Hospital bed turnover method and system based on hospital data, medium and electronic equipment

Abstract

The invention provides a hospital bed turnover method and system based on hospital data, a medium and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring sickbed occupation information of a plurality of departments; based on the sickbed occupancy information, predicting a first sickbed occupancy rate of a plurality of departments after a target duration; under the condition that the occupancy rate of the first sickbed is smaller than an occupancy rate threshold value, sickbed tension and patient waiting cost of the multiple departments are determined; and generating a sickbed optimization scheme based on the sickbed tensity of the plurality of departments and the patient waiting cost, and transferring the sickbeds of the plurality of departments according to the sickbed optimization scheme.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, system, medium, and electronic device for bed turnover based on hospital data. Background Technology

[0002] Traditional hospital bed management relies mainly on manual experience and static allocation strategies, lacking the ability to dynamically rotate bed resources across multiple departments. This leads to uneven resource allocation, with some departments experiencing bed shortages while others have idle beds, affecting the overall bed utilization efficiency of the hospital and the patient's medical experience. Summary of the Invention

[0003] In view of this, this application provides a method, system, medium, and electronic device for bed turnover based on hospital data.

[0004] One aspect of this application provides a bed turnover method based on hospital data, comprising:

[0005] Obtain bed occupancy information from multiple departments;

[0006] Based on the bed occupancy information, predict the first bed occupancy rate of multiple departments after the target duration;

[0007] If the occupancy rate of the first bed is less than the threshold occupancy rate, determine the bed shortage and patient waiting cost of the multiple departments;

[0008] Based on the bed occupancy rate and patient waiting costs of the multiple departments, a bed optimization plan is generated to facilitate the turnover of beds in the multiple departments according to the bed optimization plan.

[0009] According to an embodiment of this application, the bed occupancy information includes the current second bed occupancy rate of the multiple departments, the first number of patients expected to be admitted within the target duration, and the second number of patients expected to be discharged.

[0010] According to an embodiment of this application, determining the bed occupancy rate and patient waiting costs of the multiple departments includes:

[0011] Based on the second bed occupancy rate, the first number, the second number, and the average patient waiting time, a bed occupancy assessment matrix is ​​constructed.

[0012] Calculate the weight coefficient of each assessment indicator in the bed occupancy assessment matrix;

[0013] Based on the weighting coefficients, the bed occupancy rate of the multiple departments is calculated;

[0014] Based on the urgency coefficient of patients' conditions and patients' waiting time in the aforementioned departments, the patient waiting cost is determined.

[0015] According to an embodiment of this application, the method of generating a bed optimization scheme based on the bed occupancy rate and patient waiting cost of the multiple departments includes:

[0016] Construct a target optimization function, which is used to balance the bed occupancy rate and patient waiting costs of the multiple departments;

[0017] The constraints of the objective optimization function are determined, including the uniqueness constraint of patient bed allocation and the departmental bed capacity constraint.

[0018] The objective optimization function is solved based on the constraints to obtain the optimal bed allocation scheme.

[0019] According to an embodiment of this application, the bed occupancy information also includes the number of patients moving between different departments within the target duration;

[0020] The objective optimization function is adjusted based on the number of patients. The adjusted objective optimization function is used to balance the bed occupancy of the multiple departments, the patient waiting cost, and the cost of patients moving between departments.

[0021] The constraints of the adjusted objective optimization function also include constraints on the feasibility of patient movement across departments and the balance of the number of patients moving between departments.

[0022] The adjusted multi-objective optimization function is solved based on the constraints of the adjusted multi-objective optimization function to obtain the bed optimization scheme.

[0023] According to an embodiment of this application, the prediction of the first bed occupancy rate of multiple departments after a target duration includes:

[0024] Based on the historical bed occupancy data of the multiple departments, the probability of bed vacancy in the multiple departments after the target duration is calculated using the moving window statistical method.

[0025] The occupancy rate of the first bed in multiple departments is determined based on the bed vacancy probability after the target duration.

[0026] According to an embodiment of this application, the bed occupancy information further includes the patient's discharge time, which includes the patient's expected discharge time and the patient's actual discharge time. The method further includes:

[0027] When it is detected that the patient's actual discharge time deviates from the patient's expected discharge time, the bed vacancy probability is corrected based on an exponential decay function; the exponential decay function characterizes the degree of deviation between the patient's expected discharge time and the patient's actual discharge time.

[0028] The first bed occupancy rate of multiple departments is determined based on the corrected bed vacancy probability after the target duration.

[0029] Another aspect of this application provides a hospital data-based bed turnover system, comprising:

[0030] The acquisition module is used to acquire bed occupancy information from multiple departments;

[0031] The prediction module is used to predict the first bed occupancy rate of multiple departments after a target duration based on the bed occupancy information.

[0032] The calculation module is used to determine the bed occupancy rate and patient waiting cost of the multiple departments when the occupancy rate of the first bed is less than the threshold occupancy rate threshold.

[0033] The scheduling module is used to generate a bed optimization plan based on the bed occupancy and patient waiting costs of the multiple departments, so as to rotate the beds of the multiple departments according to the bed optimization plan.

[0034] Another aspect of this application provides an electronic device comprising:

[0035] One or more processors;

[0036] Memory, used to store one or more programs.

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described above.

[0038] Another aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0039] By employing the embodiments of this application, dynamic monitoring of hospital bed resource status is achieved by acquiring bed occupancy information from multiple departments and predicting the first bed occupancy rate of each department after a target duration based on this information. This overcomes the limitations of traditional manual experience-based management, which lacks predictive capabilities. When the first bed occupancy rate is less than a threshold occupancy rate, potential problems of uneven bed resource allocation can be identified in a timely manner. By determining the bed occupancy levels and patient waiting costs across multiple departments, the differences in resource demand among departments and their impact on patient service quality are quantitatively assessed, solving the problem that traditional static allocation strategies cannot accurately measure the effectiveness of cross-departmental resource allocation.

[0040] Furthermore, bed optimization schemes generated based on bed occupancy and patient waiting costs can guide bed turnover decisions among multiple departments, enabling dynamic allocation of bed resources. This effectively alleviates the uneven resource allocation problem where some departments have bed shortages while others have idle beds, thereby improving the overall bed utilization efficiency of the hospital and the patient's medical experience. Attached Figure Description

[0041] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0042] Figure 1 A flowchart illustrating a hospital data-based bed turnover method provided in this application is shown schematically.

[0043] Figure 2 This schematic diagram illustrates a structural block diagram of a hospital data-based bed turnover system provided in this application;

[0044] Figure 3 A schematic block diagram of an electronic device provided in this application is shown. Detailed Implementation

[0045] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0046] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0047] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0048] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0049] Figure 1 A flowchart illustrating a hospital data-based bed turnover method provided in an embodiment of this application is shown.

[0050] like Figure 1 As shown, the hospital data-based bed turnover method may specifically include steps S101 to S104.

[0051] Step S101: Obtain bed occupancy information for multiple departments;

[0052] Step S102: Based on bed occupancy information, predict the first bed occupancy rate of multiple departments after the target duration;

[0053] Step S103: If the occupancy rate of the first bed is less than the threshold occupancy rate threshold, determine the bed occupancy rate and patient waiting cost of multiple departments.

[0054] Step S104: Generate a bed optimization plan based on the bed occupancy rate and patient waiting cost of multiple departments, so as to rotate the beds of the multiple departments according to the bed optimization plan.

