Hospital outpatient service and emergency treatment resource allocation management method

Abstract

The invention provides a hospital outpatient service and emergency treatment resource allocation management method, and relates to the technical field of hospital resource allocation. The method comprises the steps that a first information set of an emergency department is collected in real time, when patient flow data reaches a first threshold value, resource allocation strategy optimization is triggered, and emergency resource requirements in a future preset time period are predicted; an initial population containing N initial allocation schemes is generated, each allocation scheme code is a binary chromosome, a chromosome coding region is divided into an emergency treatment resource section and a common resource section, and a genetic algorithm is adopted to perform iterative optimization on the initial population to obtain an optimized resource allocation strategy; according to the method, through emergency treatment resource segment gene lock protection in the genetic algorithm, consulting room and equipment gene variation is allowed, physicians are dynamically supplemented, reservation of emergency treatment resources is ensured, meanwhile, common outpatient service resources are flexibly adjusted according to needs, resource conflicts are avoided, the dynamic response efficiency of the emergency treatment resources is improved, and a priority guarantee mechanism is provided.

Description

Technical Field

[0001] This application relates to the technical field of hospital resource allocation, and specifically relates to a method for allocating and managing outpatient and emergency resources in a hospital. Background Art

[0002] In the modern medical system, the outpatient and emergency services of a hospital are important links in ensuring the health of patients. However, the resources of a hospital are limited, and there is a certain sharing relationship between outpatient and emergency services in resource use. Therefore, a scientific method for allocating outpatient and emergency resources is needed.

[0003] In the allocation of hospital resources in the prior art, the goal is often set to maximize patient satisfaction or minimize patient waiting time, and linear programming is carried out while considering constraints such as the number of resources and the working hours of physicians. However, in the actual hospital environment, the conditions of patients are complex and diverse, the patient flow fluctuates greatly at different times, and the working efficiency of physicians is also affected by various factors. The relationships between these factors are often non-linear, which leads to the lack of responsiveness of traditional methods to sudden situations such as sudden increases in patient flow or the needs of special patients, and the poor adaptability. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, this application aims to provide a method for allocating and managing outpatient and emergency resources in a hospital to improve the adaptability of hospital resource allocation; the method includes the following steps: Collect the first information set of the emergency department in real time, where the first information set includes patient flow data, equipment usage status, and physician on-duty information; When the patient flow data reaches the first threshold, trigger the optimization of the resource allocation strategy; the optimization of the resource allocation strategy includes: Based on the first information set, predict the emergency resource requirements within a preset future period; the emergency resource requirements include the number of emergency consultation rooms required, emergency equipment requirements, and emergency physician requirements; Generate an initial population containing N initial allocation schemes, and each allocation scheme is encoded as a binary chromosome. The chromosome encoding area is divided into an emergency resource segment and a general resource segment. Among them, the emergency resource segment contains gene sequences representing the number of emergency consultation rooms, emergency equipment allocation, and emergency physician configuration, and the resource allocation amount is generated according to the predicted emergency resource requirements; Use a genetic algorithm to iteratively optimize the initial population to obtain an optimized resource allocation strategy; The use of a genetic algorithm to iteratively optimize the initial population to obtain an optimized resource allocation strategy specifically includes the following steps: Calculate the fitness of chromosomes using a fitness function, where the fitness function includes an emergency resource guarantee penalty term, and the penalty value of the emergency resource guarantee penalty term is related to the predicted value of emergency resource demand and the actual allocation value of emergency resources; Select multiple chromosomes with higher fitness as parental chromosomes, perform single-point crossover operations on the parental chromosomes, and apply gene locks to protect the emergency resource segments during the crossover process, allowing only the ordinary resource segments to exchange genes to obtain offspring chromosomes; Perform mutation operations on the offspring chromosomes, and only allow the number of emergency consultation rooms and the allocation genes of emergency equipment to mutate in the emergency resource segments; Detect whether the number of emergency physicians in the offspring chromosomes meets the dynamic minimum threshold. If not, screen out the gene positions with emergency qualifications from the physician genes in the ordinary resource segments for supplementation; Merge the parental and offspring populations, retain the N individuals with the highest fitness to continue iterative optimization, and decode the optimal chromosome to generate an optimized resource allocation strategy until the preset number of iterations is reached or the fitness value converges.

[0005] According to the technical solution provided by the present application, the emergency equipment demand is obtained from the proportion of critically ill patients; the method further includes determining the dynamic minimum threshold; The determination of the dynamic minimum threshold includes the following steps: Calculate the basic physician demand based on the proportion of critically ill patients in the emergency resource demand; Add a% of the current number of patients detained in the emergency department as a buffer value; Combine the real-time fatigue monitoring data of on-duty physicians to perform weighted correction on the basic physician demand to obtain the dynamic minimum threshold.

[0006] According to the technical solution provided by the present application, before applying gene locks to protect the emergency resource segments during the crossover process, the following steps are included: Set a protection identification bit for the gene positions of the emergency resource segments in the chromosome coding structure; the identification of the protection identification bit is 1; Applying gene locks to protect the emergency resource segments during the crossover process and only allowing the ordinary resource segments to exchange genes specifically includes the following steps: Traverse the identifications of all gene positions in the chromosome coding structure, and lock the gene positions with the identification of 1 as the emergency resource segment genes; Prohibit crossover operations on the emergency resource segment genes.

[0007] According to the technical solution provided by the present application, the execution of the emergency resource guarantee penalty term includes: when the penalty value accumulates and exceeds the second threshold, start the chromosome repair program, and this program performs the following operations: Scan the gene loci where the emergency resources do not meet the standard in the chromosome; Obtain the number of physicians with emergency qualifications in the general resource segment to determine whether it is sufficient to fill the gene loci where the emergency resources do not meet the standard; If so, call the gene of the physician with emergency qualifications in the general resource segment to fill the gene loci where the emergency resource segment does not meet the standard; if not, reallocate the equipment resources from high to low according to the equipment utilization rate.

