AI-based healthy diet nutrition management method and system

Abstract

The invention relates to the technical field of data processing, and provides an AI-based healthy diet nutrition management method and system, and the method comprises the steps: collecting basic health data of a user, carrying out the analysis, obtaining the basal metabolic rate of the user and the daily required calorie, carrying out the matching, obtaining a recommended diet scheme, carrying out the health evaluation of the basal metabolic rate, and carrying out the management of the basic metabolic rate. The method comprises the steps of obtaining a nutrition matching suggestion, matching the nutrition matching suggestion with daily required heat, obtaining a daily diet suggestion, screening recommended diet schemes, obtaining an initial diet suggestion, and adjusting the initial diet suggestion in real time based on the blood glucose level, the blood pressure level and the heart rate level of a user to obtain a target diet suggestion. By collecting the basic health data of the user, generating the diet scheme and monitoring the physical condition of the user in real time, daily diet suggestions are adjusted, and the problems that a traditional method depends on consciousness and accurate recording of the user, and data accuracy and real-time performance are insufficient are solved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to an AI-based healthy diet nutrition management method and system. Background Art

[0002] Industry Overview: With the development of social economy and the improvement of people's living standards, healthy diet has received more and more attention from people. Diet is not only to meet basic survival needs, but also to maintain and promote health. The development of modern technology, especially the application of artificial intelligence, makes personalized healthy diet nutrition management possible.

[0003] Among the related technical means, healthy diet management is carried out through nutritionist advice and user self-recording. These methods usually include recording daily food intake and calories, conducting basic nutritional analysis, and giving advice based on personal health status and goals. This method helps users understand their eating habits to a certain extent and make corresponding adjustments, thereby achieving the goal of health management.

[0004] Regarding the above technical solutions, although healthy diet management can be achieved through nutritionist's advice and user's self-recording, in terms of data accuracy and real-time, the traditional method relies on the user's self-consciousness and accurate recording, and has the problem of poor flexibility. Therefore, using AI technology to manage healthy diet more accurately has become an urgent need. Summary of the invention

[0005] In order to improve the problem that traditional methods rely on the user's self-consciousness and accurate records, and are insufficient in data accuracy and real-time performance, this application provides an AI-based healthy diet nutrition management method and system.

[0006] The present invention provides an AI-based healthy diet nutrition management method, comprising: collecting basic health data of a user, analyzing the basic health data using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirement; matching the basal metabolic rate and the daily calorie requirement with diet data in a preset nutrition database to obtain several recommended diet plans, performing a health assessment on the basal metabolic rate to obtain nutritional ratio suggestions, matching the nutritional ratio suggestions with the daily calorie requirement to obtain daily dietary suggestions; using the daily dietary suggestions to screen all the recommended diet plans to obtain initial dietary suggestions, and adjusting the initial dietary suggestions in real time based on the user's blood sugar level, blood pressure level and heart rate level in the current time period to obtain target dietary suggestions.

[0007] As a preferred embodiment, the step of collecting the basic health data of the user, analyzing the basic health data using a preset neural network model, and obtaining the user's basal metabolic rate and daily calorie requirement includes: using a sensor device to obtain the user's weight, height, age and gender data, and collecting the user's eating habits, sleep quality and exercise frequency to obtain basic health data; using a multi-layer convolutional neural network to extract features from the basic health data to obtain the user's health feature vector, and inputting the health feature vector into a preset neural network model for multi-layer perceptron operation to obtain the user's basal metabolic rate and daily calorie requirement.

[0008] As a preferred embodiment, the step of matching the basal metabolic rate and the daily calorie requirement with the dietary data in a preset nutrition database to obtain a number of recommended diet plans includes: inputting the basal metabolic rate and the daily calorie requirement data into a preset matching model, in which a multi-objective optimization algorithm is used to intelligently match the basal metabolic rate and the daily calorie requirement data with the nutritional components and calorie data of ingredients in a preset nutrition database to obtain a matching result; and screening out the ingredient combinations in the nutrition database that match the matching results through a multi-level screening algorithm to obtain a number of recommended diet plans.

[0009] As a preferred embodiment, the steps of conducting a health assessment on the basal metabolic rate, obtaining a nutritional ratio recommendation, and matching the nutritional ratio recommendation with the daily calorie requirement to obtain daily dietary recommendations include: comparing the basal metabolic rate with standard data of age, gender, and weight and conducting a health risk assessment to obtain a metabolic health status, an energy demand adjustment index, and an energy consumption level, and assessing the user's malnutrition risk based on the metabolic health status to obtain a nutritional risk score; applying the energy demand adjustment index to assess the user's requirement ratio for various nutrients to obtain a protein requirement ratio, a fat requirement ratio, and a carbohydrate requirement ratio; comparing the protein requirement ratio with the energy consumption level to obtain the user's high-energy food requirement level; comparing the fat requirement ratio with the nutritional risk score to obtain the user's healthy fat requirement recommendation; comparing the carbohydrate requirement ratio with the high-energy food requirement level to obtain a nutritional ratio recommendation; matching the healthy fat requirement recommendation and the nutritional ratio recommendation with the daily calorie requirement to obtain daily dietary recommendations.

