Big data-based staff health risk monitoring method and system

Abstract

The invention provides an employee health risk monitoring method and system based on big data, and relates to the technical field of health management and data analysis, and the method comprises the steps: S1, collecting the multi-modal health data of an employee, including but not limited to physiological data, behavior data, working environment data, social interaction data and genome data, and S2, fusing and analyzing the collected multi-modal health data by adopting an integrated neural network model and an adaptive learning algorithm. According to the big data-based staff health risk monitoring method and system, through the combination of the integrated neural network and the deep causal inference model, the multi-modal health data of the staff can be deeply analyzed, and the complex causal relationship between the health data can be effectively identified. Through the dynamic analysis of the historical health data, the current health state and the working environment of the employees, the model can achieve the precise health risk prediction, and provides personalized health intervention suggestions according to the individual differences of the employees.

Description

Technical Field

[0001] The present invention relates to the technical field of health management and data analysis, and specifically to a method and system for monitoring employee health risks based on big data. Background Art

[0002] Employee health risk monitoring is a method based on the collection and analysis of employee health data. It aims to identify potential health risks through real-time monitoring of employee health status and provide early warnings and health management recommendations to businesses or organizations. This monitoring process relies not only on traditional health checkup data but also incorporates data from multiple aspects of employees' daily lives, work environments, and psychological states, using data analysis techniques to dynamically track employee health trends. Employee health risk monitoring typically collects multidimensional health data, including physiological data (such as blood pressure, blood sugar, and weight), behavioral data (such as physical activity, sleep quality, and dietary habits), and environmental factors (such as work stress and working hours). Leveraging big data technology and artificial intelligence algorithms, this data can be comprehensively analyzed to identify potential issues in employee health and predict the occurrence of health risks.

[0003] With the increasing application of big data technology, companies can achieve more refined health management by collecting and analyzing multi-dimensional employee health data (such as data on exercise, diet, and work stress). Existing employee health management systems mostly lack in-depth analysis of health data and fail to integrate big data technology with individual employee differences, making it impossible to implement targeted health interventions. For special occupational groups (such as those in high-intensity work environments), existing technologies cannot effectively identify health risks caused by the combined effects of work environment, stress, lifestyle, and other factors, nor can they provide timely and personalized health intervention recommendations.

[0004] Therefore, how to break through the limitations of the existing health management system and achieve real-time monitoring, accurate prediction and scientific intervention of employee health risks through big data technology has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a method and system for employee health risk monitoring based on big data. The technical problem to be solved by this invention is: how to analyze multimodal health data by integrating neural networks and deep causal inference models to accurately predict employee health risks and provide personalized health intervention recommendations.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for monitoring employee health risks based on big data, comprising: S1. Collect multimodal health data of employees, including but not limited to physiological data, behavioral data, work environment data, social interaction data, and genomic data; S2. Use an integrated neural network model and adaptive learning algorithm to integrate and analyze the collected multimodal health data and construct a health prediction model for individual employees; S3. Based on the health prediction model, combined with employees' historical health data, current health status, work environment, and individual differences, a causal inference model is used to analyze the interaction of multiple factors and predict health risks, aiming to identify health hazards in high-risk occupational groups at an early stage. S4. Based on the predicted health risk results, provide personalized health intervention recommendations to employees, and provide an immersive health intervention experience through virtual reality, dynamically optimize intervention strategies, and adjust health management plans in real time; S5. Feedback employees' health monitoring data and intervention results to the intelligent health management platform. Using edge computing technology, the feedback data is analyzed in real time to dynamically optimize health risk prediction results and generate health risk scores, ensuring real-time updates and continued effectiveness of health intervention measures. S6. Utilize the collective health data feedback mechanism, combined with enterprise-level health trend analysis, to optimize the enterprise's health resource allocation and intervention measures, and provide overall health management decision support for the enterprise.

[0007] Preferably, the intervention recommendations include diet, exercise, stress management and psychological counseling.

