present application, a respiratory infection assessment report of a user is obtained by acquiring a user's voice signal and physiological parameter signal, whereby a respiratory infection assessment can be implemented, based on which a respiratory infection can be detected at an early stage to facilitate confirmation, intervention and treatment. [Brief description of the drawings]
[0029] [Figure 1] FIG. 1 is a diagram of a framework for a wearable device according to an embodiment of the present application.
[0030] [Diagram 2] FIG. 1 is a diagram of a framework for a wearable device according to an embodiment of the present application.
[0031] [Diagram 3] FIG. 1 is a diagram of a framework for obtaining a first respiratory rate based on a PPG signal according to an embodiment of the present application.
[0032] [Figure 4] FIG. 1 is a diagram of a framework for obtaining a second respiratory rate based on an ACC signal according to an embodiment of the present application.
[0033] [Diagram 5] FIG. 2 is a schematic diagram of a user in a first position.
[0034] [Figure 6] FIG. 2 is a schematic diagram of a user in a second position.
[0035] [Figure 7] FIG. 1 is a diagram of a framework for obtaining pose classification results based on an ACC signal according to an embodiment of the present application.
[0036] [Figure 8] FIG. 2 is a schematic diagram of an interaction interface of a wearable device according to an embodiment of the present application.
[0037] [Figure 9] 1 is a flow chart of a method for assessing a respiratory infection, according to one embodiment of the present application.
[0038] [Figure 10] 1 is a flowchart of a method for obtaining a first respiratory rate based on a PPG signal according to an embodiment of the present application.
[0039] [Figure 11] 1 is a flowchart of a method for obtaining a first respiratory rate based on an ACC signal according to an embodiment of the present application.
[0040] [Figure 12] 1 is a flowchart of a method for extracting pose-related features according to an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0041] The terms used in the embodiments of the present application are intended to describe particular embodiments only and are not intended to limit the present application. Unless the context clearly dictates otherwise, the singular terms "a," "an," "the," "the," "the," and "a" used in the present specification and the appended claims are intended to include the plural forms.
[0042] References to "one embodiment" or "some embodiments" as described herein indicate that at least one embodiment of the present application includes a particular feature, structure, or characteristic described with reference to that embodiment. Thus, the descriptions "in one embodiment," "in some embodiments," "in some other embodiments," "in other embodiments," and "in some implementations" appearing in different places in this specification do not necessarily refer to the same embodiment, unless specifically emphasized otherwise, but mean "one or more, but not all of the embodiments." Unless specifically emphasized otherwise in a different manner, the terms "including," "comprising," and "having," and variations thereof, all mean "including, but not limited to."
[0043] The common wearable device can be worn by a user at a user's wearing position to obtain the user's physiological parameters, such as heart rate, electrocardiogram signal, blood oxygen saturation, and body temperature. The wearing position may be, for example, the user's wrist, upper arm, or forearm. Based on this, when the user needs to see these physiological parameters, the user may see these physiological parameters by using the wearable device; or the user may see these physiological parameters by using a smart terminal wirelessly connected to the wearable device, which may be a mobile phone; or the medical staff may see these physiological parameters by using a smart terminal wirelessly connected to the wearable device, which may be a bedside monitor or a central station.
[0044] It should be understood that common wearable devices typically only provide the functionality of acquiring and displaying physiological parameters, but are unable to assess the user's risk of suffering from a disease based on these physiological parameters.
[0045] A disease such as a respiratory infection usually affects the user's physical condition. For example, the user tends to have symptoms such as coughing, difficulty in breathing, or fever. However, in the early stage of a respiratory infection, the user's physical condition changes slightly and the physiological parameters fluctuate slightly. For these changes, it is generally difficult for the user to perceive the early symptoms of a respiratory infection, and common wearable devices cannot implement respiratory infection evaluation based on the acquired physiological parameters.
[0046] Due to the above-mentioned problems, the following embodiments of the present application provide a wearable device and a method for assessing respiratory infection based on the wearable device. According to the wearable device and method, a user's respiratory infection assessment report may be obtained by acquiring the user's voice signal and physiological parameter signal, and thus the risk of the user suffering from respiratory infection may be recognized. In some cases, based on the wearable device and method provided in the following embodiments, respiratory infection can be detected at an early stage, which advances disease prevention and treatment techniques and facilitates intervention and treatment.
[0047] In some embodiments, the wearable device may be a wearable watch. In some other embodiments, the wearable device may alternatively be an electronic device such as a wearable blanket or a wearable monitor. This is not limited thereto.
[0048] It should be understood that in addition to implementing respiratory infection assessment, the wearable device provided in the embodiment may further implement functions such as fall detection, wireless communication or message reminders, etc., but is not limited thereto.
[0049] Please refer to FIG. 1. The wearable device 10 provided in one embodiment of the present application may include a processor 12 and a first sensor 14. The processor 12 may be electrically or wirelessly connected to the first sensor 14. This is not limited. The first sensor 14 may be configured to acquire an audio signal of the user 20. The audio signal may be used to measure the sound generated by the user 20 and emanating from the respiratory system of the user 20. It should be understood that the first sensor 14 may be further configured to acquire the sound generated by the user 20 within a preset period. The preset period may be, for example, 10 seconds, 20 seconds, 30 seconds, or 1 minute. This is not limited.
