Weight management method and device based on user characteristics and diet recommendation method and device based on user characteristics

Abstract

The invention relates to the technical field of user diet management, and discloses a weight management method and device based on user characteristics and a diet recommendation method and device.According to the weight management method based on the user characteristics, an energy intake distribution model is combined with label information of a target user, a weight management target, an energy recommendation target and current motion information, so that the weight management efficiency is improved; according to the embodiment of the invention, the dynamic adjustment scheme of the daily diet suggestion can be generated, so that the accurate diet suggestion can be provided for the target user even if the real-time movement of the target user and / or the intake of each meal is changed, the target user is helped to realize the weight management target, and the weight management experience of the target user is enhanced. Therefore, according to the invention, not only can the future diet plan of the target user be dynamically adjusted to realize the weight management target of the target user, but also the recipe can be accurately recommended for the target user according to the diet preference of the target user.

Description

Technical Field

[0001] The present invention relates to the technical field of user diet management, and in particular, to a weight management method, a diet recommendation method and a device based on user characteristics. Background Art

[0002] With the acceleration of people's life and work rhythms, more and more people are in a sub-healthy state due to unhealthy diets and long-term lack of exercise. Therefore, it is necessary to plan or manage people's diet plans.

[0003] In related technologies, there are various calculation models for estimating energy intake and consumption. For example, the basal metabolic rate is calculated based on factors such as age, gender, height, and weight, and then the total energy consumption is estimated in combination with the activity level. For example, some diet record Apps can help users record food intake and query the calorie and nutrient information of foods through a food database. Most of the existing tools only consider a certain aspect of diet or exercise in isolation, without comprehensively analyzing the user's real-time exercise data, physiological information, and goals, resulting in inaccurate analysis results of daily energy intake in diet recommendations. Moreover, the real-time changes in the user's exercise situation and the energy intake per meal are related to the user's weight management. When the user's exercise situation changes and / or the intake per meal changes, the related technologies cannot dynamically adjust the user's daily nutrient intake requirements, daily energy intake requirements, and energy distribution per meal, resulting in the inability to formulate an accurate diet management plan for the user.

[0004] In addition, since the diet recipe is related to the daily nutrient intake requirements and the intake per meal, and the related technologies cannot dynamically adjust the daily energy intake requirements and the energy distribution per meal, the diet recipe generated in combination with this static diet recommendation is often static, ultimately resulting in the inability to recommend an accurate diet recipe for the user. Therefore, the existing methods cannot comprehensively consider the user's personalized characteristics and lack dynamic adaptability when managing the user's weight and recommending diet recipes. Summary of the Invention

[0005] In view of this, the present invention provides a weight management method, a diet recommendation method and a device based on user characteristics to solve the problem that the existing methods cannot comprehensively consider the user's personalized characteristics and lack dynamic adaptability when managing the user's weight and recommending diet recipes.

[0006] In a first aspect, the present invention provides a weight management method based on user characteristics, and the method includes:

[0007] Obtain the first information and the second information that affect the weight management of the target user. The first information includes: the label information of the target user, the weight management goal, the energy recommendation goal, and the current exercise information. The second information represents sports nutrition information;

[0008] Input the first information and the second information into the energy intake distribution model to predict the daily diet recommendations corresponding to the current weight of the target user. The daily diet recommendations include the daily energy intake requirement and the distribution value of the daily nutrient element intake requirement, and generate a dynamic adjustment plan for the daily diet recommendations to update the daily energy intake requirement, the distribution value of the daily nutrient element intake requirement, and the energy distribution value per meal corresponding to the current weight of the target user. Among them, the energy intake distribution model is a pre-trained neural network model.

[0009] In the weight management method based on user characteristics in the present disclosure, since the energy intake distribution model combines the label information, weight management goal, energy recommendation goal, and current exercise information of the target user and can generate a dynamic adjustment plan for the daily diet recommendations, even if there are real-time exercise changes and / or per-meal intake changes of the target user, it can still provide accurate diet recommendations for the target user, which is beneficial to helping the target user achieve the weight management goal, thereby enhancing the weight management experience of the target user.

[0010] In some optional implementation manners, the label information of the target user includes: height, gender, age, initial weight, current weight, and weight management duration; the current exercise information of the target user includes: exercise time, exercise type, and exercise intensity coefficient; the sports nutrition information includes: the energy density of body mass; predicting the daily energy intake requirement corresponding to the current weight of the target user includes:

[0011] Calculate the weight change amount of the target user during the weight management duration according to the current weight and the initial weight of the target user;

[0012] Calculate the energy deficit of the target user according to the energy density of body mass and the weight change amount of the target user during the weight management duration;

[0013] Obtain the current exercise type of the target user and its corresponding exercise time and exercise intensity coefficient;

[0014] Calculate the daily actual exercise energy consumption corresponding to the current exercise type of the target user according to the current exercise type of the target user and its corresponding exercise time, exercise intensity coefficient, and the initial weight of the target user;

[0015] Statistically calculate the daily actual exercise energy consumption corresponding to the current exercise type of the target user to obtain the total daily actual exercise energy consumption of the target user;

[0016] Calculate the basal metabolic rate of the target user based on the height, gender, age, and initial weight of the target user;

[0017] Calculate the total daily energy consumption of the target user based on the basal metabolic rate of the target user and the total actual daily exercise energy consumption of the target user;

[0018] Predict the daily energy intake requirement corresponding to the current weight of the target user based on the total daily energy consumption, energy deficit, and weight management duration of the target user.

[0019] In some alternative embodiments, the energy recommendation targets include: the initial value of the daily energy intake requirement, the distribution ratio of the daily nutrient intake requirement, and the sports nutrition information of the target user further includes: the adjustment coefficient for different types of exercise; predicting the distribution value of the daily nutrient intake requirement corresponding to the current weight of the target user, including:

[0020] Obtain the current exercise type of the target user;

[0021] Obtain the adjustment coefficient, exercise time, and distribution ratio of the daily nutrient intake requirement corresponding to the current exercise type of the target user;

[0022] Calculate the adjustment ratio of the daily nutrient intake requirement corresponding to the current exercise type based on the adjustment coefficient, exercise time, and distribution ratio of the daily nutrient intake requirement corresponding to the current exercise type of the target user;

[0023] Predict the distribution value of the daily nutrient intake requirement corresponding to the current weight of the target user based on the adjustment ratio of the daily nutrient intake requirement corresponding to the current exercise type and the initial value of the daily energy intake requirement.

[0024] In some alternative embodiments, the weight management targets include: the daily target adjustment energy of the target user, generating a dynamic adjustment plan for the weight management target to update the daily energy intake requirement, the distribution value of the daily nutrient intake requirement, and the energy distribution value per meal corresponding to the current weight of the target user, including:

[0025] Calculate the target value of the daily energy intake requirement of the target user based on the daily target adjustment energy of the target user and the total daily energy consumption of the target user;

[0026] Determine whether the first deviation between the target value of the daily energy intake requirement and the daily energy intake requirement corresponding to the current weight of the target user meets the preset requirements;

[0027] If the first deviation does not meet the preset requirements, continuously adjust the energy recommendation target, and then adjust the daily nutrient intake requirement allocation value until the target user achieves the weight management goal, and update the daily nutrient intake requirement allocation value corresponding to the target user's current weight according to the target value of the daily energy intake requirement and the adjustment ratio of the daily nutrient intake requirement corresponding to the current exercise type;

[0028] Update the daily energy intake requirement corresponding to the target user's current weight according to the target value of the daily energy intake requirement;

[0029] Update the energy allocation value for each meal corresponding to the target user's current weight according to the target user's daily actual total exercise energy consumption and the target user's daily total energy consumption.

[0030] In some alternative embodiments, the label information of the target user further includes: the energy already consumed by the target user in the current meal and the remaining number of meals, and the current exercise information further includes the target user's daily average exercise energy consumption during the weight management period. Updating the energy allocation value for each meal corresponding to the target user's current weight according to the target user's daily actual total exercise energy consumption, the weight management period, and the target user's daily total energy consumption includes:

[0031] Calculate the second deviation between the target user's daily average exercise energy consumption and the target user's daily actual total exercise energy consumption;

[0032] Calculate the daily energy intake adjustment value of the target user according to the second deviation and the target user's daily total energy consumption;

[0033] Calculate the estimated energy for each meal of the target user according to the daily energy intake adjustment value, the energy already consumed by the target user in the current meal, and the remaining number of meals;

[0034] Calculate the remaining meal energy requirement of the target user after the current meal according to the estimated energy for each meal of the target user and the remaining number of meals;

[0035] Predict the energy allocation value for each meal corresponding to the target user's current weight according to the remaining meal energy requirement and the remaining number of meals.