[0008] Preferably, the fusion and analysis of the integrated neural network model in S2 includes the following steps: S2.1 inputting the standardized multimodal health data into the integrated neural network model for analysis and prediction, wherein the integrated neural network model is composed of a convolutional neural network and a long short-term memory network; S2.2 extracts features from static physiological data through the convolutional neural network, and extracts local features from the physiological data; S2.3 uses the long short-term memory network to process time series data (such as sleep quality, exercise volume, work pressure, etc.), captures health status that changes over time, and captures the temporal dependencies of these features. The calculation formula of the integrated neural network model is: in: For the moment Predicted health risk value, It is a multimodal input dataset, including physiological, behavioral, environmental and other data. are the weight matrices of the convolutional layer and the LSTM layer respectively, Represents the feature map output by the convolutional neural network, For the temporal analysis of the feature map by the long short-term memory network, is the bias term.

[0009] Preferably, the adaptive learning algorithm is trained by an Adam optimizer to obtain an optimization model, and the weight matrix, bias term and loss function of the optimization model use mean square error to minimize the prediction error: in: is the loss function; is the number of samples; For the The predicted health risk value of samples; For the The true health risk value of the sample; are model parameters.

[0010] Preferably, the specific steps of S3 include: S3.1 uses a graph convolutional network combined with a deep learning framework to construct a deep causal inference graph model. The deep causal inference graph model maps the historical health data into a multidimensional data graph. The multidimensional data graph includes nodes and edges. The nodes represent different health data variables, and the edges represent the causal relationship between these variables. Each edge represents a potential causal path. The information in the graph is propagated through the graph convolutional network, thereby learning the deep causal relationship between variables. Combined with the following formula: in: For the Node representation of the layer; is the adjacency matrix of the graph, representing the causal relationship; is the weight matrix of each layer, used to capture the relationship between variables; is the activation function, usually the ReLU activation function is used; S3.2 uses reinforcement learning to optimize the causal inference model, obtaining a reinforcement learning model. By simulating changes in the health status of employees, it evaluates the nonlinear causal paths between different health data factors in real time. The reinforcement learning model automatically identifies potential causal chains. For example, work stress affects sleep quality and exercise volume, ultimately affecting employees' long-term health risks. This method breaks through the limitations of traditional causal inference models and makes health risk prediction more accurate. The update rule in the reinforcement learning model can be expressed as:

[0011] in: In state Take action quality; For immediate rewards, representing a reduction or increase in health risk; is a discount factor used to balance future rewards; is the learning rate, which controls the amplitude of model update.

[0012] S3.3 Based on the results of deep causal inference analysis, the system dynamically predicts employee health risks and adjusts health intervention plans in real time. For example, by dynamically tracking employees' physiological data and behavioral patterns, the model can not only predict impending health issues (such as cardiovascular problems and mental stress), but also provide personalized intervention recommendations based on individual employee differences (such as genetic background and work-related stress). These intervention recommendations include not only conventional diet and exercise plans, but also adjustments to work hours, improvements to sleep quality, and emotional management.

[0013] Preferably, the health risk score is calculated using the following formula: in: For the moment predicted health risk scores; Score employees' physical health status (such as blood sugar, blood pressure, weight, etc.); Score employee behavioral health (such as exercise volume, eating habits, sleep quality, etc.); Score employees' working environment and stress (such as working hours, work intensity, stress level, etc.), The weighted coefficients of physiological, behavioral and work environment factors respectively reflect the different impacts of these factors on health risks. The system can assess the immediate health status of employees and provide data support for subsequent interventions.

[0014] Preferably, the immersive health intervention experience includes meditation training, stress management, exercise guidance and healthy diet guidance, and can dynamically generate and adjust health intervention scenarios based on real-time feedback data from employees.

[0015] A big data-based employee health risk monitoring system, including: Data collection module, used to collect multimodal health data of employees; Health prediction module, used to integrate and analyze collected multimodal health data; Causal inference module, through causal inference analysis based on historical health data, current health status, work environment and individual differences; The health intervention module provides personalized health intervention suggestions to employees based on the predicted results of health risks; The data feedback module feeds employees' health monitoring data and intervention results back to the intelligent health management platform. It uses edge computing technology to analyze the feedback data in real time and dynamically optimize health risk prediction results to ensure the continuous updating and effectiveness of health intervention measures. The collective health analysis module combines health trends at the enterprise level through a collective health data feedback mechanism.

