Method, device and computer-readable storage medium for measuring body fat percentage

Abstract

The present invention discloses a method, device and computer-readable storage medium for measuring body fat percentage. The method includes: when a measurement instruction is received, obtaining first body data corresponding to a target object, where the first body data includes preset height, age, gender and body posture label; measuring second body data of the target object, where the second body data includes weight and lower limb impedance data; and determining the body fat percentage corresponding to the target object according to the first body data and the second body data. The present invention reduces the measurement cost of body fat percentage.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and device for measuring body fat percentage and a computer-readable storage medium. Background Art

[0002] With the continuous development and optimization of learning algorithms, existing eight-electrode body fat scales can already fit results close to those measured by DEXA for body fat percentage through the BIA algorithm. However, compared with eight-electrode body fat scales, four-electrode body fat scales only detect the impedance of the lower limbs of the human body and lack the impedance of the upper limbs and torso. Due to insufficient detection data, four-electrode BIA cannot highly fit DEXA detection results like eight-electrode BIA algorithms. If impedance data of the upper body is desired, it is undoubtedly necessary to add additional equipment to measure the upper limbs, which will increase the measurement cost of body fat percentage. Summary of the Invention

[0003] Embodiments of the present invention provide a method and device for measuring body fat percentage and a computer-readable storage medium, aiming to solve the technical problem of how to reduce the measurement cost of body fat percentage.

[0004] Embodiments of the present invention provide a method for measuring body fat percentage, and the method for measuring body fat percentage includes the following steps:

[0005] When a measurement instruction is received, obtain first body data corresponding to a target object, where the first body data includes preset height, age, gender, and body posture label;

[0006] Measure second body data of the target object, where the second body data includes weight and lower limb impedance data;

[0007] Determine the body fat percentage corresponding to the target object according to the first body data and the second body data.

[0008] In one embodiment, the step of determining the body fat percentage corresponding to the target object according to the first body data and the second body data includes:

[0009] Use the first body data and the second body data as input parameters of a pre-trained body fat percentage measurement model, where the body fat percentage measurement model outputs the body fat percentage according to the first body data and the second body data.

[0010] In one embodiment, before the step of using the first body data and the second body data as input parameters of a pre-trained body fat percentage measurement model, the method further includes:

[0011] Obtain a training set and a test set, where the training set and the test set include an input set and an output set. The characteristic attributes of the input set include lower limb impedance, body weight, height, age, gender, and body posture label, and the characteristic attributes of the output set include body fat percentage;

[0012] Perform model training based on the training set and the test set to obtain the body fat percentage measurement model.

[0013] In one embodiment, the step of obtaining the training set and the test set includes:

[0014] Obtain the body data samples of multiple pre-collected users. The characteristic attributes of the body data samples include lower limb impedance, body weight, height, age, gender, and body fat percentage;

[0015] Mark the body data samples so that the body data samples correspond to body posture label attributes;

[0016] Divide each of the body data samples marked with body posture label attributes into the training set and the test set.

[0017] In one embodiment, the step of performing model training based on the training set and the test set includes:

[0018] Determine the loss function and substitute the training set into the model for training;

[0019] When the loss value of the loss function converges to the best value, determine that the model training is completed;

[0020] Substitute the test set into the model for testing to obtain the performance indicators of the model;

[0021] Determine whether the performance indicators are greater than or equal to the preset performance indicators;

[0022] When the performance indicators are greater than the preset performance indicators, use the model as the body fat percentage measurement model.

[0023] In one embodiment, the step of obtaining the first body data corresponding to the target object when receiving a measurement instruction includes:

[0024] When receiving a measurement instruction, obtain the body data associated with the currently logged-in account as the first body data corresponding to the target object.

[0025] In one embodiment, the step of obtaining the body data associated with the currently logged-in account as the first body data corresponding to the target object when receiving a measurement instruction includes:

[0026] When receiving the measurement instruction, determine whether the target object has logged in;

[0027] When the target object has logged in, perform the step of obtaining the body data associated with the currently logged-in account as the first body data corresponding to the target object;

[0028] When the target object has not logged in, output a prompt message indicating that logging in is required.

