Weight change prediction method and device based on user characteristics

Abstract

The invention relates to the technical field of body weight prediction, and discloses a body weight change prediction method and device based on user characteristics, which comprehensively considers a plurality of factors to accurately predict target exercise consumption and daily energy intake demand of a target user in a to-be-measured period, and further combines the target exercise consumption and daily energy intake demand to predict the body weight change of the target user. A weight change value and an energy balance value of a target user in a to-be-measured period are accurately predicted by using a pre-trained weight change prediction model, and in weight change prediction, the energy balance value of the target user in the to-be-measured period is predicted according to a balance relation between energy intake and exercise consumption of the target user and adaptability of a body to energy change. And the body composition and the energy consumption parameter of the target user are dynamically adjusted, so that more accurate prediction of the weight change of the target user is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of weight prediction, and in particular to a method and device for predicting weight change based on user characteristics. Background Art

[0002] With the improvement of living standards, more and more people are overweight due to overnutrition caused by improper diet control and lack of exercise, which can cause health problems. Therefore, paying attention to the changes in user weight is crucial to the user's health.

[0003] In the related art, when predicting the weight change of the measured user, due to the uncertainty of the measured user's daily energy intake requirement, even if the measured user strictly follows the diet plan, the weight change prediction will still produce errors. Therefore, when predicting the weight change of the measured user in the traditional way, due to the uncertainty of the measured user's calorie requirement, there will be prediction errors when predicting the weight change of the measured user. Summary of the invention

[0004] In view of this, the present invention provides a method and device for predicting weight changes based on user characteristics to solve the problem of prediction errors in predicting weight changes of a measured user due to the uncertainty of the calorie demand of the measured user in the traditional method.

[0005] In a first aspect, the present invention provides a method for predicting weight change based on user characteristics, the method comprising:

[0006] Obtaining the target user's tag information, exercise information, test period, diet information, and basic information affecting the target user's energy intake, wherein the basic information affecting the target user's energy intake is determined based on the tag information;

[0007] Obtain the target user's daily energy intake requirements based on the basic information that affects the target user's energy intake;

[0008] According to the motion information, the period to be measured and the tag information, the target motion consumption of the target user in the period to be measured is obtained;

[0009] The label information, basic information affecting the target user's energy intake and target exercise consumption are input into a weight change prediction model to predict the target user's weight change value and energy balance value during the test period, wherein the weight change prediction model is a pre-trained neural network model.

[0010] In the embodiments of the present disclosure, multiple factors are comprehensively considered to accurately predict the target exercise consumption and daily energy intake requirements of the target user during the period to be measured. Further, in combination with the target exercise consumption and daily energy intake requirements, a pre-trained weight change prediction model is used to accurately predict the weight change value and energy balance value of the target user during the period to be measured. In the weight change prediction, according to the balance relationship between the energy intake and consumption of the target user and the adaptability of the body to energy changes, the body composition and energy consumption parameters of the target user are dynamically adjusted, so as to achieve a more accurate prediction of the weight change of the target user.

[0011] In an alternative embodiment, the label information includes: gender, height, age, initial weight, observation period, initial energy intake target, activity coefficient, historical exercise consumption and historical weight change value of the target user during the observation period; the basic information affecting the energy intake of the target user is determined according to the label information, including:

[0012] According to the initial weight, age, height and gender, calculate the initial fat parameter of the target user;

[0013] According to the initial weight and initial fat parameter of the target user, calculate the initial fat-free weight parameter of the target user;

[0014] According to the initial weight, age, and height, calculate the basal metabolic rate of the target user;

[0015] According to the basal metabolic rate and activity coefficient of the target user, calculate the spontaneous activity energy of the target user;

[0016] According to the initial energy intake target, initial fat parameter, observation period and initial fat-free weight parameter, calculate the total energy deficit of the target user during the observation period;

[0017] According to the historical exercise consumption of the target user during the observation period, calculate the daily energy consumption of the target user during the observation period.

[0018] Since the embodiments of the present disclosure record some specific label information of the target user (the initial weight, age, height and gender of the target user), the embodiments of the present disclosure can quickly calculate the basic information affecting the energy intake of the target user through some calculation rules.

[0019] In an alternative embodiment, according to the exercise information, the period to be measured and the label information, obtain the target exercise consumption of the target user during the period to be measured, including:

[0020] According to the motion information, the period to be measured, and the label information, use the motion energy consumption model to predict the target motion consumption of the target user during the period to be measured, and recommend the target motion consumption of the target user during the period to be measured according to the daily energy intake requirement, the weight change value of the target user during the period to be measured, and the energy balance value, where the motion energy consumption model is a neural network model pre-trained.

[0021] In some alternative embodiments, the label information further includes: the weight change value of the target user during the observation period, and the basic information affecting the energy intake of the target user further includes: the fat tissue weight parameter and the non-fat tissue weight parameter. Recommending the target motion consumption of the target user during the period to be measured according to the daily energy intake requirement, the weight change value of the target user during the period to be measured, and the energy balance value includes:

[0022] Calculate the energy gap conversion amount of the target user according to the weight change value, the fat tissue weight parameter, and the non-fat tissue weight parameter of the target user during the observation period;

[0023] Calculate the updated target motion consumption of the target user during the period to be measured according to the daily energy intake requirement, the basal metabolism, the spontaneous activity energy, and the energy gap conversion amount;

[0024] Keep adjusting the target motion consumption of the target user during the period to be measured according to the initial energy intake target until the target user achieves the initial energy intake target.