[0036] In a second aspect, the present disclosure provides a diet recommendation method, the method including:

[0037] Obtain third information affecting each meal diet of the target user, where the third information includes: the current location of the target user, dietary preferences, ingredient information of the current location, and food library information;

[0038] The daily energy intake requirement, the distribution value of the daily nutrient intake requirement, and the energy distribution value for each meal corresponding to the current weight of the target user updated according to the dynamic adjustment plan generated by the weight management method based on user characteristics in the first aspect or any implementation manner of the first aspect, and the third information are input into the diet recommendation model to predict the recommended recipes for each meal of the target user, where the diet recommendation model is a pre-trained neural network model.

[0039] The present disclosure simultaneously utilizes the energy intake distribution model and the diet recommendation model, which can not only dynamically adjust the future diet plan of the target user to achieve the weight management goal of the target user. In addition, since the present disclosure not only combines the diet recommendation prediction results of the energy intake distribution model, but also combines the diet preferences of the target user and the ingredient information at the current location, the present disclosure can provide recipe suggestions that match the diet preferences of different target users at their respective locations according to the personalized eating habits of different target users.

[0040] In some alternative implementation manners, the ingredient information at the current location includes: the priority score value of each type of ingredient, the weight coefficient of different ingredients in each type of recipe, and predicting the recommended recipes for each meal of the target user includes:

[0041] Obtain the priority score value of the first ingredient according to the priority score value of each type of ingredient;

[0042] Obtain the weight coefficient of the first ingredient in the recipe;

[0043] Predict the recommended recipes for each meal of the target user according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe.

[0044] In some alternative implementation manners, predicting the recommended recipes for each meal of the target user according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe includes:

[0045] When the target user replaces the first ingredient with the second ingredient, obtain the preference score value of the target user for the second ingredient according to the diet preference of the target user;

[0046] Predict the recommended recipes for each meal of the target user according to the priority score value of the first ingredient and the preference score value of the target user for the second ingredient.

[0047] In a third aspect, the present invention provides a diet recommendation device based on user characteristics, and the device includes:

[0048] A user information acquisition module, configured to acquire first information and second information that affect the weight management of a target user. The first information includes: label information of the target user, weight management goals, energy recommendation goals, and current exercise information. The second information represents sports nutrition information;

[0049] A diet recommendation prediction module, configured to input the first information and the second information into an energy intake allocation model, predict the daily diet recommendations corresponding to the current weight of the target user. The daily diet recommendations include the daily energy intake requirement and the allocation values of the daily nutrient intake requirements, and generate a dynamic adjustment plan for the daily diet recommendations to update the daily energy intake requirement, the allocation values of the daily nutrient intake requirements, and the energy allocation values for each meal corresponding to the current weight of the target user. Among them, the energy intake allocation model is a pre-trained neural network model.

[0050] In a fourth aspect, the present invention provides a computer device, including:

[0051] 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 management method based on user characteristics according to the first aspect or any corresponding embodiment thereof, or the diet recommendation method according to the second aspect or any corresponding embodiment thereof.

[0052] In a fifth 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 management method based on user characteristics according to the first aspect or any corresponding embodiment thereof, or the diet recommendation method according to the second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] 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 use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description 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.

[0054] Figure 1 is a flowchart of a weight management method based on user characteristics according to an embodiment of the present invention;

[0055] Figure 2 is a flowchart of another weight management method based on user characteristics according to an embodiment of the present invention;

[0056] Figure 3 is a flowchart of yet another weight management method based on user characteristics according to an embodiment of the present invention;

[0057] Figure 4 is a schematic flowchart of yet another user characteristic-based weight management method according to an embodiment of the present invention;

[0058] Figure 5 is a schematic flowchart of another user characteristic-based weight management method according to an embodiment of the present invention;

[0059] Figure 6 is a schematic flowchart of a diet recommendation method according to an embodiment of the present invention;

[0060] Figure 7 is a simple schematic flowchart of integrating a user characteristic-based weight management method and a diet recommendation method according to an embodiment of the present invention;

[0061] Figure 8 is a structural block diagram of a user characteristic-based weight management device according to an embodiment of the present invention;

[0062] Figure 9 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] According to an embodiment of the present invention, an embodiment of a user characteristic-based weight management method 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 the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0065] In this embodiment, a user characteristic-based weight management method is provided, which can be used in a mobile terminal, such as a mobile phone, a tablet computer, etc. Figure 1 is a flowchart of a user characteristic-based weight management method according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0066] Step S101, obtain the first information and the second information that affect the weight management of the target user. The first information includes: the label information of the target user, the weight management goal, the energy recommendation goal, and the current exercise information. The second information represents sports nutrition information.

[0067] Specifically, the target user can be any user of different types. For example, the target user can represent target user U1, target user U2, or target user U3. The first information represents some label information of the target user's personalization. These label information can include but are not limited to the height, gender, age, initial weight, current weight, etc. of the target user. The label information of target users of different types will also vary. For example, the label information of different target users is shown in Table 1 below.

[0068] Table 1

[0069]

[0070] The weight management goal includes but is not limited to a weight gain goal or a weight loss goal, etc.; the energy recommendation goal can be expressed as the initial value of the daily recommended energy intake requirement and the distribution ratio of the daily nutrient intake requirement to help the target user achieve the weight management goal. The nutrients in this disclosure can be one or more nutrients in the body. This nutrient includes but is not limited to carbohydrates, proteins, and fats, etc. Therefore, the distribution ratio of the daily nutrient intake requirement can be the distribution ratio of the carbohydrate intake requirement, the distribution ratio of the protein intake requirement, and the distribution ratio of the fat intake requirement respectively. For example, the weight management goals and energy recommendation goals of different users are shown in Table 2 below.

[0071] Table 2

[0072]

[0073]

[0074] The above-mentioned current exercise information includes but is not limited to the current exercise type, exercise time, exercise intensity coefficient, etc. of the target user. Among them, the current exercise type of the target user includes: aerobic exercise and anaerobic exercise. For example: the different exercise information of different target users is shown in Table 3 below.

[0075] Table 3

[0076]

[0077] The second information in the above represents sports nutrition information, which may include: the energy density of body mass and adjustment coefficients for different types of exercise. Among them, the energy density of body mass (kcal / kg) can be composed of the following parts: fat mass (cf = 9500 kcal / kg) and fat-free body mass (cl = 1020 kcal / kg). For example, assuming that the fat-free body mass accounts for 80% and the fat mass accounts for 20% in the body composition: energy density = 0.8×1020 + 0.2×9500 = 2826 kcal / kg. The adjustment coefficients for different types of exercise are preset coefficients determined in combination with different types of exercise. Through these adjustment coefficients for different types of exercise, the proportion of the intake requirements of different nutrient elements can be assisted in adjustment. For example, when the target user is doing aerobic exercise, the adjustment coefficient for aerobic exercise can be 0.02, and when the target user is doing anaerobic exercise, the adjustment coefficient for anaerobic exercise can be 1. The adjustment coefficients for different types of exercise can be set according to the actual situation, and through these adjustment coefficients for different types of exercise, the distribution ratio of the daily intake requirements of nutrient elements can be assisted in determination.

[0078] The first information in the above can be obtained through different application programming interfaces (API interfaces, full name: Application Programming Interface) or sensors and then stored in a data warehouse for subsequent analysis and processing.

[0079] Therefore, by obtaining the first information in the above, it is convenient to understand the personalized label information, weight management goals, energy recommendation goals, and current exercise of different target users, and thus understand the exercise habits and physical characteristics of the target users. By the second information in the above, it is convenient to understand the adjustment characteristics of different types of exercise.

