Diet management system for chronic disease patient, electronic equipment and storage medium

Abstract

The invention discloses a chronic disease patient diet management system, and the system comprises a data collection and integration module which is used for obtaining and fusing multi-source data, and forming a patient exclusive data set; the personalized diet scheme generation module is used for calculating and generating an initial diet scheme based on a medical rule base and the exclusive data set, and a final scheme is formed after the initial diet scheme is audited by the medical terminal; the diet scheme execution support module is used for assisting the user to adjust the diet scheme through a visual tool, a recipe library and an intelligent recording mode; and the monitoring and dynamic adjustment module is used for collecting diet execution data and physiological index data of the user, analyzing the relevance through a machine learning algorithm, generating an adjustment suggestion, and updating the scheme after confirmation of the medical end. According to the invention, multi-source data can be automatically integrated, a personalized diet scheme is intelligently generated and dynamically adjusted, and convenient execution support and continuous health management are provided for patients.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical management technology, specifically to a dietary management system, electronic device, and storage medium for patients with chronic diseases. Background Technology

[0002] The background of chronic disease management stems from profound changes in global population structure, lifestyle, and disease spectrum. With the accelerating aging process, the prevalence of chronic diseases such as hypertension, diabetes, coronary heart disease, and chronic obstructive pulmonary disease (COPD) continues to rise among the elderly. Simultaneously, lifestyle changes brought about by urbanization, such as sedentary lifestyles, high-fat and high-sugar diets, and increased mental stress, are causing chronic diseases to gradually spread to middle-aged and younger populations, becoming the "number one killer" threatening human health. From a societal perspective, chronic diseases are characterized by long courses, high relapse rates, and numerous complications. This not only leads to a decline in patients' quality of life but also requires frequent outpatient and inpatient treatment, consuming long-term medical resources, increasing the burden of personal medical care, and drastically increasing social medical costs, posing a challenge to the existing healthcare system's service model. The traditional medical model, centered on "treating acute illnesses," is no longer sufficient to meet the needs of chronic disease patients for continuous care, including long-term health monitoring, medication guidance, and lifestyle interventions.

[0003] Currently, the main methods for managing chronic diseases are as follows:

[0004] This offline linkage system, centered on community health service centers, connects hospital treatment with home care. After hospitals develop treatment plans, the community health service centers conduct regular follow-ups, basic monitoring, and health guidance, requiring patients to actively provide feedback. Its advantages include patient-friendly services, high trust between doctors and patients, and low cost, making it particularly suitable for elderly people in rural areas and those with stable conditions. However, it also has drawbacks such as reliance on manual information transmission leading to delays, limited community resources making it difficult to handle complex cases, and low patient cooperation affecting management effectiveness.

[0005] The "Internet+" chronic disease management system leverages smart devices and apps to connect three data links: patients' families automatically upload health data and receive alerts, communities view the data in real time and intervene, and hospitals access the data to develop precise treatment plans. This system achieves real-time information sharing, improves management efficiency and patient participation, and is suitable for urban youth and those requiring dynamic monitoring. However, it faces challenges such as technical difficulties for elderly patients, high system and equipment costs, the risk of data leakage, and insufficient integration with offline services.

[0006] The "Family Doctor Contract" Integrated Management System: This system designates the contracted family doctor as the primary responsible party, coordinating community resources and hospital support. The family doctor is responsible for daily patient management and referral coordination, while the hospital provides technical and logistical support. This system has clear responsibilities and consistent management, enabling the implementation of tiered medical services and providing personalized care. It is suitable for patients with multiple comorbidities and those requiring continuous care. However, its effectiveness is limited by insufficient family doctor resources, some contracts becoming merely a formality, and uneven hospital support.

