Body fat rate measurement method, wearable device, electronic device and medium

Abstract

The invention relates to a body fat rate measurement method, wearable equipment, electronic equipment and a medium, and the body fat rate measurement method comprises the steps: inputting a preset current to a target object based on an electrode, obtaining an impedance parameter of the target object based on the preset current, obtaining an electrocardiogram characteristic of the target object, and obtaining a body fat rate of the target object based on the impedance parameter and the electrocardiogram characteristic; and determining a target feature set, and determining the body fat rate of the target object based on the relationship between the target feature set and the body fat rate. The body fat rate of the target object can be jointly determined in combination with the impedance parameter of the target object and the electrocardiogram characteristics, the accuracy and stability of the measured body fat rate can be improved on the basis of the characteristic that the electrocardiogram characteristics are slightly influenced by external factors and internal factors of the target object, and therefore the more accurate body fat rate is obtained, and the user experience is improved. The user can conveniently manage the health, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of terminal technology, and in particular to a body fat percentage measurement method, a wearable device, an electronic device, and a medium. Background Art

[0002] At present, some wearable devices have the function of measuring the user's body fat, so that users can check their health and enhance the product competitiveness of wearable devices.

[0003] However, the body fat percentage measurement method set on wearable devices mostly measures body fat through a single bioimpedance analysis method. The measurement method is affected by factors such as temperature, the user's diet and exercise, and the measured body fat percentage has low accuracy. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a body fat percentage measurement method, a wearable device, an electronic device and a medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a body fat percentage measurement method is provided, which is applied to a wearable device, wherein the wearable device is provided with electrodes. The body fat percentage measurement method includes:

[0006] Based on the electrodes, inputting a preset current into the target object;

[0007] Based on the preset current, obtaining an impedance parameter of the target object;

[0008] Acquiring electrocardiogram characteristics of the target object;

[0009] determining a target feature set based on the impedance parameter and the electrocardiogram feature;

[0010] Based on the relationship between the target feature set and the body fat percentage, the body fat percentage of the target object is determined.

[0011] In some embodiments, the electrode includes an input electrode and an output electrode, and obtaining the impedance parameter of the target object based on the preset current includes:

[0012] obtaining a voltage between the input electrode and the output electrode;

[0013] An impedance parameter of the measured user is determined based on the voltage and the preset current.

[0014] In some embodiments, the preset current is alternating current, and the impedance parameters include an impedance modulus and a phase difference between the voltage and the preset current; wherein the impedance modulus is a ratio of the voltage to the preset current.

[0015] In some embodiments, obtaining the electrocardiogram characteristics of the target object includes:

[0016] Acquiring an electrocardiogram signal of the target object;

[0017] Extracting a preset wave signal of the electrocardiogram signal based on the electrocardiogram signal, wherein the preset wave signal includes a P wave, a Q wave, an R wave, an S wave, and a T wave;

[0018] Based on the preset wave signal, the electrocardiogram feature is determined, where the electrocardiogram feature includes a plurality of sub-features, each of which is related to the amplitude of the preset wave signal and / or the time of the preset wave signal.

[0019] In some embodiments, determining the body fat percentage of the target subject based on the relationship between the target feature set and the body fat percentage includes:

[0020] Inputting the target feature set into a pre-stored body fat percentage measurement model, wherein the features in the target feature set are arranged in a preset order;

[0021] An output value of the body fat percentage measurement model is determined as the body fat percentage of the target object.

[0022] In some embodiments, the body fat percentage measurement model is obtained by the following method:

[0023] Acquire a training set of sample objects; the training set includes multiple sample subsets, each of the sample subsets includes a sample impedance parameter and a sample electrocardiogram feature, wherein each of the sample objects is associated with one of the sample subsets;

[0024] Obtain a reference body fat percentage for each of the sample subjects, where the reference body fat percentage is the actual body fat percentage of the sample subject;

[0025] The preset target model is trained based on the training set and the reference body fat percentage to obtain the body fat percentage measurement model.

[0026] In some embodiments, the training of a preset target model based on the training set and the reference body fat percentage to obtain the body fat percentage measurement model includes:

[0027] In each training process, the sample subset associated with the sample object is input into the target model to obtain a predicted body fat percentage, wherein the sample object associated with the sample subset input in each training process is different;

[0028] Analyzing the predicted body fat percentage and the reference body fat percentage based on a pre-stored loss function, updating the parameters of the target model according to the analysis results, and using the updated target model for the next training until the loss function meets a preset condition;

[0029] The target model associated with the loss function that meets preset conditions is determined as the body fat percentage measurement model.

[0030] In some embodiments, the target model includes a linear regression model, and the loss function satisfies a preset condition, including:

[0031] If the loss function converges or the number of times the loss function is used for analysis reaches a preset number, it is determined that the loss function meets the preset conditions.

[0032] According to a second aspect of an embodiment of the present disclosure, a wearable device is provided, wherein electrodes are provided in the wearable device, and the wearable device includes:

[0033] an input module, configured to input a preset current to a target object based on the electrodes;

[0034] an acquisition module, configured to acquire an impedance parameter of the target object based on the preset current;

[0035] The acquisition module is further configured to acquire electrocardiogram characteristics of the target object;

[0036] A first determining module is configured to determine a target feature set based on the impedance parameter and the electrocardiogram feature;

[0037] The second determination module is used to determine the body fat percentage of the target object based on the relationship between the target feature set and the body fat percentage.

[0038] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0039] processor;

[0040] a memory for storing processor-executable instructions;

[0041] Wherein, the processor is configured to execute the body fat percentage measurement method as described in the first aspect of the present disclosure.

[0042] According to the fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the body fat percentage measurement method as described in the first aspect of the present disclosure.

