A personalized diet intelligent matching method for pregnant women based on gestational week image

Abstract

The present application relates to the technical field of health management during pregnancy, and discloses a pregnant woman individualized meal intelligent matching method based on gestational age image, comprising the following steps: S1, multi-dimensional data acquisition and dynamic gestational age image construction stage; S2, standardized database and multi-dimensional nutrition demand model establishment stage; S3, intelligent meal matching and heat dynamic regulation stage; S4, supporting health guidance scheme generation stage; S5, closed-loop optimization and whole-cycle file management stage; The present application realizes the change of dietary guidance during pregnancy from generalization to individualization, can fully adapt to the individual differences and special physiological conditions of different pregnant women, and through the dynamic updating of the gestational age image and the real-time heat regulation mechanism, the dietary scheme can accurately match the nutrition demand of pregnant women in different gestational period stages, and the scientificity and executability of the dietary scheme are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of pregnancy health management technology, and in particular to a method for intelligent matching of personalized diets for pregnant women based on gestational week profiles. Background Technology

[0002] With society placing increasing emphasis on prenatal health, scientific and reasonable dietary guidance has become an important aspect of ensuring maternal and fetal health.

[0003] Traditional dietary guidance during pregnancy relies heavily on the advice of medical staff. Due to insufficient medical resources and differences in individual experience, it is difficult to achieve refined and personalized nutritional intervention.

[0004] In recent years, various pregnancy diet management systems have become increasingly popular. However, most existing systems use standardized, general templates for dietary recommendations, which cannot fully adapt to the individual differences of different pregnant women and the dynamic physiological changes during pregnancy. This makes it difficult to meet the needs of modern pregnant women for high-quality, personalized pregnancy health services. Summary of the Invention

[0005] The purpose of this invention is to provide a personalized dietary intelligent matching method for pregnant women based on gestational week profiles, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A personalized dietary matching method for pregnant women based on gestational age profiles includes the following steps:

[0008] S1. Multi-dimensional data collection and dynamic gestational week profile construction stage: Collect multi-dimensional basic and health data of pregnant women, establish a hierarchical and labeled gestational week profile system, and set the profile update cycle and triggering conditions.

[0009] S2. Standardized database and multi-dimensional nutritional requirement model establishment stage: Construct a standardized food nutrition database, establish basic nutritional requirement models based on gestational week, number of fetuses, and BMI level, and set calorie intake benchmarks and weight gain targets for different groups.

[0010] S3, Intelligent Diet Matching and Dynamic Calorie Regulation Stage: A multi-objective optimization matching algorithm is used to perform multi-dimensional matching, generate personalized dietary plans, record the actual intake of pregnant women, and dynamically adjust the calorie ratio of subsequent meals.

[0011] S4. In the stage of generating supporting health guidance programs, a personalized exercise guidance program for pregnancy is generated based on the pregnant woman's gestational week, BMI and physical condition, and corresponding nutrition and health education information is pushed according to the current gestational week.

[0012] S5. Closed-loop optimization and full-cycle record management stage: collect feedback and health data from pregnant women, dynamically adjust gestational week profile tags and matching algorithm parameters, and establish and update full-cycle nutrition and health records.

[0013] As a further improvement to this technical solution: In S1, the pregnant woman's age, height, pre-pregnancy weight, current BMI, gestational age, number of fetuses, past health history, allergy history, dietary preferences, religious dietary restrictions, indicators of previous prenatal examinations, and fetal ultrasound development data are collected. After standardizing all the data, they are divided into five categories: basic attribute tags, physiological status tags, nutritional requirement tags, dietary restriction tags, and fetal development tags. Fetal number tags and nutritional requirement coefficient tags are generated for multiple pregnancies, and weight management priority tags are generated for pregnant women with abnormal BMI. The profile is set to a fixed update cycle of 7 days, and manual triggering of updates is also supported after important prenatal checkups are completed.

