Health management service processing method and device, electronic equipment and storage medium

Abstract

The invention provides a health management business processing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining health data of a patient and historical decision data of a doctor, the health data comprising historical health data of the patient and current examination data; inputting the health data of the patient into a pre-trained prediction model, and performing prediction by the prediction model according to the health data of the patient to obtain a prediction result, the prediction result being used for indicating a health management service to be executed by the patient; and inputting the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis processing, and obtaining a target business suggestion by the decision model according to the prediction result and the historical decision data of the doctor. The requirement of multi-disease co-management is met, and the requirement of basic-level medical staff for multi-disease service unified processing of service links such as evaluation, physical examination, follow-up visit and health education can be met.

Description

Technical Field

[0001] The present application relates to the technical field of medical data. Specifically, it relates to a method, device, electronic device, and storage medium for processing health management services. Background Art

[0002] Primary medical services are the foundation and gateway of the social medical service system and the first line of defense for protecting the people. The scope covered by primary medical services is relatively wide. Basic medical and health services need to address the common diseases, frequently-occurring diseases, and common health problems of the people. At the same time, work such as health education and health examinations also needs to be carried out. Therefore, the demand for co-management of multiple diseases in primary medical services is increasing.

[0003] In the prior art, business recommendations and executions are carried out according to preset rules by population and disease type in a planned manner, which cannot meet the cross-task requirements of multi-disease, sub-course, and comprehensive health management. Therefore, there is an urgent need for an intelligent processing method for resident health management services that can meet the demand for co-management of multiple diseases and can also meet the needs of primary medical staff for unified processing of multi-disease services in business links such as assessment, follow-up, and health education. Summary of the Invention

[0004] The purpose of the present application is to provide a method, device, electronic device, and storage medium for processing health management services to achieve intelligent processing of health management services and meet the demand for co-management of multiple diseases in view of the deficiencies in the above prior art.

[0005] To achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for processing health management services, the method including:

[0007] Obtain the health data of a patient and the historical decision data of a doctor, where the health data includes the historical health data and current examination data of the patient;

[0008] Input the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient to obtain a prediction result, where the prediction result is used to indicate the health management service to be executed by the patient;

[0009] Input the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing, and the decision model obtains a target service recommendation based on the prediction result and the historical decision data of the doctor, where the target service recommendation is used to indicate the health management service to be executed by the doctor in the health management service to be executed by the patient.

[0010] Optionally, after inputting the prediction result and the doctor's historical decision data into a pre-trained decision model for analysis and processing, and obtaining a target business recommendation by the decision model based on the prediction result and the doctor's historical decision data, it includes:

[0011] Input the target business recommendation into a task scheduler, and generate a target business scheduling plan by the task scheduler according to the target business recommendation.

[0012] Optionally, inputting the target business recommendation into a task scheduler, and generating a target business scheduling plan by the task scheduler according to the target business recommendation, includes:

[0013] The task scheduler obtains the usage information of resources corresponding to each health management service indicated by the target business recommendation;

[0014] The task scheduler determines the priorities of each health management service indicated by the target business recommendation;

[0015] The task scheduler generates the target business scheduling plan according to the usage information and priorities of resources corresponding to each health management service indicated by the target business recommendation.

[0016] Optionally, the task scheduler determines the priorities of each health management service indicated by the target business recommendation, including:

[0017] The task scheduler predicts the patient's health data based on a pre-trained prediction model to obtain the patient's health risk information;

[0018] The task scheduler determines the original priorities corresponding to each health management service of the patient according to the patient's health data and the original priority policy in the task scheduler;

[0019] The task scheduler determines the priorities of each health management service according to the original priorities corresponding to each health management service of the patient and the patient's health risk information.

[0020] Optionally, before inputting the patient's health data into a pre-trained prediction model and the prediction model predicts based on the patient's health data to obtain a prediction result, it includes:

[0021] Denoise, normalize, and extract features from the patient's health data to obtain preprocessed health data, and the feature extraction includes extracting the change trend features of the health data;

[0022] Input the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient, including:

[0023] Input the preprocessed health data into the pre-trained prediction model, and the prediction model makes a prediction based on the preprocessed health data to obtain the prediction result.

[0024] Optionally, before inputting the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing, and the decision model obtains a target business recommendation based on the prediction result and the historical decision data of the doctor, including:

[0025] Obtain the historical decision data of multiple doctors, and divide the historical decision data into a training data set and a test data set;

[0026] Input the training data set into an initial decision model, and use each piece of training data in the training data set to iteratively train the initial decision model until the initial decision model meets the preset requirements, and use the decision model that meets the preset requirements as an intermediate decision model;

[0027] Input the test data set into the intermediate decision model, and optimize the performance of the intermediate decision model through each piece of test data in the test data set to obtain the pre-trained decision model.