[0016] The present invention provides a method and system for monitoring employee health risks based on big data. It has the following beneficial effects:

[0017] This big data-based employee health risk monitoring method and system, by integrating neural networks with deep causal inference models, can deeply analyze employees' multimodal health data and effectively identify the complex causal relationships between individual health data. Through dynamic analysis of employees' historical health data, current health status, and work environment, the model can accurately predict health risks and provide personalized health intervention recommendations based on individual employee differences. Compared to traditional statistical prediction models, this health prediction method, based on a combination of causal inference and deep learning, is more targeted and real-time, effectively identifying high-risk groups and providing customized intervention plans.

[0018] By introducing graph convolutional networks and reinforcement learning algorithms, this solution not only captures nonlinear relationships in health data but also enables dynamic optimization based on real-time feedback from health data. After each intervention, the system automatically adjusts the intervention strategy based on employee health feedback, ensuring the continued effectiveness of the intervention. This real-time feedback mechanism transforms employee health management into a dynamic adjustment process, not just static advice. This significantly improves the adaptability and accuracy of health intervention plans, ensuring real-time monitoring and effective management of employee health. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of a process for implementing the invention; Figure 2 A schematic diagram of a process for analyzing multi-factor interactions and predicting health risks for implementing the invention; Figure 3 It is a structural diagram for realizing the invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Example 1 like Figure 1-3 As shown, an embodiment of the present invention provides a method for monitoring employee health risks based on big data, including: S1. collecting multimodal health data of employees, including but not limited to physiological data, behavioral data, work environment data, social interaction data, and genomic data; Physiological data: Use wearable devices (such as smart watches, health bracelets, etc.) to monitor employees' body temperature, blood pressure, heart rate, blood sugar, weight and other physiological parameters in real time.

[0022] Behavioral data: Record employees’ exercise volume, sleep quality, eating habits, etc. through their daily mobile devices (such as smartphones) and fitness equipment (such as smart treadmills, fitness equipment, etc.).

[0023] Work environment data: Monitor employees' work environment through smart office equipment and environmental monitoring systems (such as temperature, humidity, air quality, noise, etc.), and record working hours, work pressure, etc.

[0024] Social interaction data: Obtain employees' social interaction frequency, communication status, etc. through employees' internal social platforms and meeting records.

[0025] Genomic data: If employee-provided genomic information (e.g., genetic test results) is available, use it as an auxiliary data source for health risk prediction.

[0026] S2. Use an integrated neural network model and adaptive learning algorithm to fuse and analyze the collected multimodal health data and construct a health prediction model for individual employees. S2.1 Input the standardized multimodal health data into the integrated neural network model for analysis and prediction. The integrated neural network model is composed of a convolutional neural network and a long short-term memory network. S2.2 uses convolutional neural networks to extract features from static physiological data and local features from physiological data. S2.3 uses long short-term memory networks to process time series data (such as sleep quality, exercise volume, work pressure, etc.) to capture health status that changes over time and to capture the temporal dependencies of these features. The calculation formula of the integrated neural network model is: in: For the moment Predicted health risk value, It is a multimodal input dataset, including physiological, behavioral, environmental and other data. are the weight matrices of the convolutional layer and the LSTM layer respectively, Represents the feature map output by the convolutional neural network, For the temporal analysis of the feature map by the long short-term memory network, The bias term adaptive learning algorithm is trained through the Adam optimizer to obtain the optimized model. The weight matrix, bias term and loss function of the optimized model use the mean square error to minimize the prediction error: in: is the loss function; is the number of samples; For the The predicted health risk value of samples; For the The true health risk value of the sample; are the model parameters (including all weights and bias terms of the convolutional layer and LSTM layer); S3. Based on the health prediction model, combined with employees' historical health data, current health status, work environment, and individual differences, a causal inference model is used to analyze the interactions of multiple factors and predict health risks. This allows for early identification of health risks in high-risk occupational groups. The specific steps of S3 include: S3.1 uses a graph convolutional network combined with a deep learning framework to build a deep causal inference graph model. The deep causal inference graph model maps historical health data into a multidimensional data graph. The multidimensional data graph includes nodes and edges. Nodes represent different health data variables (such as body temperature, blood pressure, work pressure, exercise volume, etc.), and edges represent the causal relationship between these variables. Each edge represents a potential causal path. The information in the graph is propagated through the graph convolutional network, thereby learning the deep causal relationship between variables. Combined with the following formula: in: For the The node representation of the layer (the state of each variable); is the adjacency matrix of the graph, representing causal relationships (connections between variables in the graph); is the weight matrix of each layer, used to capture the relationship between variables; is the activation function, usually the ReLU activation function is used; S3.2 uses reinforcement learning to optimize the causal inference model, resulting in a reinforcement learning model. By simulating changes in employees' health status and evaluating the nonlinear causal paths between different health data factors in real time, the reinforcement learning model automatically identifies potential causal chains. For example, work stress affects sleep quality and exercise volume, ultimately affecting employees' long-term health risks. This approach breaks through the limitations of traditional causal inference models and makes health risk prediction more accurate. The update rule in the reinforcement learning model can be expressed as:

[0027] in: In state Take action quality; For immediate rewards, representing a reduction or increase in health risk; is a discount factor used to balance future rewards; is the learning rate, which controls the amplitude of model update.

[0028] S3.3 Based on the results of deep causal inference analysis, the system dynamically predicts employee health risks and adjusts health intervention plans in real time. For example, by dynamically tracking employees' physiological data and behavioral patterns, the model can not only predict impending health issues (such as cardiovascular problems and mental stress), but also provide personalized intervention recommendations based on individual employee differences (such as genetic background and work-related stress). These intervention recommendations include not only conventional diet and exercise plans, but also adjustments to work hours, improvements to sleep quality, and emotional management.

[0029] S4. Based on health risk predictions, personalized health intervention recommendations are provided to employees. An immersive health intervention experience is provided through virtual reality, dynamically optimizing intervention strategies and adjusting health management plans in real time. Intervention recommendations include diet, exercise, stress management, and psychological counseling. The immersive health intervention experience includes meditation training, stress management, exercise guidance, and healthy diet guidance. Health intervention scenarios can be dynamically generated and adjusted based on real-time employee feedback data. S5. Feedback employees' health monitoring data and intervention results to the intelligent health management platform. Using edge computing technology, the feedback data is analyzed in real time, and health risk prediction results are dynamically optimized to obtain a health risk score. This ensures the real-time updating and continued effectiveness of health intervention measures. The health risk score is calculated using the following formula: in: For the moment predicted health risk scores; Score employees' physical health status (such as blood sugar, blood pressure, weight, etc.); Score employee behavioral health (such as exercise volume, eating habits, sleep quality, etc.); Score employees' working environment and stress (such as working hours, work intensity, stress level, etc.), The weighted coefficients of physiological, behavioral and work environment factors respectively reflect the different impacts of these factors on health risks. , the system can assess the immediate health status of employees and provide data support for subsequent interventions; S6. Utilize the collective health data feedback mechanism, combined with enterprise-level health trend analysis, to optimize the enterprise's health resource allocation and intervention measures, and provide overall health management decision support for the enterprise.

[0030] A big data-based employee health risk monitoring system, including: Data collection module, used to collect multimodal health data of employees; Health prediction module, used to integrate and analyze collected multimodal health data; Causal inference module, through causal inference analysis based on historical health data, current health status, work environment and individual differences; The health intervention module provides personalized health intervention suggestions to employees based on the predicted results of health risks; The data feedback module feeds employees' health monitoring data and intervention results back to the intelligent health management platform. It uses edge computing technology to analyze the feedback data in real time and dynamically optimize health risk prediction results to ensure the continuous updating and effectiveness of health intervention measures. The collective health analysis module combines health trends at the enterprise level through a collective health data feedback mechanism.

[0031] Experimental Examples In this embodiment, unlike the first embodiment, the system uses a causal inference model to identify potential causal chains in health data, further predict employees' health risks, and provide early health intervention recommendations for high-risk occupational groups. Specific implementation methods are as follows:

[0032] S3.1 Building a Deep Causal Inference Graph Model Data preparation and mapping into multidimensional data graphs: In this step, we first map the collected employee historical health data, current health status data, and work environment data into a multidimensional data graph. In this graph, nodes represent different health data variables, such as body temperature, blood pressure, exercise volume, and work stress, and edges represent the causal relationships between these health data variables.