[0050] In some embodiments, the wearable device 10 may prompt the user 20 to cough. The first sensor 14 may measure the cough to obtain an audio signal. Based on the audio signal, the processor 12 may perform an analysis with reference to another signal to assess the risk of the user 20 suffering from a respiratory infection and indicate the risk in the form of a respiratory infection assessment report.
[0051] As described above, the wearable device 10 may prompt the user 20 to make a sound in various ways. For example, the wearable device 10 may prompt the user 20 to cough by using audio, or may display information about prompting the user 20 to cough. Based on this, after the user 20 coughs, the wearable device 10 may obtain an audio signal in response to the cough made by the user 20.
[0052] In some other embodiments, the smart terminal may alternatively prompt the user 20 to cough in various ways, so that the first sensor 14 can collect the cough. For example, the smart terminal may prompt the user 20 by using voice or by displaying an image. After the user 20 coughs, the wearable device 10 may acquire an audio signal in response to the cough made by the user 20.
[0053] It should be understood that for a user 20 without any respiratory infection and a user 20 with a respiratory infection, there is a large difference between the coughs emanating from the respiratory system of each of these users 20. Accordingly, this difference may be reflected in the respective audio signals. Based on this, the processor 12 may perform operations such as feature extraction on the audio signals, classify the audio signals through machine learning or the like, which helps in later assessment of the risk of the user 20 suffering from a respiratory infection.
[0054] In some embodiments, the processor 12 may be, but is not limited to, a MCU (Microcontroller Unit) or a CPU (Central Processing Unit) in the wearable device 10. The processor 12 may alternatively be a circuit board component in the wearable device 10. The circuit board component may be integrated with electronic components such as the MCU, CPU, radio frequency chips or filters.
[0055] Further, see FIG. 1. In some embodiments, the wearable device 10 may further include a second sensor 16. Similar to the first sensor 14, the second sensor 16 may be electrically or wirelessly connected to the processor 12. The second sensor 16 may be configured to acquire a physiological parameter signal of the user 20. The physiological parameter signal may include at least one signal used to measure the respiration rate of the user 20. For example, the physiological parameter signal may include, but is not limited to, a PPG signal and an ACC signal, which will be described later. Based on the number and type of sensors provided for the wearable device 10, the physiological parameter signal may further include a signal used to measure a physiological parameter such as a heart rate, an electrocardiogram signal, or blood oxygen saturation of the user 20.
[0056] It should be understood that for a user 20 suffering from a respiratory infection, the physiological parameters of the user 20 generally generate abnormal fluctuations. The abnormal fluctuations may indicate that at least some of the physiological parameters of the user 20 exceed normal standards. Based on this, in the wearable device 10 provided in the embodiment of the present application, the processor 12 may analyze the audio signal and the physiological parameter signal of the user 20 to determine whether the physical condition of the user 20 has changed. Therefore, the risk of the user 20 suffering from a respiratory infection may be comprehensively evaluated.
[0057] In some embodiments, after a respiratory infection assessment is performed on the user 20, the respiratory infection assessment report corresponding to the user 20 may record information such as "no abnormalities found", "low risk of suffering from respiratory infection", "medium risk of suffering from respiratory infection", or "high risk of suffering from respiratory infection". It should be understood that the wearable device 10 may display the corresponding respiratory infection assessment report on the interaction interface of the wearable device 10, so that the user 20 or a medical professional can view the report. Alternatively, the smart terminal may similarly display the respiratory infection assessment report on the interaction interface of the smart terminal. This is not limited.
[0058] For example, for a user 20 with an early respiratory infection, it is relatively difficult for the user 20 to notice the physical changes generated when the user's 20 body deals with the respiratory infection. However, the second sensor 16 of the wearable device 10 can obtain a physiological parameter signal corresponding to the physical changes of the user 20. The processor 12 can analyze the physiological parameter signal to obtain the respiratory rate of the user 20. Based on this, it is found through the analysis that the respiratory rate of the user 20 is abnormal. Then, a respiratory infection evaluation report of the user 20 can be obtained with reference to the voice signal of the user 20. The evaluation report can record information about a high risk of respiratory infection.
[0059] It should be understood that the user 20 can easily and quickly perform a respiratory infection assessment by using the wearable device 10 provided in the embodiment of the present application. In some cases, the wearable device 10 can detect a respiratory infection at an early stage, so that medical personnel can confirm, intervene and treat the respiratory infection to prevent the respiratory infection from worsening.
[0060] Please refer to FIG. 2. In some embodiments, the second sensor 16 may include a PPG (Photoplethysmography) sensor 16a. The PPG sensor 16a may acquire a PPG signal of the user 20. It should be understood that due to the commonality of human body structure, the breathing action of the user 20 affects the flow of blood in blood vessels. Accordingly, this effect may be reflected in the acquired PPG signal. Based on this, the processor 12 may extract a feature signal related to the breathing action of the user 20 as a physiological parameter signal from the PPG signal, and thus may calculate a first breathing rate of the user 20 based on the physiological parameter signal.
