Intelligent diet intervention control method and system

Abstract

The invention relates to the technical field of health management, in particular to an intelligent diet intervention control method and system.The intelligent diet intervention control method comprises the following steps that heat, protein, sugar and sodium content data are extracted from a food database based on user health data and individual nutritional requirement parameters, difference values of multiple kinds of food under differential constraints are calculated respectively, and the difference values are calculated; deviation scores are formed through accumulation calculation, and a nutrition deviation score set is generated. According to the method, multi-level processing is carried out on food combination through step-by-step screening and dynamic optimization logic, key nutrition index deviation is extracted based on health data and individual demands, quantitative scoring is carried out, the degree of adaptation of food is determined, and diversity is ensured for deviation scoring, combination screening and variation processing steps. Meanwhile, a non-dominated relation is introduced to remove low-efficiency options, the quality of a recommendation scheme is improved, personalized sorting is performed in combination with user demand weights, food combinations are balanced among nutrition balance, health constraint and personalized demands, and the health management target is accurately met.

Description

Technical Field

[0001] The present invention relates to the technical field of health management, and in particular to an intelligent diet intervention control method and system. Background Art

[0002] The technical field of health management is a systematic management that realizes the monitoring, evaluation, intervention, and maintenance of the health status of individuals or groups through advanced scientific means and information technology. This field combines multiple disciplines such as biomedicine, data processing, and artificial intelligence. Through intelligent devices and systems, it can collect health-related data in real time, analyze the health status of users, and provide personalized intervention and management suggestions, aiming to help people prevent diseases, improve the quality of life, and achieve the goal of health management. With the development of Internet of Things, cloud computing, and big data technologies, health management technology has been widely applied in healthcare, intelligent wearable devices, nutrition monitoring, chronic disease management, and other aspects.

[0003] Among them, the intelligent diet intervention control method refers to the real-time monitoring and analysis of users' diet behaviors through data processing and intelligent algorithms, so as to provide scientific and personalized diet suggestions and intervention measures. Its main purpose is to help users improve bad eating habits, manage physical health indicators, prevent nutritional imbalance and diet-related diseases, and improve the level of healthy living. This method is often applied in the fields of health management systems, weight control platforms, and chronic disease adjuvant treatment.

[0004] There are problems of insufficient data matching and recommendation optimization in the existing technology for health management. Most of them only perform simple screening based on basic health data and food indicators, lacking quantitative standards and multi-dimensional nutritional deviation evaluation, and it is difficult to accurately reflect individual needs. At the same time, the combined scheme lacks a dynamic variation and non-dominated screening mechanism, resulting in the recommendation results being limited to surface parameter matching and ignoring personalized and diverse needs. For example, only controlling calories and ignoring other nutritional balances is likely to cause long-term malnutrition or dietary simplification problems. These deficiencies make it difficult for health intervention programs to meet the multi-dimensional and dynamic health management needs of users. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent diet intervention control method and system.

[0006] To achieve the above purpose, the present invention adopts the following technical scheme: An intelligent diet intervention control method, comprising the following steps: S1: Based on the user's health data and individual nutritional requirement parameters, extract data on calories, protein, sugar, and sodium content from the food database, calculate the differences of multiple foods under differential constraints respectively, form a deviation score through cumulative calculation, and generate a set of nutritional deviation scores; S2: Based on the nutritional deviation score set, select food combinations that meet the constraints, accumulate and calculate the parameter values of multiple combinations, compare them item by item with the health constraints, eliminate the non-conforming combinations, perform mutation processing on the remaining combinations and calculate again to generate a diverse food combination set; S3: Based on the diverse food combination set, compare the parameter values of multiple combinations, eliminate the dominated combinations according to the dominance relationship, retain the non-dominated combinations and screen them again to generate a non-dominated food combination set; S4: Based on the non-dominated food combination set, combined with the user's health requirement weight value, accumulate and calculate the parameter values of multiple combinations according to the weight ratio, reorder all combinations according to the calculation results to generate a personalized evaluation score set; S5: Based on the personalized evaluation score set, extract several groups of food combinations with the highest scores, identify and display the calorie, protein, sugar, and sodium content parameters of each group of combinations to generate a multi-objective healthy food recommendation plan.

[0007] The nutritional deviation score set includes calorie difference, protein difference, sugar difference, and sodium content difference. The diverse food combination set includes food combinations that meet the constraints, eliminated combinations, and mutated combinations. The non-dominated food combination set includes non-dominated food combinations and screened combinations. The personalized evaluation score set includes health requirement weight value parameters, weight ratio accumulation calculation results, and sorted combinations. The multi-objective healthy food recommendation plan includes calorie parameters, protein parameters, sugar parameters, and sodium content parameters.

