Old people accompanying doctor scheduling optimization method considering uncertainty of doctor seeing time

Abstract

The embodiment of the invention provides an old people accompanying doctor scheduling optimization method considering the uncertainty of doctor seeing time, and belongs to the technical field of accompanying doctor scheduling. The optimization method comprises the following steps: acquiring elderly accompanying diagnosis demand information, accompanying diagnosis person information and hospital information; acquiring an initial population according to the accompanying diagnosis demand information, the accompanying diagnosis person information and the hospital information; and searching an optimal solution under the condition of the highest scheduling efficiency by adopting an Archimedes optimization algorithm according to the initial population. According to the scheduling optimization method, a target optimization model with the highest search scheduling efficiency and considering the uncertainty of the doctor seeing time is established aiming at the scheduling problem of the elderly doctor accompanying personnel. On the basis of a standard Archimedes optimization algorithm, an initial population is mapped by using Chebyshev, and a Levy flight guidance strategy is used to improve the local optimization ability of the algorithm, and the proposed improved Archimedes optimization algorithm can effectively solve the problem of accompanying doctor scheduling under the condition of aggregation and distribution of old people.

Description

Technical Field

[0001] The present invention relates to the technical field of accompanying patient scheduling, and in particular to a scheduling optimization method for elderly patient accompanying personnel taking into account the uncertainty of consultation time. Background Art

[0002] At present, my country's elderly population is huge and aging is rapid, which has become an important phenomenon that cannot be ignored in social development. Among the many challenges brought about by aging, the unbalanced and insufficient development of the elderly cause and elderly care services is particularly prominent. During the "14th Five-Year Plan" period, the aging of my country's population will further deepen, and the proportion of people aged 60 and above will exceed 20% of the total population, officially entering a moderately aging society. This means that the pressure on elderly care services will continue to increase, and the elderly's demand for the quality of elderly care services will also show an upward trend.

[0003] However, the current elderly care services are facing the dilemma of mismatch between supply and demand. On the one hand, the number of elderly people is increasing, and the demand for elderly care services is becoming increasingly diversified; on the other hand, the supply of elderly care services has not kept up in time and cannot meet the actual needs of the elderly. At the same time, the imperfect guarantee mechanism also makes it difficult for the elderly to effectively guarantee their elderly care service needs. In terms of medical care, the elderly group's demand for medical-friendly services and medical resources is constantly increasing. With the introduction of a series of policies and the rapid development of Internet technology, outpatient appointment services have been widely promoted and gradually improved across the country. Appointment registration services have become an important entry point for hospitals to improve the efficiency of outpatient resource utilization and solve outpatient service problems. In order to meet this demand, the intensity and breadth of medical adaptation for the elderly have continued to increase, and many places have actively carried out activities to create elderly-friendly medical institutions. Despite this, the personalized medical needs of the elderly have not been fully met, and there is still a lot of room for improvement. Summary of the invention

[0004] The purpose of the embodiment of the present invention is to provide an optimization method for scheduling elderly medical attendants taking into account the uncertainty of medical appointment time. The optimization method aims at the scheduling problem of elderly medical attendants and establishes a target optimization model with the highest search scheduling efficiency taking into account the uncertainty of medical appointment time. On the basis of the standard Archimedean optimization algorithm, the initial population of Chebyshev mapping is used, and the Levy flight guidance strategy is used to improve the local optimization ability of the algorithm. The proposed improved Archimedean optimization algorithm can effectively solve the scheduling problem of medical attendants under the condition of clustered distribution of the elderly.

[0005] In order to achieve the above object, an embodiment of the present invention provides a scheduling optimization method for elderly patients' companions considering the uncertainty of consultation time, comprising:

[0006] Obtain information on the elderly's need for medical companionship, medical companion information, and hospital information;

[0007] Acquire an initial population according to the accompanying medical consultation demand information, accompanying medical consultation personnel information and hospital information;

[0008] According to the initial population, the Archimedean optimization algorithm is used to search for the optimal solution with the highest scheduling efficiency, wherein the fitness function of the Archimedean optimization algorithm is the following formula (1) to formula (6):

[0009] f=min(TC+LC+PC), (1)

[0010] Among them, f is the fitness value, TC is the total driving cost, LC is the cost of accompanying the patient during the consultation, and PC is the penalty cost for the accompanying person not serving within the service time window for the elderly.

