A personalized food nutrition grade evaluation system based on a double-track database

Abstract

The application discloses a kind of dynamic food nutrition loss and gain grade evaluation system and method based on food, food material (including herbal plant) ingredient content level and individual health data.System acquires food ingredient data (such as energy, protein, fat, cellulose, potassium, sodium, magnesium, additive, etc.) and individual medical index (such as blood sugar, blood pressure, blood fat, uric acid, height and weight, allergy history, etc.) data, combined with eu nutrition score standard and China's general coefficient, then dynamically adjusts coefficient weight according to individual health condition (such as high blood pressure user adjusts high iron sodium related coefficient), finally generates general health grade and personalized recommendation grade.System presents results through mobile terminal or PC terminal App, and uses encryption technology to protect user privacy.The application solves the problem of lack of individualization in existing evaluation, and provides accurate dietary health guidance for users.

Description

Technical Field

[0001] This invention relates to the field of computer application technology, specifically to a health benefit assessment system and method based on the content of food and ingredients (including herbs) and individual medical health indicators, which can be applied to scenarios such as intelligent health management and personalized diet recommendations. Background Technology

[0002] Currently, the main shortcomings of food health assessment methods on the market are as follows: 1. Lack of personalized assessment: Most assessments are based solely on general nutritional standards and do not incorporate individual health data (such as blood sugar, blood pressure, blood lipids, uric acid, etc.), thus failing to provide users with targeted dietary advice. For example, hypertensive patients need to control their sodium intake, but general assessments do not differentiate the weighting of sodium components.

[0003] 2. Limited data dimensions: Existing systems typically only consider basic nutritional components (such as energy, protein, fat, sugar, and sodium), while ignoring risk factors such as additives, pesticide residues, and processing levels, as well as the impact of the content of core components in special ingredients such as herbs on health.

[0004] 3. Insufficient regional adaptability: Internationally accepted nutritional scoring standards (such as EU standards) do not fully take into account the dietary structure of Chinese residents (such as high-salt diets and the use of food and medicine homology ingredients), resulting in poor adaptability of the evaluation results to China's national conditions.

[0005] 4. Weak privacy protection: Some health management systems lack strict encryption for the storage and transmission of users' medical data, posing a risk of privacy leaks.

[0006] Therefore, there is an urgent need for a personalized food nutrition and health assessment system that can integrate multi-dimensional food data, combine individual health indicators, adapt to China's national conditions, and ensure data security. Summary of the Invention

[0007] 1. Purpose of the invention This invention aims to provide a dynamic profit and loss rating system and method based on the composition of food ingredients (including herbal plants) and individual health data. By integrating multi-dimensional data, dynamically adjusting coefficient weights, and strengthening privacy protection, it can achieve general health rating of food and ingredients and personalized recommendations, solving the problems of insufficient personalization and single data dimension in existing technologies.

[0008] 2. Technical Solution The technical solution of this invention includes a system architecture and an implementation method, as detailed below: (1) System Architecture Data acquisition module: Food composition data: Obtain food nutritional components (energy, protein, fat, fiber, sugar, sodium, etc.), ecological environment, additives, heavy metal residues, processing grade, etc. through standardized data interfaces provided by the product provider. At the same time, it supports users to manually input the composition data of ingredients (including herbs) and establish a dedicated composition database for food and medicine homology ingredients (such as goji berries and yams).

[0009] Individual health data: Users upload medical examination reports (indicators such as blood sugar, blood pressure, blood lipids, and uric acid), body parameters (height and weight), and allergy history through the system. The system automatically parses the data and stores it in categories.

[0010] Coefficient processing module: General coefficient preset: Based on the EU food nutrition grade scoring standards, combined with the "Dietary Guidelines for Chinese Residents" and common health risks in the Chinese population (such as the risk of hypertension due to high sodium intake), a base coefficient is set. For example, the risk coefficient of sodium is increased by 10%-20% above the general standard; an enhancement coefficient is set for beneficial components in herbs (such as anthocyanins).

[0011] Dynamic coefficient adjustment: Automatically adjusts the coefficients of corresponding components based on individual health indicators. For example: For users with hypertension / hyperlipidemia: the coefficients for sodium and saturated fatty acids should be increased by 15%-30%; For diabetic patients: The coefficient for sugar and refined carbohydrates should be increased by 20%-40%; For users with a history of allergies: Set a prohibited risk level for allergens (such as gluten and dairy products).

[0012] Level Assessment Module: General grade calculation: Multiply the food composition data by the general coefficient, and sum them to get the corresponding grade range (e.g., grade A is excellent, grade D is poor). At the same time, the processing grade is taken into account (e.g., additional deductions are set for highly processed foods).

[0013] Personalized rating generation: Based on the general rating, a coefficient adjusted for individual health indicators is added to generate a personalized recommendation rating (e.g., "Suitable for people with high blood pressure, sodium risk level B"), and dietary suggestions are provided (e.g., "It is recommended to pair with high-potassium foods to reduce the impact of sodium").

[0014] User interaction module: The system utilizes a mobile app or PC interface, allowing users to input food / health data, query assessment results, and generate recommended value reports. The interface includes visual charts (such as nutrient intake trends and risk component warnings) to enhance the user experience.

[0015] Privacy protection module: User health data is encrypted end-to-end, stored using blockchain technology with block-based notarization, and transmitted in accordance with the Personal Information Protection Law, prohibiting unauthorized access. Users can independently control the scope of data sharing.

[0016] (2) Implementation method Data collection steps: 1. Users scan food barcodes to obtain standardized ingredient data, or manually enter the ingredient composition; 2. Merchants upload product ingredient testing data; 3. Users upload medical examination reports, and the system uses OCR technology to identify key indicators (blood sugar, blood pressure, blood lipids, uric acid, etc.) and prompts users to supplement information such as allergy history.