[0008] As a further solution of the present invention, the steps for obtaining the nutritional deviation score set are specifically as follows: S111: Extract the target data of calories, proteins, sugars, and sodium content from the user's health data, match the attributes of each food according to the individual nutritional requirement parameters, and screen the food set that meets the initial constraint conditions to obtain the food attribute matching result; S112: Based on the food attribute matching result, calculate the differences of the calorie, protein, sugar, and sodium content of each food from the individual nutritional requirement parameters in absolute value mode, and accumulate the four types of differences of each food to generate a preliminary deviation score; S113: Based on the preliminary deviation score set, according to the difference between the accumulated difference score and the mean value of the individual nutritional requirement parameters, use the formula: ; Calculate the deviation score of each food to generate a nutritional deviation score set; Among them, represents the nutritional deviation score of the th food, which is used to judge the deviation degree of the food from the individual nutritional requirement, Represents the cumulative difference score of the th food, which is the cumulative result of the difference between the actual content and the target content of multiple nutrients, reflecting the overall magnitude of nutritional differences. Represents the th food's absolute deviation from the mean of individual nutritional requirement parameters, which is the degree of difference between the total nutritional value of the food and the mean of target requirements, reflecting the deviation of a single food from nutritional requirements. Represents the th food's mean square deviation among nutrient components, which is used to measure the unevenness of the distribution of differentiated nutrient components in the food. A high value indicates a more uneven distribution of nutrient components. Represents the mean of individual nutritional requirement parameters, which is the arithmetic mean of all target nutritional requirement values and is used to correct the influence of differentiated individual nutritional requirements on the calculation results.

[0009] As a further solution of the present invention, the steps for obtaining the diversified food combination set are specifically as follows: S211: Extract the cumulative values of calories, protein, sugar, and sodium content of multiple combinations from the nutrient deviation score set, compare them item by item with the health constraint parameters, and eliminate the food combinations whose cumulative values exceed the range of the health constraint parameters to obtain the preliminary food combinations that meet the health constraints; S212: Perform mutation processing on the preliminary food combinations that meet the health constraints, adjust the calories, protein, sugar, and sodium content in each food combination to random values within the deviation upper and lower limits, and recalculate the cumulative values of the four types of parameters for each combination. Eliminate the combinations whose cumulative values exceed the health constraint range after mutation to obtain the food combinations that meet the constraints after mutation; S213: Based on the food combinations that meet the constraints after mutation, use the formula: ; Calculate the diversification index of each combination, evaluate the diversification degree of the combination, and generate a diversified food combination set; Wherein, The diversified food combination set, represents the number of food types in the food combination, represents the th food's intake frequency, represents the average value of all food intake frequencies, represents the th food's intake frequency standard deviation.

[0010] As a further solution of the present invention, the steps for obtaining the non-inferior food combination set are specifically as follows: S311: Extract the nutritional parameter values of each combination from the diverse food combination set. According to the definition of the dominance relationship, compare the cumulative values of calories, protein, sugar, and sodium content of multiple combinations item by item to determine whether there is a dominance relationship, and eliminate all dominated food combinations to obtain the undominated preliminary food combinations. S312: Based on the undominated preliminary food combinations, calculate the deviation of the parameter value of each combination from the target health constraint in turn, optimize the determination process of the dominance relationship, and use the formula: ; Calculate the dominance degree score of each combination, eliminate the combinations with higher scores, and generate the updated undominated combinations. Among them, is the dominance degree score, is the number of parameters in the combination, is the actual combination value of the th parameter, is the th target value of the parameter, is the th weight coefficient of the parameter, is the number of adjustment parameters, is the actual adjustment value of the th adjustment parameter, is the th weight coefficient of the adjustment parameter; S313: Screen the updated undominated combinations again, eliminate the combinations whose cumulative values do not meet the health constraints, and retain the food combinations that meet the constraints and are undominated to generate a non-inferior food combination set.

[0011] As a further solution of the present invention, the specific steps for obtaining the personalized evaluation score set are as follows: S411: Extract the nutritional parameter values of each combination from the non-inferior food combination set, and perform weighted accumulation on each nutritional parameter according to the weight factor in the user's health needs to calculate the initial evaluation score of each food combination, and integrate it into the weighted food combination score. S412: Based on the weighted food combination score, perform optimization calculations to adjust the score, and use the formula: ; Calculate the optimized evaluation score. Among them, represents the optimized food combination score, represents the initial food combination score, represents the adjustment coefficient, represents the total weight of nutrients in the food, Represents the total calorie weight of food, Represents the contribution rate of food to health; S413: According to the optimized evaluation score, re - rank all food combinations, arrange them from high to low according to the score, and generate a personalized evaluation score set.

[0012] As a further solution of the present invention, the obtaining steps of the multi - objective healthy food recommendation solution are specifically as follows: S511: Extract several groups of food combinations with the highest scores from the personalized evaluation score set, call the personalized evaluation parameter values corresponding to calories, proteins, sugars, and sodium contents in multiple groups of combinations, bind the parameter values with the identification parameters of multiple groups of food combinations, and establish an initial food combination set; S512: Based on the initial food combination set, extract the weight values of all nutritional parameters corresponding in the combination, the associated target standard values and offset adjustment values, optimize the nutritional parameter identification values of multiple groups of food combinations, and use the formula: ; Calculate and update the multi - objective identification value of each group of food combinations to obtain the optimized multi - objective identification value; Among them, Is the optimized multi - objective identification value, Is the total value of the th nutritional parameter, Is the weight of the th nutritional parameter, Is the standard value of the th nutritional target, Is the offset adjustment value of the th nutritional parameter, Is the coefficient of the th adjustment parameter, Is the weight of the th adjustment parameter, Is the number of nutritional parameters in the combination, Is the number of adjustment parameters; S513: Add the optimized multi - objective identification value to the nutritional parameter identification corresponding to each group of food combinations, compare the optimized identifications of calories, proteins, sugars, and sodium contents with the personalized health requirement weight values and display them, and combine the identification results and parameter values to construct a multi - objective healthy food recommendation solution.

