Hospital human resource dynamic optimization configuration method and system for multi-zone cooperation

Abstract

The invention discloses a hospital human resource dynamic optimization configuration method and system for multi-zone cooperation, and relates to the technical field of hospital human resource allocation, and the method comprises the steps: integrating multi-zone hospital human resource basic data, post demand information and cross-zone constraint conditions through multi-dimensional collection, and carrying out the cross-zone medical care capability matching and adaptive screening, a supply and demand gap and redundant data are generated by applying human supply and demand prediction coupling analysis, then a deployment priority is determined through medical care human supply and demand collaborative analysis, multiple sets of cross-regional deployment schemes are formulated by relying on an intelligent assessment deployment platform, and an optimal scheme is determined and executed after comprehensive verification. Wherein the links of supply and demand prediction, collaborative analysis and scheme generation all comprise a plurality of steps, orderly connection of data processing, analysis operation and deployment execution is realized, the limitation of local configuration of a single hospital is broken, the cross-regional human adaptation accuracy and dynamic response capability are improved, multi-regional medical resources are effectively planned as a whole, and the medical resources are saved. And the cross-regional cooperation efficiency and the human resource utilization efficiency are enhanced.

Description

Technical Field

[0001] This invention relates to the field of hospital human resource allocation technology, and in particular to a method and system for dynamic optimization of hospital human resource allocation for multi-regional collaboration. Background Technology

[0002] Given the uneven distribution of medical resources across regions and the continuously growing demand for cross-regional medical services, hospitals in multiple regions face a prominent problem of mismatch between human resource allocation and actual medical workload. Significant differences exist in the departmental setup, professional qualifications of medical staff, and fluctuating workload characteristics of hospitals in different regions. Furthermore, factors such as changes in population health needs and public health emergencies further exacerbate the dynamic imbalance between human resource supply and demand. Traditional human resource allocation models rely on adjustments within a single hospital, lacking a holistic consideration of resources across multiple regions. This makes it difficult to achieve precise matching of cross-regional medical capabilities with job requirements, and it also fails to respond promptly to real-time changes in manpower shortages and redundancies in various hospitals. Consequently, medical service efficiency is limited, and the effectiveness of cross-regional medical collaboration cannot be fully realized. Therefore, there is an urgent need to construct a human resource optimization allocation system that takes into account multi-regional collaboration, dynamic adaptation, and intelligent allocation.

[0003] Existing technologies have two major shortcomings in hospital human resource allocation: First, they lack a cross-regional system collaboration mechanism, only making local adjustments to the supply and demand of human resources within a single hospital. They have not established a comprehensive matching system for the medical and nursing capabilities and job requirements of multiple regions, and cannot integrate human resource data from hospitals in different regions for global analysis. This results in insufficient adaptability of cross-regional allocation and makes it difficult to meet the actual needs of multi-regional collaborative diagnosis and treatment. Second, their dynamic optimization capabilities are weak. They have not formed a dynamic adjustment mechanism that runs through the entire process of data collection, supply and demand forecasting, collaborative analysis, efficiency evaluation, and plan implementation. Their response to changes in human resource supply and demand is lagging, and they have not built a scientific quantitative analysis model and intelligent allocation platform. They cannot achieve real-time optimization and closed-loop adjustment of human resource allocation plans, and it is difficult to adapt to the dynamic changes in medical service scenarios. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides a method and system for dynamic optimization of hospital human resources allocation for multi-regional collaboration.

[0005] The technical solution adopted in this invention is a method for dynamic optimization and allocation of hospital human resources for multi-regional collaboration, comprising the following steps: S1, collecting basic human resource data, professional qualification information of medical staff, medical service volume data of each department, and cross-regional allocation constraints from hospitals in multiple regions to construct a multi-dimensional human resource information dataset; S2, based on the dataset, using a cross-regional medical and nursing capability matching optimization model to perform preliminary matching and screening of medical staff's professional skills, work experience, and the job requirements of each hospital; S3, using a hospital human resource supply and demand prediction coupling model, combined with historical service volume fluctuation characteristics and regional population health demand change trends, generating human resource supply and demand gaps and redundancy data for each hospital in the future preset time period; S4, using a medical and nursing human resource supply and demand collaborative analysis algorithm to perform multi-dimensional correlation analysis on the human resource supply and demand data of hospitals in multiple regions and the cross-regional matching results, and outputting a human resource allocation priority ranking; S5, using a hospital human resource efficiency intelligent evaluation and allocation platform to integrate the analysis results and formulate multiple cross-regional human resource allocation schemes; S6, based on the hospital human resource dynamic optimization and allocation parameter system, performing multi-indicator comprehensive verification of the allocation schemes, determining the optimal cross-regional human resource dynamic allocation scheme, and executing it.

[0006] Furthermore, the expression for the cross-regional medical care capacity matching optimization model is: ,in, Let be the matching score between the i-th medical staff member and the j-th hospital. To assign weighting coefficients to skills, To score the comprehensive professional competence of medical staff member i, Let be the complexity coefficient of the job requirements for hospital j. The business fit factor between medical staff i and hospital j. The geographical distance influence coefficient. The spatial distance between the area where medical staff i is located and hospital j is quantified. The time cost weighting coefficient, Quantify the time required for medical staff i to travel across regions to hospital j. Adjustment coefficient for qualification matching For medical staff member i, the k-th professional qualification qualification standard value is... Let be the qualification requirement value for the k-th position in hospital j, and n be the total number of qualification assessment indicators.

[0007] Furthermore, the expression for the hospital human resource supply and demand forecasting coupling model is as follows: in, The predicted human resource demand of Institute J in time period t. Weights are coupled to historical data. For the hospital jth The actual manpower demand for a given period of time. Here, T is the time decay coefficient, and T is the total number of prediction periods. This represents the regional characteristic influence coefficient. Quantify the service coverage area of ​​hospital j. This refers to the number of beds in the S-class department of the hospital. Let S be the bed turnover rate of the s-th category department of hospital j, where S is the total number of department categories. Assign gradient coefficients to resources. Let be the second-order gradient value of the human resource distribution of hospital j.

[0008] Furthermore, the expression for the medical staff supply and demand collaborative analysis algorithm is as follows: ,in, Let p be the human resource supply and demand coordination coefficient between hospital p and hospital q. As a weighting factor for supply and demand gap coordination, Let p be the predicted demand value for hospital in time period t. For the hospital's manpower supply during time period t, For the variance of hospital staffing demand, For the variance of hospital's human resource demand, Let p be the correlation coefficient between the demand and q of the hospital. To match collaborative weights, Match the total degree value for the medical staff of hospital p and q. The feasibility coefficient for cross-regional allocation, To adjust the process complexity coefficient, This represents the impact coefficient of policy constraints.

