ECG waveform display method, medium and electronic device thereof

Abstract

The present application relates to the field of electronic technology, and discloses an ECG waveform display method, which includes: an electronic device starts an ECG waveform detection application to collect ECG waveforms; reads the wearing position data between the electronic device and the user's wrist; the wearing position data is obtained through IMU wearing position recognition; the electronic device determines the first wearing position information according to the wearing state data, and the first wearing position information includes a determined state and an uncertain state; the determined state is the first determined state or the second determined state; the electronic device obtains the second wearing position information between the electronic device and the user's wrist through ECG wearing position recognition; when the first wearing position information and the second wearing position information are the same and are in the determined state, the electronic device displays the ECG waveform on the display screen according to the display mode corresponding to the determined state. In this way, the error rate of judging whether the ECG waveform is displayed in a normal display mode can be reduced, and the accuracy of displaying the ECG waveform in a normal display mode can be improved.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to an ECG waveform display method, a medium thereof, and an electronic device. Background Art

[0002] An electrocardiogram (ECG) can reflect the user's health status. For example, ECG can reflect heart diseases (such as arrhythmia), etc. With the continuous development of wearable devices such as smart wristbands and smart watches, health detection functions such as ECG detection can be integrated into wearable devices such as smart watches to monitor the user's heart rate and other physical signs, thereby realizing the prediction of the user's physical status to effectively avoid heart conduction electronic device disorders or myocardial lesions.

[0003] When a user uses a wearable device for ECG detection, the ECG waveform is directly related to the position of the left and right hands of the user wearing the wearable device. For example, if the user wears the wearable device on the left hand and then touches the electrode of the wearable device with the right hand, the ECG waveform generated by the wearable device is a positive waveform. Without changing any configuration of the wearable device, if the user wears the wearable device on the right hand and then touches the electrode of the wearable device with the left hand, the ECG waveform generated by the wearable device is an erroneous reverse waveform.

[0004] In order to determine whether the user wears the wearable device on the left or right hand, the inertial measurement unit built into the wearable device can be used to detect and obtain the deflection angle of the smart wearable device when the user wears it, thereby identifying whether the user wears the wearable device on the left or right hand. However, when the user wears the wearable device for the first time and remains still, the ECG detection function is immediately used, and it is impossible to determine whether the wearer is wearing it on the left or right hand, and therefore it is impossible to determine whether the ECG waveform is displayed normally.

[0005] In another solution for determining whether the user wears the wearable device on the left or right hand, when the user activates the ECG detection function of the wearable device, the ECG waveform generated by the wearable device is compared with a preset reference waveform to identify whether the user wears the wearable device on the left or right hand. However, in the case of a user with a right-biased heart, when the user wears the wearable device on the left hand, the ECG waveform characteristics generated by the wearable device are similar to those of the ECG waveform generated when the user with a normal heart position wears the wearable device on the right hand, which is prone to misjudgment. Summary of the invention

[0006] The embodiments of the present application provide an ECG detection method and device, a medium and an electronic device based on left and right hand identification.

[0007] In a first aspect, an embodiment of the present application provides an ECG waveform display method, the method comprising:

[0008] The electronic device starts an ECG waveform detection application to collect ECG waveforms;

[0009] The electronic device reads the wearing position data between the electronic device and the user's wrist; the wearing position data is obtained by IMU wearing position recognition;

[0010] The electronic device determines first wearing part information according to the wearing state data, wherein the first wearing part information includes a determined state and an uncertain state; the determined state is a first determined state or a second determined state;

[0011] The electronic device obtains second wearing position information between the electronic device and the user's wrist through ECG wearing position recognition;

[0012] When the first wearing part information and the second wearing part information are the same and are in a determined state, the electronic device displays the ECG waveform on a display screen according to a display mode corresponding to the determined state.

[0013] The embodiments of the present application can reduce the error rate of determining whether the ECG waveform is displayed in a normal display mode, and improve the accuracy of displaying the ECG waveform in a normal display mode.

[0014] In a possible implementation of the first aspect, when the first wearing part information and the second wearing part information are the same and in a determined state, displaying an ECG waveform on a display screen according to a method corresponding to the determined state includes:

[0015] When the first wearing position information and the second wearing position information are the same as the preset wearing position information, the electronic device displays the ECG waveform on the display screen in a normal display manner.

[0016] In a possible implementation of the first aspect, when the first wearing part information and the second wearing part information are the same and in a determined state, displaying an ECG waveform on a display screen according to a method corresponding to the determined state includes:

[0017] When the first wearing position information and the second wearing position information are different from the preset wearing position information, the electronic device adjusts the ECG waveform so that the ECG waveform is displayed on the display screen in a normal display manner.

[0018] In a possible implementation of the first aspect above, the method further includes: when the first wearing part information and the second wearing part information are in a determined state but are not the same, performing at least one ECG wearing part identification to obtain third wearing part information, and the electronic device displays the ECG waveform on the display screen according to the display mode corresponding to the determined state represented by the third wearing part information.

[0019] In the embodiment of the present application, IMU wearing part recognition and ECG wearing part recognition are used simultaneously, and when the wearing information determined by the two is different, the number of ECG wearing part recognitions and the proportion of ECG detection confidence are increased, which to a certain extent improves the accuracy of the wearing part and ECG waveform displayed in a normal state.

[0020] In a possible implementation of the first aspect above, the method also includes: when the first wearing position information is in an uncertain state, performing ECG wearing position identification to obtain fourth wearing position information, and the electronic device displays the ECG waveform on the display screen according to the display method corresponding to the determined state represented by the fourth wearing position information.

[0021] In a possible implementation of the first aspect above, the method also includes: when the first wearing position information and the fourth wearing position information are the same and are in an uncertain state, performing at least one ECG wearing position identification to obtain the fifth wearing position information, and the electronic device displays the ECG waveform on the display screen according to the display method corresponding to the determined state represented by the fifth wearing position information.

[0022] In the embodiment of the present application, IMU wearing part recognition and ECG wearing part recognition are used simultaneously, and when the wearing information determined by the two is different, the number of ECG wearing part recognitions and the proportion of ECG detection confidence are increased, which to a certain extent improves the accuracy of the wearing part and ECG waveform displayed in a normal state.

[0023] In a possible implementation of the first aspect, the electronic device determines the first wearing position information according to the wearing state data, including:

[0024] A first wearing part position reliability is obtained according to the wearing state data, and first wearing location information is determined at least according to the first wearing part position reliability.

[0025] In a possible implementation of the first aspect, obtaining the first wearing part position reliability according to the wearing state data, and determining the first wearing part information at least according to the first wearing part position reliability, includes:

[0026] Obtaining a plurality of first wearing part position reliabilities according to the wearing state data;

[0027] Processing the plurality of first wearing part position reliabilities according to the first iterative formula to obtain a first average wearing part position reliability;

[0028] The first wearing part information is determined according to the first average wearing part position reliability.

[0029] In a possible implementation of the first aspect, the wearing part data includes an acceleration value and an attitude angle detected by an IMU, and obtaining the first wearing part position reliability according to the wearing state data includes:

[0030] The position reliability of the first wearing part is obtained according to the acceleration value and attitude angle detected by the IMU.

[0031] In a possible implementation of the first aspect, obtaining the position reliability of the first wearing part according to the acceleration value and the attitude angle detected by the IMU includes:

[0032] The currently acquired standard deviation and mean of the acceleration of the accelerometer on the X, Y, and Z axes, and the standard deviation and mean of the attitude angle of the gyroscope on the X, Y, and Z axes are input into the trained IMU wearing part identification model. The output result of the trained IMU wearing part identification model is the first wearing part position reliability.

[0033] In a possible implementation of the first aspect, obtaining the second wearing position information through ECG wearing position identification includes:

[0034] The second wearing part position reliability is obtained through ECG wearing part identification, and the second wearing position information is determined at least based on the second wearing part position reliability.

[0035] In a possible implementation of the first aspect, obtaining the second wearing part position reliability through ECG wearing part identification, and determining the second wearing position information at least based on the second wearing part position reliability, includes:

[0036] Obtaining a plurality of first wearing part position reliabilities according to the wearing state data;

[0037] Processing the plurality of first wearing part position reliabilities according to the first iterative formula to obtain a first average wearing part position reliability;

[0038] determining first wearing part information according to the first average wearing part position reliability;

[0039] Obtaining a plurality of second wearing part position reliabilities according to ECG wearing part identification;

[0040] Obtaining a second average wearing portion position reliability according to the first average wearing portion position reliability, a plurality of second wearing portion position reliability and a second iterative formula;

[0041] The second wearing part information is obtained according to the second average wearing part position reliability.

