AI-based health management method and system

Abstract

The invention provides an AI-based health management method and system, and the method comprises the steps: carrying out the analysis of diagnosis data based on a preset AI large language model if the diagnosis data of a medical worker for a user is obtained, so as to generate a diagnosis instruction which is convenient for the user to understand; displaying the diagnosis description to the user; generating a health management plan based on the diagnosis data and pre-acquired physical state data of the user; and executing the health management plan aiming at the user to perform health reminding and / or health description on the user. According to the method, the deep learning of the AI large language model and the natural language processing capability are fused, and professional medical terms and detection results are automatically converted into forms easy to understand, so that doctor-patient communication obstacles are reduced, and the diagnosis and treatment efficiency is improved; and through AI personalized medication reminding and life guidance, the patient is helped to better follow medical advices, the treatment effect is improved, the disease recurrence rate is reduced, and improvement of the disease cognition level of the patient and implementation of health management are facilitated.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an AI-based health management method and system. Background Art

[0002] In the current traditional offline medical treatment scenario, doctors are often unable to provide patients with sufficient explanations and guidance due to time constraints. At the same time, patients do not understand many terms, indicators, and explanations of terms for existing diseases. In this case, patients often find it difficult to obtain sufficient disease knowledge and medication guidance, which can easily lead to questions and confusion during the treatment process. This leads to patients not having a deep understanding of their own diseases, test indicators, and medication side effects. In addition, after obtaining treatment advice, patients tend to forget their medication plans, and lack guidance on diet and life, which is not conducive to their recovery. Summary of the invention

[0003] In view of this, this application proposes an AI-based health management method and system, the specific scheme is as follows:

[0004] In the first part, this application proposes an AI-based health management method, which includes:

[0005] If the medical staff obtains the diagnostic data for the user, the diagnostic data is parsed based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand;

[0006] presenting the diagnostic description to the user;

[0007] generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user;

[0008] The health management plan is executed for the user to provide health reminders and / or health instructions to the user.

[0009] In a specific embodiment, the diagnostic data includes: diagnostic audio data dictated by a medical professional;

[0010] The “analyzing the diagnostic data based on a preset AI large language model to generate a diagnostic description that is easy for the user to understand” includes:

[0011] Convert the diagnostic audio data based on a preset AI large language model to generate text data;

[0012] The text data is semantically recognized and colloquially processed to generate a diagnosis description that is easy for the user to understand.

[0013] In a specific embodiment, the diagnostic data includes: medical record related data output by medical personnel; the medical record related data includes: disease diagnosis, laboratory test results, one or any multiple of imaging data;

[0014] The “analyzing the diagnostic data based on a preset AI large language model to generate a diagnostic description that is easy for the user to understand” includes:

[0015] A preset AI large language model connected to a preset medical database is used to parse the medical record-related data to generate a diagnosis description that is easy for the user to understand; the diagnosis description includes: a description of the user's physical condition information and / or health precautions.

[0016] In a specific embodiment, presenting the diagnosis description to the user specifically includes:

[0017] The diagnostic description is presented to the user in text, and / or voice, and / or image, and / or audio form.

[0018] In a specific embodiment, the “generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user” specifically includes:

[0019] Automatically generate a medication plan, and / or dietary advice, and / or a life guide for the user based on the latest diagnostic data and the latest pre-acquired physical condition data of the user;

[0020] The “executing the health management plan for the user” includes:

[0021] Providing medication reminders based on the medication plan in the health management plan and the current time point; and / or

[0022] Providing dietary reminders based on the dietary recommendations in the health management plan and the current time point; and / or

[0023] Life reminders are provided based on the life guidelines in the health management plan and the current time point and environment.

[0024] In a specific embodiment, the health management plan includes: a health education plan and a health consultation plan;

[0025] The “executing the health management plan for the user” includes:

[0026] According to the disease progression in the user's physical condition data, popular science articles, and / or video tutorials, and / or online expert Q&A resources related to the user's diagnostic data are regularly pushed to promote the user's self-management and disease recovery.