[0009] Furthermore, the efficiency evaluation model expression of the hospital human resource efficiency intelligent evaluation and allocation platform is as follows: ,in, This represents the human resource efficiency evaluation value for position j in hospital category k. As a core weight for efficiency, Let k be the average workload completed by medical staff in position k. The professional skills qualification rate of medical staff in position k This is the workload impact factor. This is a quantified value for the average working hours of job position k. The coefficient representing the impact of collaboration efficiency. Rate the cooperation and coordination of medical staff in position k. For resource adaptation correction coefficients, For the m-th resource allocation quantity of hospital j, Let M be the demand for resource m for job k, and M be the total number of resource types.

[0010] Furthermore, the objective function expression for the dynamic optimization allocation of hospital human resources is: ,in, To dynamically optimize the target value, To adjust the cost weighting coefficients, 1 represents the total number of medical staff, and J represents the total number of hospitals. Let be the matching score between medical staff member i and hospital j. To quantify the distance for cross-regional allocation, For supply and demand balance weighting coefficients, Let j be the hospital's demand forecast for time period t. For the hospital's manpower supply in time period t, For collaborative efficiency weighting coefficients, The total number of hospitals participating in the collaboration, Let be the synergy coefficient between hospital p and q.

[0011] Further, S3 includes the following sub-steps: S31, extracting historical medical service volume data, seasonal fluctuation data, and public health emergency impact data of hospitals in multiple districts over the past three years, classifying and organizing them according to department category and job level, and constructing a time-series supply and demand data sequence; S32, inputting the classified time-series data into the hospital human resource supply and demand forecasting coupling model, setting the time window length and forecast step size, and generating the predicted human resource demand values ​​for each department of each hospital for the next 7 days, 30 days, and 90 days through iterative calculation of the model's internal parameters; S33, combining the current on-duty data, leave data, and training data of human resources in each hospital, calculating the human resource supply for each period, and determining the human resource gap or redundancy quantitative data for each position in each hospital through supply and demand difference calculation.

[0012] Further, S4 includes the following sub-steps: S41, collecting the cross-regional medical and nursing capacity matching results output by S2, the supply and demand forecast data generated by S3, as well as the parameters of the multi-regional medical resource sharing agreement, cross-regional transportation network data, and policy constraint data, to establish a collaborative analysis dataset; S42, calling the medical and nursing manpower supply and demand collaborative analysis algorithm to perform multi-dimensional matrix operations on the matching degree value, supply and demand gap value, and cross-regional allocation constraint parameters in the dataset to construct a manpower collaboration correlation network between hospitals; S43, based on the correlation network analysis results, sorting them from high to low according to the collaboration coefficient, outputting a priority list of manpower allocation between hospitals in multiple regions, and clarifying the priority level and correlation parameters of each allocation direction.

[0013] Further, S5 includes the following steps: S51, the hospital human resource efficiency intelligent assessment and allocation platform receives the allocation priority list from S4, integrates basic human resource information, job demand information, and cross-regional allocation constraints of hospitals in multiple regions, and establishes an allocation plan generation database; S52, the platform matches candidate medical staff for each hospital with a manpower shortage according to priority order and in combination with the adaptation results of the cross-regional medical and nursing capacity matching optimization model, forming a preliminary allocation combination; S53, based on the dynamic optimization configuration parameters of hospital human resources, the platform performs efficiency simulation calculations on the preliminary allocation combination, and evaluates the changes in human resource efficiency of each hospital and the cross-regional collaborative effect after allocation; S54, based on the simulation evaluation results, the number of medical staff allocated, the allocation time, and the allocation route are adjusted to generate 3-5 sets of differentiated cross-regional human resource allocation plans.

[0014] A dynamic optimization and allocation system for hospital human resources in a multi-regional collaborative manner is proposed. This system applies a method for dynamic optimization and allocation of hospital human resources in a multi-regional collaborative manner, including: a multi-dimensional data collection and integration unit for human resources in multiple regions, which connects to the information systems of hospitals in multiple regions through a distributed data collection interface to collect and integrate basic human resources data, job demand data, and cross-regional constraint data; the integrated data is then transmitted to a cross-regional intelligent matching and analysis unit for medical and nursing capabilities; the cross-regional intelligent matching and analysis unit for medical and nursing capabilities calls a cross-regional medical and nursing capabilities matching and optimization model to perform adaptation analysis on the received data, and outputs the matching results to a hospital human resources supply and demand time series prediction and coupling calculation unit; the hospital human resources supply and demand time series prediction and coupling calculation unit, through hospital human resources... The supply and demand forecasting coupling model generates supply and demand forecast data, which is then transmitted to the multi-dimensional collaborative analysis unit for medical and nursing staff supply and demand. This unit uses a collaborative analysis algorithm to perform correlation analysis and outputs allocation priority data to the hospital's intelligent assessment and allocation scheme generation unit. Based on the hospital's intelligent assessment and allocation platform, this unit integrates data to generate the optimal allocation scheme, which is then sent to the dynamic optimization configuration execution and feedback adjustment unit. The dynamic optimization configuration execution and feedback adjustment unit executes the allocation scheme and collects post-allocation staff efficiency data in real time, feeding it back to the multi-dimensional data collection and integration unit for human resources in multiple regions, forming a dynamic optimization closed loop.

[0015] Beneficial Effects: This invention proposes a method and system for dynamic optimization of hospital human resources allocation for multi-regional collaboration. Through multi-dimensional data collection and integration, and the construction of a cross-regional medical and nursing capability matching system, it breaks through the limitations of local allocation in a single hospital. It integrates human resource data from hospitals in multiple regions for global analysis, establishing a precise matching mechanism between cross-regional medical and nursing capabilities and job requirements. This effectively overcomes the shortcomings of existing technologies, such as lack of cross-regional system collaboration and insufficient allocation adaptability, achieving coordinated utilization and allocation of resources across multiple regions. Simultaneously, relying on the coupling analysis of human resource supply and demand forecasts, collaborative algorithm calculations, and an intelligent evaluation and allocation platform, it forms a dynamic adjustment mechanism covering the entire process from data collection, supply and demand forecasting, collaborative analysis to plan generation and execution feedback. This improves the timeliness of response to changes in human resource supply and demand. Through scientific quantitative models and intelligent platforms, it achieves real-time optimization and closed-loop adjustment of allocation plans, solving the problems of weak dynamic optimization capabilities and delayed response in existing technologies. This significantly improves the adaptability of human resource allocation to the volume of medical services in hospitals across multiple regions, strengthens the efficiency of cross-regional medical collaboration, and promotes the simultaneous improvement of human resource utilization efficiency and medical service quality. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the overall process of the method of the present invention. Figure 2 This is a flowchart of method step S3 of the present invention; Figure 3 This is a flowchart of method step S4 of the present invention; Figure 4 This is a flowchart of step S5 of the method of the present invention; Figure 5 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1As shown, the method for dynamic optimization and allocation of hospital human resources for multi-regional collaboration includes the following steps: S1, collecting basic human resource data, professional qualification information of medical staff, medical service volume data of each department, and cross-regional allocation constraints from hospitals in multiple regions to construct a multi-dimensional human resource information dataset; S2, based on the dataset, using a cross-regional medical and nursing capability matching optimization model to perform preliminary matching and screening of medical staff's professional skills, work experience, and the job requirements of each hospital; S3, using a hospital human resource supply and demand forecasting coupling model, combined with historical service volume fluctuation characteristics and regional population health demand change trends, generating human resource supply and demand gaps and redundancy data for each hospital in the future preset time period; S4, using a medical and nursing human resource supply and demand collaborative analysis algorithm to perform multi-dimensional correlation analysis on the human resource supply and demand data of hospitals in multiple regions and the cross-regional matching results, and outputting a human resource allocation priority ranking; S5, using a hospital human resource efficiency intelligent evaluation and allocation platform to integrate the analysis results and formulate multiple cross-regional human resource allocation schemes; S6, based on the hospital human resource dynamic optimization and allocation parameter system, performing multi-indicator comprehensive verification of the allocation schemes, determining the optimal cross-regional human resource dynamic allocation scheme, and executing it.

