Allocation and scheduling method and system for dynamic resources of hemodialysis center

Abstract

The invention relates to the field of hemodialysis center resource management, and particularly provides a dynamic resource allocation and scheduling method and system, which comprises a data acquisition module, a resource prediction unit, a scheduling module, a conflict detection module, an adjustment optimization module and a display output module. A resource demand distribution diagram and a priority sequence are generated by collecting patient demands, equipment states and medical staff information in real time, an initial scheduling scheme is generated by utilizing multi-dimensional weight analysis, and a final scheduling plan is formed after conflict detection and dynamic adjustment. According to the method, the resource utilization rate and the scheduling flexibility can be remarkably improved, the precise scheduling requirement in a complex scene is met, the manual intervention frequency is reduced, and the patient satisfaction degree is improved.

Description

Technical Field

[0001] The present invention belongs to the field of hemodialysis center resource management, specifically a method and system for allocating and scheduling dynamic resources in a hemodialysis center Background Art

[0002] With the continuous development of medical technology, hemodialysis centers are important places for treating patients with chronic kidney disease. The efficiency of their resource allocation and scheduling management directly affects the quality of medical services and patient satisfaction. However, existing hemodialysis centers still have many shortcomings in dynamic resource allocation and intelligent scheduling, which makes it difficult to meet the growing patient needs and complex and changing operating environment. After searching, it was found that the patent with publication number CN112750521B discloses an intelligent scheduling feedback system for dialysis patients. The system connects the patient terminal and the medical terminal through a server, realizes the function of patients adjusting their scheduling time independently, and improves work efficiency. However, this technical solution mainly focuses on the scheduling request on the patient side and the confirmation process on the medical side, and fails to fully consider the dynamic allocation of the overall resources of the hemodialysis center (such as equipment, medical staff, beds, etc.). In addition, the system lacks the ability to comprehensively analyze real-time data (such as changes in patient condition, equipment usage status, etc.), which may lead to unreasonable resource allocation or scheduling conflicts, affecting the continuity and efficiency of medical services.

[0003] At the same time, the patent with publication number CN112017765B discloses a method and system for intelligent scheduling of the ultrasound department of a large tertiary teaching hospital. This solution realizes semi-automatic intelligent scheduling by configuring basic information and scheduling rules, combined with the number of individual doctor posts predicted by the system. Although this technical solution has improved the rationality of scheduling and the level of refined management to a certain extent, its application scenario is mainly for the ultrasound department, and it does not fully consider the resource constraints unique to hemodialysis centers (such as the use time limit of the dialysis machine, the periodic treatment needs of patients, etc.). In addition, the solution has a weak response capability to dynamically changing factors (such as sudden patient needs, equipment failures, etc.), and may not be able to adjust the scheduling plan in time, resulting in waste of resources or excessive waiting time for patients.

[0004] These issues demonstrate that existing intelligent scheduling systems for hemodialysis centers suffer from insufficient dynamic resource allocation capabilities, a lack of real-time response mechanisms, and poor adaptability to specific scenarios. Therefore, a method and system that can comprehensively analyze real-time data and dynamic constraints is urgently needed to optimize resource utilization efficiency in hemodialysis centers, enhance scheduling flexibility and accuracy, and better meet the operational needs of hemodialysis centers and ensure a better patient experience. Summary of the Invention

[0005] This application provides a dynamic resource allocation and scheduling method and system, the main purpose of which is to improve resource utilization and scheduling flexibility, meet the needs of accurate scheduling in complex scenarios, reduce the frequency of manual intervention and improve patient satisfaction.