[0008] According to the technical solution provided by the present application, the weighted correction of the basic physician demand number to obtain the dynamic minimum threshold specifically includes the following steps: Obtain the physician fatigue level, current working hours, and historical consultation efficiency according to the real-time fatigue monitoring data; Construct a three-dimensional fuzzy control rule table, and the input variables are the physician fatigue level, continuous working hours, and historical consultation efficiency; Define the output correction factor μ ∈ [G, Q]. When the physician fatigue level reaches the third-level warning, activate the forced correction instruction, and the forced correction instruction includes: If the continuous working hours are greater than or equal to the first preset duration, then lower the correction factor to G; if the historical consultation efficiency is less than the product of the first coefficient and the average value of the emergency department, then the correction factor is additionally deducted by the first deduction amount; Based on the formula: dynamic minimum threshold = basic physician demand number × (1 + a%) × μ, calculate the dynamic minimum threshold.

[0009] According to the technical solution provided by the present application, the mutation operation on the offspring chromosome specifically includes the following steps: Establish an emergency equipment mutation probability matrix P of {m × n} = ( ), indicating the mutation probability of the i-th equipment type in the j-th time slice, obtained from the formula ; where: i represents the equipment type, j represents the time slice, m represents the number of equipment types, n represents the number of time slices, α and β represent dynamic weight coefficients, α + β = 1 and α = emergency waiting number / department carrying capacity limit, represents the equipment utilization rate, represents the prediction deviation rate; When the equipment utilization rate exceeds the third threshold, trigger the anti-saturation mechanism, and the anti-saturation mechanism is to automatically shield the reduction mutation operation of this equipment type and perform associated mutation on the equipment allocation genes of adjacent time slices.

[0010] According to the technical solution provided by the present application, the protection identification bit can be dynamically updated, and the dynamic update includes: After each iteration, the emergency resource allocation gap is detected, where the emergency resource allocation gap is the difference between the emergency resource demand prediction value and the emergency resource actual allocation value; When the emergency resource configuration gap is greater than the fourth threshold, the gene lock protection range is expanded, and the expanded gene lock protection range is to add an emergency backup resource segment at the end of the chromosome code, and the initial gene position identifier is set to 1.

[0011] According to the technical solution provided by this application, after detecting the gap in emergency resource allocation, the following steps are also included: When the emergency resource allocation gap is less than the fifth threshold for n consecutive iterations, the protection range is shrunk to release the identification protection of the emergency equipment allocation gene bit and convert the emergency standby resource segment into a common resource segment.

[0012] According to the technical solution provided by this application, the following steps are also included: Retrieving a second information set of the outpatient department to construct an electronic file of the patient; the second information set includes the patient's historical medical data and nursing records, and the electronic file of the patient includes a medical timeline, a diagnosis report, a medication record, and a nursing tracking label; According to the patient electronic files, the predicted target patients who will come for treatment within the future preset period are obtained, wherein the predicted target patients are patients with unclosed nursing tasks or high-risk complications; The resource allocation strategy optimization also includes: Applying a priority weight to the gene sequence of the associated physician corresponding to the predicted target patient, wherein the weight value is the product of the success rate of similar cases in history and the load pressure coefficient of the emergency department; The fitness function is obtained by combining the priority weight and the emergency resource guarantee penalty item.

[0013] According to the technical solution provided by this application, it also includes establishing a two-way data interface between the patient side and the physician side; The establishment of a two-way data interface between the patient and the physician comprises the following steps: Establish a patient-side interface: provide an electronic file query module, which supports visual display of nursing records by timeline, and pushes the consultation time of the associated physicians and the emergency resource occupancy status described in the resource allocation strategy in real time; Establish a physician-side interface: After decoding the optimal chromosome to generate a resource allocation strategy, automatically associate the high-risk tags in the patient's electronic file in the current period to generate a dynamic reminder list, which includes unclosed nursing tasks that need to be handled first, similar case characteristics that match the current physician's historical consultation records, and equipment use conflict warnings; Bind the dynamic prompt list to the resource allocation plan in the resource allocation strategy. When device conflicts or physician overload are detected, trigger a secondary resource negotiation mechanism, and select substitute resources from the idle gene positions in the ordinary resource segment in descending order of fitness scores.

[0014] Compared with the prior art, the beneficial effects of the present application are as follows: The real-time data-driven dynamic trigger mechanism proposed in the present application enables the hospital to timely capture changes in the resource requirements of the emergency department. Especially when the patient flow surges due to emergencies, it starts to optimize the resource allocation strategy, thereby improving the response ability to emergencies; The genetic algorithm is used to iteratively optimize the initial allocation plan to better adapt to the non-linear relationship in the hospital environment. The emergency resource guarantee penalty term in the fitness function takes into account the relationship between the predicted value of emergency resource requirements and the actual configuration value. This non-linear penalty mechanism can more accurately reflect the rationality of resource allocation. It also protects the genes of the emergency resource segment through the gene lock in the genetic algorithm, allows the genes of the consultation rooms and equipment to mutate, and dynamically supplements physicians, which not only ensures the relative stability of emergency resources but also provides a certain degree of flexibility for optimizing the resource allocation plan, and can better coordinate the resource usage of outpatient and emergency departments. Brief Description of the Drawings

[0015] Figure 1 It is a step flowchart of the hospital outpatient and emergency resource allocation management method provided by the present application. Detailed Embodiments

[0016] The present application will be further described in detail below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention and are not intended to limit the invention. Additionally, it should be noted that for the convenience of description, only the parts related to the invention are shown in the drawings.

[0017] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and embodiments.

[0018] Embodiment 1 As mentioned in the background art, in response to the problems in the prior art, the present application proposes a hospital outpatient and emergency resource allocation management method, as Figure 1 shown, including the following steps: S1. Real-time collect the first information set of the emergency department, where the first information set includes patient flow data, device usage status, and physician on-duty information; Specifically, the first information set is collected in real time through the hospital information system (HIS) and Internet of Things devices. Among them, the patient flow data includes the number of emergency waiting patients, patient classification (mild / serious), and the time interval between patient arrivals. The equipment usage status includes the occupancy status and usage duration of devices such as ventilators and electrocardiogram monitors.

