Physiological parameter measurement method, system, and electronic device

Abstract

The application provides a physiological parameter measurement method, system and electronic device. The method comprises: determining a first body parameter and a second body parameter of a person to be measured, the first body parameter and the second body parameter being measured by a first electronic device, the second body parameter being measured based on at least 8 electrodes possessed by the first electronic device; determining a third body parameter in response to an input of the person to be measured; determining a fourth body parameter according to the first body parameter and the third body parameter; determining a first body shape of the person to be measured according to the second body parameter; determining a first physiological parameter according to at least the first body shape and the fourth body parameter; and displaying the first physiological parameter. Thus, the body shape of the person to be measured is determined by the body parameters measured by the electronic device, and the physiological parameter of the person to be measured is determined by combining the body shape, the body parameters measured by the electronic device and the body parameters determined based on the user input, so that the physiological parameter of the person to be measured is accurately measured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal, and in particular, to a physiological parameter measurement method, system and electronic device. BACKGROUND

[0002] With the continuous improvement of living standards, fatty liver gradually becomes the first liver disease of human, and the prevalence rate shows a gradually increasing trend. Among them, the formation of fatty liver is mainly due to excessive accumulation of fat in liver cells, which leads to liver lesions. Generally speaking, if the liver fat exceeds 5% of the liver weight or more than 50% of the liver cells have fatty degeneration histologically, it can be called fatty liver, so liver fat is an important feature of detecting fatty liver.

[0003] In related technologies, in addition to the complex abdominal B-ultrasound fatty liver screening method in medical operation, we can also screen fatty liver through body mass index (BMI) and body fat ratio (BFR) in daily life. Among them, when screening fatty liver, the liver fat grade can be evaluated according to the set BMI and body fat ratio threshold. However, according to medical research, even if two people have the same body fat ratio, their fatty liver risk levels are not the same. In addition, "BMI" cannot accurately reflect a person's obesity. That is to say, it is difficult to accurately evaluate the liver fat grade by simply using BMI and body fat ratio. Therefore, how to enable users to conveniently and accurately obtain their own liver fat grade is a technical problem to be solved at present. SUMMARY

[0004] The embodiments of the present application provide a physiological parameter measurement method, system and electronic device, which can enable users to conveniently and accurately measure their own physiological parameters.

[0005] In a first aspect, the embodiments of the present application provide a physiological parameter measurement method, which comprises: determining a first body parameter and a second body parameter of a person to be measured, the first body parameter and the second body parameter being measured by a first electronic device, the second body parameter being measured based on at least 8 electrodes possessed by the first electronic device; determining a third body parameter in response to an input of the person to be measured; determining a fourth body parameter according to the first body parameter and the third body parameter; determining a first body shape of the person to be measured according to the second body parameter; determining a first physiological parameter according to at least the first body shape and the fourth body parameter; and displaying the first physiological parameter. Exemplarily, the first body parameter can be body weight, the second body parameter can be body impedance or raw data (such as voltage, current, etc.) required for calculating body impedance, the third body parameter can be height, the fourth body parameter can be body mass index (BMI), and the first physiological parameter can be liver fat level. In an example, the body impedance can include impedance related to both arms, impedance related to both legs, and impedance related to the torso. Exemplarily, the impedance related to both arms can include impedance of both arms, impedance of the left arm, or impedance of the right arm, etc., the impedance related to both legs can include impedance of both legs, impedance of the left leg, or impedance of the right leg, etc., and the impedance related to the torso can include impedance of the torso or other impedance containing the impedance of the torso, etc.

[0006] In this way, the body shape of the person to be measured is determined according to the first body parameter measured by the first electronic device, and the physiological parameter of the person to be measured is determined by combining the body shape, the first body parameter measured by the first electronic device, and the third body parameter determined based on the user input, so that the physiological parameter of the person to be measured is accurately measured.

[0007] In a possible implementation, the first body shape of the person to be measured is determined according to the second body parameter, specifically comprising: determining a fifth body parameter according to the second body parameter; if the fifth body parameter belongs to a first interval, determining the first body shape of the person to be measured according to the fourth body parameter; and if the fifth body parameter belongs to a second interval, determining the first body shape of the person to be measured according to a sixth body parameter, wherein the sixth body parameter is obtained based on the second body parameter. Exemplarily, the fifth body parameter can be waist-hip ratio, and the sixth body parameter can be muscle mass or fat mass of both arms of the person to be measured, etc. In this way, after the fifth body parameter is determined based on the second body parameter, the body shape of the person to be measured can be determined based on the interval range to which the fifth body parameter belongs, so as to improve the accuracy of determining the body shape.

[0008] In a possible implementation, the fifth body parameter is determined according to the second body parameter, specifically comprising: determining a seventh body parameter according to the second body parameter, and determining the fifth body parameter according to the seventh body parameter. For example, the seventh body parameter can be the fat amount of each segment of the body, such as the fat amount of the left arm, the fat amount of the right arm, the fat amount of the trunk, the fat amount of the left leg, or the fat amount of the right leg, and the like. Thus, the fifth body parameter is obtained from the second body parameter.

[0009] In a possible implementation, the first physiological parameter is determined according to at least the first body shape and the fourth body parameter, specifically comprising: querying a predetermined correspondence between a body shape and a detection model according to the first body shape to determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the correspondence; and inputting at least the fourth body parameter into the detection model corresponding to the first body shape to determine the first physiological parameter. Thus, the detection model suitable for the body shape of the to-be-measured person is determined based on the body shape of the to-be-measured person, and then the physiological parameter of the to-be-measured person is detected by using the detection model, so that different detection models are used to detect the physiological parameter of the user with different body shapes, and the accuracy of the physiological parameter is improved.

[0010] In a possible implementation, after the first physiological parameter is displayed, the method further comprises: determining a first photo and a second photo of the to-be-measured person in response to a first operation of the to-be-measured person, the first photo being taken when the to-be-measured person performs a first preset action, and the second photo being taken when the to-be-measured person performs a second preset action; determining an eighth body parameter of the to-be-measured person according to the first photo and the second photo; re-determining the first physiological parameter according to at least the first body shape, the fourth body parameter, and the eighth body parameter; and displaying the first physiological parameter. For example, the eighth body parameter can be the waist circumference. Thus, the body parameter that is strongly related to the physiological parameter of the to-be-measured person is determined by using the photo of the to-be-measured person, and the physiological parameter of the to-be-measured person is accurately measured by using the body parameter, so that the detection accuracy of the physiological parameter is improved.

[0011] In a possible implementation, the second physiological parameter is determined according to at least the first body shape, the fourth body parameter, and the eighth body parameter, specifically comprising: querying a predetermined correspondence between a body shape and a detection model according to the first body shape to determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the second correspondence; and inputting at least the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape to re-determine the first physiological parameter. Thus, the accuracy of the physiological parameter detection is improved.

[0012] In a possible implementation, before the fourth body parameter and the eighth body parameter are input to the detection model corresponding to the first body shape, the method further includes: determining a ninth body parameter of the to-be-tested person according to the first photo and the second photo; and determining a second body shape of the to-be-tested person according to the eighth body parameter and the ninth body parameter. For example, the ninth body parameter can be a hip circumference. Because the body shape of the to-be-tested person can be accurately presented on the photo, the body shape of the to-be-tested person can be accurately determined through the photo of the to-be-tested person, and the accuracy of the body shape detection is improved.

[0013] In a possible implementation, the method further includes: if the second body shape is inconsistent with the first body shape, querying the corresponding relationship according to the second body shape, determining the detection model corresponding to the second body shape, and selecting the detection model corresponding to the second body shape to redetermine the first physiological parameter. In this way, the body shape of the to-be-tested person detected through the photo is used as a reference, and the physiological parameter of the to-be-tested person is detected, and the accuracy of the physiological parameter detection is improved.

[0014] In a possible implementation, the first photo and the second photo of the to-be-tested person are determined, specifically including: determining an action difference degree between an action of the to-be-tested person on a target photo and a target preset action, and determining that the action difference degree is within a preset range; wherein the target photo is the first photo, and the target preset action is the first preset action, or the target photo is the second photo, and the target preset action is the second preset action. In this way, the photo collected when the to-be-tested person makes the preset action is used for detection, and the accuracy of the physiological parameter detection is improved.

[0015] In a possible implementation, the method further includes: displaying the body shape of the to-be-tested person. In this way, the to-be-tested person can view the body shape of the to-be-tested person.

[0016] In a possible implementation, the second body parameter is measured by the first electronic device controlling at least 8 electrodes to generate at least two different frequency electrical signals. In this way, the second body parameter is measured through the electrical signals of different frequencies, and the accuracy of subsequent detection is improved.

[0017] In a possible implementation, the method is performed by the first electronic device. In this way, the physiological parameter of the to-be-tested person is detected through one device.

[0018] In a possible implementation, the method is performed by the second electronic device, and the second electronic device and the first electronic device are in communication connection. The first body parameter and the second body parameter of the to-be-tested person are determined, specifically including: the second electronic device receives the first body parameter and the second body parameter sent by the first electronic device. In this way, the physiological parameter of the to-be-tested person is detected through multiple electronic devices.

[0019] In a second aspect, the embodiments of the present application provide a physiological parameter measurement system, the system comprising a first electronic device and a second electronic device, the first electronic device and the second electronic device being communicatively connected, the first electronic device having at least eight electrodes;

[0020] The first electronic device is configured to determine a first body parameter and a second body parameter of a person to be measured, and send the first body parameter and the second body parameter to the second electronic device, the second body parameter being measured based on the at least eight electrodes.

[0021] The second electronic device is configured to determine a third body parameter in response to an input of the person to be measured. The second electronic device is further configured to determine a fourth body parameter based on the first body parameter and the third body parameter in response to receiving the first body parameter and the second body parameter. The second electronic device is further configured to determine a first body shape of the person to be measured based on the second body parameter. The second electronic device is further configured to determine a first physiological parameter based on at least the first body shape and the fourth body parameter, and display the first physiological parameter.

[0022] In a possible implementation, the second electronic device is further configured to determine a fifth body parameter based on the second body parameter, determine the first body shape of the person to be measured based on the fourth body parameter if the fifth body parameter belongs to a first interval, and determine the first body shape of the person to be measured based on a sixth body parameter if the fifth body parameter belongs to a second interval, the sixth body parameter being obtained based on the second body parameter.

[0023] In a possible implementation, the second electronic device is further configured to determine a seventh body parameter based on the second body parameter, and determine the fifth body parameter based on the seventh body parameter.

[0024] In a possible implementation, the second electronic device is further configured to query a predetermined correspondence between body shapes and detection models based on the first body shape, determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the correspondence, and input at least the fourth body parameter to the detection model corresponding to the first body shape to determine the first physiological parameter.

[0025] In a possible implementation, after displaying the first physiological parameter, the second electronic device is further configured to: in response to a first operation of the to-be-tested person, determine a first photo and a second photo of the to-be-tested person, the first photo being taken when the to-be-tested person performs a first preset action, and the second photo being taken when the to-be-tested person performs a second preset action; determine an eighth body parameter of the to-be-tested person according to the first photo and the second photo; re-determine the first physiological parameter according to at least the first body shape, the fourth body parameter, and the eighth body parameter; and display the first physiological parameter.