[0014] As a further improvement to this technical solution: In step S2, a baseline nutritional requirement for singleton pregnancies with normal weight is first established, and the daily total calorie requirement for multiple pregnancies is calculated using the following formula:

[0015]

[0016] in The total daily calorie requirement for pregnant women with multiple pregnancies. This refers to the daily basal calorie requirements for a singleton pregnant woman of normal weight at the same gestational age. Based on the number of fetuses, pregnant women are classified into four categories according to their pre-pregnancy BMI: underweight, normal weight, overweight, and obese. Different daily calorie intake benchmarks are set for each category, and corresponding reasonable weight gain ranges are set for each week, month, and the entire pregnancy.

[0017] As a further improvement to this technical solution: In S3, the multi-objective optimization matching algorithm prioritizes the core nutrient requirements, followed by dietary preferences and regional differences, and finally meal distribution and ingredient diversity to generate a personalized dietary plan that includes three meals and three snacks per day, specifying the exact amount, cooking method and nutrient content of each ingredient, and marking the total calorie value for each meal and the daily total.

[0018] As a further improvement to this technical solution: In step S3, the pregnant woman's daily calorie intake is monitored in real time. When the actual calorie intake of a meal deviates from the target calorie intake by more than 10%, the target calorie intake for the next meal is calculated using the following formula:

[0019]

[0020] in The adjusted target calories for the next meal. This is the planned calorie target for the next meal. This is the target calorie amount for the current meal. Based on the actual calorie intake of the current meal, the amount and type of ingredients for the next meal are automatically adjusted according to the calculation results.

[0021] As a further improvement to this technical solution: In S4, the generated personalized exercise guidance plan for pregnancy specifies the type of exercise, duration of exercise, frequency of exercise and precautions, and the nutrition and health education information is presented in a combination of text and images, and is pushed out 1 to 2 times per week.

[0022] As a further improvement to this technical solution: In S5, the pregnant woman's dietary implementation feedback, weight change data and subsequent prenatal examination results are collected, the correlation between nutrient intake and health indicators is automatically analyzed, the gestational week profile labels and matching algorithm parameters are dynamically adjusted, the full-cycle nutrition and health record records the weight change trajectory, nutrient intake statistics, dietary plan adjustment history and key prenatal examination indicators throughout the entire pregnancy, and generates a complete nutrition guidance summary report after the end of pregnancy.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. This invention realizes the transformation of pregnancy dietary guidance from general to personalized, which can fully adapt to the individual differences and special physiological conditions of different pregnant women. Through dynamically updated gestational week profiles and real-time calorie regulation mechanisms, the dietary plan can accurately match the nutritional needs of pregnant women at different stages of pregnancy, effectively improving the scientificity and feasibility of the dietary plan.

[0025] 2. This invention constructs a complete closed-loop optimization and full-cycle record management system, which can continuously track the nutritional intake and health status of pregnant women, adjust intervention strategies in a timely manner, and integrate supporting exercise guidance and nutrition and health education services. This helps pregnant women develop good living habits, reduce the risk of pregnancy-related complications, provide comprehensive protection for maternal and fetal health, and provide complete data support for postpartum recovery and subsequent health management.

[0026] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific implementation methods are given in detail in the following embodiments and their accompanying drawings. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0028] Figure 1This is a schematic diagram of the structure of a personalized diet intelligent matching method for pregnant women based on gestational age profiles. Detailed Implementation

[0029] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are for illustrative purposes only and are not intended to limit the scope of the invention. The invention is described more specifically in the following paragraphs by way of example with reference to the accompanying drawings. It should be noted that the drawings are in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0030] Please see Figure 1 In this embodiment of the invention, a method for intelligently matching personalized diets for pregnant women based on gestational age profiles includes the following steps:

[0031] S1. Multi-dimensional data collection and dynamic gestational week profile construction stage: Collect multi-dimensional basic and health data of pregnant women, establish a hierarchical and labeled gestational week profile system, and set the profile update cycle and triggering conditions.