[0042] In a possible implementation of the first aspect, obtaining the second wearing part position reliability through ECG wearing part identification includes:

[0043] The reliability of the position of the second wearing part is determined according to the waveform feature information of the ECG waveform.

[0044] In a possible implementation of the first aspect, ECG waveform feature information is input into a trained ECG wearing part recognition model, and an output result of the trained ECG wearing part recognition model is the second wearing part position reliability.

[0045] In a possible implementation of the first aspect above, the first iterative formula is: CI1_average=a1*CI1_average+b1*CI_imui, wherein CI1_average represents the first average wearing part position reliability, CI_imui represents the first wearing part position reliability, a1 and b1 are natural numbers, the sum of a1 and b1 is 1, and a is greater than b.

[0046] In a possible implementation of the first aspect above, the second iterative formula is: CI2_average=a2*CI1_average+b2*CI_ecgi, wherein CI2_average represents the second average wearing part position reliability, CI_ecgi represents the second wearing part position reliability, a2 and b2 are natural numbers, the sum of a2 and b2 is 1, and a2 is less than b2.

[0047] In a possible implementation of the first aspect above, the waveform feature information of the ECG waveform includes:

[0048] QRS wave area, ratio of QR width to RS width, QR height, RS height, P wave amplitude, P wave area (both positive and negative), T wave width and T wave area.

[0049] In a possible implementation of the first aspect, performing ECG wearing position identification at least once to obtain third wearing position information includes:

[0050] Iteratively process the second wearing part position reliability and the third wearing part position reliability to obtain a third average wearing part position reliability; wherein the second wearing part position reliability is obtained based on the previous ECG wearing part identification, and the second wearing part position reliability corresponds to the second wearing part information;

[0051] The third wearing part information is determined according to the third average wearing part position reliability.

[0052] In a possible implementation of the first aspect above, the determined state is that the wearing state between the electronic device and the user's wrist is a right-hand wearing state or a left-hand wearing state.

[0053] In a second aspect, the present application provides a readable medium on which instructions are stored, and when the instructions are executed on an electronic device, the machine executes the ECG waveform display method described in the first aspect.

[0054] In a third aspect, the present application provides an electronic device, including:

[0055] a memory for storing instructions to be executed by one or more processors of the electronic device, and

[0056] The processor is one of the processors of the electronic device, and is used to execute the ECG waveform display method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1A According to some embodiments of the present application, an application scenario diagram of an ECG waveform display method is shown.

[0058] Figure 1B According to some embodiments of the present application, an application scenario diagram of an ECG waveform display method is shown.

[0059] Figure 1C According to some embodiments of the present application, an application scenario diagram of an ECG waveform display method is shown.

[0060] Figure 2 According to some embodiments of the present application, a structural block diagram of a smart watch is shown.

[0061] Figure 3 According to some embodiments of the present application, a flow chart of an ECG waveform display method is shown.

[0062] Figure 4 According to some embodiments of the present application, a schematic diagram of a time region of a collection period with a preset interval of 200 milliseconds and a step length of 150 milliseconds is shown.

[0063] Figure 5 According to some embodiments of the present application, a waveform diagram of the difference and standard value of the attitude angle and the difference and standard value of the acceleration changing with time is shown.

[0064] Figure 6 According to some embodiments of the present application, an example of an ECG wearing part identification prompt information display interface diagram is shown.

[0065] Figure 7 According to some embodiments of the present application, a schematic diagram of an ECG waveform is shown.

[0066] Figure 8 According to some embodiments of the present application, an example of an ECG waveform display interface diagram in an abnormal display mode is shown.

[0067] Fig. 9 According to some embodiments of the present application, an example of an ECG waveform display interface diagram in a normal display mode is shown.

[0068] Fig.10 According to some embodiments of the present application, a block diagram of a system-on-chip (SoC) is shown. DETAILED DESCRIPTION

[0069] Illustrative embodiments of the present application include, but are not limited to, ECG waveform display methods and media and electronic devices thereof.

[0070] The embodiments of the present application will be described in further detail below in conjunction with the accompanying drawings.

[0071] Figure 1A , Figure 1B and Figure 1C According to some embodiments of the present application, an application scenario diagram of an ECG waveform display method is shown. Figure 1A , Figure 1B and Figure 1C In the embodiment shown, the wearable device 100 can execute the ECG waveform display method provided by the present application. The wearable device 100 has an ECG detection module, multiple electrodes, and an inertial measurement unit (IMU). For example, the wearable device 100 includes two electrodes, which are respectively referred to as electrode A and electrode B. Figure 1B As shown, the A electrode 200 is arranged on the side of the housing of the wearable device 100, and the B electrode (not shown in the figure) is arranged on the lower surface of the wearable device 100. In some embodiments, when a user wears the wearable device 100 with a built-in ECG detection module to perform an electrocardiogram function test, for example, the user wears the wearable device 100 on his left wrist. At this time, the user's left wrist contacts the B electrode on the lower surface of the wearable device 100, and the user acts on the icon of the ECG waveform detection APP (Application) for performing an electrocardiogram test. For example, the user clicks the ECG waveform detection APP with a finger, such as Figure 1AAs shown in FIG. 1 , or when the user sends a command to open the ECG APP to the wearable device 100 by voice, the wearable device 100 detects the click operation for opening the ECG APP or receives the command to open the ECG APP, and starts the ECG detection function. The user can touch the A electrode 200 on the side of the wearable device 100 with his right finger, as shown in FIG. Figure 1B As shown, the A electrode 200 and the B electrode form an electrode pair, which can collect detailed information about the user's ventricular depolarization waveform passing through the heart tissue. The ECG detection module performs analog-to-digital conversion, filtering, and other processing on the electrical signals collected by the A electrode 200 and the B electrode to generate a single-lead ECG signal of the user. The wearable device 100 displays the user's ECG waveform generated by the ECG detection module on the display screen. Figure 1B As shown, because the smart watch 100 is set to be worn on the right hand, the ECG waveform is displayed in a normal display mode, for example, the peak of the ECG waveform is toward the left hand side, but when the smart watch 100 is worn on the left wrist of the user, the peak of the ECG waveform is toward the right hand side, so it looks abnormal, and the ECG waveform is displayed on the display screen in an abnormal display mode. In the embodiment of the present application, the wearable device 100 determines whether the user wears it on the left hand or the right hand based on the built-in IMU, and further determines whether the user wears it on the left hand or the right hand based on the ECG waveform generated by the ECG detection module, and then displays the ECG waveform on the display screen in a normal display mode according to the judgment result, as shown in FIG. Figure 1C As shown, for the convenience of users.

[0072] In this way, compared with the related art of judging the left and right hands only based on the IMU, or judging the left and right hands only based on the collected ECG waveform, the problem of high error rate caused by judging the left and right hands only based on the IMU can be avoided, and the problem of taking too long to judge the left and right hands only based on the ECG waveform can also be avoided. While shortening the judgment time, the accuracy of left and right hand recognition and ECG waveform display in a normal state is improved.

[0073] In some embodiments, the wearable device 100 can also analyze the user's electrocardiogram based on the ECG waveform generated by the ECG detection module, and display the analysis results in the form of text on its display screen, or play them in the form of voice, so that the user can understand the health of his heart more intuitively.

[0074] In the embodiment shown in FIG. 1 , the wearable device 100 can independently collect ECG data, determine the left and right hands, and display the final ECG waveform or generate an electrocardiogram report based on the determination results of the left and right hands.

[0075] Understandably, Figure 1A , Figure 1B and Figure 1C Although a smart watch 100 is shown, the electronic device suitable for the ECG waveform display method of the present application may be other wrist-worn devices, such as a smart bracelet or other dedicated wrist-worn devices with an electrocardiogram measurement function.

[0076] The processing process described in the present application, such as the process of calculating and judging based on data, can be performed on a smart bracelet, a smart phone, or other wrist-wearable devices, or can be performed on a mobile phone, a tablet computer, a personal digital assistant (PDA), a laptop computer, or other devices that are wirelessly or wired connected to the smart bracelet, smart phone, or other wrist-wearable devices.

