Comprehensive elderly evaluation system and method based on large language model

Abstract

The invention provides an old people comprehensive evaluation system and method based on a big language model, and the system comprises a data collection module which is used for collecting the data of old people; the big language model processing engine is used for analyzing the collected data of the old people by utilizing a pre-trained big language model to obtain a big language analysis result; and the assessment report generation module is used for generating a health assessment report and personalized suggestions based on the big language analysis result, and completing the comprehensive assessment of the elderly. According to the technical scheme, through an automatic evaluation process, manual intervention is reduced, and the evaluation efficiency is improved; and the accuracy and objectivity of evaluation are improved by using the deep learning ability of the large language model.

Description

Background Art

[0002] With the increasingly severe global aging problem, Comprehensive Geriatric Assessment (CGA) has become an important tool for ensuring the health of the elderly. Traditional assessment methods rely on manual questionnaires, interviews, and evaluations by professional teams, which have problems such as being time-consuming, highly subjective, and having limited coverage dimensions, and cannot meet the needs of large-scale elderly population health management. Large Language Model (LLM), with its powerful capabilities in the field of natural language processing, can efficiently process complex semantics and support the integration and analysis of multi-dimensional data. By introducing it into the field of comprehensive geriatric assessment, automated assessment can be achieved, significantly improving the assessment efficiency and providing scientific, accurate, and personalized health advice for the elderly. Summary of the Invention

[0003] This application provides a comprehensive geriatric assessment system and method based on a large language model to provide personalized health assessment reports and suggestions.

[0004] In a first aspect, a comprehensive geriatric assessment system based on a large language model is provided, including:

[0005] A data collection module for collecting data of the elderly;

[0006] A large language model processing engine for analyzing the collected data of the elderly using a pre-trained large language model to obtain large language analysis results;

[0007] An assessment report generation module for generating a health assessment report and personalized suggestions based on the large language analysis results to complete the comprehensive geriatric assessment.

[0008] In the above technical solution, through the data collection module for collecting data of the elderly; the large language model processing engine for analyzing the collected data of the elderly using a pre-trained large language model to obtain large language analysis results; the assessment report generation module for generating a health assessment report and personalized suggestions based on the large language analysis results to complete the comprehensive geriatric assessment; through an automated assessment process, manual intervention is reduced and the assessment efficiency is improved; by using the deep learning ability of the large language model, the accuracy and objectivity of the assessment are improved, and customized health suggestions can be provided according to the specific situation of the elderly.

[0009] In a specific feasible implementation, it further includes:

[0010] A user interaction interface module for providing an interface for natural language interaction with the elderly.

[0011] In a specific feasible implementation, the data collection module includes:

[0012] An automatic collection layer for integrating data provided by third-party data interfaces and directly filling relevant scale fields;

[0013] An independent input layer for mapping answers to corresponding fields of the scale for the data input by users in voice or text, combining speech recognition and natural language processing technologies, and collecting supplementary information through intelligent Q&A;

[0014] A doctor evaluation layer for providing a dedicated operation interface for doctors for the scale questions that require professional judgment.

[0015] In a specific feasible implementation, the large language model processing engine includes:

[0016] A semantic analysis and keyword extraction module for semantically parsing the voice and text data input by the elderly through the large language model, and automatically identifying and extracting key information;

[0017] A cross-modal data integration module for fusing speech-to-text data, structured data of user answers, and electronic health record data obtained from external systems to construct a complete health profile;

[0018] An evaluation index and rule matching module for calculating and analyzing the input data based on predefined health evaluation rules to obtain the large language analysis result.

[0019] In a specific feasible implementation, the evaluation index and rule matching module includes:

[0020] A rule library definition unit for constructing a rule library and structurally storing the evaluation scale and corresponding threshold ranges and evaluation criteria;

[0021] An automatic matching unit for dynamically matching the data input by the user or provided by the third-party interface combined with the doctor evaluation data with the preset standards in the rule library to generate evaluation results and suggestions;

[0022] A dynamic adjustment unit for online updating of the rule library.

[0023] In a specific feasible implementation, the evaluation report generation module includes:

[0024] A personalized health assessment report unit for generating a personalized health assessment report;

[0025] A risk warning unit for warning of outliers for potential health risks;

[0026] A health advice and intervention measures unit for generating health advice and intervention measures;

[0027] A tracking and feedback mechanism unit for designing a tracking mechanism to monitor health changes.

