Breathing anomaly detection method and device and wearable equipment

Abstract

The invention discloses a breathing anomaly detection method and device and wearable device.The method is applied to the wearable device, the wearable device is provided with a vibration sensor used for being attached to the nose wing of a wearer, and the method comprises the steps that a first vibration signal, collected by the vibration sensor, of the wearer is obtained; performing signal preprocessing on the first vibration signal to obtain a second vibration signal; and according to the second vibration signal, determining the breathing abnormality type of the wearer.

Description

Technical Field

[0001] The present invention relates to the technical field of breathing detection, and more specifically, to a breathing abnormality detection method, a breathing abnormality detection device, and a wearable device. Background Art

[0002] Wearable electronic devices, as a convenient health monitoring tool, have gradually become an indispensable part of people's daily lives. In particular, smart watches, bracelets and other devices can monitor users' heart rate, body temperature, blood oxygen saturation and other key physiological parameters in real time by integrating multiple sensors, providing users with instant feedback on health data.

[0003] However, when these wearable devices detect human breathing, they often indirectly obtain breathing parameters such as breathing rate through physiological parameters related to breathing, such as heart rate. For example, breathing rate can be inferred by analyzing the changing trend and pattern of heart rate data. Therefore, the breathing detection results obtained by this method are less accurate. Summary of the invention

[0004] One purpose of an embodiment of the present invention is to provide a new technical solution for abnormal breathing detection.

[0005] According to a first aspect of the present invention, a method for detecting abnormal breathing is provided, the method being applied to a wearable device, the wearable device being provided with a vibration sensor for fitting with a nose wing of a wearer, the method comprising:

[0006] Acquire a first vibration signal of the wearer collected by the vibration sensor;

[0007] performing signal preprocessing on the first vibration signal to obtain a second vibration signal;

[0008] The abnormal breathing type of the wearer is determined according to the second vibration signal.

[0009] Optionally, determining the abnormal breathing type of the wearer according to the second vibration signal includes:

[0010] extracting breathing characteristic information of the second vibration signal;

[0011] The wearer's breathing abnormality type is determined based on the breathing characteristic information.

[0012] Optionally, the breathing characteristic information includes periodic information and amplitude for characterizing whether the second vibration signal is a periodic signal, and determining the type of abnormal breathing of the wearer according to the breathing characteristic information includes:

[0013] When the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is less than an apnea threshold within a preset time period, determining that the wearer's breathing abnormality type is apnea;

[0014] When the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is greater than or equal to the apnea threshold within the preset time period, it is determined that the wearer's breathing abnormality type is irregular breathing.

[0015] Optionally, when the second vibration signal is a periodic signal, the breathing characteristic information further includes a vibration period, and determining the abnormal breathing type of the wearer according to the breathing characteristic information further includes:

[0016] When the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is greater than or equal to the deep breathing threshold and the vibration period is less than the vibration period threshold, determining that the wearer's abnormal breathing type is shortness of breath;

[0017] When the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is less than the shallow breathing threshold and the vibration period is greater than or equal to the vibration period threshold, determining that the wearer's abnormal breathing type is weak breathing;

[0018] When the periodic information indicates that the second vibration signal is a periodic signal and the amplitude change rate within the vibration period is greater than or equal to an amplitude change rate threshold, it is determined that the wearer's abnormal breathing type is respiratory twitch.

[0019] Optionally, after determining the abnormal breathing type of the wearer, the method further includes:

[0020] According to the abnormal breathing type of the wearer, corresponding prompt information is output.

[0021] Optionally, the acquiring the first vibration signal of the wearer collected by the vibration sensor includes:

[0022] Turning on the vibration sensor at the initial moment when detecting that the wearable device is in a worn state; wherein the vibration sensor continuously collects the first vibration signal when turned on;

[0023] A first vibration signal output by the vibration sensor is received.

[0024] Optionally, the wearable device further includes an acceleration sensor and a touch sensor, and detecting whether the wearable device is in a worn state includes:

[0025] Acquiring acceleration data collected by the acceleration sensor;

[0026] Determining whether the wearable device is in an upright state according to the acceleration data;

[0027] When the wearable device is in an upright state, acquiring touch data collected by the touch sensor;

[0028] Determining whether the wearable device is in a touched state according to the touch data;

[0029] When the wearable device is in a touched state, it is determined that the wearable device is in a worn state.