[0010] As a preferred embodiment, the step of matching the healthy fat demand recommendation, the nutritional ratio recommendation and the daily calorie requirement to obtain daily dietary recommendations includes: concretizing and personalizing the healthy fat demand recommendation and the nutritional ratio recommendation through a preset decision tree model to obtain personalized nutritional recommendations and standardized nutritional recommendations, and optimizing the matching of the personalized nutritional recommendations, the standardized nutritional recommendations and the daily calorie requirement to obtain daily dietary recommendations; wherein, the personalized nutritional recommendations are nutritional plans for individual physiological needs; and the standardized nutritional recommendations are plans that meet the nutritional needs of the general population.

[0011] As a preferred embodiment, the steps of using the daily dietary recommendations to screen all the recommended dietary plans to obtain initial dietary recommendations, and adjusting the initial dietary recommendations in real time based on the user's blood sugar level, blood pressure level, and heart rate level in the current time period to obtain target dietary recommendations include: analyzing the user's nutritional deficiencies and excesses through the daily dietary recommendations, screening all the recommended dietary plans to obtain initial dietary recommendations, comparing the initial dietary recommendations with the user's actual eating habits to obtain a preliminary draft of dietary adjustments; obtaining the user's blood sugar level, blood pressure level, and heart rate level in the current time period, and adjusting the blood sugar level, blood pressure level, and heart rate level in real time through a real-time health monitoring system. The heart rate level is analyzed in real time to obtain a blood sugar stability index, a blood pressure regulation requirement and a heart rate variability index; the blood sugar stability index is compared and adjusted with the carbohydrate intake recommendation in the first draft of the diet adjustment to obtain a carbohydrate intake optimization plan; the blood pressure regulation requirement is compared and adjusted with the sodium salt intake recommendation in the first draft of the diet adjustment to obtain a salt intake optimization plan; the heart rate variability index is compared and adjusted with the fat and protein intake in the first draft of the diet adjustment to obtain an optimized fat intake ratio and an optimized protein intake ratio; the carbohydrate intake optimization plan, the salt intake optimization plan, the optimized fat intake ratio and the optimized protein intake ratio are combined to obtain a target diet recommendation.

[0012] As a preferred embodiment, the steps of analyzing the user's nutritional deficiencies and excesses through the daily dietary recommendations, screening all the recommended dietary plans, obtaining initial dietary recommendations, and comparing the initial dietary recommendations with the user's actual dietary habits to obtain a preliminary draft of dietary adjustment include: comprehensively evaluating the daily dietary recommendations through the Dietary Reference Intakes calculator to obtain a dietary balance evaluation and a nutritional deficiency evaluation, using the USDA food database to further adjust the dietary balance evaluation to obtain adjusted dietary recommendations and nutritional supplement recommendations, using a linear programming algorithm to match the fat intake in the adjusted dietary recommendations with the nutritional deficiency evaluation to obtain a fat intake recommendation; integrating the fat intake recommendation with the nutritional supplement recommendation through a simulated annealing algorithm to obtain a comprehensive nutritional recommendation and an optimized dietary adjustment plan, and using the Academy of Nutrition andDietetics' nutritional therapy standards are used to make actual dietary adjustments to the comprehensive nutritional recommendations to obtain an adjusted daily meal plan; the recommended diet plan is screened using the adjusted daily meal plan and the optimized dietary adjustment plan to obtain initial dietary recommendations; the user's actual dietary habits are obtained through a food intake frequency questionnaire, and a comprehensive analysis of the user's actual dietary habits is performed through multivariate regression analysis to obtain an actual dietary preference assessment; the initial dietary recommendations are compared with the actual dietary preference assessment to obtain a preliminary draft of the dietary adjustment.

[0013] The present application also provides an AI-based healthy diet nutrition management system, including: a collection unit, used to collect basic health data of the user, and use a preset neural network model to analyze the basic health data to obtain the user's basal metabolic rate and daily calorie requirement; a matching unit, used to match the basal metabolic rate and the daily calorie requirement with the diet data in a preset nutrition database to obtain several recommended diet plans, perform a health assessment on the basal metabolic rate to obtain nutritional ratio suggestions, and match the nutritional ratio suggestions with the daily calorie requirement to obtain daily dietary suggestions; a screening unit, used to use the daily dietary suggestions to screen all the recommended diet plans to obtain initial dietary suggestions, and based on the user's blood sugar level, blood pressure level and heart rate level in the current time period, adjust the initial dietary suggestions in real time to obtain target dietary suggestions.

[0014] Compared with the prior art, the present application has the following beneficial effects: good real-time performance and high data accuracy. By collecting the basic health data of the user and analyzing these data using a preset neural network model, the user's basal metabolic rate and daily calorie requirement can be accurately obtained, and a recommended diet plan that matches the data can be generated; the nutritional ratio recommendations obtained after the health assessment are combined with the daily calorie requirement to generate detailed daily dietary recommendations, and finally, by real-time monitoring of the user's blood sugar level, blood pressure level, and heart rate level, the daily dietary recommendations are adjusted to suit the user's current health status, ensuring that the user's diet always meets their actual health needs, greatly improving the accuracy and effectiveness of health management, and improving the traditional method that relies on the user's self-consciousness and accurate records, and has deficiencies in data accuracy and real-time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0017] Figure 1 is a flowchart of an AI-based healthy diet nutrition management method provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of the structure of the AI-based healthy diet nutrition management system provided in an embodiment of the present invention.