[0028] In a specific implementable embodiment, the personalized health assessment report includes multiple dimensions such as physical, mental, and social.

[0029] In a specific implementable embodiment, the user interface module includes:

[0030] A multimodal interaction support unit for providing multiple interaction methods;

[0031] An education and training resources unit for providing health education and training resources.

[0032] In a second aspect, a comprehensive geriatric assessment method based on a large language model is provided, including the following steps:

[0033] Collecting elderly people's data using a data collection module;

[0034] Analyzing the collected elderly people's data using a large language model processing engine with a pre-trained large language model to obtain a large language analysis result;

[0035] Generating a health assessment report and personalized advice based on the large language analysis result using an assessment report generation module to complete the comprehensive geriatric assessment.

[0036] In the above technical solution, through a data collection module for collecting elderly people's data; a large language model processing engine for analyzing the collected elderly people's data using a pre-trained large language model to obtain a large language analysis result; an assessment report generation module for generating a health assessment report and personalized advice based on the large language analysis result to complete the comprehensive geriatric assessment; through an automated assessment process, manual intervention is reduced and the assessment efficiency is improved; using the deep learning ability of the large language model, the accuracy and objectivity of the assessment are improved, and customized health advice can be provided according to the specific situation of the elderly.

[0037] In a specific implementable embodiment, it further includes:

[0038] Providing an interface for natural language interaction with the elderly using the user interface module. Description of the Drawings

[0039] Figure 1 It is a structural block diagram of the comprehensive geriatric assessment system based on a large language model provided by an embodiment of the present application;

[0040] Figure 2This is a flowchart of the comprehensive geriatric assessment solution based on a large language model provided by an embodiment of the present application. Detailed implementation manners

[0041] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. Through these descriptions, the features and advantages of the present application will become more clearly defined.

[0042] The special term "exemplary" here means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0043] In addition, the technical features involved in different implementation manners of the present application described below can be combined with each other as long as they do not conflict with each other.

[0044] To facilitate the understanding of the comprehensive geriatric assessment system and method based on a large language model provided by an embodiment of the present application, its application scenario will be described first. The comprehensive geriatric assessment system and method based on a large language model provided by an embodiment of the present application are used to provide personalized health assessment reports and suggestions. With the increasingly severe global aging problem, comprehensive geriatric assessment (CGA) has become an important tool for ensuring the health of the elderly. Traditional assessment methods rely on manual questionnaires, interviews, and assessments by professional teams, which have problems such as time-consuming, strong subjectivity, and limited coverage dimensions, and cannot meet the needs of large-scale elderly population health management. Large language models (LLMs) rely on their powerful capabilities in the field of natural language processing, can efficiently process complex semantics, and support the integration and analysis of multi-dimensional data. By introducing it into the field of comprehensive geriatric assessment, automated assessment can be realized. The assessment efficiency can be significantly improved, and scientific, accurate, and personalized health suggestions can be provided for the elderly. For this reason, an embodiment of the present application provides a comprehensive geriatric assessment system and method based on a large language model to provide personalized health assessment reports and suggestions. It will be described in detail below with reference to specific drawings and embodiments.

[0045] Refer to Figure 1 and Figure 2 , Figure 1 This is a structural block diagram of the comprehensive geriatric assessment system based on a large language model provided by an embodiment of the present application; Figure 2 This is a flowchart of the comprehensive geriatric assessment solution based on a large language model provided by an embodiment of the present application.

[0046] In Figure 1In this embodiment of the present application, a comprehensive geriatric assessment system based on a large language model is provided, including:

[0047] A data collection module for collecting data of the elderly;

[0048] A large language model processing engine for analyzing the collected elderly data using a pre-trained large language model to obtain a large language analysis result;

[0049] An evaluation report generation module for generating a health evaluation report and personalized suggestions based on the large language analysis result to complete a comprehensive geriatric assessment.

[0050] In the above technical solution, through the data collection module for collecting data of the elderly; the large language model processing engine for analyzing the collected elderly data using a pre-trained large language model to obtain a large language analysis result; the evaluation report generation module for generating a health evaluation report and personalized suggestions based on the large language analysis result to complete a comprehensive geriatric assessment; through an automated evaluation process, manual intervention is reduced and the evaluation efficiency is improved; by utilizing the deep learning ability of the large language model, the accuracy and objectivity of the evaluation are improved, and customized health suggestions can be provided according to the specific situation of the elderly.