[0032] S2. Standardized database and multi-dimensional nutritional requirement model establishment stage: Construct a standardized food nutrition database, establish basic nutritional requirement models based on gestational week, number of fetuses, and BMI level, and set calorie intake benchmarks and weight gain targets for different groups.

[0033] S3, Intelligent Diet Matching and Dynamic Calorie Regulation Stage: A multi-objective optimization matching algorithm is used to perform multi-dimensional matching, generate personalized dietary plans, record the actual intake of pregnant women, and dynamically adjust the calorie ratio of subsequent meals.

[0034] S4. In the stage of generating supporting health guidance programs, a personalized exercise guidance program for pregnancy is generated based on the pregnant woman's gestational week, BMI and physical condition, and corresponding nutrition and health education information is pushed according to the current gestational week.

[0035] S5, Closed-loop optimization and full-cycle record management stage: collect feedback and health data from pregnant women, dynamically adjust gestational week profile tags and matching algorithm parameters, and establish and update full-cycle nutrition and health records.

[0036] Specifically, the multi-dimensional data collection and dynamic gestational profile construction phase is responsible for acquiring basic and health data of pregnant women to form a calculable individual characteristic carrier; the standardized database and multi-dimensional nutritional requirement model establishment phase is responsible for building an authoritative food nutrition data foundation and scientific nutritional requirement calculation standards; the intelligent diet matching and dynamic calorie regulation phase is responsible for matching individual needs with food resources and making real-time adjustments based on actual intake; the supporting health guidance plan generation phase is responsible for providing exercise guidance and nutritional knowledge dissemination in conjunction with the diet plan; and the closed-loop optimization and full-cycle file management phase is responsible for collecting implementation feedback, continuously optimizing the plan, and retaining complete pregnancy health data.

[0037] In S1, data such as the pregnant woman's age, height, pre-pregnancy weight, current BMI, gestational age, number of fetuses, past health history, allergy history, dietary preferences, religious dietary restrictions, indicators of previous prenatal examinations, and fetal ultrasound development data are collected. After standardizing all data, it is divided into five categories: basic attribute tags, physiological status tags, nutritional requirement tags, dietary restriction tags, and fetal development tags. Fetal number tags and nutritional requirement coefficient tags are generated for multiple pregnancies, and weight management priority tags are generated for pregnant women with abnormal BMI. The profile is set to a fixed update cycle of 7 days, and manual updates are also supported after important prenatal checkups are completed.

[0038] Specifically, the basic physiological data collected from pregnant women includes age, height, pre-pregnancy weight, current BMI, gestational age, and number of fetuses. Health-related data includes past health history, allergy history, dietary preferences, religious dietary restrictions, complete blood counts during pregnancy, liver function tests, blood glucose, blood lipids, trace element test results, and ultrasound development data such as fetal biparietal diameter, femur length, and abdominal circumference. All collected data is standardized and categorized into five types: basic attribute tags, physiological status tags, nutritional requirement tags, dietary restriction tags, and fetal development tags. For multiple pregnancies, a separate fetal number tag and corresponding nutritional requirement coefficient tag are generated. For pregnant women with a pre-pregnancy BMI below 18.5 or above 24, a weight management priority tag is generated. The gestational age profile is automatically updated every 7 days, and manual updates are supported after the pregnant woman completes important prenatal checkups such as NT scan, Down syndrome screening, detailed anomaly scan, and glucose tolerance test.

[0039] In S2, a baseline nutritional requirement is first established for singleton pregnancies with normal weight. For multiple pregnancies, the daily total calorie requirement is calculated using the following formula:

[0040]

[0041] in The total daily calorie requirement for pregnant women with multiple pregnancies. This refers to the daily basal calorie requirements for a singleton pregnant woman of normal weight at the same gestational age. Based on the number of fetuses, pregnant women are classified into four categories according to their pre-pregnancy BMI: underweight, normal weight, overweight, and obese. Different daily calorie intake benchmarks are set for each category, and corresponding reasonable weight gain ranges are set for each week, month, and the entire pregnancy.