[0019] The information on physicians on duty includes the physician resource allocation table, current working status (idle / busy), and qualification certification (whether qualified for emergency treatment). For patient flow data, people counters can be installed at the entrance of the emergency department and in each waiting area to count the number of patients entering and waiting in real time; for the equipment usage status, status monitoring sensors are installed on each emergency device to transmit the status information such as device startup, shutdown, and failure to the system in real time; for the information on physicians on duty, it is obtained through the hospital's attendance system and physician work positioning system to ensure that it is accurately known whether each physician is on duty and their location. The above data is preprocessed by the edge computing node to filter out noise and standardize the format, and then transmitted to the central database.

[0020] S2. When the patient flow data reaches the first threshold, trigger the optimization of the resource allocation strategy; the optimization of the resource allocation strategy includes: S21. Based on the first information set, predict the emergency resource requirements within a preset future period; the emergency resource requirements include the number of emergency consultation rooms required, emergency equipment requirements, and emergency physician requirements; Specifically, when the patient flow reaches 80% of the department's carrying capacity for 3 consecutive hours, trigger the optimization of the resource allocation strategy and send a signal to the optimization module. According to the historical patient flow data, a time series model is used to predict the number of consultation rooms required; combined with the proportion of critically ill patients (such as counted through the disease grading labels in the electronic medical records), calculate the equipment requirements. For example, the number of ventilator requirements = the number of critically ill patients × 0.8 (empirical coefficient); emergency physician requirements: weighted calculation based on patient classification. For example: 。

[0021] S22. Generate an initial population containing N initial allocation plans. Each allocation plan is encoded as a binary chromosome. The chromosome encoding area is divided into an emergency resource segment and a general resource segment. Among them, the emergency resource segment contains gene sequences representing the number of emergency consultation rooms, emergency equipment allocation, and emergency physician configuration, and the resource configuration amount is generated according to the predicted emergency resource requirements; Specifically, binary encoding is used to represent the consultation room, equipment, and physician configuration. Consultation room gene bit: 4-bit binary directly represents the number of consultation rooms allocated to the emergency department (0 - 15). Equipment gene bit: Each bit corresponds to one piece of equipment. Physician gene bit: Each bit corresponds to the resource allocation status of one physician. Randomly generate N chromosomes (for example, N = 100). The initial allocation plan ensures that the configuration amount of the emergency resource segment meets 80% of the predicted requirements.

[0022] Exemplarily, the predicted emergency resource requirements are as follows: Emergency consulting rooms: It is predicted that 6 consulting rooms are needed; Emergency equipment: Suppose there are 4 types of equipment, namely electrocardiogram monitors, defibrillators, ventilators, and gastric lavage machines, and the predicted demands are 3 units, 2 units, 1 unit, and 1 unit respectively. Emergency physicians: It is predicted that 5 physicians are needed. Chromosome structure: Emergency resource segment: Consulting room gene locus: 4-bit binary directly represents the number of consulting rooms allocated to the emergency department (0 - 15). Equipment gene locus: Suppose 4 bits are used to correspond to 4 types of equipment respectively (the electrocardiogram monitor is the 1st - 1st bit, the defibrillator is the 2nd - 2nd bit, the ventilator is the 3rd - 3rd bit, and the gastric lavage machine is the 4th - 4th bit). Physician gene locus: Suppose there are a total of 8 physicians, and 8-bit binary is used to represent the resource allocation status of each physician. General resource segment: The structure is the same as that of the emergency segment. According to the requirements, the initial allocation plan ensures that the configured quantity in the emergency resource segment meets 80% of the predicted demand. Then, in the initial allocation plan (the configured quantity is rounded up), there are 5 emergency consulting rooms (the dynamic minimum threshold of emergency consulting rooms), 3 electrocardiogram monitors, 2 defibrillators, 1 ventilator, 1 gastric lavage machine (the dynamic minimum threshold of emergency equipment), and 4 emergency physicians (the dynamic minimum threshold of emergency physicians). The encoding of the emergency resource segment is: Consulting room gene locus: 4-bit binary represents the number of consulting rooms allocated to the emergency department (the value range is 0 - 15). For example, the consulting room gene locus: represents that the number of consulting rooms allocated to the emergency department is 5, and the 4-bit binary encoding is 0101 (binary 0101 corresponds to the decimal value 5), that is, 4-bit binary represents the number of consulting rooms. Equipment gene locus: 4-bit binary represents the occupancy of 4 types of equipment, and the encoding is 1111, indicating that there are equipment occupied for the electrocardiogram monitor, defibrillator, ventilator, and gastric lavage machine, meeting the equipment quantity requirements calculated above. Physician gene locus: 8-bit binary represents that 4 out of 8 physicians are resource-allocated. For example, the encoding is 11001000, indicating that the 1st, 2nd, and 5th physicians are resource-allocated; The complete encoding of the emergency resource segment is 0101111111001000. Encoding of the general resource segment: The general resource segment is randomly generated. Suppose the randomly generated encoding is: Consulting room gene locus: 0011 (indicating that the number of consulting rooms allocated to the outpatient department is 3), Equipment gene locus: 0101, Physician gene locus: 00110100, The complete encoding of the general resource segment is: 0011010100110100; The complete chromosome is obtained by combining the emergency resource segment and the general resource segment, and the complete chromosome is: 01011111110010000011010100110100; According to the above method, 100 such chromosomes are randomly generated, which constitutes an initial population containing 100 initial allocation plans.

