CN112509697A - Multi-module intelligent health management information system - Google Patents

Abstract

The invention provides a multi-module intelligent health management information system, which comprises a module I crowd classification module, a module II muscle increasing and weight increasing scoring module and a module III adaptive parameter optimization module; the first module acquires data such as user age, sex, weight, body fat rate, exercise proficiency, diseases and the like provided by a user, classifies the health parameters of the crowd and obtains the health parameter range of the classified crowd; the second module obtains the crowd classification parameters provided by the first module and the user diet and exercise record parameters provided by the user to carry out health management target-muscle increasing and weight increasing target score calculation to obtain a user score; the third module obtains the score records of all classified users provided by the second module, obtains muscle-increasing weight variation data provided by the users, performs adaptive parameter optimization, obtains optimized score parameters and feeds the optimized score parameters back to the second module, and optimizes the scores of the second module by taking the optimized score parameters as the health management parameters and targets of the users; the invention has simple structure, powerful function, convenient operation and high commercial value.

Description

Multi-module intelligent health management information system

Technical Field

The invention relates to an information synthesis and analysis evaluation system for helping human physiological health, in particular to a multi-module intelligent health management information system.

Background

CN2017111065179 discloses an analysis and evaluation system of physiological information data, which comprises a data input module, a data classification module, a single health index calculation module and a health index comprehensive weighting module, the single health index calculation module comprises a rising normal distribution data calculation module, a falling normal distribution data calculation module and a platform type distribution data calculation module, the single health index calculation module is also provided with a historical data analysis module which is provided with a normalization index adjustment module, the historical data analysis module is used for comparing and analyzing the new physiological information data, the corresponding historical physiological information data and the reference target value to obtain the historical change trend result of the physiological information data, the normalization index adjusting module adjusts the normalization index of the new physiological information data according to the historical change trend result; the single health index calculation module is also provided with a health index adjustment module, and the health index adjustment module comprehensively weights the new health index and the corresponding historical health index to obtain an adjustment value of the health index; however, due to the fact that individuals have different sexes, weights, ages, life habits, exercise habits and the like, a unified standard is adopted to judge and guide people to have unbalanced healthy life; and the user score is obtained by carrying out comprehensive score calculation on the aspects of increasing muscle weight and the like through scientific classification and finally completing indexes of exercise and health management. This can provide a more effective health management effect.

Disclosure of Invention

The invention aims to provide a multi-module intelligent health management information system which helps people to manage and recommend the health of people, including diet and exercise recommendations, through a scientific and coincident crowd classification module, a muscle weight increasing and scoring module and a module capable of adaptively providing health and exercise parameter optimization indexes, and carries out statistics and calculation and evaluation on the health state of individuals through various intelligent means, and has a relatively accepted health evaluation basis at present.

The technical scheme of the invention is that the multi-module intelligent health management information system is characterized by comprising a module I crowd classification module, a module II muscle increasing and weight increasing scoring module and a module III adaptive parameter optimization module; the first module acquires data such as user age, sex, weight, body fat rate, exercise proficiency, diseases and the like provided by a user, classifies the health parameters of the crowd and obtains the health parameter range of the classified crowd; the second module obtains the crowd classification parameters provided by the first module and the user diet and exercise record parameters provided by the user to carry out health management target-muscle increasing and weight increasing target score calculation to obtain a user score; the third module obtains the score records of all classified users provided by the second module, obtains muscle-increasing weight variation data provided by the users, performs adaptive parameter optimization, obtains optimized score parameters and feeds the optimized score parameters back to the second module, and optimizes the scores of the second module by taking the optimized score parameters as the health management parameters and targets of the users;

the module-crowd classification module comprises two sub-modules, namely a sub-module 1.1 data collection sub-module and a sub-module 1.2 user data-crowd classification mapping sub-module;

submodule 1.1 user data collecting submodule for obtaining user personal data provided by user and collecting user data; the sub-module obtains the following user data provided by the user: the method comprises the following steps of collecting user data including race, gender, body fat rate, whether diseases exist, exercise habit/fatigue feeling, pump feeling, soreness feeling, height H, weight W, age Y, weight delta W needing to be increased for one week, exercise time t, anaerobic exercise group number m, anaerobic exercise group number n, anaerobic exercise unit strength weight omega, 4 nutrient intake, exercise type and exercise strength data to obtain user data required by crowd classification mapping;

submodule 1.2 user data-crowd classification mapping submodule obtains user data required by crowd classification mapping provided by submodule 1.1, and carries out user data-crowd classification mapping calculation to obtain crowd classification parameters;

in the specific example, one user is Asian, healthy, regular, male, BFR is less than or equal to 25%, and the value of the classification parameter is g₁＝0.95； g₂＝1，ν₁＝1/3，ν₂＝1/3，ν₃＝1/3；DCE₂＝275kcal，α＝66.47、β＝13.75、γ＝5.0033、Ω＝6.775；WWRF ＝485kcal/kg。

The submodule 1.2 randomly divides the crowd data into a test set and a training set; in the training set, feature selection is carried out on the crowd features, and a decision tree is recursively constructed by adopting an information gain standard; setting a loss function in consideration of the complexity of the decision tree, and pruning the decision tree; finally, classifying the crowd according to the constructed decision tree model to obtain a training model, and testing the classification model by using a test set; constructing a decision tree; until the information gain of all the characteristics is very small or no characteristics can be selected, finally obtaining a decision tree; the characteristics are selected to be 5 types of characteristics of race, disease, exercise habit, male and female and body fat rate, and the population is finally divided into 32 types;

a second module muscle-increasing weight-increasing scoring module which comprises five submodules, namely a user data collecting submodule 2.1, a motor stimulation score calculating submodule 2.2, a calorie score calculating submodule 2.3, a diet proportion score calculating submodule 2.4 and a muscle-increasing weight-increasing comprehensive score calculating module 2.5; the submodule 2.1 is that the user data collecting submodule obtains the record of diet and movement provided by the user, and collects the user data to obtain the data of diet and movement of the user; the sub-module 2.2 exercise stimulation score calculating sub-module obtains the crowd classification parameters provided by the first module crowd classification module, obtains the user exercise data provided by the sub-module 2.1 user data collecting sub-module, and calculates the exercise stimulation score to obtain the user exercise state calculation data and the exercise stimulation score; the submodule 2.3 comprises a calorie score calculating submodule for obtaining the diet and exercise data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the exercise state data of the user provided by the submodule 2.2 exercise stimulation score calculating submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the calorie score to obtain the calorie score; the submodule 2.4 is a diet proportion score calculation submodule for obtaining the diet data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the diet proportion score; the submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires a motion stimulation score provided by the submodule 2.2 motion stimulation score calculating submodule, acquires a caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires a diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires an optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain a user score;

in one embodiment, there is a user's initial score parameter ρ₁＝0.4，ρ₂＝0.3，ρ₃0.3, after being corrected by a third periodic data import module, the score parameter is optimized to rho₁＝0.35，ρ₂＝0.35，ρ₃＝0.3。

The module three-score hyper-parameter self-adaptive optimization module comprises two sub-modules, namely a user data collection sub-module 3.1 and a score hyper-parameter self-adaptive optimization calculation sub-module 3.2; the submodule 3.1 is a user data collecting submodule for obtaining muscle increasing weight variation data provided by a user, obtaining user scores provided by a module two muscle increasing weight scoring module and collecting user data; the submodule 3.2 score hyper-parameter self-adaptive optimization calculation submodule acquires user data required by score hyper-parameter optimization provided by the submodule 3.1 user data collection submodule, and performs score hyper-parameter self-adaptive optimization calculation to obtain an optimized comprehensive score hyper-parameter; and the score hyperparameter self-adaptive optimization submodule evaluates the relation between each input variable and the target variable by adopting a characteristic selection method to obtain the optimal weight.

The submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires the exercise stimulation score provided by the submodule 2.2 exercise stimulation score calculating submodule, acquires the caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires the diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires the optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain the user score.

Has the advantages that: according to scientific evidence research, the weight index, exercise and macro nutrient reference proportion related to the invention accords with the rule of human health and energy metabolism, and gives consideration to the purposes of muscle building and health. If macronutrients are determined in a macronutrient large-scale framework, new ideas of further absorption and logical modern health are needed, such as: (1) a source of protein; (2) suitably unsaturated fatty acids; (3) the staple food is matched with substances with different blood sugar loads to improve the blood sugar health. And calculating the diet proportion score by acquiring the crowd classification parameters provided by the module-crowd classification module to obtain the diet proportion score.

The invention has simple structure, powerful function, convenient operation and high commercial value.

Drawings

FIG. 1: a multi-module intelligent health management information system;

FIG. 2: a crowd classification module dataflow graph;

FIG. 3: a muscle gain score module dataflow graph;

FIG. 4: and (4) a score hyper-parameter adaptive optimization module dataflow graph.

Detailed Description

Referring to the drawings, fig. 1 is a multi-module intelligent health management information system:

module-crowd classification module

For a module-to-crowd classification module, the sub-module dataflow diagram is shown in FIG. 2. The crowd classification module comprises two sub-modules, namely a data collection sub-module and a user data-crowd classification mapping sub-module. Submodule 1.1 user data collecting submodule for obtaining user personal data provided by user and collecting user data; the sub-module 1.2 user data-crowd classification mapping sub-module obtains the user data required by the crowd classification mapping provided by the sub-module 1.1, and carries out the calculation of the user data-crowd classification mapping to obtain the crowd classification parameters.

Referring to fig. 2: crowd classification module dataflow graph

Module 1.1 user data collection submodule

For the 1.1 user data collection submodule, this submodule retrieves the following user data provided by the user: the method comprises the steps of acquiring user data, collecting the user data, and obtaining the user data required by crowd classification mapping.

Module 1.2 user data-crowd classification mapping submodule

For the 1.2 user data-crowd classification mapping sub-module, the sub-module obtains the user data required by the crowd classification mapping provided by the 1.1 user data collecting sub-module, and performs the user data-crowd classification mapping to obtain the crowd classification parameters.

Specifically, the module 1.2 randomly divides the crowd data into a test set and a training set. In the training set, feature selection is carried out on the human group features, and a decision tree is recursively constructed by adopting an information gain standard. And then setting a loss function by considering the complexity of the decision tree, and pruning the decision tree. And finally, classifying the crowd according to the constructed decision tree model to obtain a training model, and testing the classification model by using a test set. The information gain standard adopts l (x)_i)＝-log₂p(x_i) Wherein the symbol x_iIndicating a certain classification condition; p (x)_i) Representing the probability of selecting the classification; l (x)_i) Denotes x_iThe amount of information of (2). To calculate the entropy, we need to calculate the expected value of the information contained in all possible values of all classes

wherein ,p(x_i) Indicating the probability of selecting the class, and n indicates a total of n classes. Entropy of experience of

Wherein D represents a training data set, C_kRepresenting a certain classification condition of the training data set, K representing a common K classification condition, | C_kIs of class C_kThe number of samples.

The conditional entropy H (Y | X) represents the uncertainty of the random variable Y given the random variable X,

wherein, when the random variable X is X_iIn the case of such a classification, the probability p of that classification_i＝P(X＝x_i) And n represents a total of n classifications.

The information gain g (D, a) ═ H (D) -H (D | a) of feature a to training data set D, where H (D) is the empirical entropy of set D and H (D | a) represents the difference between the empirical conditional entropies of D for a given condition of feature a. Then, a decision tree is constructed, information gains of all possible characteristics are calculated for nodes from root nodes (root nodes), the characteristics with the maximum information gains are selected as the characteristics of the nodes, child nodes are established according to different values of the characteristics, and then the above method is recursively called for the child nodes to construct the decision tree; until the information gain of all the characteristics is small or no characteristics can be selected, a decision tree is obtained finally. Pruning the decision tree by minimizing the overall loss function or cost function of the decision tree, the loss function being

Wherein T represents the current leaf node, and T represents all leaf nodes of the subtree; h_t(T) represents the entropy of the T-th leaf; n is a radical of_tRepresenting the number of training samples contained in the t leaf nodes; α represents a penalty coefficient.

Wherein, the N is_tRepresenting the number of training samples contained in the t leaf nodes; n is a radical of_tkThe number of training examples contained in the kth class of the t leaf nodes is shown, and K represents a common K classification condition. In this case, the characteristics are selected as 5 types of characteristics (race, disease, exercise habit, male and female, body fat rate), and the population is finally divided into 32 types. The crowd classification module variable table and the crowd classification parameter table are shown in tables 1 and 2.

Table 1: crowd classification module variable table

Table 2: crowd classification parameter table

Module-two muscle increasing weight increasing scoring module

For the module two muscle gain score module, the submodular dataflow graph is shown in fig. 3. The muscle-increasing weight-increasing scoring module comprises five submodules, namely a user data collecting submodule 2.1, a motor stimulation score calculating submodule 2.2, a caloric score calculating submodule 2.3, a diet proportion score calculating submodule 2.4 and a muscle-increasing weight-increasing comprehensive score calculating module 2.5. The submodule 2.1 is that the user data collecting submodule obtains the record of diet and movement provided by the user, and collects the user data to obtain the data of diet and movement of the user; the sub-module 2.2 exercise stimulation score calculating sub-module obtains the crowd classification parameters provided by the first module crowd classification module, obtains the user exercise data provided by the sub-module 2.1 user data collecting sub-module, and calculates the exercise stimulation score to obtain the user exercise state calculation data and the exercise stimulation score; the submodule 2.3 comprises a calorie score calculating submodule for obtaining the diet and exercise data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the exercise state data of the user provided by the submodule 2.2 exercise stimulation score calculating submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the calorie score to obtain the calorie score; the submodule 2.4 is a diet proportion score calculation submodule for obtaining the diet data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the diet proportion score; the submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires the exercise stimulation score provided by the submodule 2.2 exercise stimulation score calculating submodule, acquires the caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires the diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires the optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain the user score.

Referring to fig. 3: and a data flow diagram of the muscle growth increasing scoring module, wherein for the submodule 2.1, a user data collection submodule acquires the diet and exercise records provided by the user and collects the user data to obtain the diet and exercise data of the user.