[0018] Description of reference numerals: 10. AI-based healthy diet nutrition management system; 11. Collection unit; 12. Matching unit; 13. Screening unit. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0021] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0024] Embodiment 1: like Figure 1 As shown, an AI-based healthy diet nutrition management method provided in an embodiment of the present application includes steps S100 to S300.

[0025] Step S100: Collect the basic health data of the user, and analyze the basic health data using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirement.

[0026] The user's basic health data including weight, height, age, gender, activity level and other parameters are collected; specifically, the basic health data is analyzed using a preset neural network model to accurately predict the user's basal metabolic rate and calculate the user's daily calorie requirement.

[0027] For example, after the user enters his or her basic health data, the user's basal metabolic rate and daily calorie requirements can be calculated and displayed in real time, providing basic data for subsequent dietary recommendations.

[0028] Step S200, matching the basal metabolic rate and the daily calorie requirement with the dietary data in a preset nutrition database to obtain several recommended dietary plans, performing a health assessment on the basal metabolic rate to obtain nutritional ratio suggestions, and matching the nutritional ratio suggestions with the daily calorie requirement to obtain daily dietary suggestions.

[0029] In this step, the basal metabolic rate and daily calorie requirements are matched with the preset nutrition database to screen out a recommended diet plan that meets the user's needs; specifically, the nutritional ratio recommendations obtained after the health assessment are combined with the user's daily calorie requirements to generate daily dietary recommendations that meet the user's health needs.

[0030] For example, based on the user's basal metabolic rate and daily calorie requirements, several recommended diet plans are automatically matched from the nutrition database, including specific food types and intake amounts.

[0031] Step S300: Filter all recommended diet plans using daily dietary recommendations to obtain initial diet recommendations. Adjust the initial diet recommendations in real time based on the user's blood sugar level, blood pressure level, and heart rate level during the current period to obtain target diet recommendations.

[0032] In this step, by real-time monitoring of the user's blood sugar level, blood pressure level, and heart rate level during the current period, the initial dietary recommendations can be dynamically adjusted to make them more in line with the user's actual health needs; specifically, based on the real-time monitoring data, the initial dietary recommendations are fine-tuned to obtain the target dietary recommendations that best suit the user's current condition.

[0033] For example, if the user's current blood sugar level is high, it is recommended to reduce carbohydrate intake and increase protein and fiber intake to help control blood sugar.

[0034] In this embodiment, the user's basic health data is collected and analyzed using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirements. Next, the basal metabolic rate and daily calorie requirements are matched with the dietary data in the preset nutrition database to generate several recommended diet plans, and a health assessment of the basal metabolic rate is performed to obtain nutritional ratio recommendations. Then, the nutritional ratio recommendations are combined with the daily calorie requirements to obtain daily dietary recommendations. Finally, based on the user's blood sugar level, blood pressure level, and heart rate level in the current period, the daily dietary recommendations are adjusted in real time to generate the final target dietary recommendations. Through the above-mentioned AI-based healthy diet nutrition management method, personalized dietary recommendations and management services can be provided to users in a more comprehensive, accurate and real-time manner, improving the traditional method that relies on the user's self-consciousness and accurate records, and has deficiencies in data accuracy and real-time performance.

[0035] Embodiment 2: In step S100, a sensor device is used to obtain the user's weight, height, age and gender data, and the user's eating habits, sleep quality and exercise frequency are collected to obtain basic health data. A multi-layer convolutional neural network is used to extract features of the basic health data to obtain the user's health feature vector. The health feature vector is input into a preset neural network model for multi-layer perceptron calculation to obtain the user's basal metabolic rate and daily calorie requirement.

[0036] The sensor equipment can more accurately obtain the user's weight, height, age and gender data; specifically, the sensor equipment includes smart weight scales, height measuring instruments, smart bracelets, etc. The data collected by these devices can be efficiently uploaded to the system for analysis. Collect the user's eating habits, sleep quality and exercise frequency data, specifically record the user's daily food intake, sleep duration and quality, daily activity and other information through the smart bracelet. Use a multi-layer convolutional neural network to extract features from these data, including parsing the type and amount of the user's daily food intake, segmented analysis of the user's sleep data, quantification of exercise frequency and intensity, and integrate all analysis results into the user's health feature vector.

[0037] For example, through smart bracelets and scales, users' weight changes, daily diet records and exercise status can be collected in real time, and automatically synchronized to the system for analysis to generate a detailed health report.

[0038] In step S200, the basal metabolic rate and daily calorie requirement are matched with the dietary data in a preset nutrition database to obtain several steps of recommended diet plans, including: inputting the basal metabolic rate and daily calorie requirement data into a preset matching model, and in the matching model, using a multi-objective optimization algorithm to intelligently match the basal metabolic rate and daily calorie requirement data with the nutritional components and calorie data of ingredients in a preset nutrition database to obtain a matching result.