[0027] In a specific embodiment, it also includes:

[0028] One or any multiple of the diagnostic data, the diagnostic description, and the health management plan are associated with the user and stored.

[0029] In a specific embodiment, the “generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user” includes:

[0030] A health management plan is generated based on the diagnosis data within a first preset time period closest to the current time and the user's physical condition data within a second preset time period closest to the current time.

[0031] In a specific embodiment, it also includes:

[0032] If new diagnostic data or new physical condition data is obtained, the step of "generating a health management plan based on the diagnostic data and the user's physical condition data obtained in advance" is repeatedly executed.

[0033] In the second part, this application proposes an AI-based health management system, which is characterized by including:

[0034] A parsing module is used to parse the diagnostic data of the user obtained by the medical staff based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand;

[0035] A display module, used for displaying the diagnosis description to the user;

[0036] A generating module, configured to generate a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user;

[0037] The reminder module is used to execute the health management plan for the user to provide health reminders and / or health instructions to the user.

[0038] Beneficial effects:

[0039] This application integrates the deep learning and natural language processing capabilities of the AI ​​large language model to automatically convert professional medical terms and complex test results into a form that is easy for users to understand, reducing communication barriers between doctors and patients and improving diagnosis and treatment efficiency; and through AI personalized medication reminders and life guidance, it helps patients better follow doctor's orders, improve treatment effects, and reduce disease recurrence rates, which effectively promotes the improvement of patients' disease awareness and the implementation of daily health management, demonstrating obvious social value and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of the AI-based health management method of an embodiment of the present application;

[0041] Figure 2 This is a schematic diagram of an AI-based health management system module according to an embodiment of the present application;

[0042] Figure 3 is a flow chart of generating a health management plan according to an embodiment of the present application;

[0043] Figure 4 This is a schematic diagram of data sources for generating a health management plan in an embodiment of the present application.

[0044] Figure numerals: 1-analysis module; 2-display module; 3-generation module; 4-reminder module. DETAILED DESCRIPTION

[0045] Hereinafter, various embodiments disclosed in the present application will be described more fully. The present application may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments disclosed in the present application to the specific embodiments disclosed herein, but the present application should be understood to cover all adjustments, equivalents and / or alternatives falling within the spirit and scope of the various embodiments disclosed in the present application.

[0046] The terms used in the various embodiments disclosed in the present application are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments disclosed in the present application. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise specified, all terms used here (including technical terms and scientific terms) have the same meaning as the meaning generally understood by ordinary technicians in the field of various embodiments disclosed in the present application. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments disclosed in the present application.

[0047] Example 1

[0048] Example 1 of the present application discloses an AI-based health management method. This embodiment integrates the deep learning of the AI ​​large language model with the natural language processing capability to automatically convert professional medical terms and complex test results into a form that is easy for users to understand, thereby reducing the communication barriers between doctors and patients and improving the efficiency of diagnosis and treatment. It also helps patients better follow doctor's orders, improve treatment effects, and reduce the recurrence rate of diseases through personalized AI medication reminders and life guidance, which effectively promotes the improvement of patients' disease cognition level and the implementation of daily health management, demonstrating obvious social value and economic benefits. The specific process is as attached to the specification. Figure 1 and attached Figure 3 The specific plan is as follows:

[0049] An AI-based health management method, as shown in the attached manual Figure 1 As shown, the method includes:

[0050] 101. If the medical staff obtains the diagnostic data for the user, the diagnostic data is parsed based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand;

[0051] 102. Display the diagnostic instructions to the user;

[0052] 103. Generate a health management plan based on the diagnostic data and the user's physical condition data acquired in advance;

[0053] 104. Implement a health management plan for the user to provide health reminders and / or health instructions to the user.

[0054] The AI-based health management method of this embodiment is applicable to a variety of scenarios, including but not limited to medical institutions, health management platforms, research institutions or individual users. For example, in hospital information systems, health monitoring equipment, disease research projects or personal health management applications, the AI-based health management method of this embodiment can be incorporated into the health management system to provide more accurate and personalized health management and services.