[0026] In a possible implementation, the second electronic device is further configured to: according to the first body shape, query the predetermined correspondence between the body shape and the detection model, and determine the detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the second correspondence; and input at least the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape, to determine the first physiological parameter.

[0027] In a possible implementation, before inputting the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape, the second electronic device is further configured to: determine a ninth body parameter of the to-be-tested person according to the first photo and the second photo; and determine a second body shape of the to-be-tested person according to the eighth body parameter and the ninth body parameter.

[0028] In a possible implementation, the second electronic device is further configured to: if the second body shape is inconsistent with the first body shape, query the correspondence according to the second body shape, determine the detection model corresponding to the second body shape, and select the detection model to determine the first physiological parameter.

[0029] In a possible implementation, the second electronic device is further configured to: determine a degree of action difference between an action of the to-be-tested person in a target photo currently acquired and a target preset action, and determine that the degree of action difference is within a preset range, wherein the target photo is the first photo, and the target preset action is the first preset action, or the target photo is the second photo, and the target preset action is the second preset action.

[0030] In a possible implementation, the second electronic device is further configured to: display the body shape of the to-be-tested person.

[0031] In a possible implementation, the first electronic device is further configured to: control the at least eight electrodes to generate at least two different frequency electrical signals; and determine a second body parameter by determining a body parameter measured based on each frequency electrical signal, respectively.

[0032] In a third aspect, an embodiment of the present application provides a physiological parameter measurement device, characterized in that the device comprises:

[0033] determining a first body parameter and a second body parameter of the to-be-tested person, the first body parameter being measured by the first electronic device, and the second body parameter being measured based on at least eight electrodes possessed by the first electronic device;

[0034] determining a third body parameter in response to an input of the to-be-tested person;

[0035] determining a fourth body parameter according to the first body parameter and the third body parameter;

[0036] determining a first body shape of the to-be-tested person according to the second body parameter;

[0037] determining the first physiological parameter according to at least the first body shape and the fourth body parameter;

[0038] displaying the first physiological parameter.

[0039] In a possible implementation, the processing module is further configured to determine a fifth body parameter according to the second body parameter; and if the fifth body parameter belongs to a first interval, the processing module determines the first body shape of the to-be-tested person according to the fourth body parameter; and if the fifth body parameter belongs to a second interval, the processing module determines the first body shape of the to-be-tested person according to a sixth body parameter, where the sixth body parameter is obtained based on the second body parameter.

[0040] In a possible implementation, the processing module is further configured to determine a seventh body parameter according to the second body parameter, and determine the fifth body parameter according to the seventh body parameter.

[0041] In a possible implementation, the processing module is further configured to query a predetermined correspondence between body shapes and detection models according to the first body shape, to determine a detection model corresponding to the first body shape, where different body shapes correspond to different detection models in the correspondence; and input at least the fourth body parameter into the detection model corresponding to the first body shape, to determine the first physiological parameter.

[0042] In a possible implementation, after the display module displays the first physiological parameter, the processing module is further configured to determine a first photo and a second photo of the to-be-tested person in response to a first operation of the to-be-tested person, the first photo being taken when the to-be-tested person performs a first preset action, and the second photo being taken when the to-be-tested person performs a second preset action; determine an eighth body parameter of the to-be-tested person according to the first photo and the second photo; and re-determine the first physiological parameter according to at least the first body shape, the fourth body parameter, and the eighth body parameter.

[0043] The display module is further configured to display the first physiological parameter.

[0044] 6.The method of claim 5, wherein the processing module is further configured to query a predetermined correspondence between body postures and detection models according to the first body posture, to determine a detection model corresponding to the first body posture, wherein different body postures correspond to different detection models in the second correspondence, and to input at least the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body posture, to redetermine the first physiological parameter.

[0045] In a possible implementation, the processing module is further configured to determine a ninth body parameter of the to-be-tested person according to the first photo and the second photo, and to determine the second body posture of the to-be-tested person according to the eighth body parameter and the ninth body parameter.

[0046] In a possible implementation, when the second body posture is inconsistent with the first body posture, the processing module is configured to query the correspondence according to the second body posture, to determine a detection model corresponding to the second body posture, and to select the detection model corresponding to the second body posture to redetermine the first physiological parameter.

[0047] In a possible implementation, the processing module is further configured to determine a motion difference degree between a motion of the to-be-tested person in the target photo and a target preset motion, and to determine that the motion difference degree is within a preset range.

[0048] In the implementation, the target photo is the first photo, and the target preset motion is the first preset motion, or the target photo is the second photo, and the target preset motion is the second preset motion.

[0049] In a possible implementation, the display module is further configured to display the body posture of the to-be-tested person.

[0050] In a possible implementation, the second body parameter is measured by the first electronic device controlling at least eight electrodes to generate at least two different frequency electric signals.

[0051] In a possible implementation, the apparatus is deployed on the first electronic device.

[0052] In a possible implementation, the apparatus is deployed on a second electronic device, and the second electronic device is in communication connection with the first electronic device. The second electronic device can receive the first body parameter and the second body parameter sent by the first electronic device.

[0053] In a fourth aspect, an electronic device is provided, and the electronic device includes at least one memory configured to store programming; and at least one processor configured to execute the programming stored in the memory, wherein the processor is configured to perform the method provided in the first aspect when the programming stored in the memory is executed.

[0054] In a fifth aspect, a computer storage medium is provided, and the computer storage medium stores instructions, wherein the instructions, when executed on a computer, cause the computer to perform the method provided in the first aspect.

[0055] In a sixth aspect, a computer program product is provided, and the computer program product includes instructions, wherein the instructions, when executed on a computer, cause the computer to perform the method provided in the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1a is a system architecture schematic diagram of a liver fat grade detection system provided by an embodiment of the present application;

[0057] Figure 1b is a system architecture schematic diagram of another liver fat grade detection system provided by an embodiment of the present application;

[0058] Figure 2 is a hardware structure schematic diagram of a body fat scale provided by an embodiment of the present application;

[0059] Figure 3 is a hardware structure schematic diagram of an electronic device provided by an embodiment of the present application;

[0060] Figure 4 is a scene schematic diagram in which a person to be measured uses a body fat scale provided by an embodiment of the present application;

[0061] Figure 5 is a schematic diagram of resistances corresponding to segments of a body of a person to be measured provided by an embodiment of the present application;

[0062] Figure 6 is a display interface schematic diagram of an electronic device provided by an embodiment of the present application;

[0063] Figure 7 is a display interface schematic diagram of an electronic device provided by an embodiment of the present application;

[0064] Figure 8 is a display interface schematic diagram of an electronic device provided by an embodiment of the present application;

[0065] Figure 9a is a display interface schematic diagram of an electronic device provided by an embodiment of the present application;

[0066] Figure 9bFigure 1 is a schematic diagram of a display interface of an electronic device according to an embodiment of the present application;

[0067] Figure 10a Figure 2 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0068] Figure 10b Figure 3 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0069] Figure 10c Figure 4 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0070] Figure 10d Figure 5 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0071] Figure 10e Figure 6 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0072] Figure 10f Figure 7 is a schematic diagram of a display interface of a mobile phone according to an embodiment of the present application;

[0073] Figure 11a Figure 8 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0074] Figure 11b Figure 9 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0075] Figure 11c Figure 10 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0076] Figure 11d Figure 11 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0077] Figure 11e Figure 12 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0078] Figure 11f Figure 13 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0079] Figure 11g Figure 14 is a schematic diagram of a display interface of a large screen according to an embodiment of the present application;

[0080] Figure 12 Figure 15 is a schematic diagram of a physiological parameter measurement method according to an embodiment of the present application;

[0081] Figure 13 Figure 16 is a schematic diagram of a step of accurately measuring a first physiological parameter of a person to be measured according to an embodiment of the present application;

[0082] Figure 14 is a schematic diagram of an architecture of a physiological parameter measurement system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below with reference to the drawings.

[0084] In the description of the embodiments of the present application, the words such as “exemplary”, “for example”, or “for instance” are used to mean serving as an example, instance or illustration. Any embodiment or design solution described as “exemplary”, “for example” or “for instance” in the embodiments of the present application should not be interpreted as being preferred or superior to other embodiments or design solutions. Rather, the words “exemplary”, “for example” or “for instance” are used to present related concepts in a specific manner.

[0085] In the description of the embodiments of the present application, the term “and / or” merely describes an association relationship of associated objects, and means that there can be three relationships, for example, A and / or B can mean that there are three cases of A alone, B alone, and A and B simultaneously. In addition, unless otherwise specified, the term “plurality” means two or more. For example, a plurality of systems means two or more systems, and a plurality of electronic devices means two or more electronic devices.

[0086] In addition, the terms “first” and “second” are used only for descriptive purposes, and should not be construed as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with “first” and “second” can explicitly or implicitly include one or more features. The terms “include”, “contain”, “have” and their variants mean “include but are not limited to”, unless otherwise specifically emphasized.

[0087] Figure 1a is a schematic diagram of a system architecture of a liver fat grade detection system provided in an embodiment of the present application. As shown in the figure, the system includes a body fat scale 11 and a mobile phone 12. The body fat scale 11 and the mobile phone 12 can establish a connection through Bluetooth. Figure 1a

[0088] ​The body fat scale 11 can detect the weight and the body impedance of the person to be measured, wherein the body impedance can include the dual-arm impedance, the dual-leg impedance and the trunk impedance. In an example, after the body fat scale 11 obtains the weight and the body impedance of the person to be measured, the body fat scale 11 can send the weight and the body impedance to the mobile phone 12 through Bluetooth. In addition, if the body fat scale 11 and the mobile phone 12 are not connected when the body fat scale 11 measures the weight and the body impedance, the data can be synchronized between the body fat scale 11 and the mobile phone 12 after the body fat scale 11 and the mobile phone 12 are connected, that is, the body fat scale 11 sends the data measured by the body fat scale 11 to the mobile phone 12. In addition, the body fat scale 11 can also send the basic data required for calculating the body impedance to the mobile phone 12, and then the mobile phone 12 can calculate the body impedance from the basic data.

[0089] The mobile phone 12 can determine the body parameters of the person to be measured based on the weight and the body impedance detected by the body fat scale 11. For example, the body parameters can include the body mass index (BMI), the body fat rate, the visceral fat level, the fat amount of each segment of the body, the waist-hip ratio, or the body shape, etc. For example, the body shape can include the apple type, the pear type, the pepper type, the hourglass type, or the inverted triangle type, etc. Then, the mobile phone 12 can determine the level determination model corresponding to the body shape of the person to be measured based on the body shape of the person to be measured. After that, the mobile phone 12 can input the body parameters of the person to be measured into the level determination model to obtain the liver fat level of the person to be measured. Finally, the mobile phone 12 can present the determined liver fat level to the person to be measured.

[0090] In the present scheme, in the process of determining the liver fat level, different level determination models can be used to calculate the liver fat level of the user for different body shapes, so that different processing methods are used for different groups of people, the accuracy of the liver fat level evaluation is improved, and the situation that all people use one liver fat level evaluation method is avoided.