[0029] In one embodiment, the step of measuring the second body data of the target object includes:

[0030] Control the measuring device to measure the lower limb impedance and weight of the target object to obtain the second body data.

[0031] An embodiment of the present invention further provides a body fat percentage measuring device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements each step of the body fat percentage measuring method described above.

[0032] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each step of the body fat percentage measuring method described above.

[0033] In the technical solution of this embodiment, when the body fat percentage measuring device receives a measurement instruction, it obtains the first body data corresponding to the target object. The first body data includes preset height, age, gender, and body posture labels; it measures the second body data of the target object, and the second body data includes weight and lower limb impedance data; it determines the body fat percentage corresponding to the target object according to the first body data and the second body data. Since the body fat percentage measuring device combines the preset first body data with the actually measured second body data to measure the body fat percentage, during the measurement process, the target object only needs to cooperate with measuring part of the second body data. Compared with the conventional technical means that require expensive equipment to obtain all quantities for measurement, the present invention reduces the cost of body fat percentage measurement. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0035] Figure 1 Schematic diagram of the hardware architecture of the body fat percentage measurement device according to an embodiment of the present invention;

[0036] Figure 2 Flow chart of the first embodiment of the method for measuring body fat percentage according to the present invention;

[0037] Figure 3 Reference diagram of the first embodiment of the method for measuring body fat percentage according to the present invention;

[0038] Figure 4 Reference diagram of the first embodiment of the method for measuring body fat percentage according to the present invention;

[0039] Figure 5 Flow chart of the second embodiment of the method for measuring body fat percentage according to the present invention;

[0040] Figure 6 Reference diagram of the second embodiment of the method for measuring body fat percentage according to the present invention;

[0041] Figure 7 Reference diagram of the second embodiment of the method for measuring body fat percentage according to the present invention;

[0042] Figure 8 Reference diagram of the second embodiment of the method for measuring body fat percentage according to the present invention;

[0043] Figure 9 Flow chart of the third embodiment of the method for measuring body fat percentage according to the present invention. Detailed implementation

[0044] In order to better understand the above technical solutions, the exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0045] The main solution of the present invention is that when the body fat percentage measurement device receives a measurement instruction, it acquires the first body data corresponding to the target object, and the first body data includes preset height, age, gender, and body posture label; measures the second body data of the target object, and the second body data includes weight and lower limb impedance data; determines the body fat percentage corresponding to the target object according to the first body data and the second body data.

[0046] Since the body fat percentage measurement device combines the preset first body data with the actually measured second body data to measure the body fat percentage, during the measurement process, the target object only needs to cooperate with the measurement of part of the second body data. Compared with the conventional technical means that require expensive equipment to obtain all the data for measurement, the present invention reduces the cost of body fat percentage measurement.

[0047] As an implementation, the body fat percentage measurement device can be as Figure 1 .

[0048] The solution of the embodiment of the present invention relates to a body fat percentage measurement device, which includes: a processor 101, such as a CPU, a memory 102, and a communication bus 103. Among them, the communication bus 103 is used to realize the connection and communication between these components.

[0049] The memory 102 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. As Figure 1 , the memory 102, as a computer-readable storage medium, may include a detection program; and the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0050] When receiving a measurement instruction, obtain the first body data corresponding to the target object, where the first body data includes the preset height, age, gender, and body posture label;

[0051] Measure the second body data of the target object, where the second body data includes weight and lower limb impedance data;

[0052] Determine the body fat percentage corresponding to the target object according to the first body data and the second body data.

[0053] In an embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0054] Use the first body data and the second body data as input parameters of a pre-trained body fat percentage measurement model, where the body fat percentage measurement model outputs the body fat percentage according to the first body data and the second body data.