[0007] In summary, the technical problems that a dietary management system for chronic disease patients needs to solve can be summarized as follows: 1. Patients' static information, dynamic physiological indicators, clinical medical data, and daily dietary records are scattered across different systems and media, with inconsistent formats, making it difficult to form unified data that can be used for analysis. 2. There is a lack of an algorithm engine to transform authoritative medical guidelines into calculable personalized data; adjustments to the plan rely on human experience, and automatic and timely optimization based on the correlation analysis between diet and indicators is not possible. 3. Data flow between the patient, medical, and device ends is not smooth, and it is difficult to solve the problem of format incompatibility.

[0008] Therefore, there is an urgent need for a dietary management system for chronic disease patients that can deeply integrate multi-source data, intelligently generate and dynamically adjust personalized dietary plans, provide convenient and accurate execution support, and ensure safe and collaborative operation, in order to solve the above-mentioned technical deficiencies and improve the efficiency and effectiveness of chronic disease management. Summary of the Invention

[0009] In order to overcome the problems in the prior art, the purpose of this invention is to provide a dietary management system for patients with chronic diseases, which can automatically integrate multi-source data, intelligently generate and dynamically adjust personalized dietary plans, and provide patients with convenient execution support and continuous health management.

[0010] To achieve the above objectives, the present invention provides a dietary management system for patients with chronic diseases, comprising:

[0011] The data acquisition and integration module is used to acquire and integrate multi-source data to form a patient-specific dataset;

[0012] The personalized diet plan generation module is communicatively connected to the data acquisition and integration module to receive the patient-specific dataset, and to calculate and generate an initial diet plan based on the medical rule base and the specific dataset, which is then reviewed by the medical end to form the final plan;

[0013] The diet plan execution support module is communicatively connected to the personalized diet plan generation module to receive the final plan, and is used to assist users in adjusting their diet plans through visualization tools, recipe libraries and intelligent recording methods;

[0014] The monitoring and dynamic adjustment module is communicatively connected to the diet plan execution support module and the data acquisition and integration module. It is used to collect user diet execution data and physiological indicator data, analyze their correlation through machine learning algorithms, generate adjustment suggestions, and update the plan after confirmation by the medical end.

[0015] Furthermore, the data acquisition and integration module includes:

[0016] The patient-side data input submodule and the patient-side condition reporting submodule are configured with a user interaction interface, which is used to receive basic information and condition information input by the user through the user interaction interface;

[0017] The medical data interface submodule is configured with a medical data interface for automatically obtaining clinical diagnostic data from the hospital's electronic medical record system.

[0018] The system data integration submodule is communicatively connected to the patient-side data input submodule, the patient-side condition reporting submodule, and the medical-side data interface submodule. It is used to receive and integrate data from the above submodules, perform cleaning and standardization processing, and store the data in the database to form a patient-specific dataset.

[0019] Furthermore, the personalized diet plan generation module includes:

[0020] The medical rule base calling submodule has a built-in rule base based on clinical dietary guidelines, which is used to extract nutrient intake constraints according to the patient's chronic disease type.

[0021] The scheme generation engine submodule communicates with the system data integration submodule and the medical rule base calling submodule. It is used to calculate daily nutritional requirements and allocate nutrient ratios based on patient data and constraints. It is also used to receive the patient-specific dataset and the nutrient intake constraints, and calculate the patient's daily nutritional requirements and allocate nutrient ratios.

[0022] The meal design submodule is connected to the scheme generation engine submodule and is used to receive the nutrient ratio and convert the nutrient ratio into a specific meal allocation scheme and a food selection list.

[0023] The medical review submodule, connected to the meal design submodule, is used to receive the meal allocation plan and food selection list, and then send the generated diet plan to the doctor's or nutritionist's client for review and confirmation before pushing it to the patient's client.

[0024] Furthermore, the diet plan execution support module includes:

[0025] The visualization tools submodule is used to provide a visual reference standard for food portion sizes;

[0026] The recipe library submodule provides detailed recipe templates;

[0027] The intelligent recording submodule includes an image recognition unit and an IoT device interface. The image recognition unit includes a camera for identifying the types of food in a food image and estimating their weight. The IoT device interface is used to connect to smart kitchen appliances to obtain data on the amount of ingredients used.