Module 2.2 Motor stimulation score calculation submodule

And for the submodule 2.2, the exercise stimulation score calculation submodule acquires the crowd classification parameters provided by the module-one crowd classification module, acquires the user exercise data provided by the submodule 2.1 user data collection submodule, and calculates the exercise stimulation score to obtain the user exercise state calculation data and the exercise stimulation score.

The control method comprises the step of obtaining the daily motor stimulation absolute score S in the period_aObtained by the following formula:

wherein X ═ a₁，a₂，a₃……a_F) For describing the vector before movement, defining each actual component of a process facing F indexes, a_fScoring for pre-exercise index f, (a)_f)_maxThe index f is the highest score before exercise; said Y ═ b₁，b₂，b₃……b_F) For describing the vector after the movement, defining each actual component of the f indexes oriented to the b process, b_fIs the score of the index f after exercise, (b)_f)_maxThe index f after exercise is the highest score; theta is the adjustment coefficient in motion, and theta max is the maximum value of the adjustment coefficient in motion. F is 1, 2 and 3 … … F (F is the maximum value of F), and only three indexes are considered at the present stage.

2. The daily exercise stimulation of the sporter is related to a plurality of indexes, and the current analysis considers that: the synergistic relationship of the three reference indexes should be strengthened, the foundation of fatigue feeling is not highlighted any more, and the dot product operation is performed and the quantity product is obtained by aiming at two effective time points which are beneficial to evaluation, namely before and after training, and the row vectors which are respectively measured under the three indexes. Based on real-world context diversity and individual variability. The expected value range is expanded, so that the self evaluation dimension of the user is improved, after the training is finished, the user is guided to recall and evaluate the whole training experience, and the adjustment coefficient is preset and expanded by combining related high-index documents.

(1) Research shows that body fatigue is common to people with regular motion at the beginning of training, or the inherent training frequency of the people and the target guidance type in system training are obtained, and the stimulation depth of a successive training plan to a trainer is obtained. Thus, when the default exerciser is in a non-fully recovered state, the mild fatigue perceived by the exerciser may be equivalent to a benign state during which the target muscle is more likely to pump fresh blood and help activate the muscle-nervous system. Indeed, mild-moderate fatigue may provide a gain for training, but it should be pointed out that moderate to strong fatigue may significantly increase the probability of exercise risks (e.g. cardiopulmonary system collapse, muscle and fascia damage, rhabdomyolysis, etc.) during training, and considering the real situation, the cyclic differentiation training concept has a profound effect in the above population, and the training under fatigue is not normal, so in this system, it should be discussed from the perspective of generalized muscular hypertrophy, and many empirical studies show that under moderate-deep fatigue, the pressure of muscle work is increased, and the pressure hormone such as cortisol in blood has a significant correlation with the pressure level, and at this time, the muscle often regulates part of biochemical metabolic processes, especially the metabolism of nitrogen element (e.g. nitrogen retention is reversed), based on the self-protection mechanism formed under the natural selection of human for a long time, namely: causes the muscle decomposition which is twice as much as the usual muscle decomposition and brings negative effects for muscle increase. Further enriches the data, and also makes similar quantitative regulation on the sensible fatigue of the body after exercise.

(2) For pump sensation, extensive empirical data indicate that "pump sensation rooted in muscle memory" is one of: such as a training feature that is difficult to emerge for a given reinforcement order for a particular activity. For high-order sporters, the strong pumping sensation has an extraordinary meaning for muscle shape modeling and is an important reference index for measuring the actual benefit of training; for ordinary sporters, the pump feeling experience can be obtained primarily through the external experimental design and the adaptation of the sporters to the performer-the environmental system, but due to the general short board (poor muscle endurance, insufficient joint stability and low deep muscle group development degree) in the training stage, the excessive pump feeling or the muscle damage accompanied with delayed perception can resist the storage of the muscle.

(3) The soreness feeling is quite different among individuals, enough, the soreness feeling can be generated by the stimulation conforming to the muscle characteristics, generally has delaying property, can be accumulated in a short period, and can be relieved by proper stretching after training, so that the accumulation of lactic acid is reduced, and the recovery is promoted. An important belief in training is: the load is applied, and the nutrition substances are reasonably taken after training, so that the generation of excess recovery can be stimulated. Within the appropriate range, the sensation of soreness is positively correlated with the positive balance of the protein.

Attached rule chart:

index one:

table 3: index-score standard table for regular sporter

Index one (regular trainer)	Perception assessment	Score (before sports)	Score (after sports)
				Feeling of fatigue	Is free of	3	2
	Mild degree of	4	3
					Of moderate degree	3	4
	Is strong and strong	2	3

Table 4: index-score standard table for general sporter

Index one (common health person)	Perception assessment	Score (before sports)	Score (after sports)
				Feeling of fatigue	Is free of	4	1
	Mild degree of	3	2
					Of moderate degree	2	3
	Is strong and strong	1	4

Index two:

table 5: index two-score standard table for regular sporter

Index two (regular sporter)	Perception assessment	Score (before sports)	Score (after exercise)
				Pump feel	Is free of	2	2
	Light and slight	3	3
					Medium and high grade	4	4
	Is strong and strong	3	3

Table 6: index two-score standard table for general sporter

Index three:

table 7: index three-point standard table for regular sporter

Table 8: index three-point standard table for common sporter

Index three (common sporter)	Perception assessment	Score (before sports)	Score (after exercise)
				Soreness and pain feeling	Is free of	3	1
	Light and slight	4	2
					Medium and high grade	3	3
	Is strong and strong	2	4

Evaluation of whole training experience:

table 9: standard table of regulating coefficient

Perception assessment	Coefficient of regulation
		Intermittent	0.8
Is normal	1
		Fluency	1.1
Immersion in water	1.2

Table 10: sports stimulation score calculation submodule variable table

3. And (4) considering the uniformity and range limitation of score distribution, carrying out normal distribution conversion on the absolute score to ensure that the stationarity is 95% and the middle axis value is the maximum absolute score. Namely at

In the distribution of the water-soluble polymer,

and μ ═ S_a)_max. Transformed S_aThe final motor stimulation score.

Submodule 2.3 Calorie calculation submodule, Absolute Calorie score S for each day of the cycle_bObtained by the following formula:

wherein, the S_MThe actual heat surplus is daily in the period; WRF is the target gain energy; s_ynDietary energy intake for each day of the cycle; s_ymDaily energy consumption for each day of the cycle; s_sEnergy is consumed for daily movements within the cycle.

In the step, the daily dietary energy intake in the period is obtained by the following formula:

wherein, the FIE_iIngesting energy for a nutrient i in food; k is a radical of_iThe energy coefficient of the nutrient i taken in unit mass is taken under the condition of referring to the digestibility of the human body; ADI_iIs the nutrient i intake; i is 1, 2 and 3 … … I (I is the maximum value of I), and only four nutrients are considered at the present stage, namely: FIE₁Representing the energy of carbohydrate intake in food, FIE₂Representing the energy of protein intake in food, FIE₃Representing energy of fat intake in fat diet, FIE₄Represents the energy intake of dietary fiber in food; ADI₁Representing the carbohydrate intake energy in food, ADI₂For protein intake, ADI₃For fat intake, ADI₄Is dietary fiber intake; k is a radical of₁In the case of referring to the human digestibility, the energy coefficient of ingested carbohydrate per unit mass is generally 4 kcal/g; k is a radical of₂In the case of referring to the human digestibility, the energy coefficient of protein ingested in unit mass is generally 4 kcal/g; k is a radical of₃In the case of referring to human digestibility, the energy coefficient of fat intake per unit mass is generally 9.6 kcal/g; k is a radical of₄In order to refer to the actual digestibility of human body, the energy coefficient of dietary fiber intake in unit mass is generally 2 kcal/g.