[0028] Optionally, after inputting the target business recommendation into a task scheduler, and the task scheduler generates a target business scheduling plan based on the target business recommendation, further including:

[0029] Obtain the execution time of each health management service in the target business scheduling plan;

[0030] Adjust the original priority policy in the task scheduler according to the execution time of each health management service.

[0031] In a second aspect, an embodiment of the present application further provides a health management service processing device, and the device includes:

[0032] An acquisition module, configured to acquire the health data of the patient and the historical decision data of the doctor, where the health data includes the historical health data and the current examination data of the patient;

[0033] An input module, configured to input the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient to obtain a prediction result, and the prediction result is used to indicate the health management service to be executed by the patient;

[0034] An input module for inputting the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing. The decision model obtains a target business recommendation based on the prediction result and the historical decision data of the doctor, and the target business recommendation is used to indicate the health management services to be performed by the doctor in the health management services to be performed by the patient.

[0035] Optionally, the input module is specifically configured to:

[0036] Input the target business recommendation into a task scheduler, and the task scheduler generates a target business scheduling plan based on the target business recommendation.

[0037] Optionally, the input module is specifically configured to:

[0038] The task scheduler obtains the usage information of the resources corresponding to each health management service indicated by the target business recommendation;

[0039] The task scheduler determines the priority of each health management service indicated by the target business recommendation;

[0040] The task scheduler generates the target business scheduling plan based on the usage information and priority of the resources corresponding to each health management service indicated by the target business recommendation.

[0041] Optionally, the input module is specifically configured to:

[0042] The task scheduler predicts the health data of the patient based on a pre-trained prediction model to obtain the health risk information of the patient;

[0043] The task scheduler determines the original priority corresponding to each health management service of the patient according to the health data of the patient and the original priority policy in the task scheduler;

[0044] The task scheduler determines the priority of each health management service according to the original priority corresponding to each health management service of the patient and the health risk information of the patient.

[0045] Optionally, the input module is specifically configured to:

[0046] Denoise, normalize, and extract features from the health data of the patient to obtain preprocessed health data, and the feature extraction includes extracting the change trend features of the health data;

[0047] Input the preprocessed health data into the pre-trained prediction model, and the prediction model makes a prediction based on the preprocessed health data to obtain the prediction result.

[0048] Optionally, the input module is specifically configured to:

[0049] Obtain historical decision-making data of multiple doctors, and divide the historical decision-making data into a training data set and a test data set;

[0050] Input the training data set into an initial decision-making model, and use each piece of training data in the training data set to iteratively train the initial decision-making model until the initial decision-making model meets the preset requirements, and use the decision-making model that meets the preset requirements as an intermediate decision-making model;

[0051] Input the test data set into the intermediate decision-making model, and optimize the performance of the intermediate decision-making model through each piece of test data in the test data set to obtain the pre-trained decision-making model.

[0052] Optionally, the input module is specifically configured to:

[0053] Obtain the execution time of each health management service in the target business scheduling plan;

[0054] According to the execution time of each health management service, adjust the original priority policy in the task scheduler.

[0055] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores program instructions executable by the processor. When the application program runs, the processor communicates with the storage medium through the bus, and the processor executes the program instructions to perform the steps of the health management service processing method described in the first aspect above.

[0056] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program is read and executes the steps of the health management service processing method described in the first aspect above.

[0057] The beneficial effects of the present application are:

[0058] A health management service processing method, device, electronic device and storage medium provided by this application can integrate services such as evaluation, follow-up, health education, and physical examination by inputting the patient's health data into a pre-trained prediction model. The prediction model makes predictions based on the patient's health data to obtain a prediction result, and can uniformly process multi-disease services. The decision-making model can obtain target service suggestions based on the prediction result and the doctor's historical decision-making data, providing evidence-based decision support for medical staff. Based on the above service processing module, a pre-trained model is used to optimize and uniformly process services such as evaluation, physical examination, follow-up, and health education, meeting the needs of multi-disease co-management and the needs of grass-roots medical staff to uniformly process multi-disease services in service links such as evaluation, physical examination, follow-up, and health education. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 It is a schematic flowchart of a health management service processing method provided by an embodiment of this application;

[0061] Figure 2 It is a schematic flowchart of another health management service processing method provided by an embodiment of this application;

[0062] Figure 3 It is a schematic flowchart of yet another health management service processing method provided by an embodiment of this application;

[0063] Figure 4 It is a complete schematic flowchart of a health management service processing method provided by an embodiment of this application;

[0064] Figure 5 It is a complete schematic flowchart of a service scheduling method provided by an embodiment of this application;

[0065] Figure 6 It is a schematic diagram of a device for a health management service processing method provided by an embodiment of this application;

[0066] Figure 7 It is a structural block diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. It should be understood that the accompanying drawings in this application are only for the purposes of illustration and description, and are not used to limit the protection scope of this application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of this application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without a logical context relationship may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of this application.