[0028] The execution feedback submodule is used to receive subjective adaptive feedback from users on the implementation process of the solution.

[0029] Furthermore, the monitoring and dynamic adjustment module includes:

[0030] The data monitoring submodule is communicatively connected to the intelligent recording submodule and the patient-end data input submodule, and is used to continuously collect user diet execution data and physiological indicator change data.

[0031] The correlation analysis submodule, connected to the data monitoring submodule, uses machine learning algorithms to analyze the correlation between fluctuations in physiological indicators and dietary behavior;

[0032] The plan adjustment engine submodule is connected to the correlation analysis module. It is used to generate dietary plan adjustment suggestions based on the analysis results and send them to the medical end review submodule for confirmation and plan update.

[0033] Furthermore, it also includes a patient education and support module, used to push dietary knowledge content to users and provide a platform for doctor-patient interaction and communication. The patient education and support module includes:

[0034] The knowledge push submodule is used to regularly push dietary science content to patients based on their disease type.

[0035] The interactive support submodule provides a platform for online communication between patients and nutritionists, as well as a community exchange platform among patients.

[0036] Furthermore, the standard medical data interface includes an HL7 interface or an FHIR interface.

[0037] The present invention also provides an electronic device, including at least one processor and a memory, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements the module functions of the dietary management system for chronic disease patients as described above.

[0038] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the module functions of the dietary management system for chronic disease patients as described above.

[0039] This invention connects to hospital electronic medical records via a standard medical interface, integrates wearable devices and IoT kitchen appliances, and incorporates patient-reported information to construct a patient-specific dataset, solving the problems of inconsistent and difficult-to-integrate multi-media data. Through a built-in rule-based and solution generation engine, medical knowledge is transformed into calculable nutritional constraints and simplified into meal design output for patients. By integrating an image recognition unit and IoT device interface, the system provides multiple methods for collecting dietary data, reducing user complexity. Through inter-module communication and data flow, a fully digital closed loop is achieved, from data collection, solution generation and review, execution support, monitoring and analysis to dynamic adjustments. By integrating medical resources, optimizing service processes, and strengthening patient self-management, this invention enables collaborative management and remote guidance based on real-time data, improving the overall management efficiency of patients with chronic diseases. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of a dietary management system for patients with chronic diseases provided in Embodiment 1 of the present invention; Detailed Implementation

[0041] The present invention provides a dietary management system for patients with chronic diseases, described below with reference to the accompanying drawings and specific embodiments. This system comprises an electronic device or smartphone on which the patient has a patient-side app installed, a medical-side app on the doctor's / nutritionist's electronic device, a cloud server cluster, and optional smart hardware. The patient-side app and the medical-side application exchange encrypted data with the cloud server via a network. The electronic device connects to the device with the app installed via Bluetooth or Wi-Fi. The following details the complete workflow of the dietary management system for patients with chronic diseases in practical applications.

[0042] like Figure 1 As shown, the chronic disease patient diet management system includes a data collection and integration module, a personalized diet plan generation module, a diet plan execution support module, and a monitoring and dynamic adjustment module.

[0043] The data acquisition and integration module is used to acquire and integrate multi-source data to form a patient-specific dataset; specifically, it includes a patient-side data input submodule, a patient-side condition reporting submodule, and a system data integration submodule.

[0044] The patient-side data input submodule and the patient-side condition reporting submodule are configured with a user interaction interface, which is used to receive basic information and condition information input by the user through the user interaction interface.

[0045] The medical data interface submodule is configured with a medical data interface for automatically acquiring clinical diagnostic data from the hospital's electronic medical record system. This medical data interface includes either an HL7 interface or an FHIR interface.