[0043] The above-mentioned method disclosed in the present invention has the following beneficial effects: the body fat percentage measurement method disclosed in the present invention can input a preset current into the target object through the electrodes set on the wearable device, and combine the impedance parameters and electrocardiogram characteristics of the target object to jointly determine the body fat percentage of the target object. Since the electrocardiogram characteristics are less affected by external factors and internal factors of the target object, the present invention can improve the accuracy and stability of the measured body fat percentage, thereby obtaining a more accurate body fat percentage, making it easier for users to manage their health and improving user experience.

[0044] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0046] Figure 1 This is a flow chart of a method for measuring body fat percentage according to an exemplary embodiment.

[0047] Figure 2 This is a flow chart of a method for measuring body fat percentage according to an exemplary embodiment.

[0048] Figure 3 This is a flow chart of a method for measuring body fat percentage according to an exemplary embodiment.

[0049] Figure 4 is a block diagram of a wearable device according to an exemplary embodiment.

[0050] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0052] Current body fat percentage measurement methods are subject to user influence. For example, drinking large amounts of water or experiencing short-term dehydration before measurement can significantly affect the results. They also have poor prediction performance for various populations, such as obese and elderly individuals. Consequently, this method is significantly affected by factors such as temperature, diet, exercise, and the user's individual condition, resulting in poor accuracy and stability in body fat percentage measurements.

[0053] To address the above issues, the present disclosure provides a method for measuring body fat percentage. The method can input a preset current into a target object through electrodes provided on a wearable device, and combine the impedance parameters and electrocardiogram characteristics of the target object (the user being measured) to jointly determine the target object's body fat percentage. Because electrocardiogram characteristics are less affected by external factors and internal factors of the target object, the present disclosure can improve the accuracy and stability of the measured body fat percentage, thereby obtaining a more accurate body fat percentage, making it easier for users to manage their health and improving the user experience.

[0054] The exemplary embodiments of the present disclosure provide a method for measuring body fat percentage. It should be noted that the method for measuring body fat percentage in the present disclosure can be applied to any body fat percentage measuring device. Specifically, the body fat percentage measuring device can be a mobile phone, tablet computer, notebook, smart robot, smart wearable device, smart body fat scale, professional body fat measuring device, and other smart devices that can measure body fat percentage. Among them, the relevant data of the target object measured by the body fat percentage measuring device can be displayed on the display screen of the body fat percentage measuring device to facilitate the user to view the data. The body fat percentage measuring device is also provided with various hardware resources and an energy storage device that provides power for the operation of various hardware resources. For body fat percentage measuring devices that do not have a display function, the body fat percentage measuring device can also be connected to the smart terminal device used by the user, so that the detected body fat percentage can be sent to the user's smart terminal, thereby facilitating the user to understand his or her own health status.

[0055] like Figure 1 As shown, the body fat percentage measurement method shown in this embodiment includes:

[0056] S101 : Inputting a preset current to a target object based on electrodes.

[0057] S102: Obtain impedance parameters of the target object based on a preset current.

[0058] S103: Obtain electrocardiogram features of the target object.

[0059] S104: Determine a target feature set based on the impedance parameters and the electrocardiogram features.

[0060] S105: Determine the body fat percentage of the target object based on the relationship between the target feature set and the body fat percentage.

[0061] In step S101, the target object may refer to a user who undergoes body fat percentage measurement, that is, a user to be measured. In one example, a preset current may be input to the target object through electrodes. The electrodes may be arranged inside the body fat percentage measuring device. For example, when the body fat percentage measuring device is an intelligent body fat scale, 4-8 electrodes are evenly arranged inside the intelligent body fat scale. In this way, when the target object stands on the intelligent body fat scale, the intelligent body fat scale inputs a weak current to the target object through the electrodes. For another example, the electrodes may be arranged inside a wearable device. When the target object wears the wearable device, the wearable device inputs a weak current to the target object through the electrodes. It should be noted that when setting the electrodes, it is usually necessary to set input electrodes and output electrodes. The input electrodes are used to input current into the human body, and the output electrodes are used to extract the current input into the body of the user to be measured and passing through the body of the user to be measured, thereby forming a current path through the human body to ensure the effectiveness and reliability of the detection.

[0062] In addition, the electrodes can also be externally connected to the body fat percentage measurement device through connecting wires. For example, the external electrodes are connected to the body fat percentage measurement device through wires, and when measuring the body fat percentage, the electrodes are respectively pasted or adsorbed on the corresponding parts of the target object, such as the left and right hands of the target object. It should be noted that the body fat percentage measurement device should be provided with an interface corresponding to the connecting wire of the external electrode to ensure the normal operation of the electrode and the body fat percentage measurement device. During use, current can be input to the target object through the contact between the target object and the external electrode.

[0063] In another example, current can also be input into the target object through an ITO (Indium Tin Oxide) electroplated film. Here, the ITO electroplated film refers to a transparent conductive material. Specifically, the ITO electroplated film can be covered on the inside of the body fat percentage measuring device. When the target object contacts the ITO electroplated film, a preset current is input into the target object. In addition, it should be noted that the ITO electroplated film generally completely covers the inside of the body fat percentage measuring device.

[0064] It should be noted that, whether inputting a preset current into the target object through an electrode or inputting current into the target object through an ITO electroplated film, the current should have an input end and an output end, so that a current loop can be formed in the body of the target object. Accordingly, if an electrode is used to input current into the target object, an input electrode and an output electrode should be provided. For example, a smart body fat scale is provided with four electrode sheets, of which two electrode sheets are provided on the left foot side and two electrode sheets are provided on the right foot side. Then, current can be input into the target object through the electrode sheet on the left foot side, and current can be output through the electrode sheet on the right foot side, forming a closed current loop. Accordingly, the electrode sheet on the left foot side is the input electrode, and the electrode sheet on the right foot side is the output electrode. In addition, when an ITO electroplated film is provided in the body fat percentage measuring device, one of the two ends in contact with the body fat percentage measuring device can be used as the input end, and the other end can be used as the output end.