[0011]

[0012] Where n is the total number of elderly people, i and j are the elderly numbers, h is the hospital number, z is the total number of hospitals, m is the total number of accompanying personnel, M is the type of accompanying service, k is the number of accompanying personnel, s is the number of accompanying service type, c is the travel cost per unit time, T ij T is the travel time required for the accompanying person to travel from elderly person i to elderly person j, hi is the one-way travel time required for the accompanying person to travel from the elderly person's location i to the hospital's location h, The time that the accompanying personnel spend with the elderly in the hospital, p ks is the unit time service cost of accompanying service s, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i, e i is the start time of the service window for the elderly, TS ik is the time when the accompanying staff k starts to serve the elderly i, σ is the penalty coefficient, which is used to calculate the penalty cost of serving earlier than the time window, and is a fixed constant, d ij is the distance between elderly i and elderly j, x ijks is the decision variable used to determine whether the companion k provides services to another elderly person j after the elderly person i, v is the driving speed, d hi is the distance between elderly person i and hospital h, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i.

[0013] Optionally, obtaining an initial population according to the accompanying medical consultation requirement information, the accompanying medical consultation personnel information and the hospital information includes:

[0014] According to formula (7) and formula (16), the constraints of the population are determined.

[0015]

[0016] x ijks ={0,1},(15)

[0017] y iks ={0,1},(16)

[0018] Among them, TS jk is the time it takes for the accompanying person k to arrive at the elderly person j, x ieks The number of times the accompanying attendant k leaves the elderly person i to serve the next elderly person, x ejks is the number of times that the accompanying attendant k leaves the last elderly person and comes to serve the elderly person j, e is the elderly person's number, l is i The latest time of the service window for the elderly, x jiks is a decision variable used to determine whether the attendant k provides services to another elderly person j after the elderly person i, x 0jks is the decision variable, which determines the number of times the accompanying attendant k leaves the accompanying service center, x j0ks is the decision variable, determining the number of times the patient escort k returns to the accompanying service center, T k setting working hours for nursing staff;

[0019] The initial population is generated by using Chebyshev chaotic mapping.

[0020] Optionally, the initial population is generated by using Chebyshev chaotic mapping, including:

[0021] Initialize the population according to formula (17):

[0022] x i+1 =cos(a×cos -1 x i ),a=8,x∈[-1,1], (17)

[0023] Among them, x i+1 is the population generated by the i-th generation population through the Chebyshev chaotic map, a is the order of the Chebyshev chaotic map, x i is the i-th generation population.

[0024] Optionally, the Archimedean optimization algorithm includes:

[0025] Obtaining the initial population;

[0026] Calculating the fitness value of each individual in the population respectively;

[0027] Selecting the best individual in the population according to the fitness value;

[0028] Iterate and update other individuals in the population according to the optimal individual;

[0029] Update the number of iterations;

[0030] Determine whether the number of iterations of the current population is greater than or equal to an iteration threshold;

[0031] When it is determined that the number of iterations of the current population is greater than or equal to the iteration threshold, outputting a global optimal solution;

[0032] When it is determined that the current number of iterations of the population is less than the iteration threshold, return to the step of respectively calculating the fitness value of each individual in the population.

[0033] Optionally, updating and iterating other individuals in the population according to the optimal individual includes:

[0034] Obtain the migration operator of the current population;

[0035] Obtaining an adaptive feedback adjustment factor of the current population;

[0036] Determine whether the current migration operator is less than or equal to 0.5;

[0037] When it is determined that the current migration operator is less than or equal to 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (21).

[0038]

[0039]

[0040] in, is the density of the i-th individual in the t+1th iteration, is the density of the i-th individual in the t-th iteration, rand is a random number between 0 and 1, and den best is the density of the optimal individual in the current iteration number, is the volume of the i-th individual in the t+1th iteration, is the volume of the i-th individual in the t-th iteration, vol best is the volume of the optimal individual in the current iteration number, is the acceleration of the ith individual in the t+1th iteration, den mr is the density of individuals randomly selected in the current iteration, vol mr is the volume of the randomly selected individual in the current iteration, acc mr is the acceleration of the randomly selected individual in the current iteration;

[0041] According to formula (23), the acceleration of other individuals is normalized.

[0042]

[0043] in, is the normalized acceleration of the ith individual in the t+1 iteration, u is the upper limit of acceleration, l is the lower limit of acceleration, min(acc) is the minimum acceleration of the individual, and max(acc) is the maximum acceleration of the individual;

[0044] According to formula (24), the position of the individual is updated.

[0045]

[0046] in, is the position of the i-th individual in the t+1 iteration, is the position of the i-th individual in the t-th iteration, C1 is a fixed constant, d is the density factor, x rand is the position of the random individual in the current iteration;

[0047] When it is determined that the current migration operator is greater than 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (22).