[0046] The system data integration submodule is communicatively connected to the patient-side data input submodule, the patient-side condition reporting submodule, and the medical-side data docking submodule. It is used to receive and integrate data from the above submodules, perform cleaning and standardization processing, and store the data in the database to form a patient-specific dataset.

[0047] The data acquisition and integration module operates as follows:

[0048] Taking a 55-year-old male patient, A, as an example, Patient A suffers from type 2 diabetes and hypertension. Patient A first enters his age (55 years old), gender (male), height (175cm), weight (85kg), and states that he is allergic to seafood and has preferred dietary habits in the user interface of the mobile app. Then, in the "Disease Reporting" section of the app, Patient A selects "Type 2 Diabetes" and "Hypertension" as the disease types and manually enters the medications he is currently taking, such as "Metformin" and "Nifedipine." This basic information and disease details are processed by the app and then transmitted to the cloud server.

[0049] To obtain authoritative clinical data, the system's medical data interface submodule adaptively calls the corresponding standard medical data interface based on the target hospital's level of informatization. For example, for hospitals that support the FHIR standard, the medical data interface submodule sends a request to the hospital's FHIR server using the HTTPS protocol, initiates a secure query to the hospital's Electronic Medical Record (EMR) system, and obtains the patient's recent clinical diagnostic data, including fasting blood glucose of 8.5 mmol / L, glycated hemoglobin of 7.2%, and a diagnosis of "grade 2 hypertension".

[0050] Meanwhile, Patient A wears a smart blood glucose meter and a smart blood pressure monitor, which measure their blood glucose and blood pressure values ​​multiple times a day and automatically sync them to their mobile app via Bluetooth. The patient-side data input submodule then packages and uploads this batch of real-time blood glucose curves and blood pressure fluctuation data, including timestamps, to the cloud.

[0051] The data integration submodule continuously receives data uploaded by the patient-side input submodule. It cleans and standardizes the data, then stores it in a database. Finally, it integrates personal information, disease data, clinical indicators, and dynamic physiological signals into a standardized, patient-specific dataset (Patient A), which is securely stored as the data foundation for subsequent protocol generation.

[0052] The personalized diet plan generation module is communicatively connected to the data acquisition and integration module to receive the patient-specific dataset. Based on a medical rule base and the specific dataset, it calculates and generates an initial diet plan, which is then reviewed by the medical staff to form the final plan. The diet plan execution support module includes a medical rule base invocation submodule, a plan generation engine submodule, a meal design submodule, and a medical staff review submodule.

[0053] The medical rule base calling submodule has a built-in rule base based on clinical dietary guidelines, which is used to extract nutrient intake constraints according to the patient's chronic disease type.

[0054] The scheme generation engine submodule communicates with the system data integration submodule and the medical rule base calling submodule. It is used to receive the patient-specific dataset and the nutrient intake constraints, calculate the patient's daily nutritional needs, and allocate the nutrient ratio.

[0055] The meal design submodule is connected to the scheme generation engine submodule and is used to receive the nutrient ratio and convert the nutrient ratio into a specific meal allocation scheme and a food selection list.

[0056] The medical review submodule, connected to the meal design submodule, is used to receive the meal allocation plan and food selection list, and then send the generated diet plan to the doctor's or nutritionist's client for review and confirmation before pushing it to the patient's client.

[0057] The working process of the diet plan execution support module is as follows:

[0058] First, the medical rule base has the "Chinese Dietary Guidelines for Type 2 Diabetes" and the "Standardized Dietary Management of Hypertension" pre-built in, from which constraints are extracted, such as recommendations to control total calories, low-GI carbohydrates, and daily sodium intake.