[0030] Optionally, performing signal preprocessing on the first vibration signal to obtain a second vibration signal includes:

[0031] Extracting a signal within a target frequency range from the first vibration signal to obtain a filtered first vibration signal; wherein the target frequency range is a range smaller than the second frequency and larger than the first frequency;

[0032] The filtered first vibration signal is subjected to signal amplification processing to obtain the second vibration signal.

[0033] According to a second aspect of the present invention, there is also provided a breathing abnormality detection device, which includes a memory and a processor, wherein the memory is used to store executable instructions; the processor is used to operate according to the control of the instructions to execute the method as described in the first aspect of the present invention.

[0034] According to a third aspect of the present invention, a wearable device is also provided, comprising a vibration sensor and the abnormal breathing detection device described in the second aspect, wherein the vibration sensor is used to collect a vibration signal of the person being detected and send it to the abnormal breathing detection device.

[0035] One beneficial effect of the present invention is that by collecting the first vibration signal through the vibration sensor that fits the nose of the wearer, real-time monitoring of the wearer's breathing can be achieved through a wearable device without adding extra burden, and compared with other respiratory detection devices that are inserted or close to the body, this data collection method has higher privacy and comfort. Then, by obtaining the first vibration signal of the wearer collected by the vibration sensor, the first vibration signal is preprocessed to obtain a second vibration signal, and the type of abnormal breathing of the wearer is determined according to the second vibration signal. Since the vibration signal is directly related to breathing, the accuracy of abnormal breathing detection can be improved compared to the method of indirectly determining the breathing rate through parameters such as heart rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0037] Figure 1 is a schematic diagram of the hardware structure of a wearable device according to an embodiment of the present invention;

[0038] Figure 2 is a flow chart of a breathing abnormality detection method according to an embodiment of the present invention;

[0039] Figure 3 (a) is a schematic diagram of a pair of glasses according to an example of the present invention in a normal state;

[0040] Figure 3 (b) is a schematic diagram of a pair of glasses according to an example of the present invention in a reversed state;

[0041] Figure 4 is a schematic diagram of waveforms of vibration signals corresponding to different types of abnormal breathing according to an example of the present invention;

[0042] Figure 5 is a waveform diagram of a second vibration signal according to an example of the present invention;

[0043] Figure 6 is a principle block diagram of a breathing abnormality detection device according to an embodiment of the present invention;

[0044] Figure 7 is a schematic diagram of the structure of a wearable device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0046] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0047] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0048] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0049] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0050] <Hardware Configuration>

[0051] Figure 1 is a block diagram of a hardware configuration of a wearable device 100 according to an embodiment of the present invention.

[0052] like Figure 1 As shown, the wearable device 100 includes a vibration sensor 1000 and a breathing abnormality detection device 2000.

[0053] Wearable devices can be AR glasses, VR glasses, headphones, smart helmets, smart masks, etc., without limitation here.

[0054] When the wearer wears the wearable device, the vibration sensor 1000 fits against the nose wing of the wearer to collect the vibration signal of the wearer, and provides the collected vibration signal to the abnormal breathing detection device 2000.

[0055] The vibration sensor 1000 may be a vibration timing dual sensor, a piezoelectric sensor, a VPU (Voice Pickup Unit), etc., which is not limited here.

[0056] In one embodiment, the vibration sensor 1000 may be a voice pickup unit VPU.

[0057] In this embodiment, since the VPU has strong resistance to environmental noise and wind noise, the VPU nose pad (i.e., the voice pickup unit VPU that fits the wearer's nose) has a higher performance in picking up vibration signals, so it is more effective to use the VPU as a vibration sensor.

[0058] The abnormal breathing detection device 2000 can perform abnormal breathing detection based on the first vibration signal.

[0059] In this embodiment, refer to Figure 1 As shown, the breathing abnormality detection device 2000 may include a processor 2100, a memory 2200, an interface device 2300, a communication device 2400, a display device 2500, an input device 2600, a speaker 2700, a microphone 2800, and the like.

[0060] The processor 2100 may be a mobile version processor. The memory 2200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 2300 may include, for example, a USB interface, a headphone interface, etc. The communication device 2400 may, for example, be capable of wired or wireless communication. The communication device 2400 may include a short-range communication device, for example, any device for short-range wireless communication based on short-range wireless communication protocols such as Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, Bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, etc. The communication device 2400 may also include a remote communication device, for example, any device for WLAN, GPRS, 2G / 3G / 4G / 5G remote communication. The display device 2500 may be, for example, a liquid crystal display, a touch display, etc., and the display device 2500 is used to display the results of abnormal breathing detection. The input device 2600 may include, for example, a touch screen, a keyboard, etc. The user may input / output voice information through the speaker 2700 and the microphone 2800.

