Operation resource allocation method and system

Abstract

The invention relates to the technical field of resource management, in particular to an operation resource allocation method and system, and the method comprises the following steps: integrating data of operation types, duration, equipment requirements and personnel requirements, combining the data with patient identity recognition information, creating an independent index, sorting the data into a queriable data set, and carrying out the data archiving processing, and obtaining a comprehensive resource data file. According to the method, dynamic adjustment of resources is effectively guided by learning historical data and predicting time distribution of equipment use frequency and personnel demands in resource management through a gradient elevator algorithm, the robustness and prediction accuracy of the model are improved through a random forest algorithm and an ensemble learning method, and the robustness and prediction accuracy of the model are improved. Therefore, the adjustment decision in the resource allocation process is more accurate, resource waste is reduced, the allocation efficiency of manpower and material resources is optimized, and the utilization rate of operation resources and the medical service quality are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and in particular to a surgical resource configuration method and system. Background Art

[0002] The field of resource management technology focuses on the effective use and allocation of resources to improve efficiency and effectiveness. In the medical environment, it includes the management of operating room equipment, surgical team configuration and other surgery-related resources. By comprehensively considering various factors, including resource availability, cost-effectiveness and medical needs, the optimal allocation of resources is achieved, thereby improving the quality and efficiency of medical services.

[0003] The surgical resource allocation method aims to improve the utilization rate of operating room resources and the work efficiency of the surgical team, with the aim of reducing resource waste, shortening patient waiting time, and increasing the success rate of surgery, thereby improving the overall quality of medical services. Reasonable allocation of human and material resources can provide more patients with efficient and timely medical services.

[0004] Traditional resource allocation methods lack support for data analysis and resource optimization algorithms. When faced with complex and changeable surgical needs and resource constraints, it is difficult to make the optimal configuration, resulting in uneven resource allocation, frequent equipment idleness or overuse, increased patient waiting time, reduced the overall operating efficiency of the operating room, affected the timeliness of surgery, and increased hospital operating costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a surgical resource configuration method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for configuring surgical resources, comprising the following steps:

[0007] Step 1: Integrate the data on surgery type, duration, equipment requirements, and personnel requirements, and combine them with patient identification information to create an independent index, organize them into a queryable data set, and archive the data to obtain a comprehensive resource data archive;

[0008] Step 2: Based on the comprehensive resource data archive, quantitative analysis is performed on the relationship between resource demand and surgical type, the frequency of equipment use and the time allocation of personnel demand are calculated, and a gradient boosting algorithm is used to adjust the resource utilization strategy and generate resource allocation analysis results;

[0009] Step 3: Based on the resource allocation analysis results, a simulation configuration plan is constructed, reasonable resource configuration is selected through real-time data comparison, simulation parameters are adjusted in combination with the actual situation of the operating room, resource allocation plan is optimized, and a resource configuration optimization plan is generated;

[0010] Step 4: Based on the resource allocation optimization plan, monitor the dynamic changes of resources during the configuration implementation process, record the matching of all resource adjustments with actual surgical needs, use the random forest algorithm to evaluate the adjustment effect, and generate an actual configuration effect report;

[0011] Step 5: Based on the actual configuration effect report, analyze the deficiencies in resource configuration, adjust equipment and personnel allocation, ensure that each resource is efficiently connected with surgical needs, and generate a revised resource configuration plan;

[0012] Step 6: Based on the revised resource configuration plan, evaluate the implementation effect, update the resource configuration strategy according to the actual feedback from the operation, adjust the resource allocation, and generate a final resource configuration plan.

[0013] As a further solution of the present invention, the specific steps of generating the comprehensive resource data archive are:

[0014] Based on the collected data on surgery type, duration, equipment requirements, and personnel requirements, the surgery type and duration are classified and sorted, and a detailed index of equipment and personnel requirements is created. The index is integrated into a queryable structure through an item-by-item association method to generate a classified index data set.

[0015] Based on the classified index data set, a link analysis between patient identity and surgical requirements is performed, and a detailed view of each surgical requirement is accurately constructed by comparing the index with the actual registration information to obtain a comprehensive data view;

[0016] Through the comprehensive data view, the data is systematically archived, and all surgery-related data are tightly integrated according to type and demand, ensuring data integrity and accessibility, and obtaining a comprehensive resource data archive.

