A human body sign monitoring method, device and intelligent monitoring pillow

Abstract

The present application relates to a kind of human body sign monitoring method, device and intelligent monitoring pillow, the human body sign monitoring method first obtains the first signal collected by sensor, then the first signal is filtered and pretreated, obtain second signal, then according to second signal, time window and iteration step, obtain third signal, finally obtain the signal feature of third signal, according to the signal feature of third signal determine whether there is snoring signal in third signal, and according to the signal feature of third signal determine the heart rate signal of user.Therefore, the human body sign monitoring method can be preprocessed to the signal collected by sensor, remove interference, then according to the signal feature of preprocessed signal, determine whether there is snoring signal, and determine the heart rate signal of user, to accurately monitor the snoring of user and the heart rate of user, improve the sleep safety of user.

Description

Technical Field

[0001] This invention relates to the field of sleep monitoring, and in particular to a method, device, and smart monitoring pillow for monitoring human vital signs. Background Technology

[0002] Heart rate plays a vital role in physical health, serving as a simple and practical indicator of cardiovascular system function and holding practical significance for the early detection of cardiovascular diseases. Snoring, the sound produced during sleep due to the vibration of the uvula (palmar) caused by narrowing of the upper airway, is often accompanied by sleep apnea syndrome, impacting sleep quality and even threatening lives. Therefore, monitoring heart rate and snoring during sleep is necessary to ensure sleep safety. Summary of the Invention

[0003] The present invention addresses at least one of the aforementioned technical problems. To this end, the present invention provides a method, device, and smart monitoring pillow for monitoring human vital signs, which can monitor whether a user snores and monitor the user's heart rate signal, thereby ensuring the user's sleep safety.

[0004] In a first aspect, embodiments of the present invention provide a method for monitoring human vital signs, applied to a human vital signs monitoring device, the human vital signs monitoring device including a sensor, the sensor being used to collect a first signal from a user, the first signal being used to characterize the user's human vital signs, the method including:

[0005] Acquire the first signal collected by the sensor;

[0006] The first signal is filtered and preprocessed to obtain the second signal;

[0007] The third signal is obtained based on the second signal, the time window, and the iteration step size;

[0008] Acquire the signal characteristics of the third signal, and determine whether there is a snoring signal in the third signal based on the signal characteristics of the third signal;

[0009] The user's heart rate signal is determined based on the signal characteristics of the third signal.

[0010] In some embodiments, the filtering preprocessing of the first signal includes:

[0011] The first signal is preprocessed by using a bandpass filter, wherein the low-end cutoff frequency of the bandpass filter is a first preset frequency, and the high-end cutoff frequency of the bandpass filter is a second preset frequency.

[0012] In some embodiments, obtaining the third signal based on the second signal, the time window, and the iteration step size includes:

[0013] The second signal is sequentially extracted from the first time window according to the first iteration step size to obtain the third signal.

[0014] In some embodiments, acquiring the signal characteristics of the third signal and determining whether a snoring signal exists in the third signal based on the signal characteristics of the third signal includes:

[0015] Obtain the number of zero-crossing points and the signal energy value of the third signal;

[0016] When the number of zero crossings and the signal energy value reach the first preset condition, it is determined that there is a snoring signal in the third signal.

[0017] In some embodiments, the first preset condition includes: the number of zero crossings is greater than a first preset threshold, and the signal energy value is within a first preset range.

[0018] In some embodiments, the filtering preprocessing of the first signal further includes:

[0019] The first signal is preprocessed by using a low-pass filter, wherein the low-end cutoff frequency of the low-pass filter is a third preset frequency.

[0020] In some embodiments, obtaining the third signal based on the second signal, the time window, and the iteration step size includes:

[0021] The second signal is sequentially extracted from the second time window according to the second iteration step size to obtain the third signal.

[0022] In some embodiments, acquiring the signal characteristics of the third signal further includes:

[0023] The third signal is subjected to baseline removal and Hamming windowing to obtain the fourth signal;

[0024] Perform a Fourier transform on the fourth signal to obtain the first curve relating amplitude and frequency;

[0025] Obtain all the maximum amplitude values ​​and their corresponding first frequencies on the first curve whose frequencies fall within the second interval.

[0026] In some embodiments, performing baseline removal and Hamming windowing operations on the third signal to obtain a fourth signal includes:

[0027] Obtain the mean value of the third signal;

[0028] The third signal is subjected to baseline removal operation, which is performed using the following formula:

[0029] r[n] = q[n] - mean;

[0030] Where r[n] is the signal obtained after removing the baseline, q[n] is the third signal, and mean is the mean of the third signal;

[0031] A Hamming window operation is performed on the third signal after baseline removal to generate a Hamming window signal, the data length of which is the same as that of the third signal.