[0039] By matching the basal metabolic rate and daily calorie requirement data with the nutrition database, scientific dietary advice can be provided to users. Specifically, in the preset matching model, a multi-objective optimization algorithm is used to comprehensively consider the nutritional content and calorie data of the ingredients to match the best dietary plan.

[0040] For example, based on the user's basal metabolic rate and daily calorie requirements, several low-calorie, high-nutrition ingredient combinations are automatically screened out from the nutrition database to provide a variety of meal options.

[0041] A multi-level screening algorithm is used to select ingredient combinations that match the matching results in the nutrition database to obtain several recommended diet plans.

[0042] The accuracy of matching results is improved through a multi-level screening algorithm; specifically, the multi-level screening algorithm includes two steps: preliminary screening and fine screening. The preliminary screening excludes ingredients that do not meet the standards based on nutritional components and calorie data, while the fine screening further screens ingredient combinations that meet the user's health needs based on the user's health feature vector.

[0043] For example, preliminary screening can exclude high-fat and high-sugar ingredients, while detailed screening compares the user's health characteristics to select the most suitable combinations of ingredients to form a recommended diet plan.

[0044] In step S200, a health assessment is performed on the basal metabolic rate to obtain nutritional ratio recommendations, and the nutritional ratio recommendations are matched with the daily calorie requirements to obtain daily dietary recommendations, including: comparing the basal metabolic rate with standard data on age, gender, and weight and conducting a health risk assessment to obtain a metabolic health status, an energy requirement adjustment index, and an energy consumption level, and assessing the user's malnutrition risk based on the metabolic health status to obtain a nutritional risk score.

[0045] Through a detailed health assessment of the basal metabolic rate, personalized nutritional recommendations can be better formulated; specifically, the user's basal metabolic rate is compared with the standard data of the same age, gender and weight to assess their metabolic health status and calculate the energy demand adjustment index and energy consumption level. Based on the metabolic health status, the user's malnutrition risk is assessed and a nutritional risk score is derived.

[0046] For example, by comparing the basal metabolic rate and energy consumption level of a 30-year-old male, it was found that his metabolic rate was low, his energy requirement index was high, his malnutrition risk score was medium, and he needed to adjust his diet structure to improve his health.

[0047] The energy requirement adjustment index is used to evaluate the user's requirement ratio for various nutrients, and the protein requirement ratio, fat requirement ratio and carbohydrate requirement ratio are obtained.

[0048] By applying the Energy Need Adjustment Index, the user's requirement ratio for various nutrients can be accurately calculated; specifically, based on the user's energy consumption level and health status, the specific requirement ratio for protein, fat and carbohydrates can be evaluated.

[0049] For example, a user who exercises intensely may require a higher proportion of protein and a relatively lower proportion of carbohydrates and fats.

[0050] Compare the protein requirement ratio with the energy consumption level to obtain the user's high-energy food requirement level.

[0051] By comparing the protein requirement ratio with the energy consumption level, the user's need for high-energy food can be determined; specifically, based on the user's protein requirement ratio and daily energy consumption, the types and intake of high-energy food that the user needs to increase can be determined.

[0052] For example, a user who is doing weight training needs to increase the intake of high-protein and high-energy foods such as chicken breast and fish to meet his high energy needs.

[0053] The fat requirement ratio is compared with the nutritional risk score to obtain the user's healthy fat requirement recommendation.

[0054] By comparing the fat requirement ratio with the nutritional risk score, scientific healthy fat requirement recommendations can be provided; specifically, based on the user's fat requirement ratio and nutritional risk score, the amount of healthy fat they need to consume is evaluated, and specific intake recommendations are provided.

[0055] For example, a user who is overweight and has a high nutritional risk score may need to reduce their intake of saturated fatty acids and increase their intake of unsaturated fatty acids, such as olive oil and nuts.

[0056] Compare the carbohydrate requirement ratio with the high-energy food requirement level to obtain nutritional ratio recommendations.

[0057] By comparing the carbohydrate requirement ratio with the high-energy food requirement level, the user's nutritional intake can be better balanced; specifically, based on the user's carbohydrate requirement ratio and high-energy food requirement level, scientific nutritional ratio recommendations are made to ensure that the user consumes a balanced nutrition.

[0058] For example, an athlete with high energy consumption needs to increase carbohydrate-rich foods such as whole grains and vegetables to maintain a high level of energy supply.

[0059] Compare the healthy fat demand recommendations and nutritional ratio recommendations with the daily calorie requirements to get daily dietary recommendations.

[0060] By matching healthy fat demand recommendations and nutritional ratio recommendations with daily calorie requirements, scientific daily dietary recommendations can be formulated; specifically, by combining the user's fat demand recommendations, nutritional ratio recommendations and daily calorie requirements, personalized daily dietary recommendations are generated to ensure that the user's nutritional intake is balanced and meets their health needs.

[0061] For example, based on the user's daily calorie requirements and nutritional ratio recommendations, a specific daily meal plan is generated, including detailed plans for breakfast, lunch, dinner and snacks.