[0017] As a further solution of the present invention, the specific steps of generating the resource allocation analysis result are:

[0018] Based on the comprehensive resource data archive, perform specific statistics on the frequency of equipment use, determine the peak demand period of various types of equipment through data distribution analysis, and generate equipment demand frequency analysis results;

[0019] The equipment demand frequency analysis result is used to calculate the time matching degree between personnel demand and surgical arrangement, and human resources are allocated to time periods to obtain personnel time allocation analysis results;

[0020] Through the personnel time allocation analysis results, the gradient boosting algorithm is used to optimize resource allocation, adjust the equipment and personnel usage plan according to the surgical schedule, ensure efficient use of resources, and generate resource allocation analysis results.

[0021] As a further solution of the present invention, the gradient boosting algorithm is according to the formula:

[0022] f n+1 (X) = f n (X)+η·γ n ·h n (X)+α·s n (X)+β·c n (X)

[0023] Where: f n+1 (X) represents the model prediction value after the n+1th iteration, f n (X) represents the model prediction value at the nth iteration, η is the learning rate, γ n represents the optimization step size of the nth iteration, h n (X) is the decision tree model for negative gradient, α is the time sensitivity weight, s n (X) is the adjustment coefficient based on time sensitivity, β is the resource utilization weight, c n (X) is the resource consumption rate adjustment factor.

[0024] As a further solution of the present invention, the specific steps of generating the resource allocation optimization solution are:

[0025] Based on the results of resource allocation analysis, a simulation configuration draft is constructed. The resource requirements of each type of surgery are analyzed using specific equipment usage data and personnel scheduling records. The resource allocation of different operating rooms is adjusted according to the expected surgery time and type to generate a simulation configuration draft.

[0026] Based on the simulation configuration draft, the actual available resources in the operating room are compared with the simulation plan, resource shortages and surpluses are identified, and simulation parameters are adjusted to obtain an adjustment response plan;

[0027] Based on the adjustment response plan, determine the resource allocation to ensure that the resources of each operating room are allocated in the best way, adjust the equipment and personnel according to the surgical needs, and generate a resource allocation optimization plan.

[0028] As a further solution of the present invention, the specific steps of generating the actual configuration effect report are:

[0029] Based on the resource allocation optimization plan, the monitoring system is started to track the implementation process of resource allocation, record the changes in equipment dynamics and personnel configuration, update data in real time, and obtain resource dynamic monitoring records;

[0030] Using the resource dynamic monitoring record, analyzing the matching between resource allocation in actual operation and surgical requirements, adjusting resource allocation according to the analysis results, improving resource utilization efficiency, and generating resource matching adjustment records;

[0031] According to the resource matching adjustment records, the random forest algorithm is used to evaluate the effects of the adjustment measures, confirm the actual performance of resource allocation, confirm the operating room operation efficiency, and generate an actual configuration effect report.

[0032] As a further solution of the present invention, the random forest algorithm is according to the formula:

[0033]

[0034] Where: MSE′ represents the improved mean square error, n represents the total number of samples, w i is the weight coefficient adjusted based on the complexity of the surgery type, Y i represents the actual operating room operating efficiency of the i-th observation, is the operational efficiency of the ith surgery predicted by the model based on the existing resource configuration, ΔY i is the error correction value learned based on historical adjustment effects.

[0035] As a further solution of the present invention, the specific steps of generating the resource configuration revision plan are:

[0036] Analyze resource utilization efficiency based on the actual configuration effect report, determine key shortage points in resource allocation through direct comparison of resource utilization rate and surgical type, adjust equipment and personnel according to surgical needs, and generate detailed resource analysis results;

[0037] The detailed resource analysis results are used to accurately match the type of surgery with the resource requirements, reallocate key equipment and necessary personnel according to the actual operating room conditions, optimize the surgical preparation process, and obtain a surgical resource matching plan;

[0038] Through the surgical resource matching plan, the configuration of equipment and personnel is adjusted and confirmed, and detailed resource readjustment is implemented to ensure efficient connection with surgical needs and generate a revised resource configuration plan.

[0039] As a further solution of the present invention, the specific steps of generating the finalized resource allocation solution are:

[0040] Based on the revised resource allocation plan, a comprehensive resource tracking system is started to collect data on equipment usage and personnel efficiency, monitor the performance of resource allocation in real time, and generate resource implementation tracking records;

[0041] Use the resources to implement tracking records, conduct in-depth analysis on the effectiveness of resource allocation, identify optimization points in resource allocation, and adjust strategies to generate resource optimization analysis results;

[0042] Based on the resource optimization analysis results, confirm and optimize the resource allocation strategy, ensure that all adjustments are reflected in surgical resource management, and generate a final resource allocation plan.

