Body fat percentage measuring method and device, electronic equipment and computer program product

Abstract

The invention discloses a body fat percentage measurement method and device, electronic equipment and a computer program product, and relates to the technical field of body fat measurement. Obtaining an initial training sample set; performing data enhancement on training samples in the initial training sample set to obtain an enhanced data set; performing data cutting on training samples in the enhanced data set; combining the initial training sample set with the clipped enhanced data set to obtain a combined training sample set; taking the human body feature measurement data corresponding to the training samples in the combined training sample set as sample input, taking the body fat percentage corresponding to the training samples as sample output for training, and obtaining a body fat percentage prediction model; and taking the human body characteristic measurement data of the user to be detected as the input of the body fat percentage prediction model for operation to obtain the body fat percentage of the user to be detected. According to the method, the device, the electronic equipment and the computer program product disclosed by the invention, the body fat percentage measurement accuracy can be improved under the condition of limited sample data.

Description

Technical Field

[0001] The present invention belongs to the technical field of body fat measurement, and specifically relates to a body fat percentage measurement method, device, electronic equipment and computer program product. Background Art

[0002] Body fat percentage (BFP) is an important indicator to measure the proportion of body fat to total body weight. It can more accurately reflect health and nutritional status than body mass index. BFP is not only closely related to bone health and cardiovascular metabolic risks, but can also effectively evaluate the effects of exercise and nutritional interventions. Therefore, its accurate measurement is crucial for health assessment and guidance of interventions.

[0003] With the development of computer technology, indirect prediction methods based on machine learning are increasingly widely used in BFP measurement. The diversity of their methods enables them to show different applicability and accuracy in different scenarios. However, machine learning methods require sufficient sample size to obtain accurate and reliable results. Insufficient sample size may lead to performance estimation bias and overfitting, reduce the possibility of capturing the true effect, and lead to poor accuracy of BFP measurement.

[0004] Therefore, how to provide an effective solution to improve the accuracy of BFP measurement when sample data is limited has become a difficult problem to be solved in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a body fat percentage measurement method, device, electronic equipment and computer program product to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for measuring body fat percentage, comprising:

[0008] Acquire an initial training sample set, wherein the training samples in the initial training sample set include body fat percentage of the sample user and human body characteristic measurement data of the sample user associated with the body fat percentage;

[0009] Performing data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set;

[0010] Perform data trimming on the training samples in the enhanced data set to obtain a trimmed enhanced data set;

[0011] Merging the initial training sample set with the cropped enhanced data set to obtain a merged training sample set;

[0012] The human body characteristic measurement data corresponding to each training sample in the combined training sample set is used as a sample input of the body fat percentage prediction model, and the body fat percentage corresponding to each training sample is used as a sample output of the body fat percentage prediction model for training to obtain a trained body fat percentage prediction model;

[0013] The human body characteristic measurement data of the user to be tested is used as the input of the trained body fat percentage prediction model to perform calculations to obtain the body fat percentage of the user to be tested.

[0014] Based on the above disclosed content, the present invention obtains an initial training sample set, wherein the training samples in the initial training sample set include the body fat percentage of the sample user and the human feature measurement data of the sample user and associated with the body fat percentage; performs data enhancement on the training samples in the initial training sample set through a sample enhancement model to obtain an enhanced data set; performs data cropping on the training samples in the enhanced data set to obtain a cropped enhanced data set; merges the initial training sample set with the cropped enhanced data set to obtain a merged training sample set; uses the human feature measurement data corresponding to each training sample in the merged training sample set as the sample input of the body fat percentage prediction model, and uses the body fat percentage corresponding to each training sample as the sample output of the body fat percentage prediction model for training to obtain a trained body fat percentage prediction model; uses the human feature measurement data of the user to be tested as the input of the trained body fat percentage prediction model for calculation to obtain the body fat percentage of the user to be tested. In this way, when training the model, the training samples can be enhanced and the number of samples can be expanded. At the same time, the training samples in the enhanced data set can be pruned to ensure that the values ​​corresponding to the expanded samples are within a reasonable range, thereby ensuring the authenticity and validity of the expanded samples. This allows effective modeling when samples are limited, significantly reducing the cost and resource consumption in the BFP measurement process, avoiding prediction model performance estimation bias and overfitting due to insufficient sample size, and improving the accuracy and robustness of BFP measurements.

