Heart rate detection method and device, wearable equipment and storage medium

Abstract

The invention discloses a heart rate detection method and device, wearable equipment and a storage medium, and belongs to the technical field of heart rate detection. According to the method, an angle sensor and at least two heart rate sensors are utilized, human body posture changes are judged by receiving angle signals, and heart rate detection is carried out based on the human body posture changes. When the angle change amplitude is smaller than a preset threshold value, the weight is calculated through the signal intensity of each heart rate sensor, and weighted fusion is carried out to obtain a heart rate value; when the angle change amplitude is larger than or equal to a preset threshold value, the heart rate sensing signals are processed in a segmented mode according to the heartbeat cycle, waveforms are screened and recombined, and the final heart rate value is calculated. According to the method, the problems of wearing position change and signal intensity change are effectively solved through analysis, weight calculation and data fusion of the signal intensity and the wave crest and wave trough pressure difference, and the accuracy and stability of heart rate detection are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of heart rate detection, and more specifically, to a heart rate detection method and apparatus, a wearable device and a storage medium. Background Art

[0002] As people's health awareness increases, heart rate detection technology is increasingly used in health monitoring devices. Especially for the elderly, heart rate detection has become an important means to pay attention to their own health. Common wearable devices on the market, such as heart rate detection bracelets, mainly use a single heart rate sensor for detection. However, during use, we found that this single sensor detection method has some shortcomings.

[0003] First, the heart rate detection bracelet requires the user to align the sensor position with the back of the wrist or the wrist during use. Due to the large deviation angle of the sensor position, sweat soaking of the hands, or wearing it too loosely, the detection accuracy of the sensor is seriously affected. These problems may lead to inaccurate heart rate detection results, thus affecting the user's judgment of their own health status.

[0004] Secondly, when this heart rate detection technology is applied to elderly care scenarios, the particularity of the elderly needs to be considered. Some elderly people may not adjust the position of the bracelet on their own, causing the heart rate detection to be inaccurate for a long time. This will not only affect the stable operation of the health monitoring system, but may also seriously affect the credibility of the alarm information and even cause the system to fail.

[0005] Finally, the heart rate bracelet is an important device for realizing real-time health monitoring of the elderly, and it is also the basis for the stable operation and function of the smart elderly care system. Unlike ordinary smart bracelet applications, some elderly people to be monitored cannot adjust the position of the bracelet independently or unconsciously. Under normal circumstances, as the human body ages, physical weakness, weak heartbeat, blood vessel blockage, heart disease, etc. will all worsen. These problems will cause the heartbeat to weaken, but the current mainstream optical heart rate sensors require a certain heartbeat intensity to collect stable signals. The weakened heartbeat will cause the interference of sensor perception data to increase. The above situations ultimately lead to the inability of heart rate sensors to measure stably in the elderly health monitoring bracelet application.

[0006] In response to the above problems, it is urgent to design a multi-sensor heart rate detection device and its supporting calculation method to solve the detection accuracy problem of a single sensor and provide a stable and reliable health monitoring solution for the elderly. Summary of the invention

[0007] In order to overcome the detection accuracy problem existing in a single sensor, the present invention provides a heart rate detection method and device, a wearable device and a storage medium.

[0008] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0009] A heart rate detection method, which uses at least two heart rate sensors to measure the heart rate, comprises the following steps:

[0010] receiving an angle signal output by an angle sensor, obtaining an angle change amplitude based on the angle signal, comparing the angle change amplitude with a predetermined threshold value, and determining a degree of change in the posture of the human body;

[0011] When the angle change amplitude is less than a predetermined threshold, receiving the heart rate sensing signal output by each of the heart rate sensors, calculating the signal strength of each heart rate sensor, calculating and assigning a weight value based on the signal strength, and performing weighted fusion on the heart rate sensing data of each of the heart rate sensors based on the weight value to obtain a heart rate value;

[0012] When the angle change amplitude is greater than or equal to a predetermined threshold, the heart rate sensing signals output by each of the heart rate sensors are received, the heart rate sensing signals within the measurement period are segmented according to the heartbeat cycle, and the heart rate sensing waveforms of each of the heart rate sensors within a single heartbeat cycle are extracted, and all heart rate sensing waveforms that meet the preset conditions within the measurement period are screened out, all heart rate sensing waveforms that meet the preset conditions are recorded into the signal waveform to be processed and recombined into a heartbeat sensing signal waveform, and calculations are performed based on the heartbeat sensing signal waveform to obtain the heart rate value.