[0032] The fourth signal is obtained by the following formula:

[0033] y[n] = r[n] * u[n];

[0034] Wherein, y[n] is the fourth signal, and u[n] is the Hamming window signal.

[0035] In some embodiments, determining the user's heart rate signal based on the signal characteristics of the third signal further includes:

[0036] The fundamental frequency of the heart rate signal is determined based on all the maximum amplitude values ​​and their corresponding first frequencies;

[0037] The user's heart rate signal is determined based on the base frequency.

[0038] In some embodiments, determining the fundamental frequency of the heart rate signal based on all the amplitude maxima and their corresponding first frequencies includes:

[0039] Based on all the amplitude maxima and their corresponding first frequencies, obtain the second frequency corresponding to the largest amplitude maxima;

[0040] If the amplitude of the heart rate signal is maximized in the third interval and maximized in the fourth interval on the first curve, then the fundamental frequency of the heart rate signal is determined to be the second frequency. The third interval is [2*k-Δf, 2*k+Δf], and the fourth interval is [3*k-Δf, 3*k+Δf], where k is the second frequency and Δf is the second preset threshold.

[0041] If the frequency on the first curve has a maximum amplitude value within the fifth interval and the frequency has a maximum amplitude value within the sixth interval, then the fundamental frequency of the heart rate signal is determined to be 0.5*k, where the fifth interval is [0.5*k-Δf, 0.5*k+Δf], the sixth interval is [1.5*k-Δf, 1.5*k+Δf], k is the second frequency, and Δf is the second preset threshold.

[0042] Secondly, embodiments of the present invention provide a human vital signs monitoring device, the human vital signs monitoring device comprising:

[0043] A sensor is used to acquire a first signal from the user, the first signal representing the user's vital signs; and,

[0044] A controller, which is communicatively connected to the sensor, includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the human vital signs monitoring method as described above.

[0045] Thirdly, embodiments of the present invention provide an intelligent monitoring pillow, the intelligent monitoring pillow comprising: a pillow body, a main control box, and a human vital sign monitoring device as described above; the sensor is disposed within the pillow body; and the controller is disposed within the main control box.

[0046] Compared with existing technologies, this invention has at least the following beneficial effects: In the human vital sign monitoring method of this invention, a first signal collected by a sensor is first acquired, then the first signal is filtered and preprocessed to obtain a second signal. Then, based on the second signal, a time window, and an iteration step size, a third signal is acquired. Finally, the signal characteristics of the third signal are acquired, and based on these characteristics, it is determined whether a snoring signal exists in the third signal, and the user's heart rate signal is also determined. Therefore, this human vital sign monitoring method can preprocess the sensor-acquired signal to remove interference, and then determine the presence of a snoring signal and the user's heart rate signal based on the signal characteristics of the preprocessed signal, thereby accurately monitoring the user's snoring and heart rate and improving the user's sleep safety. Attached Figure Description

[0047] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0048] Figure 1 This is a structural schematic diagram of one of the smart monitoring pillows provided in an embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of the circuit structure of one of the human vital signs monitoring devices provided in the embodiments of the present invention;

[0050] Figure 3 This is a schematic diagram of one controller structure provided in an embodiment of the present invention;

[0051] Figure 4 This is a schematic diagram of the application environment of one of the human vital signs monitoring devices provided in the embodiments of the present invention;

[0052] Figure 5 This is a flowchart of one of the human vital sign monitoring methods provided in the embodiments of the present invention;

[0053] Figure 6 This is a schematic diagram of one of the first and third signals provided in an embodiment of the present invention;

[0054] Figure 7 yes Figure 5 A flowchart illustrating step S54 in the middle section;

[0055] Figure 8 This is a schematic diagram of one of the first signals, second signals, and first curves provided in an embodiment of the present invention;

[0056] Figure 9 This is a schematic diagram of the structure of one of the human vital signs monitoring devices provided in the embodiments of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0058] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0059] The human vital signs monitoring device of this invention can be constructed into any suitable shape and placed in various human vital signs monitoring products to realize human monitoring functions. For example, the human vital signs monitoring device of this invention can be placed in smart mattresses, smart pillows, or even pajamas.

[0060] Human vital signs include respiratory rate, heart rate, and pulse. This information reflects a person's physical condition and includes both data and signals. Monitoring these vital signs during sleep allows for the assessment of sleep patterns and quality, facilitating the effective diagnosis and treatment of sleep disorders. Furthermore, monitoring vital signs can reveal a user's overall health, enabling timely detection and intervention to ensure a safe and healthy sleep.

[0061] Please see Figure 1 , Figure 1 This is a schematic diagram of a smart monitoring pillow provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the smart monitoring pillow 100 includes a pillow body 10, a main control box 20, and a human vital signs monitoring device 30.

