Mobile chronic health management system based on large language model

Abstract

The invention discloses a mobile chronic health management system based on a large language model, and relates to the technical field of medical information, and the application comprises six main modules: a user interface module which is developed by adopting a Flutter front-end technology, allows a patient to input hypertension, diabetes and health data related to movement and sleep, checks a health data chart, and sends the health data to a central processing module; health questions and answers are carried out through a large language model; the logic control module is developed on the basis of a SpringBoot framework and is responsible for processing business logic and data interaction, providing a RESTfulAPI interface, managing addition, deletion, modification and check of health data, processing a data analysis request and calling a large language model; the database module is used for storing and managing system data by adopting a MySQL relational database; the big language model module is used for providing a health question and answer function based on the basic information and health data of the patient by utilizing a deep learning framework and a pre-trained big language model, and providing suggestions in the aspect of diet; the push reminding module is used for pushing notices through the system and reminding the patient to take medicine on time and perform physical examination; and the electronic case module allows the patient to edit and upload the personal medical information, and manages the personal medical information in a centralized manner. And intelligent management of chronic disease patients is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a mobile chronic health management system based on a large language model. Background Art

[0002] With the continuous development of social economy and the increasingly prominent trend of population aging, chronic diseases have become one of the major challenges facing the health field in China and even the world. Globally, chronic diseases are the main cause of death, especially cardiovascular diseases (such as hypertension), cancer, chronic respiratory diseases and diabetes. According to the World Health Organization, non-communicable diseases cause about 41 million deaths each year, accounting for 74% of all deaths worldwide. Among them, 17 million people die from non-communicable diseases before the age of 70 each year. Although the age-standardized mortality rate of the four major chronic diseases in people aged 30 to 70 in China has declined between 1990 and 2019, the total number of deaths from these diseases is still expected to increase from about 2.9612 million in 2020 to about 3.1850 million by 2030. This shows that at the current rate of progress, China may find it difficult to achieve the Sustainable Development Goal of reducing premature deaths from non-communicable diseases by 2030.

[0003] At the same time, chronic diseases have had a profound impact on the social economy. They not only increase the burden on the healthcare system, leading to a substantial increase in national and family expenditures on medical expenses, but also significantly reduce labor productivity, affecting overall economic development. People with chronic diseases often require long-term treatment and care, which not only reduces their working time and efficiency, but may also lead to poverty due to illness, further exacerbating social inequality. In addition, chronic diseases also affect the education system, because family members who are ill or caring for patients may not be able to fully participate in education and vocational training, limiting the development of human resources. This is particularly evident in low-income and middle-income countries, where medical resources are limited and the high incidence of chronic diseases puts greater pressure on the public health system and hinders sustainable economic growth. Therefore, it is particularly important to strengthen attention to chronic diseases and effectively manage them.

[0004] Chronic diseases are a major health problem threatening global public health, and their management faces many challenges, including lack of initiative from patients, insufficient medical resources, and lack of personalized management plans. Summary of the invention

[0005] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a mobile chronic health management system based on a large language model.

[0006] In the first aspect, the purpose of the present invention can be achieved by the following technical solution: A mobile chronic health management system based on a large language model, comprising:

[0007] A user interface module for storing the input patient health-related data and enabling users to conduct health Q&A through a large language model;

[0008] A logic control module for processing business logic and data interaction, providing a RESTful API interface, receiving and managing the addition, deletion, modification, and query of patient health-related data within the user interface module, processing data analysis requests, and invoking the large language model;

[0009] A database module for obtaining system data, storing and managing system data through a MySQL relational database, where the system data includes patient basic information, health data, historical Q&A records, and system logs;

[0010] A large language model module for obtaining patient health-related data within the user interface module and patient basic information within the database, performing health advice and risk prediction based on a deep learning framework and a pre-trained large language model, and sending them to the push reminder module;

[0011] A push reminder module for reminding patients to take medicine on time and have physical examinations based on health advice and risk prediction, and pushing health-related advice and the latest disease prevention and control information;

[0012] An electronic medical record module for patients to edit and upload historical medical records, medical images, medication information, surgical history, and disease history, and centrally manage personal medical information.

[0013] Combined with the first aspect, in some implementation manners of the first aspect, the system further includes: The user interface module is cross-platform compatible through the Flutter framework and supports iOS and Android operating systems.

[0014] Combined with the first aspect, in some implementation manners of the first aspect, the system further includes: The logic control module uses the SpringBoot framework to build the server side and provides business logic processing and data interaction capabilities.

[0015] Combined with the first aspect, in some implementation manners of the first aspect, the system further includes: The MySQL database structure design in the database module includes a patient basic information table, a health data table, a historical Q&A record table, and a system log table.

