Hospital department relocation method and device, system, and storage medium

Abstract

This invention discloses a method, apparatus, system, and storage medium for relocating hospital departments, including: step S1, data modeling and parameter initialization; step S2, constructing a multi-objective optimization model; step S3, constructing a constraint system; step S4, dynamic priority calculation and critical path identification; step S5, relocation scheduling optimization solution; and step S6, generating the optimal relocation plan. The technical solution of this invention enables systematic optimization under multi-objective constraints, simultaneously considering economic cost, continuity of medical services, and resource utilization efficiency, while meeting the requirements of medical quality and safety.

Description

Technical Field

[0001] This invention belongs to the field of medical information technology and intelligent decision-making technology, specifically relating to a method, device, system, and storage medium for relocating hospital departments. Background Technology

[0002] With the rapid advancement of medical and health infrastructure construction, the number of new hospital construction, renovation, expansion, and overall relocation projects is increasing daily. In this process, the organization of clinical department relocation has become a critical issue affecting the normal operation of hospitals and the continuity of medical services. Department relocation not only involves the dismantling and installation of large medical equipment, personnel allocation, and the reallocation of space resources, but also directly relates to core medical quality indicators such as surgical procedures, emergency care, and patient safety. Therefore, how to achieve an efficient, orderly, and safe department relocation process under limited time and resource constraints has become an important technical issue in hospital management.

[0003] In existing technologies, hospital department relocation often relies on experience-driven manual decision-making or simple rule-based methods. For example, common strategies include relocating in batches according to department size or equipment complexity, or proceeding sequentially based on construction schedule. In addition, some studies have attempted to introduce operations research methods, abstracting the relocation problem into a scheduling or resource allocation problem, such as using linear programming, heuristic algorithms, or the Critical Path Method (CPM) from project management for optimization analysis. These methods can, to some extent, reduce relocation time or control direct costs.

[0004] However, existing technologies still have significant shortcomings: (1) The optimization objective is singular and lacks a multi-objective collaborative mechanism. Most methods focus only on the shortest relocation period or the lowest cost, failing to simultaneously consider the continuity of medical services and the efficiency of resource utilization, and thus failing to meet the comprehensive optimization needs of hospitals in complex operating environments.

[0005] (2) Lack of a modeling mechanism for medical quality and safety constraints Existing models typically do not include key medical safety indicators such as "minimum surgical guarantee rate" and "continuity of emergency services" as rigid constraints, but only as soft references or ex-post evaluations, which leads to potential medical risks in the actual application of optimization results.

[0006] (3) Ignoring the complex inter-departmental dependencies and dynamic scheduling requirements Significant functional dependencies exist between various clinical departments in hospitals (e.g., surgical departments depend on anesthesiology and ICU support). Existing methods often fail to construct systematic dependency models and lack the ability to dynamically adjust for changes during relocation.

[0007] (4) Insufficient resource constraint modeling Key resource factors, including the number of relocation teams, equipment transportation capacity, and space capacity limitations, are often simplified in existing technologies, making it difficult to accurately reflect complex relocation scenarios.

[0008] (5) Insufficient versatility and scalability Existing methods are mostly designed for specific hospitals or single scenarios, lacking parameterization and generalization capabilities, and are difficult to apply to complex situations such as different scales, multiple buildings, or phased construction.

[0009] In summary, existing technologies have not yet developed a systematic optimization method that can simultaneously consider economic costs, continuity of medical services, and resource utilization efficiency under multiple objective constraints, while also meeting the requirements for medical quality and safety. Summary of the Invention

[0010] To address the problems existing in the prior art, the present invention provides a method, apparatus, system, and storage medium for relocating hospital departments.

[0011] To achieve the above objectives, the present invention provides the following solution: A method for relocating hospital departments includes: Step S1: Obtain the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph of the hospital; Step S2: Based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, departmental characteristic parameters, resource constraint parameters, and dependency graph, construct a multi-objective optimization model with relocation decision variables as the core. Step S3: Introduce allocation constraints, time constraints, resource constraints, and medical quality and safety constraints into the multi-objective optimization model; Step S4: Based on resource constraint parameters, calculate the comprehensive priority score of each department; at the same time, perform critical path analysis on the dependency graph to identify the sequence of key departments that have the greatest impact on the overall relocation cycle, and prioritize the allocation of relocation resources. Step S5: Combining the multi-objective optimization model with the priority score after introducing the constraint system, the relocation plan is solved using a mixed integer programming algorithm or a heuristic scheduling algorithm; at the same time, in the multi-stage decision-making process, the department priority and resource allocation are dynamically adjusted according to the stage execution status to achieve rolling optimization scheduling of the relocation process; Step S6: Output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan shall meet all constraints and achieve optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime interval and resource utilization plan.

