Online health care management method and system based on big data

Abstract

The invention discloses an online health management method and system based on big data, and relates to the technical field of online health management, a virtual user executes a selected health service to simulate the process that a real virtual user participates in a health activity in actual life, and after the virtual user completes the health service, the virtual user can take part in the health activity. The pheromone concentration is updated according to the effect of the plan, the virtual user carries out selection and execution of the health care service and updating of the pheromone concentration according to the pheromone concentration and a heuristic rule, convergence is carried out after a preset number of iterations is achieved, natural attenuation of the pheromone concentration is simulated based on the volatilization rate of the pheromone concentration, and the health care service is obtained. After the last round of iteration is completed, according to the pheromone concentration and the health care service effect, the optimal health care service is selected as the final personalized recommendation. The management system effectively generates more personalized health and care services for the virtual users, progressive optimization helps the management system continuously adapt to health changes and demand evolution of the virtual users, and the long-term effectiveness of the health and care services is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of online health care management, and particularly relates to an online health care management method and system based on big data. Background Art

[0002] With the increase in the aging of society and the number of patients with chronic diseases, health management and health care have become important concerns. The traditional medical model mainly focuses on treating diseases, while health care management emphasizes more on preventing and maintaining health. The online health care management system has emerged, aiming to provide more convenient, personalized, and real-time rehabilitation and health management services through digital technology and Internet platforms. Based on the individual's health status, medical history, and needs, the management system generates personalized rehabilitation plans, including suggestions on exercise, diet, mental health, etc.

[0003] The existing technologies have the following deficiencies:

[0004] The current health care management systems have some limitations. Among them, the fixed health care models limit the full consideration of the individual differences of virtual users, resulting in relatively general recommendations for health care services and being difficult to meet the unique needs of different virtual users. In addition, these systems lack real-time performance, making it difficult to timely understand the health changes and the evolution of needs of virtual users. The static health care models cannot flexibly adapt to the actual situations of virtual users, so it is difficult to maintain the effects of health care services in the long term;

[0005] Therefore, the present invention provides an online health care management method and system based on big data, by introducing more flexible and personalized models and strengthening real-time data analysis, to meet the differential needs of virtual users and improve the effects of health care services and the satisfaction of virtual users. Summary of the Invention

[0006] The purpose of the present invention is to provide an online health care management method and system based on big data to solve the deficiencies in the background art.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An online health care management method based on big data, the management method includes the following steps:

[0008] S1: In the search space of health care services, initialize the pheromone concentration for each health care service based on big data, and the pheromone concentration is used to guide the virtual user to move in the search space;

[0009] S2: Create a virtual user group, and each virtual user in the virtual user group selects and executes a health care service according to the current pheromone concentration and heuristic rules;

[0010] S3: The virtual user executes the selected health care service, simulating the process of a real virtual user participating in health care activities in actual life;

[0011] S4: After the virtual user completes the health care service, the pheromone concentration is updated according to the effect of the plan;

[0012] S5: Repeat steps S2, S3, and S4 for iterative processing. The virtual user selects and executes health care services and updates pheromone concentrations according to pheromone concentrations and heuristic rules. Convergence is achieved after reaching a predetermined number of iterations.

[0013] S6: In each iteration, the natural decay of pheromone concentration is simulated based on the volatilization rate of pheromone concentration;

[0014] S7: After the last round of iterations, the best health care service is selected as the final personalized recommendation based on the pheromone concentration and the health care service effect.

[0015] In a preferred embodiment, in step S1, initializing the pheromone concentration for each health care service based on big data includes the following steps:

[0016] S1.1: Use big data technology to collect relevant data on health care services, including virtual user health records, health care activity history, virtual user feedback, physiological indicators, and mental health data;

[0017] S1.2: Extract characteristic data about health care services from the collected big data, including service type, duration, frequency, virtual user participation, and virtual user satisfaction;

[0018] S1.3: Construct a pheromone concentration model based on the collected characteristic data;

[0019] S1.4: Standardize the pheromone concentration, predict the pheromone concentration for each health care service through the pheromone concentration model, and assign an initial pheromone concentration to each health care service in the search space.

[0020] In a preferred embodiment, in step S1.4, standardizing the pheromone concentration comprises the following steps:

[0021] S1.4.1: The pheromone concentration model expression obtained by training is:

[0022] represents the predicted initial pheromone concentration, ω0, ω1, ω2 are regression coefficients, and ω0, ω1, ω2 are all greater than 0;

[0023] S1.4.2: Standardize the predicted initial pheromone concentration using the expression:

[0024] Where NIP represents the normalized initial pheromone concentration, represents the predicted initial pheromone concentration, represents the predicted average initial pheromone concentration, represents the standard deviation of the predicted initial pheromone concentration.