[0077] Taking the wearable device 100 as a smart watch 100 as an example, the technical solution of the ECG waveform display method provided in the present application that can be executed by a user wearing the smart watch 100 is introduced in detail below.

[0078] Figure 2 According to some embodiments of the present application, a structural block diagram of a smart watch 100 is shown. Figure 2 As shown, the smart watch 100 includes a touch display screen 101, a processor 102, an ECG detection module 103, electrodes 104a, electrodes 104b, a capacitive sensor 105, an IMU 104, an infrared spectrum detection unit (Infrared Spectroscopy, IR) 106, an inertial measurement unit (Inertial measurement unit, IMU) 107, a memory 108, a communication module 109, etc.

[0079] The touch display screen 101, on the one hand, can be used as a touch panel to collect the user's touch operation on it and drive the corresponding connection device according to a pre-set program. For example, collect the user's touch operation of clicking the ECG APP icon of the smart watch 100 by finger. On the other hand, the touch display screen 101 can also be used to display the information input by the user or the prompt information provided to the user and various menus on the smart watch 100. For example, display the user's ECG waveform detected by the smart watch 100, the user's electrocardiogram report, etc.

[0080] The processor 102 includes multiple processing units and can run the software code of the ECG waveform display method provided in some embodiments of the present application. For example, the wearing position information is determined through IMU wearing position identification and ECG wearing position identification, so as to judge whether the ECG waveform is in a normal display mode. If the ECG waveform is not in a normal display mode, the ECG waveform is adjusted to an ECG waveform in a normal display mode, the user's electrocardiogram report, etc.

[0081] ECG detection module 103 is used for processing the electrical signal of the human body detected by electrode 104a and electrode 104b into ECG waveform. For example, ECG detection module 103 may include one or more filters inside, or ECG detection module 103 may be connected to one or more filters. One or more filters may be configured to filter the human body electrical signal detected by electrode 104a and electrode 104b. For example, ECG detection module 103 may configure the frequency domain bandwidth of one or more filters. If the frequency bandwidth of the filter is 0.5-40Hz, the filter may filter its input signal (such as the electrical signal detected by electrode 104a and electrode 104b) to obtain the electrical signal within the range of 0.5-40Hz, and the electrical signal of other frequencies may be filtered out. In some embodiments, the function of processing the electrical signal detected by electrode 104a and electrode 104b into ECG waveform may be performed by other components, assemblies or circuits, and the other components, assemblies or circuits may be different components independent of processor 103. Other parts, components or circuits may be constructed from separate devices (such as semiconductor devices). For example, other parts, components or circuits may be integrated circuits (ICs), microcircuits, chips, microchips, etc. with integrated ECG detection functions. This application does not limit this.

[0082] The capacitance sensor 105 can be used to detect the capacitance between the human body and the smart watch 100, and the capacitance can reflect whether the human body and the smart watch 100 are in good contact. When the capacitance sensor 105 is set on the electrode 104a and / or the electrode 104b, the capacitance sensor 105 can detect the capacitance between the human body and the electrode 104a and / or the electrode 104b. When the capacitance detected by the capacitance sensor 105 is too large or too small, it means that the human body has poor contact with the electrode 104a and / or the electrode 104b; when the capacitance detected by the capacitance sensor 105 is moderate, it means that the human body has good contact with the electrode 104a and / or the electrode 104b. Since whether the contact between the human body and the electrode is good will affect the electrode detection electrical signal, and then affect the generation of the ECG waveform, when the smart watch 100 generates the ECG waveform, it can judge whether the user is wearing the smart watch 100 according to the capacitance detected by the capacitance sensor 106D.

[0083] The infrared spectrum detection unit 106 is used to detect the wearing status according to the different reflection values ​​of different materials.

[0084] The inertial measurement unit 107 is used to measure the three-axis attitude angle (or angular rate) and acceleration of the object. In some embodiments, the inertial measurement unit 107 includes three single-axis accelerometers and three single-axis gyroscopes. The accelerometer detects the acceleration signal of the object in the independent three-axis of the carrier coordinate system, and the gyroscope detects the angular velocity signal of the carrier relative to the navigation coordinate system, measures the angular velocity and acceleration of the object in three-dimensional space, and calculates the attitude of the object. In some embodiments of the present application, the wearing position information of the smart watch 100 on the user's wrist can be detected.

[0085] The memory 108 is used to store software programs and data, and the processor 103 executes various functional applications and data processing of the smart watch 100 by running the software programs and data stored in the memory 108. For example, in some embodiments of the present application, the memory 108 can store the ECG waveform of the human body generated by the ECG detection module 103, the capacitance between the human body and the electrode 104a and / or the electrode 104b collected by the capacitive sensor 105, and the posture angle, acceleration and other data measured by the inertial measurement unit 107.

[0086] The communication module 109 can be used to enable the smart watch 100 to communicate with other electronic devices and connect to the network through other electronic devices. For example, in some embodiments of the present application, the smart watch 100 can establish a connection with the server through the communication module 109 and send the ECG data it generates to the server. The server analyzes the user's heart function based on the received ECG data, generates an electrocardiogram report, and sends the generated report to the smart watch 100 through the communication module 109.

[0087] Understandably, Figure 2 What is shown is merely an exemplary structure for realizing the functions of the smart watch 100 in the technical solution of the present application. Smart watches 100 having other structures and realizing similar functions are also applicable to the technical solution of the present application, and no limitation is made here.

[0088] The following is a detailed introduction to the technical solution of the present application, taking the example of a user using a smart watch 100 to perform ECG detection. Figure 3 According to some embodiments of the present application, a flow chart of a method for displaying an ECG waveform is shown; Figure 3 Specifically, it includes:

[0089] Assuming that the user wears the smart watch 100 on the left hand as the set wearing position, that is, the user wears the smart watch 100 on his left wrist, the smart watch 100 will display the ECG waveform on the display screen in a normal display manner, for example, the peak of the ECG waveform is toward the left hand side. However, if the user wears the smart watch 100 on his right wrist and does not execute the ECG waveform display method provided in the embodiment of the present application, the smart watch 100 will cause the ECG waveform to be displayed on the display screen in an abnormal display manner. The directions of the waveforms displayed on the display screen in the normal display manner and the waveforms displayed on the display screen in the abnormal display manner are opposite, for example, the peak of the ECG waveform is toward the right hand side. This is explained as an example.

[0090] Step 301: The smart watch 100 starts the ECG waveform detection application to collect ECG waveforms.

[0091] In some embodiments, the smart watch 100 has an ECG waveform detection function, and the application corresponding to the ECG waveform detection function in the smart watch 100 is started, and the smart watch 100 turns on the ECG waveform detection function. For example, the user clicks the ECG waveform detection APP with a finger, such as Figure 1A As shown, or when the user sends a command to open the ECG waveform detection APP to the smart watch 100 by voice, the smart watch 100 detects the click operation to open the ECG waveform detection APP or receives the command to open the ECG APP, when the user's hand touches the electrode on the side of the smart watch, the ECG waveform detection application is turned on, and the smart watch 100 starts ECG waveform detection and collects ECG waveforms.

[0092] Step 302: The smart watch 100 determines the wearing status between the smart watch 100 and the user's wrist.

[0093] After the smart watch 100 starts the ECG waveform detection application, it collects the ECG waveform and determines the wearing state and wearing position, so that the ECG waveform of the smart watch 100 is displayed on the display screen in a normal display mode.

[0094] In some embodiments, the wearing state detection function of the smart watch 100 is implemented according to the different impedance values ​​of the capacitor in the wearing state and the non-wearing state. For example, when the user wears the smart watch 100, the human body surface impedance value is detected to be in the range of 2 to 10 kΩ, and the smart watch 100 obtains that the smart watch 100 and the user's wrist are in the wearing state. When the user is not wearing the smart watch 100, the impedance value detected on the human body surface is generally greater than 1 MΩ, and the smart watch 100 obtains that the smart watch 100 and the user's wrist are in the non-wearing state.