[0055] 101. If the diagnostic data of the medical staff for the user is obtained, the diagnostic data is parsed based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand. When the detailed diagnostic data of the medical staff for the user is successfully obtained, in practical applications, these data often contain professional medical terms, complex detection indicators, and detailed descriptions of the condition. However, for ordinary users, directly understanding these raw data may be a difficult task because medical knowledge is often profound and professional. In order to solve this problem, this embodiment uses a pre-trained AI large language model to parse the diagnostic data. The AI ​​large language model (Large Language Model, LLM) is an artificial intelligence model based on deep learning technology. It uses a large amount of data for training, aims to understand and generate natural language text, and learns the grammar, semantics and context information of the language by training massive text data, so that natural language text can be modeled and generated. In this embodiment, this AI large language model is trained based on a large amount of medical knowledge, case data and expert experience, so it has a deep understanding and analysis capability of medical data.

[0056] When diagnostic data is input into the AI ​​big language model, the AI ​​big language model will first pre-process the data, including steps such as data cleaning, format conversion, and feature extraction to ensure the quality and accuracy of the data. Then, the AI ​​big language model will use its built-in algorithms and logic to conduct in-depth analysis and interpretation of the diagnostic data. During the parsing process, the AI ​​big language model will identify key information in the diagnostic data, such as the type of disease, location of the lesion, severity, etc., and generate a concise and clear diagnostic description based on this information. This description uses easy-to-understand language, avoiding excessive medical terms and complex descriptions, allowing users to easily understand their condition and diagnosis results.

[0057] Through this method, the originally complex medical diagnosis data is converted into diagnostic instructions that are easy for users to understand, thereby improving the efficiency of medical services and user satisfaction. At the same time, this also provides medical staff with more convenient and efficient diagnostic tools, which helps to improve the service quality and level of the entire medical industry.

[0058] 102. Display the diagnosis description to the user. After generating the above diagnosis description, display the diagnosis description to the user. In actual applications, it can be displayed to the user in a variety of ways, including but not limited to text, pictures, audio, video, etc., so that the user can understand his or her health status more intuitively. In addition, in actual applications, attention should be paid to the privacy and security issues of the user. When displaying the diagnosis description, it should be ensured that the user's personal information and medical data are properly protected and not obtained by unauthorized third parties. To this end, encryption technology, access control and other measures can be used to protect the security of user data.

[0059] Furthermore, it is possible to provide users with a convenient and fast feedback channel. In the process of understanding the diagnostic instructions, users may encounter questions or need further help. Therefore, online customer service, telephone hotlines or emails can be set up to answer users' questions in a timely manner to provide users with necessary support and guidance.

[0060] 103. Generate a health management plan based on the diagnostic data and the user's physical condition data acquired in advance. Figure 4 As shown, in actual applications, the user's diagnostic data and physical condition data can be obtained by the user logging into the health management system and manually entering data or directly obtaining data from the medical platform. The diagnostic data usually includes information such as the user's disease type, lesion site, and severity of the disease, while the physical condition data covers the user's basic physiological indicators such as weight, height, body fat percentage, blood pressure, and blood sugar.

[0061] Furthermore, these data can be used to generate a comprehensive and personalized health management plan for users. Advanced AI algorithms and medical knowledge bases are used to deeply mine and interpret these data. AI algorithms can identify key information and patterns in the data, while medical knowledge bases provide rich medical knowledge and experience. Combining the advantages of these two, users can be provided with accurate health risk assessments and personalized health management recommendations.

[0062] The first is disease prevention and treatment. According to the user's diagnostic data, detailed medication instructions and precautions are given, including medication time, dosage and possible side effects; at the same time, targeted preventive measures and health advice are provided to help users reduce the risk of disease. The second is lifestyle adjustment. According to the user's physical condition data and health needs, personalized diet plans, exercise plans, sleep plans, etc. are formulated for users. Finally, the above suggestions and plans are integrated into a comprehensive and personalized health management plan and presented to the user. The display method can be in various forms such as text description, chart display, video tutorial, etc., so that users can clearly and intuitively understand their health management plan.