[0025] In a preferred embodiment, in step S2, each virtual user in the virtual user group selects a health care service according to the current pheromone concentration and the heuristic rule and then performs the following steps:

[0026] S2.1: Create a virtual user group, each virtual user in the virtual user group has characteristics;

[0027] S2.2: Obtain the standardized initial pheromone concentration and formulate heuristic rules based on the historical behavior of virtual users;

[0028] S2.3: For each virtual user, generate a health care service selection strategy based on the standardized initial pheromone concentration and heuristic rules.

[0029] In a preferred embodiment, in step S7, after the last round of iterations is completed, selecting the optimal health care service as the final personalized recommendation according to the pheromone concentration and the health care service effect includes the following steps:

[0030] S7.1: Confirm that the management system has completed the predetermined number of iterations and obtain the health care service pheromone concentration obtained in the last round of iterations;

[0031] S7.2: Evaluate the effectiveness of each health care service in the last iteration;

[0032] S7.3: Sort all health care services according to pheromone concentration and health care service effect, and generate a health care service ranking table;

[0033] S7.4: Select the health care service ranked first in the health care service ranking table as the final personalized recommendation.

[0034] In a preferred embodiment, in step S7.2, evaluating the health care service effect of each health care service in the last iteration includes the following steps:

[0035] S7.2.1: Participation frequency, health index and churn rate of virtual users in obtaining health care services;

[0036] S7.2.2: Calculate the participation frequency, health index and churn rate to obtain the service factor fw s ;

[0037] S7.2.3: Service factor fw sThe greater it is, the better the effect of the healthcare service in the last round of iteration of the healthcare service.

[0038] In a preferred embodiment, in step S7.3, sorting all healthcare services according to the pheromone concentration and the effect of the healthcare service, and generating a healthcare service sorting table includes the following steps:

[0039] S7.3.1: Obtain the normalized initial pheromone concentration NIP of the healthcare service and the service coefficient fw s ;

[0040] S7.3.2: After setting weights for the normalized initial pheromone concentration NIP and the service coefficient fw respectively s calculate and obtain the sorting assignment of the healthcare service, and the expression is: PX = 0.6 * NIP + 0.4 * fw s , where PX is the sorting assignment, NIP is the normalized initial pheromone concentration, and fw s is the service coefficient;

[0041] S7.3.3: After obtaining the sorting assignment PX of each healthcare service, sort all healthcare services in descending order according to the sorting assignment PX to generate a healthcare service sorting table.

[0042] In a preferred embodiment, in step S4, updating the pheromone concentration according to the planned effect includes the following steps:

[0043] S4.1: Obtain the service coefficient fw of the healthcare service s , the service coefficient fw s The greater it is, the better the effect of the healthcare service in the last round of iteration of the healthcare service;

[0044] S4.2: By comparing the service coefficient fw s with a preset service threshold, and the service threshold is used to distinguish between good or poor effects of the healthcare service;

[0045] S4.3: If the service coefficient fw s ≥ the service threshold, it is analyzed that the effect of the healthcare service is good, then

[0046] S4.4: If the service coefficient fw s < the service threshold, it is analyzed that the effect of the healthcare service is poor, then

[0047] where NIP 新 is the updated pheromone concentration, NIP 旧 is the pheromone concentration before update, and fw s is the service coefficient.

[0048] The present invention also provides an online health care management system based on big data, including an initialization module, a selection module, an execution module, an update module, an iteration module, a simulation module, and a recommendation module:

[0049] Initialization module: In the search space of health care services, initialize the pheromone concentration for each health care service based on big data;

[0050] Selection module: Used to create a virtual user group. Each virtual user in the virtual user group selects a health care service according to the current pheromone concentration and heuristic rules, and executes the corresponding health care service;

[0051] Execution module: Used for virtual users to execute the selected health care services, simulating the process of real virtual users participating in health care activities in actual life;

[0052] Update module: Used to update the pheromone concentration according to the planned effect after the virtual user simulates the completion of the health care service;

[0053] Iteration module: Perform iterative processing by repeating the steps in the selection module, execution module, and update module. The virtual user selects, executes, and updates the pheromone concentration of the health care service according to the pheromone concentration and heuristic rules, and converges after reaching the predetermined number of iterations;

[0054] Simulation module: Simulate the natural decay of the pheromone concentration based on the evaporation rate of the pheromone concentration;

[0055] Recommendation module: After the last round of iteration is completed, select the optimal health care service as the final personalized recommendation according to the pheromone concentration and the effect of the health care service, and display it to the real virtual user.