[0065] In one example, the preset current may be an alternating current, and the preset current may be a weak (non-harmful to the human body) alternating current of a certain frequency, for example, the magnitude of the preset current may be 100 mA, and the frequency of the preset current may be 50 kHz.

[0066] In step S102, impedance refers to the resistance to current flow in a circuit composed of resistance, inductance, and capacitance. Impedance includes both resistance and reactance. Because different tissues in the human body have different resistances, when a predetermined current is input into a target object, the target object will resist the current, thereby generating impedance.

[0067] Since the preset current is an AC current, and in an AC circuit, the direction of change of current and voltage is constantly changing, a phase difference will occur between the voltage and current. The phase difference is generally expressed as an angle, with units of degrees or radians. In one example, the impedance parameters may include the impedance modulus and the phase difference between the voltage and current. The impedance modulus refers to the ratio of the voltage to the current in the circuit, and the phase difference between the voltage and current in the circuit can also be called the impedance angle.

[0068] Specifically, the impedance modulus is calculated as follows:

[0069] Obtain the voltage between the input end of the current in the circuit and the output end of the current, and the ratio of the voltage to the preset current. Wherein, if the preset current is input through the electrode, the voltage between the input end of the current in the circuit and the output end of the current can be obtained by obtaining the voltage between the electrode sheets. For example, taking an intelligent body fat scale comprising four electrode sheets (L1, L2, R3 and R4) as an example, the two electrode sheets on the left foot side are L1 and L2, and the two electrode sheets on the right foot side are R1 and R2. Among the electrode sheets on both sides of the left and right feet, L1 and R1 are excitation electrodes for generating excitation signals, that is, L1 and R1 can be used to input a preset current to the target object, while L2 and R2 are detection electrodes for measuring voltage, that is, L2 and R2 can be used to measure the voltage between L1 and R1.

[0070] The impedance angle is calculated as:

[0071] In one example, the phase difference between voltage and current can be calculated using the sine functions of voltage and current. For example, the expression for voltage is: The expression for current is: Among them, U m Indicates the voltage amplitude, I m represents the amplitude of the current, ω represents the angular frequency, and Represent the phase of voltage and current respectively. Dividing the expressions of current and voltage by their amplitudes respectively, the relative value of current is obtained as: The relative value of the voltage is: Using the relative values of voltage and current, the phase difference between voltage and current is obtained as:

[0072] In another example, the phase difference between the voltage and the current can be calculated using complex functions of the voltage and the current. For example, the complex function of the voltage can be: The complex function of current is: Where j represents the imaginary unit, and e represents the mathematical constant, which is the base of the natural logarithm function. Let the complex numbers of voltage and current be U c and I c , dividing the expressions of current and voltage by their amplitudes respectively, the relative value of current is obtained as: The relative value of the voltage is: Using the relative values of voltage and current, the phase difference between voltage and current is obtained as: Here, arg is a mathematical function used to represent the phase angle of a complex number.

[0073] In another example, the phase difference between the voltage and current can be determined by using waveform graphs of the voltage and current. In the waveform graph, the phase difference can refer to the time difference between the voltage waveform and the current waveform. For example, the voltage waveform and the current waveform can be plotted on the same coordinate axis, and the difference between the horizontal coordinates of the two under the same vertical coordinate is calculated, which is the value of the phase difference. The phase difference can be positive or negative, and its positive or negative depends on the order of the current waveform and the voltage waveform. When the current waveform leads the voltage waveform, the phase difference is negative. Conversely, when the voltage waveform leads the current waveform, the phase difference is positive.

[0074] In step S103, the electrocardiogram characteristics of the target object can be used to monitor the heart rate variability of the target object, evaluate the metabolic state of the target object, and evaluate the cardiac load of the target object. At the same time, the electrocardiogram characteristics can also provide electrocardiogram parameters, thereby evaluating the relationship between the cardiovascular health and body fat rate of the target object. Therefore, there is a certain correlation between the electrocardiogram characteristics and the body fat rate. For example, people with a higher body fat rate (i.e., obese people) have a higher cardiac load and their heart rate is prone to abnormal conditions. Therefore, adding electrocardiogram characteristics to the body fat rate measurement process can, to a certain extent, make up for the problems of inaccurate and unstable body fat rate results in the existing technology.

[0075] An electrocardiogram (ECG) is a technique that uses an electrocardiograph to record the changes in electrical activity produced by the heart during each cardiac cycle from the body's surface. In one example, features can be extracted from the target subject's ECG to obtain ECG features. For example, ECG features such as heart rate, heart rhythm, and myocardial ischemia signals can be extracted based on the changes in the ECG.

[0076] The measurement principle of the electrocardiogram is based on the electrical conductivity of the heart. When the heart contracts, an electric current is generated, which can be transmitted within the human body. Therefore, in one example, the electrocardiogram characteristics of the target object can be obtained through externally connected electrodes or a combination of electrodes and leads. For example, one end of the electrode and lead can be set on the target object, and the other end of the electrode and lead can be set on the body fat percentage measurement device, so as to obtain the electrocardiogram of the target object and the electrocardiogram characteristics of the target object. For another example, the electrodes are attached to the corresponding parts of the target object, and the leads are clamped to the corresponding parts of the target object, and the electrocardiogram and electrocardiogram characteristics of the target object are obtained based on the electrical activity of the target object's heart. It should be noted that since the current generated by the contraction of the heart can be transmitted within the human body, in another example, the current transmitted by the target object can be detected by the electrodes inside the body fat percentage measurement device, thereby obtaining the electrocardiogram of the target object and the electrocardiogram characteristics of the target object.

[0077] Each cardiac cycle in an electrocardiogram includes multiple wave signals, such as the P wave, Q wave, R wave, S wave, and T wave. Therefore, an electrocardiogram feature can be a feature related to the aforementioned wave signals. For example, an electrocardiogram feature can be the vibration amplitude of each wave; for example, an electrocardiogram feature can be the ratio between the vibration amplitudes of some wave signals.

