Personalization-based health service customization system

Abstract

The invention discloses a health service customization system based on personalization, and relates to the technical field of health data processing, the health service customization system comprises a data acquisition module, a scheme generation module and a scheme adjustment module, multi-source data and environmental data are acquired, and multi-dimensional data fusion and dynamic feature extraction are performed; generating a personalized health scheme based on the health data of the user; through a flexible production technology, on the basis of health requirements and data of a user, personalized health products are customized, personalized suggestions are provided for the user, and an exercise scheme is automatically adjusted according to the achievement condition of a health goal. According to the system, intelligent processing and dynamic adjustment of the health data are achieved, the accuracy of the prediction result is ensured, the system can adjust the exercise intensity according to the real-time health data of the user, and the exercise experience and the health effect of the user are improved; by automatically adjusting the health goals, the system ensures the continuity and effect of health management.

Description

Technical Field

[0001] The present invention relates to the technical field of health data processing, and in particular to a personalized health service customization system. Background Art

[0002] With the rapid development of wearable devices, the Internet of Things, and artificial intelligence technologies, personalized health management systems have become a research hotspot in the field of modern health services. Such systems integrate data from a variety of sensors, such as smart watches, smart rings, and smart blood pressure monitors, to monitor users' physiological indicators in real time. At the same time, environmental monitoring equipment is also introduced to evaluate the impact of the external environment on personal health. At the data processing level, big data analysis and machine learning technologies are applied to the processing and prediction of health data to generate personalized health plans. The core of this type of technology is to provide personalized health intervention plans through in-depth analysis of health data, to help users optimize their living habits and improve their health. However, existing technologies are still in the early stages of development, and the real-time and accuracy of the system and the degree of customization of personalized plans need to be improved.

[0003] Existing personalized health data processing technologies still have obvious deficiencies in many aspects. The breadth and depth of health data collection are limited, and are usually limited to certain physiological indicators, such as heart rate, blood pressure, etc., and fail to fully integrate multi-dimensional information such as users' living habits and environmental data. This single data source makes it difficult for the system to comprehensively assess the user's health status when generating a health plan. Although existing technologies can provide certain prediction functions based on historical data, their dynamic feature extraction capabilities are weak and cannot achieve efficient processing and prediction of real-time health data, which greatly reduces the timeliness and accuracy of personalized health plans. In addition, existing systems also have limitations in the customization of health products. Most of them recommend general products and lack customized product solutions that are precisely generated according to individual needs. Finally, the achievement of users' health goals is not dynamically monitored and fed back, and the system cannot automatically adjust the health plan according to the user's progress, resulting in a lack of flexibility in the implementation of personalized plans. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing personalized health service system has the problems of single data collection, insufficient real-time dynamic analysis, lack of personalization in customized health products, and how to generate more personalized health plans and automatically adjust user health goals.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a personalized health service customization system, comprising a data acquisition module, a plan generation module and a plan adjustment module; the data acquisition module is used to collect multi-source data and environmental data, and perform multi-dimensional data fusion and dynamic feature extraction; the plan generation module is used to generate a personalized health plan based on the user's health data; the plan adjustment module is used to customize personalized health products based on the user's health needs and data through flexible production technology, provide users with personalized suggestions, and automatically adjust the exercise plan according to the achievement of health goals.

[0007] As a preferred solution of the personalized health service customization system described in the present invention, the multi-source data is collected through wearable devices, including smart watches, smart rings, and smart glasses, which collect different health data in real time; heart rate, sleep, and exercise steps are monitored in real time through smart watches; blood oxygen saturation and body temperature fluctuations are monitored through smart rings; user fatigue and focus changes are monitored through smart glasses to detect mental fatigue status; environmental data include PM2.5 concentration, humidity, and temperature in the air.

