Active health intelligent service multi-element supply platform

Abstract

The invention discloses an active health intelligent service multi-supply platform, and belongs to the field of health service platforms. The platform comprises a user interaction layer, a platform integration layer and a platform core layer. According to the method, active and accurate prediction of the health risk is realized by collecting multi-source health data and adopting an intelligent evaluation model fusing an individual baseline, a dynamic trend and a multi-index synergistic effect. Based on the evaluation result, the platform automatically generates a hierarchical intervention scheme, and cooperates with external resources to provide closed-loop management from health promotion to medical services. According to the invention, the problems of data islands and service chain breakage in the prior art are effectively solved, the mode conversion from passive response to active health management is realized, and one-stop end-to-end intelligent health service is provided for users.

Description

Technical Field

[0001] This invention relates to the field of health service platforms, and in particular to a proactive smart health service diversified supply platform. Background Technology

[0002] Currently, with the deep integration of information technology and the healthcare field, various digital health management tools have emerged in the market, such as hospital information systems, personal health monitoring applications, and wearable smart devices. However, existing technologies generally have significant limitations. These technology systems typically operate as isolated information silos, with medical institution diagnostic data, vital sign data from personal devices, and data from public health platforms fragmented and unable to achieve effective integration and interoperability, making it difficult to form a complete and continuous personal health view. Furthermore, most existing health management service models are reactive, focusing on diagnosis and treatment after disease onset, lacking the ability to proactively detect health risks and intervene early. Intervention often occurs only after users have developed obvious symptoms, thus missing the optimal time for health management. Moreover, the health assessment models used by these systems are mostly simplistic, typically relying on static thresholds for single indicators, failing to dynamically analyze the development trend of individual health status, and failing to consider the complex synergistic effects between multiple risk factors, resulting in inaccurate and unpredictable assessment results. This technological deficiency ultimately leads to a fragmented service experience. Even if users perceive potential risks through a particular device, there is a lack of a smooth, integrated path to connect with subsequent professional consultations, medical appointments, or emergency responses, among other diversified services. Therefore, the industry urgently needs a new type of health service platform that can break down data barriers, shift from a passive response to a proactive management model, adopt intelligent and personalized assessment methods, and provide an integrated closed-loop service supply. Summary of the Invention

[0003] To address the aforementioned problems in existing technologies, the present invention aims to provide a proactive health intelligent service diversified supply platform, comprising: The user interaction layer is used to interact with platform users, proactive health devices, and health management specialists to collect personal health data and issue service instructions.

[0004] The platform integration layer is used for data exchange and business collaboration with one or more external information systems.

[0005] The platform core layer, connected to the user interaction layer and the platform integration layer, is used to receive and process the personal health data and external data, and generate the service instructions based on the processing results.

[0006] The core layer of the platform includes: A data center is used to categorize, store, and manage all health-related data.

[0007] The service center is used to provide standardized atomic service components.

[0008] The application center is used to orchestrate and schedule the atomic service components of the service center according to the preset health management logic, so as to form application scenarios for the user.

[0009] Furthermore, the service center includes at least one of the following service clusters: Basic services provide the basic support functions for platform operation, including real-name authentication, rule engine, security and privacy protection, resource directory management, collaborative services, data mining and information extraction services.

[0010] The scientific assessment category offers professional health assessment functions, including vital sign monitoring, symptom collection, risk assessment, chronic disease assessment, psychological assessment, data analysis, and health advice generation services.

[0011] The prevention service category provides non-medical proactive intervention and health education functions, including text reminders, voice reminders, information push, health interaction, health education, traditional Chinese medicine health preservation, and points check-in services.

[0012] Medical services provide auxiliary services related to medical procedures, including risk warning, online appointment, map navigation, two-way referral, medication guidance, appointment services, and intelligent follow-up services.

[0013] Furthermore, the application center includes an active discovery module, which is used to call the services of the service center to realize user profile creation and data aggregation, and continuously monitor data changes to identify potential health problems.