[0091] It can be understood that part or all of the functions realized by the mobile phone 12 in the present scheme can also be realized by the body fat scale 11 or by other electronic devices other than the body fat scale 11, which is not limited herein. For example, the body fat rate can also be calculated by the body fat scale 11; that is, the body fat scale 11 can not only transmit the measured data to the mobile phone 12, but also transmit the calculated data to the mobile phone 12 after calculating some data. For example, the body fat rate can be calculated by the body fat scale 11, and then the body fat scale 11 can transmit the calculated body fat rate to the mobile phone 12. Figure 1bAs shown, the system can further include a smart screen 13. Exemplarily, the body fat scale 11 and the mobile phone 12 can establish a connection through Bluetooth, and the mobile phone 12 and the smart screen 13 can also establish a connection through a wireless network. The smart screen 13 can realize part of the functions of the mobile phone 12, for example, presenting the liver fat level determined by the mobile phone 12 to the person to be measured. For example, after determining the liver fat level of the person to be measured based on the body impedance and the body weight of the person to be measured sent by the body fat scale 11, the mobile phone 12 can project the determined liver fat level to the smart screen 13 through projection, and then the smart screen 13 can present the liver fat level to the person to be measured.

[0092] It can be understood that in the present scheme, the body fat scale 11 can also be replaced by other electronic devices, which can realize the functions of the body fat scale 11 in the present scheme, and the like. Exemplarily, the electronic device replacing the body fat scale 11 can at least have the function of detecting the body impedance and the body weight of the person to be measured. The mobile phone 12 can also be replaced by other electronic devices, which can realize the functions of the mobile phone 12 in the present scheme, and the like. Exemplarily, the electronic device replacing the mobile phone 12 can be a tablet computer, a wearable device, a smart television, a smart screen, and the like. The smart screen 13 can also be replaced by other electronic devices, which can realize the functions of the smart screen 13 in the present scheme, and the like. Exemplarily, the electronic device replacing the smart screen 13 can be a tablet computer, a wearable device, a smart television, and the like.

[0093] In addition, in the present scheme, the body fat scale 11 and the mobile phone 12 can also establish a connection through other connection manners, and the mobile phone 12 and the smart screen 13 can also establish a connection through other connection manners, which are not limited herein. Exemplarily, the body fat scale 11 and the mobile phone 12 can establish a connection through short-distance wireless connection technology or long-distance wireless connection technology; the short-distance wireless connection technology can include ZigBee, and the like; the long-distance wireless connection technology can include wireless fidelity (WIFI), cellular mobile communication, and the like. The mobile phone 12 and the smart screen 13 can also establish a connection through short-distance wireless connection technology or long-distance wireless connection technology; the short-distance wireless connection technology can include ZigBee, and the like; the long-distance wireless connection technology can include wireless fidelity (WIFI), cellular mobile communication, and the like.

[0094] Next, a schematic diagram of the hardware structure of a body fat scale provided in this solution is introduced. For example, this body fat scale can be... Figure 1a or Figure 1b The body fat scale 11 shown.

[0095] Figure 2 This is a schematic diagram of the hardware structure of a body fat scale provided in an embodiment of this application. Figure 2 As shown, the body fat scale 200 may include a scale body 21 and a handle 22. The scale body 21 and the handle 22 can be connected by a cable 23. At least four electrodes 211 may be provided on the scale body 21. At least four electrodes 221 may be provided on the handle 22. When a user uses the body fat scale 200, at least two electrodes on the scale body 21 are in contact with the user's left foot, and at least two electrodes are in contact with the user's right foot; at least two electrodes on the handle 22 are in contact with the user's left hand, and at least two electrodes are in contact with the user's right hand.

[0096] It is understandable that a pressure sensor (not shown in the figure) can also be installed in the scale body 21. This pressure sensor can detect the user's weight. In addition, a display screen 222 can be installed on the handle 22, which can display the user's weight, body fat percentage, etc.

[0097] In this solution, the body fat scale 200 may also include a processor (not shown in the figure) and a communication module (not shown in the figure). The processor in the body fat scale 200 can determine the user's weight based on the signals detected by the pressure sensor in the scale body 21; determine the user's body impedance based on the signals detected by the electrodes on the scale body 21 and the handle 22; and determine the user's body fat percentage based on the determined body impedance, etc.

[0098] The communication module in the body fat scale 200 can provide short-range or long-range communication to enable information interaction between the body fat scale 200 and other electronic devices. For example, the communication module in the body fat scale 200 can be Bluetooth, ZigBee, wireless fidelity (WIFI), cellular mobile communication, etc.

[0099] Understandably, this plan Figure 2 The illustrated structure does not constitute a specific limitation on the body fat scale. In other embodiments of this solution, the body fat scale may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0100] Next, a hardware structure schematic diagram of an electronic device provided in the present solution is introduced. Exemplarily, the electronic device can be a mobile phone 12 as shown in Figure 1a or Figure 1b a smart screen 13 as shown in Figure 1b .

[0101] Figure 3 is a hardware structure schematic diagram of an electronic device provided in an embodiment of the present application. As shown in Figure 3 , the electronic device 300 can include: a processor 301, a memory 302, and a communication module 303. Among them, the processor 301, the memory 302, and the communication module 303 can be connected through a bus or other means.

[0102] In the present solution, the processor 301 is the computing core and control core of the electronic device. The processor 301 can include one or more processing units, for example, the processor 301 can include one or more of an application processor (AP), a modem, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units can be independent devices, or can be integrated in one or more processors. In one example, the processor 301 can implement the liver fat grade detection method provided in the present solution. Exemplarily, the processor 301 can determine the body parameters of the to-be-measured person based on the body weight and body impedance detected by the body fat scale; the processor 301 can also determine the grade determination model corresponding to the body shape of the to-be-measured person based on the body shape of the to-be-measured person; the processor 301 can further input the body parameters of the to-be-measured person into the grade determination model to obtain the liver fat grade of the to-be-measured person, etc.

[0103] The memory 302 is a memory device of the electronic device, used to store programs and data, such as storing the position of the electronic device itself and the position of other electronic devices received by the electronic device, etc. It can be understood that the memory 302 this time can be a high-speed RAM memory, or a non-volatile memory. Optionally, the memory 302 can also be at least one storage device located away from the aforementioned processor 301. The memory 302 can provide a storage space that can store the operating system and executable program code of the electronic device, which can include but is not limited to: Windows system (an operating system), Linux system (an operating system), Hongmeng system (an operating system), etc., which are not limited here. Illustratively, the memory 302 can store a grade determination model for determining the liver fat grade.

[0104] The communication module 303 can provide short-distance communication or long-distance communication for the electronic device to realize information interaction between the electronic device and other electronic devices (such as body fat scales, etc.). Illustratively, the communication module 303 can be Bluetooth, ZigBee, wireless fidelity (WIFI), cellular mobile communication, etc.

[0105] Optionally, the electronic device 300 can also include a display screen 304. Illustratively, the display screen 304 can display the liver fat grade, body parameters, etc. of the person to be measured.

[0106] Optionally, the electronic device 300 can also include a camera 305. The camera 305 can be used to capture still images or videos, for example, to collect images of the person to be measured, etc.

[0107] It can be understood that the present scheme Figure 3 The schematic structure does not constitute a specific limitation on the electronic device. In other embodiments of the present scheme, the electronic device can include more or fewer components than the illustration, or combine certain components, or split certain components, or different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0108] The above is the introduction of the liver fat grade detection system involved in the present scheme, and the hardware structure of the electronic device involved in the system. Next, based on the above description, the liver fat grade detection scheme provided by the present scheme is introduced in detail.

[0109] (1) Determine the weight and body impedance of the person to be measured

[0110] In the present scheme, the weight and body impedance of the person to be measured can be determined byFigure 2 The body fat scale 200 shown determines the weight and body impedance of the person being measured. Figure 4 As shown, the person being tested, A, can stand on the body 21 of the body fat scale 200 and hold the handle 22 of the body fat scale 200. The left foot and right foot of the person being tested can contact the two electrodes 211 on the body 21; the left and right hands of the person being tested can contact the two electrodes (not shown) on the handle 22. After the person being tested starts the test, the electrodes on the body fat scale 200 can generate electrical signals of a specific frequency to measure the body impedance of the person being tested. In this scheme, body impedance can include: left arm impedance, right arm impedance, left leg impedance, right leg impedance, trunk impedance, etc.; the impedance of different areas of the body can be acquired simultaneously or at different times, depending on the actual situation, and is not limited here.

[0111] In one example, see further. Figure 4, the body fat scale 200 can first turn on the electrodes on the left and right sides of the handle 22, and then measure the double-arm impedance R1 according to the current and voltage. Next, the body fat scale 200 can stop turning on the electrodes on the handle 22, and turn on the electrodes on the body 21, and then measure the double-leg impedance R2 according to the current and voltage. Next, the body fat scale 200 can stop turning on the electrodes on the left and right sides of the body 21, and turn on the electrodes on the left side of the handle 22 and the right side of the body 21, and then measure the left oblique half-body impedance R3 according to the current and voltage. Next, the body fat scale 200 can stop turning on the electrodes on the left side of the handle 22 and the right side of the body 21, and turn on the electrodes on the right side of the handle 22 and the left side of the body 21, and then measure the right oblique half-body impedance R4 according to the current and voltage. Next, the body fat scale 200 can stop turning on the electrodes on the right side of the handle 22 and the left side of the body 21, and turn on the electrodes on the left side of the handle 22 and the left side of the body 21, and then measure the left half-body impedance R5 according to the current and voltage. Next, the body fat scale 200 can stop turning on the electrodes on the left side of the handle 22 and the left side of the body 21, and turn on the electrodes on the right side of the handle 22 and the right side of the body 21, and then measure the right half-body impedance R6 according to the current and voltage. Finally, the body fat scale 200 can determine the left arm impedance, the right arm impedance, the left leg impedance, the right leg impedance, and the torso impedance of the person A to be measured based on the measured double-arm impedance R1, the double-leg impedance R2, the left oblique half-body impedance R3, the right oblique half-body impedance R4, the left half-body impedance R5, and the right half-body impedance R6. It should be noted that in the present scheme, the order of turning on the electrodes is only illustrative, and can be determined according to actual conditions, which is not limited herein.

[0112] As shown in Figure 5 , when measuring the body impedance, the left arm 31 of the person A to be measured can be equivalent to a resistor (i.e., resistor 311), the right arm 32 of the person A to be measured can be equivalent to a resistor (i.e., resistor 321), the torso 33 of the person A to be measured can be equivalent to a resistor (i.e., resistor 331), the left leg 34 of the person A to be measured can be equivalent to a resistor (i.e., resistor 341), and the right leg 35 of the person A to be measured can be equivalent to a resistor (i.e., resistor 351). As shown in Figure 5In the scheme, the dual-arm impedance can be the sum of the resistance values of the resistor 311 and the resistor 321, that is, the dual-arm impedance can be the sum of the left-arm impedance and the right-arm impedance; the dual-leg impedance can be the sum of the resistance values of the resistor 341 and the resistor 351, that is, the dual-leg impedance can be the sum of the left-leg impedance and the right-leg impedance; and the trunk impedance can be the resistance value of the resistor 341. Further, after the body fat scale 200 measures the dual-arm impedance R1, the dual-leg impedance R2, the left oblique half-body impedance R3, the right oblique half-body impedance R4, the left half-body impedance R5, and the right half-body impedance R6, the following data can be obtained:

[0113] R1 = R311 + R321;

[0114] R2 = R341 + R351;

[0115] R3 = R311 + R331 + R351;

[0116] R4 = R321 + R331 + R341;

[0117] R5 = R311 + R331 + R341;

[0118] R6 = R321 + R331 + R351;

[0119] Further, through mathematical operations, the impedance of the left arm, the right arm, the left leg, the right leg, and the trunk of the person A to be measured can be obtained. Among them, R311 = (R1 + R5 - R4) / 2, R321 = (R1 + R6 - R3) / 2, R331 = (R3 + R4 - R1 - R2) / 2, R341 = (R2 + R5 - R3) / 2, R351 = (R2 + R6 - R4) / 2, R311 can be the left-arm impedance, R321 can be the right-arm impedance, R331 can be the trunk impedance, R341 can be the left-leg impedance, and R351 can be the right-leg impedance.