[0025] In the process of predicting the weight change of the target user in the embodiments of the present disclosure, it is possible to accurately infer the motion consumption of the target user during the period to be measured based on the weight change value of the target user during the period to be measured, and recommend the target motion consumption of the target user during the period to be measured according to the weight change value of the target user during the period to be measured and the energy balance value, further optimizing the motion consumption of the target user during the period to be measured, and thus providing a more reliable basis for fat loss or health management.

[0026] In some alternative embodiments, obtaining the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user includes:

[0027] Predict the daily energy intake requirement of the target user using the energy intake prediction model according to the basic information affecting the energy intake of the target user, and adjust the daily energy intake requirement of the target user according to the weight change value of the target user during the period to be measured and the energy balance value, where the energy intake prediction model is a neural network model pre-trained.

[0028] Embodiments of the present disclosure use an energy intake prediction model to predict the daily energy intake requirement of a target user, so as to ensure the accuracy of the prediction of the daily energy intake requirement. Moreover, during the process of predicting the daily energy intake requirement of the target user, the daily energy intake requirement of the target user can be adjusted according to the weight change value and the energy balance value of the target user, further enhancing the accuracy of the prediction of the daily energy intake requirement.

[0029] In some alternative embodiments, predicting the daily energy intake requirement of the target user by using the energy intake prediction model according to the basic information affecting the energy intake of the target user includes:

[0030] Calculating the daily energy intake requirement of the target user according to the basal metabolic rate of the target user, the spontaneous activity energy of the target user, the daily energy gap of the target user during the observation period, the historical exercise consumption of the target user during the observation period, and the daily energy consumption.

[0031] Embodiments of the present disclosure predict the daily energy intake requirement of the target user through the energy intake prediction model, ensuring the accuracy of the daily energy intake requirement of the target user.

[0032] In some alternative embodiments, the basic information affecting the energy intake of the target user includes: the amount of fat change and the amount of fat-free change. Inputting the label information, the basic information affecting the energy intake of the target user, and the target exercise consumption into the weight change prediction model to predict the weight change value and the energy balance value of the target user during the period to be measured, including:

[0033] Obtaining the initial weight of the target user from the label information;

[0034] Obtaining the initial fat parameter, the initial fat-free weight parameter, the amount of fat change, and the amount of fat-free change of the target user from the basic information affecting the energy intake of the target user, and predicting the weight change value and the energy balance value of the target user during the period to be measured.

[0035] Embodiments of the present disclosure can achieve a more accurate prediction of the weight change of the target user by introducing the weight change prediction model.

[0036] In a second aspect, the present invention provides a weight change prediction device based on user characteristics, including:

[0037] A first acquisition module, configured to acquire the label information, exercise information, period to be measured, diet information, and basic information affecting the energy intake of the target user of the target user, wherein the basic information affecting the energy intake of the target user is determined according to the label information;

[0038] A second acquisition module, configured to acquire the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user;

[0039] A third acquisition module, configured to acquire the target exercise consumption of the target user during the period to be measured according to the exercise information, the period to be measured, and the tag information;

[0040] A weight prediction module, configured to input the tag information, the basic information affecting the energy intake of the target user, and the target exercise consumption into a weight change prediction model to predict the weight change value and the energy balance value of the target user during the period to be measured, where the weight change prediction model is a neural network model pre-trained.

[0041] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the weight change prediction method based on user characteristics according to the first aspect or any corresponding implementation manner thereof.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the weight change prediction method based on user characteristics according to the first aspect or any corresponding implementation manner thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 is a schematic flowchart of a weight change prediction method based on user characteristics according to an embodiment of the present invention;

[0045] Figure 2 is a schematic flowchart of another weight change prediction method based on user characteristics according to an embodiment of the present invention;

[0046] Figure 3 is a schematic flowchart of yet another weight change prediction method based on user characteristics according to an embodiment of the present invention;

[0047] Figure 4 is a schematic flowchart of still another weight change prediction method based on user characteristics according to an embodiment of the present invention;

[0048] Figure 5 is a schematic diagram of a weight change prediction method based on user characteristics according to an embodiment of the present invention;

[0049] Figure 6 is a structural block diagram of a device for predicting weight changes based on user characteristics according to an embodiment of the present invention;

[0050] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0052] According to an embodiment of the present invention, an embodiment of a method for predicting weight change based on user characteristics is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0053] In this embodiment, a method for predicting weight change based on user characteristics is provided, which can be used in the above-mentioned computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 3 is a flow chart of a method for predicting weight change based on user characteristics according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0054] Step S101, obtaining tag information, exercise information, test period, diet information and basic information affecting energy intake of the target user, wherein the basic information affecting energy intake of the target user is determined according to the tag information.

[0055] Specifically, the target user may be any user of different types. For example, the target user may represent the target user U1 or the target user U2 or the target user U3.

[0056] In a specific example, the target user's tag information includes but is not limited to: the target user's height, gender, age, initial weight, observation period, initial energy intake target, activity coefficient, the target user's historical exercise consumption during the observation period, and historical weight change values.

[0057] The target user's height, gender, age, initial weight, observation period, initial energy intake target, activity coefficient and other information mentioned above belong to the target user's user registration information, and the target user's historical exercise consumption and historical weight change values during the observation period belong to the target user's behavior information. All of this information can be monitored through the weight change monitoring instrument.

[0058] For example, the target user U1 is male, 48 years old, with an initial weight of 62 kg, an observation period of 14 days, an initial energy intake target of 0.5 kg / 7 days, and an activity coefficient of energy intake parameters. The daily activity level (PAL) in the activity coefficient is as follows:

[0059] Sedentary lifestyle (Sedentary), PAL = 1.2;

[0060] Lightly Active, PAL = 1.375;

[0061] Moderately Active, PAL = 1.55;

[0062] Very Active, PAL = 1.725;

[0063] Extra Active, PAL=1.9.