[0063] 104. Execute health management plans for users to provide health reminders and / or health instructions to users. Health reminders are an important means to help users maintain the continuity and consistency of health management plans. In actual applications, you can set timed reminders according to the user's health management plan, such as daily breakfast reminders, timed medication reminders, exercise time reminders, etc.; regularly provide users with feedback on health management progress, such as weight changes, blood pressure improvements, etc.; provide relevant health reminders based on the user's daily life scenarios, for example, remind users to choose healthy foods when shopping in the supermarket, and remind users to pay attention to food ingredients and calorie intake when dining out, etc., to provide health reminders to users.

[0064] Health instructions are detailed guidance provided to help users better understand and follow health management plans. In actual applications, users can be briefly introduced to the goals, content and expected effects of the health management plan so that they have an overall understanding of the plan; detailed dietary recommendations can be provided to users, including daily calorie intake, nutrient ratios, food choices, etc. At the same time, personalized recipes can be formulated based on the user's taste preferences and eating habits; appropriate exercise plans can be formulated based on the user's physical condition and exercise goals, and detailed exercise guidance and precautions can be provided; for users who need drug treatment, detailed medication guidance can be provided, including the name, usage, dosage, side effects, etc. of the drug, and at the same time, the importance of taking medication as prescribed by the doctor should be emphasized to provide health instructions to users.

[0065] In one specific embodiment, the diagnostic data includes: diagnostic audio data dictated by a medical professional;

[0066] "Analyze diagnostic data based on a preset AI language model to generate diagnostic instructions that are easy for users to understand", including:

[0067] Convert diagnostic audio data based on a preset AI large language model to generate text data;

[0068] Semantic recognition is performed on text data and colloquial processing is performed to generate diagnostic instructions that are easy for users to understand.

[0069] In a specific embodiment, the diagnostic data includes diagnostic audio data spoken by medical staff. Such audio data often contains rich medical information and professional terms. For users with non-medical backgrounds, it may be difficult to directly understand the information in these audio data. Therefore, this embodiment uses a preset AI large language model to parse these diagnostic audio data to generate diagnostic instructions that are easy for users to understand.

[0070] First, based on the preset AI big language model, the diagnostic audio data is converted to generate corresponding text data. This AI big language model is usually trained with a large amount of medical diagnostic audio and corresponding text data, and can accurately convert the voice in the audio data into text. The text data is further semantically recognized and colloquially processed. Semantic recognition refers to the deep analysis and understanding of text data through natural language processing technology to identify key information such as medical terms, disease names, and symptom descriptions. This process requires the use of professional medical knowledge bases and dictionaries to ensure the accuracy of recognition. Colloquial processing is to reorganize the identified key information into a diagnostic description in plain language. This process needs to take into account the user's reading and comprehension ability, avoid using overly complex medical terms and sentences, and use simple and clear language and expressions. Through colloquial processing, the originally professional and difficult to understand diagnostic information can be converted into a language that is easy for users to understand, helping users better understand their health status.

[0071] In a specific embodiment, the diagnostic data includes: medical record related data output by medical personnel; the medical record related data includes: one or any multiple of disease diagnosis, laboratory test results, and imaging data;

[0072] "Analyze diagnostic data based on a preset AI language model to generate diagnostic instructions that are easy for users to understand", including:

[0073] The preset AI large language model connected to the preset medical database will parse the medical record-related data to generate a diagnosis description that is easy for the user to understand; the diagnosis description includes: user physical condition information description and / or health precautions.