[0055] In an embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0056] Obtain a training set and a test set. The training set and the test set include an input set and an output set. The characteristic attributes of the input set include lower limb impedance, weight, height, age, gender, and body posture label. The characteristic attribute of the output set includes body fat percentage;

[0057] Perform model training based on the training set and the test set to obtain the body fat percentage measurement model.

[0058] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0059] Obtain the body data samples of multiple pre-collected users. The characteristic attributes of the body data samples include lower limb impedance, weight, height, age, gender, and body fat percentage;

[0060] Mark the body data samples so that the body data samples correspond to body posture label attributes;

[0061] Divide each of the body data samples marked with body posture label attributes into the training set and the test set.

[0062] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0063] Determine the loss function and substitute the training set into the model for training;

[0064] When the loss value of the loss function converges to the best value, determine that the model training is completed;

[0065] Substitute the test set into the model for testing to obtain the performance metrics of the model;

[0066] Determine whether the performance metrics are greater than or equal to the preset performance metrics;

[0067] When the performance metrics are greater than the preset performance metrics, use the model as the body fat percentage measurement model.

[0068] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0069] When receiving a measurement instruction, obtain the body data associated with the currently logged-in account as the first body data corresponding to the target object.

[0070] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0071] When receiving the measurement instruction, determine whether the target object has logged in;

[0072] When the target object has logged in, perform the step of obtaining the body data associated with the currently logged-in account as the first body data corresponding to the target object;

[0073] When the target object has not logged in, output a prompt message indicating that login is required.

[0074] In one embodiment, the processor 101 may be used to call the detection program stored in the memory 102 and perform the following operations:

[0075] Control the measuring device to measure the lower limb impedance and weight of the target object to obtain the second body data.

[0076] In the technical solution of this embodiment, when the body fat percentage measuring device receives a measurement instruction, it obtains the first body data corresponding to the target object. The first body data includes preset height, age, gender, and body posture label; it measures the second body data of the target object. The second body data includes weight and lower limb impedance data; it determines the body fat percentage corresponding to the target object according to the first body data and the second body data. Since the body fat percentage measuring device combines the preset first body data with the actually measured second body data to measure the body fat percentage, during the measurement process, the target object only needs to cooperate with the measurement of part of the second body data. Compared with the conventional technical means that require expensive equipment to obtain all quantities for measurement, the present invention reduces the cost of body fat percentage measurement.

[0077] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the specification drawings and specific implementation manners.

[0078] Refer to Figure 2 , Figure 2 This is the first embodiment of the method for measuring the body fat percentage of the present invention. The method includes the following steps:

[0079] Step S10, when receiving a measurement instruction, obtain the first body data corresponding to the target object. The first body data includes preset height, age, gender, and body posture label.

[0080] Body fat scales have been widely used in daily life. Users are very concerned about the body fat percentage and other body composition indicators measured and analyzed by them, and regard them as important reference data for adjusting their diet and work and rest. Household body fat scales are often four-electrode body fat scales, which are light, flexible, easy to operate and inexpensive, making them the first choice for users' body fat measurement products. Although there are these advantages, the accuracy of the body fat percentage calculated by its measurement algorithm still has a certain gap compared with the detection results of the industry gold standard DEXA (dual-energy X-ray absorptiometry).

[0081] The body fat percentage refers to the proportion of the weight of fat in the human body in the total body weight, also known as the body fat percentage, which reflects the amount of fat in the human body. The body fat percentages of normal adults are 15% - 18% for men and 25% - 28% for women respectively. The body fat percentage should be kept within the normal range. If the body fat percentage is too high and the weight exceeds 20% of the normal value, it can be regarded as obesity. Obesity indicates insufficient exercise, overnutrition or certain endocrine system diseases, and often complications such as hypertension, hyperlipidemia, arteriosclerosis, coronary heart disease, diabetes, cholecystitis and other diseases; if the body fat percentage is too low, below the safe lower limit of body fat content, that is, 5% for men and 13% - 15% for women, it may cause dysfunction.