[0064] In another specific example, the target user's exercise information includes but is not limited to exercise type, exercise parameters, exercise intensity, exercise duration, rest duration, and historical running records, etc. For example, exercise types include but are not limited to cycling, running, etc. The exercise parameters for cycling include but are not limited to: cycling speed, power, cadence, distance, climbing slope, historical cycling records, etc.; the exercise parameters for running include but are not limited to: pace, distance, cadence, vertical amplitude, climbing height, historical running records, etc.

[0065] In another specific example, the period to be measured is a predicted time of the target user in the next few days or months, for example, a predicted weight change value of the target user in the next 14 days.

[0066] In another specific example, dietary information includes: user's daily dietary record information, for example, the user manually records dietary intake, such as: 1 egg ~ 75Kcal, for example, the user completes a dietary questionnaire, and further estimates energy intake through the dietary questionnaire, for example: how many meals a day, the proportion of staple food in each meal, the proportion of meat, etc.

[0067] In another specific example, the basic information affecting the target user's energy intake includes, but is not limited to, the target user's initial fat parameter, initial fat-free body weight parameter, basal metabolic rate, the target user's spontaneous activity energy, the target user's daily energy gap within the observation period, the target user's daily energy consumption within the observation period, fat change amount, and non-fat change amount.

[0068] The above-mentioned initial fat parameter includes initial fat mass and initial body fat percentage. The initial fat mass can be represented by F0. For example, F0 = 15.8 kg, and the initial body fat percentage can be represented by F0%. For example, F0% = 29.8%.

[0069] The initial fat mass F0 can be solved by the following equation:

[0070] For male: (W0 - (F0 - 71.73349 + 3.5907722 * F0 - 0.038273 * age + 0.6555023

[0071] * heigh - 0.002296 * F0 * age - 0.013308 * F0 * heigh + 0.0000332 * F0 ** 2 *

[0072] Age - 0.07195 * F0 ** 2 + 0.0006841 * F0 ** 3 - 0.00000162 * F0 ** 4 + 0.0002721 * F0 ** 2 * height - 0.00000187 * F0 ** 3 * heigh));

[0073] For female: W0 - (-72.055453 + 2.4837412 * F0 - 0.038273 * age + 0.6555023 * height - 0.002296 * F0 * age - 0.013308 * F0 * height - 0.0390627 * F0 ** 2 + 0.0000332 * F0 ** 2 * age + 0.00000035 * F0 ** 4 + 0.0002291 * F0 ** 3 + 0.0002721 * F0 ** 2 * height - 0.00000187 * F0 ** 3 * height + F0));

[0074] Wherein, W0 is the initial weight, F0 is the initial fat mass, age is the age, and heigh is the height.

[0075] The above-mentioned initial fat-free body weight parameter includes initial fat-free body weight and initial fat-free ratio. The initial fat-free body weight can be represented by FFM0, and the initial fat-free ratio can be represented by FFM0%.

[0076] The basal metabolic rate mentioned above is represented by BMR, and the resting metabolic data is represented by RMR. Among them, for men, RMR = 66.47 + (13.75 × W0) + (5.003 × height) - (6.755 × age); for women, RMR = 655.1 + (9.563 × W0) + (1.850 × height) - (4.676 × age).

[0077] The spontaneous activity energy of the target user mentioned above can be represented by SPA, and the initial spontaneous activity energy can be represented by SPA0, and SPA0 = (PAL - 1) * RMR.

[0078] The daily energy deficit of the target user during the observation period mentioned above represents the energy reduced by the target user due to weight loss during the period to be measured.

[0079] The daily energy consumption of the target user during the observation period mentioned above can be calculated by the following formula: exe_cal’ = METs * W0 * Hr, where exe_cal’ represents the daily energy consumption of the target user during the observation period, METs represents the exercise metabolic equivalent, W0 represents the initial weight, Hr represents the exercise duration, and the specific value of METs is associated with the exercise type. The amount of fat change mentioned above can be represented by delta_f, and the amount of non-fat change can be represented by delta_ffm.

[0080] delta_f = (1.0 - 1.990762711864407 / (1.990762711864407 + F_N - 1)) * (daily energy intake requirement - RMR - SPA0 - exe_cal - glycogen storage) / 9440.0.

[0081] delta_ffm = delta_f = (1.0 - 1.990762711864407 / (1.990762711864407 + F_N - 1)) * (daily energy intake requirement - RMR - SPA0 - target exercise energy consumption - glycogen storage) / 1807.

[0082] Step S102, according to the basic information affecting the energy intake of the target user, obtain the daily energy intake requirement of the target user.

[0083] In a specific example, the daily energy intake requirement of the target user can be predicted by using a neural network model, and can also be obtained by detecting with an energy intake detection instrument. However, in the embodiments of the present disclosure, in order to ensure accurate acquisition of the daily energy intake requirement of the target user, it is preferred to use a neural network model to predict the daily energy intake requirement of the target user.

[0084] Step S103: Obtain the target exercise consumption of the target user during the period to be measured according to the exercise information, the period to be measured, and the label information.

[0085] Similarly, the target exercise consumption is the energy consumption generated by the target user due to exercise. For example, the target user generates 80 kcal for running 1 kilometer. The target exercise consumption can also be predicted by a neural network model or detected by an exercise consumption detection instrument. However, in the embodiments of the present disclosure, in order to accurately obtain the target exercise consumption of the target user during the period to be measured, it is preferred to use a neural network model to predict the daily energy intake requirement of the target user.

[0086] Step S104: Input the label information, the basic information affecting the energy intake of the target user, the daily energy intake requirement, and the target exercise consumption into the weight change prediction model to predict the weight change value and the energy balance value of the target user during the period to be measured, where the weight change prediction model is a pre-trained neural network model.

