Chronic disease inquiry doctor dispatching method and system based on load balancing and user state

Abstract

The invention discloses a chronic disease inquiry doctor dispatching method and system based on load balancing and user states, and belongs to the technical field of computers, and the method specifically comprises the steps: collecting and preprocessing patient information, doctor information and system state information; performing preliminary health condition evaluation on the patient, determining a demand level, and evaluating a load demand level of a doctor; generating a preliminary doctor distribution scheme by making a load balancing strategy, and selecting an optimal scheme from the preliminary doctor distribution scheme by using a multi-modal matching method; meanwhile, the system state is monitored, feedback is collected, the load balancing strategy and the doctor dispatching logic are adjusted according to the feedback and a system report, the distribution scheme is optimized, the doctor resource distribution efficiency is improved, and the requirements of patients are met.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and more specifically, is a method and system for dispatching doctors for chronic disease consultation based on load balancing and user status. Background Art

[0002] With the aging of the population and the increasing number of patients with chronic diseases, the medical industry is facing huge challenges. On the one hand, patients with chronic diseases need long-term and continuous medical services, and the limited medical resources make the workload of doctors increasingly heavy. On the other hand, the increasingly diversified medical needs of patients have put forward higher requirements for the quality and efficiency of medical services. Therefore, how to reasonably allocate doctor resources and improve the efficiency and quality of medical services has become an urgent problem to be solved in the medical industry.

[0003] For example, a Chinese patent with authorization announcement number CN112185533B discloses a telemedicine system and a telemedicine doctor resource allocation method and storage medium. The telemedicine system includes: a first terminal for receiving a user's symptom description, real-time physical sign data and medical consultation request and uploading them to a server; a second terminal for displaying the user's historical consultation data and the real-time physical sign data, receiving the diagnosis result input by the doctor and sending it to the server, and receiving the doctor's appointment return visit operation; the server includes: a portrait module for obtaining doctor portrait data and user portrait data; a prediction module for predicting the number of medical consultation requests within a first preset time period; and an allocation module for realizing the allocation of the doctor based on the doctor portrait data, the user portrait data and the prediction data obtained by the prediction module. This technical solution can achieve reasonable allocation of doctors.

[0004] The above existing technologies all have the following problems: lack of dynamic adjustment mechanism and lack of feedback from patients and doctors, resulting in low accuracy and reliability. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a method and system for assigning doctors for chronic disease consultation based on load balancing and user status, which collects and preprocesses patient information, doctor information and system status information; conducts a preliminary health status assessment on the patient, determines the demand level, and evaluates the doctor's load demand level; generates a preliminary doctor allocation plan by formulating a load balancing strategy, and selects the optimal plan from it using a multimodal matching method; monitors the system status and collects feedback at the same time, and adjusts the load balancing strategy and doctor allocation logic based on the feedback and system reports, optimizes the allocation plan, improves the efficiency of doctor resource allocation, and meets patient needs.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The method for dispatching doctors for chronic disease consultation based on load balancing and user status includes:

[0008] Step S1: Collect patient information, doctor information and system status information, and perform preprocessing;

[0009] Step S2: Perform a preliminary health status assessment on the pre-processed patient information to determine the patient's demand level. At the same time, determine the doctor's load demand level based on the pre-processed doctor information and system status information;

[0010] Step S3: according to the load demand level of the doctors, a preliminary doctor allocation plan is generated using a load balancing strategy. At the same time, according to the demand level of the patients, the optimal doctor allocation plan is selected from the preliminary doctor allocation plan through a multimodal matching method;

[0011] Step S4: Apply the optimal doctor allocation scheme to the actual doctor assignment, monitor the system operation status in real time, and collect feedback from patients and doctors;

[0012] Step S5: Based on the feedback information and the system operation status report, adjust the load balancing strategy and doctor dispatch logic, optimize the optimal doctor allocation plan, and reapply the optimized load balancing strategy and doctor dispatch logic to step S1.