[0120] In addition, when the person A to be measured stands on the body fat scale 200, if the body fat scale 200 is in an open state, the body fat scale 200 can measure the weight of the person A to be measured by using the pressure sensor therein.

[0121] In one example, when measuring the body impedance of subject A, the electrodes on the body fat scale 200 can be controlled to generate electrical signals of various frequencies to measure the subject's body impedance. This allows for the determination of the impedance when intracellular fluid flows through the body and the impedance when intracellular fluid does not flow through the body, thus measuring the subject's body impedance from multiple dimensions and improving detection accuracy. For example, the electrical signals generated by the electrodes on the body fat scale 200 can be at frequencies of 50 kHz and 250 kHz. The order in which the different frequencies of electrical signals are generated can vary and is not limited here; for example, a 50 kHz signal can be generated first, followed by a 250 kHz signal, or vice versa. Because the frequency of the 50kHz electrical signal is low, it is difficult for the signal to penetrate the intracellular fluid when measured. In other words, the body impedance measured at this frequency is the impedance when the signal has not flowed through the intracellular fluid. On the other hand, because the frequency of the 250kHz electrical signal is high, it can penetrate the intracellular fluid when measured. In other words, the body impedance measured at this frequency is the impedance when the signal flows through the intracellular fluid.

[0122] (2) Determine the liver fat grade of the test subjects.

[0123] In this method, after determining the weight and body impedance of the subject using a body fat scale, the liver fat grade of the subject can be determined based on the weight and body impedance of the subject.

[0124] In one example, using Figure 2 After the body fat scale 200 shown determines the weight and body impedance of the person being tested, the body fat scale 200 can transmit the weight and body impedance of the person being tested to... Figure 3 In the electronic device 300 shown, the liver fat level of the test subject A is determined by the electronic device 300. In addition, the body impedance of the test subject A can also be calculated by the mobile phone based on the initial data measured by the body fat scale 200; wherein, the body fat scale 200 can send the measured arm impedance R1, leg impedance R2, left oblique half-body impedance R3, right oblique half-body impedance R4, left half-body impedance R5, and right half-body impedance R5 to the electronic device 300; then, the electronic device 300 calculates the body impedances such as left arm impedance, right arm impedance, left leg impedance, right leg impedance, and trunk impedance.

[0125] Before determining the liver fat level of the test subject A, the electronic device 300 can first determine basic parameters of the test subject A, such as height. For example, the electronic device 300 can have an application related to liver fat level (such as Huawei Health) installed. Figure 6As shown, the person to be tested A can input the height and other basic parameters on the application program related to the liver fat level, and after the input is completed, he or she can select the "OK" button at the area 51, i.e. the height and other basic parameters of the person to be tested A can be input into the application program related to the liver fat level.

[0126] After the height and other basic parameters of the person to be tested A are obtained, the electronic device 300 can determine the body parameters of the person to be tested A in combination with the weight and body impedance of the person to be tested, such as the body mass index BMI, the body fat rate BFR, the visceral fat amount in the trunk, the fat amount of each segment of the body, the waist-hip ratio, or the body shape, etc. For example, the visceral fat amount in the trunk can be understood as the fat content of most of the internal organs in the trunk, or the fat content of all internal organs in the trunk.

[0127] In this scheme, the body mass index BMI = W / H 2 , wherein W is the weight and H is the height.

[0128] The body fat rate can be calculated by the following formula. The formula (hereinafter referred to as "Formula One") is as follows:

[0129] BFR = α1Z1 50 + α2Z1 250 + α3Z2 50 + α4Z2 250 + α5Z3 50 + α6Z3 250 + α7w t + α8H t + α9

[0130] , wherein BFR is the body fat rate; α1,..., α9 are pre-set coefficients, which can be obtained by experiments; Z1 50 is the impedance of both legs at 50 KHz; Z1 250 is the impedance of both legs at 250 KHz; Z2 50 is the impedance of both arms at 50 KHz; Z2 250 is the impedance of both arms at 250 KHz; Z3 50 is the impedance of the trunk at 50 KHz; Z3 250 is the impedance of the trunk at 250 KHz; w t is the weight; H t is the height. In one example, after the body fat scale measures the body fat rate, the body fat scale can also send the body fat rate to the electronic device 300, so that the electronic device 300 can directly obtain the body fat rate. It can be understood that Z 50 and Z 250 in Formula One can also be replaced by the impedance at other frequencies, which are not limited herein.

[0131] The visceral fat amount in the torso can be calculated by the following formula. This formula (hereinafter referred to as "Formula Two") is:

[0132] X = β1Z1 50 + β2Z1 250 + β3Z2 50 + β4Z2 250 + β5Z3 50 + β6Z3 250 + β7W t + β8H t + β9

[0133] wherein X is the visceral fat amount in the torso; β1,..., β9 are preset coefficients, which can be obtained by experiments; Z1 50 is the 50 KHz bilateral leg impedance; Z1 250 is the 250 KHz bilateral leg impedance; Z2 50 is the 50 KHz bilateral arm impedance; Z2 250 is the 250 KHz bilateral arm impedance; Z3 50 is the 50 KHz torso impedance; Z3 250 is the 250 KHz torso impedance; w t is the body weight; H t is the body height. It can be understood that Z1 50 and Z1 250 in Formula Two can also be replaced by impedances of other frequencies, which are not limited herein.

[0134] The fat amount of each segment of the body can be calculated by the following formula. This formula (hereinafter referred to as "Formula Three") is:

[0135] P = δ1Z 50 + δ2Z 250 + δ3w t + δ4H t + δ5

[0136] wherein P is the fat amount of a body segment, which can be the fat amount of the left arm, the fat amount of the right arm, the fat amount of the left leg, the fat amount of the right leg, or the fat amount of the torso; δ1,..., δ5 are preset coefficients, which can be obtained by experiments; Z 50 is the 50 KHz impedance; Z 250 is the 250 KHz impedance; w t is the body weight; H t is the body height. It can be understood that when P is the fat amount of the left arm, Z 50 is the 50 KHz left arm impedance; Z 250 is the 250 KHz left arm impedance; when P is the fat amount of the right arm, Z 50 is the 50 KHz right arm impedance; Z 250Z is the right arm impedance at 250 KHz; Z is the left leg impedance at 50 KHz; P is the right leg fat mass; Z is the trunk impedance at 50 KHz 50 Z is the left leg impedance at 50 KHz; Z is the right arm impedance at 250 KHz; P is the left leg fat mass 250 Z is the left leg impedance at 50 KHz; Z is the right arm impedance at 250 KHz; P is the left leg fat mass 50 Z is the right arm impedance at 50 KHz; Z is the trunk impedance at 50 KHz; P is the trunk fat mass 50 Z is the trunk impedance at 50 KHz; Z is the right arm impedance at 250 KHz; P is the trunk fat mass 250 Z is the trunk impedance at 250 KHz. In determining the fat mass of different body segments, the parameters in Formula Three can be partially the same, all the same, or all different, which can be determined according to actual conditions, and is not limited herein. It can be understood that Z 50 and Z 250 in Formula Three can also be replaced by impedance at other frequencies, which is not limited herein.

[0137] The waist-to-hip ratio can be calculated by the following formula. The formula (hereinafter referred to as “Formula Four”) is as follows:

[0138] Y = γ1L1 + γ2L2 + γ3L3 + γ4L4 + γ5L5 + γ6L6 + γ7L7 + γ8L8 + γ9L9 + γ 10 L10 + γ 11

[0139] wherein Y is the waist-to-hip ratio; γ1,…, γ 11 are pre-set coefficients, which can be obtained by experiments; L1 is the left arm muscle mass; L2 is the left arm fat mass; L3 is the right arm muscle mass; L4 is the right arm fat mass; L5 is the left leg muscle mass; L6 is the left leg fat mass; L7 is the right leg muscle mass; L8 is the right leg fat mass; L9 is the trunk muscle mass; and L10 is the trunk fat mass. In an example, “left arm muscle mass L1”, “right arm muscle mass L3”, “left leg muscle mass L5”, “right leg muscle mass L7”, and “trunk muscle mass L9” in Formula Four can be adaptively selected, which is not limited herein.

[0140] In the present scheme, the muscle mass of each body segment can be calculated by the following formula. The formula (hereinafter referred to as “Formula Five”) is as follows:

[0141] M = θ1Z 50 + θ2Z 250 + θ3W t + θ4H t + θ5

[0142] wherein M is the muscle mass of each body segment, which can be the left arm muscle mass, the right arm muscle mass, the left leg muscle mass, the right leg muscle mass, or the trunk fat mass; θ1,…, θ5 are pre-set coefficients, which can be obtained by experiments; Z 50 is the impedance at 50 KHz; Z 250is the impedance at 250 KHz; w t is the weight; H t is the height. It can be understood that when M is the muscle mass of the left leg, Z 50 is the impedance of the left leg at 50 KHz; Z 250 is the impedance of the left leg at 250 KHz; when M is the muscle mass of the right leg, Z 50 is the impedance of the right leg at 50 KHz; Z 250 is the impedance of the right leg at 250 KHz; when M is the muscle mass of the left leg, Z 50 is the impedance of the left leg at 50 KHz; Z 250 is the impedance of the left leg at 250 KHz; when M is the muscle mass of the right leg, Z 50 is the impedance of the right leg at 50 KHz; when M is the muscle mass of the trunk, Z 50 is the impedance of the trunk at 50 KHz; Z 250 is the impedance of the trunk at 250 KHz. In determining the muscle mass of different body segments, the parameter θ in Formula Five can be partially the same, or all the same, or all different, which can be determined according to actual conditions, and is not limited herein. It can be understood that Z 50 and Z 250 may also be replaced by the impedance at other frequencies, which is not limited herein.

[0143] In this scheme, after the waist-hip ratio is determined, the body parameters required for determining the body shape can be determined based on the waist-hip ratio, and then the body shape is determined by the body parameters. In an example, the required body parameters can be determined based on the interval to which the waist-hip ratio belongs. For example, when the waist-hip ratio is in a preset interval a1 (such as a1 ∈ (0.78, 0.85)), the BMI can be used to determine the body shape. At this time, when the BMI is less than a preset threshold b1 (such as b1 = 21), the body shape is a chili type, and when the BMI is greater than or equal to the preset threshold b1, the body shape is a uniform type. When the waist-hip ratio is in a preset interval a2 (such as a2 ∈ (0, 0.78]), the muscle mass of the arms can be used to determine the body shape. At this time, when the ratio of the muscle mass of the arms to the total muscle mass of the body is greater than or equal to a preset threshold b2 (such as b2 = 0.0981), the body shape can be determined to be a sandglass type, and when the ratio of the muscle mass of the arms to the total muscle mass of the body is less than the preset threshold b2, the body shape can be determined to be a pear type.