[0087] Specifically, the basic information affecting the energy intake of the target user and the target exercise consumption have been described above and will not be elaborated here. The weight change value is the weight change trend of the target user in the next N days, and the energy balance value is the energy balance value generated by the target user to achieve the initial energy intake target. This energy balance value is usually the initial weight of the target user minus the weight loss target.

[0088] The overall concept of the embodiments of the present disclosure combines some physiological characteristics (such as gender, age, height, weight, etc.) and behavioral characteristics of the target user, comprehensively considers multiple factors to accurately predict the target exercise consumption and the daily energy intake requirement of the target user during the period to be measured. Further, in combination with the target exercise consumption and the daily energy intake requirement, a pre-trained weight change prediction model is used to accurately predict the weight change value and the energy balance value of the target user during the period to be measured. In the weight change prediction, according to the balance relationship between the energy intake and consumption of the target user and the adaptability of the body to energy changes, the body composition and energy consumption parameters of the target user are dynamically adjusted, so as to achieve a more accurate prediction of the weight change of the target user.

[0089] Therefore, since the embodiments of the present disclosure consider in advance various factor information of the target user (label information, exercise information, period to be measured, diet information, and basic information affecting the energy intake of the target user), the daily energy intake requirement of the target user and the target exercise consumption of the target user during the period to be measured are accurately determined, and then the weight change prediction model is used to predict the weight change value of the target user during the period to be measured, improving the accuracy of predicting the weight change value and the energy balance value of the target user.

[0090] In this embodiment, a method for predicting weight change based on user characteristics is provided, which can be used in the above-mentioned computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 2 FIG. Figure 2 is a flowchart of a method for predicting weight change based on user characteristics according to an embodiment of the present invention. The label information includes: gender, height, age, initial weight, observation period, initial energy intake target, activity coefficient, historical exercise consumption and historical weight change value of the target user during the observation period. In step S101, the basic information affecting the energy intake of the target user is determined according to the label information, including:

[0091] Step S201, calculate the initial fat parameter of the target user according to the initial weight, age, height and gender.

[0092] In a specific example, the initial fat parameter includes the initial fat mass and the initial body fat percentage. The initial fat mass can be represented by F0. For example, F0 = 15.8 kg. The initial body fat percentage can be represented by F0%. For example, F0% = 29.8%.

[0093] For the initial fat mass F0, it can be solved by the following equation:

[0094] For male: (W0 - (F0 - 71.73349 + 3.5907722 * F0 - 0.038273 * age + 0.6555023

[0095] * heigh - 0.002296 * F0 * age - 0.013308 * F0 * heigh + 0.0000332 * F0 ** 2 *

[0096] Age - 0.07195 * F0 ** 2 + 0.0006841 * F0 ** 3 - 0.00000162 * F0 ** 4 + 0.0002721 * F0 ** 2 * height - 0.00000187 * F0 ** 3 * heigh));

[0097] For female: W0 - (-72.055453 + 2.4837412 * F0 - 0.038273 * age + 0.6555023 * height - 0.002296 * F0 * age - 0.013308 * F0 * height - 0.0390627 * F0 ** 2 + 0.0000332 * F0 ** 2 * age + 0.00000035 * F0 ** 4 + 0.0002291 * F0 ** 3 + 0.0002721 * F0 ** 2 * height - 0.00000187 * F0 ** 3 * height + F0));

[0098] Wherein, W0 is the initial weight, F0 is the initial fat mass, age is the age, and height is the height.

[0099] Step S202: Calculate the initial fat-free weight parameter of the target user according to the initial weight and the initial fat parameter of the target user.

[0100] In a specific example, the above-mentioned initial fat-free weight parameter includes the initial fat-free body weight and the initial fat-free ratio. The initial fat-free body weight can be represented by FFM0, and the initial fat-free ratio can be represented by FFM0%. The initial fat-free weight (FFM0) = W0 - F0 = 53 - 15.8 = 37.2 (kg).

[0101] Step S203: Calculate the basal metabolic rate of the target user according to the initial weight, age, and height.

[0102] In a specific example, the above-mentioned basal metabolic rate is represented by BMR, and the resting metabolic data is represented by RMR. Among them, for men, RMR = 66.47 + (13.75 × W0) + (5.003 × height) - (6.755 × age); for women, RMR = 655.1 + (9.563 × W0) + (1.850 × height) - (4.676 × age). For example, RMR = 655.1 + (9.563 × 53) + (1.850 × 167) - (4.676 × 32) = 1331.25 Kcal.

[0103] Step S204: Calculate the spontaneous activity energy of the target user according to the basal metabolic rate and the activity coefficient of the target user.

[0104] Specifically, the spontaneous activity energy of the target user can be represented by SPA, and the initial spontaneous activity energy can be represented by SPA0. SPA0 = (PAL - 1) * RMR. For example, SPA = 1.25 - 1 * 1331.25 = 332.8 Kcal.

[0105] Step S205: Calculate the total energy deficit of the target user during the observation period according to the initial energy intake target, the initial fat parameter, the observation period, and the initial fat-free weight parameter.

[0106] Specifically, EM = (delt_w) * (9500 * F0% + 1020 * FFM0%) = 0.5 * (2831 + 716) = 1773.5 Kcal. EM' = EM / T, where T is the observation period, EM' is the daily energy gap of the target user during the observation period, EM is the total energy gap of the target user during the observation period, EM' is the daily energy gap of the target user during the observation period, delt_w is the initial energy intake target, F0% is the initial fat parameter (initial body fat percentage), and FFM0% is the initial fat-free body mass parameter (initial fat-free ratio). For example, EM' = EM / T = 1773.5 / 14 = 126.68 Kcal.