[0013] Specifically, the specific steps of step S2 include:

[0014] S2.1: Obtain pre-treatment patient information , and perform feature extraction to obtain patient feature data ,in, represents the a-th preprocessed patient information, and a represents the number of preprocessed patient information;

[0015] S2.2: Load the pre-trained health status assessment model and the patient characteristic data Input into the pre-trained health status assessment model and output the patient's need level ,and ,in, represents the health status assessment model, Indicates that the patient is in a condition that can receive regular follow-up. Indicates that the patient is in a non-emergency condition. Indicates that the patient is in an emergency.

[0016] Specifically, the specific steps of step S2 also include:

[0017] S2.3: Obtain pre-processed doctor information and system status information , and perform feature extraction, integrate the doctor feature data after feature extraction with the system status feature data to obtain load feature data ,in, represents the b-th preprocessed doctor information, b represents the number of preprocessed doctor information, represents the cth preprocessed system status information, c represents the number of preprocessed system status information, represents the dth load characteristic data, where d represents the number of load characteristic data;

[0018] S2.4: Load the pre-trained load demand assessment model and Input into the pre-trained load demand assessment model and output the doctor's load demand level ,and ,in, represents the load demand assessment model, Indicates that the doctor is idle. Indicates that the doctor is in a low load state. Indicates that doctors are under high load.

[0019] Specifically, the specific steps of step S3 include:

[0020] S3.1: Acquisition , and ,as well as and ;

[0021] S3.2: Use load balancing strategy in combination and , generate a preliminary physician allocation plan;

[0022] S3.3: Establish a multimodal matching model and use it to optimize the preliminary doctor allocation plan. By comparing the matching degree of different allocation plans, the optimal doctor allocation plan is selected.

[0023] Specifically, the specific steps of S3.2 include:

[0024] S3.21: Create a list of all doctors, each with a corresponding weight value ,in, represents the weight corresponding to the i-th doctor, and n represents the number of doctors;

[0025] S3.22: When there is a new request to be allocated, select The corresponding doctor will be assigned The corresponding doctor's weight is updated to , and all doctors’ weights are incrementally updated according to their original weight values , and record the doctor allocation results, where Indicates the current maximum weight. Indicates the weight value corresponding to the current doctor's weight after update, represents a fixed weight value, It represents the corresponding weight value after the incremental update of the weight of the ith doctor. represents the original weight value of the i-th doctor;

[0026] S3.23: Generate and output a preliminary doctor allocation plan based on the doctor allocation results.

[0027] Specifically, the specific steps of S3.3 include:

[0028] S3.31: Acquisition , and , and preprocessing;

[0029] S3.32: After preprocessing Perform feature extraction and obtain load feature data At the same time, load the pre-built multimodal matching model based on deep learning and use and after feature extraction Train the multimodal matching model;

[0030] S3.33: Input the preliminary doctor allocation plan obtained in step S3.23 into the trained multimodal matching model. Through calculation and analysis of the multimodal matching model, the matching degree of different doctor allocation plans is obtained, and the preliminary allocation plan is adjusted and optimized according to the matching degree. The matching degree calculation formula is:

[0031] ;

[0032] in, Indicates the degree of match between patients and doctors, , , , represents the weight coefficient;

[0033] S3.34: Among multiple optimized allocation plans, select the plan with the highest degree of match and the one that best meets patient needs and physician work arrangements as the best plan, and submit the best plan to the hospital management for approval and implementation.

[0034] Specifically, the doctor assignment logic in step S5 refers to the rules and algorithms for assigning patients to doctors, including data collection and preprocessing, preliminary evaluation and demand determination, load balancing and preliminary allocation, optimal solution selection and actual assignment, real-time monitoring and feedback optimization.

[0035] The chronic disease consultation doctor dispatching system based on load balancing and user status includes: information processing module, level determination module, plan formulation module, plan execution module, and optimization module;

[0036] The information processing module is used to collect and pre-process patient information, doctor information and system status information;

[0037] The level determination module is used to evaluate and analyze the collected patient information, doctor information and system status information to obtain the patient's demand level and the doctor's load demand level;

[0038] The plan formulation module is used to generate an optimal doctor allocation plan based on the load balancing strategy and combined with the multi-modal matching method;

[0039] The scheme execution module is used to execute the optimal doctor allocation scheme, ensure the smooth execution of the optimal doctor allocation scheme, and collect feedback from patients and doctors;

[0040] The optimization module is used to adjust and optimize the load balancing strategy and doctor dispatching logic according to feedback information and system operation status report.