[0080] Step S102: Input the first information and the second information into an energy intake distribution model to predict the daily diet recommendations corresponding to the current weight of the target user. The daily diet recommendations include the daily energy intake requirements and the distribution values of the daily intake requirements of nutrient elements, and generate a dynamic adjustment plan for the daily diet recommendations to update the daily energy intake requirements, the distribution values of the daily intake requirements of nutrient elements, and the energy distribution values for each meal corresponding to the current weight of the target user. Among them, the energy intake distribution model is a neural network model pre-trained.

[0081] Specifically, the daily energy intake requirement refers to the amount of energy intake required by the human body to maintain normal physiological functions and daily activities, which is the sum of the energy contained in all the food consumed daily, with the unit of kcal. For different target users, this daily energy intake requirement varies from person to person and is affected by various factors, including the age, gender, weight, height, activity level, and health status of different target users. Since this disclosure comprehensively considers the influence of the target user's label information, weight management goal, energy recommendation goal, current exercise information, and sports nutrition information on the target user's daily energy intake requirement, the pre-trained energy intake allocation model can accurately predict the target user's daily energy intake requirement, and thus can precisely analyze the differences in the daily energy intake requirements caused by individual differences among different target users.

[0082] The above-mentioned daily nutrient intake requirement allocation value represents the allocation of the target user's body's intake requirements for different nutrients. For example, for the recommended value of the daily energy intake requirement of 2000 kcal, the specific weights of allocating this 2000 kcal of energy to different nutrients are 250 g of carbohydrates, 165 g of protein, and 37.8 g of fat.

[0083] By using the label information, weight management goal, energy recommendation goal, current exercise information, and sports nutrition information of the target user collected historically, after data processing, the trained energy intake allocation model is continuously trained. Therefore, this energy intake allocation model is a pre-trained neural network model.

[0084] Since the target user's real-time exercise will have a certain impact on the target user's daily energy intake requirement corresponding to the current weight, the daily nutrient intake requirement allocation value, and the energy allocation value per meal. If the energy intake allocation model always predicts the target user's daily energy intake requirement corresponding to the current weight and the daily nutrient intake requirement allocation value according to the energy recommendation goal, it may not be able to ensure that the target user achieves the weight management goal, resulting in inaccurate prediction results of the daily diet advice.

[0085] Assume that the weight management goal set by the target user is weight loss. The energy recommendation goal provided by the method of the present disclosure (the daily recommended energy intake requirement is 1800 kcal), and the distribution ratio of the daily recommended nutrient intake requirements (40% for carbohydrates, 30% for protein, and 30% for fat). Since the real-time exercise amount and / or the intake per meal of the target user are uncertain, if the initial energy recommendation goal is followed, the target user may not be able to achieve the weight loss goal. Therefore, according to this static weight management method, it is possible that the target user cannot achieve the weight loss goal. In view of this, the present disclosure can generate a dynamic adjustment plan to dynamically adjust the daily energy intake requirement, the distribution value of the daily nutrient intake requirement, and the energy distribution value per meal corresponding to the current weight of the target user. Even if the real-time exercise data and / or the intake per meal of the target user change, it can dynamically adapt to this exercise change and diet change, thereby ensuring that the prediction result of the diet advice is more accurate.

[0086] Since different exercises of the target user will affect the intake per meal, therefore, by generating a dynamic adjustment plan through the above energy intake distribution model, even if the target user changes due to real-time exercise changes and / or the intake per meal, it is possible to dynamically adjust the energy distribution per meal, and thus can accurately plan the intake per meal for the target user reasonably.

[0087] Therefore, in the weight management method based on user characteristics in the present disclosure, since the energy intake distribution model combines the label information, weight management goal, energy recommendation goal, and current exercise information of the target user, it can generate a dynamic adjustment plan for the daily diet advice. Therefore, even if the real-time exercise of the target user changes and / or the intake per meal changes, it can provide accurate diet advice for the target user, which is beneficial to helping the target user achieve the weight management goal, and thus enhances the weight management experience of the target user.

[0088] In this embodiment, a weight management method based on user characteristics is provided, which can be used in mobile terminals such as mobile phones and tablet computers. Figure 2 It is a flowchart of the weight management method based on user characteristics according to an embodiment of the present invention. The label information of the target user includes: height, gender, age, initial weight, current weight, and weight management duration; the current exercise information of the target user includes: exercise time, exercise type, and exercise intensity coefficient; the sports nutrition information includes: the energy density of body mass; as Figure 2 As shown, in the above step S102, predicting the daily energy intake requirement corresponding to the current weight of the target user includes:

[0089] Step S201, according to the current weight and the initial weight of the target user, calculate the weight change amount of the target user during the weight management duration.

[0090] For example, for the target user U1 in Table 1 above, the change in weight of the target user within the weight management duration (14 days) is represented by ΔW, the current weight of the target user is represented by W1, and the initial weight of the target user is represented by W0. Then, ΔW = W1 - W0 = 68 - 70 = -2 Kg.

[0091] In addition, according to the knowledge of sports nutrition, the energy balance equation is: ΔW’ = (total daily energy intake – total daily energy expenditure) / energy density, where ΔW’ represents the daily weight change of the target user. Then, the weight change in 14 days is 14 × ΔW’ = ΔW.

[0092] Step S202: Calculate the energy deficit of the target user according to the energy density of body mass and the weight change of the target user within the weight management duration.

[0093] Specifically, since the energy density (kcal / kg) of body mass in sports nutrition information consists of the following parts: fat mass (cf = 9500 kcal / kg) and fat-free mass (cl = 1020 kcal / kg). According to the sports nutrition information, assuming that the fat-free mass in body composition accounts for 80% and the fat mass accounts for 20%, the energy density = 0.8 × 1020 + 0.2 × 9500 = 2826 kcal / kg. The energy deficit can be represented by ΔE, the energy density by Energy, and the weight management duration by t. Then, the energy deficit ΔE of the target user within the weight management duration t (14 days) is ΔE = ΔW × Energy = -2 × 2826 = -5652 kcal.

[0094] Step S203: Obtain the current exercise type of the target user and the corresponding exercise time and exercise intensity coefficient.

[0095] Specifically, the current exercise type of the target user includes: aerobic exercise and / or anaerobic exercise. For example, the aerobic exercise time of the target user U1 is 2 hours, and the anaerobic exercise is 1 hour. Among them, the exercise intensity coefficient of aerobic exercise MET = 8, and the anaerobic exercise intensity coefficient MET = 6. Of course, the current exercise type of the target user U1 can also be only aerobic exercise or anaerobic exercise.

[0096] Step S204: Calculate the daily actual exercise energy expenditure corresponding to the current exercise type of the target user according to the current exercise type of the target user, the corresponding exercise time, exercise intensity coefficient, and the initial weight of the target user.

[0097] Specifically, for the example in Step S203 above, for the aerobic exercise of the target user U1, the corresponding daily actual exercise energy expenditure is represented by E aerobicIt is represented that the exercise time of aerobic exercise is represented by T1, and the exercise intensity coefficient is represented by WET1, then E aerobic = W0 × MT1 × T1 = 70 × 8 × 2 = 1120 kcal. For the anaerobic exercise of target user U1, the corresponding daily actual exercise energy consumption is represented by E anaerobic It is represented that the exercise time of anaerobic exercise is represented by T2, and the exercise intensity coefficient is represented by MET2, then E anaerobic = W0 × MET2 × T2 = 70 × 6 × 1 = 420 kcal.

[0098] Step S205: Statistically calculate the daily actual exercise energy consumption corresponding to the current exercise type of the target user to obtain the daily actual exercise energy consumption of the target user.

[0099] Specifically, for the daily actual exercise energy consumption corresponding to aerobic exercise calculated in the above step S204, which is 1120 kcal, and the daily actual exercise energy consumption corresponding to anaerobic exercise is 420 kcal. The daily actual exercise energy consumption of target user U1 is represented by E exercise It is represented, then E exercise = E aerobic + E anaerobic = 1120 + 420 = 1540 kcal.

[0100] Step S206: Calculate the basal metabolic rate of the target user according to the height, gender, age, and initial weight of the target user.