[0074] In a specific embodiment, the diagnostic data mainly covers the medical record-related data output by medical staff. These medical record-related data not only record the user's medical history in detail, but also contain key medical information, such as disease diagnosis, laboratory test results, and imaging data. These data may involve professional medical terms and complex test results. For users with non-medical backgrounds, it may be difficult to directly understand this information. In order to convert these professional medical information into a form that is easy for users to understand, this embodiment adopts a method of parsing based on a preset AI large language model. This AI large language model not only has powerful data processing capabilities, but also accesses a preset medical database, providing rich medical knowledge and reference data for analysis.

[0075] During the parsing process, the AI ​​large language model first conducts a comprehensive analysis and understanding of the medical record-related data, extracting key information from disease diagnosis, laboratory test results, and imaging data. Then, combined with relevant knowledge in the medical database, this information is deeply analyzed and interpreted to generate a diagnostic description that is easy for users to understand. This parsing method based on the preset AI large language model can effectively convert complex medical record-related data into diagnostic descriptions that are easy for users to understand, providing users with a more convenient and efficient health management and service experience.

[0076] In a specific embodiment, presenting the diagnosis description to the user specifically includes:

[0077] The diagnostic instructions are presented to the user in the form of text, and / or voice, and / or image, and / or audio.

[0078] In this embodiment, in order to ensure that the user can fully and clearly understand the diagnosis description, a variety of display methods are used to present the diagnosis description to the user in one or more combinations of text, voice, image, and audio. In actual application, a suitable display method can be selected according to the user's personal preferences and needs, which can meet the needs and habits of different users and improve the user's understanding and acceptance of diagnostic information.

[0079] In a specific embodiment, “generating a health management plan based on diagnostic data and pre-acquired user's physical condition data” specifically includes:

[0080] Automatically generate a medication plan, and / or dietary advice, and / or a life guide for the user based on the latest diagnostic data and the latest user's physical condition data acquired in advance;

[0081] "Implement health management plans for users", including:

[0082] Medication reminders based on the medication plan in the health management plan and the current time point; and / or

[0083] Provide dietary reminders based on the dietary recommendations in the health management plan and the current time; and / or

[0084] Provide life reminders based on the life guidelines in the health management plan and the current time and environment.

[0085] In this embodiment, the system will collect and integrate the latest diagnostic data, which may come from the hospital's electronic medical records, laboratory test reports, imaging data, etc. At the same time, the system will also obtain the latest physical condition data pre-entered by the user or obtained with authorization, such as daily monitoring data such as weight, blood pressure, blood sugar, heart rate, etc. Next, the system will analyze and evaluate these comprehensive data using a preset algorithmic large language model. In this process, multiple factors such as the user's age, gender, genetic background, and lifestyle habits will be taken into account to ensure that the generated health management plan is highly targeted and personalized.

[0086] After analysis, the system will automatically generate a health management plan for the user, which includes but is not limited to medication plans, dietary advice and life guidelines. The medication plan will clearly list the name, dosage, and time of medication that the user needs to take; dietary advice will provide reasonable meal combinations and food choices based on the user's physical condition and nutritional needs; and the life guide will provide users with some advice and precautions for healthy living, such as exercise plans, work and rest schedules, and mental health.

[0087] Based on the medication plan in the health management plan and the current time point, the system will issue medication reminders to ensure that users take medications on time and in the right amount. Similarly, the system will also issue dietary reminders based on dietary recommendations and the current time point, reminding users to pay attention to healthy eating and avoid bad eating habits. In addition, the system will also provide life reminders based on the life guidelines in the health management plan and the current time point and environment. These reminders may include the execution of exercise plans, adjustment of work and rest schedules, maintenance of mental health, etc. The system will take into account the user's actual environment and conditions, and provide appropriate reminders and suggestions to help users better implement health management plans.

[0088] In a specific embodiment, the health management plan includes: a health education plan and a health consultation plan;

[0089] "Implement health management plans for users", including:

[0090] Based on the disease progression in the user's physical condition data, popular science articles, and / or video tutorials, and / or online expert Q&A resources related to the user's diagnostic data are regularly pushed to promote the user's self-management and disease recovery.