[0095] In addition, in some other embodiments, the smart watch 100 reads the wearing status data between the smart watch 100 and the user's wrist; determines the wearing status between the smart watch 100 and the user's wrist. Specifically, it includes: the smart watch 100 reads the wearing status flag in the register of the smart watch 100 to obtain the wearing status between the smart watch 100 and the user's wrist. For example, before the smart watch 100 starts the ECG waveform detection application; the smart watch 100 determines the value of the wearing status flag flag_wear in the flag register according to the different impedance values ​​of the capacitor in the wearing state and the non-wearing state. When the user wears the smart watch 100, it is detected that the human body surface impedance value is in the range of 2 to 10kΩ, and the wearing status flag flag_wear in the flag register of the smart watch 100 is assigned to 1. When the smart watch 100 reads the wearing status flag in the register of the smart watch 100 as 1, the smart watch 100 obtains that the smart watch 100 and the user's wrist are in the wearing state. When the user is not wearing the smart watch 100, the detected impedance value of the human body surface is generally greater than 1MΩ, and the wearing status flag flag_wear in the flag register of the smart watch 100 is assigned a value of 0. When the smart watch 100 reads the wearing status flag in the register of the smart watch 100 as 0, the smart watch 100 obtains that the smart watch 100 and the user's wrist are in a not-worn state.

[0096] In addition, different from the above embodiments, in some other embodiments, the infrared spectrum detection device detects different infrared spectra in the wearing state and the non-wearing state by using the principle that the reflection values ​​of infrared rays on different substances are different. Therefore, the smart watch 100 can also realize the wearing state detection function of the smart watch 100 by using the infrared spectrum detection device.

[0097] Step 303: The smart watch 100 determines whether it is in the wearing state. If yes, go to step 304; if no, it indicates that the watch is not in the wearing state, in which case the IMU wearing position detection cannot be activated. Therefore, if the judgment result of step 303 is no, the current process ends.

[0098] Step 304: The smart watch 100 determines first wearing position information through IMU wearing position recognition.

[0099] In some embodiments, when the user wears the smart watch 100, the IMU obtains the data of the attitude angle of the gyroscope changing with time, and the data of the acceleration of the accelerometer changing with time. The smart watch 100 obtains the IMU wearing part detection confidence (as an example of the first wearing part position confidence) according to the attitude angle changing with time data and the acceleration changing with time data, and obtains the IMU wearing part detection information (as an example of the first wearing part information) according to the IMU wearing part detection confidence. The IMU wearing part detection confidence is specifically described below. It can be understood that the IMU wearing part detection confidence is used to determine the authenticity probability of left hand wearing, right hand wearing, and uncertain wearing. The IMU wearing part detection confidence can be left hand wearing confidence, right hand wearing confidence, and uncertain wearing part detection confidence. The sum of the left hand wearing confidence, the right hand wearing confidence, and the uncertain wearing part detection confidence is 1. For example, the left hand wearing confidence is 0.8, the right hand wearing confidence is 0.1, and the uncertain wearing part position confidence is 0.1. According to the highest confidence, the wearing information is determined to be worn on the left hand. The wearing position information can be worn on the left hand, worn on the right hand, or an uncertain wearing position. In some embodiments, the IMU wearing position detection confidence can also be in the form of a percentage, which is not limited in this application. It can be understood that the sum of the left hand wearing confidence, the right hand wearing confidence, and the uncertain wearing position confidence of the same detection can be 100%.

[0100] Specifically, determining the IMU wearing position detection information (an example of the first wearing position information) according to the acceleration value and the attitude angle detected by the IMU includes:

[0101] The smart watch 100 processes the attitude angle data that changes with time once every preset time interval, such as 200 milliseconds, to obtain the standard deviation and mean of the attitude angle in each preset time interval.

[0102] Acceleration can be the change of the accelerometer on the X, Y, and Z axes, and attitude angle can be the change of the gyroscope on Pitch (Y axis), Roll (X axis), and Yaw (Z axis). For example, Figure 4 According to some embodiments of the present application, a time region diagram of a collection period with a preset interval of 200 milliseconds and a step length of 150 milliseconds is shown. Figure 4 As shown, when the user wears the watch, the smart watch 100 processes the data of the gyroscope and the accelerometer once every preset time interval, for example, 200 milliseconds, wherein the continuous 200ms data has an overlapping area of ​​50ms.

[0103] In some embodiments, normalization is performed on the acceleration changes of the accelerometer on the X, Y, and Z axes, and the changes of the attitude angles such as Pitch (Y axis), Roll (X axis), and Yaw (Z axis) of the gyroscope every 200 ms, and then the corresponding parameters such as the standard deviation and mean of the acceleration and attitude angle are calculated. Figure 5 According to some embodiments of the present application, a waveform diagram of the difference and standard value of the attitude angle and the difference and standard value of the acceleration changing with time is shown, such as Figure 5 As shown, it includes: the first column: the change of the mean value of the X-axis attitude angle, the change of the standard deviation of the X-axis attitude angle, the change of the mean value of the X-axis acceleration, and the change of the standard deviation of the X-axis acceleration; the second column: the change of the mean value of the Y-axis attitude angle, the change of the standard deviation of the Y-axis attitude angle, the change of the mean value of the Y-axis acceleration, and the change of the standard deviation of the Y-axis acceleration; the third column: the change of the mean value of the Z-axis attitude angle, the change of the standard deviation of the Z-axis attitude angle, the change of the mean value of the Z-axis acceleration, and the change of the standard deviation of the Z-axis acceleration. The gyroscope has attitude angles on the three axes of X, Y, and Z, which are used to determine the direction of the moving object. The user's left and right hands move in different directions, so the attitude angle data of the left and right hands measured by the gyroscope are different. In the same time period, the change of the mean value of the attitude angle on the three axes of X, Y, and Z reflects the average value of the attitude angle in a certain time period. The standard deviation of the attitude angle reflects the distribution and discreteness of the attitude angle value in a certain time period. The average value and standard deviation of the attitude angle can reflect the wearing position.

[0104] Acceleration is a vector, and its direction is the direction of the change (amount) of the object's velocity, which is the same as the direction of the resultant external force. If a force is applied to the left or right, that is, different accelerations are given, the velocity will change (including the rate and direction), but the acceleration to the left and the acceleration to the right obviously cause different effects. The direction of force applied by the left and right hands during movement is often different, and the acceleration and the direction of acceleration are different. The wearing position can be determined based on the average value and standard deviation of the acceleration.

[0105] The distribution rules and judgment criteria of the left and right hands are obtained through algorithm model training. The following is an example of the IMU wearing position recognition model.

[0106] The standard deviation and mean of the acceleration of the accelerometer on the X, Y, and Z axes, the standard deviation and mean of the attitude angles of the gyroscope on the Y, X, and Z axes, and the left and right hand state labels are input into the IMU wearing part recognition model. By training the IMU wearing part recognition model, a trained IMU wearing part recognition model that meets the preset loss function is obtained.

[0107] The standard deviation and mean of the acceleration of the accelerometer on the X, Y, and Z axes, and the standard deviation and mean of the attitude angle of the gyroscope on Pitch (Y axis), Roll (X axis), and Yaw (Z axis) are input into the trained IMU wearing part recognition model, and the output result of the trained IMU wearing part recognition model is the IMU wearing part detection confidence and / or the IMU wearing part detection information. It can be understood that the IMU wearing part detection confidence can be the IMU wearing part detection confidence for the left hand, the IMU wearing part detection confidence for the right hand, and the uncertain wearing part detection confidence. The IMU wearing part detection information can be for left hand wearing, right hand wearing, and uncertain wearing part. For example, the IMU left hand wearing detection confidence is 0.8, the IMU right hand wearing detection confidence is 0.2, and the uncertain wearing part detection confidence is 0.4. The IMU wearing part detection confidence can be a decimal or a percentage, but is not limited to this.

[0108] The wearing position data may include a left-hand wearing flag hand_flag_imu, and the value of the left-hand wearing flag hand_flag_imu is determined according to the left-hand wearing state. The left-hand wearing flag hand_flag_imu may have a value of 0, 1, or 2. Among them, 0 indicates that it is uncertain whether to wear it on the left hand or the right hand, 1 indicates that it is worn on the left hand, and 2 indicates that it is worn on the right hand. The smart watch 100 reads the value of the left-hand wearing flag hand_flag_imu to determine the wearing position information.

[0109] In some embodiments, multiple IMU wearing part detection confidences are obtained based on the acceleration values ​​and attitude angles detected by the IMU; the multiple IMU wearing part detection confidences are processed according to the first iterative formula to obtain the IMU average wearing part position confidence (as an example of the first average wearing part position confidence); and the IMU wearing part detection information is determined based on the IMU average wearing part position confidence.