[0013] An intelligent diet intervention control system, the intelligent diet intervention control system is used to execute the above - mentioned intelligent diet intervention control method, and the system includes: The data extraction module extracts data on calories, protein, sugar, and sodium content from the food database based on the user's health data and individual nutritional requirement parameters, calculates the differences between multiple foods under the constraint conditions, accumulates all the differences, and generates a nutritional deviation score set. The nutritional combination optimization module screens food combinations that meet the constraints based on the nutritional deviation score set, calculates the total values of the calorie, protein, sugar, and sodium content parameters in each group of combinations, compares and eliminates the non-conforming combinations item by item, and performs mutation processing on the remaining combinations and re-accumulates them to generate a diverse food combination set. The non-dominated combination screening module compares the total parameter values of all combinations item by item based on the diverse food combination set, eliminates the dominated combinations according to the dominance relationship, compares the dominance relationships between multiple parameters of the non-dominated combinations, and obtains a non-dominated food combination set after re-screening. The personalized recommendation module combines the user's health requirement weight values based on the non-dominated food combination set, accumulates the calorie, protein, sugar, and sodium content parameters of multiple combinations according to the weight ratio, obtains the food combination with the highest sorted score, identifies and displays the parameters, and generates a multi-objective healthy food recommendation plan.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, through a step-by-step screening and dynamic optimization logic, multi-level processing is performed on food combinations. Based on health data and individual needs, key nutritional index deviations are extracted and quantified for scoring to clarify the fitness of foods. For the deviation scores, the combination screening and mutation processing steps ensure diversity, while introducing non-dominance relationships to eliminate inefficient options and improve the quality of the recommendation plan. Personalized ranking is performed by combining the user's need weights, enabling the food combinations to achieve a balance among nutritional balance, health constraints, and personalized needs, and precisely meeting the health management goals. Through scientific calculation and dynamic adjustment, the plan achieves obvious effects in terms of personalization, comprehensiveness, and result optimization, enhancing the practicality and effectiveness of dietary intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of the working process of the present invention; Figure 2 is a flowchart of the steps for obtaining the nutritional deviation score set of the present invention; Figure 3 is a flowchart of the steps for obtaining the diverse food combination set of the present invention; Figure 4 is a flowchart of the steps for obtaining the non-dominated food combination set of the present invention; Figure 5 is a flowchart of the steps for obtaining the personalized evaluation score set of the present invention; Figure 6 is a flowchart of the steps for obtaining the multi-objective healthy food recommendation plan of the present invention. Detailed implementation manners

[0016] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0018] Embodiment 1 Please refer to Figure 1 , the present invention provides a technical solution: an intelligent diet intervention control method, including the following steps: S1: Based on the user's health data and individual nutritional requirement parameters, extract the data of calories, protein, sugar, and sodium content from the food database, calculate the differences of multiple foods under different constraints respectively, form a deviation score through cumulative calculation, and generate a nutritional deviation score set; S2: Based on the nutritional deviation score set, select food combinations that meet the constraints, cumulatively calculate the parameter values of multiple combinations, compare them item by item with the health constraints, eliminate the non-conforming combinations, perform mutation processing on the remaining combinations and calculate again to generate a diversified food combination set; S3: Based on the diversified food combination set, compare the parameter values of multiple combinations, eliminate the dominated combinations according to the dominance relationship, retain the non-dominated combinations and screen them again to generate a non-inferior food combination set; S4: Based on the non-inferior food combination set, combine the user's health requirement weight values, cumulatively calculate the parameter values of multiple combinations according to the weight ratio, and reorder all combinations according to the calculation results to generate a personalized evaluation score set; S5: Based on the personalized evaluation score set, extract several groups of food combinations with the highest scores, identify and display the parameter values of calories, protein, sugar, and sodium content for each group of combinations, and generate a multi-objective healthy food recommendation plan.

[0019] The nutritional deviation score set includes calorie difference, protein difference, sugar difference, and sodium content difference. The diverse food combination set includes food combinations that meet the constraints, eliminated combinations, and combinations after variation processing. The non-dominated food combination set includes undominated food combinations and screened combinations. The personalized evaluation score set includes health need weight value parameters, cumulative calculation results of weight ratios, and sorted combinations. The multi-objective healthy food recommendation plan includes calorie parameters, protein parameters, sugar parameters, and sodium content parameters.

[0020] Please refer to Figure 2 , and the steps for obtaining the nutritional deviation score set are specifically as follows: S111: Extract the target data of calories, proteins, sugars, and sodium content from the user's health data, match the attributes of each food according to the individual nutritional requirement parameters, and screen the food set that meets the initial constraint conditions to obtain the food attribute matching result; For the unique needs of each user, the data extraction process includes using data mining techniques to obtain data on the calories, proteins, sugars, and sodium consumed and expended by the user daily from the health monitoring system. These data are usually collected through food intake logs and health tracking devices. By analyzing these data, the system can identify patterns of overnutrition or undernutrition and clean and validate the data to ensure the quality and accuracy of the input data. Then, statistical analysis and machine learning models are used to predict and analyze the individual's nutritional needs. This process involves the selection of algorithms, the training of models, and the optimization of parameters. The system will recommend food combinations that meet the individual's nutritional needs based on the analysis results to obtain the food attribute matching result.