[0016] Combined with the first aspect, in some implementation manners of the first aspect, the system further includes: The large language model module based on the deep learning framework and the pre-trained large language model understands and generates patient health Q&A content through natural language processing technology, and combines with a dietary picture analysis module to provide dietary advice.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: The push reminder module includes a timed reminder function and an event-triggered reminder function. The timed reminder function is used to remind patients to take medicine on time and have physical examinations regularly, and the event-triggered reminder function is used to push corresponding health suggestions and disease prevention and control information according to changes in the patients' health data.

[0018] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: The large language model module performs risk prediction based on the patients' historical health data, identifies potential health risks, and presents them to the patients in the form of charts or warning messages in the user interface module.

[0019] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: The push reminder module further includes a health knowledge push function, which regularly pushes the latest health knowledge and disease prevention and control information to patients to help them pay attention to their own health.

[0020] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: It also includes a data analysis module, which can statistically analyze the collected health data, generate trend charts, assist patients and medical staff in making health management decisions, and through the health data import and export function, allows patients to exchange health data with other health management platforms.

[0021] Advantages of the present invention:

[0022] Compared with traditional machine learning and natural language processing technologies, the large language model of the present invention has significant advantages in terms of knowledge volume and understanding ability. It can understand and generate natural language, provide more accurate and user-friendly health suggestions, and significantly improve the intelligent level of the system. At the same time, by analyzing detailed health data and historical medical information, the large language model can provide personalized health suggestions and risk predictions, helping patients formulate scientific health management plans and improving the effect of disease management.

[0023] In addition, the intelligent dietary analysis function can not only identify food types but also evaluate their nutritional components by analyzing dietary pictures, providing scientific and reasonable diet suggestions for patients and promoting the formation of healthy eating habits. The push reminder module promotes patients to take health management measures in a timely manner and improves the compliance of health management by actively pushing various health management reminders and the latest disease prevention and control information. The electronic case module realizes the centralized management of patients' personal medical information, facilitating patients to view and update their health records at any time, and also helping medical institutions better understand the health status of patients and provide targeted medical services.

[0024] In terms of data security and privacy protection, the present invention attaches great importance to ensuring that patients' personal health information is not leaked or misused through security authentication and access control, meeting the requirements of relevant laws and regulations. Multilevel security measures are adopted in the system design to comprehensively protect the security and privacy of data from data transmission, storage to access rights.

[0025] The mobile chronic health management application based on the large language model of the present invention, with its intelligent, personalized and comprehensive features, can effectively improve the health management level of chronic disease patients, reduce the incidence of disease complications, and improve the quality of life of patients. At the same time, the popularization and application of this platform can also relieve the pressure on medical institutions, optimize the allocation of medical resources, with broad market prospects and significant social benefits. By integrating large language model technology with the mobile health management system, the present invention innovatively breaks through the traditional health management model and provides an efficient, intelligent and comprehensive chronic disease management solution, with important practical value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0027] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0028] Figure 2 It is a blood glucose management interface diagram of the present invention;

[0029] Figure 3 It is a blood pressure management interface diagram of the present invention;

[0030] Figure 4 It is an AI intelligent Q&A interface diagram of the present invention;

[0031] Figure 5 It is a sleep management and exercise management interface diagram of the present invention;

[0032] Figure 6 It is a schematic diagram of the electronic medical record of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0034] As Figure 1 shown, a mobile chronic health management system based on a large language model includes:

[0035] A user interface module for storing the input patient health-related data and enabling the user to conduct health Q&A through the large language model;

[0036] The user interface module is cross-platform compatible through the Flutter framework and supports iOS and Android operating systems.

[0037] A logic control module for processing business logic and data interaction, providing a RESTful API interface, receiving and managing the addition, deletion, modification, and query of patient health-related data in the user interface module, processing data analysis requests, and invoking the large language model;

[0038] The logic control module uses the SpringBoot framework to build the server side, providing efficient business logic processing and data interaction capabilities.

[0039] A database module for obtaining system data, storing and managing system data through a MySQL relational database, where the system data includes patient basic information, health data, historical Q&A records, and system logs;

[0040] The MySQL database structure design in the database module includes a patient basic information table, a health data table, a historical Q&A record table, and a system log table to ensure the systematic management and efficient retrieval of data.

[0041] A large language model module for obtaining patient health-related data in the user interface module and patient basic information in the database, making health suggestions and risk predictions based on a deep learning framework and a pre-trained large language model, and sending them to the push reminder module;

[0042] The large language model module is based on a pre-trained deep learning model, can understand and generate patient health Q&A content through natural language processing technology, and provides diet suggestions in combination with a dietary picture analysis module.

[0043] The large language model module can perform risk prediction based on the patient's historical health data, identify potential health risks, and display them to the patient in the form of charts or warning messages in the user interface module.