[0013] Further, in the heart rate detection method, the predetermined threshold used for comparison with the angle change amplitude is set to 20°;

[0014] The heart rate detection method further includes uploading the obtained heart rate value to a server, and the server is used to perform data analysis on the uploaded heart rate value.

[0015] Furthermore, three heart rate sensors are provided, and each of the heart rate sensors can independently collect heart rate sensing signals;

[0016] Based on the collected heart rate sensing signal, a single sensor heart rate calculation method is used to calculate the heart rate values ​​f1, f2, and f3 of the three heart rate sensors;

[0017] During the heart rate measurement, the signal strength is marked by the induced voltage difference between the signal peaks and troughs and recorded according to the measurement cycle.

[0018] Further, the signal strength calculation step includes:

[0019] Recording the peak-to-trough pressure difference u of the heart rate sensing signal of each heart rate sensor during the measurement period;

[0020] The maximum peak-to-trough pressure difference U of the heart rate sensor max is a fixed value;

[0021] By calculating the formula The signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement period are calculated respectively.

[0022] Further, when the angle change amplitude is less than a predetermined threshold, the heart rate value calculation process includes:

[0023] Calculate the signal strengths S1, S2, and S3 of the three heart rate sensors during a measurement period;

[0024] Calculate the differences P1, P2, and P3 between the maximum and minimum peak values ​​of the heart rate sensing waveforms of the three heart rate sensors within a measurement period;

[0025] Among them, S1, P1, and f1 correspond to each other, S2, P2, and f2 correspond to each other, and S3, P3, and f3 correspond to each other;

[0026] Arrange the signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement period in descending order, and name the signal strengths arranged in order of size S1, S2, and S3. a , S b , S c ;

[0027] will be related to the signal strength S a , S b , S c The corresponding P value is named P a , P b , P c , the P value is the difference between the maximum value of the peak and the minimum value of the peak;

[0028] will be related to the signal strength S a , S b , S c The corresponding heart rate value is named f a 、f b 、f c ;

[0029] Introducing weight coefficient k a , k b , k c , the weight coefficient k a , k b , k c is a constant and its value range satisfies k a >2*k b >3*k c ;

[0030] Calculate the weight value of each heart rate sensor:

[0031] W a =k a *S a / P a ;

[0032] W b =k b *S b / P b ;

[0033] W c =k c *S c / P c ;

[0034] After the calculation is completed, W a , W b , W c Normalize it so that W a +W b +W c =1;

[0035] According to the normalized weight value, calculate the heart rate value F:

[0036] F=W a *f a +W b *f b +W c *f c .

[0038] Further, when the angle change amplitude is greater than or equal to a predetermined threshold, the heart rate value calculation process includes:

[0039] The heart rate sensing signal in the measurement period is segmented according to the heartbeat cycle, the heart rate sensing waveforms of the three heart rate sensors in a single heartbeat cycle are extracted, and the peak and trough signal difference of the heart rate sensing waveform is recorded as u ij , and obtain a matrix:

[0040]

[0041] The value of i is 1, 2, and 3, which are used to distinguish the three heart rate sensors; the value of j is a natural number from 1 to n; n is the number of heartbeat cycles in the measurement period;

[0042] Set the reference value U of the peak-valley signal difference, where U is a constant;

[0043] Compare each set of three values ​​in the matrix with U and filter out u 1j 、u 2j 、u3j The value closer to U is selected, and the screened value is judged to be between 0.8U and 1.2U;

[0044] If the screened value is between 0.8U and 1.2U, the heart rate sensing waveform of the heartbeat cycle corresponding to the value is put into the sensing signal waveform to be processed; if the screened value is not between 0.8U and 1.2U, it is recorded as invalid data, and the cycle is skipped in the signal waveform to be processed;

[0045] The heart rate sensing waveforms of all qualified heartbeat cycles within the measurement period are screened out, all are recorded into the signal waveforms to be processed and recombined into a heartbeat sensing signal waveform, and the time and number of heart rate cycles corresponding to the heartbeat sensing signal waveform are substituted into the single sensor heart rate calculation method to obtain the heart rate value.