[0110] It can be understood that the first iteration formula can be:

[0111] CI1_average=a1*CI1_average+b1*CI_imui (Formula 1)

[0112] Among them, CI1_average represents the average IMU wearing position confidence, CI_imui represents the IMU wearing position detection confidence, that is, the single confidence CI_imui, a1 and b1 are natural numbers, the sum of a1 and b1 is 1, and a1 is greater than b1, the symbol "*" represents multiplication, and the value range of CI_average is [0,1]. For example, a1 is 0.6 and b2 is 0.4.

[0113] In some embodiments, determining the IMU wearing position detection information according to the IMU wearing position detection confidence measured once specifically includes:

[0114] When the IMU wearing position detection confidence is greater than the first threshold (for example, 0.7), it is judged as worn on the left hand; when the IMU wearing position detection confidence is less than the second threshold (for example, 0.3), it is judged as worn on the right hand; when the IMU wearing position detection confidence is in the range of the first threshold and the second threshold (for example, 0.3 to 0.7), it is judged as an uncertain wearing position; wherein the first threshold is greater than the second threshold.

[0115] For example, CI_imu represents the confidence of IMU wearing position detection, hand_flag is the wearing position flag, when CI_imu value is greater than 0.7, it is judged to be worn on the left hand, and hand_flag is assigned a value of 1; when CI_imu value is less than 0.3, it is judged to be worn on the right hand, hand_flag = 2; when CI_imu value is in the interval [0.3, 0.7], it is judged to be uncertain wearing position, hand_flag = 0. The smart watch reads the wearing position flag to determine the IMU wearing position detection information.

[0116] In addition, in some embodiments, when the IMU average wearing part position reliability is greater than a third threshold value (for example, 0.7), it is determined to be worn on the left hand; when the IMU average wearing part position reliability is less than a fourth threshold value (for example, 0.3), it is determined to be worn on the right hand; when the IMU average wearing part position reliability is between the third threshold and the fourth threshold value (for example, 0.3 to 0.7), it is determined to be an uncertain wearing position; wherein the third threshold value is greater than the fourth threshold value.

[0117] For example, CI1_average indicates the average reliability of the IMU wearing position, and hand_flag is the wearing position flag. When CI1_average is greater than 0.7, it is judged to be worn on the left hand, and hand_flag is assigned a value of 1; when CI1_average is less than 0.3, it is judged to be worn on the right hand, and hand_flag = 2; when CI1_average is in the interval [0.3, 0.7], it is judged to be an uncertain wearing position, and hand_flag = 0. The smart watch reads the wearing position flag to determine the IMU wearing position detection information.

[0118] Step 305: the smart watch 100 determines whether the first wearing position information is in a confirmed state, if so, it goes to step 306; if not, it goes to step 311;

[0119] The IMU wearing position detection information is used as an example of the first wearing position information. When the smart watch 100 determines that the IMU wearing position detection information is in a determined state, it needs to be further verified by the recognition result obtained by the ECG wearing position recognition to obtain a more accurate wearing position detection result, that is, to execute step 306. When the smart watch 100 determines that the IMU wearing position detection information is in an uncertain state, the wearing position recognition result is directly obtained by the recognition result obtained by the ECG wearing position recognition, that is, to execute step 311.

[0120] Step 306: Display ECG wearing position identification prompt information on the display screen of the smart watch 100 to instruct the user to select whether to perform ECG wearing position identification to ensure that the ECG waveform is displayed in a normal state.

[0121] Figure 6 According to some embodiments of the present application, an example of an ECG waveform detection prompt information display interface diagram is shown. Figure 6 As shown, the display screen of the smart watch 100 displays the prompt message "Further ECG wearing part identification is required to ensure that the ECG waveform is displayed normally!", and two options: "Countdown 3 seconds", "Cancel". "Countdown 3 seconds" means that the ECG wearing part identification will automatically start when the time is up. According to an embodiment of the present application, performing ECG waveform detection after IMU detection will improve the success rate of wrist recognition and provide the user with a normal electrocardiogram waveform display. Therefore, the "Countdown 3 seconds" method is used to automatically enter the ECG waveform detection unless the user forcibly terminates it. If the user clicks the "Cancel" icon, the smart watch 100 does not obtain the ECG wearing part identification request, and cancels the prompt message "Further ECG wearing part identification is required to ensure that the ECG waveform is displayed normally!", and the two options: "Countdown 3 seconds", "Cancel".

[0122] In addition, different from the above-mentioned embodiments, in some other embodiments, the user can also click the "ECG wearing part identification" icon to turn on ECG wearing part identification according to his own needs after clicking the "Cancel" icon for a period of time.

[0123] In addition, in some other embodiments, ECG wearing part identification prompt information is not displayed on the display screen of the smart watch 100 to instruct the user to choose whether to perform ECG wearing part identification. Instead, the smart watch 100 directly and automatically performs ECG wearing part identification after performing IMU wearing part identification.

[0124] In this way, in some embodiments, the left and right hand judgment results are obtained based on the wearing position information obtained by ECG wearing position recognition and the ECG wearing position detection confidence, or the left and right hand judgment results are obtained by comprehensively considering the wearing position information obtained by IMU wearing position recognition and the IMU wearing position detection confidence as well as the wearing position information obtained by ECG wearing position recognition and the ECG wearing position detection confidence.

[0125] Step 307: the smart watch 100 obtains the ECG wearing part identification request, and determines the second wearing part information through ECG wearing part identification.

[0126] In some embodiments, clicking the ECG wearing site identification icon turns on ECG wearing site identification.

[0127] In addition, in some other embodiments, Figure 6 As shown in the figure, "3 seconds countdown" means that ECG wearing position recognition will automatically start when the time is up.

[0128] In some embodiments, after the smart watch 100 obtains the ECG waveform detection request, the ECG wearing position detection confidence is obtained according to the waveform feature information of the ECG waveform; including:

[0129] Obtaining an ECG average wearing part position confidence (as an example of a second average wearing part position confidence) according to the IMU wearing part detection confidence and the ECG wearing part detection confidence;

[0130] The ECG wearing part information (an example of the second wearing position information) is determined based on the ECG average wearing part position reliability.

[0131] Specifically, in some embodiments, it includes:

[0132] Obtaining detection confidences of multiple ECG wearing locations according to waveform feature information of the ECG waveform;

[0133] Obtaining an ECG average wearing part detection confidence (as an example of the second average wearing part position confidence) according to an IMU average wearing part position confidence (as an example of the first average wearing part position confidence), a plurality of ECG wearing part detection confidences (as an example of the second wearing part position confidence), and a second iterative formula;

[0134] The ECG wearing position detection information is obtained according to the ECG average wearing position detection confidence.

[0135] The second iteration formula is:

[0136] CI2_average=a2*CI1_average+b2*CI_ecgi (Formula 2)

[0137] Among them, CI2_average represents the average wearing position reliability of ECG, CI1_average represents the average wearing position reliability of IMU, CI_ecgi represents the ECG wearing position detection confidence, a2 and b2 are natural numbers, the sum of a2 and b2 is 1, and a2 is less than b2. Considering that there may be a period of time between ECG wearing position identification and IMU wearing position identification, the weight coefficient in front of the confidence is determined according to the length of the interval time. For example, the longer the time from IMU wearing position identification detection, the larger b2. For example, a2 takes 0.4 and b2 takes 0.6. The value range of CI_ecgi is [0,1]. It can be understood that in some other embodiments, when the user is an arrhythmia patient and the ECG waveform is deformed, the IMU prediction ratio is increased, thereby improving accuracy and reducing the time taken for ECG acquisition. Specifically, it includes:

[0138] The smart watch 100 displays prompt information for the user to input physical condition on the display interface of the display screen;

[0139] If the arrhythmia information input by the user on the display interface of the smart watch 100 is obtained, the IMU prediction weight b2 is increased.

[0140] In some embodiments, when the ECG average wearing position detection confidence is greater than the fifth threshold, it is determined to be worn on the left hand; when the ECG average wearing position detection confidence is less than the sixth threshold, it is determined to be worn on the right hand; when the ECG average wearing position detection confidence is between the fifth threshold and the sixth threshold, it is determined to be an uncertain wearing position; wherein the fifth threshold is greater than the sixth threshold.