[0082] In this embodiment, the user can input a measurement instruction based on the body fat percentage measurement device. When the body fat percentage material device receives the instruction, it will trigger an operation to obtain the first body data of the target object (user). Among them, the first body data is the body data input by the user when registering the body fat percentage measurement app, and the first body data includes preset height, age, gender and body posture label.

[0083] Optionally, when the body fat percentage measurement device detects the target object, a questionnaire is output on the body fat percentage measurement device for the target user to fill in the above first identity data.

[0084] Optionally, obtain the image information of the target object, use image recognition technology to identify the body shape of the target object, judge the body posture, and obtain the body posture label in the above first identity data.

[0085] Optionally, prompt the user to input body circumference information and convert it into user body posture information using a preset formula.

[0086] Step S20, measure the second body data of the target object, where the second body data includes weight and lower limb impedance data.

[0087] In this embodiment, after obtaining the first body data, the body fat percentage measurement device will measure the second body data of the target object, where the second body data includes but is not limited to data with frequent changes such as lower limb impedance and weight.

[0088] Optionally, the control measurement device measures the lower limb impedance and weight of the target object to obtain the second body data.

[0089] Step S30: Determine the body fat percentage corresponding to the target object according to the first body data and the second body data.

[0090] In this embodiment, compared with the body fat calculation results of the ordinary four-electrode BIA algorithm, the BIA algorithm after adding body data (weight, height, age, gender, and body posture) has a significantly reduced body fat calculation error. Taking the high body fat percentage population as an example, through the consistency analysis with the body fat percentage calculation results of the eight-electrode BIA algorithm, it can be seen that the BIA algorithm containing body data (reference Figure 3 ) compared with the BIA algorithm without body data (reference Figure 4 ), the average error is reduced from -1.5 to -0.36, and the maximum absolute value of the consistency limit is reduced from 3.08 to 1.80, with obvious improvement in accuracy and being clinically acceptable. The method for measuring the body fat percentage of the present invention does not require improvement of the device hardware, and only needs to obtain the preset first body data and the measured second body data.

[0091] Optionally, in this embodiment, an eight-electrode body fat scale with measurement results data similar to DEXA is used for data acquisition, which is convenient to operate and can obtain a large amount of data at low cost.

[0092] In the technical solution of this embodiment, since the body fat percentage measurement device combines the preset first body data with the actually measured second body data to measure the body fat percentage, during the measurement process, the target object only needs to cooperate to measure part of the second body data. Compared with the conventional technical means that require using expensive equipment to obtain all quantity for measurement, the present invention reduces the cost of body fat percentage measurement.

[0093] Refer to Figure 5 , Figure 5 For the second embodiment of the method for measuring the body fat percentage of the present invention, based on the first embodiment, step S30 includes:

[0094] Step S31: Use the first body data and the second body data as input parameters of a pre-trained body fat percentage measurement model, where the body fat percentage measurement model outputs the body fat percentage according to the first body data and the second body data.

[0095] In this embodiment, the body fat percentage measurement model is a neural network model. A neural network (NN) is a complex network system formed by widely connecting a large number of simple processing units (called neurons). It reflects many basic characteristics of the human brain function and is a highly complex non-linear dynamic learning system. A neural network has the capabilities of large-scale parallelism, distributed storage and processing, self-organization, self-adaptation, and self-learning. It is particularly suitable for processing imprecise and fuzzy information processing problems that require considering many factors and conditions simultaneously. The basis of a neural network lies in neurons. A neuron is a biological model based on nerve cells in the biological nervous system. When people study the biological nervous system to explore the mechanism of artificial intelligence, the neuron is mathematized, thus generating a mathematical model of the neuron. A large number of neurons with the same form are connected together to form a neural network. A neural network is a highly non-linear dynamic system. Although the structure and function of each neuron are not complex, the dynamic behavior of the neural network is very complex. Therefore, various phenomena in the actual physical world can be expressed using a neural network. The neural network model is described based on the mathematical model of the neuron.