[0043] A surgical resource configuration system, the surgical resource configuration system is used to execute the above-mentioned surgical resource configuration method, the system comprising:

[0044] Data integration module: collects data on surgery type, duration, equipment requirements, and personnel requirements, organizes them into classified index data sets, associates them with patient identities, and generates a comprehensive resource data archive;

[0045] Resource analysis module: based on the comprehensive resource data archive, using the gradient boosting algorithm, statistics the frequency of equipment use and the matching degree of personnel time, adjusts the equipment and personnel time allocation according to the type of surgery and demand peak, and generates resource allocation analysis results;

[0046] Simulation configuration module: based on the resource allocation analysis results, construct a simulation configuration draft, compare the actual available resources in the operating room, adjust the simulation parameters according to the surgical requirements, and generate a resource allocation optimization plan;

[0047] Actual monitoring module: Based on the resource configuration optimization plan, the random forest algorithm is used to monitor the resource configuration implementation process, record equipment dynamics and personnel configuration changes, evaluate resource matching, and generate an actual configuration effect report;

[0048] Resource revision module: Based on the actual configuration effect report, analyze resource utilization efficiency, identify key resource shortage points, reallocate surgical resources, and generate a resource configuration revision plan.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are:

[0050] In the present invention, the gradient boosting machine algorithm is used to learn historical data in resource management to predict the frequency of equipment use and the time allocation of personnel needs, thereby effectively guiding the dynamic adjustment of resources. The random forest algorithm is used to improve the robustness and prediction accuracy of the model through an integrated learning method, making the adjustment decision in the resource allocation process more accurate, thereby reducing resource waste, optimizing the allocation efficiency of manpower and material resources, providing more scientific and precise decision support for operating room resource allocation, and significantly improving the utilization rate of surgical resources and the quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0052] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] Embodiment 1

[0055] See also Figure 1 The present invention provides a technical solution: a method for configuring surgical resources, comprising the following steps:

[0056] Step 1: Integrate the data on surgery type, duration, equipment requirements, and personnel requirements, and combine them with patient identification information to create an independent index, organize them into a queryable data set, and archive the data to obtain a comprehensive resource data archive;

[0057] Step 2: Based on the comprehensive resource data archive, conduct a quantitative analysis of the relationship between resource demand and surgical type, calculate the frequency of equipment use and the time allocation of personnel demand, use the gradient boosting algorithm to adjust the resource utilization strategy, and generate resource allocation analysis results;

[0058] Step 3: Based on the results of resource allocation analysis, a simulation configuration plan is constructed, reasonable resource allocation is selected through real-time data comparison, simulation parameters are adjusted according to the actual situation of the operating room, resource allocation plan is optimized, and resource allocation optimization plan is generated;

[0059] Step 4: Based on the resource allocation optimization plan, monitor the dynamic changes of resources during the configuration implementation process, record the matching of all resource adjustments with actual surgical needs, use the random forest algorithm to evaluate the adjustment effect, and generate an actual configuration effect report;

[0060] Step 5: Based on the actual configuration effect report, analyze the deficiencies in resource allocation, adjust equipment and personnel allocation, ensure that each resource is efficiently connected with surgical needs, and generate a revised resource allocation plan;

[0061] Step 6: Revise the resource allocation plan, evaluate the implementation effect, update the resource allocation strategy according to actual operational feedback, adjust resource allocation, and generate a final resource allocation plan.

[0062] The specific steps to generate a comprehensive resource data archive are:

[0063] Based on the collected data on surgery type, duration, equipment requirements, and personnel requirements, the surgery type and duration are classified and sorted, and a detailed index of equipment and personnel requirements is created. The index is integrated into a queryable structure through an item-by-item association method to generate a classified index data set.

[0064] Based on the classified index data set, we perform a link analysis between patient identity and surgical needs. By comparing the index with the actual registration information, we can accurately construct a detailed view of each surgical need and obtain a comprehensive data view.

[0065] Through comprehensive data views, data is systematically archived, all surgery-related data is tightly integrated by type and need, ensuring data integrity and accessibility, and obtaining a comprehensive resource data archive;

[0066] Based on the collected data on surgery type, duration, equipment requirements, and personnel requirements, a decision tree algorithm was used with parameters including a maximum depth limit of 10 and a minimum sample split number of 2 to classify and sort the surgery type and duration. A hash table was used with a key-value pair approach, where the key was the surgery type and the value was a list of equipment and personnel. An index of equipment and personnel requirements was constructed and integrated into a queryable structure through an item-by-item association method to generate a classified index data set.