[0021] S112: Based on the food attribute matching result, calculate the differences of the calories, proteins, sugars, and sodium content of each food from the individual nutritional requirement parameters in an absolute value mode, and accumulate the four types of differences of each food to generate a preliminary deviation score; By comparing the nutritional components of different foods with the individual's nutritional needs, the specific differences between the calorie, protein, sugar, and sodium content of the foods and the individual's needs are obtained. This process involves using the food nutritional data in the database and the nutritional need data in the individual's health record. Through data comparison, the specific differences in each nutritional component are calculated. For example, if an individual's daily calorie requirement is 2000 kcal and a certain food provides 500 kcal per 100 grams, the calorie difference between this food and the individual's need is -1500 kcal. In addition, similar calculations also apply to the protein, sugar, and sodium content. This calculation not only includes simple data comparison but also needs to consider how to meet the individual's comprehensive nutritional needs through the comprehensive evaluation of foods. This method helps to provide more personalized dietary advice for individuals, enabling them to better adjust their diet structure according to their own health conditions, and obtaining the preliminary deviation score for each food. This score reflects the fitness between the food and the individual's nutritional needs, providing a scientific basis for subsequent diet adjustment.

[0022] S113: Based on the preliminary deviation score set, according to the mean difference between the cumulative difference score and the individual nutritional need parameters, use the formula: ; Calculate the deviation score for each food to generate a nutritional deviation score set; Wherein, represents the nutritional deviation score of the th food, used to judge the deviation degree between the food and the individual's nutritional needs, represents the cumulative difference score of the th food, which is the cumulative result of the differences between the actual contents and the target contents of multiple nutritional components, reflecting the overall magnitude of the nutritional differences, represents the absolute deviation between the th food and the mean of the individual nutritional need parameters, which is the degree of difference between the total nutritional value of the food and the mean of the target needs, reflecting the deviation of a single food from the nutritional needs, represents the mean square deviation between the nutritional components in the th food, used to measure the unevenness of the distribution of differentiated nutritional components in the food. A high value indicates a more uneven distribution of nutritional components, represents the mean of the individual nutritional need parameters, which is the arithmetic mean of all target nutritional need values, used to correct the influence of differentiated individual nutritional needs on the calculation results.

[0023] Formula: ; The advantage of the formula is that by comprehensively considering the differences in food nutrient components and their absolute deviations from individual nutritional requirements, it increases the accuracy and individualization of the nutritional deviation score. This method helps to provide personalized nutritional advice.

[0024] Detailed explanation of the formula and the derivation process of the formula calculation: Set the specific parameter values as follows: (Cumulative difference score) = 20, (Absolute deviation between individual needs and food nutrients) = 5, (Mean square deviation of food nutrient components) = 3, (Mean value of individual need parameters) = 50, and the calculation process is as follows: ; The result shows that the deviation score of this food from the nutritional needs of a specific individual is 3.434, which means that compared with other foods, this food has a relatively large deviation in meeting the nutritional needs of this individual. This can be used as a basis for adjusting their diet structure and improving nutritional supply.

[0025] Please refer to Figure 3 , and the specific steps for obtaining the diversified food combination set are as follows: S211: Extract the cumulative values of calories, protein, sugar, and sodium content of multiple combinations from the nutritional deviation score set, compare them item by item with the health constraint parameters, and eliminate the food combinations whose cumulative values exceed the range of the health constraint parameters to obtain the preliminary food combinations that meet the health constraints; First, obtain the nutritional component data of different foods from the database, including the specific content of calories, protein, sugar, and sodium. Through program code, perform cumulative operations on the nutritional data of each food to obtain the total nutritional value of each food combination. This process requires ensuring the accuracy and integrity of the data. For missing values or outliers in the data, appropriate data cleaning and preprocessing should be carried out, such as filling with the average value or deleting abnormal data points, to ensure the accuracy of subsequent calculations. By comparing the cumulative nutritional value with the health constraint parameters, eliminate the food combinations whose cumulative values exceed the range of the health constraint parameters to obtain the preliminary food combinations that meet the health constraints.

[0026] S212: Perform mutation processing on the preliminary food combinations that meet the health constraints. Adjust the calories, protein, sugar, and sodium content in each food combination to random values within the range of the deviation upper and lower limits, and recalculate the cumulative values of the four types of parameters for each combination. Eliminate the combinations whose cumulative values exceed the health constraint range after mutation to obtain the food combinations that meet the constraints after mutation; After obtaining the initial food combinations that meet the health standards, the next step is to mutate these combinations. The purpose of the mutation process is to make each combination show as much difference as possible within the limits of the health standards by adjusting the specific nutritional values (calories, protein, sugar, and sodium content) in the food. The value of each nutrient element is adjusted to a random number within the upper and lower limits of the deviation. Then, recalculate the total nutrition of each food combination and conduct a new health constraint comparison. This process not only maintains the diversity of the food combinations but also increases the flexibility to adapt to different health needs. Eliminate the food combinations that still exceed the health constraint range after mutation, and the remaining food combinations that meet the constraints after mutation are the final results. These combinations provide the basis for further diversification processing, ensuring the nutritional balance of the food combinations and their applicability in actual diets.