[0055] In step S101, the bed occupancy information refers to a comprehensive data set that reflects the current bed usage status of various departments in the hospital and the trend of bed resource changes in the future. In this embodiment, it can be understood as data such as bed allocation in various departments and patient admission and discharge plans recorded in the hospital bed management system.

[0056] As an optional implementation, the bed occupancy information includes the current second bed occupancy rate of multiple departments, the first number of patients expected to be admitted within the target duration, and the second number of patients expected to be discharged.

[0057] The second bed occupancy rate refers to the ratio of the number of beds actually occupied by each department at the current moment to the total number of beds in that department. In this embodiment, it can be understood as a real-time indicator reflecting the current bed resource shortage in the department, used to assess the current bed load of the department.

[0058] Similarly, the first quantity refers to the number of patients expected to be admitted to each department within the target duration. In this embodiment, it can be understood as the future admission demand predicted based on confirmed appointment information and historical admission patterns.

[0059] Similarly, the second quantity refers to the number of patients expected to complete treatment and be discharged from each department within the target duration. In this embodiment, it can be understood as the expected number of beds to be released based on the patient's treatment progress and medical plan.

[0060] In one feasible implementation, the system establishes data connections with the bed management subsystems of various departments, periodically extracts the current bed occupancy status from the inpatient management system, obtains the expected admission patient information from the appointment registration system, collects patient discharge plan data from the doctor workstation system, and integrates the above-mentioned scattered data sources to form a unified bed occupancy information dataset.

[0061] In another feasible implementation, bed occupancy information can be obtained by combining manual input with automatic system data collection. For example, the head nurse or bed administrator updates the bed status changes in each department in real time using a dedicated terminal device. The system automatically records patient admission and discharge times, and doctors report adjustments to patient discharge plans via mobile terminals. Simultaneously, the system backend periodically synchronizes basic bed configuration information from the hospital's core business system to ensure the accuracy and real-time nature of bed occupancy information.

[0062] In step S102, the first bed occupancy rate refers to the ratio of the number of beds actually occupied by each department to the total number of beds in that department after a preset target duration. In this embodiment, it can be understood as a predictive indicator reflecting the degree of bed resource shortage in each department at a specific future time.

[0063] The target duration refers to the preset time interval from the current moment to the execution of the bed optimization allocation decision. In this embodiment, it can be understood as the prediction time window set by the hospital bed management system when making forward-looking resource allocation, which is used to determine the time range for predicting bed occupancy rate.

[0064] For example, the target duration can be set according to the hospital's actual operational needs and management precision requirements, including but not limited to: short-term target duration such as the next 2-4 hours, which is suitable for dealing with emergency allocation needs during peak admission and discharge periods of the day; medium-term target duration such as the next 8-24 hours, which is suitable for the pre-planning of bed resources and cross-departmental coordination arrangements for the next day; and long-term target duration such as the next 2-7 days, which is suitable for the periodic medical service arrangements and the configuration planning of bed capacity.

[0065] In one feasible implementation, the current number of beds occupied in each department can be used as a benchmark. The number of patients expected to be admitted within the target duration can be directly added to the current number of beds occupied, while the number of patients expected to be discharged within the target duration can be subtracted from the number of beds occupied. This yields the predicted number of beds occupied in each department after the target duration. Finally, the predicted number of beds occupied can be divided by the total number of beds in that department to obtain the first bed occupancy rate. The above method is simple to implement, has high computational efficiency, and is suitable for hospital departments with relatively regular admission and discharge processes and minimal changes.

[0066] In step S103, the bed occupancy rate refers to a quantitative assessment index that comprehensively reflects the shortage of bed resources in each department. In this embodiment, it can be understood as a departmental resource pressure coefficient calculated based on multiple dimensions of information such as the current bed occupancy status, the expected number of inpatients and discharges, and patient waiting time. It is used to quantitatively assess the occupancy rate of bed resources in each department within the target time period.

[0067] Similarly, patient waiting costs refer to the comprehensive cost losses incurred by patients due to their inability to obtain hospital bed resources in a timely manner. In this application embodiment, it can be understood as a cost indicator that is quantitatively calculated based on factors such as the urgency of the patient's condition, the length of waiting time, and the timeliness requirements of medical care, and is used to measure the degree of adverse impact that waiting for hospital admission may have on the patient's health status and treatment effect.

[0068] In one feasible implementation, the system first constructs a comprehensive evaluation matrix containing key indicators such as the current bed occupancy rate of each department, the expected number of admitted patients, the expected number of discharged patients, and the average waiting time for patients. It then calculates the importance weight of each evaluation indicator using statistical analysis methods, and finally obtains the bed occupancy level for each department based on a weighted calculation. Simultaneously, the system assigns a corresponding urgency coefficient to each patient waiting for admission according to the hospital's preset patient condition classification standards, calculates the individual waiting cost based on the patient's actual waiting time, and summarizes the overall patient waiting cost for each department.

[0069] In another feasible implementation, a dynamic threshold adjustment mechanism can be used to optimize the calculation accuracy of bed occupancy and patient waiting costs. For example, the system dynamically adjusts the weighting coefficients of each evaluation indicator and the patient urgency grading standard based on historical bed occupancy data and patient flow patterns, while also considering the impact of external factors such as holidays, special hospital events, and public health emergencies on bed demand, thus correcting the calculation results of bed occupancy and patient waiting costs in real time.

[0070] It should be noted that the calculation of bed shortage and patient waiting costs needs to fully consider the medical characteristics of each department and the characteristics of patients. Different departments differ in their medical equipment configuration, the professional competence of medical staff, and the complexity of patients' conditions, resulting in varying degrees of bed shortage and the impact of patient waiting. Therefore, in practical applications, the assessment parameters and calculation methods need to be adjusted according to the specific circumstances of each department.

[0071] In step S104, the bed optimization plan refers to a specific bed resource allocation guidance plan formed after a comprehensive analysis of the bed occupancy of each department and the patient waiting cost. In this embodiment, it can be understood as the patient bed matching and allocation results and execution sequence arrangement calculated by a multi-objective optimization algorithm.

[0072] For example, the bed optimization plan includes, but is not limited to: specific patient allocation lists and corresponding bed numbers for each department, priority ranking and time arrangement for patient admission, patient information and target departments that need to be transferred across departments, relief measures and alternative plans for departments with bed shortages, expected bed turnover time nodes and key control links, coordination and cooperation requirements for medical staff in relevant departments, risk warning and emergency response plans during the bed allocation process, etc.

[0073] In one feasible implementation, the system constructs a multi-objective optimization function aimed at minimizing bed occupancy and patient waiting costs. Constraints such as the uniqueness of patient bed allocation and departmental bed capacity are set. Mathematical optimization methods, including mixed integer programming, are used to solve for the optimal combination of patient bed allocations. The system first prioritizes departments based on their bed occupancy, allocating patients to departments with lower occupancy rates. Simultaneously, considering the impact of patient waiting costs, priority is given to patients with longer waiting times or more urgent conditions. Ultimately, this generates a bed optimization scheme that balances the overall efficiency of hospital resource allocation with the needs of patients for medical services.

[0074] In another feasible implementation, a phased optimization strategy can be adopted to improve the operability of the bed allocation plan. For example, the system divides the bed optimization process into an emergency allocation phase and a routine arrangement phase. In the emergency allocation phase, priority is given to patients with critical conditions or excessively long waiting times, quickly allocating suitable bed resources to them. In the routine arrangement phase, the bed occupancy rate of each department and the overall resource allocation efficiency are comprehensively considered to formulate a relatively long-term bed allocation plan. Furthermore, the system can establish a dynamic adjustment mechanism to correct and optimize the bed allocation plan in real time based on the actual situation and unexpected changes during the bed allocation process.