[0068] In addition, the described embodiments are only some embodiments of this application, rather than all embodiments. The components of the embodiments of this application generally described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative efforts belong to the protection scope of this application.

[0069] It should be noted that the term "including" will be used in the embodiments of this application to indicate the presence of the features stated hereinafter, but does not exclude the addition of other features.

[0070] Optionally, the health management service processing method provided in the embodiments of this application is applied to an electronic device, which can be, for example, a terminal device with computing and processing capabilities and a display function such as a mobile phone, a tablet computer, a laptop computer, a handheld computer, a desktop computer, etc., or it can also be a server. Specifically, it can be applied to an application program in a terminal device, such as: an APP (application, mobile phone software) of a mobile phone, an application system on a computer, etc.

[0071] Optionally, the electronic device may include a service processing module provided in this application, and the service processing module may include: a data access layer, a data processing layer, a model layer, a decision-making layer, and an interface layer.

[0072] Among them, the data access layer can be used to be responsible for collecting data generated in business processes such as file management, physical examination, diagnosis and treatment, screening and evaluation, follow-up, and health education.

[0073] Data processing layer: Clean, standardize, and extract features from the collected data. Among them, the feature extraction may include: extracting the change trend of the course of a certain disease in the collected health data.

[0074] Model layer: contains multiple machine learning models for analyzing data and predicting key business processes in business processes.

[0075] Decision-making layer: Based on the output of the model layer, specific business processing suggestions are put forward.

[0076] Interface layer: provides an interface for medical staff to interact with the business processing module, so that medical staff can view the prediction results and business processing suggestions obtained by the business processing module from the client front end based on this interface layer.

[0077] Next, the specific implementation process of the health management business processing provided in the embodiments of the present application will be specifically explained.

[0078] Figure 1 It is a schematic flowchart of a health management business processing method provided in an embodiment of the present application. The execution subject of this method is the aforementioned electronic device. As Figure 1 shown, this method includes:

[0079] S101. Obtain the health data of the patient and the historical decision-making data of the doctor.

[0080] Among them, the health data may include the historical health data and current examination data of the patient.

[0081] Optionally, the health data may be, for example, data generated by the patient in business processes such as file management, physical examination, diagnosis and treatment, screening and evaluation, follow-up, and health education in the community medical institution. Specifically, data generated by the patient in each business process can be collected through an automated tool.

[0082] Exemplarily, if patient A comes to this community medical institution for medical treatment, data generated by patient A in business processes such as file management, physical examination, diagnosis and treatment, screening and evaluation, follow-up, and health education in this community medical institution can be collected through the data access layer in this business processing module. For example, it may include blood pressure data, weight, height, heart rate data, etc. in the physical examination. The diagnosis and treatment records of this patient can also be collected. The diagnosis and treatment records may include the patient's medical records in different hospitals, such as the record of seeing a doctor for hypertension in Hospital B and the record of seeing a doctor for lumbar disc herniation in Hospital C. Data in the patient's file management can also be collected, such as data that the patient's hypertension is at grade three and diabetes is at low risk.

[0083] Optionally, the historical decision data of the doctor refers to the historical decision data of the doctor who treated the patient for the course of each disease. Exemplarily, if the patient A is treated by Doctor Li, the decision data of Doctor Li for the course of each disease is obtained. For example, for the course of the disease of low-risk hypertension, the historical decision data of Doctor Li is physical examination; for lumbar disc herniation, the historical decision data of Doctor Li is to go to other hospitals for in-depth diagnosis and treatment; for the course of the disease of high-risk cardiovascular, the historical decision data of Doctor Li is to continue screening and evaluation.

[0084] S102. Input the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient to obtain a prediction result.

[0085] Among them, the prediction result is used to indicate the health management service to be executed by the patient. The health management service to be executed can be, for example, at least one of the above business processes such as physical examination, diagnosis and treatment, screening and evaluation, follow-up, and health education. Specifically, it can include regular physical examination, continued screening and evaluation, monitoring of health data on the body at any time, and subsequent life suggestions, etc.

[0086] Optionally, the prediction model can be trained using a large amount of historical health data of different patients. Specifically, methods such as random forest and support vector machine can be used for training. The trained prediction model is used as the pre-trained prediction model. By analyzing and predicting the health data of the current patient through this prediction model, the future health management service trend and possible problems of the patient can be predicted, and the health management service to be executed by the current patient can be obtained.