[0015] In a possible design, the data clipping of the training samples in the enhanced data set to obtain the clipped enhanced data set includes:

[0016] Based on the value ranges of various data corresponding to the training samples in the initial training sample set, data clipping is performed on the training samples in the enhanced data set to obtain a clipped enhanced data set.

[0017] In a possible design, data clipping is performed on the training samples in the enhanced dataset according to the following formula (1);

[0018] X clipped =np clip(X min ,X max ) (1)

[0019] Among them, X min represents the minimum value of the range of values ​​corresponding to the training samples in the enhanced dataset, X max It represents the maximum value of the range of data corresponding to the training samples in the enhanced data set, and np·clip represents the np·clip function.

[0020] In one possible design, the anthropometric measurement data include age, weight, height, neck circumference, chest circumference, abdominal circumference, hip circumference, thigh circumference, knee circumference, ankle circumference, upper arm circumference, forearm circumference and / or wrist circumference.

[0021] In a possible design, the sample enhancement model is a WGAN-GP model.

[0022] In a possible design, the sample enhancement model includes a generator and a discriminator, and the loss of the generator is The loss and gradient penalty of the discriminator are in Represents the expected distribution of generated data, EMBED Equation.DSMT4 represents the expected distribution of real data, λ represents the gradient penalty coefficient, The gradient of Indicates the degree to which the gradient of the penalized discriminator deviates from 1.

[0023] In one possible design, the body fat percentage prediction model is an XGBooST model.

[0024] In a second aspect, the present invention provides a body fat percentage measuring device, comprising:

[0025] An acquisition unit, configured to acquire an initial training sample set, wherein the training samples in the initial training sample set include a body fat percentage of a sample user and human characteristic measurement data of the sample user associated with the body fat percentage;

[0026] An enhancement unit, used to perform data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set;

[0027] A cropping unit, used for cropping the training samples in the enhanced data set to obtain a cropped enhanced data set;

[0028] A merging unit, used to merge the initial training sample set with the cropped enhanced data set to obtain a merged training sample set;

[0029] A training unit, used to use the human feature measurement data corresponding to each training sample in the combined training sample set as a sample input of a body fat percentage prediction model, and the body fat percentage corresponding to each training sample as a sample output of the body fat percentage prediction model for training, so as to obtain a trained body fat percentage prediction model;

[0030] The computing unit is used to use the human body characteristic measurement data of the user to be tested as the input of the trained body fat percentage prediction model to perform computing to obtain the body fat percentage of the user to be tested.

[0031] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the body fat percentage measurement method as described in the first aspect or any possible design of the first aspect.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the body fat percentage measurement method described in the first aspect or any possible design of the first aspect.

[0033] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the body fat percentage measuring method as described in the first aspect or any possible design of the first aspect.

[0034] Beneficial effects:

[0035] The body fat percentage measurement method, device, electronic device and computer program product provided by the present invention can perform data enhancement on training samples, expand the number of samples, and perform data clipping on the training samples in the enhanced data set to ensure that the numerical values ​​corresponding to the expanded samples are within a reasonable range, thereby ensuring the authenticity and validity of the expanded samples, and can effectively build models when samples are limited, significantly reducing the cost and resource consumption in the BFP measurement process, avoiding prediction model performance estimation bias and overfitting due to insufficient sample size, improving the accuracy and robustness of BFP measurement, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flow chart of a method for measuring body fat percentage provided in an embodiment of the present application;

[0037] Figure 2 A schematic block diagram of a body fat percentage measurement device provided in an embodiment of the present application;

[0038] Figure 3A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0040] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0041] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0042] In order to improve the accuracy of BFP measurement, the embodiments of the present application provide a body fat percentage measurement method, device, electronic device and computer program product, which can improve the accuracy of BFP measurement when sample data is limited.

[0043] The body fat percentage measurement method provided in the embodiment of the present application can be applied to a user terminal or a server. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0044] The body fat percentage measurement method provided in the embodiments of the present application will be described in detail below.