[0078] In step S104, in one example, the target feature set can be obtained by combining the impedance parameters and the electrocardiogram features. That is, the elements of the target feature set are the parameters in the impedance parameters and the features in the electrocardiogram features. Assuming that the impedance parameters include parameters a and b, and the electrocardiogram features include features c, d, and e, the corresponding target feature set includes parameters a, b, c, d, and e. It should be noted that this embodiment does not limit the specific combination of the impedance parameters and the electrocardiogram features. For example, the initial impedance parameters and electrocardiogram features can be combined into a one-dimensional vector or a multi-dimensional vector. In addition, this embodiment does not limit the order in which the impedance parameters and electrocardiogram features are arranged. For example, they can be arranged in the order of impedance parameters and electrocardiogram features, or in the order of electrocardiogram features-impedance parameters. In addition, if the impedance parameters and electrocardiogram features also include multiple parameters / features, this embodiment does not limit the order in which the impedance parameters and electrocardiogram features are arranged.

[0079] In another example, the elements of the target feature set may also be deformations of the impedance parameters and / or deformations of the electrocardiogram features, or new features determined after operations are performed based on the impedance parameters and the electrocardiogram features. For example, the parameters / features with significant characteristics in the impedance parameters or electrocardiogram features can be extracted through feature extraction technology, and the remaining parameters / features can be discarded. For another example, the impedance parameters can be used as the first vector, and the electrocardiogram can be used as the second vector, and the target feature set can be determined based on the operation between the first vector and the second vector. For another example, the impedance parameters and the electrocardiogram features can be processed separately, first determining the first feature set based on the impedance parameters, then determining the second feature set based on the electrocardiogram features, and finally determining the target feature set based on the first feature set and the second feature set, wherein the elements in the first feature set can be parameters after the impedance parameters are deformed, and the elements in the second feature set can be parameters after the electrocardiogram features are deformed.

[0080] In step S105, when the body fat percentage measurement device leaves the factory, the relationship between the target feature set and the body fat percentage can be directly stored in the body fat percentage measurement device. For example, it can be written into the memory, central controller, or chip of the body fat percentage measurement device. During use, when the target feature set of the target subject is determined, the relationship between the target feature set and the body fat percentage can be directly called to determine the target subject's body fat percentage.

[0081] In one example, the relationship between the target feature set and the body fat percentage can be a corresponding relationship. For example, there is a fixed corresponding relationship between the target feature set and the body fat percentage, that is, the target feature set includes element i and element w. Usually, by querying the data written in advance inside the body fat percentage measurement device, the body fat percentage corresponding to element i and element w can be obtained. 15%.

[0082] In another example, the relationship between the target feature set and body fat percentage can be a functional relationship, for example, a fixed functional relationship y = f(x), where y represents body fat percentage and x represents features related to the target feature set, such as all features in the target feature set or features extracted from the target feature set. After determining the target feature set, the features related to the target feature set can be input into the functional relationship to obtain the body fat percentage of the target subject.

[0083] In another example, the relationship between the target feature set and body fat percentage can be a pre-existing body fat percentage measurement model. Specifically, the features in the target feature set can be input into the body fat percentage measurement model, and the body fat percentage measurement model can be continuously optimized. The final output of the body fat percentage measurement model is determined as the body fat percentage of the target subject.

[0084] In this embodiment, the target subject's (i.e., the user being measured) impedance parameters and electrocardiogram (ECG) characteristics can be combined to determine the target subject's body fat percentage. Because ECG characteristics are less affected by water intake, diet, temperature, and other factors, this embodiment can improve the accuracy and stability of body fat percentage measurement, resulting in a more accurate body fat percentage and a better user experience.

[0085] According to an exemplary embodiment, Figure 2 The body fat percentage measurement method in this embodiment includes:

[0086] S201 : Input a preset current to a target object based on electrodes.

[0087] S202: Obtain impedance parameters of the target object based on the preset current.

[0088] S203: Acquire an electrocardiogram signal of the target object.

[0089] S204: Extracting a preset wave signal of the electrocardiogram signal based on the electrocardiogram signal.

[0090] S205: Determine electrocardiogram characteristics based on the preset wave signal.

[0091] S206: Determine a target feature set based on the impedance parameters and the electrocardiogram features.

[0092] S207: Determine the body fat percentage of the target object based on the relationship between the target feature set and the body fat percentage.

[0093] Among them, steps S201-S202 and steps S206-S207 are the same as the above steps S101-S102 and steps S104-S105, and are not repeated here.

[0094] In step S203, the ECG signal is a weak physiological signal that is non-stationary, nonlinear, and highly random, with an amplitude of approximately millivolts and a frequency between 0.05Hz and 100Hz. It should be noted that the original ECG signal directly obtained generally contains noise interference, which can easily lead to inaccurate ECG signals.

[0095] Therefore, before performing step S204, the ECG signal needs to be denoised, and the denoised ECG signal is used for subsequent processes. Since the types of noise generated in different situations are different, in order to obtain a better denoising effect, different denoising methods can be performed for different noise types. Among them, the main noise types are divided into the following three categories:

[0096] Category 1: Baseline drift. This type of noise is typically caused by breathing and electrode slippage. Wavelet transform can be used to remove baseline drift from ECG signals. For specific technical methods, refer to related techniques for removing baseline drift using wavelet transform.

[0097] The second type is myoelectric interference. This type of noise is usually caused by irregular high-frequency electrical interference generated by human muscle tremors. Generally, the noise can be reduced by improving the state of the target object.

[0098] The third category is power frequency interference. This refers to electromagnetic fields radiated from the power supply and surrounding transmission lines, which can add noise to the ECG signal. This type of noise can be removed through hardware and software filtering, such as using 50Hz and 60Hz notch filters.

