Data processing method and system for health management platform

Abstract

The invention relates to the technical field of data processing, in particular to a data processing method and system for a health management platform, and the method comprises the steps: connecting a wearable device, a medical institution information system and a user manual input channel through a multi-interface data collection unit, collecting multi-source health data, and carrying out the standardized integration; after the integration is completed, encrypting the data, and constructing a distributed storage architecture based on a block chain technology to store the multi-source health data; constructing a user health baseline model according to the multi-source health data to calculate various health indexes of the user, analyzing the health data of the user through a machine learning technology, and performing real-time monitoring; and generating a personalized intervention scheme according to an analysis result, establishing an intervention effect feedback mechanism, and optimizing the personalized intervention scheme according to a feedback result. According to the invention, the service level of the health management platform is improved through standardized data integration, privacy protection enhancement and user personalized analysis model construction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a data processing method and system of a health management platform. BACKGROUND

[0002] With the improvement of people's health awareness, health management platforms have gradually become an important carrier connecting users, medical institutions and health service providers. However, there are many problems in the data processing of current health management platforms: first, the data sources are scattered and have various formats, including the exercise and heart rate data uploaded by users through wearable devices, the physical examination reports and medical records provided by medical institutions, and the diet and sleep information manually entered by users. These data formats are not unified and are difficult to effectively integrate; second, the data privacy protection is insufficient, as health data contains a large amount of personal sensitive information, and existing processing methods are prone to leakage risks during data transmission and storage; third, the data analysis accuracy is low, and it is difficult to construct personalized health models combined with the multi-dimensional health data of users, resulting in a lack of pertinence in health assessment and intervention suggestions. These problems seriously restrict the service quality and user trust of health management platforms. SUMMARY

[0003] The present application provides a data processing method and system of a health management platform to solve the problems of integration difficulty, low privacy security and inaccurate analysis in the data processing of existing health management platforms, and to improve the health management service level of the platform.

[0004] The present application is achieved by the following technical solutions: A data processing method of a health management platform is provided, which comprises the following steps: Step S10: Collecting multi-source health data and performing standardized integration through a multi-interface data acquisition unit connected to wearable devices, medical institution information systems and user manual input channels; Step S20: After integration, encrypting the data and storing the multi-source health data in a distributed storage architecture based on blockchain technology; Step S30: Calculating user health indicators based on the user health baseline model constructed from multi-source health data, and analyzing user health data and real-time monitoring through machine learning technology; Step S40: Generating personalized intervention programs based on the analysis results, and establishing an intervention effect feedback mechanism to optimize the personalized intervention programs based on the feedback results.

[0005] Preferably, the step of collecting multi-source health data and performing standardized integration in step S10 comprises: Multi-source health data collection: For wearable device data, real-time receive JSON format time series data such as exercise steps, heart rate and sleep duration through Bluetooth or WiFi, for medical institution data, get XML format structured data such as physical examination indicators and diagnosis results through HL7 FHIR standard interface, for user manual input data, provide standardized forms to convert unstructured information such as diet types and daily water intake into key-value pair format storage; Health data standardization and integration: Establish a health data standard library, define unified data elements and coding rules, use ICD-10 disease coding and LOINC laboratory index coding, clean and convert the collected data through ETL tools, and associate multi-source data through user unique identifier to form a complete user personal health record.

[0006] Preferably, the step S20 includes the step of encrypting the data after integration and storing the multi-source health data in a distributed storage architecture based on blockchain technology. Data encryption: Use end-to-end encryption technology to encrypt health data to ensure that health data cannot be cracked during transmission from the collection end to the platform, and use digital signature technology to verify the identity of the data sender to prevent data tampering or forgery; Data storage: Based on blockchain technology, build a distributed storage architecture, split user health data into a certain number of data blocks, generate a unique hash value for each data block and upload it to the blockchain, store the encrypted user health data in a distributed server, and users have data access rights through private keys. Medical institutions or service providers can access specified data blocks by obtaining user authorization and completing smart contract verification, ensuring the privacy and security of user health data. In addition, regular security checks are performed on the distributed server, and when abnormal access behavior is detected, the warning mechanism is automatically triggered.