[0042] Specifically, firstly, based on the Chinese Dietary Guidelines for Pregnant Women, a baseline of basic nutritional needs is established for singleton pregnancies with normal weight at different gestational weeks, clarifying the recommended daily intake of calories, protein, fat, carbohydrates, and various vitamins and minerals; for multiple pregnancies, the total daily calorie requirement is calculated using a formula; in the formula... This indicates the total daily calorie requirement for pregnant women carrying multiple pregnancies. This formula represents the daily basal calorie requirement for a singleton pregnant woman of normal weight at the same gestational age, where n represents the number of fetuses. The formula is based on the linear relationship between maternal metabolic load and fetal nutritional needs in multiple pregnancies, with 0.4 representing the additional nutritional requirement coefficient for a singleton pregnancy. Based on the pregnant woman's pre-pregnancy BMI, she is categorized into four levels: underweight (BMI < 18.5), normal weight (18.5 ≤ BMI < 24), overweight (24 ≤ BMI < 28), and obese (BMI ≥ 28), each corresponding to a different daily calorie intake baseline. Simultaneously, reasonable weight gain ranges are set for each level of pregnant woman: 12.5 to 18 kg for underweight pregnant women, 11.5 to 16 kg for normal weight pregnant women, 7 to 11.5 kg for overweight pregnant women, and 5 to 9 kg for obese pregnant women.

[0043] In S3, the multi-objective optimization matching algorithm prioritizes the core nutrient requirements, followed by dietary preferences and regional differences, and finally meal distribution and ingredient diversity to generate a personalized dietary plan that includes three meals and three snacks a day. It specifies the exact amount, cooking method and nutrient content of each ingredient, and marks the total calorie value for each meal and the daily total.

[0044] Specifically, the multi-objective optimization matching algorithm performs matching calculations according to a three-level priority. The first priority is to meet the core nutrient requirements for fetal development and maternal physiology. The second priority is to take into account the pregnant woman's dietary preferences and regional dietary differences. The third priority is to ensure a reasonable distribution of daily meals and a variety of ingredients. The generated personalized dietary plan includes a complete arrangement of three meals and three snacks per day, specifying the exact weight of each ingredient, the recommended cooking method, and the content of the main nutrients provided by the ingredient. At the same time, the plan separately marks the calorie value of each meal and the total calorie value for the day, so that pregnant women can intuitively understand their intake.

[0045] In S3, the pregnant woman's daily calorie intake is monitored in real time. When the actual calorie intake of a meal deviates from the target calorie intake by more than 10%, the target calorie intake for the next meal is calculated using the following formula:

[0046]

[0047] in The adjusted target calories for the next meal. This is the planned calorie target for the next meal. This is the target calorie amount for the current meal. Based on the actual calorie intake of the current meal, the amount and type of ingredients for the next meal are automatically adjusted according to the calculation results;

[0048] Specifically, the system records the pregnant woman's actual food intake at each meal in real time and calculates the deviation between the actual calorie intake and the target calorie intake. When the deviation exceeds 10% of the target calorie intake, a dynamic calorie adjustment mechanism is activated, and the target calorie intake for the next meal is calculated using a formula. This indicates the adjusted target calorie intake for the next meal. This indicates the planned calorie intake for the next meal. This indicates the target calories for the current meal. This indicates the actual calorie intake of the current meal. The formula ensures that the total daily calorie intake remains within the target range by transferring the calorie deviation of the current meal to the next meal. Based on the calculated adjusted target calorie, the system automatically re-matches the quantity and type of ingredients for the next meal to ensure that the core nutrient requirements are not affected.

[0049] In S4, the generated personalized exercise guidance plan for pregnancy clearly specifies the type of exercise, duration of exercise, frequency of exercise and precautions. Nutrition and health education information is presented in a combination of text and images and is pushed out 1 to 2 times per week.