[0046] A heart rate detection device, which uses at least two heart rate sensors to measure heart rate, and the heart rate detection device comprises:

[0047] A receiving module, the receiving module is used to receive the heart rate sensing signal output by each of the heart rate sensors and the angle signal output by the angle sensor;

[0048] A state judgment module, the state judgment module is used to obtain an angle change amplitude according to the angle signal, compare the angle change amplitude with a predetermined threshold value, and judge the degree of change of the posture of the human body;

[0049] a first calculation module, configured to calculate the signal strength of each heart rate sensor when the angle change amplitude is less than a predetermined threshold, calculate and assign a weight value based on the signal strength, and perform weighted fusion on the heart rate sensing data of each heart rate sensor based on the weight value to obtain a heart rate value;

[0050] A second calculation module is used to segment the heart rate sensing signal within the measurement period according to the heartbeat cycle when the angle change amplitude is greater than or equal to a predetermined threshold value, and extract the heart rate sensing waveform of each heart rate sensor within a single heartbeat cycle, screen out all heart rate sensing waveforms that meet the preset conditions within the measurement period, enter all heart rate sensing waveforms that meet the preset conditions into the signal waveform to be processed and recombine them into a heartbeat sensing signal waveform, and perform calculations based on the heartbeat sensing signal waveform to obtain a heart rate value.

[0051] Furthermore, there are three heart rate sensors, each of which can independently collect heart rate sensing signals, and the three heart rate sensors are connected by flexible PCBs or soft cables; the heart rate detection device also includes a wireless transmission module, which is used to upload the obtained heart rate value to the server, and the server is used to perform data analysis on the uploaded heart rate value.

[0052] A wearable device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method when executing the program.

[0053] A computer-readable storage medium stores a computer program, which implements the aforementioned method when executed by a processor.

[0054] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0055] The present invention provides a heart rate detection method and device, a wearable device and a storage medium, and provides a real-time heart rate sensing solution suitable for the elderly, including a device and a matching multi-sensor heart rate calculation and analysis method. Compared with traditional technologies, this solution not only ensures the integrity and timeliness of heart rate sensing in various scenes and environments through a multi-sensor approach, but also calculates the signal stability through the data difference between multiple sensors while giving the heart rate value, as well as the current angle of each sensor, and analyzes the stability of the corresponding heart rate. Through the matching use of heart rate value and stability, the upper-level platform can accurately monitor the physical condition of the elderly and alarm for abnormal heart rate during data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a flowchart of a heart rate detection method provided in one embodiment of the present application;

[0058] Figure 2 is a system block diagram of a heart rate detection device provided in one embodiment of the present application;

[0059] Figure 3 is a schematic diagram of the hardware composition of a heart rate detection device provided in one embodiment of the present application;

[0060] Figure 4 is a structural schematic diagram of a heart rate detection device provided in one embodiment of the present application;

[0061] Figure 5 A schematic diagram of the structure of a wearable device provided in one embodiment of the present application;

[0062] Description of the markings in the figure:

[0063] 101, receiving module; 102, state determination module; 103, first calculation module; 104, second calculation module;

[0064] 201, heart rate sensor 1; 202, heart rate sensor 2; 203, heart rate sensor 3; 204, main controller; 2041, control main board; 2042, angle sensor; 2043, power supply module; 2044, wireless transmission module;

[0065] 301. memory; 302. processor;

[0066] 401. Soft flat cable; 402. Watch strap buckle. DETAILED DESCRIPTION

[0067] In order to better understand the purpose, structure and function of the present invention, the technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0068] In the description of the present invention, it should be understood that the terms "left side", "right side", "upper part", "lower part", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. "First", "second", etc. do not indicate the importance of the parts, and therefore cannot be understood as a limitation on the present invention. The specific dimensions used in the embodiments are only for illustrating the technical solution and do not limit the scope of protection of the present invention. It is understandable to those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.

[0069] Unless otherwise clearly specified and limited, the terms "install", "set", "connect", "fix" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0070] Embodiment 1:

[0071] like Figure 1 As shown, the present invention provides a technical solution:

[0072] A heart rate detection method, which uses at least two heart rate sensors to measure the heart rate, comprises the following steps:

[0073] receiving an angle signal output by an angle sensor, obtaining an angle change amplitude based on the angle signal, comparing the angle change amplitude with a predetermined threshold value, and determining a degree of change in the posture of the human body;

[0074] When the angle change amplitude is less than a predetermined threshold, receiving the heart rate sensing signal output by each heart rate sensor, calculating the signal strength of each heart rate sensor, calculating and assigning a weight value based on the signal strength, and performing weighted fusion on the heart rate sensing data of each heart rate sensor based on the weight value to obtain a heart rate value;