[0061] In this embodiment, the memory 2200 of the abnormal breathing detection device 2000 is used to store instructions, which are used to control the processor 2100 to operate to at least perform the abnormal breathing detection method according to any embodiment of the present invention. A technician can design instructions according to the scheme disclosed in the present invention. How instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0062] Despite Figure 1 , multiple devices of the abnormal breathing detection device 2000 are shown, but the present invention may only involve some of the devices, for example, the abnormal breathing detection device 2000 only involves the memory 2200, the processor 2100 and the display device 2500.

[0063] In this embodiment, the vibration sensor is used to collect real-time vibration signals and provide them to the abnormal breathing detection device 2000. The abnormal breathing detection device 2000 implements the method according to any embodiment of the present invention based on the vibration signals to complete abnormal breathing detection.

[0064] In some embodiments, the wearable device also includes an acceleration sensor and a touch sensor.

[0065] The acceleration sensor is used to collect acceleration data and send it to the abnormal breathing detection device to detect whether the wearable device is in the upright state. The touch sensor is used to collect touch data and send it to the abnormal breathing detection device to determine whether the wearable device is in the touched state. When the wearable device is in the upright state and in the touched state, it is determined that the wearable device is in the worn state.

[0066] It should be understood that although Figure 1 Only one vibration sensor 1000 and one abnormal breathing detection device 2000 are shown, but this does not mean to limit the respective numbers. The wearable device 100 may include multiple vibration sensors 1000 and / or abnormal breathing detection devices 2000.

[0067] <Method Example>

[0068] Figure 2 2 is a flow chart of a breathing abnormality detection method according to an embodiment of the present invention, which can be implemented by a breathing abnormality detection device 2000 of a wearable device. The wearable device is provided with a vibration sensor for fitting with the nose wing of the wearer.

[0069] according to Figure 2 As shown, the breathing abnormality detection method of this embodiment may include the following steps S2100 to S2300:

[0070] Step S2100, obtaining a first vibration signal of the wearer collected by the vibration sensor.

[0071] In this embodiment, when people breathe, air enters and exits the nasal cavity, which causes changes in the internal pressure and air flow of the nasal cavity. These changes cause the nose wing and the surrounding tissue to produce tiny mechanical vibrations (i.e., breathing vibrations). When the vibration sensor of the wearable device is in direct contact with the nose wing, the vibration of the nose wing can be directly transmitted to the vibration sensor. Thus, the vibration sensor can collect the first vibration signal.

[0072] In one embodiment, the vibration sensor 1000 may be a voice pickup unit VPU.

[0073] In this embodiment, since the VPU has strong resistance to environmental noise and wind noise, the VPU nose pad (i.e., the voice pickup unit VPU that fits the wearer's nose) has a higher performance in picking up vibration signals, so it is more effective to use the VPU as a vibration sensor.

[0074] In order to avoid unnecessary abnormal breathing detection due to other environmental vibration signals when the wearable device is not worn, which in turn leads to the problem of false detection, and to save energy consumption of the wearable device, the vibration sensor can be turned on to collect vibration signals only when it is detected that the wearable device is being worn.

[0075] Based on this, in some embodiments, obtaining the first vibration signal of the wearer collected by the vibration sensor in step S2100 includes: step S2100.1 and step S2100.2.

[0076] Step S2100.1, turning on the vibration sensor at the initial moment when it is detected that the wearable device is in a worn state.

[0077] In this embodiment, the wearable device generally includes a sensor for wearing detection. The sensor for wearing detection may be, for example, an accelerometer, a proximity sensor, a heart rate sensor, etc., which are not limited here.

[0078] The sensor used for wearing detection can be used to identify whether the wearable device is already worn by the user.

[0079] The first vibration signal is continuously collected when the vibration sensor is turned on.

[0080] In one example, when it is detected that the wearable device is in a worn state, the power path of the vibration sensor can be controlled to be turned on to turn on the vibration sensor, and the vibration sensor continues to collect the first vibration signal. When it is detected that the wearable device is not worn, the power path of the vibration sensor can be controlled to be disconnected to turn off the vibration sensor.

[0081] In order to improve the accuracy of wearing detection, the acceleration data collected by the acceleration sensor and the touch data collected by the touch sensor can be combined to determine whether the wearable device is in a worn state.