[0008] As a preferred solution of the personalized health service customization system described in the present invention, the multi-dimensional data fusion and dynamic feature extraction include fusing the collected multi-source data with environmental data to build a comprehensive health profile of the user, extracting key health indicators through feature engineering, and establishing a health feature portrait of the user; using dynamic feature extraction technology to perform real-time analysis on the health data collected by wearable devices, and outputting the user's health score and health trend; using a long short-term memory network LSTM to predict the user's health trend, and using a forget gate to predict the user's health trend. Decide whether to keep the previous health data by inputting the gate Determine the impact of the current data through the cell state , the results of the forget gate and the input gate are integrated to update the current state; based on the user's health history data, a random forest is used to establish a health scoring model to evaluate the user's health status in real time.

[0009] As a preferred solution of the personalized health service customization system described in the present invention, the generation of a personalized health plan includes generating a personalized diet plan based on the user's basal metabolic rate, exercise consumption and dietary preferences, generating dietary recommendations containing corresponding nutrients when there are different physiological needs of different users, monitoring the dietary effects in real time, and dynamically adjusting the personalized diet plan; generating a corresponding exercise plan based on the user's exercise preferences, physical condition and sports injury history, and adjusting the exercise intensity and type in real time in combination with health goals.

[0010] As a preferred solution of the personalized health service customization system described in the present invention, the customized personalized health products include flexible production technology based on Industry 4.0, real-time adjustment of production plans according to the physiological needs of different users, and generation of customized supplement formulas based on the output user health scores and health trends.

[0011] As a preferred solution of the personalized health service customization system described in the present invention, the provision of personalized suggestions to users includes providing health consultation in voice or text form based on the analysis results of user health data, using natural language processing technology, and using APP to communicate with virtual health consultants to obtain personalized health suggestions.

[0012] As a preferred solution of the personalized health service customization system described in the present invention, the real-time adjustment of exercise intensity and type in combination with health goals includes that when the user completes the health goal within the customized time period, the system will automatically issue an encouragement notification and adjust the goal difficulty; when the user fails to complete the health goal within the customized time period, the reasons are analyzed and a new action plan is recommended.

[0013] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a personalized health service customization system.

[0014] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a personalized health service customization system.

[0015] Beneficial effects of the present invention: The personalized health service customization system provided by the present invention realizes intelligent processing and dynamic adjustment of health data, so that the system can cope with long-term health monitoring needs and ensure the accuracy of prediction results; generates personalized exercise plans, which not only improves the user's health management ability, but also reduces the risk of sports injuries; the system can adjust the exercise intensity according to the user's real-time health data, avoids overtraining or improper exercise, and improves the user's exercise experience and health effects; by automatically adjusting health goals, the system ensures the continuity and effectiveness of health management. The present invention achieves better results in flexibility, accuracy and personalization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is an overall flow chart of a personalized health service customization system provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a personalized health service customization system, including a data collection module, a plan generation module and a plan adjustment module.

[0020] The data acquisition module is used to collect multi-source data and environmental data, and perform multi-dimensional data fusion and dynamic feature extraction.

[0021] Furthermore, multi-source data is collected through wearable devices, including smart watches, smart rings, and smart glasses, which collect different health data in real time; smart watches monitor heart rate, sleep, and exercise steps in real time; smart rings monitor blood oxygen saturation and body temperature fluctuations; smart glasses monitor the user's fatigue and focus changes and detect mental fatigue status; environmental data include PM2.5 concentration, humidity, and temperature in the air.

[0022] It should be noted that the PM2.5, temperature and humidity data in the user's living environment can be monitored and collected daily through the installed air quality sensors and temperature and humidity sensors.

[0023] It should also be noted that multi-dimensional data fusion and dynamic feature extraction include fusing the collected multi-source data with environmental data, building a comprehensive health profile of the user, extracting key health indicators through feature engineering, and establishing a health feature portrait of the user; using dynamic feature extraction technology to conduct real-time analysis of health data collected by wearable devices, and outputting user health scores and health trends.