[0075] It should be noted that generating a bed optimization plan requires full consideration of the hospital's actual operational management system and medical service processes. Different hospitals differ in department setup, staffing, equipment resource distribution, and patient service standards, resulting in variations in the feasibility and constraints of bed allocation. Therefore, in practical applications, it is necessary to adjust the weight settings of the optimization objectives, the parameter configuration of the constraints, and the solution strategy of the optimization algorithm according to the specific circumstances of the hospital to ensure that the generated bed optimization plan effectively improves the utilization efficiency of bed resources.

[0076] By employing the embodiments of this application, dynamic monitoring of hospital bed resource status is achieved by acquiring bed occupancy information from multiple departments and predicting the first bed occupancy rate of each department after a target duration based on this information. This overcomes the limitations of traditional manual experience-based management, which lacks predictive capabilities. When the first bed occupancy rate is less than a threshold occupancy rate, potential problems of uneven bed resource allocation can be identified in a timely manner. By determining the bed occupancy levels and patient waiting costs across multiple departments, the differences in resource demand among departments and their impact on patient service quality are quantitatively assessed, solving the problem that traditional static allocation strategies cannot accurately measure the effectiveness of cross-departmental resource allocation.

[0077] Furthermore, bed optimization schemes generated based on bed occupancy and patient waiting costs can guide bed turnover decisions among multiple departments, enabling dynamic allocation of bed resources. This effectively alleviates the uneven resource allocation problem where some departments have bed shortages while others have idle beds, thereby improving the overall bed utilization efficiency of the hospital and the patient's medical experience.

[0078] In real-world hospital operations, simply adding or subtracting the current number of occupied beds from the estimated number of admitted and discharged patients to predict bed occupancy rates for a target duration often fails to accurately reflect the actual trends in bed resource availability. This is because hospital bed occupancy is influenced by a variety of complex factors, including peak admission and discharge patterns at different times, fluctuations in patient treatment cycles, the randomness of sudden medical events, and differences in medical service capabilities between departments. Static prediction methods lack in-depth analysis of historical data patterns, making it difficult to capture the cyclical changes and trends in bed occupancy, leading to significant discrepancies between predicted and actual results.

[0079] To address the aforementioned problems, based on the above embodiments, as an optional implementation method, step S102 may further include the following steps:

[0080] Step S201: Based on the historical bed occupancy data of multiple departments, the moving window statistical method is used to calculate the probability of bed vacancy in multiple departments after the target duration.

[0081] Step S202: Determine the first bed occupancy rate of multiple departments after the target duration based on the bed vacancy probability.

[0082] In step S201, the bed vacancy probability refers to the frequency of occurrence of beds in each department being unoccupied at a specific time point, which is obtained based on the statistical analysis of historical bed occupancy data. In this embodiment, it can be understood as the expected index of bed resource availability obtained by probabilistically modeling the bed usage of the same period in history through the moving window statistical method, which is used to quantitatively assess the likelihood of vacant beds in each department after the target duration.

[0083] In one feasible implementation, the system first extracts historical bed occupancy records for each department over consecutive time periods from the hospital information management system, establishing a historical dataset containing key information such as bed number, occupancy status, and timestamp. The system then determines the time range of the moving window based on the specific value of the target duration, typically selecting the historical time period corresponding to the target prediction time as the analysis object.

[0084] For example, if the target duration is the next 8 hours, the system selects bed occupancy records from the 8 hours preceding the same time point in historical data. The system slides a window across the historical data, extracting snapshots of bed occupancy status for each department within each window period. Statistical analysis is then used to calculate the frequency of bed vacancy events for each department. Based on the ratio of statistical frequency to the total sample size, the system calculates the probability of bed vacancy for each department after the target duration.

[0085] Optionally, the system can also employ a hierarchical moving window statistical method to improve the accuracy of bed vacancy probability calculation. Based on the time-varying characteristics of hospital operations, the system groups historical data into different categories such as weekdays and rest days, day shifts and night shifts, and regular days and holidays, and establishes corresponding moving window analysis models for different time types.

[0086] For each department, the system calculates the probability distribution of bed vacancy under different time categories and selects the appropriate probability prediction result based on the specific time type corresponding to the target duration. Simultaneously, the system considers the differences in medical service characteristics and patient flow patterns among departments, setting differentiated window sizes and statistical weights for different specialties to ensure that the calculation of bed vacancy probability better reflects the actual operational characteristics of each department.

[0087] For example, for department i, select historical data from the past N consecutive days, denoted as day k (k = 1, 2, ..., N); for each day, record the bed occupancy status in hours; denote the bed occupancy status of department i at historical time t (hours) as a binary function: If the bed in department i is vacant at time t on day k, then It is 1; conversely, it is 1. =0;

[0088] The moving window data set can then be represented as:

[0089] The probability of a hospital bed being vacant can be expressed as:

[0090]

[0091] In the formula, t represents the probability of bed vacancy in department i after the target duration; c Indicates the current time; t c +Δt represents the target duration; This represents the bed vacancy status at the predicted time on day k; N represents the length of the moving window.

[0092] In step S202, the system uses a direct conversion method to determine the first bed occupancy rate. The system calculates the difference between the bed vacancy probability of each department and the value 1 to obtain the corresponding bed occupancy probability, and then uses the bed occupancy probability as the predicted result of the first bed occupancy rate. During the conversion process, the system can also combine the total number of beds in each department to convert the probability prediction result into a specific expected number of occupied beds, and recalculate the first bed occupancy rate by dividing the expected number of occupied beds by the total number of beds in the department.

[0093] For example, the above process can be represented as:

[0094]

[0095] In the formula, This represents the predicted bed occupancy rate of department i after the target duration. This represents the probability of a bed being vacant in department i after the target duration.

[0096] By employing the embodiments of this application, the patterns and trends of bed occupancy in historical hospital data can be fully utilized, overcoming the limitations of simple numerical calculation methods that cannot reflect the periodic characteristics of bed occupancy. Through statistical analysis of the historical bed vacancy probability distribution for the same period, a scientific prediction of the future bed resource status can be achieved.

[0097] Based on the above embodiments, as an optional embodiment, the bed occupancy information also includes the patient's discharge time, which includes the patient's expected discharge time and the patient's actual discharge time. The above method may further include the following steps:

[0098] Step S301: When it is detected that the patient's actual discharge time deviates from the patient's expected discharge time, the bed vacancy probability is corrected based on the exponential decay function; the exponential decay function characterizes the degree of deviation between the patient's expected discharge time and the patient's actual discharge time.

[0099] Step S302: Determine the first bed occupancy rate of multiple departments after the target duration based on the corrected bed vacancy probability.

[0100] In step S301, the exponential decay function refers to a mathematical function that decays exponentially. It is used to describe the law that the impact of abnormal discharge events on the prediction of bed vacancy probability gradually weakens with the change of time distance. In this embodiment of the application, it can be understood as a calculation model that uses the exponential decay mechanism to quantify and control the degree of correction of the bed vacancy probability at different future times by the deviation of the patient's discharge time. This is used to ensure that the impact of abnormal events can be reasonably decayed with the increase of time distance, so as to avoid excessive interference to long-term prediction.