[0075] When the angle change amplitude is greater than or equal to a predetermined threshold, the heart rate sensing signals output by each heart rate sensor are received, the heart rate sensing signals within the measurement period are segmented and processed according to the heartbeat cycle, and the heart rate sensing waveforms of each heart rate sensor within a single heartbeat cycle are extracted, and all heart rate sensing waveforms that meet the preset conditions within the measurement period are screened out, and all heart rate sensing waveforms that meet the preset conditions are entered into the signal waveform to be processed and recombined into a heartbeat sensing signal waveform, and calculations are performed based on the heartbeat sensing signal waveform to obtain the heart rate value.

[0076] This embodiment uses an angle sensor to determine changes in human posture, thereby selecting an appropriate heart rate calculation method. When the angle change is less than a predetermined threshold, the stability and accuracy of the heart rate value are improved by weighted fusion of the heart rate sensor data; and when the angle change is greater than or equal to the predetermined threshold, the segmented processing and waveform screening method is used to effectively eliminate the interference caused by posture changes and improve the accuracy of detection. This method can ensure the reliability of heart rate detection under various sports and activity conditions, and avoid the data deviation that may be caused by a single sensor.

[0077] Embodiment 2:

[0078] Based on Example 1, three heart rate sensors are provided. It is hereby stated that the following calculation method is not only applicable to the three-sensor design, but also meets the design of more sensors. The calculation example in this article uses the three-sensor data for calculation;

[0079] Each heart rate sensor can independently collect heart rate sensing signals, and calculate the heart rate value through the collected heart rate signals. The heart rate value calculation here adopts the commonly used single-sensor heart rate calculation method to obtain, which are f1, f2, and f3 respectively;

[0080] At the same time, in the process of measuring heart rate, the signal strength is marked by the induced voltage difference between the signal peak and the trough, and recorded according to the measurement cycle; the larger the pressure difference value, the stronger the signal strength.

[0081] Further, the signal strength calculation steps include:

[0082] Record the peak-to-trough pressure difference u of the heart rate sensing signal of each heart rate sensor during the measurement period;

[0083] The maximum peak-to-trough pressure difference U of the known heart rate sensor max , which is a given value;

[0084] By calculating the formula The signal strengths in the measurement period are obtained; the signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement period can be calculated respectively.

[0085] In addition, the peak value of the heart rate signal is not constant and is affected by many factors. At the same time, the stability of the value also affects the accuracy of the final measurement value. Here, the difference between the maximum and minimum values ​​of the peak position sensing value in the statistical time period is recorded as P; the P values ​​in the measurement cycles of the three sensors are calculated as P1, P2, and P3 respectively;

[0086] After wearing the heart rate bracelet, the fit between the heart rate sensor on the inside of the bracelet and the skin, the position of the monitoring point corresponding to the wrist, the height of the sensor from the skin, etc. will directly affect the sensor's perception accuracy. The present invention adopts a multi-sensor design, which will effectively avoid the situation of insufficient fit with the skin and poor detection position when using a single sensor.

[0087] The present invention relates to a process of sensor sensing signals, using different three-sensor data integration calculation methods in different scenarios.

[0088] The first case is that the user does not make large movements during the entire measurement period, and the position of the bracelet is relatively stable. In this case, the position of the sensor relative to the wrist and the distance of the sensor relative to the skin are relatively stable, and the signal strength S can truly and stably represent the heart rate signal. In this case, the data of the three sensors are calculated separately, and finally the data is fused according to the weights;

[0089] The second situation is that the user swings his arm or makes other movements during the sensor measurement process. At this time, the position of the wristband sensor relative to the user's wrist may be in a changing state, or the position of the wristband sensor relative to the skin may be in a changing process. In this case, the signal strength S and the peak-to-trough pressure difference u of the sensor heart rate sensing signal are likely to have interference signals, and single sensor data cannot be effectively filtered. In this case, the three-sensor sensing data is first fused and cropped into a stable heart rate signal, and then the heart rate is calculated. The two methods complement each other to achieve the heart rate sensing process in all scenarios.