[0096] In this embodiment, the first body data including the height, age, gender, and body posture label corresponding to the target object and the second body data including the weight and lower limb impedance of the target object are input into the body fat percentage measurement model to obtain the body fat percentage output by the body fat percentage measurement model.

[0097] With the development of impedance measurement technology and BIA algorithms over the years, the eight-electrode body fat algorithm can already achieve results close to those of DEXA in body fat percentage measurement. The maximum absolute value of the consistency limit between the two is 1.41 (reference Figure 6 ), and this difference amplitude is clinically acceptable. Considering the data correlation and data acquisition cost, the measurement results of an eight-electrode body fat scale are used as the standard output in this algorithm solution, and the data required for fitting will also be provided by the eight-electrode body fat scale. By pre-learning and fitting the measurement data of various body posture groups, a fitting algorithm model that can adapt to various body posture groups is obtained. Then, a body posture discrimination method is used to discriminate the body posture of the user. Finally, the height, age, gender, body posture, weight, and lower limb impedance data of the user are input into the model for data calculation.

[0098] Specifically, in this embodiment, the steps of model training are as follows:

[0099] Step 1: Obtain a training set and a test set, wherein the training set and the test set include an input set and an output set, wherein the characteristic attributes of the input set include lower limb impedance, weight, height, age, gender, and body shape label, and the characteristic attributes of the output set include body fat percentage; perform model training according to the training set and the test set to obtain the body fat percentage measurement model. Specifically, collect a large number of body data samples measured by an eight-electrode body fat scale, statistically analyze the body fat distribution of each body data sample, and classify the body shape of the population according to the measurement results of lower limb impedance, weight, height, age, gender, body fat percentage, and body shape label attributes.

[0100] Optionally, obtain a large number of body data samples of multiple users pre-collected by an eight-electrode body fat scale, wherein the characteristic attributes of the body data samples include lower limb impedance, weight, height, age, gender and body fat percentage; label the body data samples so that the body data samples correspond to body posture label attributes; and divide each of the body data samples labeled with the body posture label attributes into the training set and the test set.

[0101] Optionally, the training process of the body fat percentage measurement model includes: determining a loss function, and substituting the training set into the model for training; when the loss value of the loss function converges to an optimal value, determining that the model training is completed; substituting the test set into the model for testing to obtain a performance index of the model; determining whether the performance index is greater than or equal to a preset performance index; when the performance index is greater than the preset performance index, using the model as the body fat percentage measurement model.

[0102] Specifically, the body type category needs to have a meaning that can be understood in a popular way and can effectively distinguish the measurement data, including the following steps:

[0103] Step 1.1, divide the body fat percentage attribute in the body data sample into multiple small intervals, and count the height attribute, weight attribute, gender attribute, and age attribute distribution of the body data sample corresponding to each small interval, and each attribute is also divided into intervals.

[0104] Step 1.2: According to the large intervals of body shape separation rules in step 1.1, set body shape labels for each interval, such as: slim, normal, strong, obese...

[0105] Step 2: Collect the four-electrode body fat scale measurement data corresponding to each label category, fit the eight-electrode body fat scale algorithm results, and obtain a fitting algorithm model containing body shape attributes. Specifically, the difference in human body impedance obtained by the four-electrode body fat scale and the eight-electrode body fat scale is as follows:

[0106] The four-electrode body fat scale can only measure the impedance of the target subject's lower limbs, such as Figure 7 shown.

[0107] In addition to measuring the lower limb impedance of the target object, the eight-electrode body fat scale can also measure the upper limb impedance of the target object, such as Figure 8 shown.