[0014] The scientific assessment module is used to call the services of the service center to conduct multi-dimensional quantitative assessments of the potential health problems and form a user health profile.

[0015] The module is actively adjusted to call the services of the service center and generate and push personalized non-medical intervention plans based on the evaluation results.

[0016] The health promotion module is used to call the services of the service center, provide early warnings for high-risk assessments, and coordinate medical resources to provide corresponding medical services.

[0017] Furthermore, the data center includes: The core database is used to store users' real-name authentication information and basic health records.

[0018] The business data repository is used to store dynamic business data generated by various services.

[0019] A rules database is used to store medical knowledge models and logical rules for assessment, early warning, and intervention.

[0020] A statistical database used to store anonymized population health statistics.

[0021] Application repository, used to store configuration information and resource catalogs for applications within the platform.

[0022] Furthermore, the platform integration layer is configured to connect and exchange data with at least one of the following external information systems: regional population health information platform, 120 emergency platform, elderly care service platform, prescription circulation platform, public health platform, internet hospital platform, food and drug administration platform, and e-government platform.

[0023] Furthermore, the method for implementing proactive health and intelligent services on the platform includes: Step S1: Collect multi-source heterogeneous health data through the user interaction layer and the platform integration layer, and store the collected data in the data center after standardization processing.

[0024] Step S2: The application center calls the assessment service in the service center to automatically assess the user's health status based on the rules and data in the data center and generate an assessment report; the application center matches and generates a personalized graded intervention plan according to the risk level in the assessment report, and delivers the intervention plan to the user through the user interaction layer.

[0025] Step S3: For high-risk users, the platform integrates external medical resources to provide services and sends the service results back to the platform, forming a service loop.

[0026] Furthermore, the automated assessment of the user's health status to calculate the assessment result includes: the scientific assessment module of the application center calling the scientific assessment service of the service center to obtain a set of the user's current health indicators, the personal historical baseline data corresponding to the health indicators, and the rate of change data of the health indicators within a preset time period from the data center; the rule engine calculating a risk comprehensive parameter Z based on the assessment model loaded from the rule database, wherein the risk comprehensive parameter Z is a combination of at least the following three risk components: a) a static risk component calculated based on the difference between the current health indicators and the personal historical baseline data; b) a dynamic trend risk component calculated based on the rate of change data of the health indicators; c) an interaction risk component calculated based on the synergistic effect between at least two preset health indicators; and substituting the risk comprehensive parameter Z into a nonlinear activation function to generate the assessment result, which is expressed as a standardized health risk score R.

[0027] Furthermore, the generation of personalized, tiered intervention plans includes: if the risk level is low, then calling the prevention service class of the service center to generate an intervention plan mainly focused on lifestyle improvement; if the risk level is medium, then in addition to generating the intervention plan mainly focused on lifestyle improvement, calling the reminder service and suggesting that the user consult the health management specialist; if the risk level is high, then calling the medical service class of the service center to trigger a risk warning.

[0028] Furthermore, providing services through the platform integration layer in collaboration with external medical resources includes: after triggering a risk warning, guiding users to use the online appointment or two-way referral services in the medical service category of the service center; collaborating with external internet hospital platforms or medical institution information systems through the platform integration layer to execute the online appointment or two-way referral; updating the diagnosis and treatment results returned by the external information system to the user's health record in the data center, and initiating intelligent follow-up services.

[0029] Furthermore, when collecting multi-source heterogeneous health data through the user interaction layer, an adaptive differential transmission strategy based on data priority is adopted. This strategy includes: dividing the health data to be transmitted into three priorities: urgent, important, and routine; transmitting the urgent data using an immediate, high-reliability channel; transmitting the important data using a strategy combining differential transmission and timed packaging; and transmitting the routine data using a batch packaging strategy.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention overcomes the limitations of existing technologies that rely solely on static, isolated threshold judgments by constructing an intelligent health assessment model that integrates individual baselines, dynamic trends, and the synergistic effects of multiple indicators. It enables forward-looking and accurate prediction and proactive discovery of health risks, realizing a shift from disease management to a truly proactive health management model.