[0056] In the above technical solution, the technical effects and advantages provided by the present invention:

[0057] The present invention simulates the process of real virtual users participating in health care activities by virtual users executing the selected health care services. After the virtual user completes the health care service, update the pheromone concentration according to the planned effect, and perform iterative processing. The virtual user selects, executes, and updates the pheromone concentration of the health care service according to the pheromone concentration and heuristic rules, and converges after reaching the predetermined number of iterations. In each iteration, simulate the natural decay of the pheromone concentration based on the evaporation rate of the pheromone concentration. After the last round of iteration is completed, select the optimal health care service as the final personalized recommendation according to the pheromone concentration and the effect of the health care service. This management system effectively generates more personalized health care services for virtual users, and the progressive optimization helps the management system continuously adapt to the health changes and demand evolution of virtual users, improving the long-term effectiveness of health care services. Brief Description of the Drawings

[0058] 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 required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0059] Figure 1 It is a flowchart of the method of the present invention.

[0060] Figure 2 It is a system module diagram of the present invention. Detailed Embodiments

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0062] Embodiment 1: Please refer to Figure 1 As shown, a method for online health care management based on big data in this embodiment, the management method includes the following steps:

[0063] In the search space of health care services, initialize the pheromone concentration for each health care service based on big data. The pheromone concentration represents the attractiveness of the health care service and is used to guide the movement of virtual users in the search space, including the following steps:

[0064] Use big data technology to collect rich data related to health care services, including virtual user health records, health care activity histories, virtual user feedback, physiological indicators, mental health data, etc. Extract the characteristics of health care services from the collected big data, which include information such as the type, duration, frequency, virtual user participation, virtual user satisfaction, etc. of the service. Based on the collected characteristic data, construct a pheromone concentration model, which is a machine learning model, such as a regression model, decision tree model, neural network, etc., for predicting the attractiveness of health care services;

[0065] Standardize the pheromone concentration to ensure it is within a suitable range so that it can effectively play a role in subsequent algorithms. Assign an initial pheromone concentration to each health care service in the search space, and these values are predicted by the pheromone concentration model. The pheromone concentration represents the attractiveness of the health care service, that is, the degree of guiding virtual users in the search space;

[0066] Based on the collected feature data, constructing a pheromone concentration model, and predicting the initial pheromone concentration of each health care service through the pheromone concentration model includes the following steps:

[0067] The feature data set of health care services, the feature data set includes the average virtual user participation and virtual user satisfaction. Mark the average virtual user participation and virtual user satisfaction as X1 and X2 respectively, and construct a regression model based on the average virtual user participation and virtual user satisfaction. The expression is:

[0068] Y = ω0 + ω1 * X1 + ω2 * X2 + ∈;

[0069] In the formula, Y is the true initial pheromone concentration of the health care service, ω0, ω1, and ω2 are regression coefficients, ω0, ω1, and ω2 are all greater than 0, and ∈ is the error term, representing the random error generated because the regression model cannot perfectly explain the initial pheromone concentration;

[0070] Take 80% of the data set as the training set, use the training set to fit the regression model, and find the optimal regression coefficients by minimizing the sum of squared residuals. The expression is:

[0071] where i = 1, 2,..., n, n represents the number of health care services in the system, n is a positive integer, X 1i represents the average virtual user participation of the i-th health care service, X 2i represents the virtual user satisfaction of the i-th health care service, Y i represents the true initial pheromone concentration of the i-th health care service, and Minimize represents the minimization operation;

[0072] Take 20% of the data set as the test set, use the test set to calculate the mean squared error to evaluate the performance of the regression model. The expression is: In the formula, MSE represents the mean squared error of the model, Y i represents the true initial pheromone concentration of the i-th health care service, represents the predicted initial pheromone concentration of the i-th health care service;

[0073] After the regression model is trained, a pheromone concentration model is obtained. Use the pheromone concentration model to predict the features of each health care service. The expression of the trained pheromone concentration model is:

[0074] represents the predicted initial pheromone concentration, ω0, ω1, and ω2 are regression coefficients, ω0, ω1, and ω2 are all greater than 0, and standardize the predicted initial pheromone concentration to ensure it is within a suitable range;

[0075] Wherein, NIP represents the normalized initial pheromone concentration, represents the predicted initial pheromone concentration, represents the average value of the predicted initial pheromone concentration, represents the standard deviation of the predicted initial pheromone concentration.