[0087] Exemplarily, based on the blood pressure data of the patient, it can be predicted whether the patient has hypertension, hypotension or normal blood pressure, as well as the course of each disease, such as low-risk hypertension, low-risk hypotension, etc. Health management suggestions can also be given to the patient based on the health data of the patient. For example, for patients with hypertension, suggestions such as less salt and sugar and more exercise are given.

[0088] S103. Input the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing, and the decision model obtains the target business suggestion based on the prediction result and the historical decision data of the doctor.

[0089] Among them, the target business suggestion can be used to indicate the health management service to be executed by the doctor in the health management service to be executed by the patient. Among them, the historical decision data of the doctor can refer to the historical decision data of the doctor for different health management services. For example, the historical decision of the doctor for health management service A is to have a physical examination in other departments of the community hospital; the historical decision for health management service B is to go to a higher-level hospital for continued screening and evaluation; the historical decision for health management service C is to have a follow-up with this doctor, etc.

[0090] Optionally, the predicted results may include multiple health management services to be performed. However, some of these health management services may not be the services provided by this doctor. For example, it may be necessary to go to other hospitals for examinations or screenings, etc., or there may be services that need to be performed in other departments of this community hospital. Therefore, in order to obtain the health management services that this doctor of this patient's visit performs on this patient, it is necessary to input the above-mentioned predicted results of this patient and the doctor's historical decision data into a pre-trained decision model for analysis. The decision model will obtain the target service recommendation based on the predicted results of this patient and the doctor's historical decision data.

[0091] Exemplarily, if the predicted results of this patient include 10 health management services to be performed, through the decision model based on the historical decision data of this doctor of this patient's visit and the predicted results, it is finally obtained that there are 5 health management services to be performed on this patient by this doctor.

[0092] In this embodiment, by inputting the patient's health data into a pre-trained prediction model, the prediction model makes predictions based on the patient's health data to obtain predicted results. Services such as evaluation, follow-up, health education, and physical examination can be integrated together to uniformly process multi-disease services; the decision model obtains the target service recommendation based on the predicted results and the doctor's historical decision data, which can provide evidence-based decision support for medical staff. Based on the above-mentioned service processing module, the pre-trained model is used to optimize and uniformly process services such as evaluation, physical examination, follow-up, and health education, meeting the needs of multi-disease co-management and the needs of grass-roots medical staff to uniformly process multi-disease services in service links such as evaluation, physical examination, follow-up, and health education.

[0093] Optionally, after inputting the predicted results and the doctor's historical decision data into the pre-trained decision model for analysis and processing in step S103, and the decision model obtains the target service recommendation based on the predicted results and the doctor's historical decision data, it may include:

[0094] Optionally, the task scheduler can be pre-deployed in the electronic device and communicate with the service processing model in the electronic device. When the decision model in the service processing module outputs the target service recommendation, it can receive the target service recommendation.

[0095] Optionally, the target business suggestion is input into the task scheduler, and the task scheduler generates a target business scheduling plan according to the target business suggestion. Specifically, the target business suggestion output by the decision-making model can be input into the task scheduler, and the task scheduler adjusts the execution priorities of the respective health management services corresponding to the target business suggestion output by the decision-making model, so as to generate a target business scheduling plan, and the patient executes the respective health management services according to the generated target business scheduling plan.

[0096] Optionally, the target business suggestion includes at least one of the health management services of the patient to be performed by the doctor. Among the predicted health management services, information such as the severity of the disease courses of the patient is included, and thus information such as the severity and urgency of the respective health management services can be obtained. Then, the health management services of the patient to be performed by the doctor in the target business suggestion are input into the task scheduler, and the task scheduler can generate a target business scheduling plan according to the health management services indicated by the target business suggestion. The target business scheduling plan refers to the scheduling information of the health management services in the target business suggestion.

[0097] Figure 2 It is a schematic flowchart of another health management service processing method provided by an embodiment of the present application. As Figure 2 shown, the above-mentioned inputting the target business suggestion into the task scheduler, and the task scheduler generating a target business scheduling plan according to the target business suggestion may include:

[0098] S201. The task scheduler obtains the resource usage information corresponding to the health management services indicated by the target business suggestion.

[0099] Specifically, the task scheduler can monitor the resource usage information corresponding to the health management services in real time. The resource usage information may include the occupation of human resources and material resources by the health management services at different times. When the task scheduler receives the input target business suggestion, it can obtain the resource usage information corresponding to the health management services according to the identifiers of the health management services indicated by the target business suggestion.