[0012] As a preferred option, the department's characteristic parameters include: the department's average daily surgical volume, the department's urgency weight, the basic cost of equipment relocation, the cost of personnel allocation, the cost of loss per stage of downtime, the minimum necessary downtime stage for the department, and the maximum allowable downtime stage.

[0013] As a preferred option, resource constraint parameters include: the maximum number of relocation work groups available at each stage, the number of work groups required for department relocation, the maximum total budget, and the location capacity coefficient.

[0014] The present invention also provides a hospital department relocation device, comprising: The first processing module is used to obtain the set of clinical departments to be relocated in the hospital, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The second processing module is used to construct a multi-objective optimization model with relocation decision variables as the core, based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The third processing module is used to introduce allocation constraints, timing constraints, resource constraints, and medical quality and safety constraints into the multi-objective optimization model. The fourth processing module is used to calculate the comprehensive priority score of each department based on resource constraint parameters; at the same time, it performs critical path analysis on the dependency graph, identifies the sequence of key departments that have the greatest impact on the overall relocation cycle, and prioritizes the allocation of relocation resources. The fifth processing module is used to combine the multi-objective optimization model with priority scores after the introduction of the constraint system, and use mixed integer programming algorithm or heuristic scheduling algorithm to solve the relocation plan; at the same time, in the multi-stage decision-making process, the department priority and resource allocation are dynamically adjusted according to the stage execution status to realize the rolling optimization scheduling of the relocation process; The sixth processing module is used to output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan satisfies all constraints and achieves optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime intervals, and resource usage plan.

[0015] As a preferred option, the department's characteristic parameters include: the department's average daily surgical volume, the department's urgency weight, the basic cost of equipment relocation, the cost of personnel allocation, the cost of loss per stage of downtime, the minimum necessary downtime stage for the department, and the maximum allowable downtime stage.

[0016] As a preferred option, resource constraint parameters include: the maximum number of relocation work groups available at each stage, the number of work groups required for department relocation, the maximum total budget, and the location capacity coefficient.

[0017] The present invention also provides a hospital department relocation system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a hospital department relocation method when executed by the processor.

[0018] The present invention also provides a storage medium storing a computer program, which executes a hospital department relocation method when running.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Construct a department relocation decision-making system that integrates a multi-objective optimization model and a dynamic scheduling mechanism. Based on a comprehensive consideration of relocation costs, continuity of medical services, and resource utilization efficiency, incorporate medical quality and safety constraints as rigid conditions into the optimization process to achieve scientific decision-making and optimized scheduling of hospital department relocation.

[0020] 2. By establishing a departmental dependency model and resource constraint system, combined with a dynamic priority scheduling strategy, the timing conflicts and resource competition issues that exist in the relocation process of multiple departments and in multiple stages can be resolved. This will reduce the overall relocation cost, shorten the relocation cycle, and improve the feasibility and security of the relocation plan while ensuring the continuous operation of key departments. Attached Figure Description

[0021] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a hospital department relocation method according to an embodiment of the present invention; Figure 2 Department relocation dependency diagram. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] Example 1 like Figure 1 As shown, the present invention provides a method for relocating hospital departments, including: Step S1, Data Modeling and Parameter Initialization: Obtain the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph; Step S2: Construct a multi-objective optimization model: Based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, departmental characteristic parameters, resource constraint parameters, and dependency graph, construct a multi-objective optimization model with relocation decision variables as the core. Step S3: Construct a constraint system: Introduce a constraint system into the multi-objective optimization model; wherein, the constraint system includes: allocation constraints, time constraints, resource constraints, and medical quality and safety constraints; Step S4: Based on resource constraint parameters, calculate the comprehensive priority score of each department, and at the same time perform critical path analysis on the dependency graph to identify the key department sequence that has the greatest impact on the overall relocation cycle, and prioritize the allocation of relocation resources. Step S5: Relocation Scheduling Optimization Solution: Combining the multi-objective optimization model with the introduced constraint system and priority scores, a mixed integer programming algorithm or a heuristic scheduling algorithm is used to solve the relocation scheme; at the same time, in the multi-stage decision-making process, the departmental priorities and resource allocation are dynamically adjusted according to the stage execution status to achieve rolling optimization scheduling of the relocation process; Step S6: Generate the optimal relocation plan: Output the relocation arrangement plan for each department at each time stage. At the same time, the relocation arrangement plan satisfies all constraints and achieves the optimal or near-optimal in a multi-objective sense. The relocation arrangement plan includes: target location allocation, downtime interval and resource usage plan.