[0082] Based on this, in some embodiments, the wearable device also includes an acceleration sensor and a touch sensor.

[0083] In this embodiment, the acceleration sensor may be, for example, an accelerometer. The touch sensor may be a capacitive touch sensor, a resistive touch sensor, a surface acoustic wave touch screen, etc., which are not limited here.

[0084] In these embodiments, detecting whether the wearable device is in a worn state includes: steps S1100 to S1500.

[0085] Step S1100, acquiring acceleration data collected by the acceleration sensor.

[0086] In this embodiment, the acceleration data may include acceleration values ​​of the wearable device in three spatial dimensions (X, Y, and Z axes).

[0087] Step S1200: determining whether the wearable device is in an upright state according to the acceleration data.

[0088] Exemplarily, the wearable device is glasses, such as Figure 3 As shown in (a), when the glasses are placed upright, that is, the lenses face forward and the temples face downward, the acceleration sensor will detect an acceleration close to the earth's gravity acceleration (about 9.8m / s 2), and this acceleration is mainly along the Z axis (assuming the Z axis is perpendicular to the ground). Figure 3 As shown in (b), that is, the lens faces backward and the temple faces upward, the acceleration sensor will also detect a signal close to the earth's gravity acceleration, but this acceleration signal will be mainly along the negative Z axis. Based on this, it can be determined whether there is a target acceleration value whose acceleration difference with the earth's gravity acceleration is within a set tolerance range according to the three-axis acceleration values ​​included in the acceleration data. If there is a target acceleration value, it is determined whether the glasses are placed right side up or inverted according to the acceleration direction corresponding to the target acceleration value.

[0089] Step S1300: When the wearable device is in an upright state, touch data collected by the touch sensor is acquired.

[0090] In this embodiment, the touch data includes touch value changes corresponding to different time points.

[0091] In an example where the corresponding touch sensor is a capacitive touch sensor, the touch data is capacitance data, which includes changes in capacitance over time. In an example where the corresponding touch sensor is a resistive touch sensor, the touch data is resistance data, which includes changes in resistance over time.

[0092] Step S1400: determining whether the wearable device is in a touched state according to the touch data.

[0093] In an example where the touch data is capacitance data, when the capacitance change rate is greater than or equal to the capacitance change rate threshold, it is determined that the wearable device is in a touched state, and when the capacitance change rate is less than the capacitance change rate threshold, it is determined that the wearable device is in an untouched state.

[0094] The capacitance change rate threshold can be obtained according to capacitance change rate data when the corresponding wearable device is touched during a touch experiment test.

[0095] In an example where the touch data is resistance data, when the resistance change rate is greater than or equal to the resistance change rate threshold, it is determined that the wearable device is in a touched state; when the resistance change rate is less than the resistance change rate threshold, it is determined that the wearable device is in an untouched state.

[0096] The resistance change rate threshold value can be obtained according to the resistance change rate data when the corresponding wearable device is touched during the touch experiment test.

[0097] Step S1500: when the wearable device is in a touched state, determining that the wearable device is in a worn state.

[0098] In this way, when the wearable device is in an upright state and in a touched state, it is determined that the wearable device is in a worn state, which can improve the accuracy of wearing detection.

[0099] Step S2100.2, receiving a first vibration signal output by the vibration sensor.

[0100] In this embodiment, while the vibration sensor continues to collect the first vibration signal, it also outputs the collected first vibration signal to the abnormal breathing detection device.

[0101] Step S2200: performing signal preprocessing on the first vibration signal to obtain a second vibration signal.

[0102] In this embodiment, the signal preprocessing may be denoising, amplification and other processing, which is not limited here.

[0103] In some embodiments, step S2200 performs signal preprocessing on the first vibration signal to obtain a second vibration signal, including: step S2200.1 and step S2200.2.

[0104] Step S2200.1, extracting a signal within a target frequency range from the first vibration signal to obtain a filtered first vibration signal.

[0105] In this embodiment, the target frequency range is a range smaller than the second frequency and larger than the first frequency.

[0106] In one example, the first frequency is 0 Hz and the second frequency is 10 Hz.

[0107] In this embodiment, when the vibration sensor collects the first vibration signal of nasal breathing, there will be some external interference burr signals, such as hair hitting the wearable device, wearable device shaking and other instantaneous high-frequency signals, and these signals usually have a frequency higher than 1KHz. The human breathing frequency can be from 12 times / minute to 100 times / minute. In most cases, the human breathing frequency is 30 times / minute to 40 times / minute, which is equivalent to a vibration signal of 0.5Hz. Therefore, after collecting the first vibration signal, the first vibration signal can be low-pass filtered with a cutoff frequency of 10Hz to filter out interference clutter and retain the vibration signal caused by breathing.