[0006] To achieve the above objectives, the present invention provides a dynamic resource allocation and scheduling system for hemodialysis centers, comprising:

[0007] Data acquisition module, used to obtain patient treatment needs, equipment status and medical staff information in real time;

[0008] Resource forecasting unit, which generates daily resource demand profiles and priority rankings based on historical data and real-time inputs;

[0009] The first scheduling module is used to perform preliminary scheduling based on patient treatment time, equipment usage sequence, and medical staff configuration through multi-dimensional weight analysis to generate an initial scheduling plan;

[0010] A conflict detection module, used to verify the feasibility of the initial scheduling plan;

[0011] An adjustment and optimization module is used to reallocate resources using dynamic constraints when conflicts are detected and generate an adjusted solution;

[0012] The second scheduling module is used to make a refined allocation of the adjusted plan in combination with the real-time updated data to generate a final scheduling plan;

[0013] The display output module is used to push the final shift schedule to a preset terminal.

[0014] Optionally, the resource prediction unit generates a daily resource demand distribution graph based on a time series analysis algorithm, and the time series analysis algorithm calculates the daily resource demand distribution R(t) through the formula R(t) = α·H(t) + (1-α)·C(t), where H(t) represents the trend value of historical data, C(t) represents the correction value of real-time input, and α is the weight coefficient.

[0015] Optionally, the first scheduling module uses a multi-objective optimization model to generate an initial scheduling plan, and the objective function F of the multi-objective optimization model is defined as F=w1·P+w2·D+w3·S, where P represents the patient priority score, D represents the equipment allocation efficiency, S represents the rationality of medical staff configuration, and w1, w2, and w3 are the weight coefficients of each factor respectively.

[0016] Optionally, the conflict detection module performs a feasibility analysis on the initial scheduling plan through a rule-based conflict identification algorithm, which converts the resource allocation relationship into a set of constraint conditions and checks one by one whether there is any violation of the constraint.

[0017] Optionally, the adjustment and optimization module uses a heuristic search algorithm to reallocate resources, and the heuristic search algorithm gradually adjusts the allocation scheme of related resources starting from the conflict point until all conflicts are eliminated.

[0018] Optionally, the second scheduling module adopts an incremental update strategy to refine the allocation of the adjusted plan, and only makes local adjustments to the affected parts to reduce computing overhead.

[0019] To achieve the above objectives, the present application also provides a method for dynamic resource allocation and scheduling in a hemodialysis center, comprising the following steps:

[0020] Collect patient treatment needs, equipment status, and medical staff information in real time and generate daily resource demand distribution maps and priority rankings;

[0021] Generate initial scheduling plan through multi-dimensional weight analysis;

[0022] Conduct conflict detection on the initial scheduling plan and adjust it to generate an optimized plan;

[0023] Combined with real-time updated data, the optimization plan is refined and allocated, and the final scheduling plan is generated and pushed to the terminal for display.

[0024] Optionally, a time series analysis algorithm is used in the step of generating a daily resource demand distribution graph. The time series analysis algorithm calculates the daily resource demand distribution R(t) through the formula R(t) = α·H(t) + (1-α)·C(t), where H(t) represents the trend value of historical data, C(t) represents the correction value of real-time input, and α is the weight coefficient.

[0025] To achieve the above objectives, the present application further provides an electronic device, comprising:

[0026] Memory, used to store computer programs;

[0027] A processor is configured to execute the computer program to implement the method as described in any one of the above items.

[0028] To achieve the above objectives, the present application also provides a computer-readable storage medium for storing a computer program, which implements any of the above methods when executed by a processor.

[0029] The present invention relates to the field of resource management of hemodialysis centers, and in particular to a method and system for allocating and scheduling dynamic resources in hemodialysis centers. In the first aspect, a dynamic resource allocation and scheduling system for a hemodialysis center is provided, comprising a data acquisition module for obtaining patient treatment needs, equipment status, and medical staff information in real time; a resource prediction unit generates a daily resource demand distribution map and priority ranking based on historical data and real-time input; a first scheduling module performs preliminary scheduling of patient treatment time, equipment usage sequence, and medical staff configuration through multi-dimensional weight analysis to generate an initial scheduling plan; a conflict detection module verifies the feasibility of the initial scheduling plan; when a conflict is detected, the adjustment and optimization module reallocates resources using dynamic constraints to generate an adjusted plan; a second scheduling module performs refined allocation of the adjusted plan in combination with real-time updated data to generate a final scheduling plan; and a display output module pushes the final scheduling plan to a preset terminal. Through multi-level resource scheduling and dynamic adjustment mechanisms, resource utilization and scheduling flexibility are significantly improved, accurate scheduling requirements in complex scenarios are met, the frequency of manual intervention is reduced, and patient satisfaction is improved.