[0059] Next, the solution generation engine submodule retrieves the "Type 2 Diabetes" and "Hypertension" tags from Patient A's specific dataset from the system data integration submodule, and performs calculations based on the aforementioned constraints. Based on the patient's height, their ideal weight is calculated to be 70 kg. Given Patient A's activity level as "light activity," the recommended daily total calorie intake is calculated using the formula (ideal weight × activity coefficient) to be 1750 kcal. Then, according to guidelines, the macronutrient ratios are allocated as follows: carbohydrates 45% (approximately 197g, choosing low-GI whole grains), protein 20% (87.5g / day, primarily high-quality protein), fat 35% (68g / day, strictly controlling saturated fat), and sodium intake ≤4g / day (approximately 10g salt). This calculation process simultaneously addresses the combined needs of "blood sugar control" and "sodium restriction."

[0060] The calculation results are passed to the meal design submodule. This submodule transforms the abstract nutrient ratios into a concrete, actionable allocation scheme of 3 main meals + 2 snacks. It generates a specific food selection list and uses a "traffic light" classification system for identification: green light foods are recommended, such as brown rice, oats, steamed fish, and plenty of vegetables; yellow light foods should be consumed in moderation, such as lean meat and fruit; and red light foods are strictly limited, such as braised pork, pickled foods, and sugary drinks. Simultaneously, to accommodate the patient's existing dietary habits, the plan suggests replacing "braised meat" with "steaming or stewing" to reduce hidden salt intake.

[0061] The medical-side review submodule pushes the generated initial diet plan to the medical-side application of patient A's attending physician or clinical nutritionist. The physician reviews the plan's scientific validity and suitability on the medical-side application, and may make minor adjustments to the ingredients of a particular meal based on their clinical experience, before finally clicking the "Confirm" button. The final approved plan is immediately pushed back to patient A's mobile app by the server.

[0062] The diet plan execution support module is communicatively connected to the personalized diet plan generation module to receive the final plan, and is used to assist users in executing the diet plan through visualization tools, recipe library and intelligent recording methods; the diet plan execution support module includes a visualization tool submodule, a recipe library submodule, an intelligent recording submodule and an execution feedback submodule.

[0063] The visualization tool submodule is used to provide a visual reference standard for food portion sizes.

[0064] The recipe library submodule is used to provide detailed recipe templates.

[0065] The intelligent recording submodule includes an image recognition unit and an IoT device interface. The image recognition unit includes a camera for identifying the types of food in a meal image and estimating their weight. The IoT device interface is used to connect to smart kitchen appliances to obtain data on the amount of ingredients used.

[0066] The execution feedback submodule is used to receive subjective adaptive feedback from users on the execution process of the solution.

[0067] The working method of the diet plan execution support module is as follows:

[0068] Patient A views the final plan through the app. The diet plan execution support module provides various tools to assist in its implementation. The visualization tool submodule displays food portion sizes visually, such as using animations to demonstrate common reference points like fists and palms, helping the patient intuitively judge food weight and manage portion sizes. The recipe library submodule provides replaceable weekly recipe templates, detailing the types and specific weights of ingredients for breakfast, lunch, dinner, and snacks, along with "low-salt, low-oil" cooking suggestions.

[0069] During actual mealtimes, the intelligent recording submodule records daily meals. For example, patient A takes a photo of their plate with their phone's camera before lunch and uploads it. The image recognition unit, based on an AI model integrated into the app, analyzes the photo, identifying that it contains "approximately 150g of brown rice," "approximately 120g of steamed sea bass," and "approximately 200g of stir-fried spinach," and automatically estimates the weight, recording it in the food log. For higher accuracy, the IoT device interface in the intelligent recording submodule is configured to support the Bluetooth protocol, enabling it to pair with and receive precise measurement data from compatible devices such as kitchen scales and smart salt spoons.

[0070] The execution feedback submodule collects patient A's subjective feelings through a questionnaire within the app, such as "feeling full after lunch" or "feeling that the portions in the menu were too small and I wasn't full." These subjective experience data, together with the objective dietary record data, constitute the data for the program execution process.