[0062] Please refer to the following: Figure 2 , Figure 2 This is a schematic diagram of the circuit structure of a human vital signs monitoring device provided in an embodiment of the present invention. Figure 2 As shown, the human vital signs monitoring device 30 includes a sensor 31 and a controller 32.

[0063] The pillow body 10 is provided with a communication interface 11, and the sensor 31 is disposed inside the pillow body 10. The controller 32 is disposed inside the main control box 20, and the sensor 31 and the controller 32 are connected by wired communication through the communication interface 11.

[0064] The communication interface 11 can be connected to the controller 32 inside the main control box 20 via a signal transmission line. The communication interface 11 can be a Type-C interface or other easy-to-connect and stable interface. The communication interface 11 supports plugging and unplugging. When it is necessary to monitor human vital signs, the plug of the signal transmission line can be plugged into the communication interface 11. When the monitoring is completed, the plug of the signal transmission line can be unplugged.

[0065] Sensor 31 can be a piezoelectric sensor. In this embodiment of the invention, it can be a piezoelectric thin-film sensor, which, as a dynamic strain sensor, is very suitable for monitoring vital signs on the surface of human skin or implanted inside the human body. Some thin-film elements are sensitive enough to detect a human pulse through a garment. Therefore, using a piezoelectric thin-film sensor can accurately acquire the user's vital signs signals.

[0066] In other embodiments, the sensor 31 and the controller 32 can also communicate wirelessly.

[0067] During sleep, the user's head rests on the pillow body 10. The sensor 31 can collect the user's vital signs signals and transmit the collected signals to the controller 32 through the communication interface 11 and the signal transmission line. The controller 32 receives and processes the signals to analyze whether the user snores during sleep and to detect the user's heart rate during sleep, so that it can take timely action if the heart rate signal is abnormal.

[0068] Please refer to the following: Figure 3 The controller 32 includes at least one processor 321 that is communicatively connected via a system bus or other means. Figure 3 (Taking a processor as an example) and memory 322. The controller 32 can exist in the form of a chip.

[0069] The memory 322 stores instructions that can be executed by the at least one processor 321. The instructions are executed by the at least one processor 321, which provides computing and control capabilities to process human vital signs signals and control the human vital signs monitoring device 30 to execute relevant commands, such as controlling the human vital signs monitoring device 30 to execute any of the human vital signs monitoring methods provided in the following embodiments of the present invention.

[0070] The memory 322, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the human vital sign monitoring method provided in the following embodiments of the present invention. The processor 321 can implement the human vital sign monitoring method in any of the following method embodiments by running the non-transitory software programs, instructions, and modules stored in the memory 322. Specifically, the memory 322 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 322 may also include memory remotely located relative to the processor 321, and these remote memories can be connected to the processor 321 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0071] Please see Figure 4 , Figure 4 This is a schematic diagram illustrating an application scenario of a human vital signs monitoring device 30 provided in an embodiment of the present invention, such as... Figure 4As shown, the human vital signs monitoring device 30 can also be connected to the mobile terminal 200. The mobile terminal 200 and the human vital signs monitoring device 30 can be connected to each other in any way, such as wired connection or wireless connection using wireless Fidelity (Wi-Fi), Bluetooth, or other mobile communication technologies such as 3rd Generation (3G), 4th Generation (4G), or 5th Generation (5G).

[0072] Mobile terminal 200 may be configured with one or more different user interaction devices for collecting user commands or displaying and providing feedback to the user. These interaction devices include, but are not limited to, buttons, displays, touch screens, and speakers. For example, mobile terminal 200 may be equipped with a touch screen display, through which it receives remote control commands from the user to the human body monitoring device and displays to the user human body monitoring device acquired human vital signs information, image information obtained from human vital signs information, or user health status assessment obtained from human vital signs information. The user can also switch the currently displayed human vital signs information on the display screen by remotely controlling the touch screen.

[0073] The mobile terminal 200 and the human vital signs monitoring device 30 transmit communication data to each other. For example, the human vital signs monitoring device 30 can transmit human vital signs information to the mobile terminal 200 for users to view in a timely manner. The mobile terminal 200 displays the human vital signs monitoring status in real time, which can be displayed in various forms for the convenience of users. At the same time, users can also control the human vital signs monitoring device 30 through the mobile terminal 200 to set the human vital signs monitoring device 30 to work in a suitable mode.

[0074] It should be noted that the mobile terminal 200 can be a smartphone, tablet computer, personal digital assistant, or other hardware device with various operating systems.

[0075] In some embodiments, the human vital signs monitoring device 30 can also be communicatively connected to a cloud 300, which in turn can be communicatively connected to a mobile terminal 200. Human vital signs information is uploaded to the cloud 300, which stores and manages the information for big data processing. The cloud 300 can also transmit the evaluation of the human vital signs information in the big data to the mobile terminal 200 for user viewing.