[0067] Based on the classified index data set, link analysis technology is used. The parameters include edge weights set as the relevance of surgical requirements, nodes representing patient identities, edges representing the connection between patients and surgical requirements, and edge weights dynamically adjusted according to surgical types and patient historical information. Link analysis of patient identities and surgical requirements is performed. By comparing the index with the actual registration information, a detailed view of each surgical requirement is constructed to generate a comprehensive data view;

[0068] Based on the comprehensive data view, database archiving technology is adopted. Parameters include setting the data storage format to a non-normalized mode and adopting a master-slave structure to ensure data consistency. The master database is responsible for read and write operations, and the slave database is responsible for backup and fault recovery. The non-normalized mode is used to optimize query performance, reduce data redundancy, and systematically archive data. All surgery-related data are tightly integrated according to type and needs to generate a comprehensive resource data archive.

[0069] The specific steps to generate resource allocation analysis results are:

[0070] Based on the comprehensive resource data archive, perform specific statistics on the frequency of equipment use, determine the peak demand period of various types of equipment through data distribution analysis, and generate equipment demand frequency analysis results;

[0071] The equipment demand frequency analysis results are used to calculate the time matching degree between personnel demand and surgical arrangement, and human resources are allocated to time periods to obtain personnel time allocation analysis results;

[0072] Through the analysis results of personnel time allocation, the gradient boosting algorithm is used to optimize resource allocation, adjust the use plan of equipment and personnel according to the surgical schedule, ensure the efficient use of resources, and generate resource allocation analysis results;

[0073] Based on the comprehensive resource data archive, frequency distribution diagram and kurtosis analysis techniques are used. The parameters include the equipment usage times and timestamps. The frequency distribution diagram is used to visualize the equipment usage frequency. The kurtosis analysis determines the data concentration and dispersion trends, identifies the peak demand period, and conducts specific statistics on the equipment usage frequency. The peak demand period of each type of equipment is determined through data distribution analysis, and the equipment demand frequency analysis results are generated;

[0074] Based on the results of equipment demand frequency analysis, a linear programming algorithm is used with parameters including resource demand matrix and time availability vector, and the optimal solution is solved through iterative optimization. The resource demand matrix describes the demand for various types of personnel for corresponding surgeries, and the time availability vector records the availability of personnel in different time periods. The time matching degree between personnel demand and surgical arrangement is calculated, and human resources are allocated to time periods to generate personnel time allocation analysis results;

[0075] Based on the results of personnel time allocation analysis, the gradient boosting machine algorithm was used. The parameters included the learning rate set to 0.1 and the tree depth limited to 6. The learning rate was used to control the model learning progress and the tree depth was used to prevent overfitting. Multiple decision trees were constructed and their prediction results were integrated to optimize performance, optimize resource allocation, adjust the equipment and personnel usage plan to adapt to the surgical schedule, and generate resource allocation analysis results.

[0076] Gradient boosting algorithm, according to the formula:

[0077] f n+1 (X) = f n (X)+η·γ n ·h n (X)+α·s n (X)+β·c n (X)

[0078] Where: f n+1 (X) represents the model prediction value after the n+1th iteration, f n (X) represents the model prediction value at the nth iteration, η is the learning rate, γ n represents the optimization step size of the nth iteration, h n (X) is the decision tree model for negative gradient, α is the time sensitivity weight, s n (X) is the adjustment coefficient based on time sensitivity, β is the resource utilization weight, c n (X) is the resource consumption rate adjustment factor;

[0079] Execution process: First, use the gradient boosting algorithm based on the initial model f n (X), predict the current resource allocation efficiency, f n (X) is the model prediction value of the nth iteration, which is obtained by the learning rate η and the optimization step size γn Adjustment, control the speed and amplitude of the model adjustment in each iteration, decision tree model h n (X) Specifically adjusts the negative gradient of the current prediction to reduce the prediction error. Considering the time sensitivity and resource utilization efficiency in the operating room, the adjustment coefficients α and β are introduced. n (X) and c n (X) performs real-time dynamic adjustment, where s n (X) Adjust time allocation based on the time urgency of the surgery, c n (X) Adjust resource allocation according to actual resource consumption, and finally update the model to f n+1 (X) Generate the final resource allocation plan to ensure the optimal use of operating room resources and improve the operating room's work efficiency and resource utilization efficiency.