[0071] The monitoring and dynamic adjustment module is communicatively connected to the diet plan execution support module and the data acquisition and integration module to receive the execution process data and updated physiological indicator data. It is used to collect user diet execution data and physiological indicator data, analyze their correlation through machine learning algorithms, generate adjustment suggestions, and update the plan after confirmation by the medical end. The monitoring and dynamic adjustment module includes: a data monitoring submodule, a correlation analysis submodule, and a plan adjustment engine submodule.

[0072] The data monitoring submodule is communicatively connected to the intelligent recording submodule and the patient-side data input submodule, and is used to continuously collect user diet execution data and physiological indicator change data.

[0073] The correlation analysis submodule is connected to the data monitoring submodule and uses machine learning algorithms to analyze the correlation between fluctuations in physiological indicators and dietary behavior.

[0074] The proposed adjustment engine submodule is connected to the correlation analysis module. It is used to generate dietary plan adjustment suggestions based on the analysis results and send them to the medical end review submodule for confirmation and plan update.

[0075] The working method of the monitoring and dynamic adjustment module is as follows:

[0076] The data monitoring submodule obtains daily dietary logs from the intelligent recording submodule and synchronizes the latest dynamic physiological indicators from the patient-side data input submodule.

[0077] The correlation analysis submodule analyzed historical data accumulated by patient A over a period of time. It was found that patient A's average postprandial blood glucose level had significantly decreased from 11.2 mmol / L to 9.0 mmol / L, indicating that the blood sugar control diet was effective; however, the improvement in her morning blood pressure was not significant and remained higher than the expected target.

[0078] Based on the analysis results of the correlation analysis submodule, the scheme adjustment engine submodule automatically generates adjustment suggestions, such as: "The patient's blood pressure control is not as expected, and excessive sodium intake is suspected. Suggestions: 1. Add high-potassium foods to the diet to promote sodium-potassium balance; 2. Push low-sodium seasoning recipes; 3. Strengthen education on identifying sodium in packaged foods." The adjustment suggestions are then sent to the medical end review submodule.

[0079] After reviewing the suggestion and the underlying data analysis report on the medical end, the nutritionist deemed the suggestion reasonable and approved it. The system then triggered a plan update process, and the personalized diet plan generation module fine-tuned patient A's diet based on the new instructions, thus achieving a closed loop from monitoring and analysis to adjustment.

[0080] The system also includes a patient education and support module, which is used to push dietary knowledge content to users and provide a platform for doctor-patient interaction. The patient education and support module includes a knowledge push submodule and an interactive support submodule.

[0081] The knowledge push submodule is used to regularly push dietary science content to patients based on their disease type.

[0082] The interactive support submodule is used to provide an online communication platform for patients and nutritionists, as well as a community exchange platform among patients.

[0083] The working method of the patient education and support module is as follows:

[0084] The knowledge push submodule regularly pushes popular science articles to Patient A's APP based on Patient A's disease type, such as "Ten Common Misconceptions about Diabetic Diets" and "How Hypertensive Patients Can Eat Healthily." The interactive support submodule provides an online community where Patient A can exchange experiences with other patients or ask questions directly to nutritionists.

[0085] In summary, the system provided in this embodiment achieves end-to-end chronic disease dietary management through the aforementioned modular and process-oriented collaborative work, encompassing data collection, intelligent solution generation, monitoring and analysis, and dynamic adjustment and optimization.

Claims

1. A dietary management system for patients with chronic diseases, characterized in that, include: The data acquisition and integration module is used to acquire and integrate multi-source data to form a patient-specific dataset; The personalized diet plan generation module is communicatively connected to the data acquisition and integration module to receive the patient-specific dataset, and to calculate and generate an initial diet plan based on the medical rule base and the specific dataset, which is then reviewed by the medical end to form the final plan; The diet plan execution support module is communicatively connected to the personalized diet plan generation module to receive the final plan, and is used to assist users in adjusting their diet plans through visualization tools, recipe libraries and intelligent recording methods; The monitoring and dynamic adjustment module is communicatively connected to the diet plan execution support module and the data acquisition and integration module. It is used to collect user diet execution data and physiological indicator data, analyze their correlation through machine learning algorithms, generate adjustment suggestions, and update the plan after confirmation by the medical end.