Those skilled in the art understand that due to the thermal effects of food, each macronutrient ingested produces less net available calories (as compared to the labeled calories of the macronutrients before a meal). In addition, some macronutrients may require more energy to be expended during digestion, absorption, transport and storage (i.e., more thermal effect on food). Specifically, the thermal effects of fat, carbohydrate and protein are 0-3%, 5-10% and 20-30%, respectively.

Daily energy consumption S of the cycle in the step_ymObtained by the following formula:

wherein, the DCE_jFor daily activities J consuming energy, J being 1, 2 … … J (J being the maximum value of J), only two daily activities are considered at the present stage, namely: DCE₁Representing basal metabolic expenditure of energy, DCE₂Representing the energy expenditure of daily activities after exercise.

Wherein, the BMR is basal metabolic rate; g_rFor correction coefficients, R is 1, 2 … … R (R is the maximum value of R), and only five correction coefficients are considered at present, namely: g₁Correction factor for BMR race, g₂Is BMR disease correction coefficient.

BMR adopts Harris-Benedict formula,

BMR＝α+(β×W)+(γ×H)-(Ω×Y)

wherein, W is the weight, H is the height, and Y is the age. The users have different sexes, and the parameters alpha, beta, gamma and omega have different values. Determining the gender of the user based on the basic user information, wherein when the user is male, the gender is 66.47, the gender is 13.75, the gender is 5.0033, and the gender is 6.775; when the user is female, α -655.1, β -9.563, γ -1.850, and Ω -4.676.

Further, said g₁For BMR race correction factor, g when the user is Asian₁Value 0.95, but g when the user is not Asian₁The value is 1. Further, said g₂The BMR disease correction coefficient is a BMR disease correction coefficient, when a user normally suffers from a disease, the BMR disease correction coefficient generally takes a value of 1, and the rest BMR disease correction coefficient can be set according to comprehensive evaluation of the physical condition of the user.

DCE₂Comprises two values, 275 with users as regular sporters and 100 with users as common sporters, and DCE adaptive to the basic user information is determined based on the basic user information₂Substituting the numerical value.

The daily exercise consumption energy S in the period of the step_sObtained by the following formula:

wherein, the SCE_qFor the motion Q to consume energy, Q is 1, 2, 3 … … Q (Q is the maximum value of Q), and only three motion forms are considered at the present stage, namely: SCE₁Energy consumption for basic exercise, SCE₂Energy expenditure for aerobic exercise, SCE₃Energy is consumed for anaerobic exercise.

The BMR is the basal metabolic rate; said g is_rTo correct the coefficient, g₁Correction factor for BMR race, g₂Is BMR disease correction coefficient.

The METs are the body activity intensity of different aerobic exercises, the W is the body weight of the user, the t is exercise time, the AETs is the body activity intensity of different anaerobic exercises, the m is the number of anaerobic exercise groups, the n is the number of times of each anaerobic exercise group, and the omega is the unit intensity weight of the anaerobic exercises.

Those skilled in the art understand that different exercise patterns have different exercise efficiencies for different areas of the body, and are classified into aerobic exercise and resistance exercise. The METs are body activity intensities of different aerobic exercises, the values of the METs are different according to different aerobic exercise modes, in a preferred embodiment, when a user selects basketball exercises, the value of the METs is 6.5, when the user selects body-building exercises, the value of the METs is 5, when the user selects weight-losing exercises, the value of the METs is 6, when the user selects swimming exercises, the value of the METs is 8, certainly, when the user selects riding bicycles, running or other aerobic exercises, corresponding values can be obtained, and the values are not stated one by one. The AETs are different measures according to different physical activity intensity differences within the anti-resistance sports category; in a preferred embodiment, when the user exercise intensity is low, the value of AETs is 1.5; when the user exercise intensity is moderate, the value of AETs is 2.25; when the user exercise intensity is higher, the value of AETs is 3.5; of course, the resistance training energy consumption can be further quantified and corrected by referring to the detailed training contents input by the user.

The WRF is obtained by the following formula:

WRF＝WWRF*ΔW

WWRF is a unit weight gain factor corresponding to different BMIs, and Δ W is the weight required to be increased in one week. When the user is male and the Body Fat Rate (BFR) is more than 25%, WWRF is 769 Kcal/kg; when the user is male and the body fat rate is less than 25%, the WWRF is 485 Kcal/kg; when the user is female and the body fat rate is more than 35%, WWRF is 769 Kcal/kg; when the user is female and the body fat rate is less than 35%, WWRF is 485 Kcal/kg.

As understood by those skilled in the art, adipocytes are composed of 80% fat, 2% protein, 18% water, muscle cells are composed of 27% protein, 73% water, and increase 1kg body weight per increase for obese people, 30% -40% muscle cells and 0% -70% fat cells, and 1kg body weight per increase for leaner people, 60% -70% muscle cells and 30% -40% fat cells. The male body fat rate is more than 25 percent of the fat people, and the female body fat rate is more than 30 percent of the fat people. The muscle increasing amount is preferably 113g-675g per week. The following list describes the value-taking situation of a male obese person group as an embodiment, and other situations are not described again.

Table 11: value taking situation of male obese people

Table 12: calorie score calculation submodule variable table

For the submodule 2.3, the calorie score calculating submodule acquires the diet and exercise data of the user provided by the submodule 2.1 user data collecting submodule, acquires the exercise state data of the user provided by the submodule 2.2 exercise stimulation score calculating submodule, acquires the crowd classification parameter provided by the module-one crowd classification module, and calculates the calorie score to obtain the calorie score.

And (4) considering the uniformity and range limitation of score distribution, carrying out normal distribution conversion on the absolute score to ensure that the stationarity is 95% and the middle axis value is the maximum absolute score. Namely at

In the distribution of the water-soluble polymer,

and μ ═ S_b)_max. Transformed S_bIs the final calorie score.

Module 2.4 diet proportion score calculation submodule: in the step, the absolute score Sc of the diet proportion of each day in the period is obtained by the following formula:

wherein, the U_hIs the absolute score of nutrient h, v_hFor the weight of nutrient H, H is 1, 2, 3 … … H (H is the maximum value of H), only three nutrients are considered at the present stage, namely: u shape₁Represents the carbohydrate absolute score, U₂Represents the absolute protein score, U₃Represents the absolute score of fat; v is₁Representing the carbohydrate weight, v₂Denotes the protein weight, v₃Representing fat weightAnd (4) heavy.

The ratio P of total energy intake of daily nutrient h in daily diet in the period of said step_hObtained by the following formula:

wherein, the S_ynTotal energy for dietary intake; the FIE_hFor the nutrient H in the food to take energy, H is 1, 2, 3 … … H (H is the maximum value of H), only three nutrients are considered at the present stage, namely: FIE₁Representing the energy intake of carbohydrates, FIE₂For protein energy intake, FIE₃Energy intake for fat; p₁Denotes the carbohydrate ratio, P₂Denotes the protein ratio, P₃The fat ratio is indicated.