[0048]

[0049] Among them, acc best is the acceleration of the best individual in the current iteration;

[0050] The acceleration of other individuals is normalized according to formula (23);

[0051] The individual position is updated according to formula (25) to formula (28),

[0052]

[0053] T=C3×TF,T∈[C3×0.3,1], (26)

[0054]

[0055] P = 2 × rand - C4, (28)

[0056] Among them, F is the direction factor, TF is the migration operator, C2 is a fixed constant, T is the calculation factor, x best is the position of the best individual in the current iteration, C3 is a fixed constant, P is the judgment calculation factor that determines the update direction of the iteration position, and C4 is a fixed constant.

[0057] Optionally, obtaining a migration operator of the current population includes:

[0058] According to formula (18), the migration operator of the current population is obtained:

[0059]

[0060] Among them, t max is the maximum number of iterations, and t is the current number of iterations.

[0061] Optionally, obtaining the adaptive feedback adjustment factor of the current population includes:

[0062] According to formula (29), the success value of individuals in the current population is determined:

[0063]

[0064] Among them, S(i,t) is the success value of the i-th individual in the current population in the t-th iteration, is the historical optimal position of individual i at the tth iteration, is the historical optimal position of individual i at the t+1th iteration;

[0065] According to formula (30), the success rate of the current population is determined.

[0066]

[0067] Among them, P s (t) is the success rate of the population in the tth iteration, and N is the population size;

[0068] According to formula (31), the normalized fitness coefficient of the individual is determined:

[0069]

[0070] Among them, F i is the normalized fitness coefficient of the ith individual, f(X i ) is the individual fitness value of the i-th generation population, f min is the minimum fitness value of the individual, and ε is a very small rational number;

[0071] Determine the adaptive feedback adjustment factor according to formula (32):

[0072]

[0073] in, is the adaptive feedback adjustment factor of the i-th generation population, α is the importance coefficient of the population evolution success rate, and β is the normalized fitness coefficient F of the i-th individual i The importance coefficient of .

[0074] Optionally, selecting the best individual in the population according to the fitness value further includes:

[0075] According to formula (33) and formula (34), the individual selection probability is calculated.

[0076]

[0077] Among them, p i is the selection probability, f i is the fitness value of the i-th individual, fit i is the calculation factor;

[0078] According to the selection probability and formula (35) to formula (37), other individuals in the current population are subjected to Levy flight guidance operation.

[0079]

[0080] Among them, s is the rotation factor, R r is a random matrix, μ and v follow a normal distribution,

[0081] Through the above technical scheme, the present invention provides a scheduling optimization method for elderly medical escorts considering the uncertainty of medical consultation time, by obtaining the elderly medical escort demand information, medical escort information and hospital information, obtaining the initial population according to the acquired medical escort demand information, medical escort information and hospital information, and using the Archimedes optimization algorithm to search for the optimal solution with the highest scheduling efficiency according to the initial population. The scheduling optimization method aims at the scheduling problem of elderly medical escorts, and establishes a target optimization model with the highest search scheduling efficiency considering the uncertainty of medical consultation time. On the basis of the standard Archimedes optimization algorithm, the Chebyshev mapping initial population is used, and the Levy flight guidance strategy is used to improve the algorithm's local optimization ability. The proposed improved Archimedes optimization algorithm can effectively solve the scheduling problem of medical escorts under the condition of clustered distribution of the elderly.

[0082] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0084] Figure 1 It is a flow chart of a method for optimizing scheduling of elderly medical companions according to an embodiment of the present invention;

[0085] Figure 2is a flowchart of obtaining an initial population according to an embodiment of the present invention;

[0086] Figure 3 It is a flow chart of obtaining the optimal solution by using Archimedean optimization algorithm in one embodiment of the present invention;

[0087] Figure 4 It is a flowchart of other individuals in the update iteration population according to one embodiment of the present invention;

[0088] Figure 5 It is a flow chart of obtaining an adaptive feedback adjustment factor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0089] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0090] like Figure 1 The figure is a flow chart of a method for optimizing the scheduling of elderly medical attendants according to an embodiment of the present invention. Figure 1 In the above, the scheduling optimization method may include:

[0091] In step S10, the elderly's medical companionship requirement information, medical companion information and hospital information are obtained;

[0092] In step S20, an initial population is obtained according to the accompanying medical consultation requirement information, the accompanying medical consultation personnel information and the hospital information;

[0093] In step S30, the Archimedes optimization algorithm is used to search for the optimal solution with the highest scheduling efficiency according to the initial population, wherein the fitness function of the Archimedes optimization algorithm is the following formula (1) to formula (6):

[0094] f=min(TC+LC+PC), (1)

[0095] Among them, f is the fitness value, TC is the total driving cost, LC is the cost of accompanying the patient during the consultation, and PC is the penalty cost for the accompanying person not serving within the service time window for the elderly.