[0030] Secondly, a dynamic resource allocation and scheduling method for a hemodialysis center is provided, including real-time collection of patient treatment needs, equipment status, and medical staff information to generate a daily resource demand distribution map and priority ranking; generating an initial scheduling plan through multi-dimensional weight analysis; performing conflict detection on the initial scheduling plan and adjusting it to generate an optimized plan; combining real-time updated data to make detailed allocations of the optimized plan, generating a final scheduling plan, and pushing it to the terminal for display.

[0031] In a third aspect, an electronic device is provided, comprising a memory and a processor to implement the aforementioned dynamic resource allocation and scheduling method for a hemodialysis center.

[0032] In a fourth aspect, a computer-readable storage medium is provided for storing a computer program, which, when executed by a processor, implements the aforementioned dynamic resource allocation and scheduling method for a hemodialysis center. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the module structure of a dynamic resource allocation and scheduling system for a hemodialysis center disclosed in this application;

[0034] Figure 2 This is an overall flow chart of a dynamic resource allocation and scheduling method for a hemodialysis center disclosed in this application;

[0035] Figure 3 This is a schematic diagram of the hardware structure of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0036] The present invention provides a method and system for dynamic resource allocation and scheduling in a hemodialysis center. The core of the method is to achieve precise management of patient treatment needs, equipment status, and medical staff configuration through a multi-level scheduling mechanism and dynamic adjustment strategy. Figure 1 To the attached Figure 3 , the specific embodiments of the present invention will be described in detail below.

[0037] like Figure 1 As shown, the dynamic resource allocation and scheduling system for hemodialysis centers of the present invention includes multiple functional modules, which work together to complete the entire process from data collection to the generation of the final scheduling plan. The operation of the system starts with the data acquisition module, which is responsible for obtaining patient treatment needs, equipment status, and medical staff information in real time. Among them, patient treatment needs include the severity of the patient's condition, treatment time window preference, and special medical needs; equipment status covers the working status, maintenance cycle, and fault records of the dialysis machine; medical staff information includes the scheduling, skill level, and current task load of doctors, nurses, and other staff. These data are collected through the hospital's internal information system or external sensor network and stored in a unified data pool to provide a basis for subsequent analysis.

[0038] After data collection is completed, the system enters the processing stage of the resource prediction unit. The resource prediction unit generates a daily resource demand distribution map and priority ranking based on historical data and real-time input. Historical data includes patient visit records, equipment usage frequency, and medical staff work mode statistics over a period of time; real-time input is provided by the data acquisition module to reflect current dynamic changes. In order to generate an accurate demand distribution map, the present invention adopts a prediction algorithm based on time series analysis. Specifically, assuming that the resource demand distribution on a certain day is R(t), it can be calculated by the following formula:

[0039] R(t)=α·H(t)+(1-α)·C(t)

[0040] Here, H(t) represents the trend value of historical data, C(t) represents the correction value of real-time input, and α is the weight coefficient used to balance the impact of historical data and real-time input. By adjusting the value of α, you can flexibly respond to demand fluctuations in different scenarios. For example, during special periods such as holidays, α can be appropriately lowered to increase sensitivity to real-time changes.

[0041] After generating the resource demand distribution map, the system enters the preliminary scheduling phase of the first scheduling module. The first scheduling module generates an initial scheduling plan by performing a multi-dimensional weighted analysis of patient treatment time, equipment usage sequence, and medical staff configuration. This process involves a comprehensive assessment of multiple key variables, including patient priority, equipment availability, and medical staff skill matching. To quantify the impact of these factors, the present invention introduces a multi-objective optimization model, whose objective function is defined as:

[0042] F=w1·P+w2·D+w3·S

[0043] Here, P represents the patient priority score, D represents the efficiency of equipment allocation, S represents the rationality of medical staff deployment, and w1, w2, and w3 represent the weighting coefficients of each factor. By adjusting the weighting coefficients, different optimization goals can be set for different scenarios. For example, in an emergency, the value of w1 can be increased to prioritize the treatment needs of high-risk patients.