[0061] In some embodiments, the second sensor 16 may further include an ACC (Accelerometer) sensor 16b. The ACC sensor 16b may acquire an ACC signal of the user 20. It should be understood that the breathing motion of the user 20 may cause fluctuations in the thoracic and abdominal cavities of the user 20, causing the upper limbs of the user 20 to swing. In some cases, the motion of swinging the upper limbs may be imaged by the ACC sensor 16b and modulated in the ACC signal. Based on this, the processor 12 may extract a feature signal related to the breathing motion of the user 20 as a physiological parameter signal from the ACC signal, thereby calculating a second breathing rate of the user 20 based on the physiological parameter signal.
[0062] In some embodiments, the PPG signal or the ACC signal may also be understood as a physiological parameter signal. The wearable device 10 may process the PPG signal and the ACC signal to obtain the respiration rate of the user 20, but it is not necessary to extract a feature signal related to the respiration rate as a physiological parameter signal from the PPG signal or the ACC signal.
[0063] In some embodiments, there may be multiple first sensors to improve the accuracy of the acquired signal, and there may also be multiple second sensors to improve the accuracy of the acquired signal.
[0064] See Fig. 3. In some embodiments, the wearable device 10 may further include a first band-pass filter 18a and a second band-pass filter 18b corresponding to the PPG signal. The first band-pass filter 18a may be configured to perform band-pass filtering on the PPG signal to obtain the positions of peak points and valley points of the PPG signal. Similarly, the second band-pass filter 18b may be configured to perform band-pass filtering on the PPG signal to obtain the waveform of the PPG signal.
[0065] The amplitude of the peak and valley points of the PPG signal can be obtained by matching the waveform of the PPG signal with the positions of the peak and valley points.Baseline Wander (BW) features, Amplitude Modulation (AM) features and Frequency Modulation (FM) features related to the respiration rate can be obtained based on the positions and amplitudes of the peak and valley points of the PPG signal.Based on this, a first respiration rate based on the PPG signal can be obtained by performing calculations on the baseline wander feature, the amplitude modulation feature and the frequency modulation feature.
[0066] In some embodiments, the frequency band of signals allowed to pass through the first bandpass filter 18a may be from 0.5 Hz to 10 Hz; and the frequency band of signals allowed to pass through the second bandpass filter 18b may be from 0.1 Hz to 10 Hz.
[0067] See FIG. 4. In some embodiments, for the ACC signal, baseline removal may be performed on the ACC signal by using software to prevent baseline fluctuation interference of the ACC signal. The wearable device 10 may further include a third bandpass filter 18c. The third bandpass filter 18c may be configured to perform bandpass filtering on the baseline-removed ACC signal to secure a frequency band corresponding to the respiration rate. The processor 12 may further be configured to perform wave peak extraction on the bandpass filtered ACC signal to obtain a second respiration rate based on the ACC signal.
[0068] In some embodiments, the frequency band of signals allowed to pass through the third bandpass filter 18c may be from 0.1 Hz to 0.5 Hz.
[0069] In some embodiments, the processor 12 may be further configured to perform filtering and fusion on the first and second respiratory rates to obtain a third respiratory rate of the user 20.
[0070] It should be understood that, compared with the first respiratory rate obtained based on the PPG signal, the second respiratory rate obtained based on the ACC signal is more accurate. However, the ACC signal is also more likely to be affected by the wearing manner of the wearable device 10 and the swaying and posture of the user 20, resulting in a more limited range of application. In some cases, a third respiratory rate, which is more accurate, can be obtained by performing filtering and fusion on the first respiratory rate and the second respiratory rate. Thus, the accuracy of the respiratory infection assessment report can be improved.
[0071] In some embodiments, the first respiratory rate, the second respiratory rate, and the third respiratory rate may be understood as respiratory rates of the user 20 obtained in different manners. In the wearable device 10 provided in the embodiment, the respiratory infection assessment report of the user 20 is mainly obtained based on the first respiratory rate or the third respiratory rate, but the present application is not limited thereto.
[0072] In some other embodiments, a respiratory infection assessment report for the user 20 may be obtained based on the second respiratory rate.
[0073] In some embodiments, the processor 12 may be further configured to obtain a posture classification result of the user 20 based on the ACC signal obtained by the ACC sensor 16b.
[0074] It should be understood that the ACC signal may include a three-axis acceleration signal associated with the user 20. A posture classification result of the user 20 may be obtained by analyzing the ACC signal. The wearable device 10 may obtain the respiration rate of the user 20 in a different manner based on the posture classification result to improve the accuracy of the respiratory infection assessment report.
[0075] The posture classification result may include a first posture and a second posture. The first posture may indicate a state in which the mounting position of the user 20 is stressed for support. The second posture may indicate a state in which the mounting position of the user 20 is naturally arranged.
[0076] When the user 20 is in a first posture, a first respiration rate of the user 20 may be obtained based on the PPG signal. When the user 20 is in a second posture, a third respiration rate of the user 20 may be obtained based on the PPG signal and the ACC signal. It should be understood that the wearable device 10 may adaptively select a corresponding measurement method based on the posture classification result. Thus, the accuracy of the measured respiration rate may be improved.