3. When the user is a healthy person, each nutrient is assigned the same weight by default, and only 3 nutrients are considered at the present stage, namely v₁＝ν₂＝ν₃1/3. However, to account for individual variability, certain nutrients may account for a higher proportion. For example, some trainers suffer from chronic diet-related diseases, including cardiovascular disease, type 2 diabetes. By increasing the weight of the nutritional elements, a user who scores high on the nutritional ingredient will obtain a higher score in the overall dietary proportion score, v₁、ν₁、ν₁The values relate to the type of chronic disease associated with diet.

Table 13: nutrient intake standard reference table

In particular, the proportion of energy intake of carbohydrates is generally within the range 55% to 60%, and that of proteinsThe energy intake ratio is required to be within 25-30%, and the fat energy intake ratio is required to be within 15-20%. Thus, in general, (P)₁)_minNamely 55 percent (P)₁)_maxI.e., (P) is 60%, (P)₂)_minI.e., (P) is 25%₂)_maxI.e., (P) is 30%, (P)₃)_minI.e., (P) is 15%, (P)₃)_maxThis was 20%.

Absolute score U of nutrient h in diet daily for the period of said step_hObtained by the following formula:

wherein, the P_hFor the daily nutrient H in the cycle, H is 1, 2, 3 … … H (H is the maximum value of H) in the ratio of the total energy of the dietary intake, and only three nutrients are considered at the present stage, namely: p₁Denotes the carbohydrate ratio, P₂Denotes the protein ratio, P₃Represents the fat ratio; (P)_h)_minIs the minimum value of the proportion of total energy of the nutrient h in the dietary intake; (P)_h)_maxIs the maximum value of the proportion of the total energy of the nutrient h in the dietary intake.

Those skilled in the art understand that the ratio of the total energy intake of the daily diet for the three macronutrients of a population with a definite muscle building requirement should be 55-60% carbohydrate, 25-30% protein and 15-20% fat. When the whole-day energy condition of the organism is evaluated, the surplus proportion of the dietary intake compared with the total consumption is not less than 15 percent and is required for the metabolism and synthesis of new tissues. The recommendation ensures that sufficient protein is ingested to promote muscle growth, sufficient carbohydrate is ingested to provide sufficient energy for intensive resistance training, and an appropriate amount of fat is provided to ensure that the blood contains sufficient testosterone. Adenosine Triphosphate (ATP) is also required for protein synthesis, so sufficient energy ensures protein synthesis. Finally, scientific empirical research shows that the macro nutrient reference proportion accords with the energy metabolism rule of human bodies and gives consideration to the purposes of muscle enhancement and health. In fact, with reference to the data such as the dietary guidelines of recent and developed countries, on the premise of the large-scale framework of macronutrients, the new views of digital and logical modern health are to be further absorbed: (1) the protein source selects high-quality animal protein of fish and the like as much as possible; (2) properly replacing saturated fat with unsaturated fatty acid to help cardiovascular health; (3) in the aspect of staple food, substances with different blood sugar loads can be matched and combined to optimize carbohydrate intake and improve blood sugar health.

Table 14: diet proportion score calculation submodule variable table

The submodule 2.4 diet proportion score calculating submodule acquires the user diet data provided by the submodule 2.1 user data collecting submodule, acquires the crowd classification parameters provided by the module-crowd classification module, and calculates the diet proportion score to obtain the diet proportion score.

And (4) considering the uniformity and range limitation of score distribution, carrying out normal distribution conversion on the absolute score to ensure that the stationarity is 95% and the middle axis value is the maximum absolute score. Namely at

In the distribution of the water-soluble polymer,

and μ ═ S_c)_max. Transformed S_cFinal diet ratio scores.

The submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires the exercise stimulation score provided by the submodule 2.2 exercise stimulation score calculating submodule, acquires the caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires the diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires the optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain the user score.

S_wFor increasing the comprehensive score of muscle weight, the formula is calculated according to the formula. Wherein the content of the first and second substances,

represents a comprehensive score coefficient vector of the muscle increasing weight,

λ₁represents the motor stimulation score coefficient, λ₂Denotes the caloric score coefficient, λ₃Represents a diet proportion score coefficient;

represents a comprehensive score vector of the muscle gain,

S_arepresents the motor stimulation score, S_bRepresents a calorie score, S_cRepresents a diet proportion score; for the

And continuously optimizing by a module three self-adaptive parameter optimization module.

Integrating user scores S for the calculated muscle gain increase_wUser scores in different ranges represent different muscle gain conditions: when 0 is less than or equal to S_wWhen the number is less than 60, the hormone level and the metabolism level of the body of the user are reduced at the stage, and the weight gain of the body is not obvious in order to maintain the state of homeostasis; when S is more than or equal to 60_wIf < 80, it indicates the hormone or hormone generation at that stageDecline level and various metabolic adaptations are recovered slowly, the user reaches a new weight level, the time is kept for 1-2 weeks in the period, the relationship with food is reestablished, caloric intake and caloric surplus are kept, and muscle weight gain is increased remarkably; when 80 is less than or equal to S_wWhen the number is less than 100, the situation that the muscle weight increasing situation is stable at the stage of the user is shown.

Table 15: table of conditions of increasing muscle weight

User score Sw	Increase muscle weight gain
		0～60	The hormone level and the metabolism level are reduced, and the muscle weight is increased insignificantly
60～80	The hormone, the metabolic level and various metabolic adaptations are slowly recovered, and the muscle increasing weight gain is obviously improved
		80～100	Stabilization of conditions of increasing muscle weight

Table 16: muscle-increasing and weight-increasing comprehensive score calculation module variable table

Name of variable	Meaning of variables	Variable unit	Value of variable
				Sw	Comprehensive score for increasing muscle weight	Is divided into	0100
λ1	Motor stimulation score coefficient	Is divided into	01
				λ2	Coefficient of caloric score	Is divided into	01
λ3	Diet ratio score coefficient	Is divided into	01
				Sa	Motor stimulation score	Is divided into	0100
Sb	Caloric score	Is divided into	0100
				Sc	Diet proportion score	Is divided into	0100

Module three-score hyperparameter self-adaptive optimization module

For the module three-score hyperparameter adaptive optimization module, a sub-module dataflow graph is shown in fig. 4. The self-adaptive parameter optimization module comprises two submodules, namely a user data collection submodule and a score hyperparameter self-adaptive optimization calculation submodule. The submodule 3.1 is a user data collecting submodule for obtaining muscle increasing weight variation data provided by a user, obtaining user scores provided by a module two muscle increasing weight scoring module and collecting user data; the sub-module 3.2 score hyper-parameter self-adaptive optimization calculation sub-module obtains the user data required by the score hyper-parameter optimization provided by the sub-module 3.1 user data collection sub-module, and carries out score hyper-parameter self-adaptive optimization calculation to obtain the optimized comprehensive score hyper-parameter.

Referring to fig. 4: score hyper-parameter adaptive optimization module dataflow graph

Submodule 3.1 the user data collection submodule obtains the augmented muscle weight variation data Δ M provided by the user, obtains the user score S provided by the module two augmented muscle weight scoring module_wAnd collecting user data.

