Clinical human resource intelligent allocation method and system based on big data analysis

Abstract

The application provides a clinical human resource intelligent configuration method and system based on big data analysis, relates to the technical field of clinical human resource configuration, and comprises the following steps: performing nursing demand analysis based on patient data to obtain a nursing demand quantity; performing nursing supply analysis based on nurse data in combination with the nursing demand quantity to obtain a nursing supply quantity; dividing a rest group based on the nursing supply quantity to obtain an initial scheduling strategy; calculating an actual execution rest duration according to an actual work load score of a real-time shift; and adjusting the initial scheduling strategy according to the actual execution rest duration to obtain an optimized scheduling strategy. Through the application, the technical problem that, in the prior art, the scheduling process relies on manual experience and static rules, lacks integrated analysis and intelligent prediction of multi-source data, and thus the scheduling scheme is insufficient in scientificity, poor in flexibility, and low in human resource configuration efficiency can be solved, and the technical effect of improving the scientificity and precision of clinical human resource intelligent configuration is achieved.

Description

Technical Field

[0001] This application relates to the field of clinical human resource allocation technology, and in particular to a method and system for intelligent allocation of clinical human resources based on big data analysis. Background Technology

[0002] As modern medical institutions continue to expand and the demand for medical services becomes increasingly complex, clinical scheduling management has become a core element affecting medical quality, operational efficiency, and employee satisfaction.

[0003] Currently, while existing basic automated systems can electronically record shift information and perform basic conflict checks, their scheduling logic is often based on static, pre-set rules, such as fixed shift cycles or uniform rest duration standards. These systems cannot adapt to real-time variables such as dynamic fluctuations in patient traffic, differences in patient severity, and changes in nurses' skill sets. These systems lack both the ability to deeply analyze historical and real-time data and the ability to intelligently link the quantified results of patient care needs with the precise allocation of human resources, leading to a frequent disconnect between scheduling plans and actual clinical scenarios.

[0004] In summary, existing technologies suffer from technical problems such as insufficient scientific rigor, poor flexibility, and low efficiency in human resource allocation because the scheduling process relies on human experience and static rules, lacks integrated analysis and intelligent prediction of multi-source data, and fails to establish a dynamic closed-loop resource optimization mechanism. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for intelligent allocation of clinical human resources based on big data analysis, in order to solve the technical problems in the existing technology, which are that the scheduling process relies on human experience and static rules, lacks integrated analysis and intelligent prediction of multi-source data, and has not established a dynamic closed-loop resource optimization mechanism, resulting in insufficient scientificity, poor flexibility and low efficiency of human resource allocation.

[0006] In view of the above problems, this application provides a method and system for intelligent allocation of clinical human resources based on big data analysis.

[0007] Firstly, this application provides a method for intelligent allocation of clinical human resources based on big data analysis, implemented through a clinical human resources intelligent allocation system based on big data analysis. The method includes: analyzing nursing needs based on patient data to obtain nursing demand; combining the nursing demand with nursing supply analysis based on nurse data to obtain nursing supply; dividing shift groups based on the nursing supply to obtain an initial scheduling strategy; calculating the actual rest time based on the actual workload score of real-time shifts; and adjusting the initial scheduling strategy according to the actual rest time to obtain an optimized scheduling strategy.

[0008] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: accessing the hospital information system to obtain the real-time number of inpatients; predicting patient inflow based on the number of scheduled outpatient appointments and scheduled surgeries, and predicting patient outflow based on clinical pathways and discharge plans; quantifying the nursing dependence of the patient's critical condition index based on the real-time number of inpatients, patient inflow, and patient outflow, and calculating the nursing demand based on the nursing dependence.

[0009] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: classifying nursing based on the nursing dependence to obtain the required nursing difficulty level; obtaining a scheduling-related group that maps skill level, skill level quantity, and nursing difficulty level; matching the required nursing difficulty level in the scheduling-related group to obtain the required skill level and required skill level quantity, and adding it to the nursing demand.

[0010] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: obtaining skill levels based on employee files, matching the skill levels required in the nursing demand to obtain the initial number of skill levels to be supplied; dividing shift types to obtain a first shift type and a second shift type; updating the initial number of skill levels to obtain the number of skill levels to be supplied based on the first shift type and the second shift type, and adding it to the nursing supply.