[0062] Among them, the steps of matching healthy fat demand recommendations and nutritional ratio recommendations with daily calorie requirements to obtain daily dietary recommendations include: using a preset decision tree model to concretize and personalize the healthy fat demand recommendations and nutritional ratio recommendations to obtain personalized nutritional recommendations and standardized nutritional recommendations, and optimizing the matching of personalized nutritional recommendations, standardized nutritional recommendations with daily calorie requirements to obtain daily dietary recommendations; wherein, personalized nutritional recommendations are nutritional plans for individual physiological needs; and standardized nutritional recommendations are plans that meet the nutritional needs of the general population.

[0063] The decision tree model can effectively analyze the healthy fat demand recommendations and nutritional ratio recommendations in detail; specifically, the decision tree model distinguishes the user's personal physiological needs from the nutritional needs of the general population through multi-level analysis, and generates personalized nutritional recommendations and standardized nutritional recommendations. These two types of recommendations are optimized with the daily calorie requirements to ensure that each user's daily dietary recommendations meet their personal needs and meet general health standards.

[0064] For example, through decision tree model analysis, the personalized nutrition recommendations for an athlete who requires high energy intake will include high-protein and high-fat intake, while standardized nutrition recommendations will provide the nutritional intake ratios of the general population, optimizing the ratio of the two to generate the final daily dietary recommendations.

[0065] In step S300, all recommended diet plans are screened using daily dietary advice to obtain initial diet advice, and the initial diet advice is adjusted in real time based on the user's blood sugar level, blood pressure level, and heart rate level during the current period to obtain target diet advice, including: analyzing the user's nutritional deficiencies and excesses through daily dietary advice, screening all recommended diet plans to obtain initial diet advice, comparing the initial diet advice with the user's actual eating habits to obtain a preliminary draft of the diet adjustment.

[0066] Analyze users' nutritional deficiencies and excesses through daily dietary recommendations to improve the accuracy of recommended diet plans; specifically, by analyzing users' daily dietary data, identify deficiencies and excesses in their nutritional intake, and screen recommended diet plans accordingly to generate initial diet recommendations. Compare and analyze the initial diet recommendations with the user's actual eating habits to obtain a preliminary draft of diet adjustments that are more in line with the user's eating habits. For example, by analyzing the user's dietary records, it is found that their vitamin D intake is insufficient and their sugar intake is excessive. Their diet plan will be adjusted accordingly, and it is recommended to increase the intake of foods rich in vitamin D and reduce the intake of high-sugar foods.

[0067] The user's blood sugar level, blood pressure level and heart rate level in the current period are obtained, and the real-time health monitoring system is used to perform real-time analysis on physiological data such as blood sugar level, blood pressure level and heart rate level to obtain blood sugar stability index, blood pressure regulation demand and heart rate variability index.

[0068] By monitoring the user's physiological data in real time, dietary recommendations can be adjusted more accurately. Specifically, the user's blood sugar level, blood pressure level, and heart rate level can be obtained in real time through smart wearable devices or physiological data monitoring systems, and these data can be transmitted to the analysis system for real-time analysis to derive the user's blood sugar stability index, blood pressure regulation needs, and heart rate variability indicators.

[0069] For example, a smart bracelet can monitor the user's blood sugar changes in real time. When a large fluctuation in blood sugar is found, the user is immediately prompted to adjust his diet to maintain blood sugar stability.

[0070] The blood sugar stability index was compared and adjusted with the carbohydrate intake recommendations in the first draft of dietary adjustment to obtain a carbohydrate intake optimization plan.

[0071] By comparing the glycemic stability index with the carbohydrate intake recommendations in the preliminary dietary advice, the carbohydrate intake plan can be optimized; specifically, the carbohydrate intake in the preliminary recommendations is adjusted according to the user's glycemic stability index to ensure that blood sugar is maintained within a stable range.

[0072] For example, if the user's glycemic stability index is low, it is recommended to reduce sugar intake and increase fiber intake to help stabilize blood sugar.

[0073] The blood pressure regulation needs were compared and adjusted with the sodium intake recommendations in the first draft of dietary adjustments to obtain an optimized salt intake plan.

[0074] By comparing blood pressure regulation needs with the sodium intake recommendations in the initial dietary advice, the salt intake plan can be optimized; specifically, based on the user's blood pressure regulation needs, the sodium intake in the initial recommendations is adjusted to help control blood pressure.

[0075] For example, if the user has a high blood pressure regulation need, it is recommended to reduce the intake of high-sodium foods and increase potassium-rich foods, such as bananas and spinach.

[0076] The heart rate variability index was compared and adjusted with the fat and protein intake in the first draft of the diet adjustment to obtain the optimized fat intake ratio and the optimized protein intake ratio.

[0077] By comparing the heart rate variability index with the fat and protein intake in the preliminary dietary recommendations, the fat and protein intake ratio can be optimized; specifically, the fat and protein intake in the preliminary recommendations are adjusted according to the user's heart rate variability index to ensure the user's cardiovascular health.

[0078] For example, if a user's heart rate variability index is low, it is recommended to reduce the intake of saturated fat and increase the intake of unsaturated fat and high-quality protein, such as fish and nuts.