[0026] In one embodiment of the present invention, in step S1, let the hospital have n clinical departments, and let the set be... The newly built surgical building provides Let there be target locations, and denote the set. The relocation plan is divided into T time phases (e.g., weekly), denoted as... .

[0027] Core decision variables ,in, Indicates department In the Phases are assigned to positions . Indicates department In the The project is currently in a state of shutdown. ). Indicates department In the The percentage of operational capacity retained during a given phase.

[0028] Furthermore, the department's characteristic parameters include: average daily surgical volume, departmental urgency weight, basic equipment relocation cost, personnel allocation cost, cost of loss per stage of downtime, minimum necessary downtime stage, and maximum allowable downtime stage, as shown in Table 1. Table 1 Furthermore, the resource constraint parameters include: the maximum number of relocation work groups available in each phase, the number of work groups required for departmental relocation, the total budget limit, and the location capacity coefficient; as shown in Table 2. Table 2 Furthermore, the dependency graph is used to describe the pre- and post-order constraints between different departments; specifically, the department dependency graph is defined. Among them, there are edges Indicates department Relocation must be After completion (preceding constraints), assign weights. This indicates the number of buffer stages required.

[0029] As one embodiment of the present invention, in step S2, the multi-objective optimization model includes at least the following optimization objectives: (1) Minimize the total cost of department relocation; (2) Minimize the losses caused by the interruption of medical services during the relocation process; (3) Minimize the overall relocation cycle; The sub-objectives are weighted and combined to form a unified optimization objective function.

[0030] Furthermore, the multi-objective optimization model employs a weighted multi-objective optimization strategy, linearly combining the three sub-objectives: in, .

[0031] Objective F1: Minimize total economic cost in, For the department Relocation Location Location adaptation costs (renovation costs, corridor distance).

[0032] Objective F2: Minimize the impact of surgery (downtime weighted) in, Losses incurred during the complete shutdown of operations; This refers to the degradation losses during partial operation. This is the penalty coefficient for downgrading.

[0033] Objective F3: Minimize the total relocation period Equivalent linearization form (introducing auxiliary variables) ): in, Indicates department In the A binary indicator variable indicating that the relocation is completed in stages (with no further work stoppages).

[0034] As one embodiment of the present invention, the constraint system in step S3 is as follows: Constraint set A: Assignment constraints A1: Each department must be assigned one and only one position. A2: Each location can accommodate a maximum of one department at the same stage (spatial exclusivity): The capacity of location A3 is matched with the size of the department: in, For the department Space requirement coefficient.

[0035] Constraint set B: Timing constraints B1 Precedence Dependency Constraints (Based on Dependency Graph) ): That is: if the department In the If work is suspended in stages, then the preceding departments... The relocation must have been completed at least Each stage.

[0036] B2 Work stoppage continuity constraint (relocation cannot be interrupted): Constraint set C: Resource constraints C1 Maximum number of working groups per phase of relocation: C2 Total Budget Constraint: C3 Stoppage Phase Constraint (Two-sided): Constraint set D: Medical quality and safety constraints D1 Minimum Surgical Guarantee Rate Constraint for Key Departments: in, (Adjustable parameters).

[0037] D2 Restrictions on simultaneous shutdowns of similar departments (to prevent simultaneous shutdowns of departmental groups): in, This is classified as a category g department group (such as the surgical group). This represents the maximum allowed concurrent shutdown ratio for this group.

[0038] D3 Emergency Access Access Constraints (Physical Layout): The emergency department must occupy a location with direct access to the emergency room at any stage. .