[0019] Step S1 involves the following steps: Connecting to the human resource management systems, electronic medical record systems, departmental operation management systems, and regional medical collaboration platforms of hospitals across multiple districts via a distributed data acquisition interface to collect multi-dimensional data. This includes basic human resource data such as the total number of on-duty medical and nursing staff in each hospital, age structure, years of service, professional title level, and educational level, categorized by 12 core departments including internal medicine, surgery, obstetrics and gynecology, and pediatrics. For each department, at least 12 months of personnel change data must be collected. Professional qualification information for medical and nursing staff includes the scope of their medical practitioner's license registration, specialty training and certification direction, skills assessment scores (recorded on a percentage basis), and the number of academic achievements. Data on the volume of medical services in each department includes outpatient visits, inpatient admissions, number of surgeries, and number of emergency treatments, categorized by day and week. The data collected includes nearly 36 months of data in monthly time dimension; the constraints for cross-regional transfer include the upper limit of commuting time (set to 120 minutes), the limit of continuous working hours for medical staff (no more than 10 hours per day), the cross-regional transfer cycle (1-30 days per transfer), and the upper limit of the number of cross-regional medical staff that the hospital can receive (no more than 30% of the on-duty staff of the corresponding department in the hospital). After all the collected data is deduplicated and format standardized, a structured dataset with 20 data dimensions is constructed, with each record corresponding to a single medical staff member or department. The dataset is updated every 24 hours.

[0020] Step S2 is implemented as follows: Based on the multi-dimensional human resources information dataset constructed in Step S1, a cross-regional medical and nursing competency matching optimization model is launched for adaptation and screening. The model first extracts core indicators of medical and nursing personnel's professional skills, including the matching degree of specialty qualifications (quantified in the range of 0-1), the number of years of work experience in the corresponding department (cumulative in years), the number of difficult cases handled, and the skill operation proficiency score. At the same time, it extracts core indicators of hospital job requirements, including the proportion of departmental workload gap, job professional direction requirements, professional title level requirements, and years of work experience requirements. Through multi-indicator weighted calculation, two-way adaptation is achieved. During the matching process, an initial screening is conducted based on professional specialization to ensure that the scope of practice of medical staff matches the job requirements. A second screening is then conducted based on years of work experience and job requirements (e.g., a minimum of 5 years of work experience is required for surgical positions in tertiary hospitals). Finally, a precise match is made based on skill scores and job complexity requirements (skill scores of 80 or higher correspond to high-complexity positions). The screening process sets three levels of matching thresholds: Level 1 corresponds to basic matching (meeting the 3 core indicators), Level 2 corresponds to moderate matching (meeting the 5 core indicators), and Level 3 corresponds to high matching (meeting all 7 indicators). The final output is a list of medical staff and hospital positions corresponding to different matching levels. The number of matching candidates for each department in each hospital is no less than 1.5 times the number of job vacancies.

[0021] Step S3 is implemented as follows: The hospital's human resource supply and demand forecasting coupling model is invoked, and the time-series data of the outpatient and inpatient volume of each department collected in Step S1 for the past 36 months is input, combined with regional population health demand trend data (including statistical data from the past 5 years on the number of permanent residents, the proportion of the elderly, the prevalence of chronic diseases, and the birth rate of infants). The model first performs trend decomposition on the historical volume data, identifying seasonal fluctuations (such as the high incidence of respiratory diseases in winter and the high incidence of intestinal diseases in summer), holiday effects (volume fluctuations before and after long holidays such as Spring Festival and National Day), and the impact of sudden factors (such as a surge in emergency room visits due to public health events). The time window length is set to 6 months, and the forecast step length is divided into three cycles: 7 days, 30 days, and 90 days. The model generates the manpower demand for each department in each hospital for the next three forecast periods. Simultaneously, it combines the current on-duty human resources data collected in step S1, approved leave data (categorized by sick leave, personal leave, and annual leave, totaling leave duration for the next forecast period), and training plan data (number of trainees and training duration for the next forecast period) to calculate the manpower supply for each period. By calculating the difference between demand and supply, the model determines the manpower shortage or redundancy for each department in each hospital during different forecast periods. The model outputs a supply-demand balance analysis report categorized by department and sorted by forecast period, including detailed information such as the professional direction, professional title, and demand period for shortage / redundancy personnel.

[0022] Step S4 is implemented as follows: The algorithm for collaborative analysis of medical and nursing staff supply and demand is activated, integrating the cross-regional medical and nursing capacity matching results from Step S2 (lists of different adaptation levels), and the supply and demand gap and redundancy data from Step S3 (supply and demand balance reports for each period). Simultaneously, parameters from the multi-regional medical resource sharing agreement (list of cross-regional collaborative hospitals, allocation of resource allocation responsibilities, and cost settlement standards), cross-regional transportation network data (commuting routes between hospitals, average travel time, and available transportation options), and policy constraints (regional medical resource allocation planning and regulations for cross-regional practice management of medical personnel) are input. The algorithm first constructs a multi-dimensional correlation analysis matrix, with rows representing hospitals and medical personnel with redundant staff, columns representing hospitals and positions with staff shortages, and matrix elements representing collaborative adaptation coefficients. By analyzing the fit between medical staff suitability levels and job vacancy requirements through matrix operations, the degree to which cross-regional allocation constraints are met, and the historical records of inter-hospital collaboration, an evaluation index system for allocation priority is determined. This system includes the weight of suitability coefficient (40%), allocation feasibility (30%), and collaboration effectiveness (30%). Priority scores are calculated for each potential allocation combination according to the index system. The scores are then sorted from highest to lowest to generate a priority list for cross-regional human resource allocation. The list includes allocation direction (redundant hospitals → hospitals with vacancies), medical staff information, job requirement information, allocation cycle suggestions, and priority scores. Each vacancy position corresponds to at least three candidate allocation schemes.