[0041] Specifically, the solution formulation module includes: a strategy formulation unit, a multimodal matching unit, a solution generation unit, and an optimal solution selection unit;

[0042] The strategy formulation unit is used to design the doctor dispatching logic according to the doctor's load and professional ability;

[0043] The multimodal matching unit is used to adopt a multimodal matching method to find the best matching solution according to the patient's needs and the doctor's ability;

[0044] The scheme generating unit is used to generate a preliminary doctor allocation scheme according to the load balancing strategy and the matching result;

[0045] The optimal solution selection unit is used to select the optimal doctor allocation solution from multiple preliminary solutions.

[0046] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for assigning doctors for chronic disease consultation based on load balancing and user status are implemented.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention proposes a chronic disease consultation doctor dispatching system based on load balancing and user status, and optimizes and improves the architecture, operating steps and processes. The system has the advantages of simple process, low investment and operating costs, and low production work costs.

[0049] 2. The present invention proposes a method for assigning doctors for chronic disease consultation based on load balancing and user status. By collecting and preprocessing patient, doctor and system status information, combined with preliminary health status assessment and load balancing strategy, it can generate and optimize doctor allocation plans, ensure that doctor resources are reasonably allocated, and improve the efficiency and quality of medical services.

[0050] 3. The present invention proposes a method for assigning doctors to chronic disease consultations based on load balancing and user status. By real-time monitoring and collecting feedback, the load balancing strategy and doctor assignment logic are continuously adjusted and optimized, thereby achieving continuous optimization of the medical service system and ensuring the stability and reliability of the system operation, thereby providing patients with better-quality and more efficient medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a method for assigning doctors for chronic disease consultation based on load balancing and user status according to the present invention;

[0052] Figure 2 This is a principle flow chart of the method for assigning doctors for chronic disease consultation based on load balancing and user status of the present invention;

[0053] Figure 3 A flowchart for realizing the optimal doctor allocation scheme of the chronic disease consultation doctor allocation method based on load balancing and user status of the present invention;

[0054] Figure 4 This is an architecture diagram of the chronic disease consultation doctor dispatching system based on load balancing and user status of the present invention. DETAILED DESCRIPTION

[0055] Example 1

[0056] See also Figure 1-Figure 3 , an embodiment provided by the present invention: a method for dispatching doctors for chronic disease consultation based on load balancing and user status, comprising the following steps:

[0057] Step S1: Collect patient information, doctor information and system status information, and perform preprocessing;

[0058] It should be noted that (1) patient information is collected through online questionnaires and electronic medical record systems to collect the patient's age, gender, condition description, past medical history, and lifestyle information; (2) doctor information is collected from the hospital management system to obtain information such as the doctor's professional background, areas of expertise, current workload, and historical patient evaluations; (3) system status information collection: real-time monitoring of the current number of online doctors, each doctor's idle time, and system load; (4) data preprocessing refers to cleaning and standardizing the collected data to ensure data accuracy and consistency.

[0059] Step S2: Perform a preliminary health status assessment on the pre-processed patient information to determine the patient's demand level. At the same time, determine the doctor's load demand level based on the pre-processed doctor information and system status information;

[0060] Step S3: according to the load demand level of the doctors, a preliminary doctor allocation plan is generated using a load balancing strategy. At the same time, according to the demand level of the patients, the optimal doctor allocation plan is selected from the preliminary doctor allocation plan through a multimodal matching method;

[0061] Step S4: Apply the optimal doctor allocation scheme to the actual doctor assignment, monitor the system operation status in real time, and collect feedback from patients and doctors;

[0062] Furthermore, the configuration of the real-time monitoring system includes: setting monitoring indicators, such as doctor attendance rate, work efficiency, patient satisfaction, monitoring frequency and alarm mechanism; feedback channels include: online survey platform, telephone hotline, suggestion box.

[0063] Ensure the stability and accuracy of the monitoring system so that the implementation effect of the doctor allocation plan can be reflected in real time.