[0108] Step S2200.2, performing signal amplification processing on the filtered first vibration signal to obtain the second vibration signal.

[0109] In this embodiment, since the vibration signal caused by breathing is relatively weak, in order to facilitate the analysis of the filtered first vibration signal, the filtered first vibration signal may be amplified to obtain the second vibration signal.

[0110] Exemplarily, the filtered first vibration signal may be amplified by 100 dB.

[0111] Step S2300: determining the wearer's abnormal breathing type according to the second vibration signal.

[0112] In this embodiment, the wearer's abnormal breathing type can be determined by performing waveform analysis, frequency analysis, periodic detection, amplitude analysis, machine learning classification, etc. on the second vibration signal, which is not limited here.

[0113] Here are some examples of specific ways to determine the type of breathing abnormality:

[0114] Waveform analysis can be to observe the waveform of the second vibration signal, analyze its periodicity, amplitude and shape, compare it with the normal breathing waveform, and identify abnormal patterns. Frequency analysis can be to calculate the respiratory frequency (number of breaths per minute) in the second vibration signal, compare it with the normal respiratory frequency range, and identify fast or slow breathing. Machine learning algorithms such as support vector machines (SVM), random forests, neural networks, etc. are used to classify the second vibration signal and identify abnormal patterns.

[0115] In some embodiments, step S2300 determines the wearer's abnormal breathing type based on the second vibration signal, including: steps S2300.1 to S2300.2.

[0116] Step S2300.1, extracting breathing characteristic information of the second vibration signal.

[0117] In this embodiment, the breathing characteristic information may be characteristic information related to breathing.

[0118] In one example, the breathing characteristic information includes amplitude, which is used to characterize the change of the amplitude value of the second vibration signal over time, that is, the intensity of the vibration signal, which reflects the magnitude of the vibration during the breathing process.

[0119] In another example, the breathing characteristic information includes periodicity information and amplitude for characterizing whether the second vibration signal is a periodic signal.

[0120] In another example, the breathing characteristic information includes periodic information, amplitude, and vibration period for characterizing whether the second vibration signal is a periodic signal, wherein the vibration period is the length of time from the start of a specific vibration state to the start of the next specific state.

[0121] Step S2300.2, determining the wearer's breathing abnormality type based on the breathing characteristic information.

[0122] In the example where the breathing characteristic information includes amplitude, if the amplitude is less than an apnea threshold (eg, 0.1v) within a preset time period (eg, 10s), the wearer's breathing abnormality type is determined to be apnea.

[0123] In the example where the breathing characteristic information includes periodic information and amplitude for characterizing whether the second vibration signal is a periodic signal, if the periodic information characterizes that the second vibration signal is a periodic signal and the rate of change of the amplitude is greater than or equal to the amplitude change rate threshold, then the wearer's breathing abnormality type is determined to be respiratory convulsions.

[0124] In the example where the breathing characteristic information includes periodic information, amplitude, and vibration period for characterizing whether the second vibration signal is a periodic signal, if the periodic information characterizes that the second vibration signal is a periodic signal and the maximum amplitude is greater than or equal to the deep breathing threshold (e.g., 0.5v) and the vibration period is less than the vibration period threshold (e.g., 1s), then it is determined that the wearer's breathing abnormality type is shortness of breath.

[0125] In some embodiments, the breathing characteristic information includes periodic information used to characterize whether the second vibration signal is a periodic signal and an amplitude used to characterize that the amplitude value of the second vibration signal changes over time.

[0126] In these embodiments, step S2300.2 determines the wearer's abnormal breathing type based on the breathing characteristic information, including: steps S2300.21 to S2300.22.

[0127] Step S2300.21, when the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is less than an apnea threshold within a preset time period, determining that the wearer's abnormal breathing type is apnea.

[0128] In this embodiment, the apnea threshold may be determined according to the amplitude of a vibration signal measured by a vibration sensor of the wearable device during an apnea experiment.

[0129] Exemplarily, the apnea threshold may be 0.1V.

[0130] In one example, the waveform of the second vibration signal corresponding to apnea as the breathing abnormality type may be: Figure 4 As shown in figure ⑤.

[0131] Step S2300.22, when the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is greater than or equal to the apnea threshold within the preset time period, determine that the wearer's breathing abnormality type is irregular breathing.