[0031] This invention integrates diverse health service resources and constructs a seamless closed-loop management process from data collection, intelligent assessment, personalized intervention to collaborative services. It effectively breaks down data barriers between different systems, solves the problems of broken service chains and inconsistent user experience in existing technologies, and provides users with one-stop, end-to-end smart health services. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the platform module structure of the present invention.

[0033] Figure 2 This is an exemplary flowchart of a health service method implemented on the platform of the present invention. Detailed Implementation

[0034] The present invention will be further described below with reference to specific embodiments.

[0035] This application discloses a proactive health intelligent service multi-supply platform, which aims to provide users with personalized, full-lifecycle health management and intervention services by integrating multi-source heterogeneous health data, advanced assessment and analysis models, and intelligent service distribution mechanisms. This platform can effectively connect users, proactive health devices, and professional service resources, enabling data-driven health status identification, risk warning, and intervention plan generation, significantly improving the efficiency of individual health management and the level of public health services.

[0036] like Figure 1 The diagram shown is a schematic block diagram of a multi-faceted supply platform module for proactive health smart services provided in this embodiment, including: The user interaction layer is used to interact with platform users, proactive health devices, and health management specialists to collect personal health data and issue service instructions. In one embodiment, the user interaction layer is the platform's front end facing the end user. It typically corresponds to a mobile application, the application interface of a smart wearable device, a web portal, or desktop client software, running on the user's smartphone, tablet, PC, or smartwatch. Through these interfaces, the platform can collect user input, questionnaire data, and health data from various sensors in proactive health devices such as smart bracelets, smart blood pressure monitors, blood glucose meters, body fat scales, and electrocardiogram monitors in real time. This data is standardized into a unified structured data package. An example of vital sign data might be: {"userId":"user123","dataType":"heartRate","value":75,"unit":"bpm","timestamp":"2023-10-26T10:30:00Z"}. Simultaneously, this layer is also responsible for receiving service instructions from the platform's core layer and presenting them on the user interface to achieve two-way information interaction between the user and the platform. An example service instruction might look like this: {"command":"showReminder","type":"text","content":"Your walking goal has been achieved!"","targetUser":"user123"}.

[0037] The platform integration layer is used for data exchange and business collaboration with one or more external information systems. In one embodiment, the platform integration layer acts as a bridge connecting the platform with the external healthcare ecosystem. It typically consists of a series of data integration services and API gateways, deployed on the platform's edge server or a dedicated data integration server. This layer enables secure and efficient data exchange and business collaboration with external information systems such as regional population health information platforms, 120 emergency medical service platforms, elderly care service platforms, prescription circulation platforms, public health platforms, internet hospital platforms, food and drug administration platforms, and e-government platforms. Data exchange is usually achieved through standardized protocols, such as HL7, FHIR, DICOM, or custom RESTful APIs, ensuring data interoperability between different systems. For example, when the platform identifies a user as high-risk, it can push anonymized user health data to the 120 emergency medical service platform or send the user's online appointment request to the appointment service interface of the internet hospital platform.

[0038] The platform core layer, connected to the user interaction layer and the platform integration layer, is used to receive and process personal health data and external data, and generate service instructions based on the processing results. In one embodiment, the platform core layer is the "brain" of the entire platform, serving as a backend service cluster, typically deployed on high-performance cloud servers or local data center clusters. It is responsible for receiving and processing massive amounts of personal health data and external data from the user interaction layer and the platform integration layer. This data first undergoes data preprocessing and standardization processes. Based on its complex internal health management logic and AI model analysis results, the platform core layer can generate various service instructions, such as health assessment reports, intervention plans, and risk warning information, and distribute these instructions to the user interaction layer or the platform integration layer.

[0039] A data center is used to categorize, store, and manage all health-related data. In one embodiment, the data center is the platform's data storage and management hub, typically composed of multiple database systems deployed on a dedicated database server cluster. It categorizes, stores, and manages all health-related data, including: a core database for storing users' real-name authentication information and basic health records, usually using a relational database containing fields such as user_id, name, gender, dob, and medical_history_json.