[0044] After the initial scheduling plan is generated, the system enters the verification stage of the conflict detection module. The main task of the conflict detection module is to conduct a feasibility analysis of the initial plan and identify potential resource conflict problems. Conflicts may arise from a variety of reasons, such as equipment being repeatedly allocated in the same time period, the task load of medical staff exceeding a reasonable range, or the patient's treatment time window not being met. In order to efficiently detect conflicts, the present invention designs a set of rule-based conflict identification algorithms. The algorithm first converts all resource allocation relationships into a set of constraints, and then checks one by one whether there are any violations of the constraints. If a conflict is detected, the operation of the adjustment optimization module is triggered.

[0045] The adjustment and optimization module is one of the core components of the system. Its function is to use dynamic constraints to reallocate resources when conflicts occur and generate adjusted plans. Dynamic constraints include hard constraints and soft constraints. Hard constraints must be strictly followed, such as the maximum usage time limit of the equipment; soft constraints allow a certain degree of flexibility, such as the patient's time window preference. The adjustment and optimization module uses a heuristic search algorithm to reallocate resources. Its basic idea is to start from the point of conflict and gradually adjust the allocation plan of related resources until all conflicts are eliminated. Taking a specific scenario as an example, assuming that a dialysis machine is allocated to two patients at the same time during a certain period of time, the adjustment and optimization module will give priority to delaying the treatment time of one of the patients and re-evaluate the feasibility of the new plan.

[0046] After adjustments and optimizations, the system enters the refined allocation phase of the second scheduling module. The second scheduling module further optimizes the adjusted plan based on real-time updated data to generate the final schedule. Real-time updated data may include new patient appointments, sudden equipment failures, or temporary leave of absence for medical staff. To ensure the accuracy of the final plan, the second scheduling module adopts an incremental update strategy, making only local adjustments to the affected areas to reduce computational overhead. Furthermore, this module supports the embedding of custom rules, such as setting specific scheduling preferences based on the requirements of hospital management.

[0047] Once the final shift schedule is generated, the display output module pushes it to a pre-defined terminal for display. This terminal can be an electronic display screen within the hospital, a medical staff member's mobile device, or a patient's personal terminal. To enhance the user experience, the display output module offers a variety of visualization formats, including Gantt charts, table views, and calendar views. Users can choose the appropriate display format based on their needs and use the interactive interface to view detailed information and make modification suggestions.

[0048] like Figure 2 As shown, the present invention also provides a dynamic resource allocation and scheduling method for a hemodialysis center, and its process is highly consistent with the above-mentioned system architecture. The implementation steps of the method include real-time collection of patient treatment needs, equipment status and medical staff information and generation of a daily resource demand distribution map and priority ranking; generating an initial scheduling plan through multi-dimensional weight analysis; performing conflict detection on the initial scheduling plan and adjusting it to generate an optimized plan; combining real-time updated data to perform refined allocation of the optimized plan, generate a final scheduling plan and push it to the terminal for display. The specific operations of each step have been described in detail in the aforementioned system description and will not be repeated here.

[0049] Finally, if Figure 3 As shown, the present invention also provides an electronic device comprising a memory and a processor for implementing the aforementioned method for dynamic resource allocation and scheduling in a hemodialysis center. The memory is used to store various data and program codes required for system operation, while the processor is responsible for performing specific computing tasks. Furthermore, the present invention also provides a computer-readable storage medium for storing a computer program that, when executed by the processor, implements all the functions of the aforementioned method.