[0108] The reason why the four-electrode algorithm is different from the eight-electrode algorithm is that the four-electrode algorithm lacks the input of upper limb impedance and trunk impedance data, so it cannot well fit the output result of the eight-electrode algorithm. Finally, the calculated body fat percentage of the whole body will tend to be the lower limb body fat percentage. The body fat distribution of people with different body postures is different. Therefore, if the body posture attribute is added to the fitting parameters, the algorithm can automatically optimize the calculation result of the overall body fat percentage of the target object. The specific steps are as follows:

[0109] Step 2.1: Use the eight-electrode body fat scale to collect a large number of body data samples of users, and at the same time label these body data samples with body posture tags (data cleaning). Since the body data samples measured by the eight-electrode body fat scale include body weight and lower limb impedance, there is no need to collect the measurement data of the four-electrode body fat scale of users separately. If there is an obvious difference in the lower limb impedance measurement between the actual four-electrode body fat scale and the eight-electrode body fat scale, the lower limb impedance data of the four-electrode body fat scale needs to be collected separately and the impedance data of the four-electrode body fat scale shall prevail.

[0110] Step 2.2: Then convert the body posture tags into body posture attribute parameters in one-hot encoding format. The conversion rules are shown in the following examples:

[0111] Suppose the set body posture tags are: slender, normal, strong, obese... If the current target object's body type evaluation result is: strong. Then the corresponding body posture attribute parameter information of the target object is: slender (corresponding to 0), normal (corresponding to 0), strong (corresponding to 1), obese (corresponding to 0).

[0112] That is, each evaluation result tag is used as an attribute. If it conforms to the attribute, the value is 1; if it does not conform to the attribute, the value is 0. The situation where multiple evaluation result tags can be conformed is allowed.

[0113] Step 2.3: Divide all the marked body data samples into training sets and test sets. Use the lower limb impedance, body weight, height, age, gender, and body posture fields of the training set as input parameters. Among them, the lower limb impedance can be multiple impedance data measured at different current frequencies, and the body fat percentage is used as the output result for fitting training.

[0114] The formal model fitting and training method can adopt deep learning to construct a multi-layer neural network, use the training set to train the model, and obtain an algorithm model with input parameters of lower limb impedance, weight, height, age, gender, and body posture, and the output result being the body fat percentage. Even if the definition of the body posture label is not completely accurate, the algorithm model will automatically adjust and allocate weights during the training and learning process to obtain the optimal effect. Finally, use the test set to test the model, verify the actual calculation effect of the model, and obtain the algorithm model.

[0115] Optionally, the specific steps of the method for measuring the body fat percentage of the target object are as follows:

[0116] Step 3.1: Obtain the body posture label of the target object.

[0117] Specifically, the body posture label of the target object needs to be collected before obtaining the user's second body data and used as preset data. The acquisition method is different from the body data samples used in training the model. The specific methods include but are not limited to any of the following:

[0118] Optionally, obtain the image information of the target object, use image recognition technology to recognize the body shape of the target object, judge the body posture, and obtain the body posture label.

[0119] Optionally, prompt the user to input body circumference information in the form of a questionnaire and convert it into the user's body posture label using a preset formula.

[0120] Step 3.2: Calculate and output the body fat percentage of the target object.

[0121] Specifically, the input parameters of the neural network model constructed in Step 2 include lower limb impedance, weight, height, age, gender, and body posture label. Therefore, before using the model, it is necessary to first obtain the lower limb impedance, weight, height, age, gender, and body posture label of the target object. Therefore, in this embodiment, the preset first body data (height, age, gender, and body posture) and the measured second body data (weight and lower limb impedance) are used to measure the body fat percentage. Input the height, age, gender, body posture of the target object, as well as the weight and lower limb impedance data measured by the four-electrode body fat scale into the trained neural network model, and the model calculates and outputs the body fat percentage of the target object.

[0122] In the technical solution of this embodiment, through the trained neural network model, the body fat percentage output by the neural network model can be directly obtained based on the first body data and the second body data, improving the measurement efficiency of the body fat percentage.

[0123] Refer to Figure 9 , Figure 9 For the third embodiment of the method for measuring the body fat percentage of the present invention, based on any of the first to second embodiments, step S10 includes:

[0124] Step S11: When a measurement instruction is received, obtain the body data associated with the currently logged-in account as the first body data corresponding to the target object.