[0099] In step S204, the electrocardiogram is usually set with a sampling time, such as 5s. During the sampling time, there will be multiple sampling points, and each sampling point can collect a cardiac cycle. In one cardiac cycle, the electrocardiogram signal will include a regular waveform period, and the preset wave signals, namely P wave, Q wave, R wave, S wave and T wave, can be extracted in this regular waveform period. Among them, the P wave represents the atrial depolarization wave, which is used to characterize the potential changes generated when the left and right atria are excited. In application, the Q wave, R wave and S wave are generally referred to as the QRS complex, which is a general term for characterizing the ventricular depolarization wave type. In the QRS complex, the first upward wave is the R wave, the first downward wave is the Q wave, and the downward wave after the R wave is the S wave. The T wave represents the ventricular repolarization wave, and the T wave is closely related to the metabolic function of myocardial cells.

[0100] It should be noted that this embodiment does not limit the ECG signal to a signal of a single cardiac cycle. That is, the ECG signal is a signal over a period of time. Therefore, in this embodiment, the target subject's ECG signal may include multiple regular waveform cycles. In other words, the target subject's ECG signal may include multiple P waves, Q waves, R waves, S waves, and T waves.

[0101] In step S205, the electrocardiogram feature can be determined based on the amplitudes of the P wave, Q wave, R wave, S wave and T wave in the electrocardiogram signal. The electrocardiogram feature includes multiple sub-features, each of which is related to the amplitude of the preset wave signal and / or the time of the preset wave signal.

[0102] In one example, since the target subject's electrocardiogram signal may include multiple P waves, Q waves, R waves, S waves, and T waves, the absolute amplitude of each P wave, Q wave, R wave, S wave, and T wave can be obtained separately, and the mean, median, standard deviation, variance, and variability of the absolute amplitudes corresponding to the P wave, Q wave, R wave, S wave, and T wave can be calculated. Taking the P wave as an example, the mean of the absolute amplitude of the P wave refers to the average value calculated by summing the absolute amplitudes of the P waves in each cardiac cycle. The median of the absolute amplitudes refers to the absolute amplitude in the middle of the sequence of the absolute amplitudes of the P waves in each cardiac cycle, arranged in order of magnitude. Furthermore, if the number of absolute amplitudes in the middle is even, the median is the average of the two absolute amplitudes in the middle. The variance of the absolute amplitudes refers to the average value calculated by summing the squares of the differences between the absolute amplitudes of the P waves in each cardiac cycle and the mean. The standard deviation of the absolute amplitude is the square root of the variance, which reflects the degree of dispersion in a set of data. The variability of the absolute amplitude is the ratio of the standard deviation to the mean, which measures the degree of dispersion in a set of data. Similarly, the calculation process for Q waves, R waves, S waves, and T waves is the same as that for P waves and will not be repeated here.

[0103] For ease of understanding, the following is an example: In chronological order, the target image's electrocardiogram signal includes 3 P waves (p1, p2, and p3), 3 Q waves (q1, q2, q3), 3 R waves (r1, r2, r3), 3 S waves (s1, s2, s3), and 3 T waves (t1, t2, t3). Furthermore, the absolute amplitudes of p1, p2, and p3 in the P wave are 4, 6, and 2, respectively; the absolute amplitudes of q1, q2, and q3 in the Q wave are 2, 3, and 4, respectively; the absolute amplitudes of r1, r2, and r3 in the R wave are 4, 5, and 6, respectively; the absolute amplitudes of s1, s2, and s3 in the S wave are 2, 3, and 4, respectively; and the absolute amplitudes of t1, t2, and t3 in the T wave are 2, 4, and 6, respectively. Correspondingly, the mean, median, and variance of the absolute amplitudes of the P wave are 4, 4, and 4. The standard deviation is The mutation rate is To save space, we will not calculate the variance, standard deviation, and variability of other waves. The mean and median absolute amplitudes of the Q wave are 3, 3, 5, 5, 3 ...

[0104] The above example extracts features from each individual wave signal. In another example, band features can be extracted. Bands include the PQ band, QR band, RS band, ST band, QT band, and TQ band. Because the ECG signal includes multiple cardiac cycles within the sampling time, there are also multiple bands between waves. Each band includes two individual wave signals, and each wave signal has a corresponding amplitude. Therefore, the mean, median, standard deviation, variance, and variability of the relative amplitudes of the PQ band, QR band, RS band, ST band, QT band, and TQ band can be obtained, as well as the mean, median, standard deviation, variance, and variability of the durations corresponding to the PQ band, QR band, RS band, ST band, QT band, and TQ band. Taking the PQ band as an example, the relative amplitude of the PQ band refers to the amplitude difference between the amplitude point of the P wave and the amplitude point of the Q wave. Specifically, the amplitude of p1 is 4 and the amplitude of q1 is -2, then the relative amplitude of this PQ band is 6. The duration of the PQ band refers to the length from the start time of the P wave to the end time of the Q wave. For example, the start time of the P wave is 10ms and the end time of the Q wave is 100ms, then the duration of the PQ band is 90ms. The calculation method of the relative amplitude and duration of other bands is the same as that of the above-mentioned PQ band, and will not be repeated here. It is worth mentioning that there is a case where the amplitude difference corresponding to the band is a negative value. Therefore, the relative amplitude in the present disclosure can refer to the absolute value of the amplitude difference.

[0105] It should be noted that, with the exception of the TQ band, the previous and next wave signals in other bands belong to the same cardiac cycle. It should be noted that the TQ band refers to the band corresponding to the T wave in the previous cardiac cycle to the Q wave in the current cardiac cycle. In other words, the QT band and TQ band can represent the bands corresponding to two adjacent heartbeats. By analyzing the QT band and TQ band, the changes between adjacent heartbeats can be determined, thereby better capturing the target subject's ECG characteristics.