[0144] It can be understood that in order to improve the accuracy of the determination of the body shape, the waist-hip ratio can be combined with multiple other body parameters when determining the body shape. For example, the waist-hip ratio, the fat mass and muscle mass of each segment of the body, the BMI, the visceral fat mass in the trunk, and the like can be used. The parameters used to determine the body shape can be input into a machine learning classification model to obtain the body shape.

[0145] Furthermore, after determining the body shape of the test subject A, the electronic device 300 can determine the corresponding grading model for the body shape of the test subject A based on the pre-set correspondence between body shapes and grading models used to determine liver fat grades. It is understood that in this scheme, the grading model used to determine liver fat grades can be trained using Gaussian process models, neural network models, support vector machines, etc.; in addition, the grading model can also be a biased function model, a proportional function model, a hybrid function model, or other mathematical function models. For example, the pre-set correspondence between body shapes and grading models used to determine liver fat grades can be shown in Table 1. When the body shape is determined to be "apple-shaped," it can be seen from Table 1 that the grading model to be selected is "Model Two."

[0146] Table 1

[0147] Body shape Grade determination model Pear shape Model one Apple shape Model two Hourglass shape Model three Pepper shape Model four

[0148] Furthermore, after the electronic device 300 determines the grading model, it can input the body parameters of the test subject A, such as BMI, body fat percentage, and waist-to-hip ratio, into the grading model. After processing by the grading model, the liver fat grade of the test subject A can be obtained. It is understandable that the parameters input into the grading model can also include other body parameters, such as visceral fat mass in the trunk, fat mass in different body segments, body shape, etc., thereby improving the accuracy of the detection.

[0149] Next, the electronic device 300 can determine the liver risk level of the test subject A based on the correspondence between liver fat grade and liver risk coefficient. For example, the pre-set correspondence between liver fat grade and liver risk level can be shown in Table 2. When the liver fat grade is determined to be "5", it can be seen from Table 2 that the liver risk level at this time is "suspected risk".

[0150] Table 2

[0151] Liver fat grade Liver risk grade 0～4 Normal 4～7 Suspected risk 7～10 High risk

[0152] In this solution, to facilitate timely access to the liver fat level of the test subject A, the electronic device 300 can present the detected liver fat level of the test subject A to the test subject A. For example, as shown... Figure 7 As shown, the electronic device 300 displays that the liver fat grade of the test subject A is 7.8, and the screening result is medium to high risk. Further reading... Figure 7In addition, the electronic device 300 can also display other parameters of the to-be-measured person A, such as height, body shape (not shown in the figure), and the like, and display exercise suggestions and the like.

[0153] Therefore, in the present scheme, in the process of determining the liver fat level, different level determination models can be used to calculate the liver fat level of the user for users with different body shapes, so that different processing methods are used for different groups of people, the accuracy of liver fat level evaluation is improved, and the case where one liver fat level evaluation method is used for all people is avoided.

[0154] The above is an introduction to the liver fat level detection scheme in the present scheme. After obtaining the liver fat level, if the user wants more accurate results, the body feature parameters of the user can be added in the detection process in the present scheme; the body feature parameters include chest circumference, waist circumference, hip circumference, and the like. It can be understood that the body feature parameters are parameters that are strongly related to the fat content in the liver, so as to improve the accuracy of liver fat level detection. In one example, the liver fat level detection system in the present scheme can be the system shown in Figure 1a , wherein the mobile phone 12 can collect the photo of the to-be-measured person to determine the body feature parameters of the to-be-measured person. In addition, the liver fat level detection system in the present scheme can be the system shown in Figure 1b , wherein the smart screen 13 can be configured with a camera; after the to-be-measured person determines the accurate measurement of the liver fat level from the mobile phone 12, the mobile phone 12 can send an instruction to the smart screen 13 to collect the photo of the to-be-measured person through the camera on the smart screen 13; then, the smart screen 13 sends the photo of the to-be-measured person to the mobile phone 12 to determine the body feature parameters of the to-be-measured person through the mobile phone 12 and obtain a more accurate liver fat level. Details are described below.

[0155] The scheme of adding the body feature parameters of the user is described in detail below.

[0156] Scenario One

[0157] In this scenario, the electronic device 300 is a mobile phone, which can be understood as an application scenario under the system shown in Figure 1a . Among them, an application program related to the liver fat level (such as Huawei Health) can be installed on the mobile phone. Continue to refer to Figure 7 , at this time, the to-be-measured person A can select the “next page” button at the region 61. Then, the electronic device 300 can display, for example, as shown in Figure 8The interface shown prompts test subject A to "open the phone camera" and allows test subject A to choose whether to measure liver fat more accurately. If test subject A selects the "Cancel" button in area 71, the accurate measurement of liver fat will stop, and the system will return to the previous screen. Figure 7 The interface shown. If test subject A selects the "OK" button in area 72, the precise liver fat measurement process will begin. In addition, test subject A can select... Figure 7 Middle area 61 to display Figure 8 In addition to the interface shown, the test subject A can also... Figure 7 The interface shown can be swiped, such as swiping from left to right, from right to left, from top to bottom, or from bottom to top, etc., to display... Figure 8 The interface shown. It is understandable that in this solution, Figure 7 The "Next Page" text displayed in area 61 can also be replaced with other content, for example, as shown in Figure 9. Figure 7 Replace "Next Page" in section 61 with Figure 9a The content in area 62 is designed to allow test subject A to select the "OK" button. After test subject A selects the "OK" button, the process proceeds to... Figure 8 The interface shown. Furthermore, as... Figure 9b As shown, it can be Figure 7 Replace "Next Page" in section 61 with Figure 9b The content in area 63 allows test subject A to select "yes" or "no". If test subject A selects "yes", the process proceeds to... Figure 8 The interface shown. In one example, Figure 9b The content in area 63 can appear as a pop-up window. If test subject A selects "Yes", then the test will proceed to... Figure 8 The interface shown allows the pop-up window to be closed when the test subject A selects "No," meaning the content in area 63 will no longer be displayed. For example, this pop-up window may appear some time after the liver fat level has been detected (e.g., 3 seconds).

[0158] Because taking photos requires capturing a full-body image of the user from a specific height, when the electronic device is a mobile phone, it needs to be fixed in a specific position. For example... Figure 10a As shown, the person being tested, A, was... Figure 8After the "OK" button at the selection area 72 on the mobile phone is selected, the mobile phone can display the suggestion information before taking the photo, which can be "1. Please place the mobile phone in a fixed position and make sure that the mobile phone can take a clear full-body photo. 2. Please wear tight clothes, expose the waist and abdomen, and do not put your hands on your legs", so as to prompt the appropriate photo action and improve the measurement accuracy. Further, when the person A is ready, the "OK" button at the selection area 1001 can be selected, and the photo process is entered. It can be understood that in the present scheme, the person A can select the button on the mobile phone by clicking, voice selection, or gesture selection, which can be determined according to the actual situation, and is not limited here. Figure 10a

[0159] Next, after entering the photo process, the mobile phone can first take a front photo of the person A, as shown in Figure 10b After the mobile phone takes the front photo of the person A, it can detect whether the photo meets the requirements. If it meets the requirements, the next process is entered, and if it does not meet the requirements, the front photo is taken again. For example, after the front photo of the person A is taken, the human body skeleton key point detection algorithm based on template matching (Pictorial Structure) and the human body skeleton key point detection algorithm based on target detection, such as cascaded feature network (CFN), regional multi-person pose estimation (RMPE), cascaded pyramid network (CPN), etc., can be used to select the human body skeleton node from the taken image and construct the limb vector; then, the standard limb vector preset is compared with the obtained limb vector to obtain the action difference degree; then, it is determined whether the obtained image meets the requirements according to the action difference degree. For example, when the action difference degree is within the preset range, it is determined to meet the requirements; when the action difference degree is not within the preset range, it is determined not to meet the requirements. It can be understood that Figure 10b The person image in the present scheme is only a schematic front image of the person A taken by the mobile phone.

[0160] When the mobile phone detects that the taken image meets the requirements, the mobile phone can take a side photo of the person A, that is, the interface shown in Figure 10c is displayed to take a side photo of the person A. After the mobile phone takes a side photo of the person A, it can detect whether the photo meets the requirements; the detection method can refer to the detection method of the front photo, which will not be repeated here. If it meets the requirements, the next process is entered, and if it does not meet the requirements, the side photo can be taken again. It can be understood that Figure 10c ​The human image in the middle is only a schematic side image of the to-be-tested person A currently captured by the mobile phone.

[0161] When the mobile phone detects that the front and side photos meet the requirements, the mobile phone can perform image segmentation on the captured front and side photos based on a neural network (such as a Unet network) to extract a human image. Then, the mobile phone can determine the corresponding human node positions (such as armpit, groin, navel, and thigh root) according to the skeleton nodes and contour nodes. For example, the human skeleton key point detection algorithm described above can be used to determine the corresponding human node positions. Then, the mobile phone can determine the feature information of the chest width, chest thickness, waist width, waist thickness, hip width, and hip thickness at the human node positions in combination with the body proportions of the to-be-tested person A determined from the human image and the height. Then, the mobile phone can infer the body shape characteristic parameters such as the chest circumference, waist circumference, and hip circumference based on the determined feature information. For example, taking the waist circumference as an example, since the waist circumference is an elliptical shape, the waist circumference can be inferred based on mathematical operations after the waist width and waist thickness are obtained. Further, after the body shape characteristic parameters are obtained, the waist-to-hip ratio can also be calculated based on the waist circumference and hip circumference in the body shape characteristic parameters. It can be understood that the waist-to-hip ratio measured before the photographing is calculated according to an empirical formula, and the calculated waist-to-hip ratio is less accurate at this time. The waist-to-hip ratio measured after the photographing is calculated according to the feature information of the to-be-tested person, and can truly reflect the body condition of the to-be-tested person, that is, the calculated waist-to-hip ratio is more accurate at this time.

[0162] Further, the mobile phone can input the body shape characteristic parameters such as the waist circumference of the to-be-tested person A, the BMI, the body fat rate, and the waist-to-hip ratio into the above-determined grade determination model, and the liver fat grade of the to-be-tested person A can be obtained after the grade determination model is processed. At this time, the waist-to-hip ratio input into the grade determination model can be the waist-to-hip ratio inferred from the photo of the to-be-tested person, or the waist-to-hip ratio calculated before the photographing; but in order to improve the accuracy of the detection, it is better to use the waist-to-hip ratio inferred from the photo of the to-be-tested person. In an example, after the waist-to-hip ratio of the to-be-tested person is determined by using the front and side photos, the waist-to-hip ratio can be compared with the waist-to-hip ratio determined based on the body impedance. If the intervals to which the two belong are consistent when determining the parameters of the body shape, the grade determination model determined before the photographing can be continuously used; if the intervals to which the two belong are inconsistent when determining the parameters of the body shape, the body shape of the to-be-tested person A can be determined again based on the waist-to-hip ratio determined based on the photo, the grade determination model can be determined again, and the liver fat grade of the to-be-tested person A can be calculated by using the re-determined grade determination model. In an example, after the body shape of the to-be-tested person A is re-determined, the re-determined body shape can also be used to replace the body shape determined before the photographing, and presented to the to-be-tested person A.