[0011] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: generating initial shift groups based on the skill level and number of skill levels provided in the nursing supply, wherein the skill levels provided in the initial shift groups are the same; defining a benchmark rest duration, including a first rest duration corresponding to the first shift type and a second rest duration corresponding to the second shift type; evaluating the shift overlap of the initial shift groups based on the benchmark rest duration to obtain a shift overlap index, wherein the shift overlap is the sum of the product of the number of overlapping days and the number of overlapping people; selecting the first shift group with the lowest shift overlap index based on the shift overlap index and executing the shift type scheduling; and iterating and recombining the remaining shift groups in the initial shift groups excluding the first shift group until the initial shift groups finish their current shift, thereby obtaining the initial scheduling strategy.

[0012] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: calculating the ratio of the required weighted sum of the actual skill level and the number of actual skill levels required in the real-time shift to the supplied weighted sum of the provided skill level and the number of supplied skill levels to obtain the actual workload score; determining whether the real-time shift belongs to an enhanced shift based on the actual workload score using a preset enhanced shift threshold; if the real-time shift belongs to an enhanced shift, dynamically increasing the fatigue compensation rest increment to the baseline rest duration to determine the actual rest duration.

[0013] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: allocating manpower from the next shift in the initial scheduling strategy based on the actual rest duration, until the number of allocated manpower meets the nursing supply; if the number of allocated manpower does not meet the nursing supply, allocating rest manpower, until the number of allocated manpower meets the nursing supply, thereby obtaining an optimized scheduling strategy.

[0014] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: calculating the rest duration of the personnel performing rest, and determining whether it meets the benchmark rest duration; if it meets the benchmark rest duration, allocating the personnel performing rest; if it does not meet the benchmark rest duration, calculating the remaining rest duration based on the rest duration, accumulating the remaining rest duration, and allocating the personnel performing rest.

[0015] Preferably, the intelligent allocation method for clinical human resources based on big data analysis further includes: increasing the shift priority of personnel who do not meet the benchmark rest duration.

[0016] Secondly, this application also provides a clinical human resource intelligent allocation system based on big data analysis, used to execute the clinical human resource intelligent allocation method based on big data analysis as described in the first aspect, including: a nursing demand acquisition module, used to perform nursing demand analysis based on patient data to obtain nursing demand; a nursing supply acquisition module, used to combine the nursing demand and perform nursing supply analysis based on nurse data to obtain nursing supply; an initial scheduling strategy acquisition module, used to divide shift groups based on the nursing supply to obtain an initial scheduling strategy; an actual rest time calculation module, used to calculate the actual rest time based on the actual workload score of the real-time shift; and an optimized scheduling strategy acquisition module, used to adjust the initial scheduling strategy according to the actual rest time to obtain an optimized scheduling strategy.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goals of accurate prediction of nursing needs driven by big data, dynamic optimization of human resources allocation, and forward-looking management of employee fatigue risks, it achieves the technical effects of improving the scientificity and accuracy of scheduling, enhancing the adaptive ability of the scheduling system to cope with fluctuations in clinical needs, and ensuring the reasonable allocation of the workload of nurses and the balanced maintenance of their rest rights.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the intelligent allocation method for clinical human resources based on big data analysis proposed in this application.

[0021] Figure 2 This is a schematic diagram of the structure of the intelligent allocation system for clinical human resources based on big data analysis proposed in this application.

[0022] Attached diagrams and their symbols: Nursing demand calculation module 1, Nursing supply calculation module 2, Initial scheduling strategy calculation module 3, Actual rest time calculation module 4, Optimized scheduling strategy calculation module 5. Detailed Implementation

[0023] This application provides a method and system for intelligent allocation of clinical human resources based on big data analysis. It addresses the technical problems in existing technologies, such as insufficient scientific rigor, poor flexibility, and low efficiency in human resource allocation. These problems stem from the reliance on manual experience and static rules in the scheduling process, the lack of integrated analysis and intelligent prediction of multi-source data, and the absence of a dynamic closed-loop resource optimization mechanism. The application achieves the technical goals of accurate prediction of nursing needs driven by big data, dynamic optimization of human resource allocation, and proactive management of employee fatigue risks. This results in improved scientific rigor and accuracy of scheduling, enhanced adaptability of the scheduling system to fluctuations in clinical demand, and ensured a reasonable distribution of workload and balanced maintenance of nurses' rest rights.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a method for intelligent allocation of clinical human resources based on big data analysis, which is applied to a clinical human resources intelligent allocation system based on big data analysis, and specifically includes the following steps:

[0026] S1: Analyze nursing needs based on patient data to obtain the nursing needs quantity.