[0076] Create a virtual user group. Each virtual user in the virtual user group selects a health care service according to the current pheromone concentration and heuristic rules, and executes the corresponding health care service, so that the selected strategy makes the virtual user more likely to select services beneficial to the health care of real virtual users. Specifically:

[0077] Create a group of virtual users. Each virtual user has characteristics, including age, gender, health status, hobbies, etc., to simulate the diversity of real virtual users. The following steps are included:

[0078] Determine the number of virtual users to be created, which depends on the scale of system simulation and the needs of testing and evaluation. Define the characteristics of each virtual user, which may include but are not limited to age, gender, health status, hobbies, occupation, etc., and ensure that the combination of characteristics can fully reflect the diversity of the real user group. Generate random or rule-based data for each virtual user to fill in its characteristics. For example, age can be randomly selected within a certain range, gender can be evenly distributed, health status can be set to levels such as good, average, and poor, and hobbies can be randomly selected or generated according to a preset pattern;

[0079] If the system needs to consider special groups, such as users with specific diseases or users with special living habits, ensure that these special groups are included in the virtual users to increase the authenticity of the simulation. Ensure that the virtual user group has sufficient diversity to cover various combinations of characteristics. For example, there is a wide age span, gender balance, and uniform distribution of health status, etc. Record the generated virtual user data for subsequent use, which can be a user data table containing all the characteristic information of each user;

[0080] Obtain the normalized initial pheromone concentration, and formulate heuristic rules based on the historical behavior of virtual users. The heuristic rules affect the tendency of virtual users to select health care services in specific situations;

[0081] For each virtual user, generate a health care service selection strategy according to the normalized initial pheromone concentration and heuristic rules. The selection strategy includes factors such as the characteristics, health status, and hobbies of the virtual user;

[0082] Formulating heuristic rules based on the historical behavior of virtual users includes the following steps:

[0083] Obtain the historical behavior data of virtual users, including information such as click records, purchase history, search behavior, evaluations, and comments of virtual users, which are obtained from website logs and databases. Clean and preprocess the collected historical behavior data of virtual users, which includes operations such as handling missing values, removing outliers, and normalizing or standardizing the data to ensure data quality;

[0084] Use data visualization techniques to analyze the behavior patterns of virtual users, explore the behavior habits of virtual users at different times, locations, and devices, discover the preferences and trends of virtual users, and determine the key features that affect virtual user preferences from the historical behavior data of virtual users, including the following steps:

[0085] Collect the historical behavior data of virtual users, including information such as timestamps, locations, used devices, and executed healthcare services, ensure that the data is complete, clean up missing or outlier values, select appropriate data visualization tools, such as Matplotlib, Seaborn, Plotly, etc., and select appropriate chart types according to the nature of the data and analysis requirements, such as line charts, bar charts, scatter plots, etc. Analyze the behavior patterns of virtual users at different times by drawing time series charts. Possible charts include daily behavior trends, weekly behavior trends, and possible seasonal variations;

[0086] Use map visualization tools to analyze the behavior habits of virtual users at different locations. Heat maps can be drawn to show the spatial distribution of user activities, or geographic scatter plots can be used to represent the behavior frequencies of users at different locations. Use charts such as bar charts or pie charts to analyze the behavior preferences of virtual users on different devices, understand whether users are more inclined to use mobile devices or desktop devices, and possible platform preferences. Use tools such as correlation charts or heat maps to analyze the relationships between different features, determine which features are closely related to user preferences and behavior patterns, and identify possible key features;

[0087] Use techniques such as time series analysis and clustering analysis to discover potential trends and patterns in virtual user behavior, which helps to identify periodic behaviors of users or behavior patterns triggered by specific events. Use interactive visualization tools, such as Plotly-Dash or Tableau, to create interactive dashboards that allow users to explore the data as needed, which helps to understand user behavior patterns more deeply. If there is user comment or tag data, text mining techniques can be used to analyze the keywords contained in user comments or tags, obtain the emotional tendencies of users and evaluations of healthcare services from them, and combine the results of data visualization to provide support for system decision-making. Adjust the recommendation strategy of healthcare services according to the discovered user preferences and trends to provide more personalized services;

[0088] Based on the analysis results, heuristic rules are formulated. Heuristic rules are statistical rules, such as "virtual users prefer to choose health services on weekends" or "virtual users often buy the same type of products". The formulation of the rules should be able to capture the behavior patterns and preferences of virtual users. Weights and priorities are assigned to each formulated rule to reflect the degree of its impact on virtual user behavior. Some rules are more decisive than others, so they require higher weights.

[0089] For each virtual user, according to the standardized initial pheromone concentration and heuristic rules, generating a health care service selection strategy includes the following steps:

[0090] Combining the standardized initial pheromone concentration and applying heuristic rules, generating the final health care service selection strategy, which is a list of rules, specifically:

[0091] If the standardized initial pheromone concentration is greater than 0, give priority to high-quality services;

[0092] If a virtual user has often chosen type A services in the past, then give priority to considering type A services;

[0093] If the standardized initial pheromone concentration is less than 0, recommend highly adaptable health care services.