[0007] Preferably, the step S30 includes the step of calculating user health indicators based on the multi-source health data to build a user health baseline model and analyzing user health data in real time through machine learning technology. Build user health baseline model: Based on the integrated multi-source health data, build a user health baseline model, including health data range definition, abnormal data removal, health indicator classification, health feature parameter extraction, baseline calculation method selection, determination of calculation parameters and baseline model verification and establishment of dynamic update mechanism. Calculate the normal range of user health indicators through the user health baseline model. For chronic disease patients, set disease-specific indicator thresholds in combination with clinical diagnosis results; User health data analysis: multi-dimensional analysis of user health data using machine learning algorithms, prediction of health index trend through time series analysis, analysis of the correlation between diet, exercise and health index using decision tree algorithm, integration of clinical guidelines using knowledge graph technology, and mapping of user health data analysis results to understandable health conclusions; User health data real-time monitoring: when real-time collected user health data exceeds the range calculated by user health baseline model or reaches the warning threshold, automatic triggering of hierarchical response mechanism, pushing health suggestions for mild abnormalities, reminding users to contact family doctors for moderate abnormalities, and automatically sending help notifications containing positioning information to emergency contacts for severe abnormalities.

[0008] Preferably, the step S40 of generating a personalized intervention plan according to the analysis result and establishing an intervention effect feedback mechanism comprises: Personalized intervention plan: generating a personalized intervention plan according to the analysis result, including specific suggestions in the dimensions of diet, exercise and work and rest, such as "walking 8000 steps a day, reducing refined sugar intake, and increasing green leafy vegetables for dinner", and the plan needs to be adjusted according to the user's living habits to ensure feasibility; Intervention effect feedback mechanism: establishing an intervention effect feedback mechanism, collecting intervention execution data through user daily check-in and regular index detection, using comparative analysis method to perform difference test on health indexes before and after intervention, such as t test, evaluating the effectiveness of the plan, dynamically optimizing the intervention plan according to the evaluation result, automatically adjusting to a lower difficulty when a certain target has not been achieved for 3 consecutive days, such as reducing daily exercise from 8000 steps to 6000 steps when the daily exercise target has not been achieved, and adjusting the intervention measures when the index improvement is not as expected.

[0009] In addition, to achieve the above purpose, the present application also provides a data processing system of a health management platform, which comprises: Multi-source health data collection and standardized integration module: used for collecting multi-source health data and performing standardized integration through multi-interface data collection unit to wearable devices, medical institution information system and user manual input channels; Data encryption and storage module: used for encrypting the data after integration, and storing the multi-source health data by using distributed storage architecture based on blockchain technology; Health data analysis and monitoring module: used for calculating user health indicators according to user health baseline model constructed from multi-source health data, and analyzing user health data and real-time monitoring by using machine learning technology; Personalized intervention plan generation and optimization module: used for generating a personalized intervention plan according to the analysis result, establishing an intervention effect feedback mechanism, and optimizing the personalized intervention plan according to the feedback result.

[0010] In addition, to achieve the above object, the present application also provides a data processing device of a health management platform, comprising a memory, a processor, and a health management platform data processing algorithm program stored in the memory and executable on the processor, wherein the health management platform data processing algorithm program is used to realize the steps of the health management platform data processing method.

[0011] In addition, to achieve the above object, the present application also provides a computer program product comprising a health management platform data processing algorithm program, wherein the health management platform data processing algorithm program is used to realize the health management platform data processing method when executed by a processor.

[0012] The present application has the following advantages and effects: The health management platform data processing method and system provided by the present application solves the problem of scattered and disordered data of the health management platform through multi-source data standardization and integration, lays a foundation for accurate analysis, realizes fine management of data authority by using a privacy protection mechanism based on a block chain, guarantees the safety of sensitive information of users, improves the accuracy of health assessment and the pertinence of intervention suggestions by using personalized modeling and analysis technology, helps users to realize active health management, improves the user compliance and enhances the health management effect through dynamic optimization of intervention schemes. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0014] Figure 1 The flow chart of the health management platform data processing method of the present application.