[0027] Furthermore, this application also includes: accessing the hospital information system to obtain the real-time number of inpatients; predicting patient inflow based on the number of scheduled outpatient appointments and scheduled surgeries, and predicting patient outflow based on clinical pathways and discharge plans; quantifying the nursing dependence of the patient's critical condition index based on the real-time number of inpatients, patient inflow, and patient outflow, and calculating the nursing demand based on the nursing dependence.

[0028] Furthermore, this application also includes: performing nursing grade based on the nursing dependence to obtain the required nursing difficulty level; obtaining a scheduling-related group mapping skill level, skill level quantity, and nursing difficulty level; matching the required nursing difficulty level in the scheduling-related group to obtain the required skill level and required skill level quantity, and adding it to the nursing demand.

[0029] Specifically, accessing the hospital information system and obtaining the real-time number of inpatients means establishing a connection with the hospital's core operation and management system through a data interface, thereby extracting and obtaining the total number of beds actually occupied in each inpatient ward at the current time, i.e., the real-time number of inpatients.

[0030] Building upon this foundation, to proactively assess future human resource needs, it is necessary to predict dynamic changes in patient numbers. Patient inflow is predicted based on outpatient appointments and scheduled surgeries, while patient outflow is predicted based on clinical pathways and discharge plans. Specifically, this involves comprehensively analyzing pre-registered outpatient visits and planned surgeries for specific future dates to estimate the number of new inpatients to be admitted. Simultaneously, it involves estimating the number of patients to be discharged based on standard treatment process templates for specific diseases and doctors' anticipated discharge plans. This process utilizes historical time-series data for machine learning modeling. Historical outpatient appointment and scheduled surgery data stored in the hospital information system are accessed, forming a time series with periodicity and trends. Subsequently, a long short-term memory neural network model is used to train on the historical data, automatically learning and capturing data patterns, including weekly fluctuations with a seven-day cycle, peaks and troughs in visits due to statutory holidays, and long-term trends caused by seasonal variations in the incidence of specific diseases. Pattern recognition is then used to calculate the estimated patient inflow most likely to translate into actual inpatient admissions within a specific future time period. When predicting patient outflow, the diagnostic information of currently hospitalized patients is matched with pre-stored standard clinical pathways in the knowledge base to establish a theoretical baseline for the number of days of hospital stay for each patient. However, actual discharge time is affected by individual differences, so discharge plan data needs to be introduced as a dynamic correction factor. By analyzing the discharge plan status submitted by attending physicians and combining it with patients' real-time vital signs data and recovery progress, a discharge probability prediction model is constructed using classification algorithms such as logistic regression or random forest. This model evaluates various indicators and calculates the probability of each patient being discharged within the next 24 or 48 hours. Finally, the theoretical number of days based on clinical pathways is combined with the probability prediction based on real-time data to obtain a weighted predicted value for the number of patients outflow.

[0031] Furthermore, to achieve precise matching of nursing resources, it is necessary to convert the number of patients into nursing workload. Nursing dependency is quantified based on real-time inpatient numbers, patient inflows, and patient outflows, using a patient condition severity index. Nursing demand is calculated based on this dependency level, determining the expected patient distribution within the target scheduling cycle. Furthermore, based on the diagnosis, treatment, and nursing records in the electronic medical records, a numerical value representing the required care intensity—the nursing dependency level—is assessed for each patient. This value comprehensively reflects the complexity of the patient's condition and the degree of self-care ability deficit. Finally, by summarizing the nursing dependency levels of all patients, the total nursing workload required to care for this batch of patients is calculated.

[0032] Nursing dependency is a quantifiable numerical indicator used to objectively measure the intensity of care required by each patient due to the severity of their condition and lack of self-care ability. Nursing dependency is used to perform a nursing grading process, categorizing continuous dependency values ​​into discrete nursing difficulty levels to obtain the required nursing difficulty level. Then, a mapping relationship is retrieved from a predefined scheduling-related group stored in the database. This scheduling-related group is a configuration table that specifies the corresponding nurse skill levels and their minimum number required for different nursing difficulty levels. For example, each patient with level 1 nursing difficulty requires a nurse with basic skills, while each patient with level 3 nursing difficulty requires a nurse with advanced skills. By using the required nursing difficulty level as a query condition and performing a matching search within the scheduling-related group, the necessary nurse skill types (i.e., required skill levels) and the minimum number of nurses required for each skill level (i.e., the required skill level quantity) are parsed and added as key parameters to the overall nursing demand definition.

[0033] S2: Based on the nursing demand, nursing supply analysis is performed using nurse data to obtain the nursing supply quantity.