[0100] Exemplarily, if the target business suggestion includes 3 health management services, such as Health Management Service 1, Health Management Service 2, and Health Management Service 3, the task scheduler can obtain the resource usage information corresponding to Health Management Service 1, the resource usage information corresponding to Health Management Service 2, and the resource usage information corresponding to Health Management Service 3. For example, the resource usage information corresponding to Health Management Service 1 and Health Management Service 2 is busy, and the resource usage information corresponding to Health Management Service 3 is idle.

[0101] S202. The task scheduler determines the priorities of the various health management services indicated by the target business recommendation.

[0102] Specifically, the priorities of the various health management services can be determined according to the urgency and importance of the various health management services indicated by the target business recommendation.

[0103] Exemplarily, for example, the priority of the above-mentioned health management service 1 is higher than that of health management service 3, and the priority of health management service 3 is higher than that of health management service 2.

[0104] S203. The task scheduler generates a target service scheduling plan according to the resource usage information and priorities corresponding to the various health management services indicated by the target recommendation.

[0105] Specifically, for example, a genetic algorithm can be used to dynamically adjust the execution order of the various health management services.

[0106] Exemplarily, for example, according to the priorities of the various health management services and the resource usage information of the various health management services, the target service scheduling plan generated by the task scheduler is, for example: first execute health management service 3, then execute health management service 1, and finally execute health management service 2.

[0107] In this embodiment, by generating a target service scheduling plan by the task scheduler according to the resource usage information and priorities corresponding to the various health management services indicated by the target recommendation, human and material resources can be reasonably allocated, and combined with the priorities of the various health management services, while efficiently completing the various health management services, high-priority health management services can also be addressed, improving work efficiency and ensuring the completion of key health management services.

[0108] Figure 3 As shown in FIG. 3, which is a schematic flowchart of another health management service processing method provided by an embodiment of the present application, in S202 above, the task scheduler determines the priorities of the various health management services indicated by the target business recommendation, which may include:

[0109] S301. The task scheduler predicts the patient's health data based on a prediction model to obtain the patient's health risk information.

[0110] Optionally, the patient's health data may include, for example, the patient's basic information, medical history, treatment history, and living habits and other data, and machine learning algorithms are used to analyze the patient's health data to predict the health risk information that the patient may have in the future.

[0111] Exemplarily, according to the patient's health data, it can be predicted that the patient has a relatively high risk of developing hypertension in the future.

[0112] S302. The task scheduler determines the original priorities corresponding to each health management service for the patient based on the patient's health data and the original priority policy.

[0113] Among them, the original priority policy can refer to the priority policy among each health management service preset in the task scheduler.

[0114] Optionally, the task scheduler can determine the original priorities corresponding to each health management service for the patient based on factors such as the patient's urgency, disease severity, treatment response, health management plan, etc., and the original priority policy.

[0115] Exemplarily, if there are 3 health management services in the target service suggestions for the patient, such as the above-mentioned Health Management Service 1, Health Management Service 2, and Health Management Service 3, and the task scheduler can determine the original priorities corresponding to each health management service for the patient based on factors such as the urgency of the diseases existing in the patient's own health data, the disease severity, the patient's treatment response, and health management, etc. The original priorities corresponding to each health management service for the patient can be: the priority of Health Management Service 3 is higher than the priority of Health Management Service 1, and the priority of Health Management Service 1 is higher than the priority of Health Management Service 3.

[0116] S303. The task scheduler determines the priorities of each health management service based on the original priorities corresponding to each health management service and the patient's health risk information.

[0117] Optionally, based on the patient's health risk information obtained in the above S301 and S302 steps and the original priorities corresponding to each health management service for the patient, determine the priorities of each health management service.

[0118] Exemplarily, if the health management service corresponding to the higher risk that the above-mentioned patient may suffer from hypertension in the future is Health Management Service 1, combining the original priorities corresponding to each health management service for the patient, it can be determined that the priority of Health Management Service 1 is higher than the priority of Health Management Service 3, and the priority of Health Management Service 3 is higher than the priority of Health Management Service 2.

[0119] In this embodiment, by first determining the original priorities of each health management service for the patient based on the patient's health data, the patient's own physical data is considered, so that the obtained original priorities are based on the patient's own situation. Then, based on the predicted health risk information and the original priorities, the priorities of each health management service are determined, which can make the finally obtained priorities of each health management service consider both the patient's own health data and the future predicted health risk information, making the obtained priorities of each health management service more reasonable and more based on evidence.

[0120] Optionally, inputting the patient's health data into a pre-trained prediction model in S102 above, and the prediction model makes a prediction based on the patient's health data to obtain a prediction result, which may include:

[0121] Optionally, perform denoising processing, normalization processing, and feature extraction on the patient's health data to obtain preprocessed health data. Among them, the feature extraction may include extracting the change trend features of the patient's health data, or may include extracting the key data of the patient's health data, etc.