[0039] In summary, the multi-objective optimization model after introducing the constraint system is as follows: As one embodiment of the present invention, in step S4, as follows: Figure 2 As shown, the department dependency graph involves five core department nodes: Emergency Department (A), Anesthesia (B), ICU (C), Operating Room (D), and Rehabilitation (E). The dependency transmission relationships between these nodes are as follows: Emergency Department (A) acts as the starting node, transmitting dependencies to both Anesthesia (B) and ICU (C); both Anesthesia (B) and ICU (C) use Operating Room (D) as their downstream node, jointly constraining Operating Room (D); after the relocation of Operating Room (D) is completed, it further drives the relocation of Rehabilitation (E). Critical path analysis identified the critical department sequence with the greatest impact on the overall relocation cycle as Emergency Department (A) → Anesthesia (B) → Operating Room (D) → Rehabilitation (E). Delays in the relocation of any node along this path will directly extend the overall relocation cycle. Therefore, the system will prioritize the allocation of relocation resources such as manpower, equipment, and time windows to departments along the critical path to ensure the timely completion of the overall relocation plan.

[0040] Furthermore, in step S4, for each department Define the overall priority score: Core rules: The higher the number, the higher the relocation priority (prioritized to quickly relieve its obstruction to subsequent departments).

[0041] Critical path identification is as follows: The weighted length of each path in the dependency graph G is defined as: in, This represents the number of buffer stages required for department i to relocate before i' is completed (preceding constraint).

[0042] Using the longest path algorithm of DAG ( Identify the critical path Departments on the critical path will be given priority in receiving relocation window allocations.

[0043] Perform topological sorting on the dependency graph G and initialize the distance array. The remaining nodes are initialized to -∞; each node is traversed in topological order. The relaxation process is performed as follows: After the traversal is complete, the node with the largest value in the dist array is the endpoint of the critical path. The complete critical path (CP) can be reconstructed by backtracking.

[0044] As one embodiment of the present invention, in step S5, a mixed integer programming algorithm or a heuristic scheduling algorithm is used to solve the relocation scheme by combining the multi-objective optimization model after introducing the constraint system and the priority score; simultaneously, in the multi-stage decision-making process, the departmental priorities and resource allocation are dynamically adjusted according to the stage execution status to achieve rolling optimization scheduling of the relocation process; specifically including Step S51: Initial resource pre-allocation based on the critical path: Extract the "critical department sequence with the greatest impact on the overall relocation cycle" identified in step S4 and use it as a mandatory priority allocation target. Under the resource constraints of meeting the upper limit of the number of available relocation work groups and the upper limit of the total budget for each stage, prioritize the allocation of target locations, relocation time stage k, and required relocation work groups to the nodes (departments) in this critical department sequence. For the remaining departments to be relocated on non-critical paths, strictly follow the comprehensive priority score calculated in step S4. The remaining relocation resources are pre-allocated in descending order using a greedy strategy to generate an initial allocation scheme. Step S52: Calculate and solve the multi-objective optimization model: The generated initial allocation scheme is used as the initial feasible solution or heuristic search starting point of the solution algorithm and input into the multi-objective optimization model with a system of constraints.

[0045] If a mixed-integer programming algorithm (such as branch and bound) is used, then the goal is to minimize the unified objective function. Guided by the constraints, precise iterative calculations are performed within the rigid boundaries of constraint sets A, B, C, and D.

[0046] If a heuristic scheduling algorithm is used, new solutions are generated through crossover, mutation and other operations. Solutions that violate the constraint set (especially medical quality and safety constraints D1 and D2) are eliminated by imposing a very large penalty function. The optimal solution with the highest fitness of objective function F is calculated and retained. Step S53, Multi-stage rolling optimization and dynamic adjustment: During the multi-phase relocation process, after the current phase k ends, the system acquires actual execution data (including actual resource consumption, departmental downtime and resumption status). Based on the actual status, the available budget balance, remaining workgroup capacity, and completion status of prior constraints in the dependency graph G are updated in the model. Subsequently, based on the updated data, the comprehensive priority score of the departments not yet relocated is recalculated. The system dynamically corrects the sequence of key departments that have the greatest impact on the overall relocation cycle in the unexecuted phase, and cyclically executes sub-steps S51 to S52. By continuously compressing the time window until all departments have completed the relocation, the system achieves rolling optimization scheduling of the relocation plan.

[0047] Step S6: Output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan shall meet all constraints and achieve optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime interval and resource utilization plan.