[0096]

[0097]

[0098] Where n is the total number of elderly people, i and j are the elderly numbers, h is the hospital number, z is the total number of hospitals, m is the total number of accompanying personnel, M is the type of accompanying service, k is the number of accompanying personnel, s is the number of accompanying service type, c is the travel cost per unit time, T ijT is the travel time required for the accompanying person to travel from elderly person i to elderly person j, hi is the one-way travel time required for the accompanying person to travel from the elderly person's location i to the hospital's location h, The time that the accompanying personnel spend with the elderly in the hospital, p xs is the unit time service cost of accompanying service s, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i, e i is the start time of the service window for the elderly, TS ik is the time when the accompanying staff k starts to serve the elderly i, σ is the penalty coefficient, which is used to calculate the penalty cost of serving earlier than the time window, and is a fixed constant, d ij is the distance between elderly i and elderly j, x ijks is the decision variable used to determine whether the companion k provides services to another elderly person j after the elderly person i, v is the driving speed, d hi is the distance between elderly person i and hospital h, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i.

[0099] In step S10 to step S30, by obtaining the information on the need for accompanying the elderly, the information on the accompanying staff and the hospital, the initial population is obtained according to the acquired information on the need for accompanying the elderly, the information on the accompanying staff and the hospital, and the Archimedes optimization algorithm is used to search for the optimal solution with the highest scheduling efficiency according to the initial population. This scheduling optimization method aims at the scheduling problem of accompanying staff for the elderly, and establishes a target optimization model with the highest search scheduling efficiency considering the uncertainty of the consultation time. On the basis of the standard Archimedes optimization algorithm, the Chebyshev mapping initial population is used, and the Levy flight guidance strategy is used to improve the algorithm's local optimization ability. The proposed improved Archimedes optimization algorithm can effectively solve the scheduling problem of accompanying staff under the condition of clustered distribution of the elderly.

[0100] In this Figure 1 In the method shown, step S10 can be used to obtain the elderly's medical companionship demand information, medical companion information and hospital information. Step S20 can be used to obtain the initial population based on the medical companionship demand information, medical companion information and hospital information. The specific method for obtaining the initial population can be various forms known to those skilled in the art. In one example of the present invention, the method for obtaining the initial population may include: Figure 2 The steps shown. Specifically:

[0101] In step S11, the constraints of the population are determined according to formula (7) and formula (16):

[0102]

[0103] TS ik ≤l i ,i∈[1,n],k∈[1,m],(10)

[0104]

[0105] x ijks ={0,1},(15)

[0106] y iks ={0,1},(16)

[0107] Among them, TS jk is the time it takes for the accompanying person k to arrive at the elderly person j, x ieks The number of times the accompanying attendant k leaves the elderly person i to serve the next elderly person, x ejks is the number of times that the accompanying attendant k leaves the last elderly person and comes to serve the elderly person j, e is the elderly person's number, l is i The latest time of the service window for the elderly, x jiks is a decision variable used to determine whether the attendant k provides services to another elderly person j after the elderly person i, x 0jks is the decision variable, which determines the number of times the medical escort k leaves the medical escort service center, x j0ks is the decision variable, determining the number of times the patient escort k returns to the accompanying service center, T k setting working hours for nursing staff;

[0108] In step S12, the initial population is generated using Chebyshev chaotic mapping.

[0109] In this Figure 2 In the method shown, step S11 can be used to determine the constraints of the population according to formula (7) and formula (16), where formula (7) represents the time when the accompanying person k arrives at the elderly j, and formula (8) represents that each elderly person can be served and one elderly person is accompanied by one accompanying person only once; formula (9) represents that if the elderly i and j are on the service path of the nursing person k, the elderly i and j are served by the nursing person k, and the accompanying person must leave after serving the elderly; formula (10) represents that the accompanying person k must start serving before the latest service time of the elderly i to ensure that the medical service is completed within the working hours of the hospital; formulas (11) to (13) represent that each accompanying person starts from the accompanying service center, returns to the accompanying service center after serving a number of elderly people, and the number of service paths for each accompanying person shall not exceed one; formula (14) represents that the working time of the accompanying person is guaranteed not to exceed the maximum working time; formulas (15) and (16) define decision variables.