[0064] Step S5: Based on the feedback information and the system operation status report, adjust the load balancing strategy and doctor dispatch logic, optimize the optimal doctor allocation plan, and reapply the optimized load balancing strategy and doctor dispatch logic to step S1.

[0065] The doctor assignment logic in step S5, i.e., the logical rules and algorithms for assigning patients to doctors during the doctor assignment process, includes data collection and preprocessing, preliminary evaluation and demand determination, load balancing and preliminary allocation, optimal solution selection and actual assignment, real-time monitoring and feedback optimization.

[0066] Specifically, when there is a new patient request or task that needs to be assigned to a doctor, the request is received and its related information is parsed, such as the description of the condition, the degree of urgency, and the required professional skills. Based on the information of the new request and the current status of each doctor, an allocation weight is calculated for each doctor, where the weight can be a comprehensive score that reflects the doctor's suitability for handling the request. The weight list is then traversed to find the doctor with the largest weight value. This doctor will be considered the most suitable doctor for handling the current request. The new request is then assigned to the doctor with the largest weight, and the doctor's current status and weight are updated. Finally, based on the allocation results, a preliminary doctor allocation plan is generated. This plan can be a simple list or table showing the tasks or patient requests assigned to each doctor.

[0067] Among them, the adjustments to the load balancing strategy and doctor dispatch logic mainly include: changing weight distribution, optimizing algorithm parameters, and increasing or reducing doctor resources.

[0068] The specific steps of step S2 include:

[0069] S2.1: Obtain pre-treatment patient information , and perform feature extraction to obtain patient feature data ,in, represents the a-th preprocessed patient information, and a represents the number of preprocessed patient information;

[0070] In the present invention, the principal component analysis method is used for feature extraction, and the principal component analysis method is the prior art content in this field, and is not the inventive solution of the present application, and will not be described in detail here.

[0071] S2.2: Load the pre-trained health status assessment model and the patient characteristic data Input into the pre-trained health status assessment model and output the patient's need level ,and ,in, represents the health status assessment model, Indicates that the patient is in a condition that can receive regular follow-up. Indicates that the patient is in a non-emergency condition. Indicates that the patient is in an emergency;

[0072] In the present invention, the regression analysis method is selected to build the model, and the historical The model is trained to obtain a trained health status assessment model. Meanwhile, the construction and training of the model are prior art contents in this field and are not the creative solutions of the present application, and will not be elaborated here.

[0073] S2.3: Obtain pre-processed doctor information and system status information , and perform feature extraction, integrate the doctor feature data after feature extraction with the system status feature data to obtain load feature data ,in, represents the b-th preprocessed doctor information, b represents the number of preprocessed doctor information, represents the cth preprocessed system status information, c represents the number of preprocessed system status information, represents the dth load characteristic data, where d represents the number of load characteristic data;

[0074] S2.4: Load the pre-trained load demand assessment model and Input into the pre-trained load demand assessment model and output the doctor's load demand level ,and ,in, represents the load demand assessment model, Indicates that the doctor is idle. Indicates that the doctor is in a low load state. It indicates that the doctor is in a high load state, and the construction, training and internal calculation process of the load demand assessment model are the prior art content in this field, which is not the creative solution of this application and will not be elaborated here.

[0075] The specific steps of step S3 include:

[0076] S3.1: Acquisition , and ,as well as and ;

[0077] S3.2: Use load balancing strategy in combination and , generate a preliminary physician allocation plan;

[0078] S3.3: Establish a multimodal matching model and use it to optimize the preliminary doctor allocation plan. By comparing the matching degree of different allocation plans, the optimal doctor allocation plan is selected.

[0079] The specific steps of S3.2 include:

[0080] S3.21: Create a list of all doctors, each with a corresponding weight value ,in, represents the weight corresponding to the i-th doctor, and n represents the number of doctors;

[0081] Here, creating a list of all doctors means: creating a list or data structure to store the current weight of each doctor, which may be calculated based on factors such as the doctor's experience, current load, free time, professional field matching, etc.