[0132] In one example, the waveform of the vibration signal corresponding to the breathing abnormality type of irregular breathing can be as follows: Figure 4 As shown in figure ③.

[0133] It should be noted that, when the second vibration signal is a non-periodic signal, it is necessary to determine the type of breathing abnormality based on the change of the amplitude of the second vibration signal over time. When the second vibration signal is a periodically changing signal, breathing abnormality can be judged only for the second vibration signal within one cycle.

[0134] In some embodiments, when the second vibration signal is a periodic signal, the breathing characteristic information further includes a vibration period, wherein the vibration period may be the time required for the second vibration signal to return to the same state after a complete vibration period starting from a certain state (e.g., a starting point).

[0135] In these embodiments, the second vibration signal is a periodic signal, and in this case, judging the abnormal breathing type according to the second vibration signal can be to detect the abnormal breathing type within a vibration period of the second vibration signal to obtain the abnormal breathing type corresponding to the second vibration signal. That is, step S2300.21 determines the abnormal breathing type of the wearer according to the breathing characteristic information and further includes: step S2300.23 and step S2300.25.

[0136] Step S2300.23, when the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is greater than or equal to the deep breathing threshold and the vibration period is less than the vibration period threshold, determine that the wearer's abnormal breathing type is shortness of breath.

[0137] In this embodiment, the deep breathing threshold may be determined according to the amplitude of a vibration signal measured by a vibration sensor of the wearable device during a deep breathing experiment.

[0138] In one example, the deep breathing threshold may be 0.5V.

[0139] The vibration cycle threshold may be the time corresponding to one normal breath. In this case, the vibration cycle threshold may also be called a breathing cycle threshold.

[0140] In one example, the vibration period threshold may be a threshold, such as 2 seconds.

[0141] The vibration period threshold may be a time range corresponding to one normal breath.

[0142] In an example, the vibration period threshold may be a range value, such as 1 s to 3 s.

[0143] In one example, the waveform of the second vibration signal corresponding to the breathing abnormality type of weak breathing can be as follows: Figure 4 As shown in ②.

[0144] Step S2300.24, when the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is less than the shallow breathing threshold and the vibration period is greater than or equal to the vibration period threshold, determine that the wearer's abnormal breathing type is weak breathing.

[0145] In this embodiment, the shallow breathing threshold may be determined according to the amplitude of a vibration signal measured by a vibration sensor of the wearable device in a shallow breathing experiment.

[0146] In one example, the shallow breathing threshold may be 0.3V.

[0147] In other embodiments, the deviation of the amplitude within a vibration cycle relative to the central value of the amplitude is symmetrical, that is, the second vibration signal is as follows: Figure 5 The sine-like vibration signal shown in FIG. can also be obtained by 1 / 2 vibration period (ie, Figure 5 In other words, when the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the 1 / 2 vibration period is greater than or equal to the deep breathing threshold and the 1 / 2 vibration period is less than the 1 / 2 vibration period threshold, the wearer's abnormal breathing type is determined to be shortness of breath. When the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the 1 / 2 vibration period is less than the shallow breathing threshold and the 1 / 2 vibration period is greater than or equal to the 1 / 2 vibration period threshold, the wearer's abnormal breathing type is determined to be weak breathing.

[0148] In this embodiment, the 1 / 2 vibration period threshold may be, for example, 1 second, or may be, for example, 0.5 seconds to 1.5 seconds.

[0149] In one example, the second vibration signal corresponding to shortness of breath may be as follows: Figure 4 As shown in figure ④.

[0150] Step S2300.25, when the periodic information indicates that the second vibration signal is a periodic signal and the amplitude change rate within the vibration period is greater than or equal to the amplitude change rate threshold, determine that the wearer's abnormal breathing type is respiratory twitch.

[0151] For example, if the waveform of the second vibration signal is as follows Figure 4 The waveform corresponding to the respiratory twitch in ①, that is, the second vibration signal appears as follows Figure 4① The spike signal shown in FIG. 1 appears in each vibration cycle of the second vibration signal. In this case, the abnormal breathing type is considered to be respiratory twitch.

[0152] The vibration period is the time from the beginning of the spike signal to the next spike signal.

[0153] In some examples, the vibration period of the second vibration signal may be as follows: Figure 4 The respiratory twitch shown in ① is greater than or equal to the vibration period threshold.

[0154] In some other examples, the vibration period of the second vibration signal may be smaller than the vibration period threshold.