[0051] In a specific feasible implementation, it further includes:

[0052] A user interaction interface module for providing an interface for natural language interaction with the elderly.

[0053] In a specific feasible implementation, the data collection module includes:

[0054] An automatic collection layer for integrating data provided by third-party data interfaces and directly filling relevant scale fields;

[0055] An independent input layer for mapping the answers to the corresponding fields of the scale for the data input by the user's voice or text, combining speech recognition and natural language processing technologies, and collecting supplementary information through intelligent Q&A;

[0056] A doctor evaluation layer for providing a dedicated operation interface for doctors for the scale questions that require professional judgment.

[0057] In a specific feasible implementation, the large language model processing engine includes:

[0058] A semantic analysis and keyword extraction module for semantically parsing the voice and text data input by the elderly through the large language model, automatically identifying and extracting key information;

[0059] A cross-modal data integration module for fusing speech-to-text data, structured data of user responses, and electronic health record data obtained from external systems to construct a complete health profile;

[0060] An evaluation index and rule matching module for calculating and analyzing input data based on predefined health evaluation rules to obtain the large language analysis results.

[0061] In a specific and feasible implementation, the evaluation index and rule matching module includes:

[0062] A rule base definition unit for constructing a rule base and storing the evaluation scale, corresponding threshold ranges, and evaluation criteria in a structured manner;

[0063] An automated matching unit for dynamically matching the data provided by user input or third-party interfaces combined with doctor evaluation data with the preset standards in the rule base to generate evaluation results and suggestions;

[0064] A dynamic adjustment unit for online updating of the rule base.

[0065] In a specific and feasible implementation, the evaluation report generation module includes:

[0066] A personalized health assessment report unit for generating a personalized health assessment report;

[0067] A risk warning unit for warning of outliers for potential health risks;

[0068] A health advice and intervention measures unit for generating health advice and intervention measures;

[0069] A tracking and feedback mechanism unit for designing a tracking mechanism to monitor health changes.

[0070] In a specific and feasible implementation, the personalized health assessment report includes multiple dimensions such as physical, mental, and social.

[0071] In a specific and feasible implementation, the user interface module includes:

[0072] A multi-modal interaction support unit for providing multiple interaction methods;

[0073] An education and training resources unit for providing health education and training resources.

[0074] Reference Figure 1 , specifically, the comprehensive geriatric assessment system based on the large language model can collect the speech and text data of the elderly through natural language interaction, and use the large language model for in-depth analysis to provide personalized health assessment reports and suggestions. Specifically, it includes:

[0075] I. Data Acquisition Module:

[0076] In the system, clear processing strategies and division of labor are established for different data sources (third - party data interfaces, self - input by the elderly, doctor - involved assessment) to ensure the scientificity and flexibility of data fusion. According to the different data sources and data types, the system sets up multi - level data acquisition modules:

[0077] Automatic Acquisition Layer:

[0078] Integrate the data provided by third - party data interfaces and directly fill in the relevant scale fields, such as blood glucose, blood pressure, past medical history, etc.

[0079] 1. Data Acquisition and Integration:

[0080] The system integrates with the Electronic Health Record (EHR) system through a standardized data interface (such as HL7 FHIR or other mainstream health data standards). Automatically extract the user's past health data, including medical history records, medication use records, allergy history, imaging reports, etc.

[0081] 2. Data Cleaning and Pre - processing:

[0082] The system uses data cleaning and deduplication algorithms to ensure the integrity and consistency of the integrated data. To enhance the timeliness of the data, the system synchronizes and updates regularly, and supports data interoperability with community health institutions, hospitals, and health management platforms to ensure comprehensive coverage of the information required for assessment.

[0083] 3. Data Mapping and Automatic Scale Filling:

[0084] The system automatically completes the filling process according to the mapping rules between the scale fields and the health data fields.

[0085] Mapping Rules: A pre - defined field matching table (such as "blood glucose level" corresponding to "diabetes risk assessment" in the scale).

[0086] Processing Logic:

[0087] When the health data is complete, directly fill in the corresponding fields.