[0048] Step S61, Target position allocation calculation: Traverse the optimal decision variable matrix for any department to be relocated. The system generates a precise "department-location" spatial mapping relationship and writes this status into the spatial allocation details table of the plan. Step S62: Generation of downtime intervals: Traverse the optimal state variable matrix for any department to be relocated. Calculated in chronological order The absolute downtime; at the same time, combined with the corresponding auxiliary variables. Extract and mark the downgraded operation transition period during the shutdown and before and after the relocation, and clarify the proportion of operation capacity to be retained at each time point; Step S63, Resource Usage Plan Calculation: Aggregate the relocation status of each department based on the stage index k, and calculate the dynamic resource scheduling details for each time stage. For any stage k, calculate the total number of relocation work groups actually required for that stage, and generate a personnel scheduling plan; simultaneously, substitute the departmental equipment relocation costs. and Calculate the expected actual capital consumption for this stage and generate a budget expenditure plan flow that runs through period T; Finally, the target location allocation, downtime intervals, and resource usage plans obtained through matrix decoding are summarized to form an intuitive and executable relocation schedule (such as a Gantt chart). The final evaluation value of the multi-objective function F is calculated and output, confirming that the output scheme achieves multi-objective collaborative optimization under the premise of satisfying all rigid constraint sets (A, B, C, D).

[0049] This invention, by constructing a multi-objective optimization model and introducing rigid constraints on medical quality and safety as well as a dynamic scheduling mechanism, has the following characteristics in the process of relocating clinical departments in hospitals: (1) Significantly reduce the overall cost of relocation This invention effectively reduces the costs of repeated equipment handling, personnel allocation conflicts, and space adaptation modifications by uniformly optimizing relocation costs, resource allocation, and route planning. Simulation results show that in a typical tertiary hospital relocation scenario, the total relocation cost can be reduced by approximately 15% to 30% compared to traditional experience-based ranking methods.

[0050] (2) Effectively reduce the impact of medical service interruptions By incorporating surgical volume-weighted losses into the optimization objective and introducing downtime constraints and dynamic scheduling mechanisms, this invention can rationally arrange the relocation sequence of departments, reducing the impact of downtime and decreased service capacity. Experimental results show that cumulative downtime can be reduced by approximately 20% to 40%, and the risk of service interruption in key surgical departments is significantly reduced.

[0051] (3) Ensure the quality and safe operation of medical care This invention is the first to incorporate medical safety indicators such as "minimum surgical guarantee rate" and "proportion of concurrent shutdowns in similar departments" as rigid constraints into the optimization model. This ensures that critical departments (such as emergency, intensive care, and cardiac surgery) maintain operational capacity at or above a set threshold during relocation. In practical applications or simulations, the shutdown rate of critical departments can be stably controlled at ≤5%, effectively preventing medical risk events.

[0052] (4) Improve resource utilization efficiency and scheduling rationality By performing refined modeling and constraint control of resources such as relocation working groups, space capacity, and budget, this invention can achieve dynamic optimization of resource allocation during multi-stage relocation processes, avoiding resource idleness or conflicts. Compared with existing methods, resource utilization can be improved by approximately 10% to 25%.

[0053] (5) Shorten the overall relocation cycle This invention combines critical path identification with a dynamic priority scheduling strategy, prioritizing departments that have a greater impact on the overall progress and effectively shortening the relocation cycle. Experimental results show that in complex multi-department relocation scenarios, the total relocation cycle can be shortened by approximately 10% to 20%.

[0054] (6) Enhancing the generality and scalability of the method This invention, through parametric modeling and modular design, is applicable to various complex scenarios such as hospitals of different sizes, multi-building relocation, and phased construction, and has good promotion and application value.

[0055] Example 2 The present invention also provides a hospital department relocation device, comprising: The first processing module is used to obtain the set of clinical departments to be relocated in the hospital, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The second processing module is used to construct a multi-objective optimization model with relocation decision variables as the core, based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The third processing module is used to introduce allocation constraints, timing constraints, resource constraints, and medical quality and safety constraints into the multi-objective optimization model. The fourth processing module is used to calculate the comprehensive priority score of each department based on resource constraint parameters; at the same time, it performs critical path analysis on the dependency graph, identifies the sequence of key departments that have the greatest impact on the overall relocation cycle, and prioritizes the allocation of relocation resources. The fifth processing module is used to combine the multi-objective optimization model with priority scores after the introduction of the constraint system, and use mixed integer programming algorithm or heuristic scheduling algorithm to solve the relocation plan; at the same time, in the multi-stage decision-making process, the department priority and resource allocation are dynamically adjusted according to the stage execution status to realize the rolling optimization scheduling of the relocation process; The sixth processing module is used to output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan satisfies all constraints and achieves optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime intervals, and resource usage plan.