[0155] That is to say, when determining whether respiratory twitching occurs, we only need to pay attention to whether the second vibration signal is a periodic signal. When the second vibration signal is a periodic vibration signal, determine whether there is a target amplitude change rate within one vibration period that is greater than or equal to the amplitude change rate threshold. If there is a target amplitude change rate, the type of respiratory abnormality is determined to be respiratory twitching.

[0156] The amplitude change rate threshold may be determined according to the amplitude change rate of a vibration signal measured by a vibration sensor of the wearable device in a respiratory twitch experiment.

[0157] The amplitude change rate threshold can be flexibly changed according to the sensitivity and structure of the breathing detection of the wearable device.

[0158] In some embodiments, after determining the abnormal breathing type of the wearer in step S2300, the method further includes:

[0159] According to the abnormal breathing type of the wearer, corresponding prompt information is output.

[0160] In this embodiment, the prompt information may be in the form of voice, text, pictures, etc., which is not limited here.

[0161] In one example, in the case where the type of respiratory abnormality is respiratory convulsions, such as Figure 4 As shown in the waveform diagram of ①, the first prompt information and preset music are output.

[0162] In this embodiment, the first prompt information may be to prompt the wearer to calm down and play preset light music.

[0163] In another example, if the abnormal breathing type is weak breathing, corresponding prompt information can be output according to the duration of the weak breathing.

[0164] In this example, if the duration of weak breathing is one minute, the wearable device will issue a voice prompt: bradypnea, asking the wearer to adjust his mood and reduce stress. If the duration of weak breathing is three minutes, the wearable device will warn the wearer to seek medical attention in time. If the duration of weak breathing is five minutes, the wearable device will emit a harsh whistle at the maximum volume to attract the attention of other people in the wearer's cycle.

[0165] In another example, the type of abnormal breathing is irregular breathing. If the duration of irregular breathing is one minute, the wearable device will issue a reminder: irregular breathing may be caused by some disease, and you should seek medical attention as soon as possible.

[0166] In yet another example, the abnormal breathing type is shortness of breath, and corresponding prompt information may be output according to the duration of the shortness of breath.

[0167] In this example, if the duration of shortness of breath is one minute, the wearable device will send out a reminder message: shortness of breath, may be excessive exercise or emotional overexertion, asking the wearer to reduce exercise and adjust the mood, and play preset light music to relieve stress. If the duration of shortness of breath is three minutes, the wearable device will send out a reminder message: please lie down and rest. If the duration of shortness of breath is five minutes, the wearable device will send out a harsh whistle at the maximum volume to attract the attention of people around the wearer.

[0168] In another example, the type of abnormal breathing is apnea. If apnea occurs more than 2 times within one minute, the wearable device will send a prompt message: there is a short breathing pause phenomenon. If the wearer does not hold his breath or take slow deep breaths, the wearer can also be prompted to seek medical attention in time.

[0169] By outputting corresponding prompt information according to the type of breathing abnormality, the wearer can be accurately prompted to take corresponding measures according to the type of breathing abnormality, which can avoid the aggravation of the breathing abnormality and prevent the wearer from ignoring his or her own breathing abnormality and causing impact on health.

[0170] According to an embodiment of the present application, by collecting a first vibration signal through a vibration sensor that fits the nose of the wearer, real-time monitoring of the wearer's breathing can be achieved through a wearable device without adding extra burden, and compared with other respiratory detection devices that are inserted or close to the body, this data collection method has higher privacy and comfort. Then, by obtaining the first vibration signal of the wearer collected by the vibration sensor, the first vibration signal is preprocessed to obtain a second vibration signal, and the type of abnormal breathing of the wearer is determined according to the second vibration signal. Since the vibration signal is directly related to breathing, the accuracy of abnormal breathing detection can be improved compared to the method of indirectly determining the breathing rate through parameters such as heart rate.

[0171] <Device Example>

[0172] Figure 6 4 is a principle block diagram of a breathing abnormality detection device 600 according to an embodiment of the present invention.

[0173] In this embodiment, the breathing abnormality detection device 600 may include a memory 6200 and a processor 6100 .

[0174] The memory 6200 is used to store instructions, which are used to control the processor 6100 to operate to perform the abnormal breathing detection method of any embodiment of the present invention. A technician can design instructions according to the scheme disclosed in the present invention. How instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0175] <Wearable Device Embodiment>

[0176] Figure 7 is a principle block diagram of a wearable device 700 according to an embodiment of the present invention.