[0080] The specific steps to generate a resource allocation optimization plan are:

[0081] Based on the results of resource allocation analysis, a simulation configuration draft is constructed. The resource requirements of each type of surgery are analyzed using specific equipment usage data and personnel scheduling records. The resource allocation of different operating rooms is adjusted according to the expected surgery time and type to generate a simulation configuration draft.

[0082] Based on the simulation configuration draft, the actual available resources in the operating room are compared with the simulation plan, resource shortages and surpluses are identified, and simulation parameters are adjusted to obtain an adjustment response plan;

[0083] Based on the adjustment response plan, determine resource allocation, ensure that the resources of each operating room are allocated in the best way, adjust equipment and personnel according to surgical needs, and generate a resource allocation optimization plan;

[0084] Based on the results of resource allocation analysis, a simulation configuration draft is constructed. The specific equipment usage data and personnel scheduling records are used. The usage data includes the equipment model and usage timestamp, and the personnel scheduling records include the employee number and shift time. The resource requirements of each type of surgery are analyzed, and the resource allocation of different operating rooms is adjusted to match the expected surgery time and type to generate a simulation configuration draft.

[0085] Based on the draft simulation configuration, a difference analysis algorithm was used, using the coefficient of variation calculation method. The parameters included the actual resource volume and the simulated resource volume. The coefficient of variation calculation method identified the difference by comparing the ratio of the standard deviation to the mean value, and compared the actual available resources in the operating room with the simulation plan to identify the shortage and surplus of resources, and adjust the simulation parameters to generate an adjustment response plan.

[0086] Based on the adjustment reflection scheme, a genetic algorithm was used with parameters including population size set to 50, number of iterations to 100, crossover probability to 0.8, and mutation probability to 0.05. The population size determined the breadth of the search space, the number of iterations determined the search depth, and the crossover probability and mutation probability controlled the exploration and utilization balance of the algorithm to determine resource allocation, adjust equipment and personnel to meet actual surgical needs, and generate a resource allocation optimization plan.

[0087] The specific steps to generate the actual configuration effect report are:

[0088] Based on the resource allocation optimization plan, the monitoring system is started to track the implementation process of resource allocation, record the changes in equipment dynamics and personnel configuration, update data in real time, and obtain resource dynamic monitoring records;

[0089] Use resource dynamic monitoring records to analyze the matching between resource allocation in actual operation and surgical needs, adjust resource allocation according to the analysis results, improve resource utilization efficiency, and generate resource matching adjustment records;

[0090] Based on the resource matching adjustment records, the random forest algorithm is used to evaluate the effect of the adjustment measures, confirm the actual performance of resource allocation, confirm the operating room operation efficiency, and generate an actual configuration effect report;

[0091] Based on the resource allocation optimization plan, the monitoring system is started. The parameters include setting the equipment status detection frequency to once per minute and the personnel configuration update interval to once every ten minutes. The implementation process of resource allocation is tracked, the changes in equipment dynamics and personnel configuration are recorded, data is updated in real time, and resource dynamic monitoring records are generated;

[0092] Using dynamic resource monitoring records, adopting deviation analysis methods, the parameters include actual resource usage data and planned resource configuration data, the mean square error calculation reflects the deviation between the planned configuration and actual usage, analyzing the matching between the resource configuration in actual operation and the surgical needs, adjusting the resource allocation according to the analysis results, and generating resource matching adjustment records;

[0093] According to the resource matching adjustment records, the random forest algorithm was adopted and the Scikit-learn library was used. The parameters included the number of trees set to 100 and the maximum depth of each tree set to 10. The number of trees increased the stability of the model and the maximum depth of each tree controlled the model complexity to prevent overfitting. The effects of the adjustment measures were evaluated, the actual performance of the resource allocation was confirmed, and a report on the actual configuration effect was generated.

[0094] Random forest algorithm, according to the formula:

[0095]

[0096] Where: MSE′ represents the improved mean square error, n represents the total number of samples, w i is the weight coefficient adjusted based on the complexity of the surgery type, Y i represents the actual operating room operating efficiency of the i-th observation, is the operational efficiency of the ith surgery predicted by the model based on the existing resource configuration, ΔY i is the error correction value learned based on historical adjustment effects;

[0097] Implementation process: First, for each surgical case, the complexity of each type of surgery is determined by analyzing historical data, and a weight coefficient w is set for each surgical type. i , which reflects the importance and difficulty of different types of surgery in resource allocation. In order to improve the accuracy of prediction, an error correction value ΔY is introduced. i Based on the average value of the actual effect and prediction deviation of similar surgical configurations in the past, the prediction result of the real-time correction model is close to the actual situation, and the corrected prediction value is and actual operating efficiency Y i The difference between them is squared to amplify the error impact, and the squared error is multiplied by the corresponding weight w i , and calculate the average of all weighted errors to obtain the evaluation index MSE′, which measures the deviation between the actual performance of the surgical resource allocation plan and the expected target. The whole process combines statistical analysis and machine learning techniques to optimize the allocation of operating room resources and improve operational efficiency.