[0076] Therefore, the human vital signs monitoring device 30 monitors human vital signs information and processes and stores the human vital signs information through the mobile terminal 200 and / or the cloud 300 for users to view and process.

[0077] Please continue reading. Figure 2 The human vital signs monitoring device 30 also includes a signal processing circuit 33, which is electrically connected to the sensor 31 and the controller 32 respectively, for processing the human vital signs signal and transmitting the processed human vital signs signal to the controller 32.

[0078] The signal processing circuit 33 can amplify and filter human vital signs signals. The amplified signals are easier to process by the controller 32. Different filtering methods can be used according to the required human vital signs information. For example, if it is necessary to analyze whether there is a snoring signal, the human vital signs signal can be band-pass filtered. If it is necessary to analyze the user's heart rate signal, the human vital signs signal can be low-pass filtered.

[0079] In some embodiments, the human vital signs monitoring device 30 further includes a wireless module 34, which is communicatively connected to the controller 32 and is used to communicate with the mobile terminal 200 and / or the cloud 300.

[0080] The wireless module 34 can be implemented in various ways, such as a Bluetooth module, a WIFI module, or other wireless modules.

[0081] In some embodiments, the human vital signs monitoring device 30 further includes a power module 35, which is electrically connected to the controller 32, the signal processing circuit 33 and the wireless module 34 respectively, and is used to supply power to the controller 32, the signal processing circuit 33 and the wireless module 34.

[0082] The power module 35 consists of a rechargeable battery, a charging circuit, and a voltage conversion circuit. The voltage conversion circuit is responsible for providing the voltage required for the normal operation of each circuit. The rechargeable battery can be charged via a USB port through the charging circuit, or wirelessly charged.

[0083] In some embodiments, the human vital signs monitoring device 30 may further include a voice module (not shown in the figure), which is electrically connected to the controller 32. When an abnormal situation occurs, the voice module can issue an abnormal alarm reminder. The controller 32 may also send the abnormal situation to the mobile terminal 200 so that the user can view it in a timely manner.

[0084] The signal processing circuit 33, the wireless module 34, the power supply module 35, and the voice module can all be placed inside the main control box 20.

[0085] Please see Figure 5 , Figure 5 This is a flowchart of a human vital sign monitoring method provided by an embodiment of the present invention, as shown below. Figure 5 As shown, this method for monitoring human vital signs includes:

[0086] S51. Acquire the first signal collected by the sensor;

[0087] The sensor collects the user's sensing signals, which are analog signals. The controller can set the sampling frequency of the sensing signals. The controller obtains the first signal by setting the sampling frequency. The first signal is a digital signal that represents the user's human vital signs. The sampling frequency can be 400Hz, 800Hz, etc.

[0088] Human vital sign monitoring devices are mostly used for sleep monitoring; therefore, the sensor is a piezoelectric sensor. Sleep monitoring products based on piezoelectric sensors can record the subject's physical activities, respiratory activities, heart rate, etc., without attaching electrodes to the body surface. They can also diagnose sleep apnea syndrome, making it an electrode-free and load-free sleep monitoring method. In this embodiment of the invention, the sensor can be a piezoelectric thin film sensor or a piezoelectric cable sensor.

[0089] S52. Perform filtering preprocessing on the first signal to obtain the second signal;

[0090] Before filtering the first signal, power frequency noise can be removed. Specifically, since the sampling frequency of the first signal is 400Hz or 800Hz, there will be power frequency interference of 50Hz and its harmonics in the first signal, which can be filtered using a comb filter. The specific filter configuration parameters are: sampling rate of 400Hz, filter order of 8, stopband bandwidth of 4, and maximum passband attenuation of 1. After removing the power frequency noise from the first signal, filtering preprocessing is performed on the first signal. The sensing signal is the signal obtained by the sensor detecting the dynamic stress generated by the human body due to micro-movements such as breathing and snoring. The first signal obtained by sampling the sensing signal is related to various different human vital signs. Different human vital signs will be monitored, and different filtering preprocessing will be applied to the first signal to obtain a signal related to the human vital signs to be monitored.

[0091] Specifically, if the human vital signs signal to be monitored is a snoring signal, a bandpass filter is used to preprocess the first signal by filtering. The low-end cutoff frequency of the bandpass filter is a first preset frequency, and the high-end cutoff frequency of the bandpass filter is a second preset frequency.

[0092] The first preset frequency and the second preset frequency can be set as needed. Since the frequency range of snoring signals is usually between 30Hz and 100Hz, the first preset frequency can be 30Hz and the second preset frequency can be 100Hz.

[0093] The bandpass filter can be a Butterworth filter, with the following specific filter configuration parameters: sampling rate 400Hz and filter order 4.