[0034] Furthermore, this application also includes: obtaining skill levels based on employee records, matching the skill levels required in the nursing demand to obtain the initial number of skill levels to be supplied; dividing shift types to obtain a first shift type and a second shift type; updating the initial number of skill levels to obtain the number of skill levels to be supplied based on the first shift type and the second shift type, and adding it to the nursing supply.

[0035] Specifically, skill levels are determined based on employee records. Employee records refer to digital records stored in the human resources database, which detail the professional competence level of each nursing staff member through official certification or internal assessment, such as identification of new nurses, senior nurses, or specialist nurses. The skill levels recorded in the records are compared and mapped one by one with the required skill levels explicitly listed in the nursing needs. The purpose is to screen qualified candidates from the existing workforce. After the matching process is completed, the total number of nurses who can theoretically meet various nursing needs levels can be calculated, thus obtaining the initial number of skill levels available.

[0036] However, in actual operation, the availability of human resources is constrained by work arrangements, thus requiring the introduction of a time dimension for refinement. The next step is to classify shift types, which refer to different work periods defined according to the hospital's operational cycle. At least two core shift types should be defined; for example, defining daytime work periods as shift type one and nighttime work periods as shift type two, thereby covering the 24-hour medical service needs.

[0037] After clarifying the shift structure, the availability of the initially collected human resources needs to be calibrated. Based on the first and second shift types defined above, and considering employee scheduling preferences, contractual working hours, and labor regulations regarding continuous work, the initial number of available skill levels is updated. This update process aims to deduct the number of personnel who cannot provide service in a specific shift due to rule restrictions or individual unavailability, thereby calculating the actual number of nurses available for dispatch and meeting the skill requirements within each specific shift—that is, the number of available skill levels. Finally, the more accurate human resource data after shift availability calibration, i.e., the number of available skill levels, is added to the nursing supply as a core component. The nursing supply is therefore no longer a general concept of total personnel, but rather a clear list broken down by shift structure, detailing the actual number of available personnel for each skill level.

[0038] S3: Divide the shift groups based on the nursing supply to obtain the initial shift scheduling strategy.

[0039] Furthermore, this application also includes: generating initial shift groups based on the skill level and number of skill levels provided in the nursing supply, wherein the skill levels provided in the initial shift groups are the same; defining a benchmark rest duration, including a first rest duration corresponding to the first shift type and a second rest duration corresponding to the second shift type; evaluating the shift overlap of the initial shift groups based on the benchmark rest duration to obtain a shift overlap index, wherein the shift overlap is the sum of the product of the number of overlapping days and the number of overlapping people; selecting the first shift group with the lowest shift overlap index based on the shift overlap index and executing the shift scheduling for the shift type; traversing and recombining the remaining shift groups in the initial shift groups other than the first shift group until the initial shift groups finish their current shift, to obtain the initial scheduling strategy.

[0040] Specifically, the organization and grouping process for human resources is implemented based on the skill levels and corresponding numbers explicitly listed in the nursing supply. The skill levels refer to the actual, certified professional competence levels currently existing within the nursing team, while the number of skill levels is the specific number of nurses at each skill level, determined after considering shift availability. Generating initial shift groups involves dividing nurses with the same skill level into several logically cooperating units based on the skill levels and their corresponding numbers. For example, all ten nurses with advanced skills might be divided into two groups of five members each, with all members within the initial shift group having the same skill level.

[0041] After the initial organization of human resources is completed, basic time guarantee rules are established for shift scheduling. A baseline rest period is defined, which is a mandatory minimum continuous rest time set for different shift types based on labor laws, hospital policies, and ergonomic principles. The first shift type, possibly day shift, corresponds to a relatively short first rest period, such as 12 hours; while the second shift type, possibly night shift, has a longer second rest period, such as 36 hours, due to its greater impact on circadian rhythms, to ensure employees can fully recover.

[0042] Next, the preliminary grouping plan is optimized and evaluated. Based on the defined baseline rest duration, the overlap rate of rest periods for each generated initial shift group is assessed. The shift overlap rate assessment is a simulation analysis process that simulates the shift arrangements for each group throughout the entire scheduling cycle and calculates a quantitative shift overlap rate index. The specific calculation method for the shift overlap rate index is to count all dates where rest periods overlap within the simulation period, multiply the number of overlapping personnel on each overlapping date by a predefined weighting coefficient, and finally sum all such products. A higher shift overlap rate index indicates a greater risk of staff shortages due to multiple personnel taking leave simultaneously under the group's shift arrangement.