[0082] S3.22: When there is a new request to be allocated, select The corresponding doctor will be assigned The corresponding doctor's weight is updated to , and all doctors’ weights are incrementally updated according to their original weight values , and record the doctor allocation results, where Indicates the current maximum weight. Indicates the weight value corresponding to the current doctor's weight after update, represents a fixed weight value, It represents the corresponding weight value after the incremental update of the weight of the ith doctor. represents the original weight value of the i-th doctor;

[0083] S3.23: Based on the doctor allocation results, generate and output a preliminary doctor allocation plan, where the doctor allocation plan should include information such as the number of tasks or requests assigned to each doctor.

[0084] The specific steps of S3.3 include:

[0085] S3.31: Acquisition , and , and preprocessing;

[0086] S3.32: After preprocessing Perform feature extraction and obtain load feature data At the same time, load the pre-built multimodal matching model based on deep learning and use and after feature extraction Train the multimodal matching model;

[0087] S3.33: Input the preliminary doctor allocation plan obtained in step S3.23 into the trained multimodal matching model. Through calculation and analysis of the multimodal matching model, the matching degree of different doctor allocation plans is obtained, and the preliminary allocation plan is adjusted and optimized according to the matching degree. The matching degree calculation formula is:

[0088] ;

[0089] in, Indicates the degree of match between the patient and the doctor. , , , represents the weight coefficient, and the construction, training and internal calculation process of the multimodal matching model based on deep learning are the prior art content in this field, which is not the inventive solution of the present application and will not be described in detail here;

[0090] S3.34: Among multiple optimized allocation plans, select the plan with the highest degree of match and the one that best meets patient needs and physician work arrangements as the best plan, and submit the best plan to the hospital management for approval and implementation.

[0091] Furthermore, the specific steps of S3.34 include:

[0092] (1) Obtaining the optimized allocation plan;

[0093] (2) Design an evaluation system to quantify the degree to which each allocation scheme matches patient needs and physician work schedules. The evaluation system can include multiple indicators, such as patient satisfaction, physician work efficiency, and resource utilization;

[0094] (3) According to the evaluation system, a weighted average method is used to calculate a matching score for each allocation scheme. The weighted average method is a prior art in this field and is not an inventive solution of the present application, so it will not be described in detail here.

[0095] (4) Compare the matching scores of various allocation plans and select the allocation plan with the highest score as the optimal plan. If there are multiple allocation plans with similar scores, make a decision based on the feasibility of the plan implementation;

[0096] (5) The optimal plan and its matching score, evaluation process and other related information are organized into approval materials and submitted to the hospital management for approval. If the management approves the optimal plan, doctors are assigned and resources are allocated according to the plan.

[0097] Example 2

[0098] See also Figure 4 Another embodiment provided by the present invention is a chronic disease consultation doctor dispatching system based on load balancing and user status, comprising:

[0099] Information processing module, level determination module, plan formulation module, plan execution module, and optimization module;

[0100] Information processing module, used for collecting and preprocessing patient information, doctor information and system status information;

[0101] A level determination module is used to evaluate and analyze the collected patient information, doctor information and system status information to obtain the patient's demand level and the doctor's load demand level;

[0102] The plan formulation module is used to generate the optimal doctor allocation plan based on the load balancing strategy and combined with the multi-modal matching method;

[0103] The program execution module is used to execute the optimal doctor allocation plan to ensure the smooth implementation of the optimal doctor allocation plan. At the same time, it collects feedback from patients and doctors to provide a basis for subsequent strategy adjustments.

[0104] The optimization module is used to adjust and optimize the load balancing strategy and doctor dispatch logic based on feedback information and system operation status reports to ensure that the system can operate continuously and efficiently.

[0105] The level determination module includes: a health status assessment unit, a load demand assessment unit;

[0106] A health status assessment unit, used to assess the health status of the patient and determine the patient's need level based on the patient's information;

[0107] The load demand evaluation unit is used to evaluate the load demand of the doctor based on the doctor's information and system status information, and determine the load demand level of the doctor.