[0015] Figure 2 The structural schematic diagram of the health management platform data processing system of the present application.

[0016] Figure 3 The structural schematic block diagram of the health management platform data processing electronic device of the present application. DETAILED DESCRIPTION

[0017] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0018] As shown in the drawings, in one embodiment of the present application, a data processing method of a health management platform comprises the following steps: Figure 1 Step S10: Collecting multi-source health data and performing standardized integration through a multi-interface data collection unit connected to wearable devices, medical institution information systems and user manual input channels. Step S10: Collecting multi-source health data and performing standardized integration through a multi-interface data collection unit connected to wearable devices, medical institution information systems and user manual input channels.

[0019] Specifically, the step of collecting multi-source health data and performing standardized integration in step S10 comprises: Multi-source health data collection: For wearable device data, real-time receive time series data such as motion steps, heart rate and sleep duration in JSON format through Bluetooth or WiFi, for medical institution data, obtain structured data such as physical examination indicators and diagnosis results in XML format through HL7 FHIR standard interface, for user manual input data, provide standardized forms to convert unstructured information such as food types and daily water intake into key-value pair format storage, for example, collect daily upload of early, midday and evening blood pressure data of patient's intelligent blood pressure meter, including systolic pressure, diastolic pressure and measurement time, blood lipid, electrocardiogram data in hospital annual physical examination report, and daily salt intake and exercise duration input by patients through the platform.

[0020] Health data standardized integration: Establish a health data standard library, define unified data elements such as "blood pressure" containing subfields such as systolic pressure, diastolic pressure and measurement time, and coding rules, adopt ICD-10 disease coding and LOINC laboratory index coding, clean and convert the collected data through ETL tools, for example, map the "heart rate" field of different devices to "heart_rate", unify the date format to "yyyy-MM-dd HH:mm:ss", and associate multi-source data through user unique identifier such as ID card number hash value, form a complete user personal health record, for example, according to the health data standard library, unify the "systolic pressure" field to "systolic_bp", and associate all data through the patient's ID card number hash value, generate a personal health record containing 12 months of historical records.

[0021] Step S20: After integration, encrypt the data and store the multi-source health data in a distributed storage architecture based on blockchain technology.

[0022] Specifically, the step of encrypting the data after integration in step S20 and constructing a distributed storage architecture based on blockchain technology to store multi-source health data includes: Data encryption: End-to-end encryption technology such as AES-256 algorithm is used to encrypt health data to ensure that health data cannot be cracked during transmission from the collection end to the platform. At the same time, digital signature technology is used to verify the identity of the data sender to prevent data tampering or forgery. For example, blood pressure data is encrypted using AES-256, and when stored, it is split into 3 data blocks, and the hash value is uploaded to the blockchain. Patients authorize family doctors to access data through private keys.

[0023] Data storage: Based on blockchain technology, a distributed storage architecture is constructed to split user health data into a certain number of data blocks, generate a unique hash value for each data block, and upload it to the blockchain. User health data is stored in a distributed server after encryption, and users have data access rights through private keys. Medical institutions or service providers obtain user authorization and complete smart contract verification to access specified data blocks, ensuring the privacy and security of user health data. In addition, regular security checks are performed on the distributed server to detect abnormal access behavior such as multiple failed login attempts or unauthorized IP address access, triggering an early warning mechanism to ensure data storage security. For example, if a stranger IP attempts to access data multiple times, an early warning is triggered and the IP's access rights are frozen.

[0024] Step S30: Calculate user health indicators based on multi-source health data to build user health baseline model and analyze user health data in real time through machine learning technology.