[0044] The large language model module can continuously optimize the accuracy and personalization of health suggestions through continuous learning and data update, improving the intelligent level of the system.

[0045] A push reminder module, which is used to remind patients to take medicine on time and have physical examinations based on health advice and risk predictions, and push health-related advice and the latest disease prevention and control information;

[0046] The push reminder module includes a timing reminder function and an event-triggered reminder function. The former is used to remind patients to take medicine on time and have physical examinations at regular intervals, and the latter is used to push corresponding health advice and disease prevention and control information according to the changes in the patients' health data.

[0047] An electronic case module, which is used to centrally manage personal medical information by allowing patients to edit and upload historical medical records, medical images, medication information, surgical history, and disease history.

[0048] The electronic case module supports the upload of multiple file formats, including but not limited to PDF, JPEG, PNG, etc., to ensure that patients can conveniently upload various medical documents and imaging materials.

[0049] The system uses a security authentication and permission control module to ensure the privacy and security of patients' data and prevent unauthorized access and data leakage.

[0050] It also includes a data analysis module that can statistically analyze the collected health data, generate trend charts, and assist patients and medical staff in making health management decisions. By integrating a large language model, it can identify the emotional state of patients based on their input content and provide corresponding emotional support suggestions. The system also integrates a health data import / export function, allowing patients to exchange health data with other health management platforms to improve data interoperability and application flexibility.

[0051] Specifically, the solution of the present invention will be further elaborated through the following embodiments:

[0052] (1) To implement a mobile chronic health management application based on a large language model, the system architecture adopts a modular design to ensure that the functions of each part are both independent and can work together. The entire health management platform mainly consists of a front-end user interface, back-end logic control, a database, a large language model service, a push reminder service, and an electronic case management module. The front and back ends communicate efficiently through RESTful APIs to ensure the timeliness and reliability of data transmission.

[0053] (2) In terms of module development and function implementation, the user interface module is developed using the Flutter framework to achieve cross-platform compatibility and ensure that the application can run smoothly on Android and iOS systems. This module focuses on the user experience, provides intuitive operation entrances, supports users to input health data such as blood pressure, blood sugar, exercise volume, and sleep quality, and displays the health data trends through charts and reports to help users and their medical teams understand the health status in a timely manner. In addition, the integrated natural language Q&A function allows users to obtain health advice in the form of conversations and supports the upload and analysis of dietary pictures. The backend logic control module is based on the Spring Boot framework, responsible for handling business logic and data interaction, and realizing functions such as addition, deletion, modification, query, and health analysis of health data through RESTful APIs. When processing health Q&A requests, this module calls the large language model service to generate intelligent answers and implements security authentication and permission control to ensure the security of the system.

[0054] (3) The database module adopts a MySQL relational database, which is responsible for storing the basic information of patients, daily health data, historical Q&A records, and system logs. The database design focuses on data integrity and traceability, supports efficient data query and analysis, and provides a solid foundation for system maintenance. The large language model module, as the core technology, uses pre-trained large language models for health data analysis and advice generation. Based on the health data of patients, the system can provide personalized health advice and dietary analysis, analyze the uploaded dietary pictures through image recognition technology, and identify food types and nutritional components.

[0055] (4) The push reminder module actively pushes medication reminders, regular check reminders, and personalized health advice to patients through the system notification function. According to the medication plan and health data of patients, customized push content is provided to improve the compliance of patients' health management. At the same time, the latest disease prevention and control knowledge is pushed to enhance the health management awareness of patients. The electronic medical record module allows patients to record and upload detailed medical information, including medical records, medical images, medication history, etc., to realize the centralized management of personal medical information. This module supports patients to authorize medical professionals to access their electronic medical records, promotes the coordination and efficiency of medical services, and ensures the security of patients' information through strict access permission control.

[0056] (5) In terms of technology selection and tools, Flutter framework is adopted for front-end development to improve development efficiency and user experience; Spring Boot framework is used for back-end development to achieve efficient business logic processing and data interaction; MySQL, which is stable and reliable, is selected as the database, suitable for storing structured data. The large language model module is built based on PyTorch, and the pre-trained domestic Qianwen model is used for health data analysis and natural language generation. The image recognition function uses neural networks integrated with PyTorch or other image processing libraries to realize the recognition and analysis of dietary pictures. The push service adopts Python's web crawling technology to capture the latest disease control news on open-source websites and push it to users in real time for them to actively pay attention to health.

[0057] (6) In terms of data processing and management, the system ensures the security of data transmission through encryption protocols such as HTTPS. All sensitive data is encrypted before storage, and strict access control mechanisms are adopted for database access to prevent unauthorized access. The system performs regular data backups to ensure data integrity and recoverability, and effectively protects user privacy.