[0107] Step S206, calculating the daily energy consumption of the target user during the observation period according to the historical exercise consumption of the target user during the observation period.

[0108] For example, the observation period is 14 days, the daily energy consumption of the target user during the observation period is represented by exe_cal', the historical exercise consumption of the target user during the observation period is represented by exe_cal, and exe_cal'=exe_cal / 14.

[0109] Since the embodiment of the present disclosure records some specific label information of the target user (initial weight, age, height and gender of the target user), the embodiment of the present disclosure can quickly calculate the basic information that affects the energy intake of the target user through some calculation rules.

[0110] In this embodiment, a method for predicting weight change based on user characteristics is provided, which can be used in the above-mentioned computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 3 is a flow chart of a method for predicting weight changes based on user characteristics according to an embodiment of the present invention. The above step S103, based on the exercise information, the period to be measured and the tag information, obtains the target exercise consumption of the target user in the period to be measured, including:

[0111] Based on the exercise information, the test period and the label information, the exercise energy consumption model is used to predict the target exercise consumption of the target user during the test period, and the target exercise consumption of the target user during the test period is recommended based on the daily energy intake requirements, the weight change value and energy balance value of the target user during the test period, wherein the exercise energy consumption model is a pre-trained neural network model.

[0112] Specifically, the motion information, the period to be measured, and the label information have been described above and will not be elaborated here. Although the metabolic equivalent in the human body is close to the absolute value of the energy consumption calculated by the heart rate device and has a high correlation in energy prediction, the average relative deviation is at the 40% level, and there are also differences between different devices. That is, different motion energy consumption detection devices will have inconsistent detection results due to detection differences when detecting motion energy consumption, which will further cause the target motion consumption of the detected target user during the period to be measured to be inaccurate. In view of this, the embodiments of the present disclosure introduce a motion energy consumption model to improve the accuracy of predicting the target motion consumption of the target user during the period to be measured, and recommend the target motion consumption of the target user during the period to be measured according to the daily energy intake requirement, the weight change value of the target user during the period to be measured, and the energy balance value, thereby providing a more reliable basis for fat loss or health management. Moreover, the embodiments of the present disclosure can provide more personalized energy intake and exercise suggestions according to the specific conditions of different individuals, improving the effectiveness and feasibility of the fat loss plan.

[0113] For example, if the initially predicted target motion consumption by the motion energy consumption model is 30 Kcal, while the recommended target motion consumption is 20 Kcal, combining with the target motion consumption can prompt the target user to reduce the duration or frequency of high-intensity exercise, or increase soothing exercises such as yoga and meditation.

[0114] In the embodiments of the present disclosure, a method for predicting weight change based on user characteristics is provided, which can be used in the above-mentioned computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 4 It is a flowchart of the method for predicting weight change based on user characteristics according to the embodiments of the present invention. According to the motion information, the period to be measured, and the label information, the motion energy consumption model is used to predict the target motion consumption of the target user during the period to be measured, and the target motion consumption of the target user during the period to be measured is recommended according to the daily energy intake requirement, the weight change value of the target user during the period to be measured, and the energy balance value, including:

[0115] Step S401, calculate the energy gap conversion amount of the target user according to the weight change value, the fat tissue weight parameter, and the non-fat tissue weight parameter of the target user during the observation period.

[0116] Specifically, the weight change value of the target user during the observation period can be represented by delta_w, and the weight change value of the target user during the observation period can be detected by a weight detection instrument. The fat tissue weight parameter can be the fat tissue weight percentage, represented by FM%, and the fat tissue weight parameter can be the fat tissue weight percentage, represented by the fat tissue weight parameter FFM%. The calculation formula for the weight change value delt_e of the target user during the observation period is expressed by the following formula:

[0117] delt_e = (delta_w) * (9500 * FM% + 1030 * FFM%).

[0118] Step S402: Calculate the updated target exercise consumption of the target user during the period to be measured according to the daily energy intake requirement, basal metabolism, energy of spontaneous activities, and energy gap conversion amount.

[0119] Specifically, the daily energy intake requirement can be represented by EI, the basal metabolism can be represented by RMR, the energy of spontaneous activities can be represented by SPA0, and the updated target exercise consumption of the target user during the period to be measured is expressed by the following formula: exe_cal” = EI - RMR - SPA0 + delt_e;

[0120] Wherein, exe_cal” is the updated target exercise consumption of the target user, EI is the daily energy intake requirement, RMR is the basal metabolism, SPA0 is the energy of spontaneous activities, and delt_e is the weight change value of the target user during the observation period.

[0121] Step S403: Continuously adjust the target exercise consumption of the target user during the period to be measured according to the initial energy intake target until the target user achieves the initial energy intake target.

[0122] Specifically, for example, the initial energy intake target input into the weight change prediction model is 0.5 kg / 7 days. Then, continuously update the target exercise consumption of the target user during the period to be measured according to this initial energy intake target until the initial energy intake target is reached.

[0123] Therefore, in the process of predicting the weight change of the target user in the embodiments of the present disclosure, it is possible to accurately infer the exercise consumption of the target user during the period to be measured based on the weight change value of the target user during the period to be measured, recommend the target exercise consumption of the target user during the period to be measured according to the weight change value and energy balance value of the target user during the period to be measured, further optimize the exercise consumption of the target user during the period to be measured, and thus provide a more reliable basis for fat loss or health management.

[0124] In this embodiment, a method for predicting weight change based on user characteristics is provided, which can be used in the above-mentioned computer devices, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 3 It is a flowchart of the method for predicting weight change based on user characteristics according to the embodiments of the present invention. The above step S102, obtaining the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user, includes:

[0125] Based on the basic information affecting the energy intake of the target user, use the energy intake prediction model to predict the daily energy intake requirement of the target user, and adjust the daily energy intake requirement of the target user according to the weight change value and energy balance value of the target user during the period to be measured. Among them, the energy intake prediction model is a pre-trained neural network model.