[0023] S23. Use a genetic algorithm to iteratively optimize the initial population to obtain an optimized resource allocation strategy; Iteratively optimize the initial population using a genetic algorithm to obtain an optimized resource allocation strategy, specifically including the following steps: S231. Calculate the chromosome fitness using a fitness function, where the fitness function includes an emergency resource guarantee penalty term, and the penalty value of the emergency resource guarantee penalty term is related to the predicted value of emergency resource demand and the actual allocation value of emergency resources; Specifically, assume the predicted demand is: 6 consulting rooms, 3 electrocardiogram monitors, and 5 physicians. The emergency section configuration of chromosome 1 is: 5 consulting rooms, 3 electrocardiogram monitors, and 4 physicians. Then the penalty calculation is as follows: Penalty for consulting rooms: ; Penalty for physicians: ; Total penalty = 0.5 + 0.3 = 0.8; Fitness = 1 / (1 + 0.8) ≈ 0.555; Calculate the fitness of 100 chromosomes in this way; S232. Select multiple chromosomes with higher fitness as parent chromosomes, perform single-point crossover operations on the parent chromosomes, and apply a gene lock protection to the emergency resource section during the crossover process, allowing only the general resource section to perform gene exchange to obtain offspring chromosomes; Furthermore, before applying the gene lock protection to the emergency resource section during the crossover process, the following steps are included: Set a protection identification bit at the gene position regarding the emergency resource section in the chromosome coding structure; the identification of the protection identification bit is 1; Specifically, in the chromosome coding structure, set a protection identification bit at the gene positions representing the allocation status of each resource in the emergency resource section; specifically including: the consulting room gene position (4 bits) representing the number of emergency consulting rooms, the equipment gene position (each bit corresponding to one piece of equipment) representing the allocation status of various emergency equipment, and the physician gene position (each bit corresponding to one physician) representing the configuration status of emergency physicians. The identification of the protection identification bit is 1.

[0024] Applying the gene lock protection to the emergency resource section during the crossover process and allowing only the general resource section to perform gene exchange specifically includes the following steps: Traverse the identification of all gene positions in the chromosome coding structure, lock the gene positions with the identification of 1 as the emergency resource section genes; Prohibit crossover operations on the emergency resource section genes.

[0025] Specifically, after selecting the parent chromosomes using the tournament selection method, perform single-point crossover operations on the parent chromosomes: Exemplarily, the general section of chromosome 1: 0011010100110100 The general section of chromosome 2: 0101010001101000 The crossover point is selected after the 5th position in the normal segment (i.e., the 21st position after the end of the emergency segment): Disassembly of the normal segment of Chromosome 1: The first 5 bits "00110" + the last 11 bits "10100110100" Disassembly of the normal segment of Chromosome 2: The first 5 bits "01010" + the last 11 bits "10001101000" After crossover, the following are generated: Normal segment of Offspring 1: "01010" + "10100110100" = 0101010100101100 Normal segment of Offspring 2: "00110" + "10001101000" = 0011010001101000 Final offspring chromosomes: Offspring 1: Emergency segment of Chromosome 1 (0101111111001000) + new normal segment (0101010100101100) Offspring 2: Emergency segment of Chromosome 2 (0111111111110000) + new normal segment (0011010001101000).

[0026] S233. Perform a mutation operation on the offspring chromosomes. Only the number of emergency consultation rooms and the emergency equipment allocation genes are allowed to mutate in the emergency resource segment; Specifically, the statement that only the number of emergency consultation rooms and the emergency equipment allocation genes are allowed to mutate in the emergency resource segment means that "only the gene positions representing the number of emergency consultation rooms and the gene positions representing the emergency equipment allocation status are allowed to mutate in the emergency resource segment". The mutation range is as follows: Emergency resource segment: Only the gene for the number of consultation rooms and the equipment allocation gene are allowed to mutate. Normal resource segment: All genes can mutate. Mutation rule: Randomly flip the gene positions with a 2% probability (mutate between 0 and 1). After the consultation room gene mutates, its rationality needs to be verified (for example, if the number of consultation rooms is represented by 3-bit binary and does not exceed 8). Exemplarily, the original encoding of the emergency segment of Chromosome 1: 110111111001000 may mutate to: 111111111001000 (the consultation room gene changes from 110→111, and the number of consultation rooms changes from 5→7).

[0027] S234. Detect whether the number of emergency physicians in the offspring chromosomes meets the dynamic minimum threshold. If not, then screen the gene positions with emergency qualifications from the physician genes in the normal resource segment for supplementation; Specifically, detecting whether the number of emergency physicians in the offspring chromosomes meets the dynamic minimum threshold means "detecting whether the number of emergency physicians calculated from the gene positions representing the emergency physician configuration status in the offspring chromosomes meets the dynamic minimum threshold".

[0028] Furthermore, the execution of the emergency resource guarantee penalty item includes: when the penalty value accumulates and exceeds the second threshold, start the chromosome repair program, and this program performs the following operations: Scan the gene positions in the chromosome where the emergency resources do not meet the standards; Specifically, scan the gene positions in the chromosome where the emergency resources do not meet the standards; for the consulting room resources, it means that the value represented by the consulting room quantity gene position is less than the demand value; for the equipment and physician resources, it means that the occupied quantity or status represented by the corresponding gene position does not meet the demand.

[0029] Obtain the number of physicians with emergency qualifications in the general resource segment to determine whether it is sufficient to fill the gene positions where the emergency resources do not meet the standards; If so, call the physician genes with emergency qualifications in the general resource segment to fill the gene positions where the emergency resource segment does not meet the standards; if not, reallocate the equipment resources in descending order of equipment utilization rate.

[0030] Specifically, the second threshold is 100. If the number of emergency physicians in the offspring chromosome < the dynamic minimum threshold of emergency physicians, screen the idle physicians with emergency qualifications from the general segment. Change the corresponding gene position in the general segment from 0→1, and at the same time change the corresponding position in the emergency segment from 0→1.

[0031] S235. Combine the parent and offspring populations, retain the N individuals with the highest fitness to continue iterative optimization. When the preset number of iterations is reached or the fitness value converges, decode the optimal chromosome to generate the optimized resource allocation strategy.

[0032] Specifically, combine the parent generation (50) and the offspring generation (50) into 100 chromosomes, sort them according to fitness, and retain the first 100 individuals to enter the next generation. When the maximum number of iterations (such as 200 generations) is reached or the fitness value changes < 1% continuously for 10 generations, use the chromosome with the highest fitness as the optimal chromosome, and then decode the optimal chromosome to obtain the emergency and general outpatient resource allocation plan. This plan can quickly generate a resource allocation strategy that takes into account both efficiency and fairness when emergency resources are in short supply, effectively improve the response ability of the emergency department, make advance resource deployment for the upcoming sudden increase in emergency visits, and overcome the situation of insufficient emergency resources or excessive occupation of outpatient resources. This plan is more suitable for medium - and short - term resource scheduling (such as triggering optimization every 2 hours).