[0094] If the human vital signs signal to be monitored is the user's heart rate signal, then a low-pass filter is used to preprocess the first signal, and the low-end cutoff frequency of the low-pass filter is a third preset frequency.

[0095] The third preset frequency can be set as needed. In this embodiment of the invention, the third preset frequency can be 15Hz.

[0096] The low-pass filter can also be a Butterworth filter, with the following specific filter configuration parameters: sampling rate of 400Hz and filter order of 4.

[0097] S53. Based on the second signal, the time window, and the iteration step size, obtain the third signal;

[0098] Different human vital signs have different durations, so different time windows and iteration steps need to be set according to different human vital signs.

[0099] Specifically, the signal collected by the sensor is not a snoring signal and a heart rate signal, but a mixed signal of multiple human vital signs. The controller needs to determine which specific human vital signs the collected signal contains. If the target human vital sign signal to be monitored is a snoring signal, the second signal is sequentially extracted from the first time window according to the first iteration step size to obtain the third signal.

[0100] The first iteration step size and the first time window can be set according to the characteristics of the snoring signal. In this embodiment of the invention, the first iteration step size is 0.5s and the first time window is 1s.

[0101] If the target human vital signs signal to be monitored is the user's heart rate signal, the second signal is sequentially extracted from the second time window according to the second iteration step size to obtain the third signal.

[0102] The second iteration step size and the second time window can be set according to the characteristics of the heart rate signal. In this embodiment of the invention, the second iteration step size is 1s and the second time window is 6s.

[0103] S54. Obtain the signal characteristics of the third signal, and determine whether there is a snoring signal in the third signal based on the signal characteristics of the third signal;

[0104] Signal characteristics include signal amplitude, frequency, initial phase, number of zero-crossings, and energy value. These characteristics directly or indirectly reflect the signal's properties. Different signals have different characteristics; therefore, the presence of snoring signals in a third signal can be analyzed using these characteristics.

[0105] Specifically, the number of zero-crossing points and the signal energy value of the third signal are obtained. When the number of zero-crossing points and the signal energy value reach a first preset condition, it is determined that there is a snoring signal in the third signal.

[0106] The first preset condition includes that the number of zero-crossing points is greater than or equal to a first preset threshold, and that the signal energy value is within a first preset range.

[0107] Both the first preset threshold and the first preset interval can be set by empirical values. In this embodiment of the invention, the first preset threshold is 40 and the first preset interval is [163840, 6560000].

[0108] If the third signal is x[n], then the number of zero-crossing points of the third signal is the number of x[n]*x[n+1]<0, where n is the sequence number of the third signal and n is an integer greater than or equal to 1. For example: if the third signal x[n]=[3,-4,2,5], then n=4, x[1]*x[2]=3*-4<0, x[2]*x[3]=-4*2<0, x[3]*x[4]=2*5>0, so the number of zero-crossing points is 2.

[0109] Signal energy refers to the signal's transmission capability. The higher the signal frequency (shortwave), the greater the attenuation and the shorter the transmission distance; conversely, the lower the signal frequency, the longer the transmission distance, and the greater the energy, resulting in a stronger signal. The signal energy value is calculated using the following formula:

[0110] E=x[1]^2+x[2]^2+x[3]^2+…+x[n]^2 (1)

[0111] Where E is the signal energy value.

[0112] If the number of zero-crossing points of the third signal reaches or exceeds the first preset threshold, and the signal energy value of the third signal is within the first preset range, then it is determined that there is a snoring signal in the third signal, indicating that the user is snoring, thus enabling snoring monitoring of the user.

[0113] For example: if the waveform of the first signal is as follows Figure 6 As shown in S1, the waveform of the third signal is as follows: Figure 6 As shown in S3, the presence of a snoring signal in the third signal is determined by the number of zero-crossing points and the signal energy value. The start and end times of the snoring signal are t1 and the end time is t2.

[0114] If it is necessary to monitor the user's heart rate signal, the signal characteristics of the acquired third signal will be different from those acquired when monitoring snoring signals.

[0115] Specifically, please refer to Figure 7 Step S54 further includes:

[0116] S541. The third signal is subjected to baseline removal and Hamming window addition to obtain the fourth signal;

[0117] Some digital signals contain baseline interference (low-frequency noise), which can adversely affect signal analysis. Therefore, it is necessary to remove baseline interference from the third signal. First, the mean of the third signal is obtained, which can be calculated using the following formula:

[0118] mean=(q[1]+q[2]+q[3]+…+q[n-1]+q[n]) / n (2)

[0119] Wherein, q[n] is the third signal, n is the sequence value of q[n], which is an integer greater than or equal to 1, and mean is the mean of the third signal.

[0120] Then remove the baseline using the following formula:

[0121] r[n]=q[n]-mean (3)

[0122] Where r[n] is the signal after removing the baseline, q[n] is the third signal, and mean is the mean of the third signal.