[0045] like Figure 1 As shown, it is a flow chart of the body fat percentage measurement method provided in the first aspect of the embodiment of the present application. The body fat percentage measurement method may include but is not limited to the following steps S101-S106.

[0046] Step S101: Acquire an initial training sample set, where the training samples in the initial training sample set include the body fat percentage of the sample user and human characteristic measurement data of the sample user associated with the body fat percentage.

[0047] Before measuring the user's body fat percentage, a large number of training samples need to be obtained for training the body fat percentage prediction model. In the embodiment of the present application, the set of all the acquired training samples is called the initial training sample set.

[0048] The training samples in the initial training sample set include the body fat percentage BFP of the sample user and the human characteristic measurement data of the sample user and associated with the body fat percentage. The human characteristic measurement data may include but is not limited to age, weight, height, neck circumference, chest circumference, abdominal circumference, hip circumference, thigh circumference, knee circumference, ankle circumference, upper arm circumference, forearm circumference and / or wrist circumference. In an embodiment of the present application, the human characteristic measurement data include age, weight, height, neck circumference, chest circumference, abdominal circumference, hip circumference, thigh circumference, knee circumference, ankle circumference, upper arm circumference, forearm circumference and wrist circumference, where the unit of weight can be kg, and the unit of height, neck circumference, chest circumference, abdominal circumference, hip circumference, thigh circumference, knee circumference, ankle circumference, upper arm circumference, forearm circumference and wrist circumference can be cm.

[0049] The body fat percentage of the sample user can be measured by, but is not limited to, dual-energy X-ray absorptiometry, underwater weighing, or bioelectrical impedance analysis. In the embodiment of the present application, the body fat percentage of the sample user can be measured by dual-energy X-ray absorptiometry.

[0050] Step S102: Perform data enhancement on the training samples in the initial training sample set using a sample enhancement model to obtain an enhanced data set.

[0051] Among them, the sample enhancement model can be but is not limited to a generative adversarial network (GAN) model or a WGAN-CP (Wasserstein GAN using Weight Clipping) model. In an embodiment of the present application, the sample enhancement model is a WGAN-CP model.

[0052] When performing data enhancement on the training samples in the initial training sample set through the sample enhancement model, the eigenvalues ​​in the training samples may be standardized first, that is, for each eigenvalue in the training sample, the mean of the eigenvalue of that class is subtracted and divided by the standard deviation of the eigenvalue of that class.

[0053] The sample enhancement model includes a generator and a discriminator. In one or more embodiments, the generator and discriminator networks are composed of fully connected layers and ReLU activation functions. The potential dimension can be set to 100. The discriminator can be updated 5 times each time the generator is updated. The model can be trained for 2000 epochs. During the training process, the generator and the discriminator can be optimized using the RMSprop optimizer, and the learning rate can be set to 0.00005.

[0054] In one or more embodiments, the generator's loss can be The loss and gradient penalty of the discriminator can be in represents the expected distribution of generated data, represents the expected distribution of real data, λ represents the gradient penalty coefficient, represents the gradient of the discriminator, It indicates that the degree to which the discriminator gradient deviates from 1 is penalized to ensure that Lipschitz continuity is satisfied.

[0055] After training is completed, new samples can be generated by inputting random noise into the trained generator. These samples can be converted back to the original data scale using the mean and standard deviation of the original data set to obtain new sample data. The collection of all new sample data can be called an enhanced data set.

[0056] Step S103: Perform data cropping on the training samples in the enhanced data set to obtain a cropped enhanced data set.

[0057] Specifically, based on the value ranges of various data corresponding to the training samples in the initial training sample set, data clipping may be performed on the training samples in the enhanced data set to obtain a clipped enhanced data set.

[0058] In one or more embodiments, data pruning may be performed on training samples in the enhanced data set according to the following formula (1).

[0059] X clipped =np clip(X min ,X max ) (1)

[0060] Among them, X clipped represents the sample data after clipping, X min represents the minimum value of the range of values ​​corresponding to the training samples in the enhanced dataset, X maxrepresents the maximum value of the value range of the data corresponding to the training sample in the enhanced data set, and np·clip represents the np·clip function. It can be understood that if the training sample includes feature data of multiple dimensions, the np·clip function can be used to perform data clipping on the feature data of each dimension in the training sample.