[0033] In a preferred embodiment, the emergency equipment demand is obtained from the proportion of critically ill patients; the method also includes determining the dynamic minimum threshold; The determination of the dynamic minimum threshold includes the following steps: Calculate the basic physician demand according to the proportion of critically ill patients in the emergency resource demand; Superimpose a% of the current number of patients detained in the emergency department as a buffer value; Based on the real-time fatigue monitoring data of on-duty physicians, the basic physician requirement number is weighted and corrected to obtain a dynamic minimum threshold.

[0034] Specifically, the basic physician requirement number is calculated according to the proportion of critically ill patients in the predicted emergency resource requirements. For example, it is set that 1 physician is required for every 5 critically ill patients. If it is predicted that there will be 20 critically ill patients within the next 24 hours, then the basic physician requirement number is 20÷5 = 4 physicians. Add the buffer value: Suppose the current number of patients staying in the emergency department is 30, and a% is 20%, then the buffer value is 30×20% = 6 people. According to the standard of 1 physician for every 5 patients, the number of physicians corresponding to the buffer value is 6÷5 = 1.2, which is rounded up to 2 physicians. Weighted correction to obtain the dynamic minimum threshold: Weighted correction is carried out in combination with the real-time fatigue monitoring data of on-duty physicians. The real-time fatigue monitoring data can be obtained through wearable devices. For example, a smart bracelet monitors data such as the heart rate and movement steps of physicians, and calculates the fatigue degree of physicians according to a preset algorithm. Suppose the basic physician requirement number is 4 physicians, plus the 2 physicians corresponding to the buffer value, getting 6 physicians. According to the fatigue monitoring data, the correction factor μ = 0.8 is determined, then the dynamic minimum threshold = 6×0.8 = 4.8, which is rounded up to 5 physicians.

[0035] Furthermore, the step of weighting and correcting the basic physician requirement number to obtain a dynamic minimum threshold specifically includes the following steps: Based on the real-time fatigue monitoring data, obtain the physician fatigue level, current working hours, and historical consultation efficiency; Specifically, the real-time fatigue monitoring data is obtained through a smart bracelet and the hospital information system.

[0036] Construct a three-dimensional fuzzy control rule table, and the input variables are the physician fatigue level, continuous working hours, and historical consultation efficiency; Exemplarily, the physician fatigue level is grade two, the current working hours are 8 hours, and the historical consultation efficiency is 3 patients per hour. By querying the fuzzy control rule table, the correction factor μ = 0.9 is obtained; Define the output correction factor μ∈[G, Q]. When the physician fatigue level reaches the third-level warning, activate the forced correction instruction, and the forced correction instruction includes: If the continuous working hours are greater than or equal to the first preset duration, then the correction factor is lowered to G; if the historical consultation efficiency is less than the product of the first coefficient and the average value of the emergency department, then the correction factor is additionally deducted by the first deduction amount; Exemplarily, when the physician fatigue level reaches the third - level warning, the forced correction instruction is activated. If the continuous working hours are greater than or equal to the first preset duration (e.g., 10 hours), the correction factor is lowered to G (the lower limit of the correction factor, e.g., 0.7); if the historical consultation efficiency is less than the product of the first coefficient (e.g., 0.8) and the average value of the emergency department (e.g., 4 patients are consulted per hour) (i.e., 0.8×4 = 3.2), the correction factor is additionally deducted by the first deduction amount (e.g., 0.1).

[0037] Based on the formula: dynamic minimum threshold = basic physician requirement number × (1 + a%) × μ, the dynamic minimum threshold is calculated.

[0038] Exemplarily, assume that the basic physician requirement number is 5, a% is 20%, and the correction factor μ = 0.9. Then the dynamic minimum threshold = 5×(1 + 20%)×0.9 = 5.4, and rounding up gives 6.

[0039] This embodiment fully details the impact of the specific state of individual physicians on the demand threshold. By considering the differences in individual physician states and introducing fuzzy control rules, the dynamic minimum threshold is adjusted dynamically. When the physician fatigue level is high, the continuous working hours are long, and the historical consultation efficiency is low, the fuzzy control rule table can reasonably lower the correction factor according to the preset rules, thereby increasing the dynamic minimum threshold to ensure that there are sufficient physician resources to guarantee emergency medical services.

[0040] In a preferred embodiment, the mutation operation on the offspring chromosome specifically includes the following steps: Establish an {m×n} emergency equipment mutation probability matrix P = ( ), where represents the mutation probability of the i - type equipment in the j - th time slice, and is obtained from the formula ; where: i represents the equipment type, j represents the time slice, m represents the number of equipment types, n represents the number of time slices, α and β represent dynamic weight coefficients, α + β = 1 and α = emergency waiting number / department capacity limit, represents the equipment utilization rate, represents the prediction deviation rate; Specifically, the prediction deviation rate is the error estimate that may exist in the prediction result due to factors such as data incompleteness, uncertainty, and the limitations of the prediction model itself when predicting the emergency equipment demand in the future preset time period. The dimension of the matrix P = ( ) is determined by the number of equipment types m and the number of time slices n. For example, when there are 3 types of equipment (such as ventilators, electrocardiogram monitors, defibrillators), and the time is divided into 4 time slices (for example, each time slice is 6 hours, and there are 4 time slices in a day), a Each element in the matrix Represents the probability that device type i will mutate within time slice j.

[0041] When the device usage rate exceeds a third threshold, an anti-saturation mechanism is triggered, wherein the anti-saturation mechanism automatically masks the variation reduction operation of the device type and performs associated variation on the device allocation genes of adjacent time slices.

[0042] Specifically, the anti-saturation mechanism is designed to prevent unreasonable variation of equipment under high utilization. For example, if the utilization rate of a device (such as a ventilator) exceeds 80% in the second time slice, the device will be prohibited from reducing variation in the second time slice. In other words, the device will not be allowed to have a reduced number of allocated devices in this busy time slice to ensure the normal use of emergency equipment.