[0077] In some embodiments, the wearable device 10 may prompt the user 20 on an interaction interface to perform a respiration rate measurement based on the first posture or the second posture.
[0078] In some other embodiments, the wearable device 10 may further automatically obtain a posture classification result of the user 20 based on the ACC signal. A corresponding sensor (14, 16a or 16b) may be selected based on the posture classification result to cooperate with the processor 12 in obtaining the respiration rate of the user 20.
[0079] It should be understood that when the user 20 is in a specific first or second posture, interference caused by the external environment and inadvertent shaking or trembling of the user 20 may be eliminated. Based on this, the wearable device 10 may acquire a PPG signal or an ACC signal with a relatively high signal-to-noise ratio, so that the accuracy of the acquired first or third respiratory rate and the accuracy of the respiratory assessment report may be improved.
[0080] An example in which the wearable device 10 is a watch and is worn on the wrist of the user 20 is used for the purpose of explanation.
[0081] FIG. 5 shows a schematic diagram of a user in a first posture. Please refer to FIG. 1 to FIG. 5 synchronously. The forearms of a seated user 20 are stably placed on a table; there is an interaction force between the forearms of the user 20 and the table. In this case, a PPG signal of the user 20 can be obtained based on the PPG sensor 16a. A first respiratory rate of the user 20 can be obtained by processing the PPG signal.
[0082] FIG. 6 shows a schematic diagram of a user in a second posture. Please refer to FIG. 1 to FIG. 6 synchronously. The palms of the sitting user 20 are naturally placed on the thighs of the user 20, and the wrists of the user 20 are naturally relaxed. In this case, when the user 20 has a breathing motion, the PPG sensor 16a may acquire a PPG signal of the user 20, and the ACC sensor 16b may acquire an ACC signal of the user 20. Accordingly, a first breathing rate and a second breathing rate may be acquired by processing the PPG signal and the ACC signal. The processor 12 may be further configured to perform filtering and fusion on the first breathing rate and the second breathing rate to acquire a third breathing rate of the user 20.
[0083] It should be understood that the first posture in Fig. 5 and the second posture in Fig. 6 are merely used as examples for explanation, and the present application is not limited thereto. In some other embodiments, specifically, the first posture may further include a state in which both forearms of the user 20 are placed on the armrests of a chair. Specifically, the second posture may further include a state in which the palms of the user 20 who is sitting are placed on the abdomen of the user 20, or a state in which both arms of the user 20 who is standing are naturally lowered.
[0084] In some embodiments, the processor 12 may extract posture-related features from the ACC signal and input the extracted features into a classification model that may classify postures of the user 20 based on these features and distinguish between a first posture and a second posture.
[0085] In some embodiments, the classification model may include a Support Vector Machine (SVM), a decision tree, XGBoost, a neural network, or deep learning, etc.
[0086] See FIG. 7. In some embodiments, the processor 12 may calculate the average value and standard deviation of the ACC signal. In addition, the wearable device 10 may further include a low-pass filter 18d. The low-pass filter 18d is configured to perform low-pass filtering on the ACC signal. The cutoff frequency of the low-pass filter 18d is 1 Hz.
[0087] The processor 12 may further calculate the power spectrum of the low-pass filtered ACC signal to obtain the position and amplitude of the peak point of the power spectrum. The classification model may classify the ACC signal based on the mean value and standard deviation of the ACC signal and the position and amplitude of the peak point of the power spectrum to determine the posture of the current user 20. For example, after the ACC signal is processed, it is determined that the posture of the current user 20 is a first posture; or it is determined that the posture of the current user 20 is a second posture.
[0088] In some embodiments, the wearable device 10 may display a guide picture of the first posture or the second posture on the interaction interface of the wearable device 10 to guide the user 20 to adjust his / her posture accordingly. In some other embodiments, the smart terminal may alternatively display a guide picture of the first posture or the second posture on the interaction interface of the smart terminal. This is not limited.
[0089] In some embodiments, if the respiratory rate of the user 20 (e.g., the first respiratory rate or the third respiratory rate) is beyond a preset range, the wearable device 10 may further display prompt information on the interaction interface of the wearable device 10. The prompt information may prompt the user 20 to switch posture and perform the measurement again. If the user 20 selects to switch posture and perform the measurement again, a signal may be acquired based on the posture after switching by using a corresponding sensor. If the user 20 does not select to switch posture or does not actively select to switch posture, the risk of the user 20 suffering from a respiratory infection may be evaluated based on the initially acquired respiratory rate.
[0090] In some embodiments, the prompt information of the wearable device 10 may alternatively prompt the user 20 to adjust the position of the wearable device 10 in the wearing position or to rewear the wearable device 10.
[0091] In some embodiments, the preset range of respiration rate may be from 9 BPM to 24 BPM, where BPM is an abbreviation for Breaths Per Minute.
[0092] For example, when the user 20 is in the first position, the respiration rate of the user 20 acquired by the wearable device 10 is 8 BPM, that is, the respiration rate exceeds a preset range of the respiration rate. Based on this, the user 20 may be prompted on the interaction interface of the wearable device 10 to switch to the second position and perform detection again. If the user 20 selects to perform the switch, the wearable device 10 may measure the respiration rate of the user 20 again in response to the operation of the user 20. If the user 20 does not select to perform the switch, the wearable device 10 may acquire a respiratory infection assessment report of the user 20 based on the previously acquired respiration rate (i.e., 8 BPM) by referring to the audio signal.