[0079] By integrating the carbohydrate intake optimization plan, salt intake optimization plan, fat intake optimization ratio and protein intake optimization ratio, we can get target dietary recommendations.

[0080] By integrating various optimization plans, we can provide users with comprehensive target diet recommendations; specifically, by combining the optimization recommendations for carbohydrates, salt, fat and protein, we can generate a comprehensive diet plan that meets the user's current health status and nutritional needs.

[0081] For example, various optimization suggestions can be integrated to generate a detailed diet plan that includes specific daily plans and intake to help users better manage their diet and health.

[0082] Among them, the steps of analyzing the user's nutritional deficiencies and excesses through daily dietary recommendations, screening all recommended dietary plans, obtaining initial dietary recommendations, comparing the initial dietary recommendations with the user's actual eating habits, and obtaining a preliminary draft of dietary adjustments include: comprehensively evaluating daily dietary recommendations through the Dietary Reference Intakes calculator to obtain a dietary balance evaluation and a nutritional deficiency assessment, using the USDA food database to further nutritionally adjust the dietary balance evaluation to obtain adjusted dietary recommendations and nutritional supplement recommendations, and using a linear programming algorithm to match the fat intake in the adjusted dietary recommendations with the nutritional deficiency assessment to obtain a fat intake recommendation.

[0083] The Dietary Reference Intakes calculator comprehensively evaluates the user's daily dietary recommendations and accurately identifies dietary balance and nutritional deficiencies. Specifically, the calculator is combined with the USDA food database to conduct a detailed analysis and adjustment of the user's nutritional intake, generating adjusted dietary recommendations and nutritional supplement recommendations. Then, a linear programming algorithm is used to supplement the fat intake in these recommendations to ensure that the user consumes a balanced nutrition.

[0084] For example, through the calculator's assessment, a user who is chronically deficient in vitamin D will be advised to increase vitamin D supplementation and adjust their fat intake through a linear programming algorithm to generate a more scientific diet plan.

[0085] The fat intake recommendations and nutritional supplement recommendations were integrated through the simulated annealing algorithm to obtain comprehensive nutritional recommendations and optimized dietary adjustment plans. The nutritional treatment standards of the Academy of Nutrition and Dietetics were used to make actual dietary adjustments to the comprehensive nutritional recommendations to obtain an adjusted daily meal plan.

[0086] The simulated annealing algorithm can optimize and integrate fat intake recommendations and nutritional supplement recommendations; specifically, after multiple iterations of fat intake and other nutritional supplements, the simulated annealing algorithm generates the best comprehensive nutritional recommendations and dietary adjustment plans. Using the Academy of Nutrition and Dietetics' nutritional treatment standards, the comprehensive nutritional recommendations are actually adjusted to form a detailed daily meal plan.

[0087] For example, through the simulated annealing algorithm, the user's fat and nutrient intake recommendations can be repeatedly adjusted to ultimately generate an optimized diet adjustment plan that includes daily plans, food types, and intake amounts.

[0088] The recommended diet plan was screened using the adjusted daily meal plan and optimized diet adjustment plan to obtain initial diet recommendations.

[0089] Through the adjusted daily meal plan and optimized diet adjustment plan, the scientificity and personalization of the recommended diet plan can be improved; specifically, by analyzing the optimized meal plan, the recommended diet plan is screened, and the options that do not meet the optimization suggestions are eliminated, and finally the initial diet recommendation is generated.

[0090] For example, through the optimized meal plan, several diet plans that best meet the user's health needs are screened out and provided as preliminary suggestions for the user to choose from.

[0091] The user's actual eating habits are obtained through a food intake frequency questionnaire, and a comprehensive analysis of the user's actual eating habits is performed through multivariate regression analysis to obtain an actual dietary preference assessment. The initial dietary recommendations are compared with the actual dietary preference assessment to obtain a preliminary draft of the dietary adjustment.

[0092] The food intake frequency questionnaire can accurately understand the user's eating habits; specifically, the dietary data collected through the questionnaire is comprehensively analyzed using multivariate regression analysis methods to generate an assessment of the user's actual dietary preferences. The initial dietary recommendations are compared and analyzed with these assessment results to generate a draft of dietary adjustments that are more in line with the user's habits.

[0093] For example, through a questionnaire survey, it was found that a user prefers a high-protein, low-carb diet. The initial diet recommendations were adjusted accordingly to generate a draft of the diet adjustment that meets his or her actual preferences.

[0094] In this embodiment, the user's weight, height, age and gender data are obtained by using a sensor device, and the user's eating habits, sleep quality and exercise frequency are collected to obtain comprehensive basic health data. The data are feature extracted using a multi-layer convolutional neural network to generate the user's health feature vector, and then the multi-layer perceptron operation is performed through a preset neural network model to accurately calculate the user's basal metabolic rate and daily calorie requirement. In the process of intelligently matching the basal metabolic rate and daily calorie requirement with the dietary data in the nutrition database, a multi-objective optimization algorithm and a multi-level screening algorithm are used to ensure the scientificity and personalization of the recommended diet plan. After a health assessment, a nutritional ratio recommendation that meets the user's needs is formulated through a detailed nutritional risk assessment and energy demand adjustment, and the dietary recommendation is dynamically adjusted according to the real-time monitored physiological data to ensure that it always meets the user's actual health needs. Finally, a comprehensive target diet plan is generated by combining the optimization suggestions of various nutrients, which improves the accuracy and effectiveness of healthy diet management and improves the user's health and quality of life.