[0101] Specifically, the basal metabolic rate of the target user can be represented by BMR. The height of the target user is represented by H, the gender factor of the target user is represented by S, the age of the target user is represented by Age. The basal metabolic rate BMR of target user U1 = 10 × W0 + 6.25 × H + 5 × Age + S. Among them, for the gender factor S, it is 5 for men and -161 for women. Substituting the W0, H, and Age of U1 in Table 1 above, then BMR = 10 × 70 + 6.25 × 175 - 5 × 30 + 5 = 1667.5 kcal / day.

[0102] Step S207: Calculate the daily total energy consumption of the target user according to the basal metabolic rate of the target user and the daily total actual exercise energy consumption of the target user.

[0103] Specifically, the daily total energy consumption of the target user can be represented by TDEE. Substituting the calculation parameters of the above example into the formula TDEE = BMR + E exercise = 1667.5 + 1540 = 3207.5 kcal / day.

[0104] When the target user is not engaged in exercise, the total daily energy expenditure of the target user can consist of the following parts: TDEE = Resting Metabolic Rate (RMR) + Physical Activity Energy Expenditure (PA) + Spontaneous Physical Activity (SPA) + Diet-Induced Thermogenesis (DIT), where the Resting Metabolic Rate (RMR) is calculated based on body composition; the Physical Activity Energy Expenditure (PA) is the energy consumed by physical activity; the Spontaneous Physical Activity (SPA) is the energy consumed by spontaneous physical activity; and the Diet-Induced Thermogenesis (DIT) is the thermogenic effect caused by diet.

[0105] Step S208: Predict the daily energy intake requirement corresponding to the current weight of the target user based on the target user's total daily energy expenditure, energy deficit, and weight management duration.

[0106] Specifically, the daily energy intake requirement corresponding to the current weight of the target user is denoted as Estimated Intake. Substitute the obtained TDEE, ΔE, and t of the target user into the following formula:

[0107]

[0108] The energy intake distribution model in the present disclosure combines the height, gender, age, initial weight, current weight, weight management duration, exercise time, exercise type, exercise intensity coefficient, and energy density of body mass of the target user, and applies some calculation strategies for the real-time exercise data, body metabolism data, and daily energy intake requirement of the target user. According to the weight change amount of the target user, the daily energy intake requirement of the target user can be accurately calculated. Since the energy intake distribution model comprehensively considers the exercise habits and specific body indicators of the target user, the energy intake distribution model is more accurate in predicting the daily energy intake requirement corresponding to the current weight of the target user.

[0109] In this embodiment, a weight management method based on user characteristics is provided, which can be used in mobile terminals such as mobile phones and tablets. Figure 3 It is a flowchart of the weight management method based on user characteristics according to an embodiment of the present invention. The energy recommendation targets include: the initial value of the daily energy intake requirement and the distribution ratio of the daily nutrient intake requirement. The sports nutrition information of the target user also includes: the adjustment coefficients of different types of exercise; as Figure 3 shown, the above step S102 of predicting the distribution value of the daily nutrient intake requirement corresponding to the current weight of the target user includes:

[0110] Step S301: Obtain the current exercise type of the target user.

[0111] Specifically, the current exercise type of the target user includes: aerobic exercise and / or anaerobic exercise.

[0112] Step S302: Obtain the adjustment coefficient, exercise time, and daily nutritional element intake requirement allocation ratio corresponding to the target user's current exercise type.

[0113] Step S303: Calculate the daily nutritional element intake requirement adjustment ratio corresponding to the current exercise type according to the nutritional element adjustment coefficient, exercise time, and daily nutritional element intake requirement allocation ratio corresponding to the target user's current exercise type.

[0114] Specifically, when the target user U1's current exercise includes both aerobic exercise and anaerobic exercise, if the target user's current exercise includes aerobic exercise, the allocation ratio of the daily carbohydrate intake requirement increases. This daily carbohydrate intake requirement adjustment ratio can be represented by P carbs as shown. where is the allocation ratio of the daily carbohydrate intake requirement. Assuming this is 40%, T1 = 2, and f aerobic is the adjustment coefficient corresponding to aerobic exercise, usually 0.05. Substitute the known parameters into the formula

[0115] Similarly, if the target user's current exercise also includes anaerobic exercise, the allocation ratio of the daily protein intake requirement increases. This daily protein intake requirement adjustment ratio can be represented by P protein as shown. where f anaerobic is the adjustment coefficient corresponding to anaerobic exercise, usually 0.03. Assuming this is 30%, T2 = 1,

[0116] Similarly, if the target user's current exercise also includes anaerobic exercise or anaerobic exercise, the allocation ratio of the daily fat intake requirement decreases. This daily fat intake requirement adjustment ratio can be represented by P fat as shown. or The allocation ratio of the daily fat intake requirement is represented by the above as shown.

[0117] Since the three major nutritional elements in the body are mainly carbohydrates, proteins, and fats, the above P carbs is 50%, and the above P protein is 33%. Therefore, for the convenience of calculation, P fat = 100% - P carbs - P protein = 100% - 50% - 33% = 17%.

[0118] Step S304: Adjust the ratio according to the daily nutrient intake requirements corresponding to the current exercise type and the initial value of the daily energy intake requirement, and predict the daily nutrient intake requirement allocation value corresponding to the current weight of the target user.

[0119] Specifically, assuming that the initial value of the daily energy intake requirement is 2000 kcal, for carbohydrates, the daily carbohydrate intake requirement allocation value corresponding to the current weight of the target user is denoted as Carbs. Combining the above example Then

[0120] Similarly, for protein, the daily protein intake requirement allocation value corresponding to the current weight of the target user is denoted as Protein. Combining the above example,

[0121] Then

[0122] Similarly, for fat, the daily fat intake requirement allocation value corresponding to the current weight of the target user is denoted as Fat. Combining the above example, P fat = 100% - P carbs - P protein = 100% - 50% - 33% = 17%.

[0123] Then

[0124] Since the energy intake allocation model of the present disclosure takes into account the influence of the exercise type of the target user on the daily nutrient intake requirements, therefore, this energy intake allocation model can accurately allocate the daily energy intake requirement of the target user to different nutrients according to different exercises of the target user.

[0125] In this embodiment, a weight management method based on user characteristics is provided, which can be used in mobile terminals such as mobile phones and tablets. Figure 4 It is a flowchart of the weight management method based on user characteristics according to an embodiment of the present invention. The weight management objectives include: the daily target adjusted energy of the target user, such as Figure 4 As shown, in the above step S102, a dynamic adjustment plan for the weight management objective is generated to update the daily energy intake requirement, the daily nutrient intake requirement allocation value, and the energy allocation value per meal corresponding to the current weight of the target user, including:

[0126] Step S401: Calculate the target value of the daily energy intake requirement of the target user according to the daily target adjusted energy of the target user and the daily total energy consumption of the target user.

[0127] Specifically, if the weight management goal of the target user is a weight loss goal, the corresponding daily target adjusted energy can be the target energy for daily weight loss; if the weight management goal of the target user is a weight gain goal, the corresponding daily target adjusted energy can be the target energy for daily weight gain; if the weight management goal of the target user is a muscle gain goal, the corresponding daily target adjusted energy can be the target energy for daily muscle gain. For example, taking the target user U1 with weight loss as the weight management goal, the daily target adjusted energy of the target user (the daily target weight loss is 500 kcal / day), at step S207 of the above embodiment, the daily total energy expenditure TDEE is calculated as TDEE = BMR + E exercise = 1667.5 + 1540 = 3207.5 kcal / day. The target value of the daily energy intake requirement of the target user can be represented by Target, then Target = TDEE - 500 = 3207.5 - 500 = 2707.5 kcal / day.

[0128] Step S402, determine whether the first deviation between the target value of the daily energy intake requirement and the daily energy intake requirement corresponding to the current weight of the target user meets the preset requirements.

[0129] Specifically, calculated at step S208 in the above embodiment Calculate the first deviation between Estimated Intake and Target through the following formula. The first deviation can be represented by Adherence.

[0130]

[0131] Assume that the preset requirement is that the first deviation is not less than 95%. Since 96.44% > 95%, it indicates that the target user can successfully lose weight according to the initial energy recommendation goal, that is, the daily energy intake requirement and the daily nutrient intake requirement corresponding to the current weight after weight loss predicted by the energy intake distribution model also meet the preset requirements.