[0040] The business data repository stores dynamic business data generated by various services, such as real-time vital sign monitoring data. A vital sign data record might look like this: {"user_id":"user123","type":"heartRate","value":72,"timestamp":"2023-10-26T15:00:00Z"}.

[0041] The rule database stores medical knowledge models and logical rules used for assessment, early warning, and intervention, such as disease risk assessment model parameters and drug interaction rules. An example of a risk assessment rule might be: {"rule_id":"diabetes_risk_rule","condition":"glucose_fasting>7.0ANDbmi>28","action":{"risk_level":"high"}}. The statistics database stores anonymized population health statistics. A population statistics database might be: {"region":"cityA","age_group":"30-40","avg_bmi":24.5,"diabetes_prevalence":0.08}. The application database stores configuration information and resource directories for applications within the platform. These databases synchronize and interact with each other via a data bus or message queue.

[0042] A service center provides standardized atomic service components. In one embodiment, the service center is the core provider of platform functionality, typically deployed in a microservice architecture on a containerized platform such as a Kubernetes cluster, providing high availability and scalability. It provides standardized atomic service components, each corresponding to a single health service function, such as data cleaning service, feature extraction service, risk assessment algorithm service, intervention plan generation service, etc. Each atomic service has a defined API interface; for example, a risk assessment service might receive {"user_id":"user123","health_metrics":{"glucose":6.5,"bmi":26}} as input and return {"risk_score":0.65,"risk_level":"medium"} as output.

[0043] The application center is used to orchestrate and schedule the atomic service components of the service center according to the preset health management logic, so as to form user-oriented application scenarios.

[0044] The service center includes at least one of the following service clusters: The basic services class provides fundamental support functions for platform operation, including real-name authentication, rule engine, security and privacy protection, resource catalog management, collaborative services, data mining, and information extraction services. In one embodiment, the basic services class provides the underlying general functions required for platform operation. The real-name authentication service ensures the authenticity of user identities and may interface with the Ministry of Public Security's identity authentication system. The rule engine service is an independent component used to execute predefined business logic and medical rules. The security and privacy protection service includes functions such as data encryption, de-identification, and access control. The resource catalog management service provides unified cataloging and management of all data, models, services, and other resources on the platform. The collaborative services support asynchronous communication and task scheduling between different modules and external systems. The data mining and information extraction services are used to discover patterns and extract useful information from raw data.

[0045] The scientific assessment category provides professional health assessment functions, including vital sign monitoring, symptom collection, risk assessment, chronic disease assessment, psychological assessment, data analysis, and health advice generation services. In one embodiment, the scientific assessment services focus on the analysis and diagnosis of the user's health status. The vital sign monitoring service receives and processes real-time physiological data from wearable devices or medical devices such as smart blood pressure monitors and blood glucose meters. The symptom collection service collects subjective symptom descriptions from users through intelligent consultation systems or forms. The risk assessment service, based on medical models and algorithms, quantitatively assesses the risk of users developing specific diseases or health problems. The chronic disease assessment service conducts long-term trend analysis and management for chronic diseases such as diabetes and hypertension. The psychological assessment service provides mental health questionnaires and assessment tools. The data analysis service performs statistical analysis and visualization of multi-source data. The health advice generation service automatically generates personalized health advice reports based on the assessment results.

[0046] The prevention service category provides non-medical proactive intervention and health education functions, including text reminders, voice reminders, information push notifications, health interactions, health education, traditional Chinese medicine (TCM) wellness, and points-based check-in services. In one embodiment, the prevention service category provides non-medical daily health management and intervention methods. Text reminder services send health tips to users via SMS or app messages. Voice reminder services are provided through smart speakers or voice assistants. Information push services push customized health information or activities based on user interests and health status. Health interaction services allow users to participate in health challenges or social groups within the platform. Health education services provide structured health knowledge content. TCM wellness services incorporate TCM theory and provide personalized wellness plans. The points-based check-in service uses gamification mechanisms to incentivize users to maintain healthy habits.