[0050] Specifically, the generated personalized exercise guidance plan for pregnancy clearly recommends the types of exercise, including low-intensity exercises such as walking, prenatal yoga, and Kegel exercises; it specifies the appropriate duration of each exercise session and the weekly exercise frequency: 15 to 20 minutes per session, 3 to 4 times per week in the first trimester; and 20 to 30 minutes per session, 4 to 5 times per week in the second and third trimesters; it also specifies precautions during exercise, avoiding supine exercises, jumping exercises, and high-risk exercises; the nutritional health education information is presented in a combination of text and images, including the developmental characteristics of the fetus at the current gestational week, the role of key nutrients at this stage, common nutritional misconceptions during pregnancy, and dietary precautions; the education information is pushed out 1 to 2 times per week, and the content is gradually updated as the pregnancy progresses.

[0051] In S5, feedback on pregnant women's diet implementation, weight change data and subsequent prenatal examination results are collected. The correlation between nutrient intake and health indicators is automatically analyzed, and the gestational week profile labels and matching algorithm parameters are dynamically adjusted. The full-cycle nutrition and health record records the weight change trajectory, nutrient intake statistics, dietary plan adjustment history and key prenatal examination indicators throughout the entire pregnancy. A complete nutrition guidance summary report is generated after the end of the pregnancy.

[0052] Specifically, the system continuously collects pregnant women's dietary follow-up feedback data, weekly weight change data, and health indicator data from each subsequent prenatal checkup; it automatically analyzes the correlation between nutritional intake and weight change and prenatal checkup indicators, and dynamically adjusts the label weights in the gestational profile and the parameters of the intelligent matching algorithm based on the analysis results; the full-cycle nutritional health record records the pregnant woman's weight change trajectory throughout the entire pregnancy, daily nutritional intake statistics, the history of adjustments to the dietary plan, and key indicators from all prenatal checkups; after the end of pregnancy, the system automatically integrates all the data in the record to generate a complete summary report of pregnancy nutrition guidance.

[0053] The method of use and working principle of this invention are as follows:

[0054] Instructions for use: First, collect the pregnant woman's basic physiological information, past health history, dietary preferences, and prenatal examination data to construct a hierarchical and tagged dynamic gestational week profile system and set corresponding update rules. Then, based on authoritative prenatal nutrition guidelines, construct a standardized food nutrition database and establish a basic nutritional needs model for different population groups and gestational weeks. Next, use a multi-objective optimization matching algorithm to match the pregnant woman's nutritional needs with food nutrient components in multiple dimensions to generate personalized dietary plans and dynamically adjust the calorie ratio of subsequent meals based on actual intake. At the same time, generate a corresponding prenatal exercise guidance plan and phased nutrition and health education information. Finally, continuously collect feedback on the pregnant woman's dietary implementation and health examination data to dynamically optimize the gestational week profile and matching algorithm parameters, and establish and update the pregnant woman's full-cycle nutritional health record.

[0055] Working principle: By collecting multi-dimensional data, the individual characteristics and health status of pregnant women are transformed into calculable tagged data, constructing a gestational profile that can be updated in real time as the pregnancy progresses. Based on authoritative nutritional standards, a scientific nutritional requirement calculation model is established. Intelligent matching algorithms are used to accurately match the individual nutritional needs of pregnant women with food resources. A dynamic calorie regulation mechanism ensures a balance in daily energy intake. At the same time, a closed-loop feedback mechanism is used to continuously iterate and optimize the plan based on actual implementation results. Integrating exercise guidance and health education content, an integrated nutrition and health management system covering the entire pregnancy is formed.

[0056] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any way. Those skilled in the art can readily implement the present invention based on the description and drawings above. However, any modifications, alterations, and variations made by those skilled in the art without departing from the scope of the present invention using the disclosed technical content are equivalent embodiments of the present invention. Furthermore, any modifications, alterations, and variations made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the present invention.