[0141] For example, the left and right demarcation thresholds are set to T1_ECG and T1_exg, and T1_ECG is greater than or equal to T1_exg. Among them, CI_ecgi takes the value of [T1_ECG, 1], [0, T1_exg), corresponding to the left hand and the right hand respectively, hand_flag_ecg corresponds to the values ​​1 and 2 respectively, CI_ecgi takes the value in the interval [T1_exg, T1_ECG], and the status of the left and right hands is uncertain. If T1_ECG takes the value of 0.5, T1_exg takes the value of 0.3, CI_ecgi takes the value in the interval [0.5, 1] ​​corresponding to the left hand, and hand_flag_ecg corresponds to 1; CI_ecgi takes the value in the interval [0, 0.3), corresponding to the right hand, hand_flag_ecg corresponds to 2, CI_ecgi takes the value in the interval [0.3, 0.5], and the status of the left and right hands is uncertain. In some embodiments, the smart watch 100 reads hand_flag_ecg to obtain ECG wearing position detection information.

[0142] In addition, in some other embodiments, different from the above-mentioned implementation mode, the ECG wearing part detection confidence is processed through the third iterative formula to obtain the ECG average wearing part position confidence (as an example of the second average wearing part position confidence), and the ECG wearing part detection information is obtained according to the ECG average wearing part position confidence.

[0143] The third iteration formula is:

[0144] CI2_average=a2*CI2_average+b2*CI_ecgi (Formula 3)

[0145] Among them, CI2_average represents the average ECG wearing part position reliability, CI_ecgi represents the ECG wearing part detection confidence, a2 and b2 are natural numbers, the sum of a2 and b2 is 1, and a2 is less than b2. Considering that the ECG wearing part recognition and the IMU wearing part recognition may be separated by a period of time, the weight coefficient in front of the confidence is determined according to the length of the interval time. For example, the longer the distance from the IMU wearing part recognition detection time, the larger b2. For example, a2 is 0.4 and b2 is 0.6. The value range of CI_ecgi is [0,1].

[0146] In addition, in some other embodiments, ECG wearing part detection information is obtained based on the ECG wearing part position reliability.

[0147] The following is an exemplary description of how to obtain the confidence of ECG wearing position detection. In some embodiments, when the user wears the smart watch 100, the left and right hands are identified based on the EGG waveform. The function of the ECG wearing position identification algorithm is to determine the position of the user wearing the smart wearable device by analyzing the ECG waveform morphology at the initial stage of user detection. Extract the ECG waveform (R wave, QRS wave group width, etc.) within t (for example, 1 to 2s) to achieve left and right hand judgment. Specifically, it includes:

[0148] Obtain an ECG waveform of a period (e.g., 1 second in length) after the user wears the smart watch 100;

[0149] Determine waveform characteristic information of an acquired ECG waveform;

[0150] The waveform feature information of the ECG waveform is input into the trained ECG wearing part recognition model, and the output result of the trained ECG wearing part recognition model is the ECG wearing part detection confidence. The ECG wearing part detection information is determined according to the ECG wearing part detection confidence. The ECG wearing part detection information can be worn on the left hand or on the right hand, and the ECG wearing part detection confidence can be the left hand wearing ECG confidence or the right hand wearing ECG confidence.

[0151] It can be understood that in ECG detection, the extracted ECG waveform feature information can be: QRS wave area, ratio of QR width to RS width, QR height, RS height, P wave amplitude, P wave area (including positive and negative), T wave width, and T wave area. Figure 7 According to some embodiments of the present application, a schematic diagram of an ECG waveform is shown, such as Figure 7 As shown, including: QRS wave area, ratio of QR width to RS width, QR height, RS height, P wave amplitude, P wave area (positive and negative), T wave width, T wave area. According to the principal component analysis, the signal is reconstructed as the principal component, and the first three principal component features with the largest change in the waveform feature information are selected. The selected principal component features are input into the trained ECG wearing part recognition model to realize the judgment of the left and right hands according to the ECG waveform, and the confidence CI_ecgi is obtained at the same time.

[0152] Step 308 : The smart watch 100 determines whether the first wearing part information is the same as the second wearing part information. If so, the process goes to step 309 ; if not, the process goes to step 310 .

[0153] The IMU wearing part detection information is used as an example of the first wearing part information; the ECG wearing part detection information is used as an example of the second wearing part information. The IMU wearing part detection information is the same as the ECG wearing part detection information, which means that the results of the IMU wearing part identification and the ECG wearing part identification are consistent, and it can be determined with certainty that the IMU wearing part detection information and the ECG wearing part detection information are the left and right wearing state or the right hand wearing state in the determined state. Therefore, the smart watch 100 can continue to execute step 309. The IMU wearing part detection information and the ECG wearing part detection information are different, which means that the results of the IMU wearing part identification and the ECG wearing part identification are inconsistent, and it is impossible to determine with certainty whether the IMU wearing part detection information and the ECG wearing part detection information are the left and right wearing state or the right hand wearing state in the determined state. Because the ECG wearing part identification is more accurate, it is necessary to further perform the ECG wearing part identification to obtain the wearing part identification result, and the smart watch 100 can continue to execute step 310.

[0154] Step 309: The smart watch 100 displays the ECG waveform on the display screen according to the display mode corresponding to the determined state.

[0155] In the embodiment of the present application, the left hand is the preset wearing position information determined by the hardware structure such as the A electrode and the B electrode on the smartphone 100 during the setting. It can be understood that in other embodiments, the preset wearing position information can also be worn on the right hand. If the wearing position information is the preset wearing position information, the ECG waveform is displayed on the display screen in a normal display mode. It can be understood that in other embodiments, the preset wearing position information can also be worn on the left hand. The IMU wearing position detection information and the ECG wearing position detection information are the left hand wearing information or the right hand wearing information, which is a confirmed state.

[0156] In some embodiments, when the IMU wearing position detection information (as an example of the first wearing position information) and the ECG wearing position detection information (as an example of the second wearing position information) are the same as the preset wearing position information, the smart watch 100 displays the ECG waveform on the display screen in a normal display manner.

[0157] For example, the preset wearing position information is worn on the left hand. If the IMU wearing position detection information and the ECG wearing position detection information are the same as the left hand wearing information, the smart watch 100 displays the ECG waveform on the display screen according to the normal display method corresponding to left hand wearing.

[0158] It can be understood that in some other embodiments, when the IMU wearing position detection information and the ECG wearing position detection information are different from the preset wearing position information, the smart watch 100 adjusts the abnormal display mode to the normal display mode to display the ECG waveform on the display screen.

[0159] For example, the preset wearing position information is left hand wearing. If the IMU wearing position detection information and the ECG wearing position detection information are different from the left hand wearing information, the smart watch 100 adjusts the abnormal display mode to the normal display mode to display the ECG waveform on the display screen.

[0160] Figure 8 According to some embodiments of the present application, an example of a display interface diagram of an ECG waveform in an abnormal display mode is shown. Because when a user wears the smart watch 100 on his left wrist, the smart watch 100 will display the ECG waveform on the display screen in a normal display mode, and when the user wears the smart watch 100 on his right wrist, the smart watch 100 will display the ECG waveform in the negative direction of the coordinate axis, that is, towards the right hand side. Figure 8 As shown, the display state of the ECG waveform on the display screen of the smart watch 100 is an abnormal display mode.

[0161] Fig. 9 According to some embodiments of the present application, an example of a display interface diagram of a normal display mode of an ECG waveform is shown. Fig. 9As shown, the ECG waveform is displayed on the display screen of the smart watch 100 in a normal display mode. Fig. 9 The waveform data in is multiplied by negative 1, the waveform is inverted, and the ECG waveform is displayed in the positive direction of the coordinate axis, that is, toward the left hand side.

[0162] This application determines the wearing position information through IMU wearing position identification and ECG wearing position identification, so as to judge whether the ECG waveform is in a normal display mode. If the ECG waveform is not in a normal display mode, the ECG waveform is adjusted to a normal display mode. In this way, the misjudgment rate of wearing position identification through IMU can be reduced, and the problem of too long time consumption caused by wearing position identification through ECG can be reduced. While shortening the identification time, the accuracy of wearing position identification and ECG waveform display in a normal state is improved.