[0122] Optionally, inputting the patient's health data into a pre-trained prediction model in S102 above, and the prediction model makes a prediction based on the patient's health data to obtain a prediction result, which may include:

[0123] Optionally, input the preprocessed health data into a pre-trained prediction model, and the prediction model makes a prediction based on the preprocessed health data to obtain a prediction result.

[0124] In this embodiment, by preprocessing each health data and inputting the preprocessed health data into a pre-trained prediction model, the preprocessed health data can be made more in line with the training data of the model, so that the prediction result obtained by the model is more accurate.

[0125] Optionally, before S103 above, inputting the prediction result and the doctor's historical decision data into a pre-trained decision model for analysis and processing, and the decision model obtains a target business recommendation based on the prediction result and the doctor's historical decision data, which may include:

[0126] Optionally, historical decision data of multiple doctors can be obtained, and the obtained historical decision data of multiple doctors are divided into a training data set and a test data set. Input the training data set into an initial decision model, and use each training data in the training data set to iteratively train the initial decision model, and continuously optimize the parameters of the decision model during the iterative training process until the preset requirements are met, and use the decision model that meets the preset requirements as an intermediate decision model. Among them, the preset requirements may be, for example, to make the parameters of the model optimal and the loss function of the model optimal, etc.

[0127] Optionally, by analyzing the data in the historical health management business process, the historical decision-making data of multiple doctors and key influencing factors can be identified, and the corresponding machine learning algorithms can be selected for learning according to the problem characteristics of the data. For example, learning algorithms such as decision trees and neural networks can be selected. Before training the model, it is also necessary to preprocess the obtained historical decision-making data, such as feature extraction and other operations, and input the preprocessed historical decision-making data into the initial decision-making model to improve the prediction accuracy of the model.

[0128] Input the test data set into the intermediate decision-making model, and optimize the performance of the intermediate decision-making model through each test data in the test data set to obtain a pre-trained decision-making model. Specifically, for example, the cross-validation method can be used to evaluate the performance of the model and optimize the performance of the model, which can ensure the generalization ability of the decision-making model, so as to obtain the final pre-trained decision-making model.

[0129] In this embodiment, by training the decision-making model with the historical decision-making data of multiple doctors, the obtained pre-trained decision-making model can be more accurate.

[0130] Optionally, the training process of the prediction model is similar to the training process of the above decision-making model. The training set data and test set data of the prediction model are the health data of multiple patients. Therefore, the training process of the prediction model will not be elaborated here.

[0131] Optionally, after the above-mentioned target business suggestion is input into the task scheduler and the task scheduler generates a target business plan according to the target business suggestion, it may further include:

[0132] Optionally, obtain the execution time of each health management business in the target business scheduling plan. Specifically, the execution time of each health management business corresponding to each patient in the target business scheduling plan for each patient can be obtained.

[0133] Exemplarily, continuing with the above-mentioned target business scheduling plan: first execute health management business 3, then execute health management business 1, and finally execute health management business 2 as an example. This patient used 20 minutes when executing health management business 3, then used 10 minutes when executing health management business 1, and finally used 30 minutes when executing health management business 2.

[0134] Optionally, according to the execution time of each health management business, the original priority policy in the task scheduler can be adjusted. Specifically, the original priority policy of each health management business in the task scheduler can be adjusted to make the original priority policy in the task scheduler more reasonable.

[0135] To more clearly illustrate the complete process of health management service processing in the above specific embodiments, this embodiment uses Figure 4 for clearer illustration. Figure 4 As shown in Figure 4 which is a schematic diagram of the complete process of a health management service processing method provided by an embodiment of this application:

[0136] S401. Preprocess the data.

[0137] Optionally, the data refers to the obtained health data of patients and the historical decision-making data of doctors. The preprocessing may include denoising, feature extraction, feature standardization processing, etc. of the obtained data.

[0138] S402. Generate decision suggestions.

[0139] Specifically, input the preprocessed data into a pre-trained model, use the pre-trained prediction model for prediction to obtain a prediction result, and obtain a target service suggestion through the pre-trained decision model.

[0140] S403. Task scheduling.

[0141] Optionally, input the obtained target service suggestion into a task scheduler, and the task scheduler generates a target service scheduling plan according to the target service suggestion, the priorities of each health management service, and the resource usage information corresponding to each health management service.

[0142] S404. Feedback adjustment.

[0143] Optionally, optimize the original priority policy in the task scheduler according to the execution time of each health management service in the corresponding target service scheduling plan executed by each patient obtained.