[0093] In some embodiments, in the process of implementing a respiratory infection assessment, the wearable device 10 may further provide prompt information in the form of pictures, text or voice, etc., to prompt the user 20 to perform related operations.
[0094] See FIG. 8. In some embodiments, the wearable device 10 may display a respiratory infection assessment report and may further display information related to the respiratory rate. For example, the wearable device may exemplarily display the change in the respiratory rate of the user 20 within a certain period of time. This period may be the last few minutes, tens of minutes, or hours. As shown in FIG. 8, for example, the respiratory infection assessment report indicates that no abnormalities are found, and the wearable device 10 further displays the change in the respiratory rate of the user 20 from 1 hour to 7 hours.
[0095] In some embodiments, the wearable device 10 may be further configured to measure the respiration rate of the user 20 in daily work and life. For example, the first respiration rate or the third respiration rate is obtained accordingly based on the posture of the user 20. The first respiration rate or the third respiration rate may be displayed in real time on a main interface or a default interface of the wearable device, so that the user 20 can see the first respiration rate or the third respiration rate. The main interface may be an interface defined by a manufacturer, or may be an interface that is displayed after the wearable device is powered on and is visible to the user without requiring any operation. The default interface may be an interface provided for user-defined settings in the wearable device, or the default interface may be the main interface.
[0096] It should be understood that for some wearable devices, after different theme plugins are loaded, the main interface of these wearable devices may or may not display the respiration rate, but the main interface should still be considered as the main interface or default interface in the above embodiments.
[0097] See Figure 9. An embodiment of the present application further provides a method for assessing respiratory infection based on a wearable device. Similar to the wearable device provided in the above embodiment, this method can also implement respiratory infection assessment. This method can include, but is not limited to, the following steps:
[0098] 101: Acquire a user's voice signal.
[0099] In some embodiments, the audio signal may be used to measure sounds made by the user and emanating from the user's respiratory system, for example the audio signal may be obtained by measuring a cough made by the user, and based on the audio signal and with reference to another signal, an analysis may be performed according to the method to assess the risk of the user suffering from a respiratory infection and present the risk in the form of a respiratory infection assessment report.
[0100] In some embodiments, the user may be prompted on an interaction interface of the wearable device to make a sound, for example, to cough. An audio signal is then acquired in response to the user coughing. Additionally, the user may alternatively be prompted on an interaction interface of the smart terminal to cough; and the wearable device may acquire an audio signal in response to the coughing.
[0101] It should be understood that there is a large difference between the coughs of normal users (without any respiratory infection) and users with respiratory infections. This difference may be reflected in the respective audio signals accordingly. Based on this, operations such as feature extraction may be performed on the audio signals; and the audio signals may be classified through machine learning, etc. This helps to later assess the risk of the user suffering from a respiratory infection.
[0102] 102: Acquire a physiological parameter signal of a user.
[0103] The physiological parameter signal may be used to measure, but is not limited to, the user's breathing rate. Depending on the number and type of sensors provided for the wearable device, the physiological parameter signal may further be used to measure physiological parameters such as the user's heart rate, electrocardiogram signal, or blood oxygen saturation.
[0104] Provided there is no inconsistency, it should be understood that there is no necessary order between these steps. For example, with respect to step 101 and step 102, step 101 may be performed before step 102; or step 102 may be performed before step 101.
[0105] 103: Obtain a respiration rate of the user based on the physiological parameter signal.
[0106] The physiological parameter signal may be a part of a PPG signal or an ACC signal. The physiological parameter signal may be obtained by analyzing the PPG signal or the ACC signal. Then, the user's respiration rate may be obtained.
[0107] It should be understood that the PPG signal or the ACC signal can also be directly understood as a physiological parameter signal. According to this method, the PPG signal and the ACC signal can be processed to obtain the user's breathing rate; however, the feature signal related to the breathing rate does not necessarily need to be extracted from the PPG signal or the ACC signal as a physiological parameter signal.
[0108] 104: Obtain a respiratory infection assessment report of the user based on the audio signal and the respiratory rate.
[0109] In some embodiments, the user's respiratory rate is directly related to the user's respiratory health, so whether the user's physical condition has changed can be determined by analyzing the user's voice signal and respiratory rate. The user's risk of suffering from a respiratory infection can then be assessed overall.
[0110] In some embodiments, after a respiratory infection assessment is performed on a user, a respiratory infection assessment report corresponding to the user may record information such as "no abnormalities found", "low risk of suffering from respiratory infection", "medium risk of suffering from respiratory infection", or "high risk of suffering from respiratory infection". It should be understood that the respiratory infection assessment report may be shown on the interaction interface of the wearable device or smart terminal, so that the user can view the report.