[0132] Step S403, if the first deviation does not meet the preset requirements, continuously adjust the energy recommendation goal, and then adjust the allocation value of the daily nutrient intake requirement until the target user achieves the weight management goal, and update the allocation value of the daily nutrient intake requirement corresponding to the current weight of the target user according to the target value of the daily energy intake requirement and the adjustment ratio of the daily nutrient intake requirement corresponding to the current exercise type.

[0133] Specifically, if the first deviation does not meet the preset requirements, it indicates that the weight loss goal cannot be achieved according to the initial energy recommendation target. Assuming that according to the initial value of the daily energy intake requirement in the energy recommendation target, which is 1800 kcal, and the daily nutrient intake requirement distribution ratio (45% for carbohydrates, 35% for protein, and 20% for fat), the first deviation Adherence between the finally calculated EstimatedIntake and Target does not meet the preset requirements. At this time, the initial value of the daily energy intake requirement can be adjusted, and then the daily nutrient intake requirement distribution ratio can be adjusted, and Adherence is gradually calculated and verified to see if it meets the preset requirements. Stop adjusting the daily nutrient intake requirement distribution value in the energy recommendation target until the preset requirements are met.

[0134] In a specific example, when the first deviation does not meet the preset requirements, corresponding to step S303 in the above embodiment, At this time, the initial daily carbohydrate intake requirement distribution ratio of 40% is adjusted to 45%, and the adjusted ratio of the daily carbohydrate intake requirement is recalculated.

[0135] Similarly, at this time, the initial daily protein intake requirement distribution ratio of 30% is adjusted to 35%, and the adjusted ratio of the daily protein intake requirement is recalculated.

[0136] Similarly, if the current exercise of the target user also includes anaerobic exercise or anaerobic exercise, and the fat distribution ratio decreases, the adjusted ratio of the daily fat intake requirement can be represented by P fat ′. Or, The daily fat intake requirement distribution ratio is represented by the above representation.

[0137] Since the three major nutrients in the body are mainly carbohydrates, proteins, and fats, the above P carbs ′ is 55%, and the above P protein ′ is 38%. Therefore, for the convenience of calculation, P fat ′ = 100% - P carbs ′ - P protein ′ = 100% - 55% - 38% = 7%.

[0138] Specifically, through step S401 in the above embodiment, it is calculated that Target = TDEE - 500 = 3207.5 - 500 = 2707.5 kcal / day. For carbohydrates, the adjusted daily carbohydrate intake requirement distribution value corresponding to the current weight of the target user is represented by Carbs′, then The allocated value of the daily protein intake requirement corresponding to the current weight of the target user after adjustment is denoted as Protein'. The allocated value of the daily fat intake requirement corresponding to the current weight of the target user after adjustment is denoted as Fat'.

[0139] Therefore, according to the dynamic adjustment plan, the allocated values of the daily nutrient intake requirements corresponding to the current weight of the target user are updated through the energy intake allocation model in the above, and are respectively updated to the allocated value of the daily carbohydrate (Carbs') intake requirement of 372.28 g, the allocated value of the daily protein intake requirement of 256.21 g, the allocated value of the daily protein intake requirement of 256.21 g, and the allocated value of the daily fat intake requirement of 21.06 g.

[0140] Step S404: Update the daily energy intake requirement corresponding to the current weight of the target user according to the target value of the daily energy intake requirement.

[0141] Specifically, in the above step S401, calculate Target = TDEE - 500 = 3207.5 - 500 = 2707.5 kcal / day, and update the target value of the daily energy intake requirement to the daily energy intake requirement corresponding to the current weight of the target user.

[0142] Step S405: Update the energy allocation value for each meal corresponding to the current weight of the target user according to the total daily actual exercise energy consumption of the target user and the total daily energy consumption of the target user.

[0143] If the first deviation meets the preset requirements, there is no need to adjust the initially recommended daily diet advice, and return to the above step S102 to directly predict the daily energy intake requirement and the allocated values of the daily nutrient intake requirements corresponding to the current weight of the target user.

[0144] Specifically, combine the total daily actual exercise energy consumption of the target user and the total daily energy consumption of the target user to update the energy allocation value for each meal corresponding to the current weight of the target user, ensuring that even if the target user's intake per meal changes due to excessive exercise, the energy allocation value for each meal of the target user can be adjusted or planned in real time and dynamically, preventing the target user from being unable to achieve the weight management goal due to unreasonable intake during each meal.

[0145] Therefore, since the present disclosure verifies whether the target user can achieve the weight management goal according to the initial energy recommendation goal by determining whether the first deviation between the target value of the daily energy intake requirement and the daily energy intake requirement corresponding to the current weight of the target user meets the preset requirements, and when it is determined that the weight management goal cannot be achieved, the daily nutrient element intake requirement allocation value and the energy allocation value for each meal are dynamically adjusted immediately to ensure that the target user successfully achieves the weight management goal, and then accurate daily diet recommendations are formulated for the target user, enhancing the target user's weight management experience.

[0146] In this embodiment, a weight management method based on user characteristics is provided, which can be used in mobile terminals such as mobile phones and tablet computers. Figure 5 It is a flowchart of the weight management method based on user characteristics according to an embodiment of the present invention. The label information of the target user further includes: the energy already consumed by the target user in the current meal and the remaining number of meals. The current exercise information further includes the average daily exercise energy consumption of the target user within the weight management duration, such as Figure 5 As shown, in step S405 above, according to the daily actual total exercise energy consumption of the target user and the daily total energy consumption of the target user, the energy allocation value for each meal corresponding to the current weight of the target user is updated, including:

[0147] Step S501, calculate the second deviation between the average daily exercise energy consumption of the target user and the actual total daily exercise energy consumption of the target user.

[0148] Specifically, in step S205 of the above embodiment, the daily actual exercise energy consumption E of the target user U1 is calculated exercise = E aerobic + E anaerobic = 1120 + 420 = 1540 kcal. Assuming that the weight management duration of the target user is 14 days, the average daily exercise energy consumption of the target user within the weight management duration of 14 days is represented by E exercise ′, and E exercise ′ = 1000 kcal.

[0149] The second deviation is represented by ΔE e , then ΔE e = |E exercise ′ - E exercise | = |1000 - 1540| = 540 kcal.

[0150] Step S502, calculate the daily energy intake adjustment value of the target user according to the second deviation and the daily total energy consumption of the target user.

[0151] Specifically, the daily total energy consumption TDEE of the target user calculated in step S207 above = BMR + E exercise= 1667.5 + 1540 = 3207.5 kcal / day. If the adjusted value of the daily energy intake of the target user is represented by AdjustCalorie, then Adjust Calorie = TDEE + E e = 3207.5 + 540 = 3747.5 kcal / day.

[0152] Step S503: Calculate the estimated energy per meal of the target user according to the adjusted value of the daily energy intake, the energy already consumed by the target user in the current meal, and the remaining number of meals.

[0153] Specifically, the energy already consumed by the target user in the current meal can be represented by Intake Calorie, the remaining number of meals can be represented by Remaining Meal, and the estimated energy per meal of the target user is represented by Meal Calorie. The estimated energy per meal is calculated by the following formula.

[0154]

[0155] Step S504: Calculate the remaining energy requirement for the remaining meals of the target user after the current meal according to the estimated energy per meal of the target user and the remaining number of meals.

[0156] Specifically, assuming that in combination with the estimated energy per meal of the above target user, the remaining energy requirement for the remaining meals of the target user after the current meal is calculated to be 1000 kcal.

[0157] Step S505: Predict the energy allocation value per meal corresponding to the current weight of the target user according to the remaining energy requirement for the remaining meals and the remaining number of meals.

[0158] Specifically, assuming that the remaining number of meals is 2 times and the remaining energy requirement for the remaining meals of the target user after the current meal is 1000 kcal, the predicted energy allocation value per meal corresponding to the current weight of the target user is 1000 / 2 = 500 kcal.

[0159] Therefore, the present disclosure dynamically adjusts the intake per meal of the target user through the second deviation between the average daily exercise energy consumption of the target user and the actual total daily exercise energy consumption of the target user, preventing the target user from failing to achieve the weight management goal due to unreasonable intake during each meal.