[0047] The healthcare services category provides auxiliary services related to medical procedures, including risk warnings, online appointments, map navigation, two-way referrals, medication guidance, appointment services, and intelligent follow-up services. In one embodiment, the healthcare services category provides auxiliary functions directly related to medical procedures. The risk warning service immediately alerts the user or their emergency contact when an urgent health risk is identified. The online appointment service allows users to directly book appointments with hospitals or doctors within the platform. The map navigation service provides users with route guidance to medical institutions. The two-way referral service supports convenient referrals between different levels of medical institutions. The medication guidance service provides drug information, medication reminders, and adverse reaction monitoring. The appointment service allows users to manage various health service appointments. The intelligent follow-up service uses automated tools to regularly track the user's health status and treatment effectiveness.

[0048] The application center includes a proactive discovery module, which invokes services from the service center to create user profiles and aggregate data, continuously monitoring data changes to identify potential health issues. In one embodiment, the proactive discovery module serves as the entry point and long-term monitoring mechanism for user health management. It invokes data collection services from basic service classes to register and create user profiles, and aggregates and standardizes multi-source health data from the user interaction layer and platform integration layer, storing it in the data center. This module continuously monitors data changes and uses a rule engine or machine learning model, combined with a rule database within the data center, to identify potential health issues and trigger subsequent assessment processes.

[0049] The scientific assessment module is used to call upon services from the service center to conduct multi-dimensional quantitative assessments of potential health problems and create a user health profile.

[0050] Actively adjust the modules to call services from the service center, and generate and push personalized non-medical intervention plans based on the evaluation results.

[0051] The health promotion module is used to call upon services from the service center, provide early warnings for high-risk assessments, and coordinate with medical resources to provide corresponding medical services.

[0052] The data center includes: a core database for storing users' real-name authentication information and basic health records; a business database for storing dynamic business data generated by various services; a rules database for storing medical knowledge models and logical rules used for assessment, early warning, and intervention; a statistics database for storing anonymized population health statistics; and an application database for storing configuration information and resource catalogs of applications within the platform.

[0053] The platform integration layer is configured to connect and exchange data with at least one of the following external information systems: regional population health information platform, 120 emergency platform, elderly care service platform, prescription circulation platform, public health platform, internet hospital platform, food and drug administration platform, and e-government platform.

[0054] like Figure 2 As shown, this embodiment illustrates a method for implementing proactive health and smart services on the platform, including: Step S1 involves collecting multi-source heterogeneous health data through the user interaction layer and platform integration layer, and then standardizing the collected data before storing it in the data center. In one embodiment, the platform collects various health data from users through the user interaction layer, such as manually entered health logs, steps recorded by smartphone applications, and real-time heart rate and sleep data transmitted by smart wearable devices connected via Bluetooth or Wi-Fi. Simultaneously, the platform integration layer exchanges data with external medical information systems to obtain hospital records, physical examination reports, and genetic testing data. This multi-source heterogeneous health data, from different sources and in various formats, such as time-series data streams generated by sensors, FHIR format data packets from medical institutions, and unstructured text entered by users, is transmitted to the platform's core layer. Here, the data processing engine standardizes this data, for example, by unifying different units, filling in missing values, cleaning outliers, and converting it into a unified structured data format before storing it in different databases within the data center.

[0055] Step S2 involves the application center invoking the assessment service within the service center. Based on the rules and data in the data center, the service center automatically assesses the user's health status and generates an assessment report. The application center then matches and generates a personalized, tiered intervention plan based on the risk level in the assessment report and delivers the intervention plan to the user through the user interaction layer. In one embodiment, step S2 is a crucial step in the platform's intelligent analysis and intervention plan generation. The platform's data processing and analysis unit periodically or in real-time invokes the assessment services within the service center, such as risk assessment or chronic disease assessment services in the scientific assessment category. These services automatically assess the user's health status and calculate the assessment results based on the medical knowledge models stored in the rule database and the standardized user health data aggregated in the business database within the data center.