Claims

1. A method for intelligently matching personalized diets for pregnant women based on gestational age profiles, characterized in that, Includes the following steps: S1. Multi-dimensional data collection and dynamic gestational week profile construction stage: Collect multi-dimensional basic and health data of pregnant women, establish a hierarchical and labeled gestational week profile system, and set the profile update cycle and triggering conditions. S2. Standardized database and multi-dimensional nutritional requirement model establishment stage: Construct a standardized food nutrition database, establish basic nutritional requirement models based on gestational week, number of fetuses, and BMI level, and set calorie intake benchmarks and weight gain targets for different groups. S3, Intelligent Diet Matching and Dynamic Calorie Regulation Stage: A multi-objective optimization matching algorithm is used to perform multi-dimensional matching, generate personalized dietary plans, record the actual intake of pregnant women, and dynamically adjust the calorie ratio of subsequent meals. S4. In the stage of generating supporting health guidance programs, a personalized exercise guidance program for pregnancy is generated based on the pregnant woman's gestational week, BMI and physical condition, and corresponding nutrition and health education information is pushed according to the current gestational week. S5. Closed-loop optimization and full-cycle record management stage: collect feedback and health data from pregnant women, dynamically adjust gestational week profile tags and matching algorithm parameters, and establish and update full-cycle nutrition and health records.

2. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In S1, the pregnant woman's age, height, pre-pregnancy weight, current BMI, gestational age, number of fetuses, past health history, allergy history, dietary preferences, religious dietary restrictions, indicators of previous prenatal examinations, and fetal ultrasound development data are collected. After standardizing all the data, they are divided into five categories: basic attribute tags, physiological status tags, nutritional requirement tags, dietary restriction tags, and fetal development tags. Fetal number tags and nutritional requirement coefficient tags are generated for multiple pregnancies, and weight management priority tags are generated for pregnant women with abnormal BMI. The profile is set to a fixed update cycle of 7 days, and manual updates are also supported after important prenatal checkups are completed.

3. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In step S2, a baseline nutritional requirement is first established for singleton pregnancies with normal weight. For multiple pregnancies, the daily total calorie requirement is calculated using the following formula: in The total daily calorie requirement for pregnant women with multiple pregnancies. This refers to the daily basal calorie requirements for a singleton pregnant woman of normal weight at the same gestational age. Based on the number of fetuses, pregnant women are classified into four categories according to their pre-pregnancy BMI: underweight, normal weight, overweight, and obese. Different daily calorie intake benchmarks are set for each category, and corresponding reasonable weight gain ranges are set for each week, month, and the entire pregnancy.

4. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In S3, the multi-objective optimization matching algorithm prioritizes core nutrient requirements, followed by dietary preferences and regional differences, and finally meal distribution and ingredient diversity to generate a personalized dietary plan that includes three meals and three snacks per day. It specifies the exact amount, cooking method, and nutrient content of each ingredient, and marks the total calorie value for each meal and the daily total.

5. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In step S3, the pregnant woman's daily calorie intake is monitored in real time. When the actual calorie intake at a meal deviates from the target calorie intake by more than 10%, the target calorie intake for the next meal is calculated using the following formula: in The adjusted target calories for the next meal. This is the planned calorie target for the next meal. This is the target calorie amount for the current meal. Based on the actual calorie intake of the current meal, the amount and type of ingredients for the next meal are automatically adjusted according to the calculation results.

6. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In S4, the generated personalized exercise guidance plan for pregnancy specifies the type of exercise, duration of exercise, frequency of exercise and precautions. Nutrition and health education information is presented in a combination of text and images and is pushed out 1 to 2 times per week.

7. The method for intelligently matching personalized diets for pregnant women based on gestational age profiles according to claim 1, characterized in that, In S5, the system collects pregnant women's feedback on diet implementation, weight change data, and subsequent prenatal examination results. It automatically analyzes the correlation between nutrient intake and health indicators, dynamically adjusts gestational week profile tags and matching algorithm parameters, and records the weight change trajectory, nutrient intake statistics, dietary plan adjustment history, and key prenatal examination indicators throughout the entire pregnancy in a full-cycle nutrition and health record. After the pregnancy ends, a complete nutrition guidance summary report is generated.

Images