[0061] Step S104: Merge the initial training sample set with the cropped enhanced data set to obtain a merged training sample set.

[0062] Step S105. Use the human feature measurement data corresponding to each training sample in the combined training sample set as the sample input of the body fat percentage prediction model, and use the body fat percentage corresponding to each training sample as the sample output of the body fat percentage prediction model for training to obtain a trained body fat percentage prediction model.

[0063] Among them, the body fat percentage prediction model can be but is not limited to an XGBooST (Extreme GradientBoosting) model, a gradient boosted tree (Gradient Boosted Decision Trees, GBDT) model, etc. In the embodiment of the present application, the body fat percentage prediction model is an XGBooST model.

[0064] In order to determine the optimal parameters of the XGBoost model, K-fold cross validation can be used to evaluate the model during the training process to ensure the robustness of the performance evaluation. For each fold in the K-fold cross validation, the combined training sample set is divided into K subsets. During the training process, the root mean square error (RMSE) can be used as an evaluation indicator, and the damage of training and testing is recorded. The performance indicators of each fold, such as the mean square error (MSE) and the coefficient of determination (R-squared, R 2 ) and report the average performance of all folds.

[0065] Step S106: using the human body characteristic measurement data of the user to be tested as the input of the trained body fat percentage prediction model to perform calculations to obtain the body fat percentage of the user to be tested.

[0066] The body fat percentage measurement method provided by the present invention comprises the following steps: obtaining an initial training sample set, wherein the training samples in the initial training sample set include the body fat percentage of a sample user and human characteristic measurement data of the sample user and associated with the body fat percentage; performing data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set; performing data cropping on the training samples in the enhanced data set to obtain a cropped enhanced data set; merging the initial training sample set with the cropped enhanced data set to obtain a merged training sample set; using the human characteristic measurement data corresponding to each training sample in the merged training sample set as a sample input of a body fat percentage prediction model, and using the body fat percentage corresponding to each training sample as a sample output of the body fat percentage prediction model for training to obtain a trained body fat percentage prediction model; using the human characteristic measurement data of a user to be measured as an input of the trained body fat percentage prediction model for calculation to obtain the body fat percentage of the user to be measured. In this way, when training the model, data enhancement can be performed on the training samples, the number of samples can be expanded, and data clipping can be performed on the training samples in the enhanced data set to ensure that the values ​​corresponding to the expanded samples are within a reasonable range, to ensure the authenticity and validity of the expanded samples, and to be able to effectively model with limited samples, reduce the need for a large amount of experimental data, save the cost of data collection and processing, and significantly reduce the cost and resource consumption in the BFP measurement process, avoid bias and overfitting of the prediction model performance estimation due to insufficient sample size, and improve the accuracy and robustness of BFP measurement. In addition, the body fat percentage measurement method provided in this application simplifies the process of body fat percentage measurement, improves measurement efficiency, and makes it more suitable for practical applications.

[0067] See also Figure 2 The embodiment of the present application provides a body fat percentage measuring device, the body fat percentage measuring device comprising:

[0068] An acquisition unit, configured to acquire an initial training sample set, wherein the training samples in the initial training sample set include a body fat percentage of a sample user and human characteristic measurement data of the sample user associated with the body fat percentage;

[0069] An enhancement unit, used to perform data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set;

[0070] A cropping unit, used for cropping the training samples in the enhanced data set to obtain a cropped enhanced data set;

[0071] A merging unit, used to merge the initial training sample set with the cropped enhanced data set to obtain a merged training sample set;

[0072] A training unit, used to use the human feature measurement data corresponding to each training sample in the combined training sample set as a sample input of a body fat percentage prediction model, and the body fat percentage corresponding to each training sample as a sample output of the body fat percentage prediction model for training, so as to obtain a trained body fat percentage prediction model;

[0073] The computing unit is used to use the human body characteristic measurement data of the user to be tested as the input of the trained body fat percentage prediction model to perform computing to obtain the body fat percentage of the user to be tested.