[0056] An example assessment result might look like this: {"userId":"user123","riskLevel":"high","riskScore":0.85,"details":{"bp_status":"stage1_hypertension"}}. This assessment result is typically a structured data package, such as an assessment report containing the user's health risk score, indicators for each risk component, and a list of potential health problems. Based on the risk level in the assessment report, such as low, medium, or high risk, the application center matches and generates personalized, tiered intervention plans. These plans are usually stored as structured objects, containing specific suggestions such as diet plans, exercise plans, and medication reminders. Finally, the platform delivers these intervention plans to users through a user interaction layer via text reminders, voice reminders, and push notifications, achieving precise intervention.

[0057] Step S3: For high-risk users, the platform integrates external medical resources to provide services and sends the service results back to the platform, forming a service loop.

[0058] The automated assessment of a user's health status to calculate the assessment result includes: the application center's scientific assessment module calling the service center's scientific assessment service to obtain a set of the user's current health indicators, the corresponding personal historical baseline data, and the rate of change data of the health indicators within a preset time period from the data center; the rule engine calculating a risk composite parameter Z based on the assessment model loaded from the rule database, wherein the risk composite parameter Z is a combination of at least the following three risk components: a) a static risk component calculated based on the difference between the current health indicators and the personal historical baseline data; b) a dynamic trend risk component calculated based on the rate of change data of the health indicators; c) an interaction risk component calculated based on the synergistic effect between at least two preset health indicators; and substituting the risk composite parameter Z into a nonlinear activation function to generate the assessment result, which is expressed as a standardized health risk score R.

[0059] In one embodiment, the automated assessment of a user's health status is a multi-dimensional, hierarchical calculation process. The scientific assessment module of the application center calls scientific assessment services from the service center. These services obtain a set of current health indicators of the user from the data center, such as current blood pressure, blood sugar, heart rate, weight, etc., and at the same time obtain the personal historical baseline data corresponding to these health indicators, such as average blood pressure and initial weight over the past year, as well as the rate of change of these health indicators within a preset time period, such as the rate of increase in blood sugar over the past week.

[0060] These metrics may be passed in the following structure: {"userId":"user123","currentMetrics":{"bp_systolic":145,"glucose":7.2},"baselineMetrics":{"bp_systolic":120,"glucose":5.5},"changeRates":{"glucose_weekly_change":0.5}} Subsequently, the platform's rule engine calculates a comprehensive risk parameter Z based on an evaluation model loaded from the rule database, such as an expert-knowledge-based decision tree model or a machine learning prediction model. This parameter Z is a combination of at least three risk components: the first is a static risk component calculated based on the difference between the current health metric and the individual's historical baseline data, reflecting the degree of deviation of the user's current health status from normal or historical health levels. A static risk component might be calculated as: static_risk = (current_bp - baseline_bp) / baseline_bp. The second is a dynamic trend risk component calculated based on the rate of change data of the health metric, capturing the trend of deterioration or improvement in health status. A dynamic risk component might be calculated as: dynamic_risk = glucose_weekly_change * weight_factor. The third type is an interaction risk component calculated based on the synergistic effect between at least two preset health indicators, which considers the mutual influence between different health problems. An interaction risk component might be calculated as: interaction_risk = is_hypertension AND is_diabetes ? 0.2 : 0. Finally, the comprehensive risk parameter Z, for example Z = static_risk + dynamic_risk + interaction_risk, is substituted into a nonlinear activation function to generate the assessment result. This assessment result is expressed as a standardized health risk score R, typically between 0 and 1, with a higher R value indicating a greater risk.

[0061] The generation of personalized, tiered intervention plans includes: if the risk level is low, the prevention service category of the service center is invoked to generate an intervention plan mainly focused on lifestyle improvement; if the risk level is medium, in addition to generating an intervention plan mainly focused on lifestyle improvement, reminder services are invoked and suggestions are made for the user to consult a health management specialist; if the risk level is high, the medical service category of the service center is invoked to trigger a risk warning.