[0098] The specific steps to generate a resource configuration revision plan are:

[0099] Analyze resource utilization efficiency based on actual configuration effect reports, identify key shortage points in resource allocation through direct comparison of resource utilization rate and surgical type, adjust equipment and personnel according to surgical needs, and generate detailed resource analysis results;

[0100] Detailed resource analysis results are used to accurately match surgical types and resource requirements, reallocate key equipment and necessary personnel according to actual operating room conditions, optimize surgical preparation processes, and obtain surgical resource matching solutions;

[0101] Through the surgical resource matching plan, adjust and confirm the configuration of equipment and personnel, implement detailed resource readjustment, ensure efficient connection with surgical needs, and generate a revised resource configuration plan;

[0102] Based on the actual configuration effect report, the resource utilization efficiency is analyzed. The Pearson correlation coefficient is used. The parameters include resource utilization rate and surgical type data. The linear relationship between the two data sets is measured. The value range is from -1 to 1. Close to 1 or -1 indicates a strong correlation. Through direct comparison of resource utilization rate and surgical type, the key shortage points in resource allocation are determined, and equipment and personnel are adjusted to match specific surgical needs to generate detailed resource analysis results.

[0103] The detailed resource analysis results are used to accurately match the surgical type and resource demand. The linear programming method is used, and the parameters include the resource supply and demand matrix and cost-effectiveness analysis. The resource allocation problem is solved by maximizing and minimizing the objective function under linear constraints. The resource supply and demand matrix describes the supply and demand of each resource corresponding to the surgical type. The cost-effectiveness analysis determines the economic efficiency of resource allocation. The key equipment and necessary personnel are reallocated according to the actual operating room situation to generate a surgical resource matching plan.

[0104] Through the surgical resource matching plan, the configuration of equipment and personnel was finally adjusted and confirmed. The decision tree algorithm was used. The parameters included the maximum depth of the tree was set to 5, the minimum number of leaf node samples was set to 10, the maximum depth of the tree controlled the complexity of the model to prevent overfitting, and the minimum number of leaf node samples ensured the representativeness of each decision node. Detailed resource readjustment was implemented to ensure efficient docking with surgical needs and generate a revised resource configuration plan.

[0105] The specific steps to generate the final resource configuration plan are:

[0106] Based on the revised resource allocation plan, launch a comprehensive resource tracking system to collect data on equipment usage and personnel efficiency, monitor the performance of resource allocation in real time, and generate resource implementation tracking records;

[0107] Use resource implementation tracking records to conduct in-depth analysis of the effectiveness of resource allocation, identify optimization points in resource allocation, and adjust strategies to generate resource optimization analysis results;

[0108] According to the results of resource optimization analysis, confirm and optimize resource allocation strategies, ensure that all adjustments are reflected in surgical resource management, and generate a final resource allocation plan;

[0109] Based on the revised resource allocation plan, a real-time data stream analysis tool is used. The parameters include data collection frequency set to once every 5 minutes. The data includes equipment usage status and personnel efficiency indicators. Data on equipment usage and personnel efficiency are collected to monitor the performance of resource allocation in real time and generate resource implementation tracking records.

[0110] Use resource implementation tracking records and use a linear regression model. The parameters include independent variables as resource usage data and dependent variables as surgical success rate. The linear regression model fits the optimal straight line by minimizing the sum of squared errors, evaluates the relationship between resource usage and surgical success rate, conducts in-depth analysis of the effectiveness of resource allocation, identifies optimization points in resource allocation, and adjusts strategies to improve resource utilization efficiency and generate resource optimization analysis results;

[0111] According to the results of resource optimization analysis, a dynamic programming algorithm is used. The parameters include decision variables as resource allocation plan and objective function as maximizing operating room utilization. The dynamic programming algorithm gradually solves the optimal decision path by constructing a recursive relationship between decision stages and states, confirms and optimizes resource allocation strategies, ensures that all adjustments are reflected in surgical resource management, and generates a final resource allocation plan.