[0101] For example, the exponential decay function can be expressed as follows:

[0102]

[0103] In the formula, λ>0 represents the decay rate coefficient control index; γ represents the abnormal event correction intensity coefficient; Δt represents the target prediction duration; t1 represents the patient's actual discharge time; and t2 represents the patient's expected discharge time.

[0104] The core of the exponential decay function lies in its decay term, which can include the abnormal event correction intensity coefficient, the decay rate coefficient, and the time distance parameter.

[0105] Among them, the abnormal event correction intensity coefficient is used to control the maximum impact of abnormal discharge events on the correction of the bed vacancy probability. The value of this coefficient is between 0 and 1, which determines the maximum correction effect that abnormal events can produce when the time distance is zero.

[0106] The decay rate coefficient controls how fast the exponential decays. This coefficient is a positive number greater than zero. The larger the value, the faster the decay occurs, and the more rapidly the impact of the abnormal event will weaken with the increase of time distance.

[0107] The time distance parameter represents the time interval difference between the target prediction time and the current time of the abnormal discharge event. This parameter is determined by calculating the difference between the target prediction time and the actual time of the abnormal event, reflecting the relative impact of the abnormal event on different prediction times.

[0108] In step S302, the system first obtains the vacancy probability values ​​of each department's beds after being corrected by the exponential decay function, and calculates the corrected bed occupancy probability through a simple probability complementarity relationship.

[0109] In another feasible implementation, the system can also optimize the calculation process of the first bed occupancy rate by combining the specific bed configuration information of each department. The system combines the corrected bed occupancy probability with the total number of beds in each department. First, it obtains the specific number of beds to be occupied by multiplying the probability by the total number of beds. Then, it divides the expected number of beds to be occupied by the total number of beds in the department to recalculate the first bed occupancy rate, thereby better handling the discrete characteristics of the number of beds.

[0110] By employing the embodiments of this application, the limitations of static historical statistics in adapting to dynamic changes can be overcome. By timely capturing and quantifying the impact of patient discharge time deviations on bed resource status, dynamic optimization of bed vacancy probability prediction is achieved. The corrected bed vacancy probability can more accurately reflect changes in the actual availability of bed resources, thereby improving the responsiveness of the entire bed optimization and allocation system.

[0111] Based on the above embodiments, as an optional embodiment, step S103, which determines the bed occupancy rate and patient waiting costs for multiple departments, may further include the following steps:

[0112] Step S401: Construct a bed occupancy assessment matrix based on the second bed occupancy rate, the first number, the second number, and the average patient waiting time.

[0113] Step S402: Calculate the weight coefficients of each assessment indicator in the bed occupancy assessment matrix;

[0114] Step S403: Calculate the bed occupancy rate of multiple departments based on weighting coefficients;

[0115] Step S404: Determine the patient waiting cost based on the urgency coefficient of the patient's condition and the patient's waiting time in multiple departments.

[0116] In step S401, the bed occupancy assessment matrix refers to a two-dimensional data matrix constructed according to the department and indicator dimensions of multiple key indicators affecting the occupancy of bed resources in each department. In this embodiment, it can be understood as a comprehensive assessment data structure formed by systematically integrating multiple dimensions of information such as the current bed occupancy status, expected future patient flow, and service quality indicators, which is used to comprehensively reflect the bed resource status of each department in multiple assessment dimensions.

[0117] For example, the bed occupancy assessment matrix can be represented as matrix Y:

[0118]

[0119] In the formula, y I1 Indicates the occupancy rate of the second hospital bed; y I2 Indicates the first quantity; y I3Indicates the second quantity; y I4 This indicates the average waiting time for patients.

[0120] The second bed occupancy rate reflects the current actual bed usage intensity of each department. It is calculated by the ratio of the number of occupied beds to the total number of beds. The higher the value, the fewer available bed resources there are.

[0121] The first number of patients expected to be admitted within the target period reflects the future patient intake pressure of each department and the number of additional beds that the department needs to arrange within the target period.

[0122] The second number of patients expected to be discharged within the target duration reflects the bed resource release capacity of each department, indicating the number of beds that the department can free up within the target duration, and assessing the bed allocation potential from a supply perspective.

[0123] The average patient waiting time reflects the degree of matching between the supply and demand of departmental bed resources, and reflects the service efficiency and the degree of resource scarcity. Patient service quality is included in the evaluation system.

[0124] In one feasible implementation, the system collects the required data in real time through the data interface with the information management systems of various departments, obtains the bed occupancy status from the nursing workstation, extracts the admission appointment record from the appointment system, collects the discharge plan from the doctor workstation, and counts the waiting time from the bed management system. After cleaning and unifying the format of the multi-source data, it organizes it into a standardized matrix according to the department and indicator dimensions.

[0125] In step S402, the weighting coefficient refers to a numerical parameter that reflects the relative importance of each assessment indicator in the bed occupancy assessment matrix. In this embodiment, it can be understood as the contribution coefficient of each assessment indicator to the overall judgment of the ward bed occupancy calculated by objective statistical analysis methods, which is used to reasonably allocate the influence weight of each indicator in the multi-indicator comprehensive assessment process.

[0126] In one feasible implementation, the system uses the entropy weighting method to calculate the weight coefficients of each evaluation indicator. Since the four indicators in the bed occupancy assessment matrix differ in dimensions and numerical range, the system first standardizes the raw data to eliminate the influence of different dimensions. For positive indicators such as the second bed occupancy rate, the expected number of admitted patients, and the average patient waiting time, the system uses a positive standardization method, ensuring that larger values ​​indicate higher bed occupancy. For the negative indicator of the expected number of discharged patients, a negative standardization method can be used, ensuring that larger values ​​indicate more abundant bed resources. During the standardization process, the system adds very small positive numbers to the calculation results to avoid calculation errors caused by zero values ​​in subsequent logarithmic operations.

[0127] After standardization, the system calculates the weighting coefficients of each evaluation indicator using information entropy theory. First, it calculates the standardized percentage of each department on each indicator, reflecting the department's performance relative to all departments on that specific indicator. Based on the standardized percentage, the system calculates the information entropy value for each evaluation indicator. The information entropy value reflects the amount of information that indicator provides in distinguishing the bed occupancy levels between different departments. Indicators with lower information entropy values ​​indicate more significant differences between different departments, possess stronger discriminative power, and should therefore receive a higher weight in the comprehensive evaluation.

[0128] For example, the process of data standardization can be represented as follows:

[0129] Because different indicators have different dimensions and units, they need to be standardized into dimensionless indicators:

[0130] Standardized formula for positive indicators:

[0131]

[0132] Standardization formula for negative indicators:

[0133]

[0134] For example, calculate the information entropy of the j-th indicator:

[0135]

[0136] In the formula, E j p represents the information entropy of the j-th index; ij This represents the standardized percentage of the i-th department in the j-th indicator.

[0137] Calculate the weighting coefficients for each indicator:

[0138] In step S403, the bed occupancy rate of each department is weighted based on the calculated weight coefficients. The system multiplies the standardized index value of each department in the bed occupancy rate assessment matrix with the corresponding weight coefficient, and then sums the weighted results of the four indicators to obtain the comprehensive bed occupancy rate score of the department.

[0139] The bed occupancy rate directly reflects the degree of scarcity of bed resources in a department. Departments with high bed occupancy rates indicate that they are experiencing resource shortages across multiple dimensions, including current bed occupancy, expected number of admissions, expected number of discharges, and average patient waiting time. These departments require priority attention and relief during bed allocation. Conversely, departments with low bed occupancy rates indicate relatively abundant bed resources and the potential to receive patients transferred from other departments.