[0090] The selection of the above two calculation methods is determined based on the angle change amplitude of the angle sensor during the measurement process. When the angle change is large, method 2 is selected; here, 20° is used as the threshold for the calculation method selection;

[0091] Furthermore, when the angle change amplitude is less than a predetermined threshold, the heart rate value calculation process includes:

[0092] Calculate the signal strengths S1, S2, and S3 of the three heart rate sensors during the measurement period;

[0093] Calculate the differences P1, P2, and P3 between the maximum and minimum peak values ​​of the heart rate sensing waveforms of the three heart rate sensors within the measurement period;

[0094] Among them, S1, P1, and f1 correspond to each other, S2, P2, and f2 correspond to each other, and S3, P3, and f3 correspond to each other;

[0095] Arrange the signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement cycle in descending order, and name the signal strengths arranged in order of size S a , S b , S c ;

[0096] will be related to the signal strength S a , S b , S c The corresponding P value is named P a , P b , P c , the P value is the difference between the maximum value of the peak and the minimum value of the peak;

[0097] will be related to the signal strength S a , S b , S c The corresponding heart rate value is named f a 、f b 、f c ;

[0098] Introducing weight coefficient k a , k b , k c , which is obtained based on historical data and experience and can be dynamically adjusted during use. The weight coefficient k a , k b , k c is a constant and its value range satisfies k a >2*k b >3*k c ;

[0099] Calculate the weight value of each heart rate sensor:

[0100] W a =k a *S a / P a ;

[0101] Wb =k b *S b / P b ;

[0102] W c =k c *S c / P c ;

[0103] After the calculation is completed, W a , W b , W c Normalize it so that W a +W b +W c =1;

[0104] According to the normalized weight value, calculate the heart rate value F:

[0105] F=W a *f a +W b *f b +W c *f c ;

[0106] At the same time, S a Defined as the final heart rate signal strength S.

[0107] Among them, the signal strength is positively correlated with the weight, the peak fluctuation P is negatively correlated with the weight, and the constant can be adjusted according to the actual design of the wristband. The main purpose of the above calculation between the multi-sensor sensed heart rate and the final heart rate is to increase the weight of high-quality sensed data and reduce or shield the impact of low-quality data on the final heart rate calculation.

[0108] Furthermore, when the angle variation is greater than or equal to a predetermined threshold, the heart rate value calculation process includes:

[0109] In the measurement cycle time t, the signal values ​​sensed by the three sensors are output simultaneously. The heart rate sensing signal in the measurement cycle t is segmented according to the heartbeat cycle, the heart rate sensing waveforms of the three sensors in a single heartbeat cycle are extracted, and the peak and trough signal difference of the heart rate sensing waveform is recorded as u ij , and obtain a matrix:

[0110]

[0111] The value of i is 1, 2, and 3, which are used to distinguish the three heart rate sensors; the value of j is a natural number from 1 to n; n is the number of heartbeat cycles in the measurement period;

[0112] Set a reference value U of the peak-to-trough signal difference, where U is a constant; the reference U value is a constant, which is a reference value of the U value of a normal human heart rate waveform obtained by the sensor at an ideal position;

[0113] By comparing the relationship between each group of three values ​​and the reference U, u is screened out. 1j 、u 2j 、u 3j The value closer to U is selected, and the value is checked to see if it is between 0.8 and 1.2 times U, where 0.8 and 1.2 times U include the end values ​​at both ends, to ensure that the screening value does not deviate from the normal U value and belongs to the reliable data range. If the above description is met, the heartbeat cycle waveform corresponding to the value is recorded in the waveform of the sensing signal to be processed. If the above description is not met, the data is recorded as invalid, and the cycle can be skipped in the waveform of the signal to be processed;

[0114] Through this method, all the heartbeat cycle waveforms that meet the requirements within the measurement period t are screened out, all of which are recorded into the signal waveform to be processed, and the partial waveforms are recombined into a new heartbeat sensing signal waveform, and the time and heart rate cycle number corresponding to the waveform are substituted into the single sensor heart rate calculation method to obtain the final heart rate value F; at the same time, the signal strength S value of the new waveform is output;

[0115] Therefore, the aforementioned preconditions include:

[0116] 1. Compare each group of three values ​​in the matrix with U and filter out u 1j 、u 2j 、u 3j The value closer to U;

[0117] 2. The screened values ​​are between 0.8U and 1.2U.

[0118] Among them, the single-sensor heart rate calculation method is a prior art, which refers to the technology of using a heart rate sensor to measure and calculate the heart rate. The core of this method is to extract the heart rate information from the signal collected by the heart rate sensor. The single-sensor heart rate calculation method is not a technical solution to be protected in this application, so it will not be described in detail.