[0126] Specifically, in the process of calculating energy intake and consumption, the calculation of energy intake covers aspects such as protein, fat, carbohydrates, and alcohol; energy consumption calculation includes resting metabolism (RMR), thermic effect of food (TEF), and energy expenditure of activity ability (EEpa). For example, the RMR values of different age groups and genders are deduced through formulas, and metabolic equivalent (MET) is used to describe the activity intensity and calculate the energy expenditure of activity ability. However, the accuracy of MET values is controversial. Experiments show that there are significant differences from the commonly used values, and there are also differences between different devices. Therefore, there will also be differences in the detection of the daily energy intake requirement of the target user by different detection devices in the traditional method, and the detection results are not unified enough, resulting in inaccurate daily energy intake requirements of the target user. In view of this, the embodiments of the present disclosure use the energy intake prediction model to predict the daily energy intake requirement of the target user to ensure the accuracy of the prediction of the daily energy intake requirement. And, in the process of predicting the daily energy intake requirement of the target user, the daily energy intake requirement of the target user can be adjusted according to the weight change value and energy balance value of the target user, further enhancing the accuracy of the prediction of the daily energy intake requirement.

[0127] For example, in the prediction of the daily energy intake requirement of the target user, the daily energy intake requirement is continuously adjusted according to the actual change situation of the target user, and by comparing the difference between the predicted weight and the actual initial weight of the target user, the purpose of optimizing the energy intake estimation is achieved.

[0128] In some alternative embodiments, predicting the daily energy intake requirement of the target user based on the basic information affecting the energy intake of the target user using the energy intake prediction model includes:

[0129] Calculate the daily energy intake requirement of the target user according to the basal metabolic rate of the target user, the spontaneous activity energy of the target user, the daily energy gap of the target user during the observation period, the historical exercise consumption of the target user during the observation period, and the daily energy consumption.

[0130] Specifically, the daily energy intake requirement of the target user is represented by EI, EI = RMR + SPA0 + exe_cal’ (assuming 200 Kcal per day) - EM’ = 1331.25 + 332.8 + 200 - 126.68 = 1737.38 Kcal.

[0131] Among them, RMR is the basal metabolism (resting metabolism) of the target user, SPA0 is the energy of spontaneous activity, exe_cal is the daily energy consumption of the target user during the observation period, and EM’ is the daily energy deficit of the target user during the observation period. EM’ = EM / T = 1773.5 / 14 = 126.68 Kcal, where T is the period to be measured.

[0132] In some alternative embodiments, the basic information affecting the energy intake of the target user includes: the amount of fat change and the amount of fat-free change. In step S104, the label information, the basic information affecting the energy intake of the target user, and the target exercise consumption are input into the weight change prediction model to predict the weight change value and the energy balance value of the target user during the period to be measured, including:

[0133] Step a1, obtaining the initial weight of the target user from the label information.

[0134] Step a2, obtaining the initial fat parameter, the initial fat-free weight parameter, the amount of fat change, and the amount of fat-free change of the target user from the basic information affecting the energy intake of the target user, and predicting the weight change value and the energy balance value of the target user during the period to be measured.

[0135] Specifically, the initial weight of the target user is represented by W0, the initial fat parameter of the target user includes the initial fat amount of the target user, the initial fat amount of the target user is represented by F0, the amount of fat change is represented by delta_f, the amount of fat-free change is represented by delta_ffm, and the initial fat-free weight parameter is represented by FFM0.

[0136] In a specific example, for instance, gender: female & height = 167 cm & weight = 53 kg & age = 32 & PAL = 1.25 & daily energy intake requirement: 1737.38 Kcal, daily exercise consumption 135 Kcal (less than the previous 200 Kcal), then:

[0137] The initial weight of the target user at N = 0 days: 53 Kg; at N = 1 day: F0 + delta_f + FFM0 + delta_ffm = (10.681398916390979 + 0.004505014121086126) + (42.33490471115823 + 0.004388181365119215) = 53.02 Kg.

[0138] Among them, the predicted weight of the target user on the Nth day is: Weight (the Nth day) = [Fat (FM_N-1) + delta_f] + [Fat-free mass (FFM_N-1) + delta_ffm fat-free mass change] + [Glycogen (gly_N-1) + delta_gly] + [Interstitial fluid (decw_N-1) + delta_decw] + [Thermal consumption (therm_N-1) + delt+therm thermic effect of food change];

[0139] Among them, delta_f = (1.0 - 1.990762711864407 / (1.990762711864407 + F_N-1)) * (Daily energy intake requirement - RMR - SPA0 - exe_cal - Glycogen storage) / 9440.0;

[0140] delta_ffm = delta_f = (1.0 - 1.990762711864407 / (1.990762711864407 + F_N-1)) * (EI - RMR - SPA0 - exe_cal - Glycogen storage) / 1807;

[0141] delta_gly = New carbohydrate intake (g) - (Carbohydrate intake (g) / Glycogen storage^2) * Glycogen storage^2 / 4180; Default value is 0

[0142] delta_decw = (New sodium intake - Baseline sodium intake - 4000 * (Daily carbohydrate intake / Baseline carbohydrate intake)) / 3220; Default state is 0.