[0160] In this embodiment, a diet recommendation method is provided, which can be used in mobile terminals such as mobile phones, tablet computers, etc. Figure 6 It is a flowchart of the diet recommendation method according to the embodiment of the present invention, as Figure 6 shown. The process includes the following steps:

[0161] Step S601, obtaining third information that affects each meal of the target user, the third information including: the current location of the target user, dietary preferences, and food information and food library information of the current location.

[0162] Specifically, the current location of the target user can use the GPS information of the target user's device or resolve the geographic location through the IP address. For example, the current location of the target user is Beijing, longitude and latitude: 39.9042°N, 116.4074°E. The food information at the current location includes the local mainstream food culture (such as Chinese food, Japanese food, Mediterranean diet), as well as cost-effective ingredients in the local market. The target user's dietary preferences represent the target user's dietary taboos (such as less spicy, less salt) and preferred tastes (such as spicy, light). The food library information stores a variety of food information.

[0163] Step S602, the daily energy intake requirement, daily nutrient element intake requirement allocation value and energy allocation value per meal corresponding to the current weight of the target user updated according to the dynamic adjustment plan generated by the weight management method based on user characteristics in the above embodiment, and the third information are input into the diet recommendation model to predict the recommended recipes for each meal of the target user, wherein the diet recommendation model is a pre-trained neural network model.

[0164] Specifically, since the target user's diet recipe is related to the daily nutrient intake requirements and the intake per meal, and the traditional method cannot dynamically adjust the daily energy intake requirements and the energy distribution per meal, the diet recipe generated by combining the static daily dietary recommendations (daily nutrient intake requirements, daily energy intake requirements) is often also static, which ultimately makes it impossible to recommend accurate diet recipes for the target users.

[0165] For example, if the target user changes due to real-time exercise and / or meal intake, and the energy intake allocation model is unable to generate a dynamic adjustment plan to dynamically adjust the dietary recommendations corresponding to the target user's current weight (daily energy intake requirements, daily nutrient intake requirement allocation values, and meal energy allocation values), it will directly result in the dietary recommendation model being unable to change the recommended recipes for each meal of the target user, and thus being unable to accurately provide recommended recipes for the target user, thereby affecting the target user's weight management.

[0166] Exemplarily, through step S403 of the above embodiments, according to the dynamic adjustment scheme, the daily nutrient intake requirement allocation values corresponding to the current weight of the target user are updated through the energy intake allocation model in the above, and are respectively updated to the daily carbohydrate (Carbs′) intake requirement allocation value of 372.28 g, the daily protein intake requirement allocation value of 256.21 g, the daily protein intake requirement allocation value of 256.21 g, and the daily fat intake requirement allocation value of 21.06 g. The recipes for the three meals of the diet recommended for the target user are respectively:

[0167] Breakfast: 100 g of oats (60 g of carbs) + 2 hard-boiled eggs (14 g of protein) + 1 apple.

[0168] Lunch: Stewed mutton with radish (200 g of mutton, 40 g of protein; 150 g of radish, 10 g of carbs).

[0169] Dinner: Stir-fried green vegetables (200 g of green vegetables, 5 g of fat) + 150 g of rice (45 g of carbs).

[0170] In a specific example, assume that the current exercise of the target user U1 is walking, and the initially predicted daily energy intake requirement through the energy intake allocation model is 2,803.79 kcal / day, and the daily nutrient intake requirements (250 g of carbohydrate intake requirement, 165 g of protein intake requirement, and 37.8 g of fat intake requirement). Combining this information with the third information, the recommended recipe for each meal of the target user U1 predicted through the diet recommendation model is A. When the current exercise of the target user U1 changes from walking to running, after dynamically adjusting the daily energy intake requirement, the daily nutrient intake requirement, and the energy allocation value for each meal through the energy intake allocation model, and then predicting the recommended recipe for each meal of the target user U1 through the diet recommendation model as B. Therefore, the present disclosure simultaneously utilizes the energy intake allocation model and the diet recommendation model, which can not only dynamically adjust the future diet plan of the target user to achieve the weight management goal of the target user, but also can accurately recommend recipes for the target user according to the dietary preferences of the target user.

[0171] In addition, since the present disclosure not only combines the prediction results of the dietary suggestions of the energy intake allocation model, but also combines the dietary preferences of the target user and the ingredient information at the current location, the present disclosure can provide recipe suggestions that match the dietary preferences for different target users at their respective locations according to the personalized eating habits of different target users.

[0172] In some alternative embodiments, the ingredient information at the current location includes: the priority score value of each type of ingredient, the weight coefficient of different ingredients in each type of recipe, and predicting the recommended recipe for each meal of the target user includes:

[0173] Step a1: Obtain the priority score value of the first ingredient according to the priority score values of each type of ingredient.

[0174] Specifically, the first ingredient can be the ingredient initially selected by the target user, and the priority score value of the first ingredient can be represented by S i The priority score value of the first ingredient is expressed by the following formula:

[0175] S i = W1×A i + W2×P i + W3×C i ;

[0176] Wherein, S i is the priority score value of the first ingredient i, A i is the easy-to-purchase score value of the first ingredient i, C i is the cultural matching degree score value of the first ingredient i, W1 is the first weight coefficient, W2 is the second weight coefficient, W3 is the third weight coefficient, and by default, W1>W2>W3.

[0177] Step a2: Obtain the weight coefficient of the first ingredient in the recipe.

[0178] Specifically, the weight coefficient of the first ingredient in the recipe can be represented by N i to represent.

[0179] Step a3: Predict the recommended recipe for each meal of the target user according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe.

[0180] Specifically, the recommended recipe for each meal of the target user is predicted by the following formula.

[0181] Recipe j = argmaxk∈Available(∑ i∈Ingredients S i ×N i );

[0182] Wherein, Recipe j is the jth recipe recommended for the target user, and ingredients are all ingredients.

[0183] Since the present disclosure can match a suitable recipe for the target user by combining the ingredient priority and the nutritional needs of the target user, it can meet the user's dietary needs.

[0184] In some alternative embodiments, the above step a3, predicting the recommended recipe for each meal of the target user according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe, includes:

[0185] Step b1: When the target user replaces the first ingredient with the second ingredient, obtain the preference score value of the target user for the second ingredient according to the target user's dietary preferences.

[0186] Step b2: Predict the recommended recipes for each meal of the target user based on the priority score value of the first ingredient and the preference score value of the target user for the second ingredient.

[0187] Specifically, predicting the recommended recipes for each meal of the target user based on the priority score value of the first ingredient and the preference score value of the target user for the second ingredient is expressed by the following formula:

[0188] S i ′ = S i - ΔC i where ΔC i is the preference portion value of the target user for the second ingredient.

[0189] Since the present disclosure considers the replacement of ingredients according to the needs of the target user in the above manner, and combines the dietary preferences of the target user to re-optimize the recommended recipes for each meal of the target user, it can enhance the dietary experience of the target user and meet the dietary needs of the target user.

[0190] As Figure 7 shown, it is a schematic diagram of the present disclosure for recommending a diet plan for the target user by combining an energy intake distribution model and a diet recommendation model. In Figure 7 , the upper large model is an energy intake distribution model, and this large model can be (ChatGlM - 4 / LWM - Text - Chat). The lower large model is a diet recommendation model. The upper large model combines user information (physiological information, goals, today's exercise) and sports nutrition knowledge to generate macroscopic dietary suggestions for the target user (the daily energy intake requirements and the distribution values of daily nutrient element intake requirements corresponding to the current weight of the target user), and then the lower large model combines the output results of the upper large model and the food environment (surrounding supermarkets, surrounding takeaways, surrounding restaurants), food library information to recommend a diet plan for the target user.

[0191] The dietary recommendation method of the present disclosure combines the prediction results of the daily dietary recommendations of the energy intake distribution model, and the energy intake distribution model optimizes the daily intake ratio of nutritional elements for different exercise types. In particular, it converts energy consumption into specific dietary requirements, accurately estimates the daily calorie requirements through a non-linear optimization algorithm, and adjusts the dietary recommendations in real time based on the weight change and goal completion of the target user, improving the accuracy and individualized experience of goal achievement. Furthermore, the auxiliary dietary recommendation model can also dynamically adjust the dietary plan, solving the deficiencies of the single static diet and recipe recommendations in the traditional method, and can also help users share and compare dietary plans, enhancing user stickiness.