[0119] The calculation process of method 2 is as follows;

[0120] Step Description:

[0121] Step 1: Segment the signal within time t according to the heartbeat cycle;

[0122] Step 2, obtain the matrix of signal peak and trough signal difference records u;

[0123] Step 3: Filter the value closest to U among the three data in each period;

[0124] Step 4: Splice the signal segment that meets the 0.8-1.2U range into the final waveform;

[0125] Step 5. Complete the calculation and screening of all waveforms to obtain the final waveform;

[0126] Step 6. Substitute the waveform related values ​​into the single sensor heart rate calculation method;

[0127] step7. Output the final heart rate value F and signal strength S;

[0128] Based on the above method, multiple waveforms of multi-sensor devices are integrated into a waveform with the highest credibility, which can avoid the problem of weak or lost sensor waveform signals caused by wearing the bracelet too loosely during activities.

[0129] Further, in the heart rate detection method, the predetermined threshold used for comparison with the angle change amplitude is set to 20°;

[0130] The heart rate detection method also includes uploading the obtained heart rate value to a server, and the server is used to perform data analysis on the uploaded heart rate value.

[0131] This embodiment effectively reduces the error caused by poor position of a single sensor or insufficient signal strength by setting three heart rate sensors and marking and calculating the signal strength of each sensor. The accuracy of the final heart rate value is further improved by normalizing the signal strength and calculating the weight. Especially when the bracelet is not worn well or the user moves frequently, this embodiment can provide more stable and reliable heart rate data.

[0132] Embodiment 3:

[0133] like Figure 2 As shown, the present invention provides a technical solution:

[0134] A heart rate detection device, which uses at least two heart rate sensors to measure heart rate, and the heart rate detection device includes:

[0135] A receiving module 101, the receiving module 101 is used to receive the heart rate sensing signal output by each heart rate sensor and the angle signal output by the angle sensor;

[0136] The state judgment module 102 is used to obtain the angle change amplitude according to the angle signal, compare the angle change amplitude with a predetermined threshold value, and judge the degree of change of the posture of the human body;

[0137] A first calculation module 103, the first calculation module 103 is used to calculate the signal strength of each heart rate sensor when the angle change amplitude is less than a predetermined threshold, calculate and assign a weight value based on the signal strength, and perform weighted fusion on the heart rate sensing data of each heart rate sensor based on the weight value to obtain a heart rate value;

[0138] The second calculation module 104 is used to segment the heart rate sensing signal within the measurement period according to the heartbeat cycle when the angle change amplitude is greater than or equal to a predetermined threshold value, and extract the heart rate sensing waveform of each heart rate sensor within a single heartbeat cycle, screen out all heart rate sensing waveforms that meet the preset conditions within the measurement period, enter all the heart rate sensing waveforms that meet the preset conditions into the signal waveform to be processed and recombine them into a heartbeat sensing signal waveform, and perform calculations based on the heartbeat sensing signal waveform to obtain the heart rate value.

[0139] This embodiment provides a heart rate detection device that can select an appropriate heart rate calculation method and perform corresponding calculation steps based on the angle signal output by the angle sensor. The modular design enhances the flexibility and adaptability of the system, so that the device can effectively perform heart rate detection in various practical application scenarios. This design enables the device to cope with the challenges brought by changes in user posture and improves the overall effect of heart rate monitoring.

[0140] Embodiment 4:

[0141] Based on Example 3, Figure 3-4 There are three heart rate sensors, each of which can independently collect heart rate sensing signals. The heart rate detection device also includes a wireless transmission module 2044, which is used to upload the obtained heart rate value to the server, and the server is used to perform data analysis on the uploaded heart rate value.

[0142] Further, if Figure 4 As shown, the three heart rate sensors are exactly the same and are evenly distributed on the bracelet at an interval of 120° from each other; the three heart rate sensors are connected by a flexible PCB or a flexible flat cable, and a main controller 204 is designed on the top;

[0143] like Figure 3 As shown, the three sensors are connected to the main controller 204 via the IIC bus. The main controller 204 includes a control mainboard 2041, an angle sensor 2042, a power supply module 2043, and a wireless transmission module 2044, wherein the wireless transmission module 2044 is used to upload the monitored heart rate data to the server in real time.

[0144] Based on Example 3, this embodiment further adopts a wireless transmission module 2044 to upload the detected heart rate value to the server for data analysis. By setting three sensors and connecting them through a flexible PCB, the durability and comfort of the device are enhanced. In addition, the design of the device adapts to different wearing methods, ensuring the effectiveness of the sensor and the accuracy of the data. This design improves the applicability and user experience of the device.