[0140] For example, the bed occupancy rate of each department is calculated based on weighting coefficients:

[0141]

[0142] In the formula, T i This indicates the bed occupancy rate of the i-th department; w j y′ represents the weight of the j-th indicator; ij This represents the standardized value of the j-th indicator for the i-th department.

[0143] In step S404, the system assigns a corresponding urgency coefficient to each patient waiting for admission based on the hospital's disease severity classification standards. The urgency coefficient is determined based on medical factors such as the patient's disease type, severity, and timeliness requirements for treatment, reflecting the patient's urgent need for timely hospitalization. The system multiplies the urgency coefficient by the patient's actual waiting time to calculate the waiting cost for a single patient. The patient's waiting time is determined by calculating the difference between the current time and the patient's scheduled admission time; a longer waiting time indicates a higher time cost for the patient.

[0144] The urgency coefficient is set with full consideration of the differences in patients' medical needs. For patients with critical conditions and high requirements for timely treatment, the system assigns a higher urgency coefficient, causing their waiting costs to increase more rapidly and giving them higher priority in the bed allocation process. For patients with relatively stable conditions and lower requirements for timely treatment, the system assigns a lower urgency coefficient, causing their waiting costs to increase more slowly, and allowing for appropriate postponement of their appointments when resources are scarce. This differentiated urgency coefficient setting ensures that bed allocation decisions prioritize the medical needs of critically ill patients.

[0145] In another feasible implementation, a dynamic urgency coefficient adjustment mechanism can be established to improve the accuracy of patient waiting cost calculation. The system dynamically adjusts the urgency coefficient based on changes in the patient's condition during the waiting period. For patients whose condition worsens during the waiting period, the urgency coefficient is appropriately increased; for patients whose condition remains stable, the original coefficient is maintained. Simultaneously, the system considers the differentiated impact of waiting at different times, giving higher cost weights to waiting periods such as nighttime and holidays when medical resources are relatively strained, ensuring that the waiting cost calculation accurately reflects the timeliness requirements of actual medical services.

[0146] The system aggregates and statistically analyzes the individual waiting costs of all waiting patients in each department to obtain the overall patient waiting cost for each department. The level of the overall waiting cost of a department reflects the overall waiting pressure and service quality of the patient population in that department, providing an assessment basis for bed allocation decisions from a patient service perspective. Departments with higher waiting costs need to prioritize bed resources or alleviate patient waiting pressure through inter-departmental allocation, while departments with lower waiting costs indicate that their patient service is relatively good.

[0147] For example, for patient j in department i, the formula for calculating patient waiting cost is:

[0148]

[0149] In the formula, U represents the waiting cost for patient j in department i; j t represents the urgency coefficient of patient j's condition; c Indicates the current moment; This indicates the scheduled admission time for patient j in department i.

[0150] By constructing a bed occupancy assessment matrix containing multiple key evaluation indicators, the limitations of single-indicator assessments are overcome, enabling a comprehensive quantitative analysis of bed resource status across departments. The objective weighting coefficient calculation method avoids the influence of subjective judgment bias, ensuring the accuracy of bed occupancy assessment. This achieves a coordinated balance between hospital resource allocation efficiency and patient service quality.

[0151] Based on the above embodiments, as an optional embodiment, step S104, which generates a bed optimization plan based on the bed occupancy rate and patient waiting costs of multiple departments, may further include the following steps:

[0152] Step S501: Construct the objective optimization function. The multi-objective optimization function is used to balance the bed occupancy rate and patient waiting costs in multiple departments.

[0153] Step S502: Determine the constraints of the objective optimization function, including the uniqueness constraint of patient bed allocation and the departmental bed capacity constraint.

[0154] Step S503: Solve the objective optimization function based on the constraints to obtain the bed optimization scheme.

[0155] In step S501, the objective optimization function refers to a mathematical function model established with the bed occupancy rate of multiple departments and the patient waiting cost as optimization objectives. In this embodiment, it can be understood as transforming the bed allocation problem into a computable multi-objective optimization problem through mathematical modeling, which is used to find an allocation scheme that can simultaneously balance the efficiency of hospital resource allocation and the quality of patient services under the constraint of limited bed resources.

[0156] The system first defines decision variables to represent the allocation relationship between patients and departments. These can be binary variables to explicitly express whether each patient is assigned to a bed in a specific department. When a patient is assigned to a department, the corresponding decision variable takes a value of 1, indicating that an allocation relationship has been established; when a patient is not assigned to that department, the decision variable takes a value of 0, indicating that no allocation relationship exists.

[0157] Based on the decision variables, an optimization function incorporating bed occupancy and patient waiting costs is constructed. The objective optimization function is minimized, determining the optimal bed allocation scheme by finding the combination of decision variables that minimizes the objective function value. The first term of the function focuses on the sum of bed occupancy across all departments, measuring the overall resource allocation pressure of the hospital by calculating the cumulative occupancy value of the departments corresponding to all allocated patients. When a patient is assigned to a department with high occupancy, this term increases accordingly, guiding the optimization algorithm to avoid further allocation of patients to already overloaded departments, thereby achieving a more balanced distribution of bed resource load within the hospital.

[0158] The second term of the objective optimization function focuses on the sum of patient waiting costs, reflecting the timeliness and quality of medical services by accumulating the waiting costs of all patients in their assigned departments. This term fully considers the urgency of patients' conditions and the length of their wait, assigning higher cost weights to patients with more urgent conditions or longer wait times to ensure that these patients receive priority during the optimization process. By minimizing the total patient waiting costs, the system can effectively improve the quality of patient services in hospitals, shorten the average waiting time for patients, and improve the patient experience.

[0159] In one feasible implementation, the system achieves a balance between the two optimization objectives by setting weighting coefficients. These weighting coefficients reflect the hospital management's preference for balancing the relative importance of bed resource allocation efficiency and patient service quality, and their values ​​directly influence the tendency of the optimization results. When the weighting coefficient for bed occupancy is large, the optimization algorithm tends to achieve a more balanced distribution of bed load across departments, prioritizing the allocation of patients to departments with lighter loads. When the weighting coefficient for patient waiting costs is large, the optimization algorithm focuses more on ensuring patients' timely access to medical care, prioritizing patients with longer waiting times or more urgent conditions.

[0160] For example, decision variables Indicate whether to assign patient j to department i;

[0161] Construct the objective optimization function Z, defined as:

[0162]

[0163] In the formula, the parameters α and β are weighting coefficients, satisfying α and β > 0 and α + β = 1.

[0164] In step S502, the constraint condition refers to the restrictive condition that must be met in the process of optimizing the allocation of hospital beds. In this embodiment, it can be understood as a constraint rule to ensure that the allocation plan is feasible and reasonable in the actual operation of the hospital, so as to avoid the optimization result from an unexecutable plan that violates the hospital management system or exceeds the resource carrying capacity.

[0165] Optionally, the system establishes constraints including the uniqueness constraint of patient bed allocation and the departmental bed capacity constraint.

[0166] The uniqueness constraint of patient bed allocation means that each patient can only be assigned one bed in one department within the bed allocation scheme. In this embodiment, it can be understood as a fundamental constraint to ensure that patient identities are not duplicated or omitted during the bed allocation process. This constraint reflects the basic logic of hospital bed management: a patient can only occupy one bed at a time, and it is not allowed for one patient to occupy multiple beds simultaneously or for multiple patients to share a single bed. By setting this constraint, the system ensures that each patient waiting for admission has one and only one clear bed allocation result, avoiding execution difficulties caused by ambiguous allocation relationships.