[0043] At the same time, associated mutation is performed on the device allocation genes of adjacent time slices (the 1st and 3rd time slices). This is because there may be a certain correlation in the use of equipment in time. A high utilization rate of a time slice may indicate that there is a high possibility of demand for adjacent time slices. By associating mutation, the allocation of equipment can be made more reasonable in time, avoiding unreasonable allocation of equipment resources due to isolated mutation operations on each time slice. This implementation method not only dynamically adjusts the mutation probability according to the accuracy, but also triggers an anti-saturation mechanism for frequently used equipment to prevent commonly used equipment from not being allocated in place.

[0044] In a preferred embodiment, the protection flag can be dynamically updated, and the dynamic update includes: After each iteration, the emergency resource allocation gap is detected, where the emergency resource allocation gap is the difference between the emergency resource demand prediction value and the emergency resource actual allocation value; When the emergency resource configuration gap is greater than the fourth threshold, the gene lock protection range is expanded, and the expanded gene lock protection range is to add an emergency backup resource segment at the end of the chromosome code, and the initial gene position identifier is set to 1.

[0045] Furthermore, after detecting the gap in emergency resource allocation, the method further includes the following steps: When the emergency resource allocation gap is less than the fifth threshold for n consecutive iterations, the protection range is shrunk to release the identification protection of the emergency equipment allocation gene bit and convert the emergency standby resource segment into a common resource segment.

[0046] Specifically, through the dynamic adjustment of the protection scope of the gene lock, excessive fluctuations in emergency resources during the iteration process are avoided. When the resource gap is large, protection is strengthened to prevent further resource loss; while when the resource gap is small, the protection scope mechanism is contracted to appropriately relax the restrictions, making resource allocation more flexible. This balanced adjustment method helps to maintain the relative stability of emergency resource allocation and ensure the continuous operation of the emergency department.

[0047] In a preferred embodiment, the following steps are further included: Retrieve the second information set of the outpatient department to construct a patient electronic file; the second information set includes the patient's historical medical record data and nursing records, and the patient electronic file includes a medical treatment timeline, a diagnosis report, a medication record, and a nursing tracking label; Specifically, for the patient's historical medical record data: Extract the patient's historical diagnosis records, medication records, surgical records, etc. from the hospital information system (HIS), and the data format is a structured database table (such as MySQL). Nursing records: Collect real-time nursing data through a mobile nursing terminal (PDA), including wound care time, infusion completion status, vital sign monitoring records, and the data format is a JSON stream. Perform OCR recognition on unstructured nursing records (such as nurses' handwritten notes) and convert them into structured data. Use timestamps to align data from different sources to ensure the consistency of the timeline.

[0048] Based on the cloud database, construct a patient electronic file. The construction process of the cloud database is as follows: Patient unique ID: Use the medical insurance number as the primary key to associate emergency and outpatient data. Medical treatment timeline: Store all the patient's medical treatment events in chronological order (such as "2023-10-01 09:00 Admitted to the emergency department"). Diagnosis report: Store CT, MRI reports, and physicians' handwritten diagnosis books in PDF format. Medication record: Store the drug name, dosage, and medication time in JSON structure (such as {"drug": "aspirin", "dosage": "100mg", "time": "2023-10-01 10:00"}). Nursing tracking label: Automatically generate labels through natural language processing (NLP). For example: Unclosed nursing tasks: Extract uncompleted nursing items from the nursing records (such as "Postoperative drainage tube not removed"). High-risk complication label: Match the risk level based on diagnostic keywords (such as "diabetic foot", "deep vein thrombosis"). Data synchronization mechanism: Use a message queue (such as Kafka) to synchronize emergency and outpatient data to the cloud in real time to ensure that the update delay of the electronic file is less than 1 second.

[0049] According to the patient electronic file, obtain the predicted target patients who will come to seek medical treatment within the future preset time period, and the predicted target patients are those with unclosed nursing tasks or high-risk complications; Specifically, by comparing the estimated completion time of a task with the current time, it is determined whether the task is in an unclosed state. For example, if a nursing task is expected to be completed within a week, but five days have passed and it has not been marked as completed, then this task is an unclosed nursing task within the preset future period. Machine learning algorithms (such as logistic regression, decision tree, random forest, etc.) or statistical methods are used to construct a complication risk prediction model based on historical patient data. The extracted risk factors are used as input variables, and whether a complication occurs is used as the output variable to train and optimize the model. The probability of a high-risk complication occurring in each patient within the preset future period is calculated through the model, and in this way, the target patients to be predicted are obtained.

[0050] The optimization of the resource allocation strategy further includes: Applying a priority weight to the gene sequence of the associated physician corresponding to the predicted target patient, and the weight value is the product of the success rate of historical similar cases received and the load pressure coefficient of the emergency department; Combining the priority weight and the emergency resource guarantee penalty term to obtain a fitness function.

[0051] Specifically, when the optimization of the resource allocation strategy is triggered, the nursing labels of the patients visiting during the current period are retrieved from the electronic file. Calculation of the priority weight: Success rate of historical similar cases received: Extract the success rate of this physician receiving similar cases in the past year from the physician performance database (e.g., success rate = number of cured cases / total number of cases received). Load pressure coefficient of the emergency department: It is calculated in real time as the current number of waiting patients / upper limit of the department's capacity, and the value range is [0,1]. Weight value formula: Weight value = success rate × load pressure coefficient; Example: If the success rate of a certain physician receiving similar cases is 80% and the current load pressure coefficient is 0.6, then the weight value = 0.8 × 0.6 = 0.48. Update of the fitness function: The original fitness function (including the emergency resource penalty term) is extended to: Fitness value = basic fitness + ∑(priority weight) - penalty value.

[0052] Based on the dynamic optimization of the priority of the patient's electronic file, combined with the outpatient visit data, a patient file is established in this embodiment, and it is predicted whether the patients with unclosed nursing tasks or high-risk complications in the future period will come to the clinic. If they come to the clinic, the physicians associated with their situations are given high weights to solve the personalized needs of the patients.