Table 17: user data collection submodule variable table

Name of variable	Meaning of variables	Variables ofUnit of	Value of variable
				ΔM	Weekly amount of muscle gain variation	kg	/
Sw	Comprehensive score for increasing muscle weight	Is divided into	0-100

The sub-module 3.2 score hyper-parameter self-adaptive optimization calculation sub-module obtains the user data required by the score hyper-parameter optimization provided by the sub-module 3.1 user data collection sub-module, and carries out score hyper-parameter self-adaptive optimization calculation to obtain the optimized comprehensive score hyper-parameter.

And the score hyperparameter self-adaptive optimization submodule evaluates the relation between each input variable and the target variable by adopting a characteristic selection method to obtain the optimal weight. Here, the Pearson correlation coefficient is used to derive the diet proportion score S_aAnd a motor stimulation score S_bAnd a calorie score S_cAnd increased muscle weight gain variation S_ΔMThe relationship of the scores, namely:

wherein the score of the variation of the muscle weight increase is S_ΔMDerived by the sub-module 3.1 user data collection sub-module, the calculation formula is:

considering the uniformity and range limitation of the score distribution, for S_ΔMNormal distribution conversion is carried out in a mode of S_ΔMNormal distribution conversion is carried out to ensure that the degree of repose is 95 percent and the central axis value is (S)_ΔM)_max. Namely at

In the distribution of the water-soluble polymer,

and μ ═ S_ΔM)_max. Transformed S_ΔMFinal diet ratio scores.

The determination mode of (2) is that each correlation coefficient accounts for the proportion of the total correlation coefficient sum, and the calculation formula is as follows:

as the user data is increased, the difference value between the real value and the measured value can be compared and used as an optimization parameter

The standard of (2) is to optimize the parameters, and the error calculation formula is as follows:

wherein ,

as a hyperparametric vector

Lower S_ΔMAnd S_wThe error of (2). The training set and the test set are randomly divided, and the parameters are continuously updated by using a gradient descent algorithm. Super-superParameter vector

The update formula is:

wherein ,

is the gradient of the parameter, η is the learning rate. When in use

When minimizing, increase the comprehensive score hyper-parameter vector of muscle weight gain

Is a global optimum.

Table 18: score hyperparameter self-adaptive optimization calculation submodule variable table

In one embodiment, there is a user's initial score parameter ρ₁＝0.4，ρ₂＝0.3，ρ₃0.3, after being corrected by a third periodic data import module, the score parameter is optimized to rho₁＝0.35，ρ₂＝0.35，ρ₃＝0.3。

Claims (10)

1. A multi-module intelligent health management information system is characterized by comprising a module I crowd classification module, a module II muscle increasing and weight increasing scoring module and a module III adaptive parameter optimization module; the first module acquires data such as user age, sex, weight, body fat rate, exercise proficiency, diseases and the like provided by a user, classifies the health parameters of the crowd and obtains the health parameter range of the classified crowd; the second module obtains the crowd classification parameters provided by the first module and the user diet and exercise record parameters provided by the user to carry out health management target-muscle increasing and weight increasing target score calculation to obtain a user score; the third module obtains the score records of all classified users provided by the second module, obtains muscle-increasing weight variation data provided by the users, performs adaptive parameter optimization, obtains optimized score parameters and feeds the optimized score parameters back to the second module, and optimizes the scores of the second module by taking the optimized score parameters as the health management parameters and targets of the users;

the module-crowd classification module comprises two sub-modules, namely a sub-module 1.1 data collection sub-module and a sub-module 1.2 user data-crowd classification mapping sub-module;

submodule 1.1 user data collecting submodule for obtaining user personal data provided by user and collecting user data; the sub-module obtains the following user data provided by the user: the method comprises the following steps of collecting user data including race, gender, body fat rate, whether diseases exist, exercise habit/fatigue feeling, pump feeling, soreness feeling, height H, weight W, age Y, weight delta W required to be increased for one week, exercise time t, anaerobic exercise group number m, anaerobic exercise group number n, anaerobic exercise unit strength weight omega, 4 nutrient intake, exercise type and exercise strength data to obtain user data required by crowd classification mapping;

submodule 1.2 user data-crowd classification mapping submodule obtains user data required by crowd classification mapping provided by submodule 1.1, and carries out user data-crowd classification mapping calculation to obtain crowd classification parameters;

the submodule 1.2 randomly divides the crowd data into a test set and a training set; in the training set, feature selection is carried out on the crowd features, and a decision tree is recursively constructed by adopting an information gain standard; setting a loss function in consideration of the complexity of the decision tree, and pruning the decision tree; finally, classifying the crowd according to the constructed decision tree model to obtain a training model, and testing the classification model by using a test set; constructing a decision tree; until the information gain of all the characteristics is very small or no characteristics can be selected, finally obtaining a decision tree; the characteristics are selected to be 5 types of characteristics of race, disease, exercise habit, male and female and body fat rate, and the population is finally divided into 32 types;

a second module muscle-increasing weight-increasing scoring module which comprises five submodules, namely a user data collecting submodule 2.1, a motor stimulation score calculating submodule 2.2, a calorie score calculating submodule 2.3, a diet proportion score calculating submodule 2.4 and a muscle-increasing weight-increasing comprehensive score calculating module 2.5; the submodule 2.1 is that the user data collecting submodule obtains the record of diet and movement provided by the user, and collects the user data to obtain the data of diet and movement of the user; the sub-module 2.2 exercise stimulation score calculating sub-module obtains the crowd classification parameters provided by the first module crowd classification module, obtains the user exercise data provided by the sub-module 2.1 user data collecting sub-module, and calculates the exercise stimulation score to obtain the user exercise state calculation data and the exercise stimulation score; the submodule 2.3 comprises a calorie score calculating submodule for obtaining the diet and exercise data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the exercise state data of the user provided by the submodule 2.2 exercise stimulation score calculating submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the calorie score to obtain the calorie score; the submodule 2.4 is a diet proportion score calculation submodule for obtaining the diet data of the user provided by the submodule 2.1 user data collecting submodule, obtaining the crowd classification parameter provided by the first crowd classification module, and calculating the diet proportion score; the submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires a motion stimulation score provided by the submodule 2.2 motion stimulation score calculating submodule, acquires a caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires a diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires an optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain a user score;

the module three-score hyper-parameter self-adaptive optimization module comprises two sub-modules, namely a user data collection sub-module 3.1 and a score hyper-parameter self-adaptive optimization calculation sub-module 3.2; the submodule 3.1 is a user data collecting submodule for obtaining muscle increasing weight variation data provided by a user, obtaining user scores provided by a module two muscle increasing weight scoring module and collecting user data; the submodule 3.2 score hyper-parameter self-adaptive optimization calculation submodule acquires user data required by score hyper-parameter optimization provided by the submodule 3.1 user data collection submodule, and performs score hyper-parameter self-adaptive optimization calculation to obtain an optimized comprehensive score hyper-parameter; the score hyperparameter self-adaptive optimization submodule evaluates the relation between each input variable and the target variable by adopting a characteristic selection method to obtain the optimal weight;

the submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires the exercise stimulation score provided by the submodule 2.2 exercise stimulation score calculating submodule, acquires the caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires the diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires the optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain the user score.