[0177] In this embodiment, the wearable device 700 may include a vibration sensor 7100 and a breathing abnormality detection device 7200 .

[0178] The vibration sensor 7100 is used to collect the vibration signal of the person being tested and send it to the abnormal breathing detection device 7200.

[0179] In some embodiments, the wearable device also includes an acceleration sensor and a touch sensor.

[0180] The acceleration sensor collects acceleration data and sends it to the abnormal breathing detection device, and the touch sensor collects touch data and sends it to the abnormal breathing detection device.

[0181] The abnormal breathing detection device determines whether the wearable device is in a worn state based on the acceleration data and the touch data.

[0182] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0183] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0184] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0185] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0186] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0187] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0188] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0189] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0190] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for detecting abnormal breathing, characterized in that: The method is applied to a wearable device, wherein the wearable device is provided with a vibration sensor for fitting with a nose wing of a wearer, and the method comprises: Acquire a first vibration signal of the wearer collected by the vibration sensor; performing signal preprocessing on the first vibration signal to obtain a second vibration signal; The abnormal breathing type of the wearer is determined according to the second vibration signal.

2. The method according to claim 1, characterized in that The step of determining the abnormal breathing type of the wearer according to the second vibration signal includes: extracting breathing characteristic information of the second vibration signal; The wearer's breathing abnormality type is determined based on the breathing characteristic information.

3. The method according to claim 2, characterized in that The breathing characteristic information includes periodic information and amplitude for characterizing whether the second vibration signal is a periodic signal, and determining the type of abnormal breathing of the wearer according to the breathing characteristic information includes: When the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is less than an apnea threshold within a preset time period, determining that the wearer's breathing abnormality type is apnea; When the periodic information indicates that the second vibration signal is a non-periodic signal and the amplitude is greater than or equal to the apnea threshold within the preset time period, it is determined that the wearer's breathing abnormality type is irregular breathing.

4. The method according to claim 3, characterized in that: In the case where the second vibration signal is a periodic signal, the breathing characteristic information further includes a vibration period, and determining the type of abnormal breathing of the wearer according to the breathing characteristic information further includes: When the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is greater than or equal to the deep breathing threshold and the vibration period is less than the vibration period threshold, determining that the wearer's abnormal breathing type is shortness of breath; When the periodic information indicates that the second vibration signal is a periodic signal and the maximum amplitude within the vibration period is less than the shallow breathing threshold and the vibration period is greater than or equal to the vibration period threshold, determining that the wearer's abnormal breathing type is weak breathing; When the periodic information indicates that the second vibration signal is a periodic signal and the amplitude change rate within the vibration period is greater than or equal to an amplitude change rate threshold, it is determined that the wearer's abnormal breathing type is respiratory twitch.

5. The method according to claim 1, characterized in that After determining the abnormal breathing type of the wearer, the method further includes: According to the abnormal breathing type of the wearer, corresponding prompt information is output.

6. The method according to claim 1, characterized in that The obtaining of the first vibration signal of the wearer collected by the vibration sensor comprises: Turning on the vibration sensor at the initial moment when detecting that the wearable device is in a worn state; wherein the vibration sensor continuously collects the first vibration signal when turned on; A first vibration signal output by the vibration sensor is received.

7. The method according to claim 6, characterized in that The wearable device further includes an acceleration sensor and a touch sensor, and detecting whether the wearable device is in a worn state includes: Acquiring acceleration data collected by the acceleration sensor; Determining whether the wearable device is in an upright state according to the acceleration data; When the wearable device is in an upright state, acquiring touch data collected by the touch sensor; Determining whether the wearable device is in a touched state according to the touch data; When the wearable device is in a touched state, it is determined that the wearable device is in a worn state.

8. The method according to claim 1, characterized in that The performing signal preprocessing on the first vibration signal to obtain a second vibration signal includes: Extracting a signal within a target frequency range from the first vibration signal to obtain a filtered first vibration signal; wherein the target frequency range is a range smaller than the second frequency and larger than the first frequency; The filtered first vibration signal is subjected to signal amplification processing to obtain the second vibration signal.

9. A breathing abnormality detection device, comprising a memory and a processor, wherein the memory is used to store executable instructions; and the processor is used to operate according to the control of the instructions to execute the method as described in any one of claims 1 to 8.

10. A wearable device comprising a vibration sensor and the abnormal breathing detection device according to claim 9, wherein the vibration sensor is used to collect a vibration signal of a subject and send the vibration signal to the abnormal breathing detection device.

Images