[0027] S213: Based on the food combinations that meet the constraints after mutation, use the formula: ; Calculate the diversification index of each combination, evaluate the degree of diversification of the combination, and generate a set of diversified food combinations; Among them, The set of diversified food combinations, represents the number of food types in the food combination, represents the th intake frequency of the th food, represents the average value of all food intake frequencies, represents the standard deviation of the intake frequency of the

[0028] Formula: ; The advantage of the formula is that by considering the intake frequency of the food and its deviation from the average value, weighted by its consumption volatility (standard deviation), it can comprehensively evaluate food diversity and consumption balance, which is of great significance for formulating more reasonable diet guidance and nutrition intervention strategies.

[0029] Detailed explanation of the formula and the derivation process of the formula calculation: Let the number of food types , the intake frequency of each food , the average intake frequency , the standard deviation , calculate each item , calculate item by item to get , after summing and averaging, get ; The results show that the diversification index of the given food combination is 1.656, which reflects the balance and diversity of food intake in the combination. A higher diversification index indicates that the food combination shows greater diversity in the differences and fluctuations of intake frequencies.

[0030] Please refer to Figure 4 , and the specific steps for obtaining the non-inferior food combination set are as follows: S311: Extract the nutritional parameter values of each combination from the diversified food combination set. According to the definition of the dominance relationship, compare the cumulative values of calories, protein, sugar, and sodium content of multiple combinations item by item to determine whether there is a dominance relationship, and eliminate all dominated food combinations to obtain the undominated preliminary food combinations; Extract the nutritional parameter values of each combination from the diversified food combination set. Through the defined dominance relationship criteria, compare between combinations. This process involves item-by-item comparison of the cumulative values of calories, protein, sugar, and sodium content in each combination. By comparison, it is found that the dominated combinations whose other combinations are superior to or equal to themselves in all indicators will be eliminated from the set, thus screening out the dominant combinations that are not dominated by any other combination in at least one nutritional parameter. Such a screening process ensures that only the most nutritionally balanced food combinations are retained, forming a set composed of undominated preliminary food combinations.

[0031] S312: Based on the undominated preliminary food combinations, calculate the deviation of the parameter value of each combination from the target health constraint in turn, optimize the determination process of the dominance relationship, and use the formula: ; Calculate the dominance degree score of each combination, eliminate the combinations with higher scores, and generate the updated undominated combinations; Among them, is the dominance degree score, is the number of parameters in the combination, is the actual combination value of the th parameter, is the target value of the th parameter, is the weight coefficient of the th parameter, is the adjustment parameter number, is the actual adjustment value of the th adjustment parameter, is the weight coefficient of the th adjustment parameter; Formula: ; The advantage of the formula is that it provides a method to quantify the degree of combined dominance by comprehensively considering the deviation between the actual values and the target values of each parameter, as well as the importance of each parameter. This helps to identify and optimize food combinations to be closer to health goals.

[0032] Detailed Explanation of the Formula and the Derivation Process of Formula Calculation: Suppose a simple food combination dataset that contains two parameters: calories and protein. Set the target calories to 500 calories and the target protein to 50 grams. Considering that the weight of calories is 0.6 and the weight of protein is 0.4, the actual calories of this combination are 480 calories and the actual protein is 45 grams. Let the adjustment parameters R and S both be 1, and substitute them into the formula for calculation. First, calculate the deviation values of calories and protein: ; ; Then calculate the entire formula: ; The result shows that the dominance degree score of this food combination is 19.01. A higher score means that this combination performs poorly in achieving health goals and needs to be optimized or removed.

[0033] S313: Re-screen the updated non-dominated combinations, remove the combinations whose cumulative values do not meet the health constraints, and retain the food combinations that meet the constraints and are not dominated to generate a set of non-inferior food combinations.

[0034] In the re-screening of the updated non-dominated combinations, remove the combinations whose cumulative values do not meet the health constraints, conduct further nutritional parameter tests on the food combinations during the screening process, and re-evaluate whether the nutritional components of those combinations that survived in the previous screening step still meet the health standards, especially for the four key nutritional parameters of calories, protein, sugar, and sodium content. Accurately measure each parameter to ensure that they will not cause excess or deficiency under the new health standards. Integrate the food combinations that meet the health standards in all nutritional parameters into a set of non-inferior food combinations, and these combinations will provide the best nutritional choices for consumers.