[0143] In the weight change prediction method based on user characteristics in the embodiments of the present disclosure, by introducing the exercise activity behavior and weight record behavior of the target user, and continuously optimizing the weight change prediction model, the long-term weight prediction error caused by factors such as uncertain energy requirements is reduced. That is, during the weight prediction process of the target user, according to the balance relationship between energy intake and consumption and the body's adaptability to energy changes, the body composition and energy consumption parameters of the target user can be dynamically adjusted, so as to achieve a more accurate prediction of the weight change of the target user.

[0144] As Figure 5 shown, it is a simple schematic diagram of the weight change prediction method based on user characteristics in the embodiments of the present disclosure. In Figure 5In the example, user data includes: height, age, weight, weight change, gender, exercise history (running, walking, training, etc.), and these data are transmitted to the exercise energy consumption prediction model, weight change prediction model, and (body composition, energy consumption, energy gap) calculation unit. After the calculation unit completes the calculation, the data is transmitted to the energy intake prediction model. The weight change prediction model predicts the weight change of the target user based on the prediction period based on the user data, daily energy intake prediction results, questionnaires, diet record methods, and weight loss goals. The weight change prediction model feeds back the weight change prediction results to the exercise consumption prediction model to recommend energy consumption. At the same time, the energy intake prediction model also feeds back the daily energy intake prediction results to the exercise consumption prediction model, and the exercise consumption prediction model also obtains some exercise-related training data.

[0145] In the present embodiment, a weight change prediction device based on user characteristics is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0146] This embodiment provides a weight change prediction device based on user characteristics, such as Figure 6 As shown, including:

[0147] The first acquisition module 601 is used to acquire the tag information, exercise information, test period, diet information and basic information affecting the energy intake of the target user, wherein the basic information affecting the energy intake of the target user is determined according to the tag information;

[0148] The second acquisition module 602 is used to acquire the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user;

[0149] The third acquisition module 603 is used to acquire the target motion consumption of the target user in the test period according to the motion information, the test period and the tag information;

[0150] The weight prediction module 604 is used to input label information, basic information affecting the target user's energy intake and target exercise consumption into a weight change prediction model to predict the target user's weight change value and energy balance value during the test period, wherein the weight change prediction model is a pre-trained neural network model.

[0151] In an optional implementation, the tag information includes: gender, height, age, initial weight, observation period, initial energy intake target, activity coefficient, historical exercise consumption and historical weight change value of the target user during the observation period; the first acquisition module 601 includes:

[0152] The first calculation submodule is used to calculate the initial fat parameters of the target user according to the initial weight, age, height and gender;

[0153] A second calculation submodule is used to calculate the initial fat-free body mass parameter of the target user according to the initial body weight and initial fat parameter of the target user;

[0154] The third calculation submodule is used to calculate the basal metabolic rate of the target user according to the initial weight, age and height;

[0155] a fourth calculation submodule, for calculating the spontaneous activity energy of the target user according to the basal metabolic rate and activity coefficient of the target user;

[0156] The fourth calculation submodule is used to calculate the total energy deficit of the target user during the observation period according to the initial energy intake target, the initial fat parameter, the observation period and the initial fat-free body mass parameter;

[0157] The fifth calculation submodule is used to calculate the daily energy consumption of the target user during the observation period according to the historical exercise consumption of the target user during the observation period.

[0158] In an optional implementation, the third acquisition module 603 includes:

[0159] The exercise consumption recommendation submodule is used to predict the target exercise consumption of the target user during the test period based on the exercise information, the test period and the label information, using the exercise energy consumption model, and recommend the target exercise consumption of the target user during the test period based on the daily energy intake requirements, the target user's weight change value and energy balance value during the test period, wherein the exercise energy consumption model is a pre-trained neural network model.

[0160] In some optional embodiments, the tag information also includes: the weight change value of the target user during the observation period, the basic information affecting the target user's energy intake also includes: adipose tissue weight parameters and non-fat tissue weight parameters, and the exercise consumption recommendation submodule includes:

[0161] A first calculation unit is used to calculate the energy deficit conversion amount of the target user according to the weight change value, fat tissue weight parameter and non-fat tissue weight parameter of the target user during the observation period;

[0162] A second calculation unit, configured to calculate the updated target exercise consumption of the target user during the period to be measured according to the daily energy intake requirement, basal metabolism, spontaneous activity energy, and energy gap conversion amount.

[0163] A dynamic adjustment unit, configured to continuously adjust the target exercise consumption of the target user during the period to be measured according to the initial energy intake target until the target user achieves the initial energy intake target.

[0164] In some alternative embodiments, the second acquisition module 602 includes:

[0165] A dynamic adjustment sub-module, configured to predict the daily energy intake requirement of the target user by using an energy intake prediction model according to the basic information affecting the energy intake of the target user, and adjust the daily energy intake requirement of the target user according to the weight change value and energy balance value of the target user during the period to be measured, wherein the energy intake prediction model is a neural network model pre-trained.

[0166] In some alternative embodiments, the weight prediction module 604 includes:

[0167] A calculation sub-module, configured to calculate the daily energy intake requirement of the target user according to the basal metabolic rate of the target user, the spontaneous activity energy of the target user, the daily energy gap of the target user during the observation period, the historical exercise consumption of the target user during the observation period, and the daily energy consumption.

[0168] In some alternative embodiments, the basic information affecting the energy intake of the target user includes: fat change amount and fat-free change amount, and the weight prediction module 604 includes:

[0169] A first acquisition sub-module, configured to acquire the initial weight of the target user from the label information;

[0170] A data prediction sub-module, configured to acquire the initial fat parameter, initial fat-free weight parameter, fat change amount, and fat-free change amount of the target user from the basic information affecting the energy intake of the target user, and predict the weight change value and energy balance value of the target user during the period to be measured.

[0171] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding above embodiments, and will not be elaborated here.