[0094] The virtual user executes the selected health care service, simulating the process of a real virtual user participating in health care activities in actual life. The health care services include activities in aspects such as sports, diet, and mental health, specifically:

[0095] According to the generated health care service selection strategy, simulate the execution of the selected health care service, which includes simulating virtual behaviors such as virtual users participating in fitness activities, receiving health consultations, and participating in social activities. During the simulation execution process, collect the virtual user's simulated behaviors and feedback, which are information such as the virtual user's evaluation of the health care service, participation frequency, and satisfaction. According to the collected feedback information, update the standardized initial pheromone concentration. If the health care service selection is considered successful by the virtual user, increase the pheromone concentration of the relevant service; conversely, if the selection is not successful, decrease the pheromone concentration of the relevant service;

[0096] Define the specific update rules for pheromone concentration. For example, determine the amplitude of the increase or decrease in pheromone concentration based on the satisfaction score of virtual users. A successful service selection leads to a relatively large increase in pheromone concentration, while an unsuccessful selection results in a relatively small decrease. During the update process of pheromone concentration, consider the long-term and short-term effects. Some successful health care services require a relatively high pheromone concentration to be accumulated over a long period, while some unsuccessful selections need to have a certain rapid decrease in the short term. After the virtual user completes the health care service, update the pheromone concentration according to the planned effect. Generally, services with good planned effects will increase their relevant pheromone concentration, while services with poor effects will decrease the relevant pheromone concentration.

[0097] Perform iteration by repeating the steps. In each iteration, the virtual user makes a selection, executes, and updates the pheromone concentration of the health care service according to the pheromone concentration and heuristic rules. The whole process is repeated until convergence after reaching the predetermined number of iterations. Specifically:

[0098] Determine the total number of iterations or set the convergence conditions. The number of iterations is the total number of rounds for the system to update, and the convergence condition is that the pheromone concentration changes little in several consecutive iterations or the behavior of the virtual user tends to be stable;

[0099] Enter the iteration loop and execute the following steps:

[0100] For each virtual user, generate a health care service selection strategy based on the current pheromone concentration and heuristic rules;

[0101] According to the generated strategy, simulate the execution of the health care service, collect the simulated behavior and virtual user feedback, including the following steps:

[0102] Select or generate a group of virtual users from the simulation environment. These users represent the characteristics and behaviors of real users in the system. For each virtual user, according to the generated health care service strategy, select a health care service suitable for their characteristics and needs, simulate the execution of the selected health care service, considering all aspects of the health care plan, including exercise, nutrition, mental health, etc. This may involve simulating the user's activities, food intake, mental activities, etc. Simulate the behavioral data of the user during the execution of the health care service, which may include the user's exercise volume, eating habits, frequency of participating in social activities, etc. The simulated user may provide feedback, including the satisfaction with the health care service, perception of the planned effect, etc. This can be a quantitative score or a qualitative opinion. Record the simulation results of each virtual user, including the execution situation of the health care service, simulated behavioral data, and user feedback;

[0103] Update the pheromone concentration according to the results and feedback of the simulated execution. A successful service selection increases the pheromone concentration of the relevant service, while an unsuccessful selection leads to a decrease in the pheromone concentration;

[0104] Check whether the set convergence condition is met. If it is met, end the iterative loop; otherwise, continue the next iteration. When the predetermined number of iterations is reached or the convergence condition is satisfied, end the entire iterative process.

[0105] To simulate the evaporation phenomenon of pheromones in nature, an evaporation rate of pheromone concentration is introduced. In each iteration, the pheromone concentration of the health care service will gradually decrease at a certain evaporation rate to simulate the natural decay of pheromone concentration.

[0106] After the last iteration is completed, based on the pheromone concentration and the effect of the health care service, select the optimal health care service as the final personalized recommendation. Specifically:

[0107] Confirm that the system has completed the predetermined number of iterations or met the convergence condition, enter the last iteration, obtain the pheromone concentration obtained in the last iteration. By statistically analyzing the change trend of the pheromone concentration, check which health care services have a high pheromone concentration and which have a low pheromone concentration. For each health care service, evaluate its health care service effect in the last iteration;

[0108] Sort all health care services according to the pheromone concentration and the health care service effect to generate a ranking table of health care services. Select the health care service ranked first in the ranking table of health care services as the final personalized recommendation. A high pheromone concentration indicates that the system believes that this service is more attractive, and a good effect indicates that the virtual user has a positive feedback on this service. Select the optimal health care service as the final personalized recommendation result. This is a recommendation list that includes the health care services that the system believes are most suitable for the virtual user. Provide a feedback mechanism for the virtual user to encourage the virtual user to evaluate and feedback on the recommendation result. The virtual user feedback is used to further optimize the system's recommendation strategy. Incorporating the virtual user feedback into the system learning process requires the next iteration, which helps the system continuously improve the recommendation accuracy and the effect of personalized services;

[0109] For each health care service, the steps to evaluate its health care service effect in the last iteration include the following:

[0110] Obtain the participation frequency, health index, and churn rate of the virtual user in the health care service;

[0111] The participation frequency is reflected in the search space where the virtual user frequently participates in the simulation activities of the health care service and is obtained after recording the frequency and duration of the virtual user's participation in the health care service;

[0112] The health index is obtained by recording the health status of the virtual user through simulated health data during the simulation execution;

[0113] The churn rate reflects that virtual users lose interest in or no longer participate in health care services during the simulation process. It is obtained by tracking the continuity of virtual users' participation in health care services and recording the proportion of virtual users who no longer use the services.