[0033] The following employee health data were collected: 2. Graph Convolutional Network Construction and Information Dissemination: Using a graph convolutional network, nodes and edges in health data are represented as a graph structure. The state of each node represents the employee's health status (such as blood sugar, blood pressure, work stress, etc.), while each edge represents the causal relationship between variables. For example, "work stress" may indirectly affect an employee's "heart rate" or "blood pressure" by affecting "sleep quality" and "exercise level."

[0034] Set the adjacency matrix of the graph To express causality: In graph convolutional networks, the adjacency matrix Represents the causal relationship between variables. Each graph convolution operation propagates the information of each node through weighted propagation, forming a deeper causal relationship propagation.

[0035] Calculation formula (graph convolution layer): in: For the The node representation of the layer (the state of each variable); is the normalized adjacency matrix, which represents the connection between variables; is the weight matrix of each layer; is the activation function, and the ReLU activation function is usually used.

[0036] In this way, graph convolutional networks are able to gradually learn complex causal relationships between health variables.

[0037] S3.2 Reinforcement Learning Optimization of Causal Inference Models 1. Reinforcement Learning Model Design: Reinforcement learning (RL) simulates changes in employee health status and adjusts the model's predictive capabilities in real time based on feedback. By simulating employee health data (such as sleep quality and exercise volume), the RL model can automatically identify nonlinear causal pathways between different health data factors.

[0038] Assuming that an employee's health risk score is determined by multiple factors (such as "work stress", "exercise level", "sleep quality", etc.), the goal of the RL model is to adjust the values ​​of these factors according to the employee's health status, thereby achieving the goal of optimizing health management.

[0039] 2. RL update rule: The update rule in reinforcement learning can be expressed as: in: In state Take action quality; For immediate rewards, it means a reduction or increase in health risk; is a discount factor used to balance future rewards; is the learning rate, which controls the amplitude of model update.

[0040] Each time the reinforcement learning model is updated, it optimizes the causal inference model by simulating the impact of different health factors on the health status of employees, making health risk predictions more accurate.

[0041] S3.3 Health Risk Prediction and Personalized Intervention Recommendations 1. Dynamic Health Risk Prediction: Based on the results of deep causal inference analysis, the system dynamically predicts employees' health risks. For example, by tracking employees' physiological data (such as body temperature, blood sugar, and blood pressure) and behavioral patterns (such as exercise volume and sleep quality), the system can identify health trends in real time and predict impending health issues (such as cardiovascular disease and mental stress).

[0042] 2. Personalized health intervention: When potential health risks are predicted, the system generates personalized health intervention recommendations based on individual employee differences (such as genetic background and work-related stress). For example, if an employee's health risk score is high, the system may recommend interventions such as increasing exercise, improving sleep quality, or reducing work hours.

[0043] Example of intervention recommendations: Exercise intervention: If employees lack exercise for a long time, the system can predict health risks and recommend a certain amount of aerobic exercise (such as brisk walking, running, etc.) every day.

[0044] Stress management: If an employee's health risk profile indicates high work stress, the system can recommend stress management activities such as meditation training and relaxation training.

[0045] Dietary intervention: If an employee's blood sugar level is high, the system can recommend adjusting the diet structure and reducing the intake of high-sugar foods.

[0046] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring employee health risks based on big data, characterized in that: include: S1. Collect multimodal health data of employees, including but not limited to physiological data, behavioral data, work environment data, social interaction data, and genomic data; S2. Use an integrated neural network model and adaptive learning algorithm to integrate and analyze the collected multimodal health data and construct a health prediction model for individual employees; S3. Based on the health prediction model, combined with the employee's historical health data, current health status, work environment, and individual differences, a causal inference model is used to analyze the interaction of multiple factors and predict health risks; S4. Based on the predicted health risk results, provide personalized health intervention recommendations to employees, and provide an immersive health intervention experience through virtual reality, dynamically optimize intervention strategies, and adjust health management plans in real time; S5. Feedback employees' health monitoring data and intervention results to the intelligent health management platform. Using edge computing technology, the feedback data is analyzed in real time to dynamically optimize health risk prediction results and generate health risk scores, ensuring real-time updates and continued effectiveness of health intervention measures. S6. Leverage collective health data feedback mechanisms combined with enterprise-level health trend analysis.