2. The multi-module intelligent health management information system of claim 1, wherein sub-module 1.2 randomly partitions the crowd data into test and training sets; in the training set, the characteristics of the crowd are selected, and a method for recursively constructing a decision tree by adopting an information gain standard is adopted;

the information gain standard adopts l (x)_i)＝-log₂p(x_i) Wherein the symbol x_iIndicating a certain classification condition; p (x)_i) Representing the probability of selecting the classification; l (x)_i) Denotes x_iThe amount of information of (a);

to calculate the entropy, we need to calculate the expected value of the information contained in all possible values of all classes

wherein ,p(x_i) Representing the probability of selecting the classification, n representing a total of n classifications;

entropy of experience of

Wherein D represents a training data set, C_kRepresenting a certain classification condition of the training data set, K representing a common K classification condition, | C_kIs of class C_kThe number of samples of (a);

the conditional entropy H (Y | X) represents the uncertainty of the random variable Y given the random variable X,

wherein, when the random variable X is X_iIn the case of such a classification, the probability p of that classification_i＝P(X＝x_i) N represents a total of n classifications;

the information gain g (D, a) ═ H (D) -H (D | a) of the feature a to the training data set D, where H (D) is the empirical entropy of the set D and H (D | a) represents the difference between the empirical conditional entropies of D for a given condition of the feature a; and then, constructing a decision tree, starting from a root node, calculating information gains of all possible characteristics for the nodes, selecting the characteristics with the maximum information gains as the characteristics of the nodes, establishing child nodes according to different values of the characteristics, and recursively calling the method for the child nodes.

3. The multi-module intelligent health management information system of claim 1,

the submodule 2.5 muscle-increasing and weight-increasing comprehensive score calculating module acquires a motor stimulation score provided by the submodule 2.2 motor stimulation score calculating submodule, acquires a caloric score provided by the submodule 2.3 caloric score calculating submodule, acquires a diet proportion score provided by the submodule 2.4 diet proportion score calculating submodule, acquires an optimized comprehensive score hyperparameter provided by the module three-adaptive parameter optimizing module, and performs muscle-increasing and weight-increasing comprehensive score calculation to obtain a user score:

S_wcalculating the comprehensive score for increasing muscle weight by the formula; wherein,

represents a comprehensive score coefficient vector of the muscle increasing weight,

λ₁represents the motor stimulation score coefficient, λ₂Denotes the caloric score coefficient, λ₃Represents a diet proportion score coefficient;

represents a comprehensive score vector of the muscle gain,

S_arepresents the motor stimulation score, S_bRepresents a calorie score, S_cRepresents a diet proportion score; for the

And continuously optimizing by a module three self-adaptive parameter optimization module.

4. The multi-module intelligent health management information system of claim 1,

for the sub-module 2.2, the exercise stimulation score calculation sub-module obtains the crowd classification parameters provided by the first module crowd classification module, obtains the user exercise data provided by the sub-module 2.1 user data collection sub-module, and calculates the exercise stimulation score to obtain the user exercise state calculation data and the exercise stimulation score;

the control method comprises the step of obtaining the daily motor stimulation absolute score S in the period_aObtained by the following formula:

wherein X ═ a₁，a₂，a₃……a_F) For describing the vector before movement, defining each actual component of a process facing F indexes, a_fScoring for pre-exercise index f, (a)_f)_maxThe index f is the highest score before exercise; said Y ═ b₁，b₂，b₃……b_F) For describing the vector after the movement, defining each actual component of the f indexes oriented to the b process, b_fIs the score of the index f after exercise, (b)_f)_maxThe index f after exercise is the highest score; theta is the adjustment coefficient in motion, and theta max is the maximum value of the adjustment coefficient in motion. F is 1, 2 and 3 … … F (F is the maximum value of F), and only three reference indexes are considered at the present stage; the daily exercise stimulation of the animal is related to a plurality of indexes, and the current analysis considers that: the synergetic relation of the three reference indexes should be strengthened, the foundation of fatigue feeling is not highlighted any more, and the dot product operation is carried out and the quantity product is obtained aiming at two effective time points which are beneficial to evaluation, namely before and after training and row vectors which are respectively measured under the three indexes;

the three reference indexes refer to the fatigue feeling of the body; pump sensation rooted in muscle memory, "excessive pump sensation or muscle damage that would accompany delayed perception, resisting muscle storage; feeling of soreness and distension.

5. The system of claim 1, wherein in the module 2.3 calorie score calculation submodule, the absolute calorie score S of each day in the period in the step_bObtained by the following formula:

wherein, the S_MThe actual heat surplus is daily in the period; WRF is the target gain energy;S_yndietary energy intake for each day of the cycle; s_ymDaily energy consumption for each day of the cycle; s_sConsuming energy for daily movements within the cycle;

in the step, the daily dietary energy intake in the period is obtained by the following formula:

wherein, the FIE_iIngesting energy for a nutrient i in food; k is a radical of_iThe energy coefficient of the nutrient i taken in unit mass is taken under the condition of referring to the digestibility of the human body; ADI_iIs the nutrient i intake; i is 1, 2 and 3 … … I (I is the maximum value of I), and only four nutrients are considered at the present stage, namely FIE₁Representing the energy of carbohydrate intake in food, FIE₂Representing the energy of protein intake in food, FIE₃Representing energy of fat intake in fat diet, FIE₄Represents the energy intake of dietary fiber in food; ADI₁Representing the carbohydrate intake energy in food, ADI₂For protein intake, ADI₃For fat intake, ADI₄Is dietary fiber intake; k is a radical of₁In the case of referring to the human digestibility, the energy coefficient of ingested carbohydrate per unit mass is generally 4 kcal/g; k is a radical of₂In the case of referring to the human digestibility, the energy coefficient of protein ingested in unit mass is generally 4 kcal/g; k is a radical of₃In the case of referring to human digestibility, the energy coefficient of fat intake per unit mass is generally 9.6 kcal/g; k is a radical of₄In order to refer to the actual digestibility of human body, the energy coefficient of dietary fiber intake in unit mass is generally 2 kcal/g.

6. The system of claim 1, wherein the energy of daily consumption S for each day of the cycle in the step_ymObtained by the following formula:

wherein, the DCE_jFor daily activities J consuming energy, J being 1, 2 … … J (J being the maximum value of J), only two daily activities are considered at the present stage, namely: DCE₁Representing basal metabolic expenditure of energy, DCE₂Representing the daily activity expenditure of energy after exercise;

wherein, the BMR is basal metabolic rate; g_rFor correction coefficients, R is 1, 2 … … R (R is the maximum value of R), and only five correction coefficients are considered at present, namely: g₁Correction factor for BMR race, g₂Is BMR disease correction coefficient;

BMR adopts Harris-Benedict formula,

BMR＝α+(β×W)+(γ×H)-(Ω×Y)

wherein, W is the weight, H is the height, and Y is the age; the user gender is different, and the parameters alpha, beta, gamma and omega are different; determining the gender of the user based on the basic user information, wherein when the user is male, the gender is 66.47, the gender is 13.75, the gender is 5.0033, and the gender is 6.775; when the user is female, α ═ 655.1, β ═ 9.563, γ ═ 1.850, Ω ═ 4.676;

said g is₁For BMR race correction factor, g when the user is Asian₁Value 0.95, but g when the user is not Asian₁The value is 1; further, said g₂A BMR disease correction coefficient is adopted, when a user normally suffers from a disease, the BMR disease correction coefficient generally takes a value of 1, and the rest BMR disease correction coefficient can be set according to comprehensive evaluation of the physical condition of the user;

DCE₂comprises two values, 275 with users as regular sporters and 100 with users as common sporters, and DCE adaptive to the basic user information is determined based on the basic user information₂Substituting the numerical value.