[0144] To more clearly illustrate the complete process of generating the target service scheduling plan above, this embodiment uses Figure 5 for clearer illustration. Figure 5 As shown in Figure 5 which is a schematic diagram of the complete process of a service scheduling method provided by an embodiment of this application:

[0145] S501. Obtain the data of the patient.

[0146] S502. Determine the original priorities corresponding to each health management service of the patient.

[0147] S503. Analyze the patient's condition.

[0148] Optionally, the analysis of the patient's condition refers to the above-mentioned prediction of the patient's health data by the task scheduler based on a pre-trained prediction model to obtain the patient's health risk information.

[0149] S504. Generate a target business schedule.

[0150] Optionally, generate a target business scheduling plan according to the patient's health risk information, the original priorities corresponding to each health management service of the patient, and the resource usage information corresponding to each health management service.

[0151] S505. Execute the scheduling.

[0152] Optionally, the patient executes each health management service according to the target business scheduling plan.

[0153] S506. Evaluate and adjust.

[0154] Optionally, evaluate the scheduling effect according to the actual execution result and the scheduling result of the patient obtained, and adjust the original priority policy.

[0155] Figure 6 It is a schematic diagram of a device for a health management service processing method provided by an embodiment of the present application. As Figure 6 shown, the device includes:

[0156] An acquisition module 601, configured to acquire the patient's health data and the doctor's historical decision data, where the health data includes the patient's historical health data and current examination data;

[0157] An input module 602, configured to input the patient's health data into a pre-trained prediction model, and the prediction model predicts according to the patient's health data to obtain a prediction result, where the prediction result is used to indicate the health management services to be executed by the patient;

[0158] An input module 602, configured to input the prediction result and the doctor's historical decision data into a pre-trained decision model for analysis and processing, and the decision model obtains a target business recommendation according to the prediction result and the doctor's historical decision data, where the target business recommendation is used to indicate the health management services to be executed by the doctor among the health management services to be executed by the patient.

[0159] Optionally, the input module 602 is specifically configured to:

[0160] Input the target business recommendation into a task scheduler, and the task scheduler generates a target business scheduling plan according to the target business recommendation.

[0161] Optionally, the input module 602 is specifically configured to:

[0162] The task scheduler obtains the usage information of the resources corresponding to each health management service indicated by the target service recommendation;

[0163] The task scheduler determines the priorities of the health management services indicated by the target service recommendation;

[0164] The task scheduler generates the target service scheduling plan according to the usage information and priorities of the resources corresponding to the health management services indicated by the target service recommendation.

[0165] Optionally, the input module 602 is specifically configured to:

[0166] The task scheduler predicts the health data of the patient based on a pre-trained prediction model to obtain the health risk information of the patient;

[0167] The task scheduler determines the original priorities corresponding to the health management services of the patient according to the health data of the patient and the original priority policy in the task scheduler;

[0168] The task scheduler determines the priorities of the health management services according to the original priorities corresponding to the health management services of the patient and the health risk information of the patient.

[0169] Optionally, the input module 602 is specifically configured to:

[0170] Perform denoising processing, normalization processing, and feature extraction on the health data of the patient to obtain preprocessed health data, and the feature extraction includes extracting the change trend features of the health data;

[0171] Input the preprocessed health data into the pre-trained prediction model, and the prediction model makes a prediction according to the preprocessed health data to obtain the prediction result.

[0172] Optionally, the input module 602 is specifically configured to:

[0173] Obtain the historical decision data of multiple doctors, and divide the historical decision data into a training data set and a test data set;

[0174] Input the training data set into the initial decision model, and use each training data in the training data set to iteratively train the initial decision model until the initial decision model meets the preset requirements, and use the decision model that meets the preset requirements as the intermediate decision model;

[0175] Input the test data set into the intermediate decision model, and optimize the performance of the intermediate decision model through each test data in the test data set to obtain the pre-trained decision model.

[0176] Optionally, the input module 602 is specifically configured to:

[0177] Obtain the execution time of each health management service in the target business scheduling plan;

[0178] Adjust the original priority policy in the task scheduler according to the execution time of each health management service.

[0179] Figure 7 This is a structural block diagram of an electronic device 700 provided by an embodiment of the present application. As Figure 7 shown, the electronic device may include: a processor 701 and a memory 702.

[0180] Optionally, a bus 703 may further be included, where the memory 702 is used to store machine-readable instructions executable by the processor 701 (for example, Figure 5 the acquisition module and the execution instructions corresponding to the who module in the device in ), when the electronic device 700 runs, the processor 701 communicates with the memory 702 through the bus 703, and when the machine-readable instructions are executed by the processor 701, the method steps in the above method embodiments are executed.