[0024] It should also be noted that the use of dynamic feature extraction technology to perform real-time analysis of health data collected by wearable devices includes processing health data from different sources (such as heart rate, blood pressure, blood oxygen, exercise data, etc.) to dynamically predict the user's health trend; compared with static data analysis, dynamic feature extraction can continuously and in real time analyze time series data, thereby providing users with more accurate health assessments and early warnings; the system not only integrates the physiological data monitored by wearable devices (such as smart watches, smart rings), but also combines environmental sensors and other equipment to provide comprehensive health data collection. Compared with traditional analysis that only relies on single physiological data, multi-source data fusion improves the accuracy of health trend prediction; the present invention uses a long short-term memory network LSTM to predict the user's future health trend. The long short-term memory network LSTM is a deep learning model that can remember long-term dependent information and is suitable for processing time series data; compared with traditional RNN, LSTM can effectively solve the conflict between long time spans and short-term fluctuations in health data through memory units.

[0025] It should also be noted that in the long short-term memory network of the present invention, the forget gate Decide whether to keep the previous health data; through the input gate Determine the impact of the current data through the cell state , the results of the forget gate and the input gate are combined to update the current state.

[0026] It should also be noted that the output of the forget gate controls whether the health data of the previous time step continues to affect the current time step. The forget gate determines whether to exclude the early health data from the analysis based on the historical health data (such as heart rate and blood pressure fluctuations). When it is close to 0, it means that the early data is forgotten, indicating that the previous health status has little effect on the current prediction; When it is close to 1, it means that the early data is retained, indicating that the previous health status is still crucial to the prediction of the current time step; if the system continuously monitors the user's heart rate and detects that the heart rate fluctuations in the past few days are small and stable (for example, the heart rate has been between 70 and 75 in the past five days), the output of the forget gate If the value is close to 0, it means that these relatively stable historical data have little impact on future heart rate prediction and can be excluded. On the contrary, if the heart rate fluctuates greatly in the past few days (for example, from 70 to 90), the output of the forget gate will be close to 1, indicating that these historical fluctuations are very important for predicting future heart rate and should not be ignored.

[0027] It should also be noted that the output of the input gate is used to determine the current health data Is it worth adding to the model? If the current data is of high importance (for example, the current heart rate suddenly increases abnormally), the input gate If it is close to 1, it means that the current data is strongly introduced into the model; if the current data does not change much or is not significant (for example, the current blood pressure is basically consistent with the past data), Close to 0, it means that the new data has little impact on the model; when analyzing blood pressure data, if the user's current blood pressure fluctuates greatly, for example, from 120 / 80 to 140 / 90, the system detects this change through the input gate. The value will be close to 1, indicating that this new health data should have an important impact on the prediction of future blood pressure. If the current data does not change much, for example, the current blood pressure remains at 120 / 80, the output of the input gate If it is close to 0, the system will ignore this information and focus on analyzing historical trends.

[0028] It should also be noted that the cell state The update integrates the forget gate and input gate The result; when Close to 1 When it is close to 0, the model relies entirely on historical data, and the current data has little impact on the prediction; Close to 0 When it is close to 1, the model almost ignores past data and mainly relies on current input; if and If both are large, both historical data and current data will have a greater impact on the prediction; through the forget gate, input gate and cell state update mechanism of the LSTM model, the system can automatically determine whether to retain or exclude early data according to the changes in health data; specifically, the forget gate is adjusted by The value of determines the importance of historical data, and the input gate is Determine whether the current data affects the model; in actual applications, the system can flexibly adjust the way it processes data based on the dynamic changes of health indicators such as heart rate, blood pressure, and blood sugar, thereby achieving more accurate health prediction and risk management.

[0029] It should also be noted that the output of user health scores includes building a health score model based on the user's health history data using random forests to evaluate the user's health status in real time; random forests predict the user's future health risk by building multiple decision trees and combining the user's multi-dimensional health characteristics; the key formula in the random forest model is Gini Impurity, which is used to select the most discriminative features to divide the data, expressed as:

[0030] in, is the health data set of the current user, Belongs to the category The data ratio represents the probability of being sick or not sick. is the number of categories (for binary classification problems, such as "whether to get sick", ); Gini impurity is used to measure the "purity" of the data in the current node, that is, whether the data can be well separated. When it is 0, it means that the data of the node are completely the same. The decision tree in the random forest of the present invention selects the feature with the smallest Gini impurity for partitioning to improve the classification effect; the random forest predicts diabetes risk by constructing multiple decision trees, and each decision tree is constructed from a different subset of training data; for each tree, a set of health features is randomly selected, and the optimal partition is selected by Gini impurity. The health score includes the diabetes risk score. The output of the model after training is a risk probability, which is expressed as:

[0031] in, is the predicted value of diabetes risk, indicating the probability of the user suffering from diabetes. is the number of decision trees, For the A decision tree for features The prediction output is the classification of diabetes risk (0 means no diabetes, 1 means diabetes). Each decision tree is based on the user's health characteristics. Make predictions independently and finally determine the final predicted value of diabetes risk by averaging all trees ,when When the user's diabetes risk is low, the system will not issue a warning; when When the user's diabetes risk is moderate, the system recommends that the user increase health monitoring or change lifestyle habits; when When the user's risk of diabetes is high, the system will issue a clear health warning and recommend that the user undergo a detailed physical examination or consult a doctor.

[0032] It should also be noted that through the LSTM model, the system can automatically determine which historical data is helpful to predict the current health trend based on the user's recent health data (such as heart rate and blood pressure fluctuations). The combination of the forget gate and the input gate enables the system to flexibly process volatile data over a long period of time, effectively improving the timeliness and accuracy of health warnings. Through the random forest algorithm, the system can accurately predict the user's diabetes risk, adjust the health score in real time, and prompt the user's current health status and risk level. The system will set different health intervention measures based on different risk scores. For example, low-risk users do not need intervention, while high-risk users will receive health alerts and further action recommendations. It can accurately identify the user's health risks and provide real-time feedback based on multi-dimensional health data to help users detect potential health problems early. By optimizing feature selection through Gini impurity, the system ensures the efficiency and accuracy of health risk assessment.

[0033] The plan generation module is used to generate a personalized health plan based on the user's health data.

[0034] Furthermore, generating personalized health plans includes generating personalized diet plans based on the user's basal metabolic rate, exercise consumption and dietary preferences. When there are different physiological needs of users, dietary recommendations containing corresponding nutrients are generated, dietary effects are monitored in real time, and personalized diet plans are dynamically adjusted; according to the user's exercise preferences, physical condition and sports injury history, corresponding exercise plans are generated, and the intensity and type of exercise are adjusted in real time in combination with health goals.

[0035] It should be noted that the system can provide users with targeted dietary plans; for example, when a user lacks a certain nutrient (such as iron or vitamin D), the system will help the user supplement specific nutrients through dietary recommendations, monitor the dietary effects in real time, and continuously optimize the plan to ensure that health goals are achieved; when the user's exercise intensity increases, the system will adjust the dietary structure in real time to ensure that the user can obtain sufficient energy and nutritional support. Compared with traditional static health plans, the real-time adjustment capability ensures the sustainability and effectiveness of the health plan.

[0036] It should also be noted that generating personalized exercise plans not only improves the user's health management capabilities, but also reduces the risk of sports injuries. The system can adjust exercise intensity based on the user's real-time health data, avoid overtraining or improper exercise, and enhance the user's exercise experience and health effects.

[0037] The program adjustment module is used to customize personalized health products based on the user's health needs and data through flexible production technology, provide users with personalized suggestions, and automatically adjust the exercise plan according to the achievement of health goals.

[0038] Furthermore, customized and personalized health products include flexible production technology based on Industry 4.0, which adjusts production plans in real time according to the physiological needs of different users, and generates customized supplement formulas based on the output user health scores and health trends.

[0039] It should be noted that providing personalized advice to users includes providing health consultation in voice or text form based on the results of user health data analysis. The system uses natural language processing technology and uses the APP to communicate with virtual health consultants to obtain personalized health advice.