[0192] In this embodiment, a weight management device based on user characteristics is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0193] This embodiment provides a weight management device based on user characteristics, as Figure 8 shown, including:

[0194] A user information acquisition module 801, configured to acquire the first information and the second information that affect the weight management of the target user. The first information includes: the label information of the target user, the weight management goal, the energy recommendation goal, and the current exercise information of the target user. The second information represents exercise nutrition information;

[0195] A dietary recommendation prediction module 802, configured to input the first information and the second information into the energy intake distribution model, predict the daily dietary recommendations corresponding to the current weight of the target user. The daily dietary recommendations include the daily energy intake requirement and the distribution value of the daily nutritional element intake requirement, and generate a dynamic adjustment plan for the daily dietary recommendations to update the daily energy intake requirement, the distribution value of the daily nutritional element intake requirement, and the energy distribution value per meal corresponding to the current weight of the target user. Among them, the energy intake distribution model is a pre-trained neural network model.

[0196] In some optional implementation manners, the label information of the target user includes: height, gender, age, initial weight, current weight, and weight management duration; the current exercise information of the target user includes: exercise time, exercise type, and exercise intensity coefficient; the exercise nutrition information includes: the energy density of body mass; the dietary recommendation prediction module 802 includes:

[0197] A first calculation sub-module, configured to calculate the weight change amount of the target user during the weight management duration according to the current weight and the initial weight of the target user;

[0198] A second calculation sub-module, configured to calculate the energy deficit of the target user according to the energy density of the body mass and the change in body weight of the target user during the weight management period;

[0199] A third calculation sub-module, configured to obtain the current exercise type of the target user and the corresponding exercise time and exercise intensity coefficient;

[0200] A fourth calculation sub-module, configured to calculate the daily actual exercise energy consumption corresponding to the current exercise type of the target user according to the current exercise type of the target user, the corresponding exercise time, the exercise intensity coefficient, and the initial body weight of the target user;

[0201] A fifth calculation sub-module, configured to count the daily actual exercise energy consumption corresponding to the current exercise type of the target user to obtain the total daily actual exercise energy consumption of the target user;

[0202] A sixth calculation sub-module, configured to calculate the basal metabolic rate of the target user according to the height, gender, age, and initial body weight of the target user;

[0203] A seventh calculation sub-module, configured to calculate the total daily energy consumption of the target user according to the basal metabolic rate of the target user and the total daily actual exercise energy consumption of the target user;

[0204] An eighth calculation sub-module, configured to predict the daily energy intake requirement corresponding to the current body weight of the target user according to the total daily energy consumption, energy deficit, and weight management period of the target user.

[0205] In some alternative embodiments, the energy recommendation targets include: the initial value of the daily energy intake requirement, the distribution ratio of the daily nutrient intake requirements, and the sports nutrition information of the target user further includes: the adjustment coefficients for different types of exercises; the diet recommendation prediction module 802 includes:

[0206] A first acquisition sub-module, configured to acquire the current exercise type of the target user;

[0207] A second acquisition sub-module, configured to acquire the adjustment coefficient, exercise time, and distribution ratio of the daily nutrient intake requirements corresponding to the current exercise type of the target user;

[0208] A third acquisition sub-module, configured to calculate the adjustment ratio of the daily nutrient intake requirements corresponding to the current exercise type according to the adjustment coefficient, exercise time, and distribution ratio of the daily nutrient intake requirements corresponding to the current exercise type of the target user;

[0209] The fourth acquisition sub-module is used to adjust the ratio according to the daily nutrient intake requirement corresponding to the current exercise type and the initial value of the daily energy intake requirement, and predict the daily nutrient intake requirement allocation value corresponding to the current weight of the target user.

[0210] In some alternative embodiments, the weight management goal includes: the daily target adjusted energy of the target user. The diet recommendation prediction module 802 includes:

[0211] The target calculation sub-module is used to calculate the target value of the daily energy intake requirement of the target user according to the daily target adjusted energy of the target user and the daily total energy consumption of the target user;

[0212] The deviation judgment sub-module is used to judge whether the first deviation between the target value of the daily energy intake requirement and the daily energy intake requirement corresponding to the current weight of the target user meets the preset requirements;

[0213] The first update sub-module is used to continuously adjust the energy recommendation target if the first deviation does not meet the preset requirements, and then adjust the daily nutrient intake requirement allocation value until the target user achieves the weight management goal, and update the daily nutrient intake requirement allocation value corresponding to the current weight of the target user according to the target value of the daily energy intake requirement and the daily nutrient intake requirement adjustment ratio corresponding to the current exercise type;

[0214] The second update sub-module is used to update the daily energy intake requirement corresponding to the current weight of the target user according to the target value of the daily energy intake requirement;

[0215] The third update sub-module is used to update the energy allocation value for each meal corresponding to the current weight of the target user according to the daily actual total exercise energy consumption of the target user and the daily total energy consumption of the target user.

[0216] In some alternative embodiments, the label information of the target user further includes: the energy already consumed by the target user in the current meal and the remaining number of meals. The current exercise information further includes the daily average exercise energy consumption of the target user during the weight management period. The third update sub-module includes:

[0217] The first calculation unit is used to calculate the second deviation between the daily average exercise energy consumption of the target user and the daily actual total exercise energy consumption of the target user;

[0218] The second calculation unit is used to calculate the daily energy intake adjustment value of the target user according to the second deviation and the daily total energy consumption of the target user;

[0219] The third calculation unit is used to calculate the estimated energy for each meal of the target user according to the daily energy intake adjustment value, the energy already consumed by the target user in the current meal, and the remaining number of meals.

[0220] A fourth calculation unit, configured to calculate the remaining dietary energy requirement of the target user after the current meal according to the estimated energy per meal of the target user and the remaining number of meals.

[0221] A fifth calculation unit, configured to predict the energy allocation value per meal corresponding to the current weight of the target user according to the remaining dietary energy requirement and the remaining number of meals.

[0222] In a second aspect, the present disclosure provides a dietary recommendation device, including:

[0223] A user information acquisition module, configured to acquire third information affecting the diet per meal of the target user, where the third information includes: the current location of the target user, dietary preferences, ingredient information at the current location, and food library information.

[0224] A recommended recipe prediction module, configured to input the daily energy intake requirement, the distribution value of the daily nutrient element intake requirement, and the energy allocation value per meal corresponding to the current weight of the target user updated according to the dynamic adjustment plan generated by the dietary recommendation method based on user characteristics in the first aspect or any implementation manner of the first aspect, and the third information into a dietary recommendation model, and predict the recommended recipes for the diet per meal of the target user, where the dietary recommendation model is a neural network model pre-trained.

[0225] In some optional implementation manners, the ingredient information at the current location includes: the priority score value of each type of ingredient, the weight coefficient of different ingredients in each type of recipe, and the recommended recipe prediction module includes:

[0226] A first acquisition sub-module, configured to acquire the priority score value of the first ingredient according to the priority score value of each type of ingredient.

[0227] A second acquisition sub-module, configured to acquire the weight coefficient of the first ingredient in the recipe.

[0228] A recipe prediction sub-module, configured to predict the recommended recipes for the diet per meal of the target user according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe.

[0229] In some optional implementation manners, the recommended recipe prediction module includes:

[0230] A user preference acquisition sub-module, configured to acquire the preference score value of the target user for the second ingredient according to the dietary preferences of the target user when the target user replaces the first ingredient with the second ingredient.

[0231] A recommended recipe prediction sub-module, configured to predict the recommended recipes for the diet per meal of the target user according to the priority score value of the first ingredient and the preference score value of the target user for the second ingredient.

[0232] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0233] The weight management device or diet recommendation 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.

[0234] The embodiment of the present invention further provides a computer device having the above-mentioned weight management device or diet recommendation device based on user characteristics.

[0235] Please refer to Figure 9 , Figure 9 which is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As shown in Figure 9 , 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 9 In

[0236]

[0237] Processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, processor 10 can further include a hardware chip. The above-mentioned hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0238] Among them, 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.The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0239] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.