[0035] Please refer to Figure 5 , and the specific steps for obtaining the personalized evaluation score set are as follows: S411: Extract the nutritional parameter values of each combination from the set of non-inferior food combinations, and according to the weight factors in the user's health needs, perform weighted accumulation on each nutritional parameter according to the weight to calculate the initial evaluation score of each food combination, and integrate it into the weighted food combination score; First, according to the user's health needs, key nutritional parameters such as protein, carbohydrates, fat, vitamins, and minerals need to be extracted from the known food combination dataset. These data can be obtained through a nutritional database. The data for each food is usually obtained through experiments and analyses by professional institutions to ensure the accuracy and reliability of the data. After extracting these nutritional parameters, the weight of each nutrient must be set according to the user's specific health conditions, such as diabetes, cardiovascular diseases, or fitness goals. The setting of the weights should be based on the latest nutritional research and the user's individual health records, and be personalized through a cooperative medical and health platform. After that, a mathematical weighting formula is used to perform weighted accumulation on each nutrient, calculate the comprehensive nutritional score of each food combination, and finally integrate these scores to evaluate the nutritional value of each food combination and guide the user to make reasonable dietary choices.

[0036] S412: Based on the weighted food combination scores, perform optimization calculations to adjust the scores, using the formula: ; Calculate the optimized evaluation score; Wherein, represents the optimized food combination score, represents the initial food combination score, represents the adjustment coefficient, represents the total weight of nutrients in the food, represents the total calorie weight of the food, represents the contribution rate of the food to health; Formula: ; The advantage of this formula is that it comprehensively considers the initial score of the food, the trade-off between nutrition and calories, and the squared impact of the food's contribution to health, thus more accurately reflecting the health value of the food combination. By setting the adjustment coefficients and , the formula can adapt to different nutritional needs and health goals, providing customized food combination suggestions for users.

[0037] Detailed explanation of the formula and the derivation process of the formula calculation: Set points, , , , . The calculation steps are as follows: 1. Calculate ; 2. Calculate the square root and addition operations: ; 3. Calculate the optimized score: ; The result shows that the optimized food combination score is 4.14, which means that by adjusting the original score and incorporating the trade-off between nutrition and calories, as well as the impact of food on health, the health value of food can be more accurately evaluated, thus helping users make better food choices.

[0038] S413: According to the optimized evaluation score, reorder all food combinations, arrange them from high to low according to the score, and generate a personalized evaluation score set.

[0039] First, it is necessary to extract the weighted evaluation scores of each food combination from the database. Using sorting algorithms such as quicksort or mergesort, sort the food combinations from high to low according to the scores. The key to this process lies in the efficient algorithm implementation and optimization to ensure speed and stability when processing a large amount of data. By reordering the food combinations, it can intuitively show which food combinations are more suitable for the user's health needs. The sorting result not only reflects the nutritional value of the food but also reflects the user's personalized needs. Generate a personalized evaluation score set, present these sorted food combinations in a list form, and users can select the food combination that best suits their health conditions according to the list.

[0040] Please refer to Figure 6 , the steps to obtain the multi-objective healthy food recommendation plan are specifically as follows: S511: Extract several groups of food combinations with the highest scores from the personalized evaluation score set, call the personalized evaluation parameter values corresponding to the calories, proteins, sugars, and sodium contents in multiple groups of combinations, bind the parameter values to the identification parameters of multiple groups of food combinations, and establish an initial food combination set; First, it is necessary to record the nutritional information of each food in detail, including the specific values of calories, proteins, sugars, and sodium contents. These data are matched with the nutritional requirement parameters in the health database to ensure that the selected food combinations meet the user's health needs. For this purpose, a matching parameter table needs to be set up to record the nutritional values of each food and the comparison results with the corresponding health standards. This process is executed through database queries and data processing algorithms. By traversing all food combinations in the personalized evaluation score set, summarize the calories, proteins, sugars, and sodium contents of each combination, calculate its total nutritional value, and use this as the basis for screening.

[0041] S512: Based on the initial food combination set, extract the weight values corresponding to all nutritional parameters in the combination, the associated target standard values, and the offset adjustment values, optimize the nutritional parameter identification values of multiple groups of food combinations, and use the formula: ; Calculate and update the multi-objective identification values of each group of food combinations to obtain the optimized multi-objective identification values; Among them, is the optimized multi-objective identification value, is the total value of the th nutritional parameter, is the weight of the th nutritional parameter, is the standard value of the th nutritional target, is the offset adjustment value of the th nutritional parameter, is the coefficient of the th adjustment parameter, is the weight of the th adjustment parameter, is the number of nutritional parameters in the combination, is the number of adjustment parameters; S513: Add the optimized multi-objective identification value to the nutritional parameter identification corresponding to each food combination, compare the optimized identifications of calories, protein, sugar, and sodium content with the personalized health requirement weight value and then display them. Combine the identification results and parameter values to construct a multi-objective healthy food recommendation plan.

[0042] This process first needs to determine the specific optimized values of the nutritional components of each food combination. This step requires detailed calculation of the new identification values of each food component such as calories, protein, sugar, and sodium content. The calculation formula for each component is carried out according to the foregoing formula, comprehensively considering the health impact weight of each component and the specific health requirements of the user. Through special software for data analysis, all data is integrated to update the nutritional identification of the food combination. On this basis, re-sort each combination, evaluate the health value of each combination according to the new nutritional identification value, display the health impact of these food combinations, and establish a detailed food recommendation plan. The plan will specifically point out the contribution degree of each food combination to meeting different health requirements, and how to optimize the user's diet structure by adjusting the food combination.