[0074] The working process, working details and technical effects of the body fat percentage measuring device provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0075] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the body fat percentage measurement method as described in the first aspect of the embodiment.

[0076] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0077] In a fourth aspect of the present embodiment, there is provided a computer-readable storage medium storing instructions for the body fat percentage measurement method described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the body fat percentage measurement method described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, a CD, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0078] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the body fat percentage measurement method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0079] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0080] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for measuring body fat percentage, characterized in that: include: Acquire an initial training sample set, wherein the training samples in the initial training sample set include body fat percentage of the sample user and human body characteristic measurement data of the sample user associated with the body fat percentage; Performing data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set; Perform data trimming on the training samples in the enhanced data set to obtain a trimmed enhanced data set; Merging the initial training sample set with the cropped enhanced data set to obtain a merged training sample set; The human body characteristic measurement data corresponding to each training sample in the combined training sample set is used as a sample input of the body fat percentage prediction model, and the body fat percentage corresponding to each training sample is used as a sample output of the body fat percentage prediction model for training to obtain a trained body fat percentage prediction model; The human body characteristic measurement data of the user to be tested is used as the input of the trained body fat percentage prediction model to perform calculations to obtain the body fat percentage of the user to be tested.

2. The method for measuring body fat percentage according to claim 1, characterized in that: The step of performing data clipping on the training samples in the enhanced data set to obtain a clipped enhanced data set includes: Based on the value ranges of various data corresponding to the training samples in the initial training sample set, data clipping is performed on the training samples in the enhanced data set to obtain a clipped enhanced data set.

3. The method for measuring body fat percentage according to claim 2, characterized in that: According to the following formula (1), the training samples in the enhanced data set are trimmed; X clipped =np·clip(X min ,X max ) (1) Among them, X min represents the minimum value of the range of values ​​corresponding to the training samples in the enhanced dataset, X max It represents the maximum value of the range of data corresponding to the training samples in the enhanced dataset, and np@clip represents the np clip function.

4. The method for measuring body fat percentage according to claim 1, characterized in that: The human body characteristic measurement data includes age, weight, height, neck circumference, chest circumference, abdominal circumference, hip circumference, thigh circumference, knee circumference, ankle circumference, upper arm circumference, forearm circumference and / or wrist circumference.

5. The method for measuring body fat percentage according to claim 1, characterized in that: The sample enhancement model is the WGAN-GP model.

6. The method for measuring body fat percentage according to claim 5, characterized in that: The sample enhancement model includes a generator and a discriminator, and the loss of the generator is The loss and gradient penalty of the discriminator are in Represents the expected distribution of generated data, EMBED Equation.DSMT4 represents the expected distribution of real data, λ represents the gradient penalty coefficient, The gradient of Indicates the degree to which the gradient of the penalized discriminator deviates from 1.

7. The method for measuring body fat percentage according to claim 1, characterized in that: The body fat percentage prediction model is the XGBooST model.

8. A body fat percentage measuring device, characterized in that: include: An acquisition unit, configured to acquire an initial training sample set, wherein the training samples in the initial training sample set include a body fat percentage of a sample user and human characteristic measurement data of the sample user associated with the body fat percentage; An enhancement unit, used to perform data enhancement on the training samples in the initial training sample set by using a sample enhancement model to obtain an enhanced data set; A cropping unit, used for cropping the training samples in the enhanced data set to obtain a cropped enhanced data set; A merging unit, used to merge the initial training sample set with the cropped enhanced data set to obtain a merged training sample set; A training unit, used to use the human feature measurement data corresponding to each training sample in the combined training sample set as a sample input of a body fat percentage prediction model, and the body fat percentage corresponding to each training sample as a sample output of the body fat percentage prediction model for training, so as to obtain a trained body fat percentage prediction model; The computing unit is used to use the human body characteristic measurement data of the user to be tested as the input of the trained body fat percentage prediction model to perform computing to obtain the body fat percentage of the user to be tested.

9. An electronic device, characterized in that: It comprises a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the body fat percentage measurement method as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the body fat percentage measuring method according to any one of claims 1 to 7 is implemented.

Images