[0167] In one feasible implementation, the system achieves uniqueness in patient bed allocation by summing the allocation variables across all departments. For each patient awaiting admission, the system sums up their allocation variables across all departments, ensuring the sum does not exceed one. When the sum equals one, it indicates that the patient has been assigned to a specific department; when the sum equals zero, it indicates that the patient has not yet been assigned and will need to be reassigned in subsequent adjustments.

[0168] The departmental bed capacity constraint refers to the fact that the total number of patients allocated to each department cannot exceed the predicted number of available beds in that department after the target duration. In this embodiment, it can be understood as an upper limit constraint on the department's patient reception capacity determined based on the actual bed resources and predicted vacancy status of each department. This constraint ensures that the bed allocation scheme will not exceed the actual carrying capacity of each department, avoiding a situation where too many patients are allocated to a certain department, resulting in a bed shortage.

[0169] In one feasible implementation, the system determines the specific value of the capacity constraint by calculating the predicted number of vacant beds in a department. The predicted number of vacant beds is calculated based on the total number of beds in the department and the predicted bed occupancy rate after the target duration. The number of beds available for allocation to new patients is obtained by multiplying the total number of beds by the vacancy rate.

[0170] For example, the uniqueness constraint of patient bed allocation can be defined as:

[0171]

[0172] Departmental bed capacity constraints can be defined as:

[0173]

[0174] In step S503, mixed-integer programming can be used as the primary solution method. Mixed-integer programming effectively handles optimization problems involving integer decision variables and continuous objective functions, systematically searching for the optimal solution in the feasible solution space through branch and bound, cutting plane, and other algorithmic techniques. The system first transforms the previously constructed objective function and constraints into a standard mixed-integer programming model, clarifying the coefficient matrix of the objective function, the coefficient matrix of the constraints, and the upper and lower bounds of the variables. Then, the system calls a professional optimization solver, such as a high-performance solver engine in a commercial software package, utilizing its mature algorithm implementation and optimization strategies to calculate the optimal solution.

[0175] In another feasible implementation, considering the real-time requirements and computational resource constraints of hospital bed allocation problems, the system can also employ heuristic algorithms to quickly obtain high-quality approximate optimal solutions. Greedy algorithms are a commonly used heuristic method. The system allocates beds step-by-step based on the priority order of patient waiting costs and departmental bed occupancy, selecting the seemingly optimal allocation option at each decision step, and quickly generating feasible allocation schemes while ensuring that constraints are met. Although greedy algorithms cannot guarantee finding a globally optimal solution, their computational complexity is low, and they can provide practical allocation suggestions in a very short time, making them suitable for applications with high response time requirements.

[0176] The system can also employ metaheuristic methods such as genetic algorithms to balance solution quality and computational efficiency. Genetic algorithms simulate biological evolution, maintaining a population containing multiple candidate solutions. Through operations such as selection, crossover, and mutation, the quality of solutions in the population is continuously improved, eventually converging to a high-quality near-optimal solution. The advantages of genetic algorithms lie in their strong global search capability, making them less prone to getting trapped in local optima. Furthermore, the algorithms exhibit good parallelism, making them suitable for accelerating solutions in multi-core computing environments. The system represents the bed allocation problem as a chromosome form that can be processed by genetic algorithms by designing a suitable encoding scheme, setting appropriate evolutionary parameters and termination conditions, and searching for high-quality allocation schemes within a preset computation time.

[0177] By employing the embodiments of this application, and constructing a scientifically sound multi-objective optimization function, the limitations of traditional single-objective decision-making methods are overcome, achieving a coordinated balance between the efficiency of bed resource allocation and the quality of patient services. By establishing a comprehensive constraint system, the feasibility and rationality of the optimization results in actual hospital operations are ensured, avoiding the disconnect between theoretical optimality and practical operability, and improving the efficiency of hospital bed allocation decisions.

[0178] In actual hospital operations, traditional bed allocation methods often treat each department as an independent resource unit. Patients can only wait for beds in the specific department they have booked or been referred to, and there is no flexible cross-departmental allocation based on the actual supply and demand of beds. This rigid allocation model leads to an imbalance in resource allocation within the hospital, with some departments experiencing extreme bed shortages and long waiting lists, while other departments have a large number of vacant beds that cannot be effectively utilized.

[0179] In addition, some patients with relatively stable conditions and common treatment plans are actually medically feasible to be admitted across departments, but the relevant bed management system lacks the technical means to identify and utilize this potential for cross-departmental allocation, resulting in a significant decline in the overall bed utilization efficiency of the hospital and a deterioration in the patient's medical experience.

[0180] To address the aforementioned issues, based on the above embodiments, as an optional embodiment, the bed occupancy information also includes the number of patients moving between different departments within a target duration; step S104, which generates a bed optimization plan based on the bed occupancy levels and patient waiting costs across multiple departments, may further include the following steps:

[0181] Step S601: Adjust the objective optimization function based on the number of patients. The adjusted objective optimization function is used to balance the bed occupancy of multiple departments, patient waiting costs, and patient inter-departmental mobility costs.

[0182] Step S602, the constraints of the adjusted objective optimization function also include the feasibility constraint of patient movement across departments and the balance constraint of the number of patients moving between departments;

[0183] Step S603: Solve the adjusted multi-objective optimization function based on the constraints of the adjusted multi-objective optimization function to obtain the bed optimization scheme.

[0184] In step S601, the adjusted objective optimization function refers to a three-objective collaborative optimization mathematical model that adds the cost of patient interdepartmental mobility to the original dual-objective optimization of bed occupancy and patient waiting costs. In this embodiment, it can be understood as a comprehensive decision function that realizes the global optimization of hospital bed resources by introducing a cost quantification mechanism for interdepartmental patient allocation. It is used to take into account multiple objective requirements such as resource allocation efficiency, patient service quality and hospital operation and management convenience in the process of bed allocation.

[0185] The system adds a third term, interdepartmental mobility cost, to the original objective optimization function. This newly added third term is specifically designed to quantify and control the additional costs incurred during the process of transferring patients across departments.

[0186] In one feasible implementation, the cost of interdepartmental mobility comprises two components: patient disruption costs and additional medical costs.

[0187] Among them, patient disruption costs mainly reflect the psychological discomfort, adaptation difficulties, and communication and coordination costs that patients may experience due to being reassigned to non-appointment departments. These costs are closely related to the individual patient's adaptability, the complexity of their condition, and their sensitivity to changes in the medical environment.

[0188] Similarly, additional healthcare costs focus on the increased operational costs resulting from differences in medical procedures between departments. These include the additional training nursing staff need to receive to adapt to the nursing requirements of patients in different departments, the management costs of transferring and handing over medical records between departments, and the coordination and communication costs caused by differences in medical equipment and treatment procedures.

[0189] In one feasible implementation, the system quantifies the cost of patient disruption by establishing an individual patient characteristic assessment method. The system first extracts basic patient information from the hospital's electronic medical record system, including demographic characteristics such as age, gender, educational background, and past medical history, as well as clinical characteristics such as disease type, severity, and treatment complexity. Based on this information, the system constructs a patient adaptability assessment scale, quantifying soft indicators such as psychological resilience, environmental adaptability, and communication cooperation. For older patients, those with lower levels of education, or those hospitalized for the first time, the system assigns a higher adaptation difficulty coefficient, reflecting their sensitivity to changes in the healthcare environment; for younger patients, those with higher levels of education, or those with multiple hospitalizations, the system assigns a lower adaptation difficulty coefficient, reflecting their relatively stronger environmental adaptability.