[0043] An intelligent diet intervention control system, the intelligent diet intervention control system is used to execute the above intelligent diet intervention control method, and the system includes: The data extraction module extracts the data of calories, protein, sugar, and sodium content in the food database based on the user's health data and individual nutritional requirement parameters, calculates the differences of multiple foods under the constraint conditions, accumulates all the differences, and generates a nutritional deviation score set; The nutritional combination optimization module filters out the food combinations that meet the constraints based on the nutritional deviation score set, calculates the total values of the parameters of calories, protein, sugar, and sodium content in each group of combinations, compares item by item and eliminates the unqualified combinations, performs mutation processing on the remaining combinations and re-accumulates to generate a diversified food combination set; The non-dominated combination screening module compares the total parameter values of all combinations item by item based on the diverse food combination set, eliminates the dominated combinations according to the dominance relationship, and compares the non-dominated combinations for the dominance relationship among multiple parameters. After re-screening, a non-dominated food combination set is obtained; The personalized recommendation module is based on the non-dominated food combination set, combines the user's health need weight values, accumulates the calorie, protein, sugar, and sodium content parameters of multiple combinations according to the weight ratio, obtains the food combination with the highest score after sorting, marks and displays the parameters, and generates a multi-objective healthy food recommendation plan.

[0044] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent diet intervention control method, characterized in that: The following steps are involved: Based on the user's health data and individual nutritional requirement parameters, the calorie, protein, sugar, and sodium content data are extracted from the food database, and the difference values ​​of various foods under differentiation constraints are calculated respectively. The deviation scores are formed by cumulative calculation to generate a nutritional deviation score set; Based on the nutritional deviation score set, select food combinations that meet the constraints, accumulate and calculate the parameter values ​​of multiple combinations, compare them with the health constraints item by item, eliminate combinations that do not meet the requirements, perform mutation processing on the remaining combinations and calculate them again to generate a diversified food combination set; Based on the diversified food combination set, the parameter values ​​of multiple combinations are compared, the dominated combinations are eliminated according to the dominance relationship, the non-dominated combinations are retained and screened again, and a non-inferior food combination set is generated; Based on the non-inferior food combination set and the user's health demand weight value, the parameter values ​​of multiple combinations are cumulatively calculated according to the weight ratio, and all combinations are reordered according to the calculation results to generate a personalized evaluation score set; Based on the personalized assessment score set, several food combinations with the highest scores are extracted, and the calorie, protein, sugar, and sodium content parameters of each combination are labeled and displayed to generate a multi-objective healthy food recommendation plan.

2. The intelligent diet intervention control method according to claim 1, characterized in that: The nutritional deviation score set includes calorie difference, protein difference, sugar difference, and sodium content difference; the diversified food combination set includes food combinations that meet the constraints, combinations after elimination, and combinations after variation processing; the non-inferior food combination set includes undominated food combinations and screened combinations; the personalized assessment score set includes health need weight value parameters, weight ratio cumulative calculation results, and sorted combinations; the multi-objective healthy food recommendation plan includes calorie parameters, protein parameters, sugar parameters, and sodium content parameters.

3. The intelligent diet intervention control method according to claim 2, characterized in that: The steps for obtaining the nutrition deviation score set are specifically as follows: The target data of calories, protein, sugar, and sodium content are extracted from the user's health data, and the attributes of each food are matched according to the individual nutritional requirement parameters, and the food set that meets the initial constraints is screened to obtain the food attribute matching results; Based on the food attribute matching results, the difference of the calorie, protein, sugar and sodium content of each food with respect to the individual nutritional requirement parameters is calculated using the absolute value mode, and the four types of differences of each food are accumulated to generate a preliminary deviation score set; Based on the preliminary deviation score set, according to the difference between the cumulative difference score and the mean value of the individual nutritional requirement parameter, the formula is used: ； Calculate the deviation score of each food and generate a nutritional deviation score set; in, Representative The nutritional deviation score of each food is used to determine the degree of deviation between the food and the individual's nutritional needs. Representative The cumulative difference score of a food is the cumulative result of the difference between the actual content of multiple nutrients and the target content, reflecting the overall size of the nutritional difference. Representative The absolute deviation between a food and the mean of individual nutritional requirement parameters is the difference between the total nutritional value of the food and the mean of the target requirement, reflecting the deviation of a single food from the nutritional requirement. Representative The mean square error between nutrients in a food is used to measure the imbalance in the distribution of differentiated nutrients in a food. A high value indicates a more uneven distribution of nutrients. The mean of the individual nutritional requirement parameter is the arithmetic mean of all target nutritional requirement values ​​and is used to correct the impact of differentiated individual nutritional requirements on the calculation results.

4. The intelligent diet intervention control method according to claim 3, characterized in that: The steps for obtaining the diversified food combination set are specifically as follows: Extracting the cumulative values ​​of calories, protein, sugar and sodium content of multiple combinations from the nutritional deviation score set, comparing them with the health constraint parameters item by item, eliminating food combinations whose cumulative values ​​exceed the health constraint parameter range, and obtaining preliminary food combinations that meet the health constraint; Performing mutation processing on the preliminary food combinations that meet the health constraints, adjusting the calorie, protein, sugar and sodium content in each food combination to random values ​​within the upper and lower limits of the deviation, and recalculating the cumulative values ​​of the four types of parameters for each combination, eliminating the combinations whose cumulative values ​​exceed the health constraint range after mutation, and obtaining the food combinations that meet the constraints after mutation; Based on the food combination that meets the constraints after the mutation, the formula is used: ； Calculate the diversity index of each combination, evaluate the diversity of the combination, and generate a diversified food combination set; in, Diverse food combination set, Represents the number of food types in the food combination, Representative The frequency of food intake, represents the average frequency of all food intake, Representative The standard deviation of the frequency of food intake.