[0025] Specifically, the step of calculating user health indicators based on multi-source health data to build user health baseline model and analyze user health data in real time through machine learning technology in step S30 includes: Build user health baseline model: Based on integrated multi-source health data, build user health baseline model, including health data range definition, abnormal data removal, health indicator classification, health feature parameter extraction, baseline calculation method selection, determination of calculation parameters, and baseline model verification and establishment of dynamic update mechanism. Calculate the normal range of user health indicators such as resting heart rate fluctuation interval and fasting blood glucose baseline value through the user health baseline model. For chronic disease patients, combine clinical diagnosis results to set disease-specific indicator thresholds, such as a 2-hour postprandial blood glucose threshold of 10.0 mmol / L for diabetic patients. User health data analysis: Multi-dimensional analysis of user health data using machine learning algorithms, predicting health index trends through time series analysis such as LSTM models, for example, predicting blood sugar peak values next week based on 7 consecutive days of blood sugar data, using decision tree algorithms to analyze the correlation between diet, exercise and health indicators, such as identifying the correlation between "high-salt diet + sedentary" and high blood pressure, integrating clinical guidelines using knowledge graph technology, mapping user health data analysis results to understandable health conclusions, such as "current blood pressure is high, which may be related to excessive salt intake in the past 3 days"; Real-time monitoring of user health data: When real-time collected user health data exceeds the range calculated by the user health baseline model, such as a 15% or more sudden increase in heart rate, or reaching the warning threshold, automatically triggering a hierarchical response mechanism, pushing health recommendations for mild abnormalities, such as suggesting resting for 10 minutes and rechecking heart rate, reminding users to contact family doctors for moderate abnormalities, and automatically sending help notifications with location information to emergency contacts for severe abnormalities.

[0026] For example, calculate the patient's blood pressure baseline, with a normal range of systolic pressure 120-135mmHg and diastolic pressure 70-85mmHg, set the high blood pressure warning threshold as systolic pressure ≥140mmHg or diastolic pressure ≥90mmHg, and through the LSTM model prediction display, if the current diet pattern is maintained, the systolic pressure will rise to 145mmHg next week; through decision tree analysis, it is found that when salt intake >6g / day and exercise <30 minutes / day, the probability of blood pressure exceeding the standard increases by 60%.

[0027] Step S40: Generate personalized intervention programs based on analysis results and establish intervention effect feedback mechanisms to optimize personalized intervention programs based on feedback results.

[0028] Specifically, in step S40, personalized intervention programs are generated based on analysis results, and intervention effect feedback mechanisms are established, including: Personalized intervention programs: Generate personalized intervention programs based on analysis results, including specific recommendations for diet, exercise and work-rest dimensions, such as "walk 8000 steps a day, reduce refined sugar intake, and increase green leafy vegetables for dinner", the program needs to be adjusted based on the user's lifestyle, such as vegetarian preference and working hours, to ensure feasibility; Intervention Effect Feedback Mechanism: An intervention effect feedback mechanism will be established. This mechanism will collect intervention implementation data through daily user check-ins (such as uploading photos of food and exercise records) and regular indicator monitoring (such as weekly weight measurements). Comparative analysis methods will be used to examine the differences in health indicators before and after the intervention, such as t-tests, to evaluate the effectiveness of the program. The intervention program will be dynamically optimized based on the evaluation results. If a certain goal is not achieved for three consecutive days, the difficulty level will be automatically adjusted to a lower level. For example, if the daily exercise goal is not achieved, the daily exercise will be reduced from 8,000 steps to 6,000 steps. If the improvement of an indicator does not meet expectations, such as a blood pressure reduction of less than 5%, the intervention measures will be adjusted based on the evaluation results, such as adding meditation relaxation suggestions.

[0029] For example, the initial plan included a daily salt intake of ≤5g, 40 minutes of brisk walking, and blood pressure monitoring 7 times a week. After 2 weeks, feedback showed that the patient's salt intake met the target but the exercise was only 50% complete. The plan was then adjusted to "30 minutes of brisk walking + 1 hour of cycling on weekends". After 1 month, the blood pressure dropped by an average of 8 mmHg. The plan was further optimized to "add 10 minutes of meditation every day" to further improve blood pressure fluctuations.