[0111] For example, for a user with an early respiratory infection, it is relatively difficult for the user to notice the changes in the user's physical condition that are generated when the user's body deals with the respiratory infection. According to the method provided in the embodiment of the present application, the user's respiratory rate can be obtained by obtaining a physiological parameter signal corresponding to the change in the user's physical condition and analyzing the physiological parameter signal. Based on this, it is found through the analysis that the user's respiratory rate is abnormal. Then, a respiratory infection assessment report of the user can be obtained with reference to the user's voice signal. The assessment report records information indicating that the user is at high risk of suffering from a respiratory infection.
[0112] It should be understood that according to the method provided in the embodiment of the present application, a user can easily and quickly implement respiratory infection assessment by using a wearable device. In some cases, the respiratory infection can be detected at an early stage according to the method, so that medical personnel can confirm, intervene and treat the respiratory infection to prevent the respiratory infection from worsening.
[0113] In some embodiments, the respiratory infection assessment report further records information related to the respiratory rate. For example, the respiratory infection assessment report may record the user's respiratory rate distribution status over a period of time, which may be the last few minutes, tens of minutes, or hours.
[0114] Before step 101, the method provided in the embodiment of the present application may further include a step of detecting whether the user is wearing the wearable device.
[0115] In some embodiments, if the user is wearing the wearable device, step 101 may be executed to implement a respiratory infection assessment for the user.
[0116] In some other embodiments, if the user is not wearing the wearable device, step 101 is not executed. In some cases, to execute step 101, the method may further prompt the user on an interaction interface of the wearable device or smart terminal to wear the wearable device.
[0117] In some embodiments, in the aspect of obtaining a physiological parameter signal, the method may specifically include obtaining a PPG signal of the user.
[0118] It should be understood that a respiration-related feature signal may be extracted from the PPG signal as a physiological parameter signal, and the user's first respiration rate is calculated based on the physiological parameter signal.
[0119] See Figure 10. In some embodiments corresponding to a PPG signal, the method may specifically further include the following steps.
[0120] 111: Perform a first band-pass filtering on the PPG signal to obtain the positions of the peak points and valley points of the PPG signal.
[0121] In some embodiments, this filtering may be performed on the PPG signal by using a first bandpass filter, the frequency band of the signal allowed to pass through the first bandpass filter may be from 0.5 Hz to 10 Hz.
[0122] 112: Perform second band-pass filtering on the PPG signal to obtain the amplitudes of the peak points and valley points of the PPG signal by referring to the positions of the peak points and valley points of the PPG signal.
[0123] In some embodiments, this filtering may be performed on the PPG signal by using a second bandpass filter to obtain a waveform of the PPG signal. The amplitudes of the peaks and valleys of the PPG signal may be obtained by matching the waveform of the PPG signal with the positions of the peaks and valleys.
[0124] In some embodiments, the frequency band of the signal allowed to pass through the second bandpass filter may be from 0.1 Hz to 10 Hz.
[0125] 113: A first respiratory rate based on the PPG signal is obtained based on the positions and amplitudes of the peaks and valleys of the PPG signal.
[0126] In some embodiments, a baseline fluctuation feature, an amplitude modulation feature, and a frequency modulation feature related to a respiration rate can be obtained based on the positions and amplitudes of peaks and valleys of the PPG signal. A first respiration rate based on the PPG signal can be obtained by performing calculations on the baseline fluctuation feature, the amplitude modulation feature, and the frequency modulation feature.
[0127] In some embodiments, in aspects of obtaining a physiological parameter signal, the method may further specifically include obtaining an ACC signal of the user.
[0128] It should be understood that the user's breathing action may cause the user's chest and abdominal cavity to fluctuate, and the user's upper limbs to swing. In some cases, the action of swinging the upper limbs may be imaged by the ACC sensor and modulated in the ACC signal. Based on this, a breathing-related feature signal may be extracted from the ACC signal as a physiological parameter signal; and the user's second breathing rate is calculated based on the physiological parameter signal.
[0129] See Figure 11. In some embodiments, for an ACC signal, the method may specifically include the following steps:
[0130] 121: Perform baseline removal on the ACC signal.
[0131] Based on step 121, the baseline of the ACC signal may be removed through software to prevent baseline drift interference of the ACC signal, thereby improving the accuracy of the measured respiration rate.
[0132] 122: Perform band-pass filtering on the baseline removed ACC signal.
[0133] In some embodiments, this filtering may be performed on the ACC signal by using a third bandpass filter to capture the frequency band of the ACC signal corresponding to the respiratory rate. The frequency band of the signal allowed to pass through the third bandpass filter may be from 0.1 Hz to 0.5 Hz.
[0134] 123: Perform wave peak extraction on the filtered ACC signal to obtain a second respiratory rate based on the ACC signal.
[0135] In some embodiments, in aspects of obtaining a respiratory rate, the method may further include performing filtering and fusion on the first respiratory rate and the second respiratory rate to obtain a third respiratory rate of the user.
[0136] It should be understood that, compared with the first respiratory rate obtained based on the PPG signal, the second respiratory rate obtained based on the ACC signal is more accurate. However, the ACC signal is also more likely to be affected by the wearing manner of the wearable device and the user's swaying and posture, etc., resulting in a more limited range of application. In some cases, a third respiratory rate that is more accurate can be obtained by performing filtering and fusion on the first respiratory rate and the second respiratory rate. Thus, the accuracy of the respiratory infection assessment report can be improved.