[0088] If the data is incomplete or in conflict, prompt the user to input and confirm manually. That is, input through the following questionnaire in voice / text

[0089] Self - Input Layer:

[0090] For the data input by users in voice or text, combining speech recognition and natural language processing technologies, map the answers to the corresponding fields of the scale, and collect supplementary information through intelligent Q&A. The present invention proposes a voice and text interaction module based on scale question collection, which realizes accurate data collection and real-time filling by decomposing scale questions into more natural guided Q&A. The elderly can complete answering questions by voice. The system converts the voice into text through speech recognition technology, and combines the semantic analysis ability of the large language model to intelligently analyze the answers.

[0091] 1. Embedded collection of scale questions:

[0092] Directly embed the questions of the evaluation scale into the collection module. The user's answers are collected in voice or text form, and are parsed in real time based on the large model system and automatically filled into the corresponding fields of the scale.

[0093] 2. Natural language guidance and question simplification:

[0094] Decompose the professional term questions in the scale into guided dialogue questions that are easy for the elderly to understand.

[0095] For example, "What is the skin type?" is optimized to "Has your skin been prone to breakage or feeling dry recently?"

[0096] 3. Real-time data filling and feedback:

[0097] Every time the user answers a question, the system maps the answer to the scale field in real time. For the questions in the scale that require score calculation, the system automatically completes the calculation and feedbacks the final score.

[0098] 4. Flexible switching between voice and text input

[0099] Provide dual-mode support for voice collection and text input, and dynamically adjust the collection method according to the user's habits and capabilities.

[0100] Doctor evaluation layer:

[0101] For the scale questions that require professional judgment, the system provides a dedicated operation interface for doctors, displays the unfinished parts, and supports doctors to evaluate relevant content.

[0102] Data priority logic: When there are multiple sources of data in the same field, the priority is set as:

[0103] Doctor input (highest priority to ensure professionalism).

[0104] User's independent input (if the doctor does not modify, keep the data provided by the user).

[0105] Third-party data interface (as the default filling data, to be confirmed).

[0106] Division Strategy for Some Scale Questions

[0107] Considering that some questions in the scale may require more complex input or professional knowledge, the following strategy can be adopted:

[0108] Specific design idea:

[0109] Divide the scale questions into three levels:

[0110] Fully automated filling: Third-party interfaces directly provide data (such as BMI, laboratory indicators).

[0111] User's independent answer: Collect the user's answer through voice or text (such as activities of daily living ability, subjective symptom description).

[0112] Doctor's evaluation questions: Require the doctor to participate in answering or verification.

[0113] Dynamic question allocation:

[0114] The system dynamically allocates processing methods according to question classification. For example:

[0115] If the system detects fields such as "data missing" or "requiring professional judgment" (such as pulmonary function test results), it will automatically mark the corresponding fields as "pending doctor evaluation" and highlight them in the doctor interface.

[0116] For questions that the elderly can answer (such as living habits, mental state), collect them through voice or text interaction.

[0117] II. Large Language Model Processing Engine:

[0118] The large language model processing engine is the core component of this system, mainly responsible for semantic understanding and in-depth analysis of the collected voice, text, and structured data.

[0119] 1. Semantic analysis and keyword extraction:

[0120] Through the large language model, perform semantic parsing on the voice and text data input by the elderly, and automatically identify and extract key information, such as descriptions of health status, cognitive function, nutritional status, activities of daily living ability, mental state, and social support information required for scale evaluation.

[0121] Model training: Fine-tune in combination with a large number of annotated elderly health-related corpora accumulated to enhance the recognition ability of medical domain terms and common expressions. Use the extended dataset to generate diverse semantic expressions and improve the generalization ability of the model.

[0122] 2. Cross-modal data integration:

[0123] The system supports the unified processing of multimodal data, integrating speech-to-text data, structured data of user responses, and electronic health record (EHR) data obtained from external systems to construct a complete health profile.

[0124] 3. Evaluation Metrics and Rule Matching:

[0125] Based on predefined health assessment rules (such as clinical guidelines or personalized assessment parameters), the system performs calculations and analyzes on the input data. The system generates specific scores according to the core dimensions of comprehensive geriatric assessment (such as physical health, cognitive function, mental health, living ability, social support, etc.).