[0125] Optionally, when the measurement instruction is received, determine whether the target object has logged in; when the target object has logged in, execute the step of obtaining the body data associated with the currently logged-in account as the first body data corresponding to the target object; when the target object has not logged in, output a prompt message indicating the need to log in.

[0126] In the technical solution of this embodiment, when the target object has not logged in to the app account, the body fat percentage measurement device cannot obtain the first body data. Therefore, when the instruction is received, first determine whether the target object has logged in, which can prevent the measurement process from getting stuck and improve the stability of body fat percentage measurement.

[0127] To achieve the above object, an embodiment of the present invention further provides a body fat percentage measurement device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements each step of the body fat percentage measurement method as described above.

[0128] To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each step of the body fat percentage measurement method as described above.

[0129] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be implemented in the form of a network configuration product program implemented on one or more computer-usable computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0130] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing body fat percentage measurement devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing body fat percentage measurement devices generate for implementation in the process Figure 1one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0131] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions in the process Figure 1 one or more processes and / or blocks Figure 1 specified in one or more blocks

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions in the process Figure 1 one or more processes and / or blocks Figure 1 specified in one or more blocks

[0133] It should be noted that, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several distinct elements and by means of a suitably programmed computer. In a unit claim listing several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words may be interpreted as names

[0134] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention

[0135] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations

Claims

1. A method for measuring body fat percentage, characterized in that, the method for measuring body fat percentage is used for a four-electrode body fat scale, and the method for measuring body fat percentage includes the following steps: When a measurement instruction is received, determine whether the target object has logged in. When the target object has logged in, obtain the body data associated with the currently logged-in account as the first body data corresponding to the target object. The first body data is the body data input by the user when registering the body fat percentage measurement app, including preset height, age, gender, and body posture label; Measure the second body data of the target object, where the second body data includes weight and lower limb impedance data; Obtain the body data samples of multiple users pre-collected by an eight-electrode body fat scale. The characteristic attributes of the body data samples include lower limb impedance, weight, height, age, gender, and body fat percentage. Mark the body data samples so that the body data samples correspond to body posture label attributes. Among them, divide the body fat percentage attribute in the body data samples into multiple small intervals, count the distribution of height attributes, weight attributes, gender attributes, and age attributes of the body data samples corresponding to each small interval. Each attribute is also divided into intervals, and the intervals divided for each attribute are segmented into regular large intervals by body posture, and body posture labels are set for each large interval; Divide each of the body data samples marked with body posture label attributes into a training set and a test set. The training set and the test set include an input set and an output set. The characteristic attributes of the input set include lower limb impedance, weight, height, age, gender, and body posture label, and the characteristic attribute of the output set includes body fat percentage; Perform model training according to the training set and the test set to obtain a body fat percentage measurement model; Use the first body data and the second body data as input parameters of the pre-trained body fat percentage measurement model. Among them, the body fat percentage measurement model outputs the body fat percentage according to the first body data and the second body data.

2. The method for measuring body fat percentage according to claim 1, characterized in that, the step of performing model training according to the training set and the test set includes: Determine a loss function and substitute the training set into the model for training; When the loss value of the loss function converges to the best value, determine that the model training is completed; Substitute the test set into the model for testing to obtain the performance index of the model; Determine whether the performance index is greater than or equal to a preset performance index; When the performance index is greater than the preset performance index, use the model as the body fat percentage measurement model.

3. The method for measuring body fat percentage according to claim 1, characterized in that, after the step of obtaining the body data associated with the currently logged-in account as the first body data corresponding to the target object when the target object has logged in, it includes: When the target object has not logged in, output a prompt message to log in.

4. The method for measuring body fat percentage according to claim 1, characterized in that, the step of measuring the second body data of the target object includes: Control the four-electrode body fat scale to measure the lower limb impedance and body weight of the target object, and obtain the second body data.

5. A body fat percentage measurement device, characterized in that, the body fat percentage measurement device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, it implements the body fat percentage measurement method according to any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the body fat percentage measurement method according to any one of claims 1 to 4.

Images