[0163] In this scheme, after the phone takes front and side photos but before obtaining the liver fat grade of subject A, i.e., during the calculation of subject A's liver fat grade, the phone can display as follows: Figure 10d The displayed interface is intended to inform the test subject of the processing progress. It is understandable that the parameters input into the grading model can also include other parameters, such as visceral fat mass in the torso, fat mass in different body segments, body shape, chest circumference, hip circumference, etc., thereby improving the accuracy of the detection.

[0164] After the phone calculates the liver fat level of the test subject A, it can be used as follows: Figure 10e As shown, the phone displays "Liver Fat Level". Furthermore, to allow the test subject A to access their own body shape parameters (i.e., body size information), the phone can also display... Figure 10f The interface shown allows the person being tested, A, to intuitively understand their own parameters such as chest circumference, waist circumference, hip circumference, and waist-to-hip ratio. It is understandable that... Figure 10e and 10f The display order of the interfaces shown may vary depending on the situation and is not limited here.

[0165] Scene 2

[0166] In this scenario, electronic device 300 is a large screen in a fixed position, such as a smart screen. This screen is equipped with an image acquisition device (such as a camera) to capture images of the person being tested. Additionally, an application related to liver fat levels (such as Huawei Health) can be installed on the screen. This scenario essentially involves... Figure 1a The phone model 12 has been replaced with a larger screen. In this scenario, the interaction is between the larger screen and the body fat scale, which can establish a connection via Bluetooth. See further... Figure 7 At this point, the person being tested, A, can click on area 61, which displays the "Fatty Liver Risk Level". For example, Figure 7 The color at point 61 in the middle region can be distinguished from... Figure 6 The colors of other areas are used so that the person being tested, A, can know that area 61 is clickable, for example... Figure 7 The other areas can be gray or white, while area 61 can be green or blue. Then, the electronic device 300 can display... Figure 11a The interface shown prompts test subject A to "turn on the large screen camera function," and allows test subject A to choose whether to measure liver fat more accurately. If test subject A selects the "Cancel" button in area 91, the accurate measurement of liver fat will stop, and the system will return to the previous screen. Figure 7The interface shown in FIG. 8. If the person to be tested A selects the "OK" button at the area 92, the precise measurement of liver fat process is performed. In addition, the person to be tested A can select the "No" button at the area 61 to display the interface shown in FIG. 7, or select the "Yes" button at the area 61 to display the interface shown in FIG. 8. Figure 7 In addition to the interface shown in FIG. 7, the person to be tested A can also display the interface shown in FIG. 8 by swiping the interface shown in FIG. 7 from left to right, from right to left, from top to bottom, or from bottom to top, and so on. It can be understood that in the present scheme, the "next page" displayed in the area 61 can also be replaced by other contents. For example, as shown in FIG. 9, the "next page" in the area 61 can be replaced by the content in the area 62 in FIG. 9, so that the person to be tested A can select "Yes" or "No", wherein when the person to be tested A selects "Yes", the interface shown in FIG. 8 is displayed. Figure 11a Figure 7 Figure 11a Figure 7 It can be understood that in the present scheme, the "next page" displayed in the area 61 can also be replaced by other contents. For example, as shown in FIG. 9, the "next page" in the area 61 can be replaced by the content in the area 62 in FIG. 9, so that the person to be tested A can select "Yes" or "No", wherein when the person to be tested A selects "Yes", the interface shown in FIG. 8 is displayed. Figure 7 Figure 11a

[0167] After the person to be tested A selects the "OK" button on the large screen, the large screen can display the suggestion information before taking the photo, which can be "Please wear tight clothes, expose the waist and abdomen, and do not put your hands on your legs", so as to prompt the person to be tested A to make appropriate photo actions and improve the measurement accuracy. Further, when the person to be tested A is ready, the person to be tested A can select the "OK" button at the area 93 and enter the photo process. It can be understood that in the present scheme, the person to be tested A can select by clicking, voice selection, or gesture selection when selecting the button on the large screen, which is not limited by the actual situation. Figure 11b Figure 11b Next, after entering the photo process, the large screen can first use the camera 901 to take a front photo of the person to be tested A, as shown in FIG. 10. After taking the front photo of the person to be tested A, the large screen can detect whether the photo meets the requirements. If it meets the requirements, the next process is entered, and if it does not meet the requirements, the camera 901 can be used to take a front photo again. The way to detect whether the photo meets the requirements is described in detail in the "Scenario One" above, which will not be repeated here. It can be understood that the image of the person in the area 91 is only a schematic image of the front image of the person to be tested A currently collected by the large screen.

[0168] When the large screen detects that the taken image meets the requirements, the large screen takes a side photo of the person to be tested A, which can be displayed as shown in FIG. 11. Figure 11c Figure 11c

[0169] When the large screen detects that the taken image meets the requirements, the large screen takes a side photo of the person to be tested A, which can be displayed as shown in FIG. 11. Figure 11d ​​​​​​​​The interface shown, and the side photo of the person A to be tested is taken by the camera 901. After the side photo of the person A to be tested is taken, the large screen can detect whether the photo meets the requirements. If it meets the requirements, it enters the next process, if it does not meet the requirements, it can use the camera 901 to retake the front photo. It can be understood that, Figure 11d The figure image in the middle is only a schematic of the front image of the person A to be tested currently collected by the large screen.

[0170] When the large screen detects that the taken front photo and side photo meet the requirements, the large screen can perform image segmentation on the taken front photo and side photo based on a neural network (such as a Unet network), and extract a human body image. Then, the large screen determines the corresponding human body node positions such as armpit, groin, navel, thigh root, etc. according to the skeleton nodes and contour nodes. Then, the large screen can determine the feature information of chest width, chest thickness, waist width, waist thickness, hip width, hip thickness, thigh width, and thigh thickness at the human body node positions in combination with the human body image and height. Then, the large screen can infer the body shape characteristic parameters such as chest circumference, waist circumference, and hip circumference based on the determined feature information. For example, taking the waist circumference as an example, since the waist circumference is an elliptical shape, after the waist width and waist thickness are obtained, the waist circumference can be inferred based on mathematical operations. Further, after the body shape characteristic parameters are obtained, the waist-hip ratio can also be calculated based on the waist circumference and hip circumference in the body shape characteristic parameters. It can be understood that the waist-hip ratio measured before taking the photo is calculated according to an empirical formula, and at this time the calculated waist-hip ratio is less accurate; while the waist-hip ratio measured after taking the photo is calculated according to the feature information of the body of the person to be tested, which can truly reflect the body condition of the person to be tested, that is, the calculated waist-hip ratio at this time is more accurate. It can be understood that the parameters input into the level determination model can also include other parameters, such as visceral fat amount in the trunk, fat amount of each segment of the body, body shape, chest circumference, hip circumference, etc., so as to improve the detection accuracy.

[0171] Further, the large screen can input the body shape characteristic parameters of the to-be-tested person A, such as the waist circumference, the BMI, the body fat rate, the waist-hip ratio, and the like, into the determined grade determination model, and the liver fat grade of the to-be-tested person A can be obtained after the grade determination model is processed. At this time, the waist-hip ratio input into the grade determination model can be the waist-hip ratio estimated from the photo of the to-be-tested person, or can be the waist-hip ratio calculated before the photo is taken. In order to improve the accuracy of the detection, the waist-hip ratio estimated from the photo of the to-be-tested person is preferably selected. In an example, after the waist-hip ratio of the to-be-tested person is determined by using the front photo and the side photo, the waist-hip ratio can be compared with the waist-hip ratio determined based on the body impedance. If the intervals to which the two belong are consistent when the parameters required to determine the body shape are determined, the grade determination model determined before the photo is taken can be continuously used. If the intervals to which the two belong are inconsistent when the parameters required to determine the body shape are determined, the body shape of the to-be-tested person A can be determined again based on the waist-hip ratio determined from the photo, the grade determination model is determined again, and the liver fat grade of the to-be-tested person A is calculated by using the determined grade determination model. In an example, after the body shape of the to-be-tested person A is determined again, the determined body shape can be used to replace the body shape determined before the photo is taken, and is presented to the to-be-tested person A.

[0172] In the present scheme, after the large screen takes the front photo and the side photo, and before the liver fat grade of the to-be-tested person A is obtained, that is, in the process of calculating the liver fat grade of the to-be-tested person A, the large screen can display an interface as shown in Figure 11e to make the to-be-tested person know the processing progress.

[0173] After the large screen calculates the liver fat grade of the to-be-tested person A, the large screen can display the "liver fat grade" as shown in Figure 11f . In addition, in order to enable the to-be-tested person A to know the body shape characteristic parameters (that is, the body size information) of himself / herself, the large screen can also display an interface as shown in Figure 11g to enable the to-be-tested person A to intuitively know the chest circumference, the waist circumference, the hip circumference, the waist-hip ratio, and the like of himself / herself. It can be understood that Figure 11f and 11g the display order of the interfaces shown in

[0174] It should be noted that in the present scheme, the prompt information of each operation process in Figures 11a to 11g may also be replaced by other prompt information, which can prompt the user to make the same or similar action as the standard action, and the present scheme does not limit this. In addition, the prompt information in other figures can also be replaced by other prompt information, and the present scheme does not limit this.

[0175] Scene Three

[0176] The scene is Figure 1b The system described illustrates an application scenario where an application related to liver fat levels (such as Huawei Health) can be installed on the phone 12. In this scenario, the liver fat level (i.e., liver fat level) is displayed on the phone 12. Figure 7 The interface shown can be configured as follows: (12) After the electronic device 300 is a mobile phone, the person being tested, A, can click... Figure 7 The area containing "Next Page" is 61. Then, as... Figure 10a As shown, the phone 12 can display pre-test suggestions, such as "1. Please turn on the large screen camera function and ensure the large screen is on. 2. Please wear tight-fitting clothing to expose your waist and abdomen, and let your arms hang down without touching your legs." The large screen can be understood as the smart screen 13. If the person being tested, A, selects the "Cancel" button, the accurate measurement of liver fat will stop, and the test will return to... Figure 7 The interface shown is as follows. If the test subject A selects the "OK" button, the mobile phone 12 sends a photo-taking command to the smart screen 13. It is understood that in this solution, when the test subject A selects a button on the mobile phone, he / she can click, select by voice, or select by gesture, depending on the actual situation, and is not limited here.

[0177] After receiving the photo-taking command from the mobile phone 12, the smart screen 13 can activate its camera 1201 and enter the photo-taking process. During this process, the smart screen 13 can first use its camera 1201 to take a frontal photo of the person being tested, A. After taking the photo, the smart screen 13 can send it to the mobile phone 12 for verification. If the mobile phone 12 detects that the photo meets the requirements, it sends a command to the smart screen 13 to proceed to the next step; if it detects that the photo does not meet the requirements, it sends a command to the smart screen 13 to retake the photo using the camera 1201. The method by which the mobile phone 12 verifies the photo's compliance is detailed in "Scenario 1" above and will not be repeated here.

[0178] After receiving the instruction from mobile phone 12 to proceed to the next step, smart screen 13 can use camera 1201 to capture a side view of the person being tested, A. After capturing the side view, smart screen 13 can send the photo to mobile phone 12 for verification. If mobile phone 12 detects that the photo meets the requirements, it sends an instruction to smart screen 13 to end the shooting process; if mobile phone 12 detects that the photo does not meet the requirements, it sends an instruction to smart screen 13 to retake the side view using camera 1201.