[0181] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the method steps in the above method embodiments of the health management service processing method are executed.

[0182] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the method embodiments, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection shown or discussed with each other can be through some communication interfaces, and the indirect coupling or communication connection of the devices or modules can be in an electrical, mechanical or other form.

[0183] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0184] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application.

Claims

1. A method for processing a health management service, characterized in that, The method includes: Obtaining the health data of the patient and the historical decision-making data of the doctor, where the health data includes the historical health data and the current examination data of the patient; Inputting the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient to obtain a prediction result, where the prediction result is used to indicate the health management services to be performed by the patient; Inputting the prediction result and the historical decision-making data of the doctor into a pre-trained decision model for analysis and processing, and the decision model obtains a target service recommendation based on the prediction result and the historical decision-making data of the doctor, where the target service recommendation is used to indicate the health management services to be performed by the doctor in the health management services to be performed by the patient.

2. The health management service processing method according to claim 1, wherein After inputting the prediction result and the historical decision-making data of the doctor into a pre-trained decision model for analysis and processing, and the decision model obtains a target service recommendation based on the prediction result and the historical decision-making data of the doctor, it includes: Inputting the target service recommendation into a task scheduler, and the task scheduler generates a target service scheduling plan based on the target service recommendation.

3. The health management service processing method according to claim 2, wherein The inputting the target service recommendation into a task scheduler, and the task scheduler generates a target service scheduling plan based on the target service recommendation, includes: The task scheduler obtains the usage information of the resources corresponding to each health management service indicated by the target service recommendation; The task scheduler determines the priorities of each health management service indicated by the target service recommendation; The task scheduler generates the target service scheduling plan based on the usage information and priorities of the resources corresponding to each health management service indicated by the target service recommendation.

4. The health management service processing method according to claim 3, wherein The task scheduler determines the priorities of each health management service indicated by the target service recommendation, includes: The task scheduler makes a prediction on the health data of the patient based on a pre-trained prediction model to obtain the health risk information of the patient; The task scheduler determines the original priorities corresponding to each health management service of the patient according to the health data of the patient and the original priority policy in the task scheduler; The task scheduler determines the priorities of each health management service according to the original priorities corresponding to each health management service of the patient and the health risk information of the patient.

5. The health management service processing method according to claim 1, characterized in that Before inputting the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient to obtain a prediction result, it includes: Performing denoising processing, normalization processing, and feature extraction on the health data of the patient to obtain pre-processed health data, where the feature extraction includes extracting the change trend features of the health data; The inputting the health data of the patient into a pre-trained prediction model, and the prediction model makes a prediction based on the health data of the patient, includes: Input the preprocessed health data into the pre-trained prediction model, and have the prediction model make a prediction based on the preprocessed health data to obtain the prediction result.

6. The health management service processing method according to claim 1, characterized in that, Before inputting the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing, and having the decision model obtain the target business recommendation based on the prediction result and the historical decision data of the doctor, it includes: Obtain the historical decision data of multiple doctors, and divide the historical decision data into a training data set and a test data set; Input the training data set into the initial decision model, and use each training data in the training data set to iteratively train the initial decision model until the initial decision model meets the preset requirements, and use the decision model that meets the preset requirements as the intermediate decision model; Input the test data set into the intermediate decision model, and optimize the performance of the intermediate decision model through each test data in the test data set to obtain the pre-trained decision model.

7. The health management service processing method according to claim 2, characterized in that, After inputting the target business recommendation into the task scheduler, and having the task scheduler generate a target business scheduling plan based on the target business recommendation, it further includes: Obtain the execution time of each health management service in the target business scheduling plan; Adjust the original priority policy in the task scheduler according to the execution time of each health management service.

8. A health management service processing device, characterized in that, It includes: An acquisition module, configured to acquire the health data of the patient and the historical decision data of the doctor, where the health data includes the historical health data and the current examination data of the patient; A prediction module, configured to input the health data of the patient into a pre-trained prediction model, and have the prediction model make a prediction based on the health data of the patient to obtain a prediction result, where the prediction result is used to indicate the health management services to be executed by the patient; A decision module, configured to input the prediction result and the historical decision data of the doctor into a pre-trained decision model for analysis and processing, and have the decision model obtain a target business recommendation based on the prediction result and the historical decision data of the doctor, where the target business recommendation is used to indicate the health management services to be executed by the doctor among the health management services to be executed by the patient.

9. An electronic device, characterized in that, It includes a memory and a processor, where the memory stores a computer program executable by the processor, and when the processor executes the computer program, it implements the steps of the health management service processing method according to any one of claims 1-7 above.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by the processor, it executes the steps of the health management service processing method according to any one of claims 1-7 above.

Images