[0030] In addition, such as Figure 2 As shown, in one embodiment of the present invention, a data processing system for a health management platform is proposed, the system comprising: Multi-source health data collection and standardized integration module: Used to connect to wearable devices, medical institution information systems and user manual input channels through multi-interface data collection units to collect multi-source health data and perform standardized integration; Data encryption and storage module: used to encrypt the data after integration, and to store multi-source health data using a distributed storage architecture based on blockchain technology; Health data analysis and monitoring module: used to build a user health baseline model based on multi-source health data, calculate various health indicators of users, analyze user health data and monitor it in real time through machine learning technology; Personalized intervention plan generation and optimization module: This module generates personalized intervention plans based on the analysis results, establishes a feedback mechanism for intervention effects, and optimizes the personalized intervention plans based on the feedback results.

[0031] This application provides a data processing system for a health management platform, employing a data processing method for a health management platform as described in the above embodiments. This system addresses the technical problems of low data integration and inaccurate data analysis in traditional health management platforms. Compared to existing technologies, the beneficial effects of the data processing system for a health management platform provided in this application are the same as those of the data processing method for a health management platform provided in the above embodiments. Furthermore, other technical features of the data processing system for a health management platform are the same as those disclosed in the methods of the above embodiments, and will not be elaborated upon here.

[0032] This application provides a data processing device for a health management platform, the data processing device for the health management platform comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the data processing method of the health management platform in the first embodiment described above.

[0033] like Figure 3 As shown in the illustration, in one embodiment of the present invention, a structural schematic diagram of a data processing device suitable for implementing a health management platform according to an embodiment of the present application is presented. The data processing device for a health management platform according to an embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The data processing device of the health management platform shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0034] Figure 3The data processing apparatus of a health management platform can include a processing system 1001 (e.g., a central processor, a graphics processor, etc.) that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or loaded from a storage system 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the data processing apparatus of a health management platform are also stored in the RAM 1004. The processing system 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input system 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage system 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication system 1009. The communication system 1009 can allow the data processing apparatus of a health management platform to communicate with other devices wirelessly or by wire to exchange data. Although the data processing apparatus of a health management platform with various systems is shown in the figure, it should be understood that all of the illustrated systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0035] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product including a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through a communication system, or installed from the storage system 1003, or installed from the ROM 1002. When the computer program is executed by the processing system 1001, the above-described functions defined in the methods of embodiments of the present disclosure are performed.

[0036] The health management platform data processing device provided by the application can solve the technical problem of low data processing integration and inaccurate data analysis of the traditional health management platform. Compared with the prior art, the health management platform data processing device provided by the application has the same beneficial effects as the health management platform data processing method provided by the above-mentioned embodiments, and other technical features in the health management platform data processing device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0037] Parts of the application can be implemented in hardware, software, firmware, or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0038] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the health management platform data processing method as described above.

[0039] The computer program product provided by the application can solve the technical problem of low data processing integration and inaccurate data analysis of the traditional health management platform. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the health management platform data processing method provided by the above-mentioned embodiments, which will not be repeated here.

[0040] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and variations.

Claims

1. A data processing method of a health management platform, characterized by, The method comprises the following steps: Step S10: Collecting multi-source health data and performing standardized integration through data acquisition unit, wearable device, medical institution information system and user manual input channel; Step S20: After integration, encrypting the data and storing the multi-source health data in a distributed storage architecture based on blockchain technology; Step S30: Calculating user health indicators based on the multi-source health data, analyzing user health data through machine learning technology and real-time monitoring; Step S40: Generating personalized intervention programs based on the analysis results and establishing an intervention effect feedback mechanism to optimize the personalized intervention programs based on the feedback results.

2. The data processing method of a health management platform according to claim 1, wherein, The step S10 of collecting multi-source health data and performing standardized integration comprises: Multi-source health data collection: For wearable device data, real-time receive JSON format time series data of motion steps, heart rate and sleep duration through Bluetooth or WiFi, for medical institution data, obtain XML format structured data of physical examination indicators and diagnosis results through HL7 FHIR standard interface, for user manual input data, provide standardized forms to convert unstructured information of diet types and daily water consumption into key-value pair format storage; Health data standardized integration: Establish a health data standard library, define unified data elements and coding rules, use ICD-10 disease coding and LOINC laboratory index coding, clean and convert the collected data through ETL tools, and associate multi-source data through user unique identification to form a complete user personal health record.