2. The dietary management system for patients with chronic diseases according to claim 1, characterized in that, The data acquisition and integration module includes: The patient-side data input submodule and the patient-side condition reporting submodule are configured with a user interface for receiving basic information and condition information input by the user through the user interface. The medical data interface submodule is configured with a medical data interface for automatically obtaining clinical diagnostic data from the hospital's electronic medical record system. The system data integration submodule is communicatively connected to the patient-side data input submodule, the patient-side condition reporting submodule, and the medical-side data interface submodule. It is used to receive and integrate data from the above submodules, perform cleaning and standardization processing, and store the data in the database to form a patient-specific dataset.

3. The dietary management system for patients with chronic diseases according to claim 2, characterized in that, The personalized diet plan generation module includes: The medical rule base calling submodule has a built-in rule base based on clinical dietary guidelines, which is used to extract nutrient intake constraints according to the patient's chronic disease type. The scheme generation engine submodule communicates with the system data integration submodule and the medical rule base calling submodule. It is used to calculate daily nutritional requirements and allocate nutrient ratios based on patient data and constraints. It is also used to receive the patient-specific dataset and the nutrient intake constraints, and calculate the patient's daily nutritional requirements and allocate nutrient ratios. The meal design submodule is connected to the scheme generation engine submodule and is used to receive the nutrient ratio and convert the nutrient ratio into a specific meal allocation scheme and a food selection list. The medical review submodule, connected to the meal design submodule, is used to receive the meal allocation plan and food selection list, and then send the generated diet plan to the doctor's or nutritionist's client for review and confirmation before pushing it to the patient's client.

4. The dietary management system for patients with chronic diseases according to claim 3, characterized in that, The diet plan execution support module includes: The visualization tools submodule is used to provide a visual reference standard for food portion sizes; The recipe library submodule provides detailed recipe templates; The intelligent recording submodule includes an image recognition unit and an IoT device interface. The image recognition unit includes a camera for identifying the types of food in a food image and estimating their weight. The IoT device interface is used to connect to smart kitchen appliances to obtain data on the amount of ingredients used. The execution feedback submodule is used to receive subjective adaptive feedback from users on the implementation process of the solution.

5. A dietary management system for patients with chronic diseases according to claim 4, characterized in that, The monitoring and dynamic adjustment module includes: The data monitoring submodule is communicatively connected to the intelligent recording submodule and the patient-end data input submodule, and is used to continuously collect user diet execution data and physiological indicator change data. The correlation analysis submodule, connected to the data monitoring submodule, uses machine learning algorithms to analyze the correlation between fluctuations in physiological indicators and dietary behavior; The plan adjustment engine submodule is connected to the correlation analysis module. It is used to generate dietary plan adjustment suggestions based on the analysis results and send them to the medical end review submodule for confirmation and plan update.

6. A dietary management system for patients with chronic diseases according to claim 1, characterized in that, It also includes a patient education and support module, used to push dietary knowledge content to users and provide a platform for doctor-patient interaction and communication. The patient education and support module includes: The knowledge push submodule is used to regularly push dietary science content to patients based on their disease type. The interactive support submodule provides a platform for online communication between patients and nutritionists, as well as a community exchange platform among patients.

7. A dietary management system for patients with chronic diseases according to claim 2, characterized in that, The standard medical data interface includes an HL7 interface or an FHIR interface.

8. An electronic device comprising at least one processor and a memory, characterized in that, The memory stores a computer program, which, when executed by the processor, implements the module functions of the dietary management system for chronic disease patients as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the module functions of the dietary management system for chronic disease patients as described in any one of claims 1 to 7.

Images