[0043] The decision-making stage begins based on the calculated shift overlap index. By prioritizing the most stable and lowest-risk option, the group with the lowest shift overlap index value is selected from all initial shift groups and designated as the first shift group. This optimized group, which can most effectively avoid rest conflicts within the current scheduling cycle, is used to execute the actual scheduling for the current shift type.

[0044] After determining the optimal shift group, the remaining human resources are allocated. For the remaining shift groups not selected as the first shift group in the initial shift group, a process of iteration and recombination is performed. Unselected groups are disbanded, their members are returned to the available manpower pool, and the same regrouping and evaluation process is attempted to find suboptimal or suitable grouping schemes for subsequent shifts. This iterative process continues until shifts are assigned to all available personnel, meaning the entire initial shift group has completed its current shift. This generates an initial shift strategy covering the entire cycle and all manpower.

[0045] S4: Calculate the actual rest time based on the actual workload score of the real-time shift.

[0046] Furthermore, this application also includes: calculating the actual workload score by comparing the weighted sum of the actual required skill levels and the number of actual required skill levels in the real-time shift with the weighted sum of the supplied skill levels and the number of supplied skill levels; determining whether the real-time shift belongs to an enhanced shift based on the actual workload score using a preset enhanced shift threshold; if the real-time shift belongs to an enhanced shift, dynamically increasing the fatigue compensation rest increment to the baseline rest duration to determine the actual execution rest duration.

[0047] Specifically, the required weighted sum is calculated based on the actual skill level and the actual number of skill levels required in a real-time shift. A real-time shift refers to a specific work period that is currently being executed or has just ended. The actual required skill level reflects the actual professional competence level required to care for patients within that real-time shift, while the actual required number of skill levels refers to the specific number of nurses required for each skill level given the current patient composition. The required weighted sum is a comprehensive calculation value obtained by multiplying different skill levels and their corresponding quantities and summing the results, used to characterize the standard nursing workload that should theoretically be provided in that real-time shift. Simultaneously, the supplied skill levels and the supplied skill levels are also calculated using the same weighted sum, representing the skill and number composition of the nurses actually on duty in that real-time shift. The ratio of the required weighted sum to the supplied weighted sum is calculated by dividing the actual required standard workload by the theoretical workload that the actual on-duty personnel can provide; the resulting quotient is the actual workload score, reflecting the pressure level between the actual needs of the shift and the existing configuration.

[0048] After obtaining quantified stress indicators, decision-making is made based on preset standards. The actual workload score is assessed based on a preset enhanced shift threshold. This threshold is a numerical cutoff point pre-set by hospital management based on historical data and operational goals, used to define the level of workload for a shift. The assessment process involves comparing the calculated actual workload score with the preset enhanced shift threshold. If the score equals or exceeds the threshold, the shift is considered an enhanced shift, meaning the workload significantly exceeds the normal level, causing additional physical and mental strain on employees.

[0049] Once a shift is designated as an intensive shift, a compensation mechanism will be automatically triggered. If a shift is indeed an intensive shift, a fatigue compensation rest increment will be dynamically added to the baseline rest time. The baseline rest time refers to the basic, mandatory minimum rest time set for different shift types. The fatigue compensation rest increment is an additional rest time dynamically determined according to the degree to which the actual workload score exceeds a threshold, using predefined calculation rules. The baseline rest time is added to this increment, resulting in a new, longer rest period, which is the actual rest time implemented, ensuring that employees who have undergone high-intensity work receive adequate recovery commensurate with their exertion.

[0050] S5: Adjust the initial scheduling strategy according to the actual rest duration to obtain an optimized scheduling strategy.

[0051] Furthermore, this application also includes: based on the actual rest duration, allocating manpower from the next shift in the initial scheduling strategy until the number of allocated manpower meets the nursing supply; if the number of allocated manpower does not meet the nursing supply, allocating rest manpower until the number of allocated manpower meets the nursing supply, thereby obtaining an optimized scheduling strategy.

[0052] Furthermore, this application also includes: calculating the rest duration of the personnel performing the rest, and determining whether it meets the benchmark rest duration; if it meets the benchmark rest duration, allocating the personnel performing the rest; if it does not meet the benchmark rest duration, calculating the remaining rest duration based on the rest duration, accumulating the remaining rest duration, and allocating the personnel performing the rest.

[0053] Furthermore, this application also includes: increasing the shift priority of personnel who do not meet the said benchmark rest duration.