[0040] It should also be noted that the flexible production technology of Industry 4.0 is mainly used to customize health products (such as nutritional supplements, dietary products, etc.) in real time according to the user's personalized health data. Industry 4.0 realizes intelligent management of production systems through advanced Internet of Things (IoT), artificial intelligence (AI) and automation equipment; flexible production systems can quickly respond to users' health needs. For example, by analyzing users' health scores, health trends and other data, the system can automatically issue production tasks, adjust production lines in real time, and produce health products that meet users' current needs; through automation and intelligent management, production lines can quickly adjust product formulas and production processes to meet the personalized needs of different users. This production method avoids the problem of inflexible customization in traditional mass production, improves user experience, and reduces product waste; in a flexible production system, users can feedback their health status through APP or virtual health consultants, and the system makes real-time adjustments based on these feedbacks. For example, if a user completes a health goal within a certain period of time, the system may automatically adjust the dietary plan or the ingredients of the supplement, and quickly generate new products through flexible production technology.

[0041] It should also be noted that real-time adjustment of exercise intensity and type in combination with health goals includes when the user completes the health goal within a customized time period, the system will automatically send an encouragement notification and adjust the goal difficulty; when the user fails to complete the health goal within the customized time period, the system will analyze the reasons and recommend a new action plan.

[0042] It should also be noted that through flexible production, the system can quickly respond to users' health needs and customize highly personalized health products to ensure that each user can obtain nutritional support suitable for their physical condition. Unlike traditional fixed-formula health products, the customization of personalized products greatly improves the accuracy and effectiveness of health interventions. Virtual health consultants can analyze users' health data in real time and provide customized health advice. When users reach specific health goals, the system will issue encouragement notifications and automatically adjust the difficulty of subsequent goals, allowing users to continuously challenge higher health levels. Through this step, the system not only improves users' health management capabilities, but also enhances users' health motivation through incentive mechanisms. By automatically adjusting health goals, the system ensures the continuity and effectiveness of health management.

[0043] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0044] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0045] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0046] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logical function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0047] Example 2, an embodiment of the present invention, provides a personalized health service customization system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0048] First of all, the experimental subjects are 6 users, and the experimental period is 30 days. Each user wears a smart watch, a smart ring and a smart glasses. At the same time, air quality sensors and temperature and humidity sensors are installed in their living environment. Through these devices, the system collects physiological data such as heart rate, blood oxygen saturation, body temperature fluctuations, sleep quality, exercise steps, and environmental data such as PM2.5, temperature, and humidity. During the experiment, all data are transmitted to the central server. The system uses the long short-term memory network (LSTM) for dynamic feature extraction and combines it with the random forest algorithm to make real-time predictions on the user's health trends. LSTM processes data fluctuations in different periods through the forget gate and input gate, and dynamically adjusts the health prediction model to ensure that when the user's health status is abnormal, The system can issue real-time warnings. At the same time, the random forest model evaluates the user's future health risks and generates a personalized health score. The health score data covers multiple dimensions such as heart rate fluctuations, blood oxygen levels, and the impact of environmental data on health. The system scores the user's health status at different time periods and generates personalized health management suggestions based on the scoring results, such as adjusting diet and exercise plans. During the experiment, when the user's health score is lower than 0.4, the system will not issue a warning; when the health score is between 0.4 and 0.7, the system recommends that the user increase health monitoring or moderately adjust lifestyle habits; when the health score is higher than 0.7, the system will issue a health warning and recommend that the user conduct further examinations. Refer to Table 1 to record and analyze the experimental data.