[0114] The participation frequency, health index and churn rate are calculated comprehensively to obtain the service coefficient fw s , the calculation expression is: In the formula, CY is the participation frequency, JK is the health index, LS is the churn rate, α, β, and γ are the proportional coefficients of the participation frequency, health index, and churn rate, respectively, and α, β, and γ are all greater than 0;

[0115] Service factor fw s The larger it is, the better the health care service effect is in the last iteration of health care services;

[0116] All health care services are sorted according to pheromone concentration and health care service effect. Generating a health care service sorting table includes the following steps:

[0117] Obtain the standardized initial pheromone concentration NIP and service coefficient fw of health care services s , respectively, are the standardized initial pheromone concentration NIP and the service coefficient fw s After setting the weight, calculate and obtain the ranking value of health care services. The expression is: PX = 0.6*NIP+0.4*fw s , where PX is the ranking value, NIP is the standardized initial pheromone concentration, and fw s is the service coefficient;

[0118] After obtaining the ranking value PX of each health care service, all health care services are sorted from large to small according to the ranking value PX to generate a health care service ranking table.

[0119] This application uses virtual users to perform the selected health care services, simulating the process of real virtual users participating in health care activities in real life. After the virtual user completes the health care service, the pheromone concentration is updated according to the planned effect, and iterative processing is performed. The virtual user selects, executes and updates the health care service according to the pheromone concentration and heuristic rules, and converges after reaching a predetermined number of iterations. In each iteration, the natural attenuation of the pheromone concentration is simulated based on the volatility of the pheromone concentration. After the last round of iterations, the optimal health care service is selected as the final personalized recommendation based on the pheromone concentration and the health care service effect. The management system effectively generates more personalized health care services for users, and progressive optimization helps the management system to continuously adapt to the health changes and demand evolution of users, and improve the long-term effectiveness of health care services.

[0120] Example 2: After the virtual user completes the health care service, update the pheromone concentration according to the planned effect. Generally, services with good planned effects will increase their relevant pheromone concentrations, while services with poor effects will reduce the relevant pheromone concentrations. Specifically:

[0121] Obtain the service coefficient fw of the health care service s , the service coefficient fw s The larger it is, the better the effect of the health care service in the last iteration of the health care service;

[0122] By comparing the service coefficient fw s with a preset service threshold, which is used to distinguish between good or poor effects of the health care service;

[0123] If the service coefficient fw s ≥ the service threshold, and it is analyzed that the effect of the health care service is good, then

[0124] If the service coefficient fw s < the service threshold, and it is analyzed that the effect of the health care service is poor, then

[0125] In the formula, NIP 新 is the updated pheromone concentration, NIP 旧 is the pheromone concentration before update, and fw s is the service coefficient.

[0126] To simulate the evaporation phenomenon of pheromones in nature, the evaporation rate of pheromone concentration is introduced. In each iteration, the pheromone concentration of the health care service will gradually decrease at a certain evaporation rate to simulate the natural attenuation of pheromone concentration. The evaporation rate is a decimal between 0 and 1, indicating the percentage of reduction of pheromone in each iteration. If you want the pheromone to adapt to the new environment or user needs relatively quickly, choose a higher evaporation rate, which will cause the pheromone to decrease relatively quickly so as to accept new information more quickly. The evaporation rate is also set according to the specific situation being simulated to make the system more in line with the actual situation. For example, some pheromones are relatively stable in nature and have a low evaporation rate, while some pheromones will evaporate relatively quickly. The choice of evaporation rate also involves the balance between the stability and flexibility of the system. A lower evaporation rate results in relatively stable pheromones and poor adaptability; while a higher evaporation rate results in greater fluctuations in pheromones and stronger adaptability;

[0127] For example:

[0128] Suppose we have a health care service management system with two types of health care services: Service A and Service B. Each service has a pheromone concentration associated with it, which represents its importance or attractiveness in the system. To simulate the natural decay of the pheromone concentration, we introduce a evaporation rate, which represents the percentage by which the pheromone concentration decreases in each iteration;

[0129] Initially, the pheromone concentration of Service A is 1.0, and the pheromone concentration of Service B is 0.8;

[0130] For each iteration, the system simulates the effect of the health care plan, which can be a value obtained based on user feedback or other evaluations;

[0131] Each service updates its pheromone concentration based on its corresponding plan effect and evaporation rate, which is achieved through the following formula:

[0132] New pheromone concentration = (1 - evaporation rate) × old pheromone concentration + plan effect;

[0133] This formula means that the new pheromone concentration is equal to the previous pheromone concentration multiplied by the remaining percentage (1 - evaporation rate), plus the current plan effect. In this way, the pheromone concentration is adjusted according to the plan effect in each iteration and gradually decreases due to the influence of the evaporation rate.