3. The data processing method of claim 1, wherein, The step S20 of encrypting the data after integration and storing the multi-source health data in a distributed storage architecture based on blockchain technology comprises: Data encryption: Encrypt health data using end-to-end encryption technology, and verify the identity of the data sender through digital signature technology; Data storage: Based on blockchain technology, build a distributed storage architecture, split user health data into a certain number of data blocks, generate a unique hash value for each data block and upload it to the blockchain, store the encrypted user health data in a distributed server, users have data access rights through private keys, medical institutions or service providers obtain user authorization and complete smart contract verification to access specified data blocks, in addition, regularly check the security of the distributed server, and when abnormal access behavior is detected, automatically trigger the early warning mechanism.

4. The data processing method of a health management platform according to claim 1, wherein, The step S30 of calculating user health indicators based on the multi-source health data, analyzing user health data through machine learning technology and real-time monitoring comprises: Building a user health baseline model: based on the integrated multi-source health data, a user health baseline model is built, including health data range definition, abnormal data removal, health index classification, health feature parameter extraction, baseline calculation method selection, determination of calculation parameters and baseline model verification and establishment of dynamic updating mechanism, through the user health baseline model, the normal range of each health index of the user is calculated, for chronic disease patients, combined with clinical diagnosis results, set disease-specific index threshold; User health data analysis: using machine learning algorithm for multi-dimensional analysis of user health data, predicting the trend of health index change through time series analysis, analyzing the correlation between diet, exercise and health index using decision tree algorithm, integrating clinical guidelines using knowledge graph technology, mapping user health data analysis results to health conclusions; Real-time monitoring of user health data: when the real-time collected user health data exceeds the range calculated by the user health baseline model, or reaches the warning threshold, the hierarchical response mechanism is automatically triggered.

5. The data processing method of a health management platform according to claim 1, wherein, The step S40 of generating a personalized intervention scheme according to the analysis result and establishing an intervention effect feedback mechanism comprises: Personalized intervention scheme: generating a personalized intervention scheme according to the analysis result, including specific suggestions for diet, exercise and work and rest, adjusting the scheme according to the user's living habits; Intervention effect feedback mechanism: establish an intervention effect feedback mechanism, collect intervention execution data through user daily check-in and regular index detection, use comparative analysis method to test the difference of health index before and after intervention, evaluate the effectiveness of the scheme, dynamically optimize the intervention scheme according to the evaluation result, automatically adjust the difficulty when a certain target is not achieved for 3 consecutive days, adjust the intervention measures when the index improvement does not meet the expectation.

6. A data processing system of a health management platform, characterized by, The data processing system of the health management platform comprises: Multi-source health data collection and standardized integration module: used for collecting multi-source health data through data collection unit and standardizing integration of wearable devices, medical institution information system and user manual input channel; Data encryption and storage module: used for encrypting the data after integration, and storing the multi-source health data by using distributed storage architecture based on blockchain technology; Health data analysis and monitoring module: used for calculating user health indicators based on multi-source health data, analyzing user health data and real-time monitoring by using machine learning technology; Personalized intervention scheme generation and optimization module: used for generating a personalized intervention scheme according to the analysis result, and establishing an intervention effect feedback mechanism, and optimizing the personalized intervention scheme according to the feedback result.

7. A data processing device of a health management platform, characterized by, The data processing device of the health management platform comprises: A memory, a processor and a health management platform data processing program stored on the memory and executable on the processor, wherein the health management platform data processing program is executed by the processor to realize the health management platform data processing method of any one of claims 1 to 5. The data processing device of the health management platform comprises:

8. A computer program product, characterised in that, The computer program product comprises a data processing program of a health management platform, which, when executed by a processor, implements the data processing method of the health management platform according to any one of claims 1 to 5.

Images