[0126] Rule Base Definition: Construct a rule base to structurally store assessment scales, corresponding threshold ranges, and assessment criteria.

[0127] Automated Matching: The system dynamically matches the preset criteria in the rule base based on the data provided by user input or third-party interfaces plus doctor assessment data to generate assessment results and recommendations.

[0128] Dynamic Adjustment: Support online updates of the rule base to ensure synchronization with the latest guidelines and doctor requirements.

[0129] III. Assessment Report Generation Module:

[0130] Personalized Health Assessment Report:

[0131] Based on the analysis results of the large language model, generate a personalized health assessment report covering multiple dimensions such as physiology, psychology, and society.

[0132] The report details the current health status of the elderly, providing decision-making support for the elderly and medical professionals.

[0133] Risk Warning:

[0134] Through the assessment results, the system warns of outliers for potential health risks, such as fall risk, pressure ulcer risk, etc., and gives early warnings and intervention suggestions.

[0135] Health Recommendations and Intervention Measures:

[0136] Health Recommendations: Through the natural language generation ability of the LLM, provide customized health recommendations such as diet adjustment, exercise plans, and medication management according to the specific situation of the elderly to help the elderly improve their health status.

[0137] Intervention Measures: Utilize the learning ability of the large model to recommend appropriate intervention measures according to the latest medical research and clinical guidelines, and dynamically adjust according to the feedback and health changes of the elderly.

[0138] Tracking and Feedback Mechanism:

[0139] Design a tracking mechanism to regularly update the health status of the elderly and compare it with the previous assessment results to monitor health changes. Adjust health advice and intervention measures according to the tracking results to ensure the timeliness and effectiveness of the assessment and advice.

[0140] IV. User Interface:

[0141] Friendly User Interface Design:

[0142] Design a simple and intuitive user interface that is convenient for the elderly to use, including large fonts, a high-contrast color scheme, and simple navigation.

[0143] Provide voice control and touch screen operation to adapt to the operating habits of different elderly people.

[0144] Multimodal Interaction Support:

[0145] Support multiple interaction methods such as voice and text to meet the different communication needs of the elderly.

[0146] Education and Training Resources:

[0147] Provide health education and training resources to help the elderly understand health knowledge and improve their self-management ability.

[0148] Regularly push health tips to encourage the elderly to participate in the practice of a healthy lifestyle.

[0149] In this embodiment, a practical comprehensive elderly assessment system is provided. By using a large language model, the assessment process is automated and personalized. The automated data collection and assessment process significantly reduces manual intervention, supports continuous health monitoring and risk prediction, and realizes dynamic adjustment of health management. It is applicable to large-scale elderly health management scenarios and has broad practical application value.

[0150] In the above technical solution, there is a data collection module for collecting elderly people's data; a large language model processing engine for analyzing the collected elderly people's data using a pre-trained large language model to obtain large language analysis results; an assessment report generation module for generating a health assessment report and personalized advice based on the large language analysis results to complete the comprehensive elderly assessment. Through the automated assessment process, manual intervention is reduced, and the assessment efficiency is improved. By using the deep learning ability of the large language model, the accuracy and objectivity of the assessment are improved, and customized health advice can be provided according to the specific situation of the elderly.

[0151] In Figure 2 this application embodiment provides a comprehensive elderly assessment method based on a large language model, including the following steps:

[0152] Collect the data of the elderly using the data collection module;

[0153] Use the large language model processing engine to analyze the collected data of the elderly using a pre-trained large language model to obtain the large language analysis result;

[0154] Use the evaluation report generation module to generate a health evaluation report and personalized suggestions based on the large language analysis result to complete the comprehensive elderly assessment.

[0155] In the above technical solution, through the data collection module, which is used to collect the data of the elderly; the large language model processing engine, which is used to analyze the collected data of the elderly using a pre-trained large language model to obtain the large language analysis result; the evaluation report generation module, which is used to generate a health evaluation report and personalized suggestions based on the large language analysis result to complete the comprehensive elderly assessment; through the automated evaluation process, manual intervention is reduced and the evaluation efficiency is improved; by using the deep learning ability of the large language model, the accuracy and objectivity of the evaluation are improved, and customized health suggestions can be provided according to the specific situation of the elderly.