[0145] Embodiment 5:

[0146] The present invention provides a technical solution:

[0147] A wearable device includes a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302. When the processor 302 executes the program, the aforementioned method is implemented.

[0148] In actual use, a flexible PCB can be used to design a substrate for three or more sensors, thereby realizing a bendable wristband with internal wiring.

[0149] Or it can be designed as a bracelet. Since the internal sensors are evenly distributed and the multi-sensor design can ensure that there are sensors that fit the skin at any angle of human movement, it can be designed as a loose bracelet, no longer limited to the traditional bracelet form, that is, the strap cannot be too loose, and the sensor must be directly on the back of the wrist and the wrist; if the strap is too loose, the sensor will be too far away from the skin surface, and the sensor cannot effectively sense the heartbeat. The advantage of this technical solution is that the bracelet solution is no longer limited to the bracelet form, and does not require the wearing direction, so the main controller can be designed to be hidden.

[0150] This embodiment provides a wearable device, including a memory 301 and a processor 302, and implements the above method through a computer program. The design allows the device to be in the form of a flexible PCB or a bracelet, and is no longer limited to the traditional bracelet form, providing more wearing options. This design improves the wearing comfort of the device without affecting the accuracy of heart rate detection, making the device more in line with user needs and usage habits.

[0151] Embodiment 6:

[0152] The present invention provides a technical solution:

[0153] A computer-readable storage medium stores a computer program, which implements the aforementioned method when executed by a processor.

[0154] This embodiment provides a computer-readable storage medium storing a program for implementing the above-mentioned heart rate detection method. This technical solution enables the heart rate detection method to be widely applied through a computer program, facilitating the implementation and promotion of the method. Through program execution, efficient heart rate detection and data processing can be achieved, further promoting the application and development of the technology.

[0155] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A heart rate detection method, characterized in that: At least two heart rate sensors are used to measure the heart rate, which includes the following steps: receiving an angle signal output by an angle sensor, obtaining an angle change amplitude based on the angle signal, comparing the angle change amplitude with a predetermined threshold value, and determining a degree of change in the posture of the human body; When the angle change amplitude is less than a predetermined threshold, receiving the heart rate sensing signal output by each of the heart rate sensors, calculating the signal strength of each heart rate sensor, calculating and assigning a weight value based on the signal strength, and performing weighted fusion on the heart rate sensing data of each of the heart rate sensors based on the weight value to obtain a heart rate value; When the angle change amplitude is greater than or equal to a predetermined threshold, the heart rate sensing signals output by each of the heart rate sensors are received, the heart rate sensing signals within the measurement period are segmented according to the heartbeat cycle, and the heart rate sensing waveforms of each of the heart rate sensors within a single heartbeat cycle are extracted, and all heart rate sensing waveforms that meet the preset conditions within the measurement period are screened out, all heart rate sensing waveforms that meet the preset conditions are recorded into the signal waveform to be processed and recombined into a heartbeat sensing signal waveform, and calculations are performed based on the heartbeat sensing signal waveform to obtain the heart rate value.

2. The heart rate detection method according to claim 1, characterized in that: In the heart rate detection method, the predetermined threshold used for comparison with the angle change amplitude is set to 20°; The heart rate detection method further includes uploading the obtained heart rate value to a server, and the server is used to perform data analysis on the uploaded heart rate value.

3. The heart rate detection method according to claim 1, characterized in that: There are three heart rate sensors, each of which can independently collect heart rate sensing signals; Based on the collected heart rate sensing signal, a single sensor heart rate calculation method is used to calculate the heart rate values ​​f1, f2, and f3 of the three heart rate sensors; During the heart rate measurement, the signal strength is marked by the induced voltage difference between the signal peaks and troughs and recorded according to the measurement cycle.

4. The heart rate detection method according to claim 3, characterized in that: The signal strength calculation step includes: Recording the peak-to-trough pressure difference u of the heart rate sensing signal of each heart rate sensor during the measurement period; The maximum peak-to-trough pressure difference U of the heart rate sensor max is a fixed value; By calculating the formula The signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement period are calculated respectively.