[0091] In a specific embodiment, the health management plan not only involves the daily life management and disease treatment of the user, but also includes the improvement of the user's health awareness and the popularization of professional knowledge. Therefore, the health management plan is divided into two main parts: a health education plan and a health consultation plan.

[0092] First of all, the health education program aims to improve users' awareness and management of their own health conditions through systematic and continuous educational means. This includes educating users on health knowledge popularization, healthy behavior cultivation, health risk assessment, etc. The system will regularly push popular science articles or video tutorials closely related to the user's diagnostic data based on the disease progression in the user's physical condition data. These articles and videos may involve knowledge on the causes, development process, treatment methods, preventive measures, etc. of the disease, aiming to help users better understand their condition and learn to manage themselves in daily life. In addition, in order to meet users' needs for professional health consultation, the system also provides online expert Q&A resources. Users can consult professional doctors or health consultants through the system platform to obtain personalized health advice and guidance.

[0093] In a specific embodiment, it also includes:

[0094] One or more of the diagnostic data, diagnostic instructions, and health management plan are associated with the user and stored.

[0095] In this embodiment, in order to ensure that the diagnosis data, diagnosis instructions and health management plans can be effectively managed and utilized, the system associates these key information with the user and stores them. This step not only ensures the accuracy and completeness of the data, but also provides users with a personalized health management experience.

[0096] First, the system will identify and collect the user's personal information, including but not limited to the user's name, age, gender, contact information, etc. This information will be used as a unique identifier for the user's identity and for subsequent data association and query. The system will then associate the diagnostic data with the user. Diagnostic data is an important record of the user's health status, including disease diagnosis, laboratory test results, imaging data, etc. By associating diagnostic data with the user, the system can ensure the accuracy and traceability of the data, and it is also convenient for users to view their diagnostic records at any time.

[0097] At the same time, the system will also associate the diagnosis description with the user. The diagnosis description is an interpretation and explanation of the diagnostic data, describing the user's health status, disease conditions and possible risks in plain language. By associating the diagnosis description with the user, the system can ensure that the user can clearly and accurately understand his or her health status and take appropriate health management measures accordingly.

[0098] Finally, the health management plan will also be associated with the user. The health management plan is generated based on the user's diagnostic data and physical condition data, and is designed to provide users with personalized health guidance and management suggestions. By associating the health management plan with the user, the system can ensure that the user can execute it according to the plan and achieve the goal of improving health status.

[0099] In the process of associative storage, the system will use advanced data encryption and backup technology to ensure the security and reliability of user data. At the same time, the system will also provide convenient data query and export functions, so that users can view and share their health information at any time.

[0100] In a specific embodiment, “generating a health management plan based on diagnostic data and pre-acquired user's physical condition data” includes:

[0101] A health management plan is generated based on the diagnosis data within a first preset time period closest to the current time and the user's physical condition data within a second preset time period closest to the current time.

[0102] In this embodiment, in order to generate a more accurate health management plan that is in line with the user's current health status, the system will pay special attention to the diagnostic data and the user's physical condition data within the latest preset time period. This time period-based data screening method can ensure that the health management plan is closer to the user's current health status, thereby providing more targeted and practical suggestions.

[0103] First, the system will collect diagnostic data within the first preset time period closest to the current one. The setting of this time period is usually determined based on factors such as the course of the disease, the treatment cycle, and the timeliness of the data. For example, for patients with chronic diseases, it may be necessary to collect diagnostic data from the past few months or even a year to fully understand the changes in the patient's condition; for patients with acute diseases, it may only be necessary to collect data from the past few days or a week. These diagnostic data include but are not limited to disease diagnosis, laboratory test results, imaging data, etc., which provide an important basis for the generation of health management plans.

[0104] At the same time, the system will also obtain the user's physical condition data within the most recent preset second time period. The setting of this time period is usually determined based on the frequency of the user's daily monitoring data and the representativeness of the data. For example, for users who monitor weight, blood pressure and other data every day, it may be necessary to collect data from the past week or two; for users with lower monitoring frequency, it may be necessary to collect data from the past month or longer. These physical condition data include daily monitoring indicators such as weight, blood pressure, blood sugar, heart rate, etc., which can reflect the user's current health status and potential risks.