[0112] See also Figure 2 , a surgical resource configuration system, the system comprising:

[0113] Data integration module: collects data on surgery type, duration, equipment requirements, and personnel requirements, organizes them into classified index data sets, associates them with patient identities, and generates a comprehensive resource data archive;

[0114] Resource analysis module: Based on the comprehensive resource data archive, the gradient boosting algorithm is used to count the frequency of equipment use and the matching degree of personnel time, adjust the equipment and personnel time allocation according to the type of surgery and demand peak, and generate resource allocation analysis results;

[0115] Simulation configuration module: Based on the resource allocation analysis results, a simulation configuration draft is constructed, compared with the actual available resources in the operating room, simulation parameters are adjusted according to surgical requirements, and a resource allocation optimization plan is generated;

[0116] Actual monitoring module: Based on the resource allocation optimization plan, the random forest algorithm is used to monitor the resource allocation implementation process, record equipment dynamics and personnel configuration changes, evaluate resource matching, and generate actual configuration effect reports;

[0117] Resource revision module: Based on the actual configuration effect report, analyze resource utilization efficiency, identify key resource shortage points, reallocate surgical resources, and generate resource configuration revision plans.

[0118] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for allocating surgical resources, characterized in that: The following steps are involved: Step 1: Integrate the data on surgery type, duration, equipment requirements, and personnel requirements, and combine them with patient identification information to create an independent index, organize them into a queryable data set, and archive the data to obtain a comprehensive resource data archive; Step 2: Based on the comprehensive resource data archive, quantitative analysis is performed on the relationship between resource demand and surgical type, the frequency of equipment use and the time allocation of personnel demand are calculated, and a gradient boosting algorithm is used to adjust the resource utilization strategy and generate resource allocation analysis results; Step 3: Based on the resource allocation analysis results, a simulation configuration plan is constructed, reasonable resource configuration is selected through real-time data comparison, simulation parameters are adjusted in combination with the actual situation of the operating room, resource allocation plan is optimized, and a resource configuration optimization plan is generated; Step 4: Based on the resource allocation optimization plan, monitor the dynamic changes of resources during the configuration implementation process, record the matching of all resource adjustments with actual surgical needs, use the random forest algorithm to evaluate the adjustment effect, and generate an actual configuration effect report; Step 5: Based on the actual configuration effect report, analyze the deficiencies in resource configuration, adjust equipment and personnel allocation, ensure that each resource is efficiently connected with surgical needs, and generate a revised resource configuration plan; Step 6: Based on the revised resource configuration plan, evaluate the implementation effect, update the resource configuration strategy according to the actual feedback from the operation, adjust the resource allocation, and generate a final resource configuration plan.

2. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the comprehensive resource data archive are: Based on the collected data on surgery type, duration, equipment requirements, and personnel requirements, the surgery type and duration are classified and sorted, and a detailed index of equipment and personnel requirements is created. The index is integrated into a queryable structure through an item-by-item association method to generate a classified index data set. Based on the classified index data set, a link analysis between patient identity and surgical requirements is performed, and a detailed view of each surgical requirement is accurately constructed by comparing the index with the actual registration information to obtain a comprehensive data view; Through the comprehensive data view, the data is systematically archived, and all surgery-related data are tightly integrated according to type and demand, ensuring data integrity and accessibility, and obtaining a comprehensive resource data archive.

3. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the resource allocation analysis result are: Based on the comprehensive resource data archive, perform specific statistics on the frequency of equipment use, determine the peak demand period of various types of equipment through data distribution analysis, and generate equipment demand frequency analysis results; The equipment demand frequency analysis result is used to calculate the time matching degree between personnel demand and surgical arrangement, and human resources are allocated to time periods to obtain personnel time allocation analysis results; Through the personnel time allocation analysis results, the gradient boosting algorithm is used to optimize resource allocation, adjust the equipment and personnel usage plan according to the surgical schedule, ensure efficient use of resources, and generate resource allocation analysis results.

4. The surgical resource allocation method according to claim 1, characterized in that: The gradient boosting algorithm is based on the formula: f n+1 (X)=f n (X)+η·γ n ·h n (X)+α·s n (X)+β·c n (X) Where: f n+1 (X) represents the model prediction value after the n+1th iteration, f n (X) represents the model prediction value at the nth iteration, η is the learning rate, γ n represents the optimization step size of the nth iteration, h n (X) is the decision tree model for negative gradient, α is the time sensitivity weight, s n (X) is the adjustment coefficient based on time sensitivity, β is the resource utilization weight, c n (X) is the resource consumption rate adjustment factor.

5. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the resource configuration optimization plan are: Based on the results of resource allocation analysis, a simulation configuration draft is constructed. The resource requirements of each type of surgery are analyzed using specific equipment usage data and personnel scheduling records. The resource allocation of different operating rooms is adjusted according to the expected surgery time and type to generate a simulation configuration draft. Based on the simulation configuration draft, the actual available resources in the operating room are compared with the simulation plan, resource shortages and surpluses are identified, and simulation parameters are adjusted to obtain an adjustment response plan; Based on the adjustment response plan, determine the resource allocation to ensure that the resources of each operating room are allocated in the best way, adjust the equipment and personnel according to the surgical needs, and generate a resource allocation optimization plan.

6. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the actual configuration effect report are: Based on the resource allocation optimization plan, the monitoring system is started to track the implementation process of resource allocation, record the changes in equipment dynamics and personnel configuration, update data in real time, and obtain resource dynamic monitoring records; Using the resource dynamic monitoring record, analyzing the matching between resource allocation in actual operation and surgical requirements, adjusting resource allocation according to the analysis results, improving resource utilization efficiency, and generating resource matching adjustment records; According to the resource matching adjustment records, the random forest algorithm is used to evaluate the effects of the adjustment measures, confirm the actual performance of resource allocation, confirm the operating room operation efficiency, and generate an actual configuration effect report.

7. The surgical resource allocation method according to claim 1, characterized in that: The random forest algorithm is based on the formula: Where: MSE′ represents the improved mean square error, n represents the total number of samples, w i is the weight coefficient adjusted based on the complexity of the surgery type, Y i represents the actual operating room operating efficiency of the i-th observation, is the operational efficiency of the ith surgery predicted by the model based on the existing resource configuration, ΔY i is the error correction value learned based on historical adjustment effects.

8. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the resource configuration revision plan are: Analyze resource utilization efficiency based on the actual configuration effect report, determine key shortage points in resource allocation through direct comparison of resource utilization rate and surgical type, adjust equipment and personnel according to surgical needs, and generate detailed resource analysis results; The detailed resource analysis results are used to accurately match the type of surgery with the resource requirements, reallocate key equipment and necessary personnel according to the actual operating room conditions, optimize the surgical preparation process, and obtain a surgical resource matching plan; Through the surgical resource matching plan, the configuration of equipment and personnel is adjusted and confirmed, and detailed resource readjustment is implemented to ensure efficient connection with surgical needs and generate a revised resource configuration plan.

9. The surgical resource allocation method according to claim 1, characterized in that: The specific steps of generating the finalized resource configuration plan are: Based on the revised resource allocation plan, a comprehensive resource tracking system is started to collect data on equipment usage and personnel efficiency, monitor the performance of resource allocation in real time, and generate resource implementation tracking records; Use the resources to implement tracking records, conduct in-depth analysis on the effectiveness of resource allocation, identify optimization points in resource allocation, and adjust strategies to generate resource optimization analysis results; Based on the resource optimization analysis results, confirm and optimize the resource allocation strategy, ensure that all adjustments are reflected in surgical resource management, and generate a final resource allocation plan.

10. A surgical resource allocation system, characterized in that: According to the surgical resource configuration method according to any one of claims 1 to 9, the system comprises: Data integration module: collects data on surgery type, duration, equipment requirements, and personnel requirements, organizes them into classified index data sets, associates them with patient identities, and generates a comprehensive resource data archive; Resource analysis module: based on the comprehensive resource data archive, using the gradient boosting algorithm, statistics the frequency of equipment use and the matching degree of personnel time, adjusts the equipment and personnel time allocation according to the type of surgery and demand peak, and generates resource allocation analysis results; Simulation configuration module: based on the resource allocation analysis results, construct a simulation configuration draft, compare the actual available resources in the operating room, adjust the simulation parameters according to the surgical requirements, and generate a resource allocation optimization plan; Actual monitoring module: Based on the resource configuration optimization plan, the random forest algorithm is used to monitor the resource configuration implementation process, record equipment dynamics and personnel configuration changes, evaluate resource matching, and generate an actual configuration effect report; Resource revision module: Based on the actual configuration effect report, analyze resource utilization efficiency, identify key resource shortage points, reallocate surgical resources, and generate a resource configuration revision plan.

Images