5. The heart rate detection method according to claim 4, characterized in that: When the angle change amplitude is less than a predetermined threshold, the heart rate value calculation process includes: Calculate the signal strengths S1, S2, and S3 of the three heart rate sensors during a measurement period; Calculate the differences P1, P2, and P3 between the maximum and minimum peak values ​​of the heart rate sensing waveforms of the three heart rate sensors within a measurement period; Among them, S1, P1, and f1 correspond to each other, S2, P2, and f2 correspond to each other, and S3, P3, and f3 correspond to each other; Arrange the signal strengths S1, S2, and S3 of the three heart rate sensors in the measurement period in descending order, and name the signal strengths arranged in order of size S1, S2, and S3. a , S b , S c ; will be related to the signal strength S a , S b , S c The corresponding P value is named P a , P b , P c , the P value is the difference between the maximum value of the peak and the minimum value of the peak; will be related to the signal strength S a , S b , S c The corresponding heart rate value is named f a 、f b 、f c ; Introducing weight coefficient k a , k b , k c , the weight coefficient k a , k b , k c is a constant and its value range satisfies k a >2*k b >3*k c ; Calculate the weight value of each heart rate sensor: W a =k a *S a / P a ; W b =k b *S b / P b ; W c =k c *S c / P c ; After the calculation is completed, W a , W b , W c Normalize it so that W a +W b +W c =1; According to the normalized weight value, calculate the heart rate value F: F=W a *f a +W b *f b +W c *f c 。 6. The heart rate detection method according to claim 4, characterized in that: When the angle change amplitude is greater than or equal to a predetermined threshold, the heart rate value calculation process includes: The heart rate sensing signal in the measurement period is segmented according to the heartbeat cycle, the heart rate sensing waveforms of the three heart rate sensors in a single heartbeat cycle are extracted, and the peak and trough signal difference of the heart rate sensing waveform is recorded as u ij , and obtain a matrix: The value of i is 1, 2, and 3, which are used to distinguish the three heart rate sensors; the value of j is a natural number from 1 to n; n is the number of heartbeat cycles in the measurement period; Set the reference value U of the peak-valley signal difference, where U is a constant; Compare each set of three values ​​in the matrix with U and filter out u 1j 、u 2j 、u 3j The value closer to U is selected, and the screened value is judged to be between 0.8U and 1.2U; If the screened value is between 0.8U and 1.2U, the heart rate sensing waveform of the heartbeat cycle corresponding to the value is put into the sensing signal waveform to be processed; if the screened value is not between 0.8U and 1.2U, it is recorded as invalid data, and the cycle is skipped in the signal waveform to be processed; The heart rate sensing waveforms of all qualified heartbeat cycles within the measurement period are screened out, all are recorded into the signal waveforms to be processed and recombined into a heartbeat sensing signal waveform, and the time and number of heart rate cycles corresponding to the heartbeat sensing signal waveform are substituted into the single sensor heart rate calculation method to obtain the heart rate value.

7. A heart rate detection device, characterized in that: At least two heart rate sensors are used to measure the heart rate, and the heart rate detection device includes: A receiving module, the receiving module is used to receive the heart rate sensing signal output by each of the heart rate sensors and the angle signal output by the angle sensor; A state judgment module, the state judgment module is used to obtain an angle change amplitude according to the angle signal, compare the angle change amplitude with a predetermined threshold value, and judge the degree of change of the posture of the human body; a first calculation module, configured to calculate the signal strength of each heart rate sensor when the angle change amplitude is less than a predetermined threshold, calculate and assign a weight value based on the signal strength, and perform weighted fusion on the heart rate sensing data of each heart rate sensor based on the weight value to obtain a heart rate value; A second calculation module is used to segment the heart rate sensing signal within the measurement period according to the heartbeat cycle when the angle change amplitude is greater than or equal to a predetermined threshold value, and extract the heart rate sensing waveform of each heart rate sensor within a single heartbeat cycle, screen out all heart rate sensing waveforms that meet the preset conditions within the measurement period, enter all heart rate sensing waveforms that meet the preset conditions into the signal waveform to be processed and recombine them into a heartbeat sensing signal waveform, and perform calculations based on the heartbeat sensing signal waveform to obtain a heart rate value.

8. The heart rate detection device according to claim 7, characterized in that: There are three heart rate sensors, each of which can independently collect heart rate sensing signals, and the three heart rate sensors are connected by flexible PCBs or soft cables; the heart rate detection device also includes a wireless transmission module, which is used to upload the obtained heart rate value to a server, and the server is used to perform data analysis on the uploaded heart rate value.

9. A wearable device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images