[0190] Furthermore, for chronic disease patients with relatively stable conditions and highly standardized treatment plans, the system assumes that the psychological impact of cross-departmental transfer is relatively small, assigning a lower psychological discomfort coefficient. For patients with acute and severe conditions and complex treatment processes, due to their strong dependence on the medical environment and nursing quality, the system assigns a higher psychological discomfort coefficient, reflecting the potential adverse effects of cross-departmental transfer on their treatment confidence and emotional stability. The system calculates the final patient disruption cost by weighting the adaptation difficulty coefficient and the psychological discomfort coefficient, and combining this with the patient's waiting time in the original department.

[0191] Regarding the calculation of nursing handover communication and coordination costs, the system analyzes the degree of standardization differences between different departments in nursing operation procedures, key points of patient observation, medication management methods, and rehabilitation guidance content, and quantifies the additional learning and adaptation workload that nursing staff need to undertake when receiving patients transferred from other departments.

[0192] For departments with similar nursing standards, such as cardiology and gastroenterology within the internal medicine system, the complexity of nursing handover is relatively low, and the corresponding communication and coordination costs are small. For departments with significant differences in nursing standards, such as surgery and internal medicine, nursing staff need to adjust their nursing focus and operating habits, resulting in relatively high communication and coordination costs.

[0193] The system can also take into account the integrity requirements of information transmission during the nursing handover process, including detailed handover of patient medical history, accurate communication of medication information, and key explanations of nursing precautions, and include the time and manpower costs of this information handover work in the calculation of nursing handover communication and coordination costs.

[0194] In another feasible implementation, historical data statistical analysis can be used to quantify additional medical costs. The system extracts nursing staff training records from the hospital's human resource management system, statistically analyzes the historical frequency, duration, and cost of cross-training between different departments, and establishes a training cost prediction model based on departmental professional differences. The system categorizes hospital departments according to their medical specialties, such as internal medicine, surgery, obstetrics and gynecology, and pediatrics, and analyzes the degree of nursing skill differences between departments within the same system and between departments across systems.

[0195] For transfers within the same system, nursing staff usually have basic professional knowledge, so the additional training cost is relatively low; for transfers across systems, nursing staff need to learn entirely new professional knowledge and operational skills, which increases the additional training cost.

[0196] Furthermore, it can also statistically analyze the differences in medical record templates between different departments in the hospital's electronic medical record system, and calculate the workload required for format adjustments, content supplementation, and highlighting when converting medical record information between departments. For departments with similar medical record standards, information transmission is relatively simple and management costs are low; for departments with significant differences in medical record styles, a large amount of information processing and conversion work is required, resulting in correspondingly higher management costs.

[0197] Furthermore, dynamic balance among multiple objectives can be achieved by setting three weighting coefficients. When hospitals wish to reduce the management complexity and operational costs associated with interdepartmental transfers, they can increase the weighting coefficient of the third item, interdepartmental mobility costs, to limit unnecessary patient transfers.

[0198] For example, the adjusted objective function is defined as follows:

[0199]

[0200] In the formula, The cost of interdepartmental mobility can be defined as:

[0201]

[0202] In the formula, This represents the disruption costs incurred by patient j due to interdepartmental movement; This represents the additional medical costs incurred when patient j moves from department i to department i′.

[0203] In step S602, the system adds two cross-departmental mobility constraints to the original patient bed allocation uniqueness constraint and departmental bed capacity constraint.

[0204] The feasibility constraint for patient interdepartmental mobility ensures that all interdepartmental patient transfers must be based on pre-assessment results that conform to medical professional judgment and hospital operational management standards. The system establishes a patient interdepartmental mobility suitability assessment mechanism, comprehensively considering multiple factors such as the patient's condition characteristics, treatment needs, nursing requirements, and the medical service capacity of the target department, and assigns a feasibility rating for each patient's mobility between different departments.

[0205] In assessing patient condition characteristics, the system focuses on key medical indicators such as the specialist matching degree of the patient's disease type, the nursing needs of the severity of the condition, the standardization of the treatment plan, and the reliance on equipment during the rehabilitation process. For patients with relatively stable conditions, highly standardized treatment plans, and low reliance on specialist equipment, the system allows them to be transferred between departments with similar medical service characteristics; for example, a gastroenterology patient can be transferred to a cardiology department for treatment. For patients with complex and variable conditions, requiring special specialist treatment, and highly dependent on professional equipment, the system strictly restricts their movement between departments to ensure that patients receive the most suitable specialist medical services.

[0206] The interdepartmental patient flow balance constraint is used to prevent certain departments from experiencing medical resource strain due to excessive acceptance of patients transferred from other departments, or from resource waste due to a large outflow of patients. The system sets an upper limit threshold for the net outflow of patients for each department, and determines a reasonable range for the number of mobile patients by comprehensively considering factors such as the department's basic bed configuration, number of medical staff, medical equipment capacity, and daily medical service load.

[0207] In terms of assessing departmental capacity, the system analyzes the changing patterns of medical service load in each department over different time periods, identifying the department's patient reception potential and capacity boundaries for specific periods. For departments with relatively abundant medical resources and ample nursing staff, the system allows them to receive more patients transferred from other departments, making full use of idle medical resources. For departments whose medical load is nearing saturation and whose staffing is relatively tight, the system uses quantity balancing constraints to limit their continued acceptance of additional patients, avoiding a decline in the quality of medical services due to resource overload.

[0208] For example, the feasibility constraint for patient interdepartmental mobility can be defined as the requirement that patient interdepartmental mobility must meet the interdepartmental mobility criteria permitted by the hospital's actual operations, as shown below:

[0209]

[0210] In the formula, F ii′j Whether a patient j, pre-labeled by the hospital, is allowed to move from department i to department i′, with a value of 1 or 0.

[0211] Similarly, the interdepartmental patient flow balance constraint can be defined as the difference between the number of outflowing and inflowing patients for each department, which should satisfy the department's bed capacity constraint, as specifically expressed below:

[0212]

[0213] In the formula, This indicates the number of patients leaving department i; This indicates the number of patients flowing into department i; This indicates the net outflow of patients allowed for interdepartmental movement within department i.

[0214] Using the embodiments of this application, the system can identify and utilize the potential for bed allocation between departments, transferring patients with suitable conditions from departments with limited resources to departments with relatively abundant resources, thereby improving the overall bed utilization efficiency and patient service level of the hospital. By establishing constraints, the reliability of patient allocation in terms of medical safety and service quality is ensured, avoiding the medical risks and management chaos that may result from blind allocation.

[0215] Figure 2 This schematic diagram illustrates a structural block diagram of a hospital data-based bed turnover system provided in this application, which may include:

[0216] The acquisition module is used to acquire bed occupancy information from multiple departments;

[0217] The prediction module is used to predict the first bed occupancy rate of multiple departments after a target duration based on bed occupancy information.

[0218] The calculation module is used to determine the bed occupancy rate and patient waiting costs of multiple departments when the occupancy rate of the first bed is less than the threshold occupancy rate threshold.

[0219] The scheduling module is used to generate bed optimization plans based on the bed occupancy and patient waiting costs of multiple departments, so as to rotate beds in multiple departments according to the bed optimization plans.