[0179] After the smart screen 13 receives the instruction sent by the mobile phone 12 for indicating the end of shooting, the smart screen 13 can close the camera and end the shooting work.

[0180] Further, after receiving the front and side photos of the person A to be tested sent by the smart screen 13 and detecting that the front and side photos meet the requirements, the mobile phone 12 can perform image segmentation on the front and side photos based on a neural network (such as Unet network) to extract the human image. Then, the mobile phone 12 can determine the human node positions such as armpit, groin, navel, and thigh root according to the skeleton nodes and contour nodes. Then, the mobile phone 12 can determine the feature information such as chest width, chest thickness, waist width, waist thickness, hip width, hip thickness, thigh width, and thigh thickness based on the human node positions, the human image, and the height. Then, the mobile phone 12 can infer the body shape parameters such as chest circumference, waist circumference, and hip circumference based on the determined feature information. For example, the waist circumference is an ellipse, so the waist circumference can be inferred based on the waist width and the waist thickness.

[0181] Further, the mobile phone 12 can input the body shape parameters such as the waist circumference, BMI, body fat rate, and waist-hip ratio of the person A to be tested into the determined grade determination model to obtain the liver fat grade of the person A to be tested. In one example, after the waist-hip ratio of the person to be tested is determined based on the front and side photos, the waist-hip ratio determined based on the body impedance can be compared with the waist-hip ratio determined based on the photos. If the intervals of the two waist-hip ratios are consistent when determining the body shape parameters, the grade determination model determined before the shooting can be continuously used. If the intervals of the two waist-hip ratios are inconsistent when determining the body shape parameters, the body shape of the person A to be tested can be determined again based on the waist-hip ratio determined based on the photos, the grade determination model can be determined again, and the liver fat grade of the person A to be tested can be calculated based on the determined grade determination model. In one example, after the body shape of the person A to be tested is determined again, the body shape determined before the shooting can be replaced with the determined body shape and presented to the person A to be tested.

[0182] In this scheme, after the mobile phone 12 obtains the front and side photos of the person A to be tested and before the mobile phone 12 obtains the liver fat grade of the person A to be tested, i.e., during the process of calculating the liver fat grade of the person A to be tested, the mobile phone 12 can display an interface as shown in FIG. 13A to FIG. 13C to the person A to be tested to inform the person A to be tested of the processing progress. Figure 10d It can be understood that the parameters input into the grade determination model can also include other parameters such as the visceral fat amount in the trunk, the fat amount of each segment of the body, the body shape, the chest circumference, the hip circumference, and the like, so as to improve the detection accuracy.

[0183] After the mobile phone 12 calculates the liver fat level of the person A to be measured, the mobile phone 12 can display the liver fat level as shown in Figure 10e In addition, in order to enable the person A to be measured to know the body feature parameters (i.e. body size information) of himself / herself, the mobile phone 12 can also display an interface as shown in Figure 10f to enable the person A to be measured to intuitively know the parameters such as the chest circumference, waist circumference, hip circumference and waist-hip ratio of himself / herself. It can be understood that Figure 10e and 10f The display order of the interfaces shown in FIGS. 15 and 16 can be determined according to actual conditions and is not limited herein. In addition, the mobile phone 12 can also send the measured liver fat level and / or the body feature parameters to the smart screen 13, for example, in a projection manner to the smart screen 13, so as to be displayed on the smart screen 13.

[0184] Therefore, in the liver fat level detection process, the body feature parameters and body shape parameters of the person to be measured are combined, so that different processing manners are adopted for different people, the accuracy of the liver fat level evaluation is further improved, and the situation that all people are evaluated by one liver fat level evaluation manner is avoided.

[0185] Next, based on the above-described liver fat level detection scheme, a physiological parameter detection method provided by the embodiments of the present application is introduced. It can be understood that the method is proposed based on the above-described liver fat level detection scheme, and part or all of the contents in the method can be referred to the description of the liver fat level detection scheme above.

[0186] Figure 12 is a flowchart of a physiological parameter measurement method provided by the embodiments of the present application. As shown in Figure 12 The method can include the following steps:

[0187] Step 101, determining a first body parameter and a second body parameter of a person to be measured.

[0188] In the present scheme, the first body parameter and the second body parameter can be measured by a first electronic device. The first electronic device can have at least 8 electrodes, and the second body parameter can be measured based on the at least 8 electrodes of the first electronic device. For example, the second body parameter can be measured by the first electronic device controlling the at least 8 electrodes to generate at least two different frequency electrical signals, so that the second body parameter is measured by different frequency electrical signals, thereby improving the accuracy of subsequent detection. For example, the first electronic device can be a body fat scale 11 as shown in Figure 1a

[0189] ​In one example, the first body parameter can be weight, and the second body parameter can be body impedance or raw data (e.g. voltage, current, etc.) required for calculating body impedance. In one example, the body impedance can include impedance related to both arms, impedance related to both legs, and impedance related to the torso. Exemplary, the impedance related to both arms can include impedance of both arms, impedance of left arm, or impedance of right arm, etc., the impedance related to both legs can include impedance of both legs, impedance of left leg, or impedance of right leg, etc., and the impedance related to the torso can include impedance of the torso, or other impedance including the impedance of the torso, etc.

[0190] Step 102, determining a third body parameter in response to input of the person to be measured.

[0191] Exemplary, the third body parameter can be height.

[0192] Step 103, determining a fourth body parameter according to the first body parameter and the third body parameter.

[0193] Exemplary, the fourth body parameter can be body mass index (BMI). When the first body parameter is weight and the third body parameter is height, the fourth body parameter can be BMI. The formula for determining BMI is: Body Mass Index (BMI) = W / H 2 wherein W is weight and H is height.

[0194] Step 104, determining a first body shape of the person to be measured according to the second body parameter.

[0195] In one example, when determining the first body shape of the person to be measured, a fifth body parameter can be determined according to the second body parameter first. Then, judging the interval to which the fifth body parameter belongs. Wherein, if the fifth body parameter belongs to a first interval, the first body shape of the person to be measured is determined according to the fourth body parameter; if the fifth body parameter belongs to a second interval, the first body shape of the person to be measured is determined according to a sixth body parameter, wherein the sixth body parameter is obtained based on the second body parameter. Exemplary, the fifth body parameter can be waist-hip ratio, and the sixth body parameter can be muscle mass or fat mass of both arms of the person to be measured, etc. Wherein, when the second body parameter is body impedance, the fat mass of each segment of the body of the person to be measured can be determined based on the body impedance using the formula three described above first, and then the waist-hip ratio can be determined based on the fat mass using the formula four described above; then the body shape is determined by the waist-hip ratio selected body parameter, and finally the body shape is determined by the selected body parameter. Exemplary, the selected body parameter can be BMI, muscle mass, fat mass, etc. The method for calculating muscle mass can be referred to the description in the formula five above.

[0196] Step 105, determining a first physiological parameter according to at least the first body shape and the fourth body parameter.

[0197] In this scheme, based on the first body shape, a pre-determined correspondence between body shapes and detection models can be queried to determine the detection model corresponding to the first body shape. Different body shapes correspond to different detection models in the correspondence. At least a fourth body parameter is input into the detection model corresponding to the first body shape to determine the first physiological parameter. Thus, based on the body shape of the test subject, a detection model suitable for that body shape is determined. This detection model is then used to detect the physiological parameters of the test subject, thereby enabling the use of different detection models for users with different body shapes to detect physiological parameters, improving the accuracy of physiological parameters. For example, the detection model can be the grade determination model described above, and the correspondence can be as shown in Table 1 above. For example, the first physiological parameter can be the liver fat grade.

[0198] Step 106: Display the first physiological parameters.

[0199] In this scheme, after determining the first physiological parameter of the test subject, the first physiological parameter can be displayed so that the test subject can intuitively view their own physiological parameters. For example, when the first physiological parameter is the liver fat grade, it can be displayed as follows: Figure 7 The interface shown displays this first physiological parameter.

[0200] In one example, after displaying the first physiological parameter, the subject's first physiological parameter can be precisely measured. Specifically, such as... Figure 13 As shown, it includes the following steps:

[0201] Step 201: In response to the first operation of the person being tested, determine the first and second photos of the person being tested.

[0202] In this process, the subject can perform a first operation, which can be a precise measurement of a first physiological parameter. Following this first operation, a first photograph and a second photograph of the subject can be taken. Specifically, in this scheme, the first photograph is taken when the subject performs a first preset action, and the second photograph is taken when the subject performs a second preset action.

[0203] For example, when the first physiological parameter is the liver fat grade, the first operation can be performed on the test subject... Figure 7 The click operation is located at point 61 in the central area. The first photo can be a frontal photo of the test subject, and the second photo can be a side photo of the test subject. The methods for obtaining the frontal and side photos are detailed in scenarios one through three above, and will not be repeated here.

[0204] In one example, determining the first photo and the second photo of the to-be-tested person can specifically include: determining an action difference degree between an action of the to-be-tested person in a target photo currently acquired and a target preset action, and determining that the action difference degree is within a preset range; wherein the target photo is the first photo, and the target preset action is the first preset action, or the target photo is the second photo, and the target preset action is the second preset action. In this way, the acquired photo is used for detection when the to-be-tested person performs the preset action, and the accuracy of physiological parameter detection is improved. Exemplarily, the action difference degree can be detected by using the human body skeleton key point detection algorithm (Pictorial Structure) based on template matching and the human body skeleton key point detection algorithm based on target detection described above, such as a cascaded feature network (CFN), a regional multi-person pose estimation (RMPE), a cascaded pyramid network (CPN), and the like. Details are described above.

[0205] Step 202, determining an eighth body parameter of the to-be-tested person according to the first photo and the second photo.

[0206] In this way, after the first photo and the second photo are determined, the eighth body parameter of the to-be-tested person can be determined according to the first photo and the second photo. Exemplarily, the eighth body parameter can be a waist circumference. Details of the determination of the waist circumference are described above in scenes one to three, and will not be described here.

[0207] Step 203, re-determining the first physiological parameter according to at least the first body shape, the fourth body parameter and the eighth body parameter.

[0208] In this way, after the eighth parameter is determined, the first body shape can be used to query a predetermined corresponding relationship between a body shape and a detection model to determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the second corresponding relationship. At least the fourth body parameter and the eighth body parameter are input into the detection model corresponding to the first body shape, and the first physiological parameter is re-determined. Exemplarily, the detection model can be the level determination model described above, and the corresponding relationship can be shown in Table 1. Exemplarily, the first physiological parameter can be a liver fat level.

[0209] In one example, before the fourth body parameter and the eighth body parameter are input into the detection model corresponding to the first body shape, a ninth body parameter of the to-be-measured person can also be determined according to the first photo and the second photo; and a second body shape of the to-be-measured person can be determined according to the eighth body parameter and the ninth body parameter. Exemplarily, the ninth body parameter can be a hip circumference. Since the body shape of the to-be-measured person can be accurately presented on the photo, the body shape of the to-be-measured person can be accurately determined through the photo of the to-be-measured person, and the accuracy of the body shape detection is improved. For the determination method of the hip circumference, refer to the description in scenes one to three above, which will not be repeated here.