[0108] The solution formulation module includes: strategy formulation unit, multimodal matching unit, solution generation unit, and optimal solution selection unit;

[0109] A strategy formulation unit, which is used to design the doctor dispatch logic according to the doctor's load and professional ability;

[0110] A multimodal matching unit, used to adopt a multimodal matching method to find the best matching solution according to patient needs and doctor capabilities;

[0111] A plan generation unit, used for generating a preliminary doctor allocation plan according to the load balancing strategy and matching results;

[0112] The optimal solution selection unit is used to select the optimal doctor allocation solution from multiple preliminary solutions.

[0113] The scheme execution module includes: an allocation scheme execution unit, a system status monitoring unit, and a feedback unit;

[0114] An allocation plan execution unit, used for applying the optimal doctor allocation plan to the actual doctor allocation;

[0115] System status monitoring unit, used to monitor the system operation status in real time to ensure the smooth execution of the allocation plan;

[0116] Feedback unit, used to collect feedback from patients and doctors.

[0117] The optimization module includes: strategy analysis unit, strategy adjustment unit, and optimization solution application unit;

[0118] A strategy analysis unit, used to analyze the current load balancing strategy and doctor dispatch logic based on feedback information and system operation status reports;

[0119] A strategy adjustment unit, used to adjust and optimize the load balancing strategy and doctor dispatching logic according to the analysis results;

[0120] The optimization solution application unit is used to reapply the optimized load balancing strategy and doctor dispatching logic to the system to ensure that the system can run continuously and efficiently.

[0121] Example 3

[0122] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for assigning doctors for chronic disease consultation based on load balancing and user status are implemented. For details, please refer to the above method embodiment, which will not be repeated here.

[0123] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

[0124] If the disclosed technical solution involves personal information, the product using the disclosed technical solution has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the disclosed technical solution involves sensitive personal information, the product using the disclosed technical solution has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for assigning doctors for chronic disease consultation based on load balancing and user status, characterized in that: include: Step S1: Collect patient information, doctor information and system status information, and perform preprocessing; Step S2: Perform a preliminary health status assessment on the pre-processed patient information to determine the patient's demand level. At the same time, determine the doctor's load demand level based on the pre-processed doctor information and system status information; Step S3: according to the load demand level of the doctors, a preliminary doctor allocation plan is generated using a load balancing strategy. At the same time, according to the demand level of the patients, the optimal doctor allocation plan is selected from the preliminary doctor allocation plan through a multimodal matching method; Step S4: Apply the optimal doctor allocation scheme to the actual doctor assignment, monitor the system operation status in real time, and collect feedback from patients and doctors; Step S5: Based on the feedback information and the system operation status report, adjust the load balancing strategy and doctor dispatch logic, optimize the optimal doctor allocation plan, and reapply the optimized load balancing strategy and doctor dispatch logic to step S1.

2. The method for assigning doctors for chronic disease consultation based on load balancing and user status according to claim 1, characterized in that: The specific steps of step S2 include: S2.1: Obtain pre-treatment patient information , and perform feature extraction to obtain patient feature data ,in, represents the a-th preprocessed patient information, and a represents the number of preprocessed patient information; S2.2: Load the pre-trained health status assessment model and the patient characteristic data Input into the pre-trained health status assessment model and output the patient's need level ,and ,in, represents the health status assessment model, Indicates that the patient is in a condition that can receive regular follow-up. Indicates that the patient is in a non-emergency condition. Indicates that the patient is in an emergency.

3. The method for assigning doctors for chronic disease consultation based on load balancing and user status as claimed in claim 2, characterized in that: The specific steps of step S2 also include: S2.3: Obtain pre-processed doctor information and system status information , and perform feature extraction, integrate the doctor feature data after feature extraction with the system status feature data to obtain load feature data ,in, represents the b-th preprocessed doctor information, b represents the number of preprocessed doctor information, represents the cth preprocessed system status information, c represents the number of preprocessed system status information, represents the dth load characteristic data, where d represents the number of load characteristic data; S2.4: Load the pre-trained load demand assessment model and Input into the pre-trained load demand assessment model and output the doctor's load demand level ,and ,in, represents the load demand assessment model, Indicates that the doctor is idle. Indicates that the doctor is in a low load state. Indicates that doctors are under high load.