[0023] Step S5 is implemented as follows: The hospital's intelligent human resource efficiency assessment and allocation platform is activated. This platform includes a data integration module, a plan generation module, an efficiency assessment module, and a plan adjustment module. First, the data integration module receives the allocation priority list output from step S4, and simultaneously calls the basic dataset from step S1, the matching results from step S2, and the supply and demand forecast data from step S3 to establish an allocation plan generation database. The platform extracts candidate allocation combinations according to priority, and combines the highly adaptive results of the cross-regional medical and nursing capacity matching optimization model to match 1-2 core candidate medical and nursing personnel and 2-3 alternative candidate medical and nursing personnel for each vacancy position in each hospital with a shortage, forming a preliminary allocation combination. Subsequently, the efficiency assessment module simulates the allocation execution effect. Evaluation indicators include changes in medical and nursing personnel workload (controlled within ±15%), changes in hospital department operational efficiency (quantified by the completion rate of treatment volume), cross-regional collaboration costs (calculated by allocation distance and cycle), and patient satisfaction-related indicators, and quantitatively scores the preliminary allocation combination. Based on the scoring results, the plan adjustment module optimizes and adjusts the number of medical staff to be deployed (allocating backup personnel at 1.2 times the number of shortages), deployment duration (setting a flexible period at 1.5 times the predicted period), and deployment routes (selecting the route with the shortest commuting time), generating 3-5 differentiated cross-regional human resource deployment plans. Each plan includes a list of deployed personnel, the departments to be deployed, the deployment period, the specific execution time, and collaborative support measures. Each plan is accompanied by an effectiveness evaluation report and risk warnings (such as personnel adaptation risks and period adjustment risks).

[0024] Step S6 involves the following process: Based on the parameter system for the dynamic optimization and allocation of hospital human resources, a multi-indicator comprehensive verification is performed on the 3-5 cross-regional human resource allocation plans generated in Step S5. Verification indicators include: accuracy of human resource supply and demand matching (required to be no less than 90%), feasibility of cross-regional allocation (meeting all constraints), improvement in human resource efficiency (no less than 15% improvement compared to before allocation), control of cross-regional collaboration costs (not exceeding the preset budget limit), plan flexibility (no less than 5 adjustable parameters), and stability of medical service quality (fluctuations in core diagnostic and treatment indicators not exceeding 5%). The verification process first performs individual indicator verification, eliminating plans that do not meet key indicators (accuracy of matching, feasibility), and then performs a multi-indicator comprehensive scoring (calculating the total score according to the indicator weights). The plan with the highest total score is determined as the optimal cross-regional dynamic human resource allocation plan. Once the optimal solution is generated, deployment instructions are sent to relevant hospitals, departments, and medical staff through the regional medical collaboration platform. The personnel status information in the human resources management systems of each hospital is updated simultaneously, and the deployment execution tracking mechanism is activated to monitor the on-duty status and job suitability of medical staff in real time. Daily execution progress reports are generated to ensure that the solution is implemented according to the predetermined process, while providing data support for subsequent dynamic adjustments.

[0025] Preferably, the expression for the cross-regional medical care capacity matching optimization model is: ,in, Let be the matching score between the i-th medical staff member and the j-th hospital. To assign weighting coefficients to skills, To score the comprehensive professional competence of medical staff member i, Let be the complexity coefficient of the job requirements for hospital j. The business fit factor between medical staff i and hospital j. The geographical distance influence coefficient. The spatial distance between the area where medical staff i is located and hospital j is quantified. The time cost weighting coefficient, Quantify the time required for medical staff i to travel across regions to hospital j. Adjustment coefficient for qualification matching For medical staff member i, the k-th professional qualification qualification standard value is... Let be the qualification requirement value for the k-th position in hospital j, and n be the total number of qualification assessment indicators.

[0026] Specifically, the cross-regional medical staff capability matching optimization model is based on a multi-dimensional supply and demand adaptation logic. First, through literature review and clinical practice summaries, it identifies core factors influencing the matching of medical staff with hospital positions, including professional skill fit, geographical distance cost, time allocation cost, and qualification compliance. Then, it uses the analytic hierarchy process (AHP) to determine the weights of each factor and constructs the model structure using a combination of linear weighting and multiplicative methods. This model is based on the principle that cross-regional human resource allocation must simultaneously consider both matching accuracy and feasibility. Skill-related factors are combined additively to reflect synergistic effects, cost-related factors are divided to reflect constraining effects, and qualification matching factors are multiplicatively applied to reinforce multi-indicator compliance requirements. The parameter values ​​were determined through statistical analysis of historical allocation data. The skill matching weight ranged from 0.3 to 0.5, the geographical distance influence coefficient ranged from 0.1 to 0.2, the time cost weight coefficient ranged from 0.15 to 0.25, and the qualification matching correction coefficient ranged from 0.2 to 0.4. The total number of qualification assessment indicators was set to 5-8 items according to the needs of different departments. Each qualification qualification qualification was assigned a value of 0 or 1 depending on whether the requirements were met. The job qualification requirement values ​​were assigned values ​​of 1, 0.8, and 0.5 respectively, based on whether core qualifications were required, important qualifications were prioritized, and general qualifications were optional. The implementation method involved converting the medical staff and hospital job data collected in step S1 according to the model parameters, inputting it into the model for calculation, outputting the matching degree value, sorting it from high to low according to the matching degree value, and selecting the top 30% as high-fit candidate combinations to provide a preliminary basis for cross-regional manpower allocation.

[0027] Preferably, the expression for the hospital human resource supply and demand forecasting coupling model is: in, The predicted human resource demand of Institute J in time period t. Weights are coupled to historical data. For the hospital jth The actual manpower demand for a given period of time. Here, T is the time decay coefficient, and T is the total number of prediction periods. This represents the regional characteristic influence coefficient. Quantify the service coverage area of ​​hospital j. This refers to the number of beds in the S-class department of the hospital. Let S be the bed turnover rate of the s-th category department of hospital j, where S is the total number of department categories. Assign gradient coefficients to resources. Let be the second-order gradient value of the human resource distribution of hospital j.

[0028] Specifically, the hospital's human resource supply and demand forecasting coupling model is based on time-series data forecasting theory, combined with the fluctuation characteristics of medical business volume, and constructed using a combination of historical data smoothing and regional feature coupling analysis. The model is established based on the fact that hospital human resource demand is influenced by the inertia of historical business volume, driven by regional population health characteristics, and constrained by resource distribution gradients. The historical data portion uses an exponential decay method to weaken the influence of long-term data; the regional feature portion uses a square root method to balance the differences in data between different departments; and the resource distribution portion uses a second-order gradient method to reflect the spatial distribution imbalance. Parameter values ​​are determined through regression analysis and calibration with actual needs. The historical data coupling weight ranges from 0.6 to 0.8, the time decay coefficient ranges from 0.05 to 0.1, the regional feature influence coefficient ranges from 0.2 to 0.3, the resource allocation gradient coefficient ranges from 0.1 to 0.2, the total number of forecast periods is set to 3-6 based on allocation planning needs, and the total number of department categories covers all clinical and medical technology departments in the hospital, totaling 15-20 categories. The implementation method involves standardizing and inputting nearly 36 months of historical business volume data, regional population health data, and hospital resource allocation data into the model according to parameter requirements. The prediction step size is set to 7 days, 30 days, and 90 days. The model iteratively calculates the predicted value of manpower demand for each period and combines it with the current manpower supply data to calculate the supply and demand gap and redundancy, providing quantitative support for subsequent allocation decisions.