[0210] In one example, if the second body shape is inconsistent with the first body shape, a detection model corresponding to the second body shape can be determined according to the second body shape by querying the corresponding relationship, and the first physiological parameter can be determined again by using the detection model corresponding to the second body shape. Thus, the body shape of the to-be-measured person detected through the photo is used as a reference, and the physiological parameter of the to-be-measured person is detected, and the accuracy of the physiological parameter detection is improved.

[0211] Step 204, display the first physiological parameter.

[0212] After the first physiological parameter is determined, the redetermined first physiological parameter can be displayed. Exemplarily, the redisplayed first physiological parameter can be displayed in the interface shown in FIG. 11. Figure 10e In addition, the redetermined body shape of the to-be-measured person can also be displayed.

[0213] It should be noted that, Figure 12 The method provided in the embodiment can be executed by the first electronic device or the second electronic device. When executed by the second electronic device, the second electronic device and the first electronic device can be in communication connection; and when determining the first body parameter and the second body parameter of the to-be-measured person, the second electronic device can receive the first body parameter and the second body parameter sent by the first electronic device. Thus, the physiological parameter of the to-be-measured person is detected by combining multiple electronic devices. Exemplarily, the first electronic device can be the body fat scale 11 shown in FIG. 11, and the second electronic device can be the mobile phone 12 shown in FIG. 12. Figure 1a Figure 1a

[0214] Next, based on the liver fat grade detection scheme described above, a physiological parameter detection system provided by the embodiment of the present application is introduced. It can be understood that the system is proposed based on the liver fat grade detection scheme described above, and part or all of the contents in the method can be referred to the description of the liver fat grade detection scheme above.

[0215] Figure 14 ​​Fig. 1 is a schematic diagram of an architecture of a physiological parameter measurement system according to an embodiment of the present application. As shown in Fig. 1, the system includes a first electronic device 1401 and a second electronic device 1402, which are communicatively connected, and the first electronic device 1401 has at least eight electrodes. Figure 14

[0216] The first electronic device 1401 can be configured to determine a first body parameter and a second body parameter of a person to be measured, and send the first body parameter and the second body parameter to the second electronic device 1402, wherein the second body parameter is measured based on the at least eight electrodes. The second electronic device 1402 can be configured to determine a third body parameter in response to an input of the person to be measured. The second electronic device 1402 can be further configured to determine a fourth body parameter based on the first body parameter and the third body parameter in response to receiving the first body parameter and the second body parameter. The second electronic device 1402 can be further configured to determine a first body shape of the person to be measured based on the second body parameter. The second electronic device 1402 can be further configured to determine a first physiological parameter based on at least the first body shape and the fourth body parameter, and display the first physiological parameter.

[0217] For example, the first electronic device 1401 can be a body fat scale 11 as shown in Fig. 1, and the second electronic device 1402 can be a mobile phone 12 as shown in Fig. 1. Figure 1a Figure 1a

[0218] In one example, the second electronic device 1402 can be further configured to:

[0219] determine a fifth body parameter based on the second body parameter;

[0220] if the fifth body parameter belongs to a first interval, determine the first body shape of the person to be measured based on the fourth body parameter;

[0221] if the fifth body parameter belongs to a second interval, determine the first body shape of the person to be measured based on a sixth body parameter, wherein the sixth body parameter is obtained based on the second body parameter.

[0222] In one example, the second electronic device 1402 can be further configured to:

[0223] determine a seventh body parameter based on the second body parameter, and determine the fifth body parameter based on the seventh body parameter.

[0224] In one example, the second electronic device 1402 can be further configured to:

[0225] ​​​According to the first body shape, the correspondence relationship between the predetermined body shape and the detection model is queried, and the detection model corresponding to the first body shape is determined, wherein different body shapes correspond to different detection models in the correspondence relationship.

[0226] The fourth body parameter is input into the detection model corresponding to the first body shape, and the first physiological parameter is determined.

[0227] In one example, the second electronic device 1402, after displaying the first physiological parameter, can be further configured to:

[0228] In response to the first operation of the to-be-tested person, the first photo and the second photo of the to-be-tested person are determined, the first photo is taken when the to-be-tested person makes the first preset action, and the second photo is taken when the to-be-tested person makes the second preset action;

[0229] According to the first photo and the second photo, the eighth body parameter of the to-be-tested person is determined;

[0230] According to the first body shape, the fourth body parameter, and the eighth body parameter, the first physiological parameter is re-determined;

[0231] The first physiological parameter is displayed.

[0232] In one example, the second electronic device 1402 can be further configured to: according to the first body shape, query the correspondence relationship between the predetermined body shape and the detection model, and determine the detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the second correspondence relationship; and input the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape to determine the first physiological parameter.

[0233] In one example, the second electronic device 1402, before inputting the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape, can be further configured to: according to the first photo and the second photo, determine the ninth body parameter of the to-be-tested person; and according to the eighth body parameter and the ninth body parameter, determine the second body shape of the to-be-tested person.

[0234] In one example, the second electronic device 1402 can be further configured to: when the second body shape is inconsistent with the first body shape, according to the second body shape, query the correspondence relationship, determine the detection model corresponding to the second body shape, and select the detection model to determine the first physiological parameter.

[0235] In one example, the second electronic device 1402 can be further configured to: determine the action difference degree between the action of the to-be-tested person in the target photo currently acquired and the target preset action, and determine that the action difference degree is within a preset range.

[0236] The target photo is the first photo, and the target preset action is the first preset action, or the target photo is the second photo, and the target preset action is the second preset action.

[0237] In one example, the second electronic device 1402 can also be configured to display the body shape of the person to be measured.

[0238] In one example, the first electronic device 1401 can also be configured to control the at least 8 electrodes to generate at least two different frequency electrical signals, and determine the body parameters measured based on the electrical signals of the respective frequencies to obtain the second body parameters. For example, the first electronic device 1401 can control the 8 electrodes to generate electrical signals of 50 KHz and 250 KHz.

[0239] It should be understood that the second electronic device described above can be configured to execute the method in the above-described embodiments, and the implementation principle and technical effects are similar to those described in the above method. The working process of the second electronic device can refer to the corresponding process in the above method, which will not be described here.

[0240] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0241] The method steps in the embodiments of the present application can be implemented by hardware, or by a combination of software and hardware executed by a processor. The software instructions can be composed of a corresponding software module, which can be stored in a random access memory (RAM), a flash memory, a read-only memory (ROM), a programmable read-only memory (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0242] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0243] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of differentiation, and do not limit the scope of the embodiments of the present application.

Claims

1. A physiological parameter measurement system, characterized by The system comprises a first electronic device and a second electronic device, the first electronic device and the second electronic device are communicatively connected, the first electronic device has at least 8 electrodes; The first electronic device is configured to determine a first body parameter and a second body parameter of a to-be-tested person, and send the first body parameter and the second body parameter to the second electronic device, the second body parameter is measured based on the at least 8 electrodes; the first body parameter comprises body weight, and the second body parameter comprises related data of body impedance; The second electronic device is configured to determine a third body parameter in response to an input of the to-be-tested person; the third body parameter comprises height; The second electronic device is further configured to determine a fourth body parameter according to the first body parameter and the third body parameter in response to receiving the first body parameter and the second body parameter; the fourth body parameter comprises body mass index (BMI); The second electronic device is further configured to determine a first body shape of the to-be-tested person according to the second body parameter; the first body shape comprises one of apple type, pear type, pepper type, hourglass type and inverted triangle type; The second electronic device is further configured to determine a first physiological parameter according to at least the first body shape and the fourth body parameter, and display the first physiological parameter; the first physiological parameter comprises liver fat grade.

2. The system of claim 1, wherein, The second electronic device is further configured to: determine a fifth body parameter according to the second body parameter; the fifth body parameter comprises waist-hip ratio; determine that a parameter value corresponding to the fifth body parameter belongs to a first interval, and determine the first body shape of the to-be-tested person according to the fourth body parameter; or determine that the parameter value corresponding to the fifth body parameter belongs to a second interval, and determine the first body shape of the to-be-tested person according to a sixth body parameter, wherein the sixth body parameter is obtained based on the second body parameter; the sixth body parameter comprises muscle mass or fat mass of both arms.

3. The system of claim 2, wherein, The second electronic device is further configured to: determine a seventh body parameter according to the second body parameter, and determine the fifth body parameter according to the seventh body parameter; the seventh body parameter comprises fat mass of each segment of the body.

4. The system according to any of claims 1-3, characterized in that, The second electronic device is further configured to: query a predetermined correspondence between body shape and detection model according to the first body shape, and determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the correspondence; input at least the fourth body parameter to the detection model corresponding to the first body shape, and determine the first physiological parameter.

5. The system of claim 4, wherein, After displaying the first physiological parameter, the second electronic device is further configured to: determine a first photo and a second photo of the to-be-tested person in response to a first operation of the to-be-tested person, the first photo is taken when the to-be-tested person makes a first preset action, and the second photo is taken when the to-be-tested person makes a second preset action; determine an eighth body parameter of the to-be-tested person according to the first photo and the second photo; the eighth body parameter comprises a waistline; redetermine the first physiological parameter according to at least the first body shape, the fourth body parameter and the eighth body parameter; display the first physiological parameter.

6. The system of claim 5, wherein, The second electronic device is further configured to: query a predetermined correspondence between body shapes and detection models according to the first body shape, and determine a detection model corresponding to the first body shape, wherein different body shapes correspond to different detection models in the second correspondence; input at least the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape, and determine the first physiological parameter.

7. The system of claim 6, wherein, Before the second electronic device inputs the fourth body parameter and the eighth body parameter into the detection model corresponding to the first body shape, the second electronic device is further configured to: determine a ninth body parameter of the to-be-tested person according to the first photo and the second photo; the ninth body parameter comprises a hip circumference; determine a second body shape of the to-be-tested person according to the eighth body parameter and the ninth body parameter, and determine that the second body shape is consistent with the first body shape.

8. The system of claim 7, wherein, The second electronic device is further configured to: determine that the second body shape is inconsistent with the first body shape; query the correspondence according to the second body shape, determine a detection model corresponding to the second body shape, and select the detection model to determine the first physiological parameter.

9. The system of any of claims 5-7, wherein, The second electronic device is further configured to: determine a motion difference degree between a motion of the to-be-tested person in a target photo currently acquired and a target preset motion, and determine that the motion difference degree is within a preset range; wherein the target photo is the first photo, and the target preset motion is the first preset motion, or the target photo is the second photo, and the target preset motion is the second preset motion.

10. The system of any of claims 1-3, wherein, The second electronic device is further configured to: display the body shape of the to-be-tested person.

11. The system of any of claims 1-3, wherein, The first electronic device is further configured to: control the at least 8 electrodes to generate electrical signals of at least two different frequencies; determine body parameters measured based on electrical signals of each frequency respectively, and obtain the second body parameters.

12. An electronic device, comprising: comprise: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, and when the programs stored in the memory are executed, the processor is configured to execute the algorithm functions embodied in the system according to any one of claims 1-11.

13. A computer storage medium, wherein instructions are stored in the computer storage medium, and when the instructions are run on a computer, the computer is caused to execute the algorithm functions embodied in the system according to any one of claims 1-11.

14. A computer program product comprising instructions, and when the instructions are run on a computer, the computer is caused to execute the algorithm functions embodied in the system according to any one of claims 1-11.

Images