[0062] The platform integration layer coordinates with external medical resources to provide services including: after triggering a risk warning, guiding users to use online appointment or two-way referral services in the medical service category of the service center; conducting business collaboration with external Internet hospital platforms or medical institution information systems through the platform integration layer to execute online appointments or two-way referrals; updating the diagnosis and treatment results returned by external information systems to the user's health record in the data center and initiating intelligent follow-up services.

[0063] When collecting multi-source heterogeneous health data through the user interaction layer, an adaptive differential transmission strategy based on data priority is adopted. This strategy includes: dividing the health data to be transmitted into three priorities: urgent, important, and routine; transmitting urgent data using an immediate and highly reliable channel; transmitting important data using a strategy combining differential transmission and timed packaging; and transmitting routine data using a batch packaging strategy.

[0064] In one embodiment, to ensure the efficiency and reliability of multi-source heterogeneous health data transmission, especially under unstable network conditions, the platform employs an adaptive differential transmission strategy based on data priority when collecting data through the user interaction layer. This strategy divides the health data to be transmitted into three priorities: emergency data, important data, and routine data. For emergency data, such as when a user's smart wearable device detects a life-threatening heart rate abnormality or a fall, this data is immediately identified as emergency data, and the system uses an instant, high-reliability channel for transmission, ensuring that the data is sent to the platform's core layer with zero latency and no data loss. An emergency heart rate data packet might be: {"priority":"emergency","userId":"user123","dataType":"heartRate","value":180,"timestamp":"2023-10-26T15:00:00Z"}. For important data, such as daily steps, sleep quality, and blood pressure measurements, the system uses a strategy combining differential transmission and timed packetization for transmission. Differential transmission refers to transmitting only the incremental portion of the data changes. Scheduled packetization refers to packaging changes over a period of time into a single data packet for transmission. A scheduled packet for steps might look like this: {"priority":"important","userId":"user123","dataType":"steps","delta":350,"period":"5min"}. For routine data, such as user daily activity logs and questionnaire responses, the system employs a batch packetization strategy for transmission. This data is typically transmitted in batches during periods of network idleness or after reaching a certain data volume, minimizing the consumption of real-time bandwidth. A batch-packaged questionnaire data packet might look like this: {"priority":"routine","userId":"user123","logType":"mood","data":{"mood":"happy","date":"2023-10-25"}}. This adaptive differential transmission strategy ensures the timeliness and reliability of critical health data while optimizing overall network resource utilization.

[0065] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the scope defined by the invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A proactive health and smart service diversified supply platform, characterized in that: include, The user interaction layer is used to interact with platform users, proactive health devices, and health management specialists to collect personal health data and issue service instructions. The platform integration layer is used for data exchange and business collaboration with one or more external information systems; The platform core layer, connected to the user interaction layer and the platform integration layer, is used to receive and process the personal health data and external data, and generate the service instructions based on the processing results. The core layer of the platform includes: Data centers are used to categorize, store, and manage all health-related data; The service center is used to provide standardized atomic service components; The application center is used to orchestrate and schedule the atomic service components of the service center according to the preset health management logic, so as to form application scenarios for the user.

2. The proactive health smart service diversified supply platform according to claim 1, characterized in that: The service center includes at least one of the following service clusters. Basic services provide the basic support functions for platform operation, including real-name authentication, rule engine, security and privacy protection, resource directory management, collaborative services, data mining and information extraction services; Scientific assessment category provides professional health assessment functions, including vital sign monitoring, symptom collection, risk assessment, chronic disease assessment, psychological assessment, data analysis, and health advice generation services; Preventive services provide non-medical proactive intervention and health education functions, including text reminders, voice reminders, information push, health interaction, health education, traditional Chinese medicine health preservation, and points check-in services; Medical services provide auxiliary services related to medical procedures, including risk warning, online appointment, map navigation, two-way referral, medication guidance, appointment services, and intelligent follow-up services.