[0137] In some embodiments, the first respiratory rate, the second respiratory rate and the third respiratory rate can be understood as the respiratory rates of the user obtained in different manners. In the method provided in the embodiment, the respiratory infection assessment report of the user is mainly obtained based on the first respiratory rate or the third respiratory rate, but the present application is not limited thereto. In some other embodiments, the user's respiratory infection assessment report may alternatively be obtained based on the second respiratory rate.
[0138] In some embodiments, in order to improve the accuracy of measuring the respiration rate, the method may further include obtaining a user posture classification result based on the ACC signal prior to the step of obtaining the physiological parameter signal.
[0139] It should be understood that the ACC signal may include a three-axis acceleration signal associated with the user. A posture classification result of the user may be obtained by analyzing the ACC signal. The respiration rate of the user may be obtained in a different manner based on the posture classification result to improve the accuracy of the respiratory infection assessment report.
[0140] In some embodiments, the posture classification result may include a first posture and a second posture. The first posture may indicate a state in which the user's wearing position is stressed for support. The second posture may indicate a state in which the user's wearing position is naturally positioned.
[0141] When the user is in a first posture, the first respiratory rate of the user can be obtained based on the PPG signal. When the user is in a second posture, the third respiratory rate of the user can be obtained based on the PPG signal and the ACC signal. It should be understood that the corresponding measurement method can be adaptively selected based on the posture classification result. Therefore, the accuracy of the measured respiratory rate and the accuracy of the respiratory infection assessment report can be improved.
[0142] In some embodiments, similar to prompting the user to produce a sound, the user may be prompted on an interaction interface of the wearable device to perform a respiration rate measurement based on the first or second posture.
[0143] In some other embodiments, the user's posture classification result can be further automatically obtained based on the ACC signal. A corresponding method for obtaining the user's breathing rate can be selected based on the posture classification result.
[0144] In some embodiments, in the aspect of obtaining a user posture classification result based on the ACC signal, the method may specifically include extracting posture-related features from the ACC signal and inputting the extracted features into a classification model, which may classify the user posture based on these features.
[0145] See Figure 12. In some embodiments, in the aspect of extracting posture-related features, the method may specifically include the following steps.
[0146] 131: Calculate the mean and standard deviation of the ACC signal.
[0147] 132: Perform low-pass filtering on the ACC signal.
[0148] In some embodiments, this filtering may be performed on the ACC signal by using a low pass filter, the cutoff frequency of which may be 1 Hz.
[0149] 133: Calculate the power spectrum of the low-pass filtered ACC signal to obtain the position and amplitude of the peak point of the power spectrum.
[0150] In some embodiments, the classification model may classify the ACC signal based on the mean and standard deviation of the ACC signal, and the location and amplitude of the peak point of the power spectrum, to determine the current user posture.
[0151] In some embodiments, the guide picture of the first posture or the second posture may be displayed on the interaction interface of the wearable device to guide the user to adjust his / her posture accordingly. In some other embodiments, the guide picture of the first posture or the second posture may alternatively be displayed on the interaction interface of the smart terminal. This is not limited.
[0152] In some embodiments, if the user's respiratory rate (e.g., the first respiratory rate or the third respiratory rate) is beyond a preset range, prompt information may be further displayed on the interaction interface of the wearable device. The prompt information may prompt the user to switch posture and perform detection again. If the user selects to switch posture and perform measurement again, a signal may be acquired based on the switched posture by using a corresponding sensor. If the user does not select to switch posture or does not actively select to switch posture, the risk of the user suffering from respiratory infection may be evaluated based on the initially acquired respiratory rate.
[0153] In some embodiments, the prompt information may alternatively prompt the user to adjust the position of the wearable device in the wearing position or to rewear the wearable device.
[0154] In some embodiments, the preset range of the respiration rate may be from 9 BPM to 24 BPM. For example, when the user is in the first position, the respiration rate of the user obtained based on the PPG signal is 25 BPM, that is, the respiration rate exceeds the preset range of the respiration rate. Based on this, the user may be prompted on the interaction interface of the wearable device to switch to the second position and perform detection again. If the user selects to perform the switch, the user's respiration rate may be measured again in response to the user's operation. If the user does not select to perform the switch, the user's respiratory infection assessment report may be obtained based on the previously obtained respiration rate (i.e., 26 BPM) with reference to the audio signal.
[0155] In some embodiments, the process of implementing the method for assessing a respiratory infection may further provide prompt information in the form of pictures, text, or audio, etc., to prompt the user to perform an associated operation.
[0156] In some embodiments, the method may further include providing guide information in the form of pictures, text, audio, etc. The guide information may be used to acquire and process the audio signals and the physiological parameter signals by guiding the user to perform associated operations.
Claims
1. a first sensor configured to acquire a voice signal of a user; a second sensor configured to acquire a physiological parameter signal of the user; and a processor configured to obtain a respiratory rate of the user based on the physiological parameter signal, and to obtain a respiratory infection assessment report of the user based on the audio signal and the respiratory rate. A wearable device comprising:
2. 2. The wearable device of claim 1, wherein the second sensor comprises a PPG sensor configured to acquire a PPG signal of the user, and the processor is configured to acquire a first respiratory rate of the user based on the PPG signal.