[0106] In another example, the ratio of the relative amplitudes between bands, that is, the relative ratio of the amplitudes, can also be obtained; the ratio of the durations between bands can also be obtained. Among them, the relative ratio of the amplitudes and the relative ratio of the durations can both be used to characterize the heartbeat fluctuations of the target object. Specifically, the average, median, standard deviation, variance and variation rate of the relative amplitude ratios / durations corresponding to PQ / RR, QR / RR, RS / RR, ST / RR, QT / RR, TQ / RR and QT / TQ can be obtained respectively. It should be noted that RR refers to the band composed of the R wave in the previous cardiac cycle to the R wave in the current cardiac cycle, and the relative amplitude ratios and relative duration ratios of QT / TQ can be used to characterize the changes in adjacent heartbeats.

[0107] In summary, the electrocardiogram feature may include the sub-features in any of the three examples above, or may include a combination of the sub-features in any of the three examples above. Preferably, in order to ensure that the number of sub-features is sufficient and the feature coverage is comprehensive, all the sub-features shown in the three examples above may be used as electrocardiogram features.

[0108] This embodiment provides a method for determining ECG characteristics. By determining the ECG characteristics and combining them with impedance parameters, the target subject's body fat percentage can be determined. This allows for a more accurate determination of the target subject's body fat percentage based on the ECG characteristics, which are unaffected by external factors, thereby improving the target subject's experience. Furthermore, the target subject can manage their health based on the accurate body fat percentage.

[0109] According to an exemplary embodiment, Figure 3 As shown, the body fat percentage measurement method in this embodiment includes:

[0110] S301 : Input a preset current to a target object based on electrodes.

[0111] S302: Obtain impedance parameters of the target object based on the preset current.

[0112] S303: Obtain electrocardiogram features of the target object.

[0113] S304: Determine a target feature set based on the impedance parameters and the electrocardiogram features.

[0114] S305: Input the target feature set into a pre-stored body fat percentage measurement model.

[0115] S306: Determine the output value of the body fat percentage measurement model as the body fat percentage of the target object.

[0116] Among them, steps S301-S304 are the same as steps S101-S104 in the above embodiment and are not repeated here.

[0117] In step S305, the body fat percentage measurement model can be written into the body fat percentage measurement device before the body fat percentage measurement device leaves the factory, so as to facilitate the subsequent process of calculating the body fat percentage. In addition, the input of the body fat percentage measurement model in this embodiment is a target feature set. It should be noted that during the training process of the body fat percentage measurement model, the features in the feature set of the input sample set are generally sorted in a certain order, so as to ensure the accuracy of the body fat percentage measurement model. Therefore, in order to ensure the accuracy of the input target features combined with the corresponding body fat percentage, the features in the target feature set input each time can be arranged in a preset order, for example, in the order of parameter a, parameter b, feature c, feature e and feature d.

[0118] In one example, a body fat percentage measurement model can be obtained by following the steps below:

[0119] S110: Obtain a training set of sample objects.

[0120] S120: Obtain a reference body fat percentage for each sample subject.

[0121] S130: Training a preset target model based on the training set and the reference body fat percentage to obtain a body fat percentage measurement model.

[0122] In step S110, the number of sample objects should be larger, and the types of people covered in the sample objects should be as wide as possible to ensure that the trained body fat percentage model is more accurate. In order to make the body fat percentage measurement model more accurate, the sample objects should be various types of objects, such as obese people, elderly people, young people, or children. It is necessary to consider multiple factors such as age, gender, occupation, height, weight, etc. to ensure sample diversity. In this way, the body fat percentage measurement model trained using the above sample objects is applicable to various types of target objects during use, and the body fat percentage of the target objects determined will also be more accurate. In addition, the data in the training set should be sufficient to support the training of the body fat percentage measurement model. Therefore, the training set can include multiple sample subsets, wherein each sample object is associated with a sample subset, each sample subset includes sample impedance parameters and sample electrocardiogram features, and the parameters contained in each sample subset are only related to the sample object with which it is associated.

[0123] In step S120, the reference body fat percentage refers to the actual body fat percentage of the sample subject.

[0124] In one example, a body composition analyzer or a body composition detector can be used to obtain a reference body fat percentage. It should be noted that the above-mentioned body composition analyzer or body composition detector must be an instrument that has obtained a medical device registration certificate.

[0125] In another example, a reference body fat percentage can be obtained using dual-energy X-ray absorptiometry. X-rays are highly penetrating electromagnetic waves that can penetrate matter and absorb it. Because different elements and combinations absorb X-rays to varying degrees, the body composition and, therefore, the reference body fat percentage can be determined by measuring the absorption of X-rays of different energies by different tissues.

[0126] The true body fat percentage of the sample object can be considered as a label in the training process, that is, the gold standard of body fat. During the model training process, it is necessary to continuously adjust and correct the label as a reference object to make the training model more accurate.

[0127] In step S130, the target model refers to the initial body fat percentage measurement model, wherein the target model can be any predictive machine learning model, such as a regression analysis model, a support vector machine model, a neural network model, and the like.

[0128] In one example, during training, a sample subset associated with a sample object can be input into the target model to obtain a predicted body fat percentage. This embodiment does not limit the order in which the sample subsets associated with the sample objects are input, but it should be noted that the sample objects associated with each sample subset input should be different.

[0129] In one example, the predicted body fat percentage and the reference body fat percentage can be analyzed based on a loss function. Specifically, the predicted result and the actual result can be analyzed based on the loss function. This embodiment does not limit the specific type of loss function; for example, the loss function may include mean squared error, absolute value error, or Huber loss function. Mean squared error refers to the average of the squared distances between a sample's predicted value and its true value. In this embodiment, mean squared error refers to the average of the squared differences between the sample's predicted body fat percentage and its reference body fat percentage. Absolute value error refers to the average of the absolute differences between a sample's predicted value and its true value. In this embodiment, absolute value error refers to the average of the absolute differences between the sample's predicted body fat percentage and its reference body fat percentage. The Huber loss function is a combination of mean squared error and absolute value error. Specifically, it calculates the difference between the sample's predicted value and its true value. When the difference is less than or equal to a preset threshold, mean squared error is used; conversely, when the difference is greater than the preset threshold, absolute value error is used.