[0058] (7) Security measures include adopting a multi-factor authentication mechanism to ensure the authenticity of user identities. Different user roles, such as patients and administrators, are assigned different permissions to control the scope of data access. SSL / TLS encryption is used during transmission, and sensitive data is encrypted during storage to avoid data leakage. The system also records operation logs and conducts regular reviews to detect potential security threats and abnormal behaviors.

[0059] (8) The development process is carried out in stages. The front-end builds the user interface based on Flutter, and the back-end uses Spring Boot to implement business logic, integrating the large language model and image recognition functions. The testing stage includes unit testing, integration testing, performance testing, and security testing to ensure the correctness of each module's functions and the stability of the system.

[0060] (9) In terms of deployment and maintenance, the back-end part is deployed in the cloud. Alibaba Cloud Object Storage is used to store medical imaging data, and Cloud RDS database is used to store the key data and information of patients, administrators, and the system. The front-end part is integrally deployed using domestic tablets, which can be used immediately after startup, facilitating patients' operation and use.

[0061] Through the above specific implementation plans, the mobile chronic health management application based on the large language model will achieve the goal of perfect functions and user-friendliness, significantly improve the health management level of chronic disease patients, optimize the allocation of medical resources, and have broad market prospects and significant social benefits. In the future, with the continuous progress of technology and the change of user needs, the system will continue to iterate and upgrade, maintain its leading edge, and achieve innovative breakthroughs in the field of health management.

[0062] Based on the same inventive concept, the present invention further provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is configured to execute the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is used to implement one or more instructions. Specifically, it is used to load and execute one or more instructions in the computer storage medium to implement the above method.

[0063] It should be further noted that, based on the same inventive concept, the present invention further provides a computer storage medium, on which a computer program is stored, and the computer program, when run by a processor, executes the above method. The storage medium may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, apparatus, or device.

[0064] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0065] The foregoing has shown and described the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure will also have various changes and improvements, and these changes and improvements all fall within the scope of the present disclosure claimed.

Claims

1. A mobile chronic health management system based on a large language model, characterized in that: include: A user interface module, which is used to store the input patient health-related data and enable users to conduct health questions and answers through a large language model; The logic control module is used to process business logic and data interaction, provide a RESTful API interface, receive and manage the addition, deletion, modification and query of patient health-related data in the user interface module, process data analysis requests, and call the large language model; The database module is used to obtain system data and store and manage system data through the MySQL relational database, wherein the system data includes basic patient information, health data, historical question and answer records, and system logs; The large language model module is used to obtain the patient health-related data in the user interface module and the patient's basic information in the database, make health recommendations and risk predictions based on the deep learning framework and pre-trained large language model, and send them to the push reminder module; Push reminder module, which is used to remind patients to take medication and undergo physical examinations on time based on health advice and risk prediction, and push health-related advice and the latest disease prevention and control information; The electronic medical record module is used to centrally manage personal medical information by allowing patients to edit and upload historical medical records, medical images, medication information, surgical history and disease history.

2. A mobile chronic health management system based on a large language model according to claim 1, characterized in that: The user interface module achieves cross-platform compatibility through the Flutter framework and supports iOS and Android operating systems.

3. According to claim 1, a mobile chronic health management system based on a large language model is characterized in that: The logic control module uses the SpringBoot framework to build the server side and provide business logic processing and data interaction capabilities.

4. According to claim 1, a mobile chronic health management system based on a large language model is characterized in that: The MySQL database structure design in the database module includes a patient basic information table, a health data table, a historical question and answer record table, and a system log table.

5. The mobile chronic health management system based on a large language model according to claim 1 is characterized in that: The large language model module, which is based on a deep learning framework and pre-trained large language model, uses natural language processing technology to understand and generate health question and answer content for patients, and provides dietary recommendations in combination with a dietary picture analysis module.

6. The mobile chronic health management system based on a large language model according to claim 1, characterized in that: The push reminder module includes a timed reminder function and an event-triggered reminder function. The timed reminder function is used to regularly remind patients to take medications and undergo physical examinations on time, and the event-triggered reminder function is used to push corresponding health advice and disease prevention and control information based on changes in the patient's health data.

7. The mobile chronic health management system based on a large language model according to claim 1, characterized in that: The large language model module performs risk prediction based on the patient's historical health data, identifies potential health risks, and displays them to the patient in the form of charts or warning messages in the user interface module.

8. The mobile chronic health management system based on a large language model according to claim 7, characterized in that: The push reminder module also includes a health knowledge push function, which regularly pushes the latest health knowledge and disease prevention and control information to patients to help patients pay attention to their own health.

9. The mobile chronic health management system based on a large language model according to claim 1, characterized in that: It also includes a data analysis module that can perform statistical analysis on the collected health data, generate trend charts, assist patients and medical staff in making health management decisions, and allow patients to exchange health data with other health management platforms through the health data import and export function.

Images