[0123] After removing the baseline from the third signal, a Hamming window operation is applied. The Hamming window is a type of cosine window, also known as a modified raised cosine window. To process the baseline-removed third signal, a windowing operation is needed. Data is taken in segments, analyzed, and then the next segment is taken and analyzed again; that is, only the data within the window is processed at a time. The Hamming window is a function whose shape resembles a window, hence similar functions are called window functions.

[0124] Specifically, a Hamming window operation is performed on the third signal after baseline removal to generate a Hamming window signal. The data length of the Hamming window signal is the same as that of the third signal. The fourth signal is then obtained using the following formula:

[0125] y[n]=r[n]*u[n] (4)

[0126] Wherein, y[n] is the fourth signal, and u[n] is the Hamming window signal.

[0127] S542. Perform a Fourier transform on the fourth signal to obtain the first curve relating amplitude and frequency;

[0128] S543. Obtain all the maximum amplitude values ​​and their corresponding first frequencies on the first curve whose frequencies are in the second interval.

[0129] The amplitudes corresponding to the fundamental frequency and its harmonics of the heart rate signal are both maximum values ​​on the first curve. This characteristic can be used to determine the fundamental frequency of the heart rate signal, and then the user's heart rate can be determined based on the fundamental frequency.

[0130] The second interval is set based on empirical values, within which the heart rate signal is stronger. In this embodiment of the invention, the second interval is [0.67Hz-15Hz].

[0131] There are multiple maximum amplitude values ​​within the second frequency range, and there are also multiple corresponding first frequencies. The fundamental frequency of the heart rate signal is determined from these multiple first frequencies, and then the user's heart rate signal is determined based on the fundamental frequency.

[0132] Specifically, firstly, based on all amplitude maxima and their corresponding first frequencies, the second frequency corresponding to the largest amplitude maxima is obtained. If all amplitude maxima are denoted as F, and their corresponding first frequencies are denoted as H, then F contains multiple amplitude maxima, and H also contains multiple frequencies. The largest amplitude maxima in F is found, denoted as z, and its corresponding frequency is the second frequency, denoted as k, where z and k are both single values.

[0133] For example: the first signal, such as Figure 8 As shown in S1, the second signal is as follows Figure 8 As shown in S2, the first curve is as follows: Figure 8 As shown in S4, on the first curve S4, the horizontal axis represents frequency and the vertical axis represents amplitude. On the first curve S4, there are multiple amplitude maxima within the second interval, and their corresponding frequencies are also multiple. The figure shows four amplitude maxima and their corresponding frequencies, which are (0.7031HZ, 7.984e+05), (1.094HZ, 1.191e+06), (2.168HZ, 1.862e+05), and (3.262HZ, 3.081e+05). The largest amplitude maxima among all amplitude maxima is 1.191e+06, and the second frequency k is 1.094HZ.

[0134] The amplitudes corresponding to the second frequency, its second harmonic, and its third harmonic on the first curve are all amplitude maxima. Therefore, this characteristic can be used to determine the fundamental frequency of the heart rate signal from all amplitude maxima and their corresponding frequencies.

[0135] The amplitude corresponding to the second frequency k is the maximum value among all amplitude maxima. Assuming the second frequency k is the fundamental frequency, it is then determined whether the amplitudes corresponding to the second harmonic and the third harmonic of the second frequency k are amplitude maxima. Specifically, if the amplitude maxima exist within the third interval and the amplitude maxima exist within the fourth interval on the first curve, then the fundamental frequency of the heart rate signal is determined to be the second frequency. Here, the third interval is [2*k-Δf, 2*k+Δf], the fourth interval is [3*k-Δf, 3*k+Δf], k is the second frequency, and Δf is the second preset threshold.

[0136] The third interval is the second harmonic interval of the second frequency, the fourth interval is the third harmonic interval of the second frequency, and Δf represents the allowable error range of the interval, which can be set as needed. In this embodiment of the invention, it is 0.1.

[0137] Since slight body movements may cause interference components to be superimposed on the amplitude at the harmonic position, leading to misjudgment of the maximum amplitude, i.e., inaccurate determination of z and k, the fundamental frequency of the heart rate signal can be determined by whether there are amplitude maxima at both the half harmonic and the 1.5 harmonic of the second frequency when the above conditions are not met. Specifically, if the amplitude maxima exist in both the fifth and sixth harmonics of the frequency on the first curve, the fundamental frequency of the heart rate signal is determined to be 0.5*k, where the fifth harmonic is [0.5*k-Δf, 0.5*k+Δf] and the sixth harmonic is [1.5*k-Δf, 1.5*k+Δf].