4. The method for assigning doctors for chronic disease consultation based on load balancing and user status as claimed in claim 3, characterized in that: The specific steps of step S3 include: S3.1: Acquisition , and ,as well as and ; S3.2: Use load balancing strategy in combination and , generate a preliminary physician allocation plan; S3.3: Establish a multimodal matching model and use it to optimize the preliminary doctor allocation plan. By comparing the matching degree of different allocation plans, the optimal doctor allocation plan is selected.

5. The method for assigning doctors for chronic disease consultation based on load balancing and user status according to claim 4, characterized in that: The specific steps of S3.2 include: S3.21: Create a list of all doctors, each with a corresponding weight value ,in, represents the weight corresponding to the i-th doctor, and n represents the number of doctors; S3.22: When there is a new request to be allocated, select The corresponding doctor will be assigned The corresponding doctor's weight is updated to , and all doctors’ weights are incrementally updated according to their original weight values , and record the doctor allocation results, where Indicates the current maximum weight. Indicates the weight value corresponding to the current doctor's weight after update, represents a fixed weight value, It represents the corresponding weight value after the incremental update of the weight of the ith doctor. represents the original weight value of the i-th doctor; S3.23: Generate and output a preliminary doctor allocation plan based on the doctor allocation results.

6. The method for assigning doctors for chronic disease consultation based on load balancing and user status according to claim 5, characterized in that: The specific steps of S3.3 include: S3.31: Acquisition , and , and preprocessing; S3.32: After preprocessing Perform feature extraction and obtain load feature data At the same time, load the pre-built multimodal matching model based on deep learning and use and after feature extraction Train the multimodal matching model; S3.33: Input the preliminary doctor allocation plan obtained in step S3.23 into the trained multimodal matching model. Through calculation and analysis of the multimodal matching model, the matching degree of different doctor allocation plans is obtained, and the preliminary allocation plan is adjusted and optimized according to the matching degree. The matching degree calculation formula is: ； in, Indicates the degree of match between the patient and the doctor. , , , represents the weight coefficient; S3.34: Among multiple optimized allocation plans, select the plan with the highest degree of match and the one that best meets patient needs and physician work arrangements as the best plan, and submit the best plan to the hospital management for approval and implementation.

7. The method for assigning doctors for chronic disease consultation based on load balancing and user status according to claim 6, characterized in that: The doctor assignment logic in step S5 refers to the rules and algorithms for assigning patients to doctors, including data collection and preprocessing, preliminary evaluation and demand determination, load balancing and preliminary allocation, optimal solution selection and actual assignment, real-time monitoring and feedback optimization.

8. A system for dispatching doctors for chronic disease consultation based on load balancing and user status, which is used to implement a method for dispatching doctors for chronic disease consultation based on load balancing and user status as described in any one of claims 1 to 7, characterized in that: include: Information processing module, level determination module, plan formulation module, plan execution module, and optimization module; The information processing module is used to collect and pre-process patient information, doctor information and system status information; The level determination module is used to evaluate and analyze the collected patient information, doctor information and system status information to obtain the patient's demand level and the doctor's load demand level; The plan formulation module is used to generate an optimal doctor allocation plan based on the load balancing strategy and combined with the multi-modal matching method; The scheme execution module is used to execute the optimal doctor allocation scheme, ensure the smooth execution of the optimal doctor allocation scheme, and collect feedback from patients and doctors; The optimization module is used to adjust and optimize the load balancing strategy and doctor dispatching logic according to feedback information and system operation status report.

9. The chronic disease consultation doctor dispatching system based on load balancing and user status as claimed in claim 8, characterized in that: The solution formulation module includes: a strategy formulation unit, a multi-modal matching unit, a solution generation unit, and an optimal solution selection unit; The strategy formulation unit is used to design the doctor dispatching logic according to the doctor's load and professional ability; The multimodal matching unit is used to adopt a multimodal matching method to find the best matching solution according to the patient's needs and the doctor's ability; The scheme generating unit is used to generate a preliminary doctor allocation scheme according to the load balancing strategy and the matching result; The optimal solution selection unit is used to select the optimal doctor allocation solution from multiple preliminary solutions.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for assigning doctors for chronic disease consultation based on load balancing and user status as described in any one of claims 1-7 are implemented.

Images