[0163] Step 310: the smart watch 100 performs ECG wearing position identification at least once more to obtain third wearing position information, and the smart watch 100 displays the ECG waveform on the display screen according to the display mode corresponding to the determined state represented by the third wearing position information.

[0164] In some embodiments, if the wearing position information obtained by the smart watch 100 according to the IMU wearing position recognition is different from the wearing position information obtained according to the ECG wearing position recognition, the ECG wearing position recognition is continued to be performed at least once to obtain ECG wearing position detection information (as an example of the third wearing position information) and ECG wearing position detection confidence. The method of determining the wearing state according to the result of the further performed EGC wearing position recognition can have the following exemplary implementations.

[0165] In one embodiment, ECG wearing part identification is performed at least once again to obtain the third wearing part information, that is, the number of ECG wearing part identification times is increased, and the ECG average wearing part detection confidence (as a third average wearing part position confidence) is regained based on multiple ECG wearing part detection confidences (as an instance of the second wearing part position confidence) and ECG average wearing part detection confidence (as an instance of the second average wearing part position confidence) obtained according to the increased number of ECG wearing part identification times; and the ECG wearing part detection information (as an instance of the third wearing part information) is determined based on the regained ECG average wearing part detection confidence.

[0166] The ECG average wearing position detection confidence calculation formula is obtained again:

[0167] CI3average=a3*CI2_average+b3*CIN_CI_ecgi (Formula 4)

[0168] Among them, CI3_average represents the regained ECG average wearing position detection confidence, CI2_average represents the ECG average wearing position detection confidence, CIN_CI_ecgi represents the ECG wearing position detection confidence corresponding to the increased number of ECG waveform detection times, a3 and b3 are natural numbers, the sum of a3 and b3 is 1, and a3 is less than b3.

[0169] Set the left and right boundary thresholds to T1_CI3 and T1_ci3, T1_ECG is greater than or equal to T1_CI3. Among them, CI3_average takes values ​​of [T1_CI3, 1], [0, T1_ci3), corresponding to the left hand (hand_flag_ecg = 1) and the right hand (hand_flag_ecg = 2), respectively. CI3_average takes values ​​in the interval [T1_ci3, T1_CI3], and the status of the left and right hands is uncertain.

[0170] For example, when the hand_flag_ecg value and the hand_flag value are both 1 or 2, the corresponding ECG waveform is displayed. For example, when hand_flag = 1 (hand_flag_ecg = hand_flag = 1), the ECG waveform is displayed forward; when hand_flag = 2 (hand_flag_ecg = hand_flag = 2), the ECG waveform is displayed reversely, that is, the ECG waveform data is multiplied by -1.

[0171] It can be understood that in some embodiments, when the user wears the watch to measure immediately, the number of judgments based on the IMU is small and cannot be predicted correctly, so the proportion of waveform feature prediction is increased, and the accuracy of judgment based on the waveform is higher than the accuracy of identification based on the IMU wearing position, thereby improving the accuracy of the left and right hand wearing positions and the normal display of ECG.

[0172] In this way, IMU wearing part recognition and ECG wearing part recognition are used at the same time, and when the wearing information determined by the two is different, the number of ECG wearing part recognitions and the proportion of ECG detection confidence are increased, which to a certain extent improves the accuracy of the wearing part and ECG waveform displayed in a normal state.

[0173] In addition, in some other embodiments, at least one third wearing part position reliability can be directly obtained by performing ECG wearing part identification at least once more, and the third wearing position information can be determined according to the at least one third wearing part position reliability.

[0174] For example, ECG wearing part identification is performed again to obtain an ECG wearing part detection confidence (as an example of the third wearing part position confidence), and the third wearing position information is determined based on the ECG wearing part detection confidence.

[0175] For example, the ECG wearing part detection confidence is processed through the fifth iterative formula to obtain the ECG average wearing part position confidence (as an example of the third average wearing part position confidence), and the ECG wearing part detection information is obtained according to the ECG average wearing part position confidence.

[0176] The ECG average wearing position detection confidence calculation formula is obtained again (as an example of the fifth iteration formula):

[0177] CI3_average=a3*CI3_average+b3*CIN_CI_ecgi (Formula 5)

[0178] Among them, CI3_average represents the regained ECG average wearing position detection confidence, CIN_CI_ecgi represents the ECG wearing position detection confidence corresponding to the increased number of ECG waveform detection times, a3 and b3 are natural numbers, the sum of a3 and b3 is 1, and a3 is less than b3.

[0179] Next, refer to Figure 3 , then return to the judgment of step S05. If the judgment result of this step is no, enter the processing of step S311.

[0180] Step 311: The smart watch 100 performs ECG wearing position recognition to obtain fourth wearing position information.

[0181] In some embodiments, at least one ECG wearing part detection confidence (as an example of a fourth wearing part position confidence) can be directly obtained by performing ECG wearing part identification at least once more, and ECG wearing part detection information (as an example of a fourth wearing position information) can be determined based on at least one ECG wearing part detection confidence.

[0182] For example, ECG wearing part identification is performed again to obtain an ECG wearing part detection confidence (as an example of the fourth wearing part position confidence), and ECG wearing part detection information is determined based on the ECG wearing part detection confidence.

[0183] In addition, in some other embodiments, the ECG wearing part detection confidence is processed through the sixth iterative formula to obtain the ECG average wearing part position confidence (as an example of the fourth average wearing part position confidence), and the ECG wearing part detection information (fourth wearing part information) is obtained based on the ECG average wearing part position confidence.

[0184] For example, the ECG average wearing position detection confidence calculation formula is retrieved (as an example of the sixth iterative formula):

[0185] CI6_average=a6*CI6_average+b6*CIN_CI_ecgi (Formula 6)

[0186] Among them, CI6_average represents the regained ECG average wearing position detection confidence, CIN_CI_ecgi represents the ECG wearing position detection confidence corresponding to the increased number of ECG waveform detection times, a6 and b6 are natural numbers, the sum of a6 and b6 is 1, and a6 is less than b6.

[0187] Step 312: The smart watch 100 determines whether the fourth wearing part information is in a confirmed state. If so, the process goes to step 313; if not, the process goes to step 314.

[0188] Step 313: The smart watch 100 displays the ECG waveform on the display screen according to the display mode corresponding to the determined state.

[0189] The embodiments of step 313 and step 309 are based on the same concept and will not be described in detail here.

[0190] Step 314: the smart watch 100 performs ECG wearing position identification at least once more to obtain fifth wearing position information, and the smart watch 100 displays the ECG waveform on the display screen according to the display mode corresponding to the determined state represented by the fifth wearing position information.

[0191] In some embodiments, at least one ECG wearing part detection confidence (as an example of the fifth wearing part position confidence) can be directly obtained by performing ECG wearing part identification at least once more, and the fifth wearing position information can be determined based on the at least one ECG wearing part detection confidence.

[0192] For example, ECG wearing part recognition is performed again to obtain an ECG wearing part detection confidence (as an example of the fifth wearing part position confidence), and the fifth wearing position information is determined based on the ECG wearing part detection confidence.

[0193] In addition, in some other embodiments, the ECG wearing part detection confidence is processed through the seventh iterative formula to obtain the ECG average wearing part position confidence (as an example of the fifth average wearing part position confidence), and the ECG wearing part detection information (fifth wearing part information) is obtained based on the ECG average wearing part position confidence.

[0194] For example, the calculation formula for retrieving the average ECG wearing position detection confidence is:

[0195] CI7_average=a7*CI7_average+b7*CIN_CI_ecgi (Formula 7)

[0196] Among them, CI7_average represents the regained ECG average wearing position detection confidence, CIN_CI_ecgi represents the ECG wearing position detection confidence corresponding to the increased number of ECG waveform detection times, a7 and b7 are natural numbers, the sum of a7 and b7 is 1, and a7 is less than b7.

[0197] The process of determining the fifth wearing position information according to the ECG wearing position detection confidence is similar to the concept of the process of obtaining the wearing position information according to Formula 1, Formula 2 or Formula 3, and will not be repeated here.

[0198] An embodiment of the present application further provides a readable medium on which instructions are stored, and when the instructions are executed on a machine, the machine executes the above-mentioned ECG waveform display method.