2. The method for monitoring employee health risks based on big data according to claim 1, characterized in that: The intervention recommendations include diet, exercise, stress management and psychological counseling.

3. The method for monitoring employee health risks based on big data according to claim 1, characterized in that: The integration and analysis of the integrated neural network model in S2 includes the following steps: S2.1 inputting the standardized multimodal health data into the integrated neural network model for analysis and prediction, wherein the integrated neural network model is composed of a convolutional neural network and a long short-term memory network; S2.2 extracts features from static physiological data using the convolutional neural network, and extracts local features from the physiological data; S2.3 processes time series data using the long short-term memory network to capture health status that changes over time. The calculation formula of the integrated neural network model is: in: For the moment Predicted health risk value, It is a multimodal input dataset, including physiological, behavioral, environmental and other data. are the weight matrices of the convolutional layer and the LSTM layer respectively, Represents the feature map output by the convolutional neural network, For the temporal analysis of the feature map by the long short-term memory network, is the bias term.

4. The method for monitoring employee health risks based on big data according to claim 3, characterized in that: The adaptive learning algorithm is trained using the Adam optimizer to obtain an optimized model. The weight matrix, bias term, and loss function of the optimized model use mean square error to minimize the prediction error: in: is the loss function; is the number of samples; For the The predicted health risk value of samples; For the The true health risk value of the sample; are model parameters.

5. The method for monitoring employee health risks based on big data according to claim 1, characterized in that: The specific steps of S3 include: S3.1 uses a graph convolutional network combined with a deep learning framework to construct a deep causal inference graph model. The deep causal inference graph model maps the historical health data into a multidimensional data graph. The multidimensional data graph includes nodes and edges. The nodes represent different health data variables, and the edges represent the causal relationship between these variables. Each edge represents a potential causal path, combined with the following formula: in: For the Node representation of the layer; is the adjacency matrix of the graph, representing the causal relationship; is the weight matrix of each layer, used to capture the relationship between variables; is the activation function, usually the ReLU activation function is used; S3.2 uses reinforcement learning to optimize the causal inference model to obtain a reinforcement learning model. By simulating changes in the health status of employees, the nonlinear causal paths between different health data factors are evaluated in real time. The reinforcement learning model automatically identifies potential causal chains. The update rule in the reinforcement learning model can be expressed as: in: In state Take action quality; For immediate rewards, representing a reduction or increase in health risk; is a discount factor used to balance future rewards; is the learning rate, which controls the amplitude of model update; S3.3 Based on the results of deep causal inference analysis, the system dynamically predicts employees' health risks and adjusts health intervention plans in real time.

6. The method for monitoring employee health risks based on big data according to claim 1, characterized in that: The health risk score is calculated using the following formula: in: For the moment predicted health risk scores; Score the physical health status of employees; scoring employee behavioral health; Score employees' work environment and stress levels, are the weighted coefficients of physiological, behavioral and work environment factors, respectively, reflecting the different impacts of these factors on health risks.

7. The method for monitoring employee health risks based on big data according to claim 1, characterized in that: The immersive health intervention experience includes meditation training, stress management, exercise guidance and healthy diet guidance.

8. A big data-based employee health risk monitoring system, characterized by: include: Data collection module, used to collect multimodal health data of employees; Health prediction module, used to integrate and analyze collected multimodal health data; Causal inference module, through causal inference analysis based on historical health data, current health status, work environment and individual differences; The health intervention module provides personalized health intervention suggestions to employees based on the predicted results of health risks; The data feedback module feeds employees' health monitoring data and intervention results back to the intelligent health management platform, and uses edge computing technology to analyze the feedback data in real time; The collective health analysis module combines health trends at the enterprise level through a collective health data feedback mechanism.

Images