[0029] Preferably, the expression for the medical staff supply and demand collaborative analysis algorithm is: ,in, Let p be the human resource supply and demand coordination coefficient between hospital p and hospital q. As a weighting factor for supply and demand gap coordination, Let p be the predicted demand value for hospital in time period t. For the hospital's manpower supply during time period t, For the variance of hospital staffing demand, For the variance of hospital's human resource demand, Let p be the correlation coefficient between the demand and q of the hospital. To match collaborative weights, Match the total degree value for the medical staff of hospital p and q. The feasibility coefficient for cross-regional allocation, To adjust the process complexity coefficient, This represents the impact coefficient of policy constraints.

[0030] Specifically, the medical staff supply and demand coordination analysis algorithm, based on coordination theory and multi-objective optimization, identifies the core influencing factors of inter-hospital staff coordination, including the complementarity of supply and demand gaps, the correlation of demand fluctuations, the matching degree, allocation feasibility, and the degree of constraint satisfaction. The algorithm structure is constructed using a combination of fractions and addition. The algorithm is based on the principle that multi-regional coordinated allocation must simultaneously consider gap complementarity efficiency and execution feasibility. The supply and demand gap coordination part uses a numerator-denominator correspondence form to reflect the balance between the degree of complementarity and fluctuation risk, while the matching coordination part uses a product form to reinforce the dual requirements of adaptability and feasibility. The parameter values ​​were determined through orthogonal experiments and verification with actual data. The supply-demand gap coordination weight ranged from 0.4 to 0.6, the matching coordination weight ranged from 0.4 to 0.6, the demand fluctuation variance was calculated using business volume data from the past 12 months, the demand correlation coefficient ranged from -1 to 1, the cross-regional allocation feasibility coefficient was assigned a comprehensive value of 0.3 to 1.0 based on transportation convenience, policy permissibility, and hospital collaboration history, the allocation process complexity coefficient was assigned a value of 0.1 to 0.3 based on the number of approval steps and execution steps, and the policy constraint impact coefficient was assigned a value of 0.8 to 1.0 based on whether it complies with regional medical planning. The implementation method involves collecting supply and demand data, matching results, and constraint data from hospitals in multiple regions, constructing an analysis matrix according to algorithm requirements, inputting the matrix into the algorithm for multi-dimensional correlation calculations, outputting coordination coefficients, and sorting the allocation priorities according to the coordination coefficients to clarify the optimal direction and order of personnel flow between hospitals.

[0031] Preferably, the efficiency evaluation model expression of the hospital human resource efficiency intelligent evaluation and allocation platform is as follows: ,in, This represents the human resource efficiency evaluation value for position j in hospital category k. As a core weight for efficiency, Let k be the average workload completed by medical staff in position k. The professional skills qualification rate of medical staff in position k This is the workload impact factor. This is a quantified value for the average working hours of job position k. The coefficient representing the impact of collaboration efficiency. Rate the cooperation and coordination of medical staff in position k. For resource adaptation correction coefficients, For the m-th resource allocation quantity of hospital j, Let M be the demand for resource m for job k, and M be the total number of resource types.

[0032] Specifically, the efficiency evaluation model of the hospital's intelligent human resource efficiency assessment and allocation platform is based on human resource efficiency evaluation theory and combined with the actual operation and management of hospitals. It selects business completion volume, skill attainment rate, workload, collaboration and cooperation degree, and resource matching as core evaluation indicators, and constructs the model using a combination of linear combination and square root. The model is based on the principle that human resource efficiency should comprehensively reflect output efficiency, ability matching, and collaboration level. Core efficiency factors use an additive combination to reflect their dominant role, influencing factors use a division method to reflect their constraining role, and resource matching factors use a square root method to balance the influence of multiple resource types. Parameter values ​​are determined through expert scoring and calibration with actual efficiency data. The core efficiency weight ranges from 0.4 to 0.6, the workload influence coefficient ranges from 0.15 to 0.25, the collaboration efficiency influence coefficient ranges from 0.1 to 0.2, the resource matching correction coefficient ranges from 0.2 to 0.3, and the total number of resource types is set to 6-10 categories, including medical equipment, treatment areas, and support personnel. The implementation method involves collecting job performance data, skills assessment data, working hours data, collaboration score data, and resource allocation data through the platform's data interface. After conversion according to the model parameters, the data is input into the evaluation model to calculate the human resource efficiency evaluation value for each job. The evaluation results serve as the core basis for optimizing the allocation plan, ensuring a significant improvement in human resource efficiency after allocation.

[0033] Preferably, the objective function expression for the dynamic optimization allocation of hospital human resources is: ,in, To dynamically optimize the target value, To adjust the cost weighting coefficients, 1 represents the total number of medical staff, and J represents the total number of hospitals. Let be the matching score between medical staff member i and hospital j. To quantify the distance for cross-regional allocation, For supply and demand balance weighting coefficients, Let j be the hospital's demand forecast for time period t. For the hospital's manpower supply in time period t, For collaborative efficiency weighting coefficients, The total number of hospitals participating in the collaboration, Let be the synergy coefficient between hospital p and q.

[0034] Specifically, the objective function for the dynamic optimization of hospital human resources allocation is based on multi-objective optimization theory. Combining the core needs of cross-regional human resource allocation, it takes allocation cost control, supply-demand balance assurance, and improved collaborative efficiency as the three major optimization objectives. The objective function is constructed using a linear weighted summation form, with the minimum value as the optimization direction. The function is established based on the premise that cross-regional human resource allocation must achieve supply-demand balance and collaborative efficiency under the premise of controllable costs. Each objective factor is combined additively to reflect the comprehensive optimization requirements, and the priority of different objectives is reflected through weight allocation. Parameter values ​​are determined through cost-benefit analysis and hospital management needs. The weight coefficient for allocation cost ranges from 0.3 to 0.4, the weight coefficient for supply-demand balance ranges from 0.4 to 0.5, and the weight coefficient for collaborative efficiency ranges from 0.2 to 0.3. The implementation method involves organizing the matching degree data, cross-regional distance data, supply and demand forecast data, and coordination coefficient data generated in steps S2 to S5 according to the function requirements, inputting them into the objective function for calculation, calculating the target value for each of the multiple allocation schemes, and selecting the scheme with the smallest target value as the optimal allocation scheme to ensure that the allocation scheme achieves comprehensive optimization in terms of cost, balance, and coordination, while also meeting the various constraints of cross-regional manpower allocation.

[0035] Preferred, such as Figure 2 As shown, S3 includes the following sub-steps: S31, extracting historical medical service volume data, seasonal fluctuation data, and public health emergency impact data of hospitals in multiple districts over the past three years, classifying and organizing them according to department category and job level, and constructing a time-series supply and demand data sequence; S32, inputting the classified time-series data into the hospital human resource supply and demand forecasting coupling model, setting the time window length and forecast step size, and generating the predicted human resource demand values ​​for each department of each hospital for the next 7 days, 30 days, and 90 days through iterative calculation of the model's internal parameters; S33, combining the current on-the-job data, leave data, and training data of human resources in each hospital, calculating the human resource supply for each period, and determining the human resource gap or redundancy quantitative data for each position in each hospital through supply and demand difference calculation.