[0138] When the frequency is k, the corresponding amplitude is the maximum amplitude value. Therefore, it is not necessary to check the 2nd harmonic of 0.5*k. We can simply check whether there is a maximum amplitude value in the interval [0.5*k-Δf, 0.5*k+Δf] and [1.5*k-Δf, 1.5*k+Δf], where Δf can be 0.1.

[0139] If neither frequency k nor 0.5*k meets the condition that there are maximum amplitude values ​​at the first, second, and third harmonics, then it is determined that the heart rate fundamental frequency has not been found. In this case, the fundamental frequency of the heart rate signal is set to 0, indicating that the heart rate fundamental frequency has been found.

[0140] S55. Determine the user's heart rate signal based on the signal characteristics of the third signal.

[0141] If the fundamental frequency of the heart rate signal is obtained through the above method, the user's heart rate signal is then determined based on the fundamental frequency. Specifically, the heart rate is equal to the fundamental frequency * 60 BPM / min. If the fundamental frequency is k, the user's heart rate is k * 60 BPM / min; if the fundamental frequency is 0.5 * k, the user's heart rate is 0.5 * k * 60 BPM / min.

[0142] In summary, this human vital sign monitoring method first acquires a first signal from a sensor, then preprocesses the first signal by filtering to obtain a second signal. Next, based on the second signal, a time window, and an iteration step size, a third signal is acquired. Finally, the signal characteristics of the third signal are obtained, and based on these characteristics, the presence of snoring signals and the user's heart rate are determined. Therefore, this human vital sign monitoring method can preprocess the sensor-acquired signals to remove interference, and then determine the presence of snoring signals and the user's heart rate based on the signal characteristics of the preprocessed signals, thus accurately monitoring the user's snoring and heart rate and improving the user's sleep safety.

[0143] It should be noted that in the above embodiments, there is no necessarily a certain order between the above steps. Those skilled in the art can understand from the description of the embodiments of the present invention that the above steps may have different execution orders in different embodiments, that is, they may be executed in parallel or in interchange, etc.

[0144] As another aspect of this invention, this embodiment provides a human vital signs monitoring device 30. The human vital signs monitoring device 30 can be a software module, which includes several instructions stored in the memory of a controller 32. The processor can access the memory, call the instructions, and execute them to complete the human vital signs monitoring methods described in the above embodiments.

[0145] In some embodiments, the human vital signs monitoring device 30 can also be constructed from hardware devices. For example, the human vital signs monitoring device 30 can be constructed from one or more chips, and the chips can work together to complete the human vital signs monitoring method described in the above embodiments. As another example, the human vital signs monitoring device 30 can also be constructed from various logic devices, such as general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), microcontrollers, ARM (Acorn RISC Machine) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of these components.

[0146] Please see Figure 9 , Figure 9This invention provides a human vital signs monitoring device 30, which includes a first acquisition module 91, a filtering module 92, a second acquisition module 93, a first determination module 94, and a second determination module 95.

[0147] The first acquisition module 91 is used to acquire the first signal collected by the sensor;

[0148] The filtering module 92 is used to perform filtering preprocessing on the first signal to obtain the second signal;

[0149] The second acquisition module 93 is used to obtain the third signal based on the second signal, the time window, and the iteration step size;

[0150] The first determining module 94 is used to acquire the signal characteristics of the third signal and determine whether there is a snoring signal in the third signal based on the signal characteristics of the third signal.

[0151] The second determining module 95 is used to determine the user's heart rate signal based on the signal characteristics of the third signal.

[0152] Therefore, this human vital signs monitoring device can preprocess the signals collected by the sensor to remove interference, and then determine whether there is a snoring signal and the user's heart rate signal based on the signal characteristics of the preprocessed signal, so as to accurately monitor the user's snoring and heart rate and improve the user's sleep safety.

[0153] It should be noted that since the human vital signs monitoring device and the human vital signs monitoring method in the above embodiments are based on the same inventive concept, the corresponding contents in the above method embodiments are also applicable to the device embodiments, and will not be described in detail here.

[0154] This invention also provides a non-transitory computer-readable storage medium storing computer-executable instructions that are executed by one or more processors, for example... Figure 3 One of the processors 321 can enable the one or more processors to execute the human vital signs monitoring method in any of the above method embodiments.

[0155] This invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, which, when executed by a controller 32, cause the controller 32 to perform any of the human vital signs monitoring methods described above.

[0156] In summary, this human vital signs monitoring device can preprocess the signals collected by the sensors to remove interference, and then determine the presence of snoring signals and the user's heart rate signals based on the signal characteristics of the preprocessed signals, so as to accurately monitor the user's snoring and heart rate and improve the user's sleep safety.