[0095] Embodiment 3: like Figure 2 As shown, the present application also provides an AI-based healthy diet nutrition management system 10, including a collection unit 11, a matching unit 12 and a screening unit 13.

[0096] The collection unit 11 is mainly used to collect the basic health data of the user, and analyze the basic health data using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirement.

[0097] The matching unit 12 is mainly used to match the basal metabolic rate and the daily calorie requirement with the dietary data in the preset nutrition database to obtain several recommended dietary plans, conduct a health assessment on the basal metabolic rate, obtain nutritional ratio suggestions, match the nutritional ratio suggestions with the daily calorie requirement, and obtain daily dietary suggestions.

[0098] The screening unit 13 is mainly used to screen all recommended diet plans using daily dietary recommendations to obtain initial diet recommendations, and to make real-time adjustments to the initial diet recommendations based on the user's blood sugar level, blood pressure level, and heart rate level during the current period to obtain target diet recommendations.

[0099] In this embodiment, the basic health data of the user, such as weight, height, age, gender, eating habits, sleep quality and exercise frequency, are collected by the collection unit 11, and the basic health data is operated by a multi-layer perceptron using a preset neural network model to accurately calculate the user's basal metabolic rate and daily calorie requirement. The matching unit 12 inputs the basal metabolic rate and daily calorie requirement data into the multi-objective optimization algorithm, and intelligently matches it with the preset nutrition database to obtain a recommended diet plan that meets the user's health needs. After the health assessment, the generated nutritional ratio suggestion is further comprehensively matched with the user's daily calorie requirement to generate a scientific daily dietary suggestion. The screening unit 13 uses the daily dietary suggestion to screen all recommended diet plans, and dynamically adjusts the initial dietary suggestion by real-time monitoring of the user's blood sugar level, blood pressure level and heart rate level, and finally obtains a personalized target dietary suggestion. The system not only improves the accuracy and personalization of dietary management, but also can respond to the user's health changes in real time, improve the overall health management effect, and significantly improve the user's dietary habits and health status.

[0100] It should be noted that technical personnel in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each unit described above can refer to the corresponding process in the aforementioned AI-based healthy diet nutrition management method embodiment, and will not be repeated here.

[0101] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A healthy diet nutrition management method based on AI, characterized in that: include: Collecting basic health data of the user, analyzing the basic health data using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirement; Matching the basal metabolic rate and the daily calorie requirement with the dietary data in a preset nutrition database to obtain several recommended dietary plans, performing a health assessment on the basal metabolic rate to obtain nutritional ratio suggestions, and matching the nutritional ratio suggestions with the daily calorie requirement to obtain daily dietary suggestions; The daily dietary recommendations are used to screen all the recommended diet plans to obtain initial diet recommendations. Based on the user's blood sugar level, blood pressure level and heart rate level in the current period, the initial diet recommendations are adjusted in real time to obtain target diet recommendations.

2. The AI-based healthy diet nutrition management method according to claim 1, characterized in that: The step of collecting the basic health data of the user, analyzing the basic health data using a preset neural network model, and obtaining the basal metabolic rate and daily calorie requirement of the user includes: Use sensor equipment to obtain the user's weight, height, age and gender data, and collect the user's eating habits, sleep quality and exercise frequency to obtain basic health data; A multi-layer convolutional neural network is used to extract features from the basic health data to obtain a health feature vector of the user, and the health feature vector is input into a preset neural network model for multi-layer perceptron calculation to obtain the user's basal metabolic rate and daily calorie requirement.

3. The AI-based healthy diet nutrition management method according to claim 1, characterized in that: The step of matching the basal metabolic rate and the daily calorie requirement with the dietary data in a preset nutrition database to obtain a plurality of recommended dietary plans includes: Inputting the basal metabolic rate and the daily calorie requirement data into a preset matching model, in which a multi-objective optimization algorithm is used to intelligently match the basal metabolic rate and the daily calorie requirement data with the food nutrient composition and calorie data in a preset nutrition database to obtain a matching result; The food combinations matching the matching results in the nutrition database are screened out through a multi-level screening algorithm to obtain a number of recommended diet plans.

4. The AI-based healthy diet nutrition management method according to claim 1, characterized in that: The step of performing a health assessment on the basal metabolic rate to obtain a nutritional ratio recommendation, and matching the nutritional ratio recommendation with the daily calorie requirement to obtain a daily dietary recommendation comprises: Compare the basal metabolic rate with standard data of age, gender, and weight and conduct health risk assessment to obtain metabolic health status, energy demand adjustment index, and energy consumption level; assess the user's malnutrition risk based on the metabolic health status to obtain a nutritional risk score; The energy requirement adjustment index is used to evaluate the user's requirement ratio for various nutrients to obtain the protein requirement ratio, fat requirement ratio and carbohydrate requirement ratio; Comparing the protein requirement ratio with the energy consumption level to obtain the user's high-energy food requirement level; Comparing the fat requirement ratio with the nutritional risk score to obtain a healthy fat requirement recommendation for the user; Comparing the carbohydrate requirement ratio with the high-energy food requirement level to obtain a nutritional ratio recommendation; The healthy fat requirement recommendation, the nutritional ratio recommendation and the daily calorie requirement are matched to obtain daily dietary recommendations.