[0036] Specifically, step S3 utilizes step S31 to first clarify the data collection scope and classification standards, extracting the clinical service volume data of hospitals in multiple districts for the past three years (36 months). This data is categorized into 15-20 departments, including internal medicine, surgery, and obstetrics and gynecology. Simultaneously, seasonal fluctuation data (divided into spring, summer, autumn, and winter) and data on the impact of public health emergencies (recording the timing of events, affected departments, and the magnitude of changes in service volume) are collected. Further refinement is then made by job level (junior, intermediate, and senior titles), ultimately constructing a unified time-series supply and demand data sequence. This data sequence is stored at a daily granularity to ensure prediction accuracy. Step S32 imports the categorized time-series data into the hospital's human resource supply and demand prediction coupling model, setting a 6-month time window length and defining three prediction steps: 7 days, 30 days, and 90 days. The model iterates using internal parameters (50-80 iterations), combining historical data trends and fluctuation characteristics to generate predicted human resource demand values ​​for each department in each hospital within the three prediction periods. The prediction results are stored by department and prediction period. S33 retrieves the current on-duty human resources data (updated in real-time to the current day), leave data (cumulative leave duration calculated according to each future forecast period), and training data (clearly specifying the number of personnel participating in training and the start and end times of training in each period) collected in step S1. It calculates the human resource supply for each period and accurately quantifies the human resource gap or redundancy data for each position in each hospital in different forecast periods by calculating the difference between the demand forecast and the supply. It outputs a detailed analysis report including the number of gaps / redundancies, the corresponding professional directions, and the demand period.

[0037] Preferred, such as Figure 3 As shown, S4 includes the following sub-steps: S41, collecting the cross-regional medical and nursing capacity matching results output by S2, the supply and demand forecast data generated by S3, as well as the parameters of the multi-regional medical resource sharing agreement, cross-regional transportation network data, and policy constraint data, to establish a collaborative analysis dataset; S42, calling the medical and nursing manpower supply and demand collaborative analysis algorithm to perform multi-dimensional matrix operations on the matching degree value, supply and demand gap value, and cross-regional allocation constraint parameters in the dataset to construct a manpower collaboration correlation network between hospitals; S43, based on the correlation network analysis results, sorting them from high to low according to the collaboration coefficient, outputting a priority list of manpower allocation between hospitals in multiple regions, and clarifying the priority level and correlation parameters of each allocation direction.

[0038] Specifically, step S4 uses the medical and nursing staff supply and demand collaborative analysis algorithm as its core, and achieves multi-dimensional collaborative analysis through three sub-steps. S41 comprehensively collects basic data, including the cross-regional medical and nursing staff capability matching results output by step S2 (including a list of different adaptation levels), the supply and demand forecast data generated by step S3 (gap / redundancy reports for each period), and supplements the parameters of the multi-regional medical resource sharing agreement (clarifying the division of responsibilities and resource allocation authority of cross-regional collaborative hospitals), cross-regional transportation network data (commuting routes between hospitals and average travel time), and policy constraint data (cross-regional practice license requirements and allocation approval process). After standardizing the format of all data, a collaborative analysis dataset including three dimensions—staff adaptation, supply and demand balance, and constraints—is established. The dataset is updated every 24 hours, consistent with step S1. S42 initiates a collaborative analysis algorithm for medical staff supply and demand, transforming the matching degree values, supply-demand gap values, and cross-regional allocation constraint parameters in the dataset into algorithm-recognizable input variables. This constructs a collaborative relationship matrix between hospitals (rows and columns represent the total number of participating hospitals). Through matrix operations (using a multi-dimensional weighted summation method), the complementarity, suitability, and constraint satisfaction of hospital staff supply and demand are analyzed, forming a collaborative relationship network between hospitals. The weights of network nodes are assigned according to the potential for collaboration. S43, based on the network analysis results, extracts collaboration coefficients (quantified in the 0-1 range), sorts them from high to low, and generates a priority list for multi-regional hospital staff allocation. The list clearly indicates the priority level (divided into 1-5 levels), corresponding medical staff suitability levels, supply-demand gap numbers, and cross-regional constraint satisfaction status for each allocation direction (from redundant hospitals to hospitals with shortages), providing a clear basis for subsequent allocation plan formulation.

[0039] Preferred, such as Figure 4 As shown, S5 includes the following steps: S51, the hospital human resource efficiency intelligent assessment and allocation platform receives the allocation priority list from S4, integrates basic human resource information, job demand information, and cross-regional allocation constraints of hospitals in multiple regions, and establishes an allocation plan generation database; S52, the platform matches candidate medical staff for each hospital with a manpower shortage according to the priority order and the adaptation results of the cross-regional medical and nursing capacity matching optimization model, forming a preliminary allocation combination; S53, based on the dynamic optimization configuration parameters of hospital human resources, the platform performs efficiency simulation calculations on the preliminary allocation combination, and evaluates the changes in human resource efficiency of each hospital and the cross-regional collaborative effect after allocation; S54, based on the simulation evaluation results, the number of medical staff allocated, the allocation time, and the allocation route are adjusted to generate 3-5 sets of differentiated cross-regional human resource allocation plans.

[0040] Specifically, step S5 utilizes the hospital's intelligent human resource efficiency assessment and allocation platform to generate multiple allocation plans through four sub-steps. In S51, the platform first integrates data. It receives the allocation priority list output from step S4 and simultaneously accesses the multi-dimensional human resource basic information, job requirement information, and cross-regional allocation constraints from step S1 to establish an allocation plan generation database. This database employs a distributed storage architecture to ensure efficient data reading and processing. In S52, the platform extracts candidate allocation combinations according to priority (from level 1 to level 5). Combining this with the highly compatible results output by the cross-regional medical and nursing capability matching optimization model, it matches 1-2 core candidate medical and nursing personnel and 2-3 alternative candidate medical and nursing personnel for each vacancy position in each hospital with a manpower shortage. Simultaneously, it considers cross-regional allocation constraints (such as commuting time not exceeding 120 minutes) to form preliminary allocation combinations. The number of preliminary combinations for each vacancy position is no less than 3. S53, based on the dynamic optimization parameters of hospital human resources (including human resource efficiency evaluation indicators and allocation cost control thresholds), performs efficiency simulation calculations on the initial allocation combination. The simulation calculates changes in human resource efficiency in each hospital after allocation (quantified by three indicators: business completion efficiency, job suitability, and workload balance) and cross-regional collaboration effects (quantified by changes in collaboration coefficients). The number of simulations is set to 30-50 times to ensure result stability. S54, based on the simulation evaluation results, optimizes and adjusts the initial allocation combination, including adjusting the number of medical staff allocated (configuring reserve personnel at 1.2 times the shortage), allocation duration (setting a flexible period at 1.5 times the prediction period), and allocation routes (selecting routes with the shortest commuting time and highest constraint satisfaction). Finally, 3-5 differentiated cross-regional human resource allocation plans are generated, each plan including complete execution details and parameter descriptions.