[0172] The weight change prediction device based on user characteristics in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0173] An embodiment of the present invention further provides a computer device, which has the above-mentioned weight change prediction device based on user characteristics.

[0174] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As shown in Figure 7 , the computer device includes: one or more processors 10, a memory 20, and an interface for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 7 In

[0175] FIG., a single processor 10 is taken as an example.

[0176] The processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0177] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0178] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, a hard disk, or a solid state drive; the memory 20 may further include a combination of the above types of memory.

[0179] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0180] An embodiment of the present invention further provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented by downloading through a network and originally stored in a remote storage medium or a non-transitory machine-readable storage medium and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state drive, etc.; further, the storage medium can also include a combination of the above types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiment is implemented.

[0181] A part of the present invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the method and / or technical solution according to the present invention can be called or provided. Those skilled in the art should be able to understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.

[0182] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting weight changes based on user characteristics, characterized in that, The method includes: Obtaining the label information, exercise information, measurement period, diet information, and basic information affecting the energy intake of the target user, wherein the basic information affecting the energy intake of the target user is determined according to the label information; Obtaining the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user; Obtaining the target exercise consumption of the target user during the measurement period according to the exercise information, the measurement period, and the label information; Inputting the label information, the basic information affecting the energy intake of the target user, and the target exercise consumption into a weight change prediction model to predict the weight change value and energy balance value of the target user during the measurement period, wherein the weight change prediction model is a pre-trained neural network model.

2. The method according to claim 1, wherein The label information includes: gender, height, age, initial weight, observation period, initial energy intake target, activity coefficient, historical exercise consumption and historical weight change value of the target user during the observation period; determining the basic information affecting the energy intake of the target user according to the label information includes: Calculating the initial fat parameter of the target user according to the initial weight, the age, the height, and the gender; Calculating the initial fat-free weight parameter of the target user according to the initial weight and the initial fat parameter of the target user; Calculating the basal metabolic rate of the target user according to the initial weight, the age, and the height; Calculating the spontaneous activity energy of the target user according to the basal metabolic rate and the activity coefficient of the target user; Calculating the total energy deficit of the target user during the observation period according to the initial energy intake target, the initial fat parameter, the observation period, and the initial fat-free weight parameter; Calculating the daily energy consumption of the target user during the observation period according to the historical exercise consumption of the target user during the observation period.

3. The method according to claim 1 or 2, characterized in that, Obtaining the target exercise consumption of the target user during the measurement period according to the exercise information, the measurement period, and the label information includes: Predicting the target exercise consumption of the target user during the measurement period according to the exercise information, the measurement period, and the label information by using an exercise energy consumption model, and recommending the target exercise consumption of the target user during the measurement period according to the daily energy intake requirement, the weight change value and energy balance value of the target user during the measurement period, wherein the exercise energy consumption model is a pre-trained neural network model.

4. The method according to claim 2, wherein The label information further includes: the weight change value of the target user during the observation period, and the basic information affecting the energy intake of the target user further includes: fat tissue weight parameter and non-fat tissue weight parameter. Recommending the target exercise consumption of the target user during the measurement period according to the daily energy intake requirement, the weight change value and energy balance value of the target user during the measurement period includes: Calculate the energy deficit conversion amount of the target user according to the weight change value of the target user during the observation period, the adipose tissue weight parameter, and the non-adipose tissue weight parameter; Calculate the updated target exercise consumption of the target user during the period to be measured according to the daily energy intake requirement, the basal metabolism, the spontaneous activity energy, and the energy deficit conversion amount; Keep adjusting the target exercise consumption of the target user during the period to be measured according to the initial energy intake target until the target user achieves the initial energy intake target; 5. The method according to claim 2, characterized in that, Obtain the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user, including: Predict the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user by using an energy intake prediction model, and adjust the daily energy intake requirement of the target user according to the weight change value and the energy balance value of the target user during the period to be measured, wherein the energy intake prediction model is a neural network model pre-trained; 6. The method according to claim 2, wherein Predict the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user, including: Calculate the daily energy intake requirement of the target user according to the basal metabolic rate of the target user, the spontaneous activity energy of the target user, the daily energy deficit of the target user during the observation period, the historical exercise consumption of the target user during the observation period, and the daily energy consumption; 7. The method according to claim 2, characterized in that The basic information affecting the energy intake of the target user includes: the fat change amount and the non-fat change amount. Input the label information, the basic information affecting the energy intake of the target user, and the target exercise consumption into a weight change prediction model to predict the weight change value and the energy balance value of the target user during the period to be measured, including: Obtain the initial weight of the target user from the label information; Obtain the initial fat parameter, the initial fat-free weight parameter, the fat change amount, and the non-fat change amount of the target user from the basic information affecting the energy intake of the target user, and predict the weight change value and the energy balance value of the target user during the period to be measured; 8. A weight change prediction device based on user characteristics, characterized in that, The device includes: A first acquisition module, configured to acquire the label information, the exercise information, the period to be measured, the diet information, and the basic information affecting the energy intake of the target user of the target user, wherein the basic information affecting the energy intake of the target user is determined according to the label information; A second acquisition module, configured to acquire the daily energy intake requirement of the target user according to the basic information affecting the energy intake of the target user; A third acquisition module, configured to acquire the target exercise consumption of the target user during the period to be measured according to the exercise information, the period to be measured, and the label information; A weight prediction module, configured to input the label information, basic information affecting the energy intake of the target user, and the target exercise consumption into a weight change prediction model, and predict the weight change value and energy balance value of the target user within the period to be measured, wherein the weight change prediction model is a neural network model pre-trained.

9. A computer device, characterized in that, Comprising: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the weight change prediction method based on user characteristics according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the weight change prediction method based on user characteristics according to any one of claims 1 to 7.

Images