[0056] As one embodiment of the present invention, the department characteristic parameters include: the average daily number of surgeries in the department, the department's urgency weight, the basic cost of equipment relocation, the cost of personnel allocation, the cost of loss per stage of downtime, the minimum necessary number of downtime stages in the department, and the maximum allowable number of downtime stages.

[0057] As one embodiment of the present invention, the resource constraint parameters include: the upper limit of the number of relocation work groups available in each stage, the number of work groups required for department relocation, the upper limit of the total budget, and the capacity coefficient of the location.

[0058] Example 3 The present invention also provides a hospital department relocation system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a hospital department relocation method when executed by the processor.

[0059] Example 4 The present invention also provides a storage medium storing a computer program, which executes a hospital department relocation method when running.

[0060] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method of relocating a hospital department, characterized by, include: Step S1: Obtain the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph of the hospital; Step S2: Based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, departmental characteristic parameters, resource constraint parameters, and dependency graph, construct a multi-objective optimization model with relocation decision variables as the core. Step S3: Introduce allocation constraints, time constraints, resource constraints, and medical quality and safety constraints into the multi-objective optimization model; Step S4: Based on resource constraint parameters, calculate the comprehensive priority score of each department; at the same time, perform critical path analysis on the dependency graph to identify the sequence of key departments that have the greatest impact on the overall relocation cycle, and prioritize the allocation of relocation resources. Step S5: Combining the multi-objective optimization model with the priority score after introducing the constraint system, the relocation scheme is solved using a mixed integer programming algorithm or a heuristic scheduling algorithm; Meanwhile, during the multi-stage decision-making process, the departmental priorities and resource allocation are dynamically adjusted based on the stage implementation, so as to achieve rolling optimization scheduling of the relocation process; Step S6: Output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan shall meet all constraints and achieve optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime interval and resource utilization plan.

2. The hospital department relocation method of claim 1, wherein, Departmental characteristic parameters include: average daily surgical volume, departmental urgency weight, basic cost of equipment relocation, personnel allocation cost, cost of loss per stage of downtime, minimum necessary downtime stage, and maximum allowable downtime stage.

3. The hospital department relocation method of claim 2, wherein, Resource constraints include: the maximum number of relocation work groups available in each phase, the number of work groups required for department relocation, the total budget limit, and the location capacity coefficient.

4. A hospital department relocation apparatus, characterized by, include: The first processing module is used to obtain the set of clinical departments to be relocated in the hospital, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The second processing module is used to construct a multi-objective optimization model with relocation decision variables as the core, based on the set of clinical departments to be relocated, the set of target locations, the set of relocation time stages, department characteristic parameters, resource constraint parameters, and dependency graph. The third processing module is used to introduce allocation constraints, timing constraints, resource constraints, and medical quality and safety constraints into the multi-objective optimization model. The fourth processing module is used to calculate the comprehensive priority score of each department based on resource constraint parameters; at the same time, it performs critical path analysis on the dependency graph, identifies the sequence of key departments that have the greatest impact on the overall relocation cycle, and prioritizes the allocation of relocation resources. The fifth processing module is used to combine the multi-objective optimization model with priority scores after the introduction of the constraint system, and use mixed integer programming algorithm or heuristic scheduling algorithm to solve the relocation plan; at the same time, in the multi-stage decision-making process, the department priority and resource allocation are dynamically adjusted according to the stage execution status to realize the rolling optimization scheduling of the relocation process; The sixth processing module is used to output the relocation arrangement plan for each department at each time stage. The relocation arrangement plan satisfies all constraints and achieves optimal or near-optimal results under multiple objectives. The relocation arrangement plan includes: target location allocation, downtime intervals, and resource usage plan.

5. The hospital department relocation apparatus of claim 4, wherein, Departmental characteristic parameters include: average daily surgical volume, departmental urgency weight, basic cost of equipment relocation, personnel allocation cost, cost of loss per stage of downtime, minimum necessary downtime stage, and maximum allowable downtime stage.

6. The hospital department relocation apparatus of claim 5, wherein, Resource constraints include: the maximum number of relocation work groups available in each phase, the number of work groups required for department relocation, the total budget limit, and the location capacity coefficient.

7. A hospital department relocation system, characterized by, include: A memory and a processor, wherein the memory stores a computer program executed by the processor, the computer program performing the hospital department relocation method as described in any one of claims 1-3 when executed by the processor.

8. A storage medium, characterized by The storage medium stores a computer program that, when executed, performs the hospital department relocation method as described in any one of claims 1-3.

Images