[0130] In one example, after determining the loss function, an optimization algorithm is generally used to optimize the loss function, thereby updating the parameters of the target model. The optimization algorithm can be a gradient descent algorithm, a momentum gradient descent algorithm, a gradient descent algorithm with an adaptive learning rate, a gradient squared algorithm with a decaying moving average, an extended algorithm of the gradient descent optimization algorithm, and the like. The specific process of optimizing the loss function using the optimization algorithm is not further described in this embodiment.

[0131] In one example, the updated target model can be used for the next training until the loss function meets the preset conditions. The preset conditions include: the loss function converges (when the loss function is minimized) or the number of times the loss function is used for analysis reaches a preset number of times. That is, this embodiment can loop through the process of inputting a sample subset—obtaining the predicted body fat percentage of the sample object—calculating the loss function based on the predicted body fat percentage and the reference body fat percentage—optimizing the loss function based on the optimization algorithm—obtaining the parameters of the updated target model until the loss function converges or the number of times the loss function is used for analysis reaches a preset number of times (it can also refer to the above cycle reaching a preset number of times). When the loss function meets the preset conditions, there is a set of parameters for the target model. Therefore, the target model associated with this set of parameters can be used to determine the final body fat percentage measurement model.

[0132] Specifically, the following takes the regression analysis model as an example to illustrate the training process of the target model:

[0133] The initial model for the regression analysis is set to: Y = b0 + b1 * X. Here, b0 represents the intercept, b1 represents the coefficient, X represents the input sample subset, and Y represents the output predicted body fat percentage for that sample. At the beginning of training, b0 and b1 can be initialized to 0 or random values.

[0134] The sample subset associated with each sample object is input into the regression analysis model to obtain the output value of the regression analysis model (ie, the predicted value of the body fat percentage corresponding to the sample object).

[0135] Construct a loss function, and calculate the difference between the output value and the reference body fat percentage of the sample object based on the loss function. Use the gradient descent algorithm to minimize the loss function, and obtain the values of b0 and b1 corresponding to when the loss function converges or reaches a preset number of times. Substitute b0 and b1 into the initial model of the regression analysis model to obtain the body fat percentage measurement model.

[0136] In step S306, after the target feature set is input into the pre-stored body fat percentage measurement model, an output value corresponding to the target feature set is obtained. This output value is the body fat percentage of the target subject.

[0137] This example demonstrates the training process for a body fat percentage measurement model. Specifically, the process involves calculating the loss function between the predicted and reference body fat percentages for each sample subject, optimizing the loss function using an optimization algorithm, and ultimately obtaining the parameters of a target model whose loss function satisfies pre-set conditions. This ensures the accuracy and stability of the body fat percentage measurement model, allowing accurate body fat percentages of the target subject to be accurately determined during use, improving the user experience.

[0138] For ease of understanding, a specific example is given in this embodiment:

[0139] S210 , inputting a preset current into the target object through the electrodes.

[0140] S220: Obtain impedance parameters of the target object based on the preset current.

[0141] S230: Obtain an electrocardiogram signal of the target object through electrodes.

[0142] S240: Extracting a preset wave signal of the electrocardiogram signal, and determining the electrocardiogram characteristics of the target object based on the preset wave signal.

[0143] S250: Determine a target feature set based on the electrocardiogram features and impedance parameters of the target object.

[0144] S260: Input the target feature set into a pre-stored body fat percentage measurement model to obtain the body fat percentage of the target object.

[0145] In step S210 , the electrodes include input electrodes and output electrodes.

[0146] In this embodiment, the target feature set of the target object is determined by obtaining the impedance parameters and electrocardiogram signal of the target object, and the target feature set is input into a pre-trained body fat percentage measurement model to obtain the body fat percentage of the target object.

[0147] An exemplary embodiment of the present disclosure provides a wearable device, wherein electrodes are provided in the wearable device, such as Figure 4 As shown, the present disclosure shows a block diagram of a wearable device.

[0148] The block diagram includes an input module 41, an acquisition module 42, a first determination module 43, and a second determination module 44. Input module 41 is configured to input a preset current into a target subject based on electrodes. Acquisition module 42 is configured to acquire impedance parameters of the target subject based on the preset current. Acquisition module 42 is also configured to acquire electrocardiogram (ECG) features of the target subject. First determination module 43 is configured to determine a target feature set based on the impedance parameters and ECG features. Second determination module 44 is configured to determine the target subject's body fat percentage based on the relationship between the target feature set and body fat percentage.

[0149] In some embodiments, the electrodes include input electrodes and output electrodes, and the acquisition module 42 is specifically configured to:

[0150] obtaining the voltage between the input electrode and the output electrode;

[0151] Based on the voltage and the preset current, the impedance parameter of the measurement user is determined.

[0152] In some embodiments, the preset current is an alternating current, and the impedance parameters include an impedance modulus and a phase difference between the voltage and the preset current;

[0153] The impedance modulus is the ratio of voltage to preset current.

[0154] In some embodiments, the acquisition module 42 is specifically configured to:

[0155] Acquiring an electrocardiogram signal of a target object;

[0156] Extracting preset wave signals of the electrocardiogram signal based on the electrocardiogram signal, where the preset wave signals include P wave, Q wave, R wave, S wave and T wave;

[0157] Based on the preset wave signal, an electrocardiogram feature is determined, where the electrocardiogram feature includes a plurality of sub-features, and each sub-feature is related to the amplitude of the preset wave signal and / or the time of the preset wave signal.

[0158] In some embodiments, the second determining module 44 is specifically configured to:

[0159] Inputting the target feature set into a pre-stored body fat percentage measurement model, wherein the features in the target feature set are arranged in a preset order;

[0160] The output value of the body fat percentage measurement model is determined as the body fat percentage of the target object.