[0053] In a preferred embodiment, it further includes establishing a two-way data interface between the patient end and the physician end; The establishment of the two-way data interface between the patient end and the physician end specifically includes the following steps: Establish a patient - side interface: Provide an electronic medical record query module. The electronic medical record query module supports visualizing nursing records along a timeline and real - time pushing the consultation time slots of the associated physicians and the emergency resource occupancy status in the resource allocation strategy. Specifically, timeline visualization: Use the ECharts library to generate an interactive timeline, supporting click events to view details. Nursing record display: Fold and display by category (such as infusion, wound care), and highlight key events (such as "post - operative infection alarm"). Real - time push: Push resource allocation strategy updates to the patient's mobile device through the WebSocket protocol.

[0054] Establish a physician - side interface: After decoding the optimal chromosome to generate a resource allocation strategy, automatically associate high - risk tags in the patient's electronic medical record during the current period, and generate a dynamic prompt list. The dynamic prompt list includes unclosed nursing tasks that need to be processed preferentially, similar case characteristics matching the current physician's historical consultation records, and equipment usage conflict warnings. Specifically, high - risk tag association: After decoding the resource allocation strategy, generate a prompt list according to the tag matching rules in the patient's electronic medical record (such as "diabetic foot → high risk in the endocrinology department"). List content: Unclosed nursing tasks: Extract unfinished items from the nursing record (such as "Patient A has not completed postoperative dressing change").

[0055] Similar case characteristics: Based on the physician's historical consultation data, match the similarity between the current patient and historical cases (such as "85% similarity with case #123 in 2022"). Equipment conflict warning: Detect equipment allocation conflicts in the resource allocation strategy (such as "the ventilator is overloaded at 14:00"). List binding and display: Embed the dynamic prompt list into the physician's workbench interface and sort it by urgency.

[0056] Bind the dynamic prompt list to the resource allocation plan in the resource allocation strategy. When detecting equipment conflicts or physician overload, trigger a secondary resource negotiation mechanism, and select substitute resources in descending order of fitness scores from the idle gene positions in the general resource segment.

[0057] Specifically, conflict detection: Equipment conflict: Detect whether the equipment allocation gene position exceeds the actual number of devices (such as the ventilator gene position is "1111" but there are actually only 3 devices). Physician overload: Judge whether the continuous working hours of the physician exceed 8 hours. Substitute resource selection: Fitness score calculation: For the idle gene positions in the general resource segment (such as unoccupied physicians or devices), calculate their fitness with the current demand: Fitness score = resource idle rate × historical utilization rate; Substitute call rule: Select resources in descending order of fitness scores (such as the highest - scoring spare ventilator is called first). Update the chromosome gene position and mark the substitute resource as occupied in the emergency segment (the gene position changes from "0" to "1").

[0058] Exemplarily, the electronic file of patient Zhang shows his "under postoperative observation" label, and the system automatically assigns a attending physician with similar surgical experience to him, improving the consultation efficiency by 30%. Dynamic prompt list: Physician Li's workbench receives a prompt: "Patient Wang's nursing task is not completed: postoperative drainage tube maintenance; equipment conflict: at 14:00, 2 ventilators are overloaded", triggering the system to automatically call the backup ventilator in the general outpatient clinic.

[0059] In this article, specific examples are used to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. The above are only the preferred implementation manners of the present application. It should be noted that due to the limited nature of written expression and the objectively infinite specific structures, for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements, retouches or changes can be made, or the above technical features can be combined in an appropriate manner; these improvements, retouches, changes or combinations, or directly applying the concept and technical solution of the invention to other occasions without improvement, shall all be regarded as the protection scope of the present application.

Claims

1. A method for hospital outpatient and emergency resource allocation management, characterized in that, It includes the following steps: Collect the first information set of the emergency department in real time, where the first information set includes patient flow data, equipment usage status, and physician on-duty information; When the patient flow data reaches the first threshold, trigger the optimization of the resource allocation strategy; The optimization of the resource allocation strategy includes: Based on the first information set, predict the emergency resource requirements within a preset future period; the emergency resource requirements include the number of emergency consultation rooms required, emergency equipment requirements, and emergency physician requirements; Generate an initial population containing N initial allocation plans, each allocation plan is encoded as a binary chromosome, and the chromosome encoding area is divided into an emergency resource segment and a general resource segment. Among them, the emergency resource segment contains gene sequences representing the number of emergency consultation rooms, emergency equipment allocation, and emergency physician configuration, and the resource allocation amount is generated according to the predicted emergency resource requirements; Use the genetic algorithm to iteratively optimize the initial population to obtain an optimized resource allocation strategy; The step of using the genetic algorithm to iteratively optimize the initial population to obtain an optimized resource allocation strategy specifically includes the following steps: Calculate the chromosome fitness with a fitness function, and the fitness function includes an emergency resource guarantee penalty term, and the penalty value of the emergency resource guarantee penalty term is related to the predicted value of the emergency resource requirements and the actual allocation value of the emergency resources; Select multiple chromosomes with higher fitness as the parent chromosomes, perform a single-point crossover operation on the parent chromosomes, and apply a gene lock protection to the emergency resource segment during the crossover process, and only allow the general resource segment to perform gene exchange to obtain the offspring chromosomes; Perform a mutation operation on the offspring chromosomes, and only allow the mutated number of emergency consultation rooms and emergency equipment allocation genes in the emergency resource segment; Detect whether the number of emergency physicians in the offspring chromosomes meets the dynamic minimum threshold. If not, screen out the gene positions with emergency qualifications from the physician genes in the general resource segment for supplementation; Merge the parent and offspring populations, retain the N individuals with the highest fitness and continue to perform iterative optimization until the preset number of iterations or the fitness value converges, and decode the optimal chromosome to generate an optimized resource allocation strategy.