7. According toThe system of claim 1, wherein the daily exercise consumption of energy S during the cycle of said step_sObtained by the following formula:

wherein, the SCE_qFor the motion Q to consume energy, Q is 1, 2, 3 … … Q (Q is the maximum value of Q), and only three motion forms are considered at the present stage, namely: SCE₁Energy consumption for basic exercise, SCE₂Energy expenditure for aerobic exercise, SCE₃Consuming energy for anaerobic exercise;

the BMR is the basal metabolic rate; said g is_rTo correct the coefficient, g₁Correction factor for BMR race, g₂Is BMR disease correction coefficient;

the METs is the body activity intensity of different aerobic exercises, the W is the body weight of the user, the t is the exercise time, the AETs is the body activity intensity of different anaerobic exercises, the m is the number of anaerobic exercise groups, the n is the number of times of each anaerobic exercise group, and the omega is the unit intensity weight of the anaerobic exercises;

the METs are the body activity intensity of different aerobic exercises, and the values of the METs are different according to different aerobic exercise modes.

8. The system of claim 1, wherein the WRF is obtained by the following formula:

WRF＝WWRF*△W

WWRF is a unit weight gain factor corresponding to different BMIs, and delta W is the weight to be increased in one week; when the user is male and the Body Fat Rate (BFR) is more than 25%, WWRF is 769 Kcal/kg; when the user is male and the body fat rate is less than 25%, the WWRF is 485 Kcal/kg; when the user is female and the body fat rate is more than 35%, WWRF is 769 Kcal/kg; when the user is female and the body fat rate is less than 35%, WWRF is 485 Kcal/kg.

9. The system of claim 1, wherein for the sub-module 2.3 caloric score calculation sub-module, the user diet and exercise data provided by the sub-module 2.1 user data collection sub-module is obtained, the user exercise state data provided by the sub-module 2.2 exercise stimulation score calculation sub-module is obtained, the crowd classification parameters provided by the module-one crowd classification module are obtained, and the caloric score is calculated; considering the uniformity and range limitation of score distribution, carrying out normal distribution conversion on the absolute score to ensure that the stationarity is 95 percent and the middle axis value is the maximum absolute score value; namely at

In the distribution of the water-soluble polymer,

and μ ═ S_b)_max(ii) a Transformed S_b(iv) a final calorie score;

module 2.4 diet proportion score calculation submodule, in the step absolute score S of diet proportion of every day in the period_cObtained by the following formula:

wherein, the U_hIs the absolute score of nutrient h, v_hTaking H as 1, 2 and 3 … … H (H is the maximum value of H) as the weight of the nutrient H, only three nutrients are considered at present, namely U₁Represents the carbohydrate absolute score, U₂Represents the absolute protein score, U₃Represents the absolute score of fat; v is₁Denotes the carbohydrate weight, v₂Denotes the protein weight, v₃Representing the fat weight;

the ratio P of total energy intake of daily nutrient h in daily diet in the period of said step_hObtained by the following formula:

wherein, the S_ynTotal energy for dietary intake; the FIE_hThe energy is taken as nutrient H in food, H is 1, 2, 3 … … H (H is the maximum value of H), and only three nutrients are considered at present, namely FIE₁Representing the energy intake of carbohydrates, FIE₂For protein energy intake, FIE₃Energy intake for fat; p₁Denotes the carbohydrate ratio, P₂Denotes the protein ratio, P₃Represents the fat ratio;

when the user is a healthy person, each nutrient is assigned the same weight by default, and only 3 nutrients are considered at the present stage, i.e. v₁＝v₂＝v₃1/3; by increasing the weight of the nutritional element, a user who scores high on the nutritional component will get a higher score in the overall dietary proportion score, i.e. v₁、v₁、v₁The value is related to the type of chronic diseases related to diet; trainers suffer from chronic diet-related diseases including cardiovascular disease, type 2 diabetes; absolute score U of nutrient h in diet daily for the period of said step_hObtained by the following formula:

wherein, the P_hTaking 1, 2 and 3 … … H (H is the maximum value of H) as the proportion of total energy of daily nutrient H in diet intake in a period, only three nutrients are considered at present, namely P₁Denotes the carbohydrate ratio, P₂Denotes the protein ratio, P₃Represents the fat ratio; (P)_h)_minIs the minimum value of the proportion of total energy of the nutrient h in the dietary intake; (P)_h)_maxIs the maximum value of the proportion of the total energy of the nutrient h in the dietary intake.

10. The system of claim 1, wherein the sub-module 3.1 the user data collection sub-module obtains augmented muscle weight change data Δ M provided by the user, obtains a user score S provided by the module two augmented muscle weight scoring module_wCollecting user data;

the submodule 3.2 score hyper-parameter self-adaptive optimization calculation submodule acquires user data required by score hyper-parameter optimization provided by the submodule 3.1 user data collection submodule, and performs score hyper-parameter self-adaptive optimization calculation to obtain an optimized comprehensive score hyper-parameter;

the score hyperparameter self-adaptive optimization submodule evaluates the relation between each input variable and the target variable by adopting a characteristic selection method to obtain the optimal weight; here, the Pearson correlation coefficient is used to derive the diet proportion score S_aAnd a motor stimulation score S_bAnd a calorie score S_cAnd increased muscle weight gain variation S_ΔMThe initial relationship of the scores, namely:

wherein the score of the variation of the muscle weight increase is S_ΔMDerived by the sub-module 3.1 user data collection sub-module, the calculation formula is:

considering the uniformity and range limitation of the score distribution, for S_ΔMNormal distribution conversion is carried out in a mode of S_ΔMNormal distribution conversion is carried out to ensure that the degree of repose is 95 percent and the central axis value is (S)_ΔM)_max(ii) a Namely at

In the distribution of the water-soluble polymer,

and μ ═ S_ΔM)_max(ii) a Transformed S_ΔMScoring the final diet proportion;

the initial determination mode of (2) is that each correlation coefficient accounts for the proportion of the total correlation coefficient sum, and the calculation formula is as follows:

as the user data is increased, the error between the real value and the measured value is compared and used as an optimization parameter

The standard of (2) is to optimize the parameters, and the error calculation formula is as follows:

wherein ,

as a hyperparametric vector

Lower S_ΔMAnd S_wAn error of (2); randomly dividing a training set and a testing set, and continuously updating parameters by using a gradient descent algorithm; hyper-parametric vector

Update the formula to

wherein ,

is the gradient of the parameter, η is the learning rate; when in use

When minimizing, increase the comprehensive score hyper-parameter vector of muscle weight gain

Is a global optimum.

Images