[0041] like Figure 5As shown, a hospital human resource dynamic optimization allocation system for multi-regional collaboration is applied to a method for dynamic optimization allocation of hospital human resources for multi-regional collaboration. This system includes: a multi-dimensional data collection and integration unit for multi-regional human resources connects to the information systems of hospitals in multiple regions through a distributed data collection interface, collecting and integrating basic human resource data, job requirement data, and cross-regional constraint data, and transmitting the integrated data to a cross-regional intelligent matching and analysis unit for medical and nursing capabilities; the cross-regional intelligent matching and analysis unit calls a cross-regional medical and nursing capabilities matching optimization model to perform adaptation analysis on the received data, and outputs the matching results to a hospital human resource supply and demand time series prediction and coupling calculation unit; the hospital human resource supply and demand time series prediction and coupling calculation unit, through hospital human resources... The supply and demand forecasting coupling model generates supply and demand forecast data, which is then transmitted to the multi-dimensional collaborative analysis unit for medical and nursing staff supply and demand. This unit uses a collaborative analysis algorithm to perform correlation analysis and outputs allocation priority data to the hospital's intelligent assessment and allocation scheme generation unit. Based on the hospital's intelligent assessment and allocation platform, this unit integrates data to generate the optimal allocation scheme, which is then sent to the dynamic optimization configuration execution and feedback adjustment unit. The dynamic optimization configuration execution and feedback adjustment unit executes the allocation scheme and collects post-allocation staff efficiency data in real time, feeding it back to the multi-dimensional data collection and integration unit for human resources in multiple regions, forming a dynamic optimization closed loop.

[0042] The formula in this invention integrates different scalar and vector parameters for unified calculation, constructing a collaborative computation system through standardization, dimensional consistency calibration, and weight coefficient adaptation. First, all input parameters are transformed into dimensionless values. Vector parameters (such as the set of multi-route travel times in cross-regional traffic network data, or the sequence of multi-dimensional qualification indicators for medical personnel) are decomposed into single-dimensional quantified values. Scalar parameters (such as the number of job vacancies in a single hospital, or the skill scores of medical personnel) are directly normalized, mapping different types of parameters to 0-1 or a specific unified range, eliminating computational conflicts caused by dimensional differences. Second, based on the priority of parameters in human resource allocation, weight coefficients are determined through analytic hierarchy process (AHP) and calibration with historical data. For example, the scalar form of medical personnel skill scores and the vector-decomposed cross-regional allocation constraint quantified values ​​are incorporated into the matching degree calculation according to their respective weights, ensuring a reasonable match between the contributions of different attribute parameters. For example, in the formula for matching cross-regional medical and nursing capabilities, the vector-based multi-qualification compliance indicators, after being decomposed and quantified, are incorporated into the same computational framework along with the scalar-based geographical distance quantification value through weight allocation. In the formula for predicting human resource supply and demand, the vector-based time-series business volume data, after trend decomposition, yields a single-period quantification value, which is then used in conjunction with the scalar-based regional characteristic coefficients. Simultaneously, the formula employs structural designs such as addition, multiplication, or fractional combinations to ensure that the absolute influence of scalar parameters complements the relative influence after vector decomposition. This preserves the core information of each parameter while achieving self-consistency in the computational logic, ultimately achieving effective integration and accurate calculation of different types of parameters within a unified formula.

[0043] This invention presents a method and system for dynamic optimization of hospital human resource allocation across multiple regions. By collecting and integrating basic human resource data, job requirements, and cross-regional constraints from multiple hospitals across different regions, and combining this with a specialized cross-regional medical and nursing capability matching system, it achieves precise matching of the professional skills and work experience of medical personnel in different regions with the needs of hospital positions. This design breaks through the limitations of traditional single-hospital localized allocation, conducting a global and integrated analysis of scattered multi-regional human resource data to form a scientific basis for cross-regional human resource deployment. It effectively overcomes the shortcomings of existing technologies, such as the lack of cross-regional system collaboration mechanisms and insufficient deployment adaptability, making the flow of cross-regional medical resources more targeted and rational, and significantly improving the overall utilization efficiency of human resources across multiple regions.

[0044] This invention utilizes human resource supply and demand forecasting and analysis, collaborative algorithm computation, and an intelligent evaluation and allocation platform to construct a complete closed-loop mechanism from data collection, supply and demand forecasting, collaborative analysis to solution generation and execution feedback. By accurately capturing historical business data and real-time demand changes, it achieves early prediction of human resource supply and demand trends. Simultaneously, through multiple rounds of performance evaluation and solution adjustments, it ensures that the allocation plan can respond in real-time to dynamic changes in human resource supply and demand. This invention solves the problems of weak dynamic optimization capabilities and delayed response in existing technologies, enabling human resource allocation to shift from passive adaptation to proactive prediction. It not only meets the real-time diagnostic and treatment needs of various hospitals but also strengthens the stability and sustainability of multi-regional medical collaboration, promoting a dual improvement in medical service quality and resource allocation efficiency.

[0045] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0046] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0047] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0048] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0049] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0050] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for dynamic optimization of hospital human resource allocation for multi-regional collaboration, characterized in that, Includes the following steps: S1 collects basic human resources data, professional qualification information of medical staff, diagnosis and treatment volume data of each department, and cross-regional transfer constraints of hospitals in multiple districts to construct a multi-dimensional human resources information dataset; S2. Based on the dataset, a cross-regional medical and nursing capacity matching optimization model is used to conduct preliminary matching and screening of medical and nursing staff's professional skills, work experience and the job requirements of various hospitals. S3 utilizes a hospital human resource supply and demand forecasting coupling model, combining historical business volume fluctuation characteristics with regional population health demand change trends, to generate human resource supply and demand gaps and redundancy data for each hospital in the future preset time period. S4 employs a collaborative analysis algorithm for medical staff supply and demand to perform multi-dimensional correlation analysis on the supply and demand data of staff in hospitals in multiple regions and the results of cross-regional matching, and outputs a priority ranking of staff allocation. S5 integrates and analyzes the results through the hospital's intelligent human resource efficiency assessment and allocation platform to formulate multiple cross-regional human resource allocation plans; S6. Based on the hospital's dynamic optimization configuration parameter system for human resources, the allocation plan is comprehensively verified by multiple indicators to determine the optimal cross-regional dynamic human resources allocation plan and execute it.

2. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, The expression for the cross-regional medical and nursing capacity matching optimization model is: ， in, Let be the matching score between the i-th medical staff member and the j-th hospital. To adapt weighting coefficients to skills, To score the comprehensive professional competence of medical staff member i, Let be the complexity coefficient of the job requirements for hospital j. The business fit factor between medical staff i and hospital j. The geographical distance influence coefficient. The spatial distance between the area where medical staff i is located and hospital j is quantified. This is the time cost weighting coefficient. Quantify the time required for medical staff i to travel across regions to hospital j. Adjustment coefficient for qualification matching For medical staff member i, the k-th professional qualification qualification standard value is... Let be the qualification requirement value for the k-th position in hospital j, and n be the total number of qualification assessment indicators.

3. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, The expression for the hospital human resource supply and demand forecasting coupling model is as follows: ;in, The predicted human resource demand of Institute J in time period t. Weights are coupled to historical data. For the hospital jth The actual manpower demand for a given period of time. Here, T is the time decay coefficient, and T is the total number of prediction periods. This represents the regional characteristic influence coefficient. Quantify the service coverage area of ​​hospital j. This refers to the number of beds in the S-class department of the hospital. Let S be the bed turnover rate of the s-th category department of hospital j, where S is the total number of department categories. Assign gradient coefficients to resources. Let be the second-order gradient value of the human resource distribution of hospital j.

4. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, The expression for the algorithm for collaborative analysis of supply and demand of medical and nursing personnel is: ， in, Let p be the human resource supply and demand coordination coefficient between hospital p and hospital q. As a weighted indicator of supply and demand gap, Let p be the predicted demand value for hospital in time period t. For the hospital's manpower supply during time period t, Let p be the variance of hospital staffing demand. For the variance of hospital's human resource demand, Let p be the correlation coefficient between the demand of hospital p and q. To match collaborative weights, Match the total degree value for the medical staff of hospital p and q. The feasibility coefficient for cross-regional allocation, To adjust the process complexity coefficient, This represents the impact coefficient of policy constraints.

5. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, The efficiency evaluation model expression of the hospital human resource efficiency intelligent evaluation and allocation platform is as follows: ， in, This represents the human resource efficiency evaluation value for position j in hospital category k. As a core weight for efficiency, Let k be the average workload completed by medical staff in position k. The professional skills qualification rate of medical staff in position k This is the workload impact factor. This is a quantified value for the average working hours of job position k. The coefficient representing the impact of collaboration efficiency. Rate the cooperation and coordination of medical staff in position k. For resource adaptation correction coefficients, For the m-th resource allocation quantity of hospital j, Let M be the demand for resource m for job k, and M be the total number of resource types.

6. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, The objective function expression for the dynamic optimization allocation of hospital human resources is: ， in, To dynamically optimize the target value, To adjust the cost weighting coefficients, 1 represents the total number of medical staff, and J represents the total number of hospitals. Let be the matching score between medical staff member i and hospital j. To quantify the distance for cross-regional allocation, For supply and demand balance weighting coefficients, Let j be the hospital's demand forecast for time period t. For the hospital's manpower supply in time period t, For collaborative efficiency weighting coefficients, The total number of hospitals participating in the collaboration, Let be the synergy coefficient between hospital p and q.

7. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, S3 includes the following steps: S31. Extract historical medical service volume data, seasonal fluctuation data, and public health emergency impact data from hospitals in multiple districts over the past three years. Classify and organize these data according to department category and job level to construct a time-series supply and demand data sequence. S32, input the classified time series data into the hospital human resource supply and demand forecasting coupling model, set the time window length and forecast step size, and generate the human resource demand forecast values ​​for each department of each hospital in the next 7 days, 30 days and 90 days through iterative calculation of the internal parameters of the model. S33 combines current on-duty, leave, and training data of human resources in each hospital to calculate the human resource supply for each period. Through supply-demand difference calculation, the human resource gap or redundancy quantitative data for each position in each hospital is determined.

8. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration as described in claim 1, characterized in that, S4 includes the following steps: S41 collects the cross-regional medical and nursing capacity matching results output by S2, the supply and demand forecast data generated by S3, as well as the parameters of the multi-regional medical resource sharing agreement, cross-regional transportation network data, and policy constraint data to establish a collaborative analysis dataset; S42 calls the medical staff supply and demand collaborative analysis algorithm to perform multi-dimensional matrix operations on the matching degree value, supply and demand gap value, and cross-regional allocation constraint parameters in the dataset to construct a human resources collaborative relationship network between hospitals. S43, based on the results of the correlation network analysis, sorts the coordination coefficients from high to low, outputs a priority list of human resource allocation among hospitals in multiple regions, and clarifies the priority level and correlation parameters of each allocation direction.

9. The method for dynamic optimization allocation of hospital human resources for multi-regional collaboration according to claim 1, characterized in that, S5 includes the following steps: S51, the hospital human resource efficiency intelligent assessment and allocation platform receives the allocation priority list from S4, integrates basic human resource information, job demand information and cross-regional allocation constraints of hospitals in multiple regions, and establishes an allocation plan generation database; S52, the platform matches candidate medical staff for each hospital with a manpower shortage according to priority and the adaptation results of the cross-regional medical and nursing capacity matching optimization model, forming an initial allocation combination; S53, based on the dynamic optimization configuration parameters of hospital human resources, performs efficiency simulation calculations on the initial allocation combination, and evaluates the changes in human resource efficiency of each hospital and the effect of cross-regional collaboration after the allocation. S54. Based on the simulation evaluation results, adjust the number of medical staff to be deployed, the deployment time and the deployment route, and generate 3-5 sets of differentiated cross-regional human resource deployment plans.

10. A dynamic optimization and allocation system for hospital human resources oriented towards multi-regional collaboration, characterized in that: This system is applied to the dynamic optimization allocation method for hospital human resources oriented towards multi-regional collaboration as described in claim 1, comprising: The multi-dimensional collection and integration unit for human resources data in multiple regions connects to the information systems of hospitals in multiple regions through a distributed data collection interface. It collects and integrates basic human resources data, job requirement data, and cross-regional constraint data, and transmits the integrated data to the cross-regional medical and nursing capacity intelligent matching and analysis unit. The cross-regional medical and nursing capacity intelligent matching and analysis unit calls the cross-regional medical and nursing capacity matching optimization model, performs adaptation analysis on the received data, and outputs the matching results to the hospital human resource supply and demand time series prediction and coupling calculation unit. The hospital human resource supply and demand time series prediction and coupling calculation unit generates supply and demand prediction data through the hospital human resource supply and demand prediction coupling model, and transmits it to the multi-dimensional collaborative analysis unit of medical and nursing human resource supply and demand. The multi-dimensional collaborative analysis unit for medical and nursing staff supply and demand uses a collaborative analysis algorithm for medical and nursing staff supply and demand to perform correlation analysis and output allocation priority data to the hospital human resource efficiency intelligent assessment and allocation plan generation unit. The hospital human resource efficiency intelligent assessment and allocation plan generation unit, based on the hospital human resource efficiency intelligent assessment and allocation platform, integrates data to generate the optimal allocation plan and sends it to the dynamic optimization configuration execution and feedback adjustment unit. The dynamic optimization configuration execution and feedback adjustment unit executes the allocation plan and collects manpower efficiency data in real time after allocation, feeding it back to the multi-dimensional human resources data collection and integration unit in multiple regions to form a dynamic optimization closed loop.

Images