2. The hospital outpatient and emergency resource allocation management method according to claim 1, wherein, The emergency equipment requirements are obtained from the proportion of critically ill patients; the method also includes determining the dynamic minimum threshold; The determination of the dynamic minimum threshold includes the following steps: According to the proportion of critically ill patients in the emergency resource requirements, calculate the basic physician requirement number; Superimpose a% of the current number of patients detained in the emergency department as a buffer value; Combined with the real-time fatigue monitoring data of the on-duty physicians, perform weighted correction on the basic physician requirement number to obtain the dynamic minimum threshold.

3. The hospital outpatient and emergency resource allocation management method according to claim 1, characterized in that Before applying the gene lock protection to the emergency resource segment during the crossover process, it includes the following steps: Set a protection identification bit for the gene positions of the emergency resource segment in the chromosome encoding structure; the identification of the protection identification bit is 1; Applying the gene lock protection to the emergency resource segment during the crossover process and only allowing the general resource segment to perform gene exchange specifically includes the following steps: Traverse the identifications of all gene positions in the chromosome encoding structure, and lock the gene positions with the identification of 1 as the emergency resource segment genes; Prohibit crossover operations on the emergency resource segment genes.

4. The hospital outpatient and emergency resource allocation management method according to claim 1, wherein The execution of the emergency resource guarantee penalty item includes: when the penalty value exceeds the second threshold, starting the chromosome repair program, which performs the following operations: Scanning chromosomes for loci where emergency resources are not met; Obtaining the number of physicians with emergency qualifications in the general resource segment to determine whether it is sufficient to fill the gene position where emergency resources do not meet the standards; If so, call the gene of the physician with emergency qualification in the general resource segment to fill the gene position that does not meet the standard in the emergency resource segment; if not, reallocate the equipment resources from high to low according to the equipment utilization rate.

5. The hospital outpatient and emergency resource allocation management method according to claim 2, characterized in that, The weighted correction of the number of basic physician requirements to obtain a dynamic minimum threshold specifically includes the following steps: According to the real-time fatigue monitoring data, the physician's fatigue level, current working hours, and historical reception efficiency are obtained; A three-dimensional fuzzy control rule table was constructed, with the input variables being the physician's fatigue level, continuous working hours, and historical reception efficiency; Define an output correction factor μ∈[G, Q], when the physician fatigue level reaches the third alert level, activate the mandatory correction instruction, the mandatory correction instruction includes: If the continuous working time is greater than or equal to the first preset time, the correction factor is lowered to G; if the historical reception efficiency is less than the product of the first coefficient and the average value of the emergency department, the correction factor is additionally deducted by the first deduction amount; Based on the formula: dynamic minimum threshold = number of basic physician requirements × (1 + a%) × μ, the dynamic minimum threshold is calculated.

6. The hospital outpatient and emergency resource allocation management method according to claim 3, wherein The mutation operation on the offspring chromosome specifically comprises the following steps: Establish an emergency equipment mutation probability matrix \(P\) of \(\{m\times n\}=( )\), where \(p_{ij}\) represents the mutation probability of the \(i\)-th equipment type within the \(j\)-th time slice, and is obtained by the formula ; Where: i represents the device type, j represents the time slice, m represents the number of device types, n represents the number of time slices, α and β represent dynamic weight coefficients, α + β = 1 and α = the number of emergency patients waiting / the upper limit of the department's capacity, represents the device utilization rate, represents the prediction deviation rate; When the device usage rate exceeds a third threshold, an anti-saturation mechanism is triggered, wherein the anti-saturation mechanism automatically masks the variation reduction operation of the device type and performs associated variation on the device allocation genes of adjacent time slices.

7. The hospital outpatient and emergency resource allocation management method according to claim 3, wherein The protection flag can be dynamically updated, and the dynamic update includes: After each iteration, the emergency resource allocation gap is detected, where the emergency resource allocation gap is the difference between the emergency resource demand prediction value and the emergency resource actual allocation value; When the emergency resource configuration gap is greater than the fourth threshold, the gene lock protection range is expanded, and the expanded gene lock protection range is to add an emergency backup resource segment at the end of the chromosome code, and the initial gene position identifier is set to 1.

8. The hospital outpatient and emergency resource allocation management method according to claim 7, wherein After detecting the gap in emergency resource allocation, the following steps are also included: When the emergency resource allocation gap is less than the fifth threshold for n consecutive iterations, the protection range is shrunk to release the identification protection of the emergency equipment allocation gene bit and convert the emergency standby resource segment into a common resource segment.

9. The hospital outpatient and emergency resource allocation management method according to claim 1, wherein The following steps are also included: Retrieving a second information set of the outpatient department to construct an electronic file of the patient; the second information set includes the patient's historical medical data and nursing records, and the electronic file of the patient includes a medical timeline, a diagnosis report, a medication record, and a nursing tracking label; According to the patient electronic files, the predicted target patients who will come for treatment within the preset time period in the future are obtained, wherein the predicted target patients are patients with unclosed nursing tasks or high-risk complications; The resource allocation strategy optimization also includes: Apply a priority weight to the gene sequence of the associated physician corresponding to the predicted target patient, and the weight value is the product of the success rate of similar cases received historically and the emergency department load pressure coefficient; Combine the priority weight and the emergency resource guarantee penalty term to obtain a fitness function.

10. The hospital outpatient and emergency resource allocation management method according to claim 9, characterized in that, It also includes establishing a two-way data interface between the patient side and the physician side; The establishment of the two-way data interface between the patient side and the physician side specifically includes the following steps: Establish a patient-side interface: Provide an electronic file query module, which supports visual display of nursing records according to the time axis and real-time push of the reception time period of the associated physician and the emergency resource occupancy status in the resource allocation strategy; Establish a physician-side interface: After decoding the optimal chromosome to generate a resource allocation strategy, automatically associate the high-risk tags in the patient's electronic file during the current period to generate a dynamic prompt list, and the dynamic prompt list includes unclosed nursing tasks that need to be processed first, similar case characteristics matching the physician's historical reception records, and equipment usage conflict warnings; Bind the dynamic prompt list to the resource allocation plan in the resource allocation strategy. When a device conflict or physician overload is detected, trigger a secondary resource negotiation mechanism to select substitute resources from the idle gene positions in the ordinary resource segment in descending order of fitness score.

Images