[0134] Example 3: Please refer to Figure 2 As shown, the online health care management system based on big data described in this embodiment includes an initialization module, a selection module, an execution module, an update module, an iteration module, a simulation module, and a recommendation module:

[0135] Initialization module: In the search space of health care services, based on big data, initialize the pheromone concentration for each health care service. The pheromone concentration represents the attractiveness of the health care service and is used to guide the virtual user to move in the search space. The pheromone concentration information is sent to the selection module;

[0136] Selection module: Create a virtual user group. Each virtual user in the virtual user group selects a health care service according to the current pheromone concentration and heuristic rules, and executes the corresponding health care service, so that the selected strategy makes the virtual user more likely to select a service that is beneficial to the health care of real virtual users. The selected health care service is sent to the execution module;

[0137] Execution module: The virtual user executes the selected health care service, simulating the process of real virtual users participating in health care activities in actual life. The health care services include activities in aspects such as sports, diet, and mental health. The simulation results are sent to the update module;

[0138] Update Module: After the virtual user simulates the completion of the health care service, update the pheromone concentration according to the planned effect. Generally, for services with good planned effects, increase the pheromone concentration related to them, while for services with poor effects, decrease the related pheromone concentration. The updated pheromone concentration is sent to the iteration module;

[0139] Iteration Module: Perform iterative processing by repeating the steps in the selection module, execution module, and update module. In each iteration, the virtual user selects, executes, and updates the pheromone concentration of the health care service according to the pheromone concentration and heuristic rules. The whole process is repeated until convergence after reaching the predetermined number of iterations, and the updated result of the health care service is sent to the recommendation module.

[0140] Simulation Module: In order to simulate the evaporation phenomenon of pheromones in nature, introduce the evaporation rate of the pheromone concentration. In each iteration, the pheromone concentration of the health care service will gradually decrease at a certain evaporation rate to simulate the natural attenuation of the pheromone concentration.

[0141] Recommendation Module: After the last round of iteration is completed, select the optimal health care service as the final personalized recommendation according to the pheromone concentration and the effect of the health care service, and display it to the real virtual user.

[0142] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0143] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described are combined in a suitable manner in any one or more embodiments or examples.

[0144] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not elaborate on all the details, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An online health care management method based on big data, characterized in that: The management method comprises the following steps: S1: In the search space of health care services, the pheromone concentration is initialized for each health care service based on big data. The pheromone concentration is used to guide the virtual user to move in the search space; S2: Create a virtual user group, and each virtual user in the virtual user group selects and executes health care services based on the current pheromone concentration and heuristic rules; S3: The virtual user performs the selected health care service, simulating the process of real virtual users participating in health care activities in real life; S4: After the virtual user completes the health care service, the pheromone concentration is updated according to the effect of the plan; S5: Repeat steps S2, S3, and S4 for iterative processing. The virtual user selects and executes health care services and updates pheromone concentrations according to pheromone concentrations and heuristic rules. Convergence is achieved after reaching a predetermined number of iterations. S6: In each iteration, the natural decay of pheromone concentration is simulated based on the volatilization rate of pheromone concentration; S7: After the last round of iterations, the best health care service is selected as the final personalized recommendation based on the pheromone concentration and the health care service effect.

2. The online health management method based on big data according to claim 1, characterized in that: In step S1, initializing the pheromone concentration for each health care service based on big data includes the following steps: S1.1: Use big data technology to collect relevant data on health care services, including virtual user health records, health care activity history, virtual user feedback, physiological indicators, and mental health data; S1.2: Extract characteristic data about health care services from the collected big data, including service type, duration, frequency, virtual user participation, and virtual user satisfaction; S1.3: Construct a pheromone concentration model based on the collected characteristic data; S1.4: Standardize the pheromone concentration, predict the pheromone concentration for each health care service through the pheromone concentration model, and assign an initial pheromone concentration to each health care service in the search space.