5. The AI-based healthy diet nutrition management method according to claim 4, characterized in that: The step of matching the healthy fat requirement recommendation, the nutritional ratio recommendation and the daily calorie requirement to obtain daily dietary recommendations includes: The healthy fat demand recommendation and the nutritional ratio recommendation are concretized and personalized through a preset decision tree model to obtain personalized nutritional recommendations and standardized nutritional recommendations, and the personalized nutritional recommendations, the standardized nutritional recommendations and the daily calorie requirements are optimally matched to obtain daily dietary recommendations; wherein the personalized nutritional recommendations are nutritional plans for individual physiological needs; and the standardized nutritional recommendations are plans that meet the nutritional needs of the general population.

6. The AI-based healthy diet nutrition management method according to claim 1, characterized in that: The step of screening all the recommended diet plans by using the daily dietary recommendations to obtain initial diet recommendations, and adjusting the initial diet recommendations in real time based on the user's blood sugar level, blood pressure level, and heart rate level during the current period to obtain target diet recommendations includes: Analyze the user's nutritional deficiencies and excesses through the daily dietary recommendations, screen all the recommended dietary plans, obtain initial dietary recommendations, compare the initial dietary recommendations with the user's actual dietary habits, and obtain a preliminary draft of dietary adjustments; Obtaining the user's blood sugar level, blood pressure level and heart rate level in the current period, and performing real-time analysis on the blood sugar level, blood pressure level and heart rate level through a real-time health monitoring system to obtain a blood sugar stability index, blood pressure regulation requirements and heart rate variability indicators; Comparing and adjusting the blood sugar stability index with the carbohydrate intake recommendations in the draft of the dietary adjustment to obtain a carbohydrate intake optimization plan; Comparing and adjusting the blood pressure regulation requirements with the sodium intake recommendations in the draft of the dietary adjustment to obtain a salt intake optimization plan; Comparing and adjusting the heart rate variability index with the fat and protein intake in the first draft of the diet adjustment to obtain an optimized fat intake ratio and an optimized protein intake ratio; The target diet recommendation is obtained by combining the carbohydrate intake optimization plan, salt intake optimization plan, fat optimization intake ratio and protein optimization intake ratio.

7. The AI-based healthy diet nutrition management method according to claim 6, characterized in that: The steps of analyzing the user's nutritional deficiencies and excesses through the daily dietary recommendations, screening all the recommended dietary plans to obtain initial dietary recommendations, and comparing the initial dietary recommendations with the user's actual dietary habits to obtain a preliminary draft of dietary adjustments include: Comprehensively evaluate the daily dietary recommendations using the Dietary Reference Intakes calculator to obtain a dietary balance evaluation and a nutritional deficiency evaluation, further adjust the dietary balance evaluation using the USDA food database to obtain adjusted dietary recommendations and nutritional supplement recommendations, and use a linear programming algorithm to match the fat intake in the adjusted dietary recommendations with the nutritional deficiency evaluation to obtain a fat intake recommendation; The fat intake recommendation and the nutritional supplement recommendation are integrated by a simulated annealing algorithm to obtain a comprehensive nutritional recommendation and an optimized dietary adjustment plan, and the nutritional treatment course standard of the Academy of Nutrition and Dietetics is used to make actual dietary adjustments to the comprehensive nutritional recommendation to obtain an adjusted daily dietary plan; Using the adjusted daily dietary plan and the optimized dietary adjustment plan to screen the recommended dietary plan to obtain initial dietary advice; The user's actual eating habits are obtained through a food intake frequency questionnaire, and the user's actual eating habits are comprehensively analyzed through multivariate regression analysis to obtain an actual dietary preference assessment. The initial dietary recommendations are compared with the actual dietary preference assessment to obtain a preliminary draft of the dietary adjustment.

8. An AI-based healthy diet nutrition management system, characterized in that: include: A collection unit, used to collect basic health data of the user, and analyze the basic health data using a preset neural network model to obtain the user's basal metabolic rate and daily calorie requirement; A matching unit, used to match the basal metabolic rate and the daily calorie requirement with the dietary data in a preset nutrition database to obtain a number of recommended dietary plans, perform a health assessment on the basal metabolic rate to obtain nutritional ratio suggestions, and match the nutritional ratio suggestions with the daily calorie requirement to obtain daily dietary suggestions; The screening unit is used to screen all the recommended diet plans using the daily dietary recommendations to obtain initial diet recommendations, and to adjust the initial diet recommendations in real time based on the user's blood sugar level, blood pressure level and heart rate level in the current period to obtain target diet recommendations.

Images