[0017] Steps for calculating coefficients: 1. The system matches preset universal coefficients based on food composition, such as a coefficient of 0.5 for every 100g of food containing 100mg of sodium. 2. If the user's blood pressure is higher than the normal range, the system will automatically adjust the sodium coefficient to 0.7 to complete the dynamic weighting.

[0018] Level generation steps: 1. General grade = Σ{(content of positive and beneficial components a × corresponding coefficient a) + (content of positive and beneficial components b × corresponding coefficient b) + ...} / Σ{(content of negative and harmful components a × corresponding coefficient a) + (content of negative and harmful components b × corresponding coefficient b) + ...} x 100% 2. Exclusive rating = Σ (individual health indicator value adjustment coefficient × component content), which is ultimately converted into AD rating and text description.

[0019] 3. Beneficial effects Personalized and precise assessment: By dynamically adjusting coefficients based on individual health data, the assessment results are made more closely aligned with the user's actual needs. For example, diabetic patients can intuitively understand the sugar risk level of food.

[0020] Multi-dimensional data integration: covering nutritional components, additives, pesticide residues, processing grades, and medicinal components of herbal plants, providing a more comprehensive evaluation.

[0021] Highly adaptable to national conditions: Combining China's dietary structure and the culture of food and medicine sharing the same origin, exclusive coefficients are set for the core components of common local ingredients (including herbs) to improve the practicality of the evaluation.

[0022] Privacy and security protection: We use encrypted storage and blockchain technology to ensure that users' health data is not leaked and complies with data security regulations.

[0023] This invention, through technological integration, upgrades from general nutritional assessment to precise individual recommendations, providing users with scientific and personalized dietary health management solutions. Attached Figure Description Figure 1 This is a schematic diagram of the system architecture described in this invention, illustrating the interaction relationships between modules such as the food database, medical testing database, dynamic scoring engine, and personalized nutrition level. Figure 2 This is a flowchart of the dynamic coefficient adjustment described in this invention, which shows the steps of medical data threshold judgment, coefficient adjustment and final grade generation; Figure 3 This is a schematic diagram of the mobile terminal interface described in this invention, showing the display format of health ratings, warning information, and alternative food recommendations.

[0024] A pioneering dual-track data dynamic coupling mechanism: resolving the contradiction between individual health needs and general food nutrition grade standards. Balancing Privacy and Functionality: Achieving "Data Usable but Not Visible" Through Federated Learning Business closed-loop innovation: Incentivizing merchants to upload complete data to obtain more objective ratings.

Claims

1. A personalized food nutrition grade assessment system based on a dual-track database, characterized in that, include: - Data Acquisition Module: Used to acquire compositional data of food and ingredients (including herbs), including energy, protein, fiber, nuts, fruits, calcium, magnesium, zinc, selenium, potassium, anthocyanins, saturated fatty acids, sugar, sodium, additives, antibiotics, pesticide residues, processing grade, etc., as well as individual user medical and health indicator data, including blood sugar, blood pressure, blood lipids, uric acid, heart, liver, spleen, lungs and kidneys related indicators, height and weight, allergy history, genetic testing, etc. - Coefficient processing module: Based on the EU food nutrition grade scoring standard and combined with China's national conditions, it presets general nutritional component coefficients, and dynamically adjusts the coefficient weights of corresponding components according to the medical and health index data of individual users. For example, it increases the coefficient of sodium for users with high blood pressure and increases the coefficient of sugar for users with high blood sugar. - Rating module: Based on the adjusted coefficients, calculate the nutritional components of food and ingredients submitted by users and merchants, and generate a general health benefit rating and a personalized recommendation rating based on individual data; - User interaction module: Presents assessment results through a mobile app or PC interface, and supports user input of data and query of historical records; - Privacy protection module: Encrypts and stores user health data during transmission, complying with data privacy protection regulations; 2. The evaluation system according to claim 1, characterized in that, The coefficient processing module includes adjustments based on China's national conditions, such as setting specific coefficients for herbal plant components that are both food and medicine, and setting risk coefficient thresholds for common high-intake components (such as sodium, fat, and sugar) for Chinese residents.

3. The evaluation system according to claim 1, characterized in that, The calculation method of the grade assessment module includes: multiplying food component data by preset coefficients and dynamic adjustment coefficients, summing the results, and generating different grades such as A, B, C, D, and E according to preset grade intervals. The calculation formula of the nutrition grade assessment model is as follows: General nutrition grade score = Σ(actual content of positive nutritional components in a food × weight of that component) / Σ(actual content of negative nutritional components in a food × weight of that component) × 100%. The higher the score, the higher the grade. The personalized recommendation level needs to be combined with the risk coefficient of the individual's health indicators, that is, the personalized level score = Σ (actual content of positive nutritional components of a certain food × dynamically adjusted coefficient) / Σ (actual content of negative nutritional components of a certain food × dynamically adjusted coefficient) × 100%; 4. A method for dynamic profit and loss rating based on food composition and individual health data, characterized in that, Includes the following steps: - Collect data on food and ingredient composition, as well as individual users' medical and health indicators; - A general coefficient is preset based on EU standards and China's national conditions, and the coefficient is dynamically adjusted according to individual health data; - Generate a general health rating and an individual-specific recommendation rating through weighted calculation; - Display results on mobile or PC, and encrypt and protect user data; 5. The system according to claim 3, characterized in that, The evaluation results output by the evaluation result output module include: Individualized nutrition levels are divided into 5 levels: A (Excellent), B (Good), C (Average), D (Poor), and E (Not Recommended).

Images