[0199] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0200] An embodiment of the present application further provides an electronic device, the electronic device comprising:

[0201] A memory for storing instructions executed by one or more processors of an electronic device, and a processor, which is one of the processors of the electronic device, for executing the above-mentioned firewall rule configuration method. The electronic device has the function of implementing the above-mentioned ECG waveform display method. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions.

[0202] According to an embodiment of the present application, Fig.10 A block diagram of a SoC (System on Chip) 1000 is shown. Fig.10 In the FIG, similar components have the same reference numerals. In addition, the dashed boxes are optional features of more advanced SoCs. Fig.10 In the embodiment, SoC 1000 includes: an interconnect unit 1050, which is coupled to an application processor 1010; a system agent unit 1070; a bus controller unit 1080; an integrated memory controller unit 1040; a group or one or more coprocessors 1020, which may include integrated graphics logic, an image processor, an audio processor, and a video processor; a static random access memory (SRAM) unit 1030; and a direct memory access (DMA) unit 1060.

[0203] In one embodiment, coprocessor 1020 includes a special purpose processor such as, for example, a network or communication processor, a compression engine, a GPGPU, a high throughput MIC processor, or an embedded processor, among others.

[0204] The embodiments disclosed in the present application may be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present application may be implemented as a computer program or program code executed on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0205] Program code can be applied to input instructions to perform the functions of the ECG waveform display method described in this application and generate output information. The output information can be applied to one or more output devices in a known manner.

[0206] For purposes of this application, a processing system includes any system having a processor, such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0207] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0208] Although the present application has been illustrated and described with reference to certain preferred embodiments thereof, it will be apparent to those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application.

Claims

1. A method for displaying an ECG waveform, characterized in that: include: The electronic device starts an ECG waveform detection application to collect ECG waveforms; The electronic device reads the wearing position data between the electronic device and the user's wrist; The wearing position data is obtained by IMU wearing position recognition; The electronic device determines first wearing part information according to the wearing part data, the first wearing part information including a determined state and an uncertain state; the determined state is a first determined state or a second determined state, the first determined state is that the wearing state between the electronic device and the user's wrist is a right-hand wearing state or a left-hand wearing state, and the second determined state is that the wearing state between the electronic device and the user's wrist is a left-hand wearing state or a right-hand wearing state; The electronic device obtains second wearing position information between the electronic device and the user's wrist through ECG wearing position recognition; When the first wearing part information and the second wearing part information are the same and in a determined state, the electronic device displays an ECG waveform on a display screen according to a display mode corresponding to the determined state; When the first wearing part information and the second wearing part information are in a determined state but are not the same, ECG wearing part identification is performed at least once to obtain third wearing part information, and the electronic device displays the ECG waveform on the display screen according to the display mode corresponding to the determined state represented by the third wearing part information.

2. The method according to claim 1, characterized in that When the first wearing part information and the second wearing part information are the same and in a determined state, displaying an ECG waveform on a display screen according to a method corresponding to the determined state includes: When the first wearing position information and the second wearing position information are the same as the preset wearing position information, the electronic device displays the ECG waveform on the display screen in a normal display manner.

3. The method according to claim 1, characterized in that When the first wearing part information and the second wearing part information are the same and in a determined state, displaying an ECG waveform on a display screen according to a method corresponding to the determined state includes: When the first wearing position information and the second wearing position information are different from the preset wearing position information, the electronic device adjusts the ECG waveform so that the ECG waveform is displayed on the display screen in a normal display manner.

4. The method according to claim 1, characterized in that Also includes: When the first wearing part information is in an uncertain state, ECG wearing part identification is performed to obtain fourth wearing part information, and the electronic device displays the ECG waveform on the display screen according to a display mode corresponding to the determined state represented by the fourth wearing part information.

5. The method according to claim 4, characterized in that Also includes: When the first wearing part information and the fourth wearing part information are the same and are in an uncertain state, ECG wearing part identification is performed at least once to obtain the fifth wearing part information, and the electronic device displays the ECG waveform on the display screen according to the display method corresponding to the determined state represented by the fifth wearing part information.

6. The method according to claim 1, characterized in that The electronic device determines first wearing position information according to the wearing position data, including: A first wearing part position reliability is obtained according to the wearing part data, and first wearing part information is determined at least according to the first wearing part position reliability.

7. The method according to claim 6, characterized in that The step of obtaining a first wearing part position reliability according to the wearing part data, and determining first wearing part information at least according to the first wearing part position reliability, comprises: Obtaining a plurality of first wearing part position reliabilities according to the wearing part data; Processing the plurality of first wearing part position reliabilities according to the first iterative formula to obtain a first average wearing part position reliability; The first wearing part information is determined according to the first average wearing part position reliability.

8. The method according to claim 6, characterized in that The wearing part data includes acceleration value and attitude angle detected by IMU, and obtaining the first wearing part position reliability according to the wearing part data includes: The position reliability of the first wearing part is obtained according to the acceleration value and attitude angle detected by the IMU.

9. The method according to claim 8, characterized in that The obtaining of the first wearing part position reliability according to the acceleration value and the attitude angle detected by the IMU includes: The currently acquired standard deviation and mean of the acceleration of the accelerometer on the X, Y, and Z axes, and the standard deviation and mean of the attitude angle of the gyroscope on the X, Y, and Z axes are input into the trained IMU wearing part identification model. The output result of the trained IMU wearing part identification model is the first wearing part position reliability.

10. The method according to claim 1, characterized in that The obtaining of the second wearing position information through ECG wearing position identification includes: The second wearing part position reliability is obtained through ECG wearing part identification, and the second wearing part information is determined at least based on the second wearing part position reliability.

11. The method according to claim 10, characterized in that The obtaining of the second wearing part position reliability through ECG wearing part identification, and determining the second wearing part information at least based on the second wearing part position reliability, comprises: Obtaining a plurality of first wearing part position reliabilities according to the wearing part data; Processing the plurality of first wearing part position reliabilities according to the first iterative formula to obtain a first average wearing part position reliability; determining first wearing part information according to the first average wearing part position reliability; Obtaining a plurality of second wearing part position reliabilities according to ECG wearing part identification; Obtaining a second average wearing portion position reliability according to the first average wearing portion position reliability, a plurality of second wearing portion position reliability and a second iterative formula; The second wearing part information is obtained according to the second average wearing part position reliability.

12. The method according to any one of claims 10 or 11, characterized in that: The obtaining of the second wearing part position reliability through ECG wearing part identification includes: The reliability of the position of the second wearing part is determined according to the waveform feature information of the ECG waveform.

13. The method according to claim 12, characterized in that include: The waveform feature information of the ECG is input into a trained ECG wearing part recognition model, and the output result of the trained ECG wearing part recognition model is the second wearing part position reliability.

14. The method according to any one of claims 7 or 11, characterized in that: The first iterative formula is: CI1_average=a1*CI1_average+b1*CI_imui, wherein CI1_average represents the first average wearing part position reliability, CI_imui represents the first wearing part position reliability, a1 and b1 are natural numbers, the sum of a1 and b1 is 1, and a is greater than b.

15. The method according to claim 11, characterized in that The second iterative formula is: CI2_average=a2*CI1_average+b2*CI_ecgi, wherein CI2_average represents the second average wearing part position reliability, CI_ecgi represents the second wearing part position reliability, a2 and b2 are natural numbers, the sum of a2 and b2 is 1, and a2 is less than b2.

16. The method according to claim 12, characterized in that The waveform characteristic information of the ECG waveform includes: QRS wave area, ratio of QR width to RS width, QR height, RS height, P wave amplitude, P wave area (both positive and negative), T wave width and T wave area.

17. The method according to claim 1, characterized in that The performing at least one more ECG wearing position identification to obtain third wearing position information includes: Iteratively process the second wearing part position reliability and the third wearing part position reliability to obtain a third average wearing part position reliability; wherein the second wearing part position reliability is obtained based on the previous ECG wearing part identification, and the second wearing part position reliability corresponds to the second wearing part information; The third wearing part information is determined according to the third average wearing part position reliability.

18. A readable medium, characterized in that The readable medium stores instructions, which, when executed on an electronic device, enable the machine to execute the ECG waveform display method according to any one of claims 1 to 17.

19. An electronic device comprising: a memory for storing instructions to be executed by one or more processors of the electronic device, and The processor is one of the processors of the electronic device, and is used to execute the ECG waveform display method according to any one of claims 1 to 17.

Images