[0220] Based on the above embodiments, as an optional embodiment, the calculation module is also used to construct a bed occupancy assessment matrix based on the second bed occupancy rate, the first number, the second number, and the average patient waiting time; calculate the weight coefficient of each assessment indicator in the bed occupancy assessment matrix; calculate the bed occupancy of multiple departments based on the weight coefficients; and determine the patient waiting cost based on the urgency coefficient of the patient's condition and the patient's waiting time in multiple departments.

[0221] Based on the above embodiments, as an optional embodiment, the scheduling module is also used to construct an objective optimization function, which is used to balance the bed occupancy and patient waiting costs of multiple departments; determine the constraints of the objective optimization function, including the uniqueness constraint of patient bed allocation and the department bed capacity constraint; and solve the objective optimization function based on the constraints to obtain the bed optimization scheme.

[0222] Based on the above embodiments, as an optional embodiment, the scheduling module is also used to adjust the objective optimization function based on the number of patients. The adjusted objective optimization function is used to balance the bed occupancy of multiple departments, patient waiting costs, and patient inter-departmental mobility costs. The constraints of the adjusted objective optimization function also include feasibility constraints for patient inter-departmental mobility and balance constraints for the number of patients moving between departments. The adjusted multi-objective optimization function is solved based on the constraints of the adjusted multi-objective optimization function to obtain the bed optimization scheme.

[0223] Based on the above embodiments, as an optional embodiment, the prediction module is further configured to, based on the above embodiments and as an optional embodiment, calculate the probability of bed vacancy in multiple departments after a target duration using a moving window statistical method, and determine the first bed occupancy rate of multiple departments after the target duration based on the bed vacancy probability.

[0224] Based on the above embodiments, as an optional embodiment, the prediction module is further used to correct the bed vacancy probability based on an exponential decay function when it is detected that the patient's actual discharge time deviates from the patient's expected discharge time; the exponential decay function characterizes the degree of deviation between the patient's expected discharge time and the patient's actual discharge time; and the first bed occupancy rate of multiple departments is determined according to the corrected bed vacancy probability after the target duration.

[0225] It should be noted that the hospital data-based bed turnover system part in the embodiments of this application corresponds to the hospital data-based bed turnover method part in the embodiments of this application. For a detailed description of the hospital data-based bed turnover system part, please refer to the hospital data-based bed turnover method part, which will not be repeated here.

[0226] Figure 3 The diagram illustrates a structural block diagram of an electronic device suitable for implementing the methods described above, according to an embodiment of this application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0227] like Figure 3As shown, an electronic device 300 according to an embodiment of this application includes a processor 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage portion 308 into a random access memory (RAM) 303. The processor 301 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 301 may also include onboard memory for caching purposes. The processor 301 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0228] RAM 303 stores various programs and data required for the operation of electronic device 300. Processor 301, ROM 302, and RAM 303 are interconnected via bus 304. Processor 301 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 302 and / or RAM 303. It should be noted that the programs may also be stored in one or more memories other than ROM 302 and RAM 303. Processor 301 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0229] According to embodiments of this application, the electronic device 300 may further include an input / output (I / O) interface 305, which is also connected to a bus 304. The system 300 may also include one or more of the following components connected to the input / output (I / O) interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output (I / O) interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 310 as needed so that computer programs read from it can be installed into the storage section 308 as needed.

[0230] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by processor 301, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0231] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0232] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0233] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 302 and / or RAM 303 described above and / or one or more memories other than ROM 302 and RAM 303.

[0234] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this application. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of this application.

[0235] When the computer program is executed by the processor 301, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0236] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via communication section 309, and / or installed from removable medium 311. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0237] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0238] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not expressly stated in this application. In particular, the various embodiments and / or features described in the claims of this application may be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

[0239] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this application is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this application, and all such substitutions and modifications should fall within the scope of this application.

[0240] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this application is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this application, and all such substitutions and modifications should fall within the scope of this application.

Claims

1. A bed turnover method based on hospital data, comprising: Obtain bed occupancy information from multiple departments; Based on the bed occupancy information, predict the first bed occupancy rate of multiple departments after the target duration; If the occupancy rate of the first bed is less than the threshold occupancy rate, determine the bed shortage and patient waiting cost of the multiple departments; Based on the bed occupancy rate and patient waiting costs of the multiple departments, a bed optimization plan is generated to facilitate the turnover of beds in the multiple departments according to the bed optimization plan.

2. The method according to claim 1, wherein the bed occupancy information includes the current second bed occupancy rate of the plurality of departments, the first number of patients expected to be admitted within the target duration, and the second number of patients expected to be discharged.

3. The method according to claim 2, wherein determining the bed occupancy rate and patient waiting cost of the plurality of departments includes: Based on the second bed occupancy rate, the first number, the second number, and the average patient waiting time, a bed occupancy assessment matrix is ​​constructed. Calculate the weight coefficient of each assessment indicator in the bed occupancy assessment matrix; Based on the weighting coefficients, the bed occupancy rate of the multiple departments is calculated; Based on the urgency coefficient of patients' conditions and patients' waiting time in the aforementioned departments, the patient waiting cost is determined.

4. The method according to claim 2, wherein generating a bed optimization scheme based on the bed occupancy rate and patient waiting cost of the multiple departments includes: Construct a target optimization function, which is used to balance the bed occupancy rate and patient waiting costs of the multiple departments; The constraints of the objective optimization function are determined, including the uniqueness constraint of patient bed allocation and the departmental bed capacity constraint. The objective optimization function is solved based on the constraints to obtain the optimal bed allocation scheme.

5. The method according to claim 4, wherein the bed occupancy information further includes the number of patients moving between different departments within the target duration; The objective optimization function is adjusted based on the number of patients. The adjusted objective optimization function is used to balance the bed occupancy of the multiple departments, the patient waiting cost, and the cost of patients moving between departments. The constraints of the adjusted objective optimization function also include constraints on the feasibility of patient movement across departments and the balance of the number of patients moving between departments. The adjusted multi-objective optimization function is solved based on the constraints of the adjusted multi-objective optimization function to obtain the bed optimization scheme.

6. The method according to claim 2, wherein predicting the first bed occupancy rate of multiple departments after a target duration includes: Based on the historical bed occupancy data of the multiple departments, the probability of bed vacancy in the multiple departments after the target duration is calculated using the moving window statistical method. The occupancy rate of the first bed in multiple departments is determined based on the bed vacancy probability after the target duration.

7. The method according to claim 6, wherein the bed occupancy information further includes the patient's discharge time, the patient's discharge time including the patient's expected discharge time and the patient's actual discharge time, and the method further includes: When it is detected that the patient's actual discharge time deviates from the patient's expected discharge time, the bed vacancy probability is corrected based on an exponential decay function; The exponential decay function characterizes the degree of deviation between the patient's expected discharge time and the patient's actual discharge time; The first bed occupancy rate of multiple departments is determined based on the corrected bed vacancy probability after the target duration.

8. A hospital bed turnover system based on hospital data, comprising: The acquisition module is used to acquire bed occupancy information from multiple departments; The prediction module is used to predict the first bed occupancy rate of multiple departments after a target duration based on the bed occupancy information. The calculation module is used to determine the bed occupancy rate and patient waiting cost of the multiple departments when the occupancy rate of the first bed is less than the threshold occupancy rate threshold. The scheduling module is used to generate a bed optimization plan based on the bed occupancy and patient waiting costs of the multiple departments, so as to rotate the beds of the multiple departments according to the bed optimization plan.

9. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 7.

Images