[0105] The system will then use advanced data analysis technology and personalized algorithms to conduct a comprehensive analysis and evaluation of this data. During this process, the system will consider multiple factors such as the user's age, gender, genetic background, and lifestyle habits to ensure that the generated health management plan is highly targeted and personalized. Finally, the system will automatically generate a health management plan based on the analysis results. The plan may include medication plans, dietary recommendations, exercise guidance, health monitoring recommendations, and other aspects. These recommendations are designed to help users improve their health, prevent recurrence or worsening of diseases, and improve their overall quality of life.

[0106] By generating a health management plan based on the diagnostic data and physical condition data within the latest preset time period, the system can provide users with more accurate and effective health management services. This service can not only meet the personalized needs of users, but also promote the rational use of medical resources and the continuous improvement of medical services.

[0107] In a specific embodiment, it also includes:

[0108] If new diagnostic data or new physical condition data is obtained, the step of "generating a health management plan based on the diagnostic data and the user's physical condition data obtained in advance" is repeated.

[0109] In this embodiment, in order to ensure the real-time and effectiveness of the health management plan, the system has specially designed a dynamic update mechanism. Specifically, when the system obtains new diagnostic data or new physical condition data of the user, it will immediately trigger the repetition of the previous step of "generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user".

[0110] The design of this mechanism is based on a full understanding of the dynamic changes in the user's health status. Over time, the user's health status may change due to a variety of factors, such as the effect of treatment, changes in lifestyle, environmental influences, etc. Therefore, the system needs to continuously update and adjust the health management plan based on the latest data to ensure that it can continuously and accurately guide the user's health management.

[0111] When the system detects new diagnostic data or new physical condition data, it will first verify and cleanse the data to ensure its accuracy and reliability. The system will then merge the new data with the previously stored data to form a complete and up-to-date set of user health data. Next, the system will again use the previously mentioned data analysis technology and personalized algorithms to comprehensively analyze and evaluate this new data set to generate an updated health management plan.

[0112] This updated health management plan will be pushed to the user immediately and may contain different suggestions and guidance from the old plan. For example, if the user's disease condition improves, the system may recommend reducing the dosage of certain medications or changing the diet plan; if the user's weight increases, the system may recommend increasing the amount of exercise or adjusting the diet structure.

[0113] Through this dynamic update mechanism, the system can track the changes in the user's health status in real time and adjust the health management plan accordingly. This not only ensures the real-time and effectiveness of the health management plan, but also improves the user's trust and satisfaction with the system. At the same time, this mechanism also provides strong support for the rational use of medical resources and the continuous improvement of medical services.

[0114] In summary, this embodiment provides an AI-based health management method, which automatically converts professional medical terms and complex test results into a form that is easy for users to understand by integrating the deep learning and natural language processing capabilities of the AI ​​large language model, thereby reducing the communication barriers between doctors and patients and improving the efficiency of diagnosis and treatment; and through AI personalized medication reminders and life guidance, it helps patients better follow the doctor's orders, improve treatment effects, and reduce the recurrence rate of the disease, which effectively promotes the improvement of patients' disease awareness level and the implementation of daily health management, and demonstrates obvious social value and economic benefits.

[0115] Example 2

[0116] Embodiment 2 of the present application discloses an AI-based health management system, which systematizes the AI-based health management method of Embodiment 1 to make it more practical. The overall structure diagram of the AI-based health management system is shown in the attached manual. Figure 2 The specific plan is as follows:

[0117] This embodiment proposes an AI-based health management system, which includes:

[0118] Parsing module 1 is used to parse the diagnostic data of the user obtained by the medical staff based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand;

[0119] Display module 2, used to display the diagnosis description to the user;

[0120] A generating module 3, for generating a health management plan based on the diagnostic data and the user's physical condition data acquired in advance;

[0121] The reminder module 4 is used to execute a health management plan for the user to provide health reminders and / or health instructions to the user.