[0049] Table 1 Experimental data record table

[0050] Through the analysis of the tabular data, it can be seen that the system effectively monitors data such as heart rate fluctuations, blood oxygen saturation, and environmental PM2.5 concentration under different users' health conditions. The health scores of users 4 and 5 are both over 0.7, indicating that there is a potential risk in their health status, so the system issued an early warning. In contrast, although the health scores of users 1, 2, and 6 fluctuated slightly, they did not reach the threshold of the system early warning, so no alarm was triggered. It can be seen from the data that the environment with a high PM2.5 concentration has a greater impact on the health score, especially for users 4 and 5. The PM2.5 concentration in their living environment reached 80 and 55 micrograms / cubic meter respectively, which had an adverse effect on their cardiopulmonary function. In addition, User 4 has large heart rate fluctuations and a short sleep duration (only 5 hours), which results in a high health score and eventually triggers an early warning. User 3 is in a healthy state because of stable blood oxygen levels, small heart rate fluctuations, and adequate sleep, with a health score of 0.3. Through the forget gate and input gate of LSTM, the present invention can effectively balance historical health data with current real-time data, thereby providing accurate health trend predictions. This mechanism enables the system to make timely adjustments based on changes in indicators such as heart rate and blood oxygen, avoiding the limitations of traditional methods that ignore environmental factors or short-term fluctuations. Combined with the random forest health score, the present invention can provide a more comprehensive management solution for user health status, thereby improving the accuracy and practicality of health monitoring.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A personalized health service customization system, characterized by: It includes data collection module, solution generation module and solution adjustment module; The data acquisition module is used to collect multi-source data and environmental data, and perform multi-dimensional data fusion and dynamic feature extraction; The plan generation module is used to generate a personalized health plan based on the user's health data; The program adjustment module is used to customize personalized health products based on the user's health needs and data through flexible production technology, provide personalized suggestions to the user, and automatically adjust the exercise program according to the achievement of health goals; The customized and personalized health products include flexible production technology based on Industry 4.0, real-time adjustment of production plans according to the physiological needs of different users, and generation of customized supplement formulas based on output user health scores and health trends; The provision of personalized recommendations to users includes providing health consultation in voice or text form based on the analysis results of user health data. The system uses natural language processing technology to communicate with a virtual health consultant using an APP to obtain personalized health recommendations.

2. The personalized health service customization system according to claim 1, characterized in that: The multi-source data is collected through wearable devices, including smart watches, smart rings, and smart glasses, which collect different health data in real time; Real-time monitoring of heart rate, sleep, and exercise steps through smart watches; Monitor blood oxygen saturation and body temperature fluctuations through smart rings; Smart glasses monitor users’ fatigue and focus changes to detect mental fatigue; Environmental data includes PM2.5 concentration, humidity, and temperature in the air.

3. The personalized health service customization system according to claim 2, characterized in that: The multi-dimensional data fusion and dynamic feature extraction include fusing the collected multi-source data with environmental data, building a comprehensive health profile of the user, extracting key health indicators through feature engineering, and establishing a health feature profile of the user; Use dynamic feature extraction technology to analyze health data collected by wearable devices in real time and output user health scores and health trends; The long short-term memory network LSTM is used to predict the user's health trend and the forget gate Decide whether to keep the previous health data by inputting the gate Determine the impact of the current data through the cell state , update the current state by integrating the results of the forget gate and the input gate; Based on the user's health history data, a random forest is used to establish a health scoring model to evaluate the user's health status in real time.

4. The personalized health service customization system according to claim 3, characterized in that: The generating of personalized health plan includes generating personalized diet plan based on the user's basal metabolic rate, exercise consumption and dietary preferences, generating diet recommendations containing corresponding nutrients when there are different physiological needs of different users, monitoring the dietary effects in real time, and dynamically adjusting the personalized diet plan; Generate a corresponding exercise plan based on the user's exercise preferences, physical condition and sports injury history, and adjust the exercise intensity and type in real time based on health goals.

5. The personalized health service customization system according to claim 4, characterized in that: The customized and personalized health products include flexible production technology based on Industry 4.0, which adjusts the production plan in real time according to the physiological needs of different users, and generates customized supplement formulas based on the output user health scores and health trends.

6. The personalized health service customization system according to claim 5, characterized in that: The provision of personalized recommendations to users includes providing health consultation in voice or text form based on the analysis results of user health data. The system uses natural language processing technology to communicate with a virtual health consultant using an APP to obtain personalized health recommendations.

7. The personalized health service customization system according to claim 5, characterized in that: The real-time adjustment of exercise intensity and type in combination with health goals includes that when the user completes the health goal within a customized time period, the system will automatically send an encouragement notification and adjust the goal difficulty; When users do not achieve their health goals within a customized time period, analyze the reasons and recommend new actions.

Images