[0050] In summary, the present invention significantly improves the resource utilization and scheduling flexibility of the hemodialysis center through a multi-level resource scheduling and dynamic adjustment mechanism, meets the demand for accurate scheduling in complex scenarios, reduces the frequency of manual intervention and improves patient satisfaction.

Claims

1. A dynamic resource allocation and scheduling system for hemodialysis centers, characterized in that: include: Data acquisition module, used to obtain patient treatment needs, equipment status and medical staff information in real time; Resource forecasting unit, which generates daily resource demand profiles and priority rankings based on historical data and real-time inputs; The first scheduling module is used to perform preliminary scheduling based on patient treatment time, equipment usage sequence, and medical staff configuration through multi-dimensional weight analysis to generate an initial scheduling plan; A conflict detection module, used to verify the feasibility of the initial scheduling plan; An adjustment and optimization module is used to reallocate resources using dynamic constraints when conflicts are detected and generate an adjusted solution; The second scheduling module is used to make a refined allocation of the adjusted plan in combination with the real-time updated data to generate a final scheduling plan; The display output module is used to push the final shift schedule to a preset terminal.

2. The dynamic resource allocation and scheduling system for hemodialysis centers according to claim 1, characterized in that: The resource prediction unit generates a daily resource demand distribution diagram based on a time series analysis algorithm. The time series analysis algorithm calculates the daily resource demand distribution R(t) through the formula R(t) = α·H(t) + (1-α)·C(t), where H(t) represents the trend value of historical data, C(t) represents the correction value of real-time input, and α is the weight coefficient.

3. The dynamic resource allocation and scheduling system for hemodialysis centers according to claim 1, characterized in that: The first scheduling module uses a multi-objective optimization model to generate an initial scheduling plan. The objective function F of the multi-objective optimization model is defined as F=w1·P+w2·D+w3·S, where P represents the patient priority score, D represents the equipment allocation efficiency, S represents the rationality of medical staff configuration, and w1, w2, and w3 are the weight coefficients of each factor respectively.

4. The dynamic resource allocation and scheduling system for hemodialysis centers according to claim 1, characterized in that: The conflict detection module performs a feasibility analysis on the initial scheduling plan through a rule-based conflict identification algorithm. The conflict identification algorithm converts the resource allocation relationship into a set of constraint conditions and checks one by one whether there are any violations of the constraints.

5. The dynamic resource allocation and scheduling system for hemodialysis centers according to claim 1, characterized in that: The adjustment and optimization module uses a heuristic search algorithm to reallocate resources. The heuristic search algorithm gradually adjusts the allocation scheme of related resources starting from the conflict point until all conflicts are eliminated.

6. The dynamic resource allocation and scheduling system for hemodialysis centers according to claim 1, characterized in that: The second scheduling module uses an incremental update strategy to fine-tune the allocation of the adjusted plan, and only makes local adjustments to the affected parts to reduce computational overhead.

7. A dynamic resource allocation and scheduling method for a hemodialysis center, characterized in that: The following steps are involved: Collect patient treatment needs, equipment status, and medical staff information in real time and generate daily resource demand distribution maps and priority rankings; Generate initial scheduling plan through multi-dimensional weight analysis; Conduct conflict detection on the initial scheduling plan and adjust it to generate an optimized plan; Combined with real-time updated data, the optimization plan is refined and allocated, and the final scheduling plan is generated and pushed to the terminal for display.

8. The dynamic resource allocation and scheduling method for hemodialysis center according to claim 7, characterized in that: The step of generating the daily resource demand distribution graph adopts a time series analysis algorithm, which calculates the daily resource demand distribution R(t) through the formula R(t) = α·H(t) + (1-α)·C(t), where H(t) represents the trend value of historical data, C(t) represents the correction value of real-time input, and α is the weight coefficient.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the dynamic resource allocation and scheduling method for a hemodialysis center as described in any one of claims 7 to 8.

10. A computer-readable storage medium, characterized in that Used to store a computer program, which, when executed by a processor, implements the dynamic resource allocation and scheduling method for a hemodialysis center as described in any one of claims 7 to 8.

Images