[0157] The device or equipment embodiments described above are merely illustrative. The unit modules described as separate components may or may not be physically separate. The components shown as module units may or may not be physical units; that is, they may be located in one place or distributed across multiple network module units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the human vital sign monitoring method described in various embodiments or some parts of embodiments.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for monitoring human vital signs, applied to a human vital signs monitoring device, characterized in that, The human vital signs monitoring device includes a sensor, the sensor being used to collect a first signal from the user, the first signal being used to characterize the user's human vital signs, and the method including: Acquire the first signal collected by the sensor; The first signal is subjected to power frequency noise removal to eliminate power frequency interference; The first signal, after removing power frequency noise, is filtered and preprocessed to obtain the second signal; The filtering preprocessing includes: when used for snoring signal detection, a bandpass filter is used to preprocess the first signal, wherein the low-end cutoff frequency of the bandpass filter is a first preset frequency and the high-end cutoff frequency is a second preset frequency; when used for heart rate signal detection, a low-pass filter is used to preprocess the first signal, wherein the low-end cutoff frequency of the low-pass filter is a third preset frequency. A third signal is obtained based on the second signal, the time window, and the iteration step size. When used for snoring signal detection, the time window is a first time window and the iteration step size is a first iteration step size. When used for heart rate signal detection, the time window is a second time window and the iteration step size is a second iteration step size. The first time window is smaller than the second time window, and the first iteration step size is smaller than the second iteration step size. Acquiring the signal characteristics of the third signal and determining whether a snoring signal exists in the third signal based on the signal characteristics of the third signal, the acquisition of the signal characteristics of the third signal and the determination of whether a snoring signal exists in the third signal based on the signal characteristics of the third signal include: acquiring the number of zero-crossing points and the signal energy value of the third signal; when the number of zero-crossing points and the signal energy value reach a first preset condition, it is determined that a snoring signal exists in the third signal, the first preset condition includes: the number of zero-crossing points is greater than a first preset threshold, and the signal energy value is within a first preset interval, the first preset threshold is 40, and the first preset interval is [163840, 6560000]; Determining the user's heart rate signal based on the signal characteristics of the third signal, wherein determining the user's heart rate signal based on the signal characteristics of the third signal includes: removing the baseline and adding a Hamming window to the third signal to obtain a fourth signal; performing a Fourier transform on the fourth signal to obtain a first curve relating amplitude and frequency; obtaining all amplitude maxima on the first curve where the frequency is in a second interval and their corresponding first frequencies; determining the fundamental frequency of the heart rate signal based on all amplitude maxima and their corresponding first frequencies, wherein determining the fundamental frequency of the heart rate signal based on all amplitude maxima and their corresponding first frequencies includes: obtaining the second frequency corresponding to the largest amplitude maxima based on all amplitude maxima and their corresponding first frequencies; if the frequency is in a third interval on the first curve... If the amplitude of the heart rate signal is maximized within the third interval and the amplitude of the signal is maximized within the fourth interval, then the fundamental frequency of the heart rate signal is determined to be the second frequency. Here, the third interval is [2*k-Δf, 2*k+Δf], the fourth interval is [3*k-Δf, 3*k+Δf], k is the second frequency, and Δf is a second preset threshold. If the amplitude of the heart rate signal is maximized within the fifth interval and the frequency of the heart rate signal is maximized within the sixth interval on the first curve, then the fundamental frequency of the heart rate signal is determined to be 0.5*k. Here, the fifth interval is [0.5*k-Δf, 0.5*k+Δf], the sixth interval is [1.5*k-Δf, 1.5*k+Δf], k is the second frequency, and Δf is a second preset threshold. Based on the fundamental frequency, the user's heart rate signal is determined.

2. The method for monitoring human vital signs according to claim 1, characterized in that, The process of removing the baseline and adding a Hamming window to the third signal to obtain the fourth signal includes: Obtain the mean value of the third signal; The third signal is subjected to baseline removal operation, which is performed using the following formula: r[n] = q[n] - mean; Where r[n] is the signal obtained after removing the baseline, q[n] is the third signal, and mean is the mean of the third signal; A Hamming window operation is performed on the third signal after baseline removal to generate a Hamming window signal, the data length of which is the same as that of the third signal. The fourth signal is obtained by the following formula: y[n]=r[n]*u[n]; Wherein, y[n] is the fourth signal, and u[n] is the Hamming window signal.

3. A human vital signs monitoring device, characterized in that, The human vital signs monitoring device includes: A sensor is used to acquire a first signal from the user, the first signal representing the user's vital signs; and, A controller, which is communicatively connected to the sensor, includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the human vital signs monitoring method as described in any one of claims 1-2.

4. A smart monitoring pillow, characterized in that, The intelligent monitoring pillow includes: a pillow body, a main control box, and a human vital signs monitoring device as described in claim 3; the sensor is disposed inside the pillow body; and the controller is disposed inside the main control box.

Images