3. The online health management method based on big data according to claim 2, wherein: In step S1.4, standardizing the pheromone concentration includes the following steps: S1.4.1: The pheromone concentration model expression obtained by training is: It represents the initial pheromone concentration of the prediction. ω0, ω1, and ω2 are regression coefficients, and ω0, ω1, and ω2 are all greater than 0; S1.4.2: Standardize the predicted initial pheromone concentration using the expression: In the formula, NIP represents the normalized initial pheromone concentration, represents the predicted initial pheromone concentration, represents the average value of the predicted initial pheromone concentration, represents the standard deviation of the predicted initial pheromone concentration.

4. The online health management method based on big data according to claim 3, wherein: In step S2, each virtual user in the virtual user group selects a health care service based on the current pheromone concentration and heuristic rules and executes The following steps are involved: S2.1: Create a virtual user group, each virtual user in the virtual user group has characteristics; S2.2: Obtain the standardized initial pheromone concentration and formulate heuristic rules based on the historical behavior of virtual users; S2.3: For each virtual user, generate a health care service selection strategy based on the standardized initial pheromone concentration and heuristic rules.

5. The online health management method based on big data according to claim 1, characterized in that: In step S7, after the last round of iterations is completed, selecting the optimal health care service as the final personalized recommendation according to the pheromone concentration and the health care service effect includes the following steps: S7.1: Confirm that the management system has completed the predetermined number of iterations and obtain the health care service pheromone concentration obtained in the last round of iterations; S7.2: Evaluate the effectiveness of each health care service in the last iteration; S7.3: Sort all health care services according to the pheromone concentration and the effects of health care services to generate a health care service ranking list; S7.4: Select the health care service ranked first in the health care service ranking list as the final personalized recommendation.

6. The online health care management method based on big data according to claim 5, characterized in that: In step S7.2, evaluating the effects of each health care service in the last round of iteration includes the following steps: S7.2.1: Obtain the participation frequency, health index, and churn rate of virtual users in the health care services; S7.2.2: Calculate the service coefficient fw by comprehensively calculating the participation frequency, health index, and churn rate s ; S7.2.3: Service coefficient fw s The larger it is, the better the effect of the health care service in the last round of iteration of the health care service is.

7. The online health care management method based on big data according to claim 6, characterized in that: In step S7.3, sorting all health care services according to the pheromone concentration and the effects of health care services to generate a health care service ranking list includes the following steps: S7.3.1: Obtain the standardized initial pheromone concentration NIP and service factor fw for health care services s ; S7.3.2: The initial pheromone concentration NIP and the service coefficient fw after standardization respectively s After setting the weights, calculate and obtain the ranking assignment of the health care service. The expression is: PX = 0.6 * NIP + 0.4 * fw s , where PX is the ranking assignment, NIP is the initial pheromone concentration after standardization, and fw s is the service coefficient; S7.3.3: After obtaining the ranking assignment PX of each health care service, sort all health care services in descending order according to the ranking assignment PX to generate a health care service ranking list.

8. The online health care management method based on big data according to claim 7, characterized in that: In step S4, updating the pheromone concentration according to the planned effects includes the following steps: S4.1: Obtain the service coefficient fw of the health and wellness service s , where the service coefficient fw s is larger, indicating that the health and wellness service effect in the last round of iteration of the health and wellness service is better; S4.2: By comparing the service coefficient fw s with a preset service threshold, which is used to distinguish between good and poor effects of the health care service; S4.3: If the service coefficient fw s ≥ the service threshold, and the analysis shows that the effect of the health care service is good, then S4.4: If the service coefficient fw s < the service threshold, and the analysis shows that the effect of the health care service is poor, then Where, NIP 新 is the updated pheromone concentration, NIP 旧 is the pheromone concentration before update, and fw s is the service coefficient.

9. An online health care management system based on big data, which is used to implement the management method described in any one of claims 1-8, and is characterized in that: Including an initialization module, a selection module, an execution module, an update module, an iteration module, a simulation module, and a recommendation module: Initialization module: In the search space of health care services, initialize the pheromone concentration for each health care service based on big data; Selection module: Used to create a virtual user group. Each virtual user in the virtual user group selects a health care service according to the current pheromone concentration and heuristic rules and executes the corresponding health care service; Execution module: Used for virtual users to execute the selected health care services, simulating the process of real virtual users participating in health care activities in actual life; Update module: Used to update the pheromone concentration according to the planned effects after the virtual users complete the simulation of the health care services; Iteration module: Perform iterative processing by repeating the steps in the selection module, execution module, and update module. Virtual users select, execute, and update the pheromone concentration of health care services according to the pheromone concentration and heuristic rules, and converge after reaching the predetermined number of iterations; Simulation module: Simulate the natural decay of the pheromone concentration based on the evaporation rate of the pheromone concentration; Recommendation module: After the last round of iteration is completed, select the optimal health care service as the final personalized recommendation according to the pheromone concentration and the effects of health care services, and display it to real virtual users.

Images