[0240] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0241] Embodiments of the present invention also provide a computer-readable storage medium. The methods according to the embodiments 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 as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and to be stored on a local storage medium, so that the methods described herein can be stored on such software processes on a storage medium using a general computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disc, 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 memories. 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, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0242] 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 weight management method based on user characteristics, characterized in that, The method includes: Obtaining first information and second information that affect the weight management of a target user, where the first information includes: label information of the target user, weight management goal, energy recommendation goal, current exercise information, and the second information represents sports nutrition information; Inputting the first information and the second information into an energy intake allocation model to predict the daily diet recommendation corresponding to the current weight of the target user, where the daily diet recommendation includes the daily energy intake requirement and the allocation value of the daily nutrient intake requirement, and generating a dynamic adjustment plan for the daily diet recommendation to update the daily energy intake requirement, the allocation value of the daily nutrient intake requirement, and the energy allocation value for each meal corresponding to the current weight of the target user. Here, the energy intake allocation model is a pre-trained neural network model.

2. The weight management method based on user characteristics according to claim 1, wherein The label information of the target user includes: height, gender, age, initial weight, current weight, and weight management duration; the current exercise information of the target user includes: exercise time, exercise type, and exercise intensity coefficient; the sports nutrition information includes: energy density of body mass. Predicting the daily energy intake requirement corresponding to the current weight of the target user includes: Calculating the weight change of the target user during the weight management duration based on the current weight and the initial weight of the target user; Calculating the energy deficit of the target user based on the energy density of body mass and the weight change of the target user during the weight management duration; Obtaining the current exercise type of the target user and its corresponding exercise time and exercise intensity coefficient; Calculating the daily actual exercise energy consumption corresponding to the current exercise type of the target user based on the current exercise type of the target user, its corresponding exercise time, exercise intensity coefficient, and the initial weight of the target user; Statistical analysis of the daily actual exercise energy consumption corresponding to the current exercise type of the target user to obtain the total daily actual exercise energy consumption of the target user; Calculating the basal metabolic rate of the target user based on the height, gender, age, and initial weight of the target user; Calculating the total daily energy consumption of the target user based on the basal metabolic rate of the target user and the total daily actual exercise energy consumption of the target user; Predicting the daily energy intake requirement corresponding to the current weight of the target user based on the total daily energy consumption of the target user, the energy deficit, and the weight management duration.

3. The weight management method based on user characteristics according to claim 2, wherein The energy recommendation goal includes: the initial value of the daily energy intake requirement and the allocation ratio of the daily nutrient intake requirement. The sports nutrition information of the target user further includes: adjustment coefficients for different types of exercise. Predicting the allocation value of the daily nutrient intake requirement corresponding to the current weight of the target user includes: Obtaining the current exercise type of the target user; Obtaining the adjustment coefficient, exercise time, and the allocation ratio of the daily nutrient intake requirement corresponding to the current exercise type of the target user; Calculate the daily nutrient element intake requirement adjustment ratio corresponding to the current exercise type according to the adjustment coefficient corresponding to the current exercise type of the target user, the exercise time, and the daily nutrient element intake requirement allocation ratio; The daily nutrient element intake requirement allocation value corresponding to the current weight of the target user is predicted based on the daily nutrient element intake requirement adjustment ratio corresponding to the current exercise type and the initial value of the daily energy intake requirement.

4. The weight management method based on user characteristics according to claim 2, wherein The weight management goal includes: the target user's daily target energy adjustment, and the dynamic adjustment plan for generating the weight management goal to update the target user's daily energy intake requirement, daily nutrient element intake requirement allocation value, and energy allocation value per meal corresponding to the current weight of the target user includes: Calculating a target value of the target user's daily energy intake requirement according to the target user's daily target-adjusted energy and the target user's daily total energy consumption; Determining whether a first deviation between the target value of the daily energy intake requirement and the daily energy intake requirement corresponding to the current weight of the target user meets a preset requirement; If the first deviation does not meet the preset requirement, the energy recommendation target is adjusted continuously, and then the daily nutrient element intake requirement allocation value is adjusted until the target user achieves the weight management target, and the daily nutrient element intake requirement allocation value corresponding to the current weight of the target user is updated according to the target value of the daily energy intake requirement and the daily nutrient element intake requirement adjustment ratio corresponding to the current exercise type; According to the target value of the daily energy intake requirement, updating the daily energy intake requirement corresponding to the current weight of the target user; The energy allocation value for each meal corresponding to the current weight of the target user is updated according to the actual total daily exercise energy consumption of the target user and the total daily energy consumption of the target user.

5. The weight management method based on user characteristics according to claim 4, wherein The tag information of the target user also includes: the energy consumed by the target user in the current meal and the number of remaining meals; the current exercise information also includes the target user's daily average exercise energy consumption during the weight management period; and the energy allocation value for each meal corresponding to the current weight of the target user is updated according to the target user's actual daily total exercise energy consumption, the weight management period, and the target user's daily total energy consumption, including: Calculating a second deviation between the target user's daily average exercise energy consumption and the target user's daily actual total exercise energy consumption; Calculating a daily energy intake adjustment value of the target user according to the second deviation and the daily total energy consumption of the target user; Calculate the estimated energy per meal of the target user according to the daily energy intake adjustment value, the energy already ingested by the target user in the current meal, and the number of remaining meals; Calculating the remaining meal energy requirement of the target user after the current meal according to the estimated energy per meal of the target user and the remaining number of meals; The energy distribution value for each meal corresponding to the current weight of the target user is predicted according to the remaining meal energy demand and the remaining number of meals.

6. A diet recommendation method, characterized in that, The method comprises: Obtain third information that affects the diet of the target user for each meal, where the third information includes: the current location of the target user, dietary preferences, ingredient information at the current location, and food library information; Update the daily energy intake requirement, daily nutrient intake requirement allocation value, and energy allocation value for each meal corresponding to the current weight of the target user according to the dynamic adjustment plan generated by the weight management method based on user characteristics described in any one of claims 1 to 4, and input the third information into the diet recommendation model to predict the recommended recipes for the diet of the target user for each meal, where the diet recommendation model is a neural network model pre-trained.

7. The dietary recommendation method according to claim 6, wherein The ingredient information at the current location includes: the priority score value for each type of ingredient, the weight coefficient of different ingredients in each type of recipe. Predicting the recommended recipes for the diet of the target user for each meal includes: According to the priority score value for each type of ingredient, obtain the priority score value of the first ingredient; Obtain the weight coefficient of the first ingredient in the recipe; According to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe, predict the recommended recipes for the diet of the target user for each meal.

8. The dietary recommendation method according to claim 7, characterized in that, Predicting the recommended recipes for the diet of the target user for each meal according to the priority score value of the first ingredient and the weight coefficient of the first ingredient in the recipe includes: When the target user replaces the first ingredient with the second ingredient, according to the dietary preferences of the target user, obtain the preference score value of the target user for the second ingredient; According to the priority score value of the first ingredient and the preference score value of the target user for the second ingredient, predict the recommended recipes for the diet of the target user for each meal.

9. A diet recommendation device based on user characteristics, characterized in that, The device includes: A user information acquisition module, configured to acquire first information and second information that affect the weight management of the target user. The first information includes: label information of the target user, weight management goal, energy recommendation goal, current exercise information, and the second information represents sports nutrition information; A diet recommendation prediction module, configured to input the first information and the second information into an energy intake allocation model to predict the daily diet recommendation corresponding to the current weight of the target user. The daily diet recommendation includes the daily energy intake requirement and the daily nutrient intake requirement allocation value, and generate a dynamic adjustment plan for the daily diet recommendation to update the daily energy intake requirement, the daily nutrient intake requirement allocation value, and the energy allocation value for each meal corresponding to the current weight of the target user, where the energy intake allocation model is a neural network model pre-trained.

10. A computer device, characterized in that, Includes: 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 management method based on user characteristics described in any one of claims 1 to 5, or the diet recommendation method described in any one of claims 6 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the method for weight management based on user characteristics according to any one of 1 to 5 described in any one of claims 1 to 7, or the method for diet recommendation according to any one of claims 6 to 8.

Images