3. 3. The wearable device of claim 2, wherein the second sensor further comprises an ACC sensor, the ACC sensor configured to acquire an ACC signal of the user, and the processor is further configured to acquire a second respiration rate of the user based on the ACC signal.
4. 4. The wearable device of claim 3, wherein the processor is further configured to perform filtering and fusion on the first respiratory rate and the second respiratory rate to obtain a third respiratory rate of the user.
5. The processor is further configured to obtain a posture classification result of the user based on the ACC signal, the posture classification result including a first posture and a second posture, the first posture including a state in which a wearing position of the user is stressed for support, and the second posture including a state in which the wearing position of the user is naturally disposed; When the user is in the first position, the processor is configured to obtain the respiratory infection assessment report based on the first respiratory rate and the audio signal; and When the user is in the second position, the processor is configured to obtain the respiratory infection assessment report based on the third respiratory rate and the audio signal. The wearable device according to claim 3 or 4.
6. The wearable device further comprises a low pass filter, the low pass filter configured to perform low pass filtering on the ACC signal, the cutoff frequency of the low pass filter being 1 Hz; The processor is configured to calculate a mean value and a standard deviation of the ACC signal and calculate a power spectrum based on the low-pass filtered ACC signal to obtain a position and an amplitude of a peak point of the power spectrum; and The processor is further configured to input the mean value and the standard deviation of the ACC signal and the location and the amplitude of the peak point of the power spectrum into a classification model to obtain the posture classification result. The wearable device of claim 5 .
7. The processor is further configured to prompt the user to switch to the second position when the user is in the first position and the first breathing rate is above a preset range; and The processor is further configured to, in response to an operation for switching to the second position being performed by the user, obtain the third respiratory rate based on the PPG signal and the ACC signal, and obtain the respiratory infection assessment report based on the third respiratory rate and the audio signal. The wearable device of claim 5 .
8. The wearable device of claim 1 , wherein the wearable device is a wearable watch, a wearable blanket, or a wearable monitor.
9. 1. A method for assessing a respiratory infection based on a wearable device, comprising: obtaining a voice signal of a user; acquiring a physiological parameter signal of the user; obtaining a respiration rate of the user based on the physiological parameter signal; and obtaining a respiratory infection assessment report for the user based on the audio signal and the respiratory rate; A method comprising:
10. The step of acquiring a physiological parameter signal of the user specifically comprises: acquiring a PPG signal of the user, the PPG signal including the physiological parameter signal; and The step of obtaining a respiration rate of the user based on the physiological parameter signal specifically comprises: obtaining a first respiration rate of the user based on the PPG signal; have 10. The method of claim 9.
11. The step of acquiring a physiological parameter signal of the user specifically comprises: acquiring a PPG signal and an ACC signal of the user, wherein the PPG signal and the ACC signal each include the physiological parameter signal. and The step of obtaining a respiration rate of the user based on the physiological parameter signal specifically comprises: obtaining a first respiratory rate of the user based on the PPG signal; obtaining a second respiration rate of the user based on the ACC signal; and performing filtering and fusing on the first respiratory rate and the second respiratory rate to obtain a third respiratory rate of the user; have 10. The method of claim 9.
12. Prior to the step of acquiring a physiological parameter signal of the user, obtaining an ACC signal of the user; and obtaining a posture classification result of the user based on the ACC signal; wherein: The posture classification result includes a first posture and a second posture, the first posture including a state in which the wearing position of the user is stressed for support, and the second posture including a state in which the wearing position of the user is naturally disposed; and The step of obtaining a respiratory infection assessment report of the user based on the audio signal and the respiratory rate specifically includes: obtaining the respiratory infection assessment report based on the first respiratory rate and the audio signal when the user is in the first position; or obtaining the respiratory infection assessment report based on the third respiratory rate and the audio signal when the user is in the second position. having 12. The method according to any one of claims 9 to 11.
13. Specifically, the step of acquiring a posture classification result of the user based on the ACC signal includes: calculating the mean and standard deviation of the ACC signal; performing low-pass filtering on the ACC signal and calculating a power spectrum of the ACC signal to obtain a position and an amplitude of a peak point of the power spectrum, where a cutoff frequency of the low-pass filtering is 1 Hz; and inputting the mean value and the standard deviation of the ACC signal and the location and the amplitude of the peak point of the power spectrum into a classification model to obtain the posture classification result. having The method of claim 11.
14. when the user is in a first position and the first respiratory rate exceeds a preset range; prompting the user to switch to a second position; acquiring the third respiration rate based on the PPG signal and the ACC signal in response to an operation for switching to the second posture being performed by the user; and obtaining the respiratory infection assessment report based on the third respiratory rate and the audio signal. The method of claim 13 further comprising:
Citation Information
Patent Citations
Method and apparatus for measuring respiratory rate
JP2010535047A
System and method for continuous monitoring of respiratory ailments
WO2021022222A1
Cited By
Lung function evaluation method and device, electronic equipment and storage medium
CN120477747A