3. The proactive health smart service diversified supply platform according to claim 1, characterized in that: The application center includes an active discovery module, which is used to call the services of the service center to realize user profile creation and data aggregation, and continuously monitor data changes to identify potential health problems; The scientific assessment module is used to call the services of the service center to conduct multi-dimensional quantitative assessments of the potential health problems and form a user health profile. The module is actively adjusted to call the services of the service center and generate and push personalized non-medical intervention plans based on the evaluation results; The health promotion module is used to call the services of the service center, provide early warnings for high-risk assessments, and coordinate medical resources to provide corresponding medical services.

4. The proactive health smart service diversified supply platform according to claim 1, characterized in that: The data center includes, The core database is used to store users' real-name authentication information and basic health records; A business data repository is used to store dynamic business data generated by various services. A rules database is used to store medical knowledge models and logical rules for assessment, early warning, and intervention. A statistical database used to store desensitized population health statistics; Application repository, used to store configuration information and resource catalogs for applications within the platform.

5. The proactive health smart service diversified supply platform according to claim 1, characterized in that: The platform integration layer is configured to connect and exchange data with at least one of the following external information systems: regional population health information platform, 120 emergency platform, elderly care service platform, prescription circulation platform, public health platform, internet hospital platform, food and drug administration platform, and e-government platform.

6. The proactive health intelligent service diversified supply platform according to claim 1, wherein the method for implementing proactive health intelligent services on the platform is characterized in that: include, Step S1: Collect multi-source heterogeneous health data through the user interaction layer and the platform integration layer, and store the collected data in the data center after standardization processing. Step S2: The application center calls the assessment service in the service center to automatically assess the user's health status based on the rules and data in the data center and generate an assessment report. The application center matches and generates personalized, graded intervention plans based on the risk levels in the assessment report, and delivers the intervention plans to users through the user interaction layer; Step S3: For high-risk users, the platform integrates external medical resources to provide services and sends the service results back to the platform, forming a service loop.

7. The proactive health smart service diversified supply platform according to claim 6, characterized in that: The automated assessment of the user's health status to calculate the assessment result includes: the scientific assessment module of the application center calling the scientific assessment service of the service center to obtain a set of the user's current health indicators, the personal historical baseline data corresponding to the health indicators, and the rate of change data of the health indicators within a preset time period from the data center; the rule engine calculating a risk comprehensive parameter Z based on the assessment model loaded from the rule database, wherein the risk comprehensive parameter Z is a combination of at least the following three risk components: a) a static risk component calculated based on the difference between the current health indicators and the personal historical baseline data; b) a dynamic trend risk component calculated based on the rate of change data of the health indicators; c) an interaction risk component calculated based on the synergistic effect between at least two preset health indicators; and substituting the risk comprehensive parameter Z into a nonlinear activation function to generate the assessment result, which is expressed as a standardized health risk score R.

8. The proactive health smart service diversified supply platform according to claim 6, characterized in that: The generation of personalized, tiered intervention plans includes: if the risk level is low, then calling the prevention service class of the service center to generate an intervention plan mainly focused on lifestyle improvement; if the risk level is medium, then in addition to generating the intervention plan mainly focused on lifestyle improvement, calling the reminder service and suggesting that the user consult the health management specialist; if the risk level is high, then calling the medical service class of the service center to trigger a risk warning.

9. The proactive health smart service diversified supply platform according to claim 6, characterized in that: The platform integration layer coordinates with external medical resources to provide services including: after triggering a risk warning, guiding users to use the online appointment or two-way referral services in the medical service category of the service center; conducting business collaboration with external Internet hospital platforms or medical institution information systems through the platform integration layer to execute the online appointment or two-way referral; updating the diagnosis and treatment results returned by the external information system to the user's health record in the data center, and initiating intelligent follow-up services.

10. A proactive health smart service diversified supply platform according to claim 6, characterized in that: When collecting multi-source heterogeneous health data through the user interaction layer, an adaptive differential transmission strategy based on data priority is adopted. This strategy includes: dividing the health data to be transmitted into three priorities: urgent, important, and routine; transmitting the urgent data using an immediate, high-reliability channel; transmitting the important data using a strategy combining differential transmission and timed packaging; and transmitting the routine data using a batch packaging strategy.

Images