[0156] In a specific and feasible implementation, it further includes:

[0157] Use the user interface module to provide an interface for natural language interaction with the elderly.

[0158] Those skilled in the art of the present application know that the present application can be implemented as a system, a method or a computer program product.

[0159] Therefore, the present disclosure can be specifically implemented in the following forms, that is: it can be completely hardware, can also be completely software (including firmware, resident software, microcode, etc.), and can also be in the form of a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" in this article. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable media contains computer-readable program code.

[0160] Any combination of one or more computer-readable media may be employed. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present document, a computer-readable storage medium may be any tangible medium that contains or stores a program which can be used by or in connection with an instruction execution system, apparatus, or device.

[0161] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application. On this basis, various substitutions and improvements can be made to the present application, and all of these fall within the protection scope of the present application.

Claims

1. A comprehensive assessment system for the elderly based on a large language model, characterized in that: include: Data collection module, used to collect data on the elderly; A large language model processing engine, used to analyze the collected data of the elderly using a pre-trained large language model to obtain a large language analysis result; An assessment report generation module is used to generate a health assessment report and personalized suggestions based on the big language analysis results to complete a comprehensive assessment of the elderly.

2. The comprehensive assessment system for the elderly based on a large language model according to claim 1 is characterized in that: Also includes: The user interaction interface module is used to provide an interface for natural language interaction with the elderly.

3. The comprehensive assessment system for the elderly based on a large language model according to claim 2 is characterized in that: The data acquisition module comprises: Automatic collection layer, used to integrate data provided by third-party data interfaces and directly fill in relevant scale fields; The autonomous input layer is used to map the answers to the corresponding fields of the scale based on the user's voice or text input data by combining speech recognition and natural language processing technology, and collect supplementary information through intelligent question and answer; The doctor assessment layer is used to provide doctors with a dedicated operation interface for scale questions that require professional judgment.

4. The comprehensive assessment system for the elderly based on a large language model according to claim 3 is characterized in that: The large language model processing engine includes: The semantic analysis and keyword extraction module is used to perform semantic analysis on the speech and text data input by the elderly through a large language model, and automatically identify and extract key information; A cross-modal data integration module is used to integrate speech-to-text data, structured data of user answers, and electronic health record data obtained from external systems to build a complete health profile; The evaluation index and rule matching module is used to calculate and analyze the input data based on predefined health evaluation rules to obtain the big language analysis results.

5. The comprehensive assessment system for the elderly based on a large language model according to claim 4 is characterized in that: The evaluation index and rule matching module includes: A rule base definition unit is used to construct a rule base and to store the evaluation scales, corresponding threshold ranges and evaluation criteria in a structured manner; An automated matching unit, which is used to dynamically match the data input by the user or provided by the third-party interface with the doctor's evaluation data and the preset standards in the rule base to generate evaluation results and suggestions; The dynamic adjustment unit is used to update the rule base online.

6. The comprehensive assessment system for the elderly based on a large language model according to claim 5 is characterized in that: The evaluation report generating module comprises: A personalized health assessment report unit, used for generating a personalized health assessment report; Risk warning unit, used to warn of abnormal values ​​of potential health risks; The Health Advice and Interventions Unit, which is used to generate health advice and interventions; The tracking and feedback mechanism unit is used to design tracking mechanisms to monitor health changes.

7. The comprehensive assessment system for the elderly based on a large language model according to claim 6 is characterized in that: The personalized health assessment report includes multiple dimensions including physiological, psychological and social.

8. The comprehensive assessment system for the elderly based on a large language model according to claim 7 is characterized in that: The user interaction interface module comprises: A multimodal interaction support unit, used to provide multiple interaction modes; The Education and Training Resources Unit is used to provide health education and training resources.

9. A comprehensive assessment method for the elderly based on a large language model, characterized in that: The following steps are involved: Collect data on the elderly using the data collection module; Analyze the collected data of the elderly using a large language model processing engine and a pre-trained large language model to obtain a large language analysis result; An assessment report generation module is used to generate a health assessment report and personalized suggestions based on the big language analysis results to complete the comprehensive assessment of the elderly.

10. The comprehensive assessment method for the elderly based on a large language model according to claim 9, characterized in that: Also includes: A user interaction interface module is used to provide an interface for natural language interaction with the elderly.

Images