[0054] Specifically, a dynamic reallocation process for human resources is implemented based on the actual rest duration. The actual rest duration refers to the final rest time calculated for employees who have completed high-intensity shifts, including fatigue compensation increments, and may be longer than the baseline rest duration. The initial scheduling strategy refers to the original shift plan generated at the beginning of the scheduling cycle, without considering dynamic adjustments. The next shift refers to a work plan that immediately follows the current shift in the time sequence. Personnel reallocation refers to the readjustment of personnel arrangements in shifts that have not yet started, within the limits allowed by established scheduling rules. Nursing supply refers to the number of nurses of each skill level necessary to meet anticipated nursing needs, as determined in the aforementioned process. Since some employees are unable to work as originally planned due to extended rest, other nurses must be pre-assigned from their subsequent shifts, such as those of tomorrow or the day after, to fill the resulting vacancies. This ensures that at any given time, the total number of nurses on duty and their skill structure meet the nursing supply requirements, thereby maintaining service continuity.

[0055] However, there may be a situation where simply redeploying nurses from subsequent shifts cannot fully compensate for the staffing shortage. If the total number of nurses gathered through the above methods is still lower than the nursing care required for the current shift, it means that the reserve staff for future shifts is also insufficient. In this case, a higher-priority emergency redeployment mechanism will be activated, namely, redeploying nurses on rest days. Rest days refer to nurses currently within their legally mandated or prescribed rest periods. This will break standard rest guarantees, attempting to contact and reassign nurses who are currently on rest but may be eligible to work. This operation will continue until the total number of nurses successfully redeployed, i.e., the number of nurses redeployed, finally meets the nursing care required for the current shift, addressing extreme staffing shortages.

[0056] Once the manpower shortage was successfully addressed, an updated scheduling plan was developed to adapt to real-time changes—the optimized scheduling strategy. The optimized scheduling strategy is the final, executable plan formed by incorporating responses to actual workload and dynamic allocation of human resources based on the initial scheduling strategy.

[0057] Furthermore, calculating the rest duration for staff on leave is a necessary verification before any human resource allocation. Staff on leave refers to nursing personnel currently on continuous leave, and rest duration refers to the continuous time interval from the end of the employee's last shift to the proposed allocation time. The process involves determining whether the employee meets the baseline rest duration, which is the minimum mandatory rest time set for different shift types to ensure basic employee recovery. The calculated actual rest duration is then compared with the corresponding baseline rest duration to confirm whether the employee's rest has met the minimum standard required by policy.

[0058] If it is determined that the actual rest time of the employee on rest has been equal to or exceeded the prescribed baseline rest time, it indicates that the employee has completed the minimum recovery and their physical condition meets the basic conditions for being reassigned. Therefore, the employee is deemed available for redeployment, and the redeployment operation is immediately carried out, changing their status from rest to awaiting work and incorporating them into the current shift's human resource supply.

[0059] Conversely, if it is determined that the actual rest time of the employee performing the rest is less than the prescribed baseline rest time, it means that the mandatory rest guarantee period has not yet ended. In this case, a more detailed calculation is initiated. Based on the employee's actual rest time, the remaining mandatory rest time, i.e., the remaining rest time, is calculated as the baseline rest time minus the actual rest time. This remaining rest time is accumulated and recorded, linked to the employee's personal file. After this recording, the employee performing the rest will still be reassigned, allowing them to return to work early. However, this reassignment and the resulting remaining rest time will be accurately recorded as a clear basis for subsequent compensation for working hours or priority arrangement of compensatory time off.

[0060] Furthermore, after completing the reassignment of personnel who have not met the rest requirements and recording their remaining rest time, the rotation priority of personnel who do not meet the benchmark rest time is increased. Personnel who do not meet the benchmark rest time refer to nursing staff who are recorded and reassigned to work before the mandatory rest guarantee period has expired. Rotation priority is a numerical parameter used for ranking, determining the right to be prioritized when multiple rest applications or rotation opportunities exist in subsequent scheduling cycles.

[0061] In summary, the intelligent allocation method for clinical human resources based on big data analysis provided in this application has the following technical effects: by achieving the technical goals of accurate prediction of nursing needs driven by big data, dynamic optimization of human resource allocation, and proactive management of employee fatigue risks, it can improve the scientificity and accuracy of scheduling, enhance the adaptive ability of the scheduling system to cope with fluctuations in clinical needs, and ensure the reasonable allocation of the workload of nurses and the balanced maintenance of their rest rights.