[0122] This embodiment proposes an AI-based health management system, which systematizes the AI-based health management method of Embodiment 1 to make it more practical.

[0123] This application integrates the deep learning and natural language processing capabilities of the AI ​​large language model to automatically convert professional medical terms and complex test results into a form that is easy for users to understand, reducing communication barriers between doctors and patients and improving diagnosis and treatment efficiency; and through AI personalized medication reminders and life guidance, it helps patients better follow doctor's orders, improve treatment effects, and reduce disease recurrence rates, which effectively promotes the improvement of patients' disease awareness and the implementation of daily health management, demonstrating obvious social value and economic benefits.

[0124] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present invention. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be changed accordingly and located in one or more devices different from the present implementation scenario.

Claims

1. A health management method based on AI, characterized in that: include: If the medical staff obtains the diagnostic data for the user, the diagnostic data is parsed based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand; presenting the diagnostic description to the user; generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user; The health management plan is executed for the user to provide health reminders and / or health instructions to the user.

2. The method according to claim 1, characterized in that: The diagnostic data includes: diagnostic audio data orally narrated by medical personnel; The “parsing the diagnostic data based on a preset AI large language model to generate a diagnostic description that is easy for the user to understand” includes: Convert the diagnostic audio data based on a preset AI large language model to generate text data; The text data is semantically recognized and colloquially processed to generate a diagnosis description that is easy for the user to understand.

3. The method according to claim 1, characterized in that The diagnostic data includes: medical record related data output by medical staff; the medical record related data includes: disease diagnosis, laboratory test results, one or more of imaging data; The “parsing the diagnostic data based on a preset AI large language model to generate a diagnostic description that is easy for the user to understand” includes: A preset AI large language model connected to a preset medical database is used to parse the medical record-related data to generate a diagnosis description that is easy for the user to understand; the diagnosis description includes: a description of the user's physical condition information and / or health precautions.

4. The method according to claim 1, characterized in that: The presenting the diagnosis description to the user specifically includes: The diagnostic description is presented to the user in text, and / or voice, and / or image, and / or audio form.

5. The method according to claim 1, characterized in that: The “generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user” specifically includes: Automatically generate a medication plan, and / or dietary advice, and / or a life guide for the user based on the latest diagnostic data and the latest pre-acquired physical condition data of the user; The “executing the health management plan for the user” includes: Providing medication reminders based on the medication plan in the health management plan and the current time point; and / or Providing dietary reminders based on the dietary recommendations in the health management plan and the current time point; and / or Life reminders are provided based on the life guidelines in the health management plan and the current time point and environment.

6. The method according to claim 1, characterized in that The health management plan includes: health education plan and health consultation plan; The “executing the health management plan for the user” includes: According to the disease progression in the user's physical condition data, popular science articles, and / or video tutorials, and / or online expert Q&A resources related to the user's diagnostic data are regularly pushed to promote the user's self-management and disease recovery.

7. The method according to claim 1, characterized in that Also includes: One or any multiple of the diagnostic data, the diagnostic description, and the health management plan are associated with the user and stored.

8. The method according to claim 1, characterized in that The “generating a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user” includes: A health management plan is generated based on the diagnosis data within a first preset time period closest to the current time and the user's physical condition data within a second preset time period closest to the current time.

9. The method according to claim 1 or 8, characterized in that: Also includes: If new diagnostic data or new physical condition data is obtained, the step of "generating a health management plan based on the diagnostic data and the user's physical condition data obtained in advance" is repeated.

10. An AI-based health management system, characterized in that: include: A parsing module is used to parse the diagnostic data of the user obtained by the medical staff based on the preset AI large language model to generate a diagnostic description that is easy for the user to understand; A display module, used for displaying the diagnosis description to the user; A generating module, configured to generate a health management plan based on the diagnostic data and the pre-acquired physical condition data of the user; The reminder module is used to execute the health management plan for the user to provide health reminders and / or health instructions to the user.

Images