[0161] In some embodiments, the body fat percentage measurement model is obtained by the following method:

[0162] Obtaining a training set of sample objects; the training set includes multiple sample subsets, each sample subset includes a sample impedance parameter and a sample electrocardiogram feature, wherein each sample object is associated with a sample subset;

[0163] Obtain the reference body fat percentage of each sample subject, where the reference body fat percentage is the actual body fat percentage of the sample subject;

[0164] The preset target model is trained based on the training set and the reference body fat percentage to obtain a body fat percentage measurement model.

[0165] In some embodiments, the second determining module 44 is specifically configured to:

[0166] In each training process, the sample subset associated with the sample object is input into the target model to obtain the predicted body fat percentage. The sample objects associated with the sample subset input in each training process are different.

[0167] The predicted body fat percentage and the reference body fat percentage are analyzed based on the pre-stored loss function. The parameters of the target model are updated according to the analysis results. The updated target model is used for the next training until the loss function meets the preset conditions.

[0168] The target model associated with the loss function that meets the preset conditions is determined as the body fat percentage measurement model.

[0169] In some embodiments, the target model includes a linear regression model, and the second determination module 44 is specifically configured to:

[0170] If the loss function converges or the number of times the loss function is analyzed reaches a preset number, it is determined that the loss function meets the preset conditions.

[0171] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0172] Figure 5 is a block diagram of an electronic device 500 according to an exemplary embodiment.

[0173] Reference Figure 5 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0174] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 502 may include one or more modules to facilitate interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.

[0175] The memory 504 is configured to store various types of data to support operations on the electronic device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0176] The power supply assembly 506 provides power to the various components of the electronic device 500. The power supply assembly 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0177] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0178] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 504 or transmitted via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0179] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0180] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the electronic device 500, the relative positioning of components, such as the display and keypad of the electronic device 500. The sensor assembly 514 can also detect changes in the position of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and temperature changes of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0181] The communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0182] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0183] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by the processor 520 of the electronic device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0184] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the body fat percentage measurement method provided by an exemplary embodiment of the present disclosure.

[0185] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0186] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for measuring body fat percentage, characterized in that: Applied to a wearable device, wherein the wearable device is provided with electrodes, the body fat percentage measurement method includes: Based on the electrodes, inputting a preset current into the target object; Based on the preset current, obtaining an impedance parameter of the target object; Acquiring electrocardiogram characteristics of the target object; determining a target feature set based on the impedance parameter and the electrocardiogram feature; Based on the relationship between the target feature set and the body fat percentage, the body fat percentage of the target object is determined.

2. The method for measuring body fat percentage according to claim 1, wherein: The electrodes include an input electrode and an output electrode, and obtaining the impedance parameter of the target object based on the preset current includes: obtaining a voltage between the input electrode and the output electrode; An impedance parameter of the measured user is determined based on the voltage and the preset current.

3. The body fat percentage measurement method according to claim 2, characterized in that: The preset current is alternating current, and the impedance parameters include an impedance modulus and a phase difference between the voltage and the preset current; wherein the impedance modulus is a ratio of the voltage to the preset current.

4. The method for measuring body fat percentage according to claim 1, wherein: The obtaining of the electrocardiogram characteristics of the target object includes: Acquiring an electrocardiogram signal of the target object; Extracting a preset wave signal of the electrocardiogram signal based on the electrocardiogram signal, wherein the preset wave signal includes a P wave, a Q wave, an R wave, an S wave, and a T wave; Based on the preset wave signal, the electrocardiogram feature is determined, where the electrocardiogram feature includes a plurality of sub-features, each of which is related to the amplitude of the preset wave signal and / or the time of the preset wave signal.

5. The method for measuring body fat percentage according to claim 1, wherein: The determining the body fat percentage of the target object based on the relationship between the target feature set and the body fat percentage includes: Inputting the target feature set into a pre-stored body fat percentage measurement model, wherein the features in the target feature set are arranged in a preset order; An output value of the body fat percentage measurement model is determined as the body fat percentage of the target object.

6. The method for measuring body fat percentage according to claim 5, wherein: The body fat percentage measurement model is obtained by the following method: Acquire a training set of sample objects; the training set includes multiple sample subsets, each of the sample subsets includes a sample impedance parameter and a sample electrocardiogram feature, wherein each of the sample objects is associated with one of the sample subsets; Obtain a reference body fat percentage for each of the sample subjects, where the reference body fat percentage is the actual body fat percentage of the sample subject; The preset target model is trained based on the training set and the reference body fat percentage to obtain the body fat percentage measurement model.

7. The method for measuring body fat percentage according to claim 6, wherein: The step of training a preset target model based on the training set and the reference body fat percentage to obtain the body fat percentage measurement model includes: In each training process, the sample subset associated with the sample object is input into the target model to obtain a predicted body fat percentage, wherein the sample object associated with the sample subset input in each training process is different; Analyzing the predicted body fat percentage and the reference body fat percentage based on a pre-stored loss function, updating the parameters of the target model according to the analysis results, and using the updated target model for the next training until the loss function meets a preset condition; The target model associated with the loss function that meets preset conditions is determined as the body fat percentage measurement model.

8. The method for measuring body fat percentage according to claim 7, wherein: The target model includes a linear regression model, and the loss function satisfies preset conditions, including: If the loss function converges or the number of times the loss function is used for analysis reaches a preset number, it is determined that the loss function meets the preset conditions.

9. A wearable device, characterized in that: The wearable device is provided with electrodes, and the wearable device includes: an input module, configured to input a preset current to a target object based on the electrodes; an acquisition module, configured to acquire an impedance parameter of the target object based on the preset current; The acquisition module is further configured to acquire electrocardiogram characteristics of the target object; A first determining module is configured to determine a target feature set based on the impedance parameter and the electrocardiogram feature; The second determination module is used to determine the body fat percentage of the target object based on the relationship between the target feature set and the body fat percentage.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the body fat percentage measurement method as described in any one of claims 1-8.

11. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the body fat percentage measuring method as described in any one of claims 1 to 8.

Images