5. The intelligent diet intervention control method according to claim 4, characterized in that: The steps for obtaining the non-inferior food combination set are specifically as follows: Extracting the nutritional parameter value of each combination from the diversified food combination set, comparing the cumulative values ​​of calories, protein, sugar and sodium content of multiple combinations item by item according to the definition of dominance relationship, determining whether there is a dominance relationship, eliminating all dominated food combinations, and obtaining preliminary non-dominated food combinations; Based on the undominated preliminary food combinations, the deviation of the parameter value of each combination from the target health constraint is calculated in turn, and the determination process of the dominance relationship is optimized, using the formula: ； Calculate the dominance score of each combination, remove the combinations with higher scores, and generate updated non-dominated combinations; in, To rate the degree of dominance, is the number of parameters in the combination, For the The actual combination of parameters, For the The target value of the parameter, For the The weight coefficients of the parameters, To adjust the number of parameters, For the The actual adjustment value of the adjustment parameter, For the The weight coefficient of the adjustment parameter; The updated undominated combinations are screened again to eliminate combinations whose cumulative values ​​do not meet the health constraints, and the food combinations that meet the constraints and are undominated are retained to generate a non-inferior food combination set.

6. The intelligent diet intervention control method according to claim 5, characterized in that: The steps for obtaining the personalized evaluation score set are specifically as follows: Extracting the nutritional parameter value of each combination from the non-inferior food combination set, weighting and accumulating each nutritional parameter according to the weight factor in the user's health needs, calculating the initial evaluation score of each food combination, and integrating it into a weighted food combination score; Based on the weighted food combination score, an optimization calculation is performed to adjust the score using the formula: ； Calculate the optimized evaluation score; in, Represents the optimized food combination score, represents the initial food combination score, represents the adjustment factor, Represents the total weight of nutrients in food. Represents the total caloric weight of the food. Represents the contribution of food to health; According to the optimized evaluation scores, all food combinations are reordered and arranged from high to low scores to generate a personalized evaluation score set.

7. The intelligent diet intervention control method according to claim 6, characterized in that: The steps for obtaining the multi-objective healthy food recommendation scheme are specifically as follows: Extracting several food combinations with the highest scores from the personalized evaluation score set, calling personalized evaluation parameter values ​​corresponding to the calories, protein, sugar and sodium content in the multiple combinations, binding the parameter values ​​with the identification parameters of the multiple food combinations, and establishing an initial food combination set; Based on the initial food combination set, the weight values ​​corresponding to all nutritional parameters in the combination and the associated target standard values ​​and offset adjustment values ​​are extracted to optimize the nutritional parameter identification values ​​of multiple groups of food combinations, using the formula: ； Calculate and update the multi-objective identification value of each food combination to obtain an optimized multi-objective identification value; in, is the optimized multi-target identification value, For the The total value of the nutritional parameters, For the The weights of the nutritional parameters, For the Standard values ​​for nutritional targets, For the Offset adjustment values ​​for various nutritional parameters, For the The coefficients of the adjustment parameters, For the The weights of the adjustment parameters, is the number of nutritional parameters in the combination, is the number of adjustment parameters; The optimized multi-target identification value is added to the nutritional parameter identification corresponding to each food combination, the optimized identification of calories, protein, sugar and sodium content is compared with the personalized health demand weight value and displayed, and a multi-target healthy food recommendation plan is constructed by combining the identification results and parameter values.

8. An intelligent diet intervention control system, characterized in that: According to the intelligent diet intervention control method according to any one of claims 1 to 7, the system comprises: The data extraction module extracts the calorie, protein, sugar, and sodium content data from the food database based on the user's health data and individual nutritional requirement parameters, calculates the difference between multiple foods under the constraints, and accumulates all the differences to generate a nutritional deviation score set; The nutrition combination optimization module screens food combinations that meet the constraints based on the nutrition deviation score set, calculates the total values ​​of the calories, protein, sugar, and sodium content parameters in each combination, compares and removes the combinations that do not meet the requirements item by item, performs mutation processing on the remaining combinations, and re-accumulates them to generate a diversified food combination set; The non-inferior combination screening module compares the total parameter values ​​of all combinations item by item based on the diversified food combination set, removes the dominated combinations according to the dominance relationship, compares the dominance relationship between multiple parameters of the non-dominated combinations, and obtains the non-inferior food combination set after re-screening; The personalized recommendation module is based on the non-inferior food combination set and combined with the user's health demand weight value, and accumulates the calorie, protein, sugar, and sodium content parameters of multiple combinations according to the weight ratio, obtains the sorted food combination with the highest score, identifies and displays the parameters, and generates a multi-objective healthy food recommendation plan.

Images