[0062] Example 2: Based on the same inventive concept as the big data analysis-based intelligent allocation method for clinical human resources in the foregoing examples, this application also provides a big data analysis-based intelligent allocation system for clinical human resources. Please refer to the appendix. Figure 2The system includes: a nursing demand acquisition module 1, used to analyze nursing demand based on patient data to obtain nursing demand; a nursing supply acquisition module 2, used to combine the nursing demand with nurse data to analyze nursing supply to obtain nursing supply; an initial scheduling strategy acquisition module 3, used to divide shift groups based on the nursing supply to obtain an initial scheduling strategy; an actual rest time calculation module 4, used to calculate the actual rest time based on the actual workload score of the real-time shift; and an optimized scheduling strategy acquisition module 5, used to adjust the initial scheduling strategy according to the actual rest time to obtain an optimized scheduling strategy.

[0063] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used to: access the hospital information system to obtain the real-time number of inpatients; predict patient inflow based on the number of scheduled outpatient appointments and scheduled surgeries, and predict patient outflow based on clinical pathways and discharge plans; quantify the nursing dependence of the patient's critical condition index based on the real-time number of inpatients, patient inflow, and patient outflow, and calculate the nursing demand based on the nursing dependence.

[0064] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used for: classifying nursing care based on the nursing dependence to obtain the required nursing difficulty level; obtaining scheduling-related groups that map skill levels, skill level quantities, and nursing difficulty levels; matching the required nursing difficulty level in the scheduling-related groups to obtain the required skill level and required skill level quantity, and adding it to the nursing demand.

[0065] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used for: obtaining skill levels based on employee records, matching the skill levels required in the nursing demand, and obtaining the initial number of skill levels to be supplied; classifying shift types to obtain a first shift type and a second shift type; updating the initial number of skill levels to obtain the number of skill levels to be supplied based on the first shift type and the second shift type, and adding it to the nursing supply.

[0066] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used for: generating initial shift groups based on the skill level and number of skill levels provided in the nursing supply, wherein the skill levels provided in the initial shift groups are the same; defining a benchmark rest duration, including a first rest duration corresponding to the first shift type and a second rest duration corresponding to the second shift type; evaluating the shift overlap of the initial shift groups based on the benchmark rest duration to obtain a shift overlap index, wherein the shift overlap is the sum of the product of the number of overlapping days and the number of overlapping people; selecting the first shift group with the lowest shift overlap index based on the shift overlap index and executing the shift scheduling for the shift type; and iterating and recombining the remaining shift groups in the initial shift groups excluding the first shift group until the initial shift groups finish their current shift, thereby obtaining the initial scheduling strategy.

[0067] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used to: calculate the actual workload score by comparing the weighted sum of the actual required skill levels and the number of actual required skill levels in the real-time shift with the weighted sum of the supplied skill levels and the number of supplied skill levels; determine whether the real-time shift belongs to an enhanced shift based on the actual workload score; if the real-time shift belongs to an enhanced shift, dynamically increase the fatigue compensation rest increment to the baseline rest time to determine the actual rest time.

[0068] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used to: allocate manpower from the initial scheduling strategy to the next shift based on the actual rest duration, until the number of allocated manpower meets the nursing supply; if the number of allocated manpower does not meet the nursing supply, allocate rest manpower until the number of allocated manpower meets the nursing supply, thereby obtaining an optimized scheduling strategy.

[0069] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used to: calculate the rest duration of the personnel performing rest, and determine whether it meets the benchmark rest duration; if it meets the benchmark rest duration, allocate the personnel performing rest; if it does not meet the benchmark rest duration, calculate the remaining rest duration based on the rest duration, accumulate the remaining rest duration, and allocate the personnel performing rest.

[0070] Furthermore, the intelligent allocation system for clinical human resources based on big data analysis is also used to: increase the priority of shifts for personnel who do not meet the benchmark rest duration.

[0071] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The intelligent configuration method and specific examples of clinical human resources based on big data analysis in the foregoing embodiment 1 are also applicable to the intelligent configuration system of clinical human resources based on big data analysis in this embodiment. Through the foregoing detailed description of the intelligent configuration method of clinical human resources based on big data analysis, those skilled in the art can clearly understand the intelligent configuration system of clinical human resources based on big data analysis in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0072] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0073] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for intelligent allocation of clinical human resources based on big data analysis, characterized in that: include: Nursing needs are analyzed based on patient data to obtain the nursing needs quantity; Based on the nursing demand, nursing supply analysis is performed using nurse data to obtain the nursing supply. Based on the nursing supply, shift groups were divided to obtain an initial shift scheduling strategy; The actual rest time is calculated based on the actual workload score of the real-time shift. The initial scheduling strategy is adjusted based on the actual rest duration to obtain an optimized scheduling strategy.

2. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 1, characterized in that, Nursing needs analysis based on patient data yields nursing needs quantities, including: Connect to the hospital information system to obtain real-time number of inpatients; Patient inflow is predicted based on outpatient appointments and surgical appointments, and patient outflow is predicted based on clinical pathways and discharge plans. Nursing dependence is quantified based on the real-time number of inpatients, patient inflow and outflow, and the nursing demand is calculated based on the nursing dependence.

3. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 2, characterized in that, The nursing needs are calculated based on the nursing dependency, including: Based on the nursing dependence, nursing care is graded to obtain the required nursing difficulty level; Obtain scheduling-related groups that map skill levels, skill level quantities, and nursing difficulty levels. Match the required nursing difficulty level in the scheduling-related groups to obtain the required skill level and required skill level quantity, and add them to the nursing demand.

4. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 3, characterized in that, Based on the stated nursing demand, a nursing supply analysis is performed using nurse data to obtain the nursing supply, including: Based on the employee's records, skill levels are obtained and matched with the required skill levels in the nursing needs to obtain the initial number of skill levels to be supplied. Classify the shift types to obtain the first shift type and the second shift type; Based on the first shift type and the second shift type, the initial supply skill level quantity is updated to obtain the supply skill level quantity, which is then added to the nursing supply quantity.

5. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 4, characterized in that, Based on the nursing supply, shift groups are divided to obtain an initial shift scheduling strategy, including: An initial shift group is generated based on the skill level and quantity of the nursing care provided, wherein the skill levels provided in the initial shift group are the same. Define a baseline rest duration, including the first rest duration corresponding to the first shift type and the second rest duration corresponding to the second shift type; The overlap of shifts in the initial shift group is evaluated based on the baseline rest duration to obtain a shift overlap index. The shift overlap is the sum of the product of the number of overlapping days and the number of overlapping people. Based on the shift overlap index, the first shift group with the lowest shift overlap index is selected, and the shift scheduling of the shift type is executed; The remaining shift groups in the initial shift groups, excluding the first shift group, are traversed and recombined until the initial shift groups finish their current shift rotation, thus obtaining the initial shift scheduling strategy.

6. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 5, characterized in that, Calculate the actual rest time based on the real-time shift's actual workload score, including: The actual workload score is calculated by comparing the weighted sum of the actual required skill levels and the number of actual required skill levels in the real-time shifts with the weighted sum of the supplied skill levels and the number of supplied skill levels. Based on a preset enhanced shift threshold, the actual workload score is used to determine whether the real-time shift belongs to an enhanced shift. If the real-time shift is an intensive shift, the fatigue compensation rest increment is dynamically added to the baseline rest duration to determine the actual rest duration.

7. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 1, characterized in that, The initial scheduling strategy is adjusted based on the actual rest duration to obtain an optimized scheduling strategy, including: Based on the actual rest duration, manpower is allocated from the next shift in the initial scheduling strategy until the number of allocated personnel meets the nursing supply. If the number of personnel to be allocated does not meet the nursing supply, off-duty personnel will be allocated until the number of personnel to be allocated meets the nursing supply, thus obtaining an optimized scheduling strategy.

8. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 7, characterized in that, Allocate and manage resting personnel, including: Calculate the rest duration of the personnel performing the rest, and determine whether it meets the benchmark rest duration; If the baseline rest duration is met, the required manpower for the rest period will be reallocated. If the baseline rest duration is not met, the remaining rest duration is calculated based on the rest duration, the remaining rest duration is accumulated, and the manpower for the rest is allocated accordingly.

9. The intelligent allocation method for clinical human resources based on big data analysis as described in claim 8, characterized in that, Increase the priority of shift work for personnel whose rest time does not meet the aforementioned benchmark.

10. A clinical human resource intelligent allocation system based on big data analysis, characterized in that: The steps for implementing the intelligent allocation method for clinical human resources based on big data analysis as described in any one of claims 1 to 9 include: The nursing needs calculation module is used to analyze nursing needs based on patient data and obtain nursing needs. The nursing supply quantity acquisition module is used to combine the nursing demand quantity with nursing data to perform nursing supply analysis and obtain the nursing supply quantity. The initial scheduling strategy acquisition module is used to divide shift groups based on the nursing supply to obtain the initial scheduling strategy; The actual rest duration calculation module is used to calculate the actual rest duration based on the actual workload score of the real-time shift. The optimized scheduling strategy module is used to adjust the initial scheduling strategy according to the actual rest time to obtain the optimized scheduling strategy.

Images