[0110] Step S12 can be used to generate an initial population using Chebyshev chaotic mapping. Slight differences in the initial population in the solution space may affect the evolution direction of the algorithm and ultimately produce completely different final results. In the initialization stage, the Archimedean algorithm is susceptible to random interference and aggregation. In this embodiment, the specific method for generating the initial population can be a variety of forms known to those skilled in the art. In one example of the present invention, a Chebyshev chaotic mapping can be used to generate the initial population to improve the algorithm's traversal ability in the solution space and map it to the solution space, so that the population has better dispersion in the search space, which is conducive to better exploration of the search space and avoids premature convergence to the local optimal solution. Specifically, the population is initialized according to formula (17),

[0111] x i+1 =cos(a×cos -1 x i ),a=8,x∈[-1,1], (17)

[0112] Among them, x i+1 is the population generated by the i-th generation population through the Chebyshev chaotic map, a is the order of the Chebyshev chaotic map, x i is the i-th generation population.

[0113] Step S30 may be used to search for the optimal solution with the highest scheduling efficiency using the Archimedes optimization algorithm according to the initial population. The specific method of using the Archimedes algorithm to obtain the optimal solution may be in various forms known to those skilled in the art. In one example of the present invention, the Archimedes algorithm may include: Figure 4 The steps shown. Specifically:

[0114] In step S21, an initial population is obtained;

[0115] In step S22, the fitness value of each individual in the population is calculated respectively;

[0116] In step S23, the best individual in the population is selected according to the fitness value;

[0117] In step S24, other individuals in the iterative population are updated according to the optimal individual;

[0118] In step S25, the number of iterations is updated;

[0119] In step S26, it is determined whether the number of iterations of the current population is greater than or equal to the iteration threshold;

[0120] In step S27, when it is determined that the number of iterations of the current population is greater than or equal to the iteration threshold, the global optimal solution is output;

[0121] In step S28, when it is determined that the number of iterations of the current population is less than the iteration threshold, the process returns to the step of calculating the fitness value of each individual in the population.

[0122] In this Figure 4 In the method shown, step S21 can be used to obtain an initial population. Step S22 can be used to calculate the fitness value of each individual in the population. Step S23 can be used to select the best individual in the population according to the fitness value. Step S24 can be used to update other individuals in the iterative population according to the best individual. The specific method for updating other individuals in the iterative population can be in various forms known to those skilled in the art. In one example of the present invention, the method for updating other individuals in the iterative population can include: Figure 4 The steps shown. Specifically:

[0123] In step S31, the migration operator of the current population is obtained;

[0124] In step S32, the adaptive feedback adjustment factor of the current population is obtained;

[0125] In step S33, it is determined whether the current migration operator is less than or equal to 0.5;

[0126] In step S34, when it is determined that the current migration operator is less than or equal to 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (21).

[0127]

[0128]

[0129] in, is the density of the i-th individual in the t+1th iteration, is the density of the i-th individual in the t-th iteration, rand is a random number between 0 and 1, and den best is the density of the optimal individual in the current iteration number, is the volume of the i-th individual in the t+1th iteration, is the volume of the i-th individual in the t-th iteration, vol best is the volume of the optimal individual in the current iteration number, is the acceleration of the ith individual in the t+1th iteration, den mr is the density of individuals randomly selected in the current iteration, vol mr is the volume of the randomly selected individual in the current iteration, acc mr is the acceleration of the randomly selected individual in the current iteration;

[0130] In step S35, the acceleration of other individuals is normalized according to formula (23):

[0131]

[0132] in, is the normalized acceleration of the ith individual in the t+1 iteration, u is the upper limit of acceleration, l is the lower limit of acceleration, min(acc) is the minimum acceleration of the individual, and max(acc) is the maximum acceleration of the individual;

[0133] In step S36, the position of the individual is updated according to formula (24):

[0134]

[0135] in, is the position of the i-th individual in the t+1 iteration, is the position of the i-th individual in the t-th iteration, C1 is a fixed constant, d is the density factor, x rand is the position of the random individual in the current iteration;

[0136] In step S37, when it is determined that the current migration operator is greater than 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (22).

[0137]

[0138] Among them, acc best is the acceleration of the best individual in the current iteration;

[0139] In step S38, the acceleration of other individuals is normalized according to formula (23);

[0140] In step S39, the position of the individual is updated according to formula (25) to formula (28),

[0141]

[0142] T=C3×TF,T∈[C3×0.3,1], (26)

[0143]

[0144] P = 2 × rand - C4, (28)

[0145] Among them, F is the direction factor, TF is the migration operator, C2 is a fixed constant, T is the calculation factor, x bestis the position of the best individual in the current iteration, C3 is a fixed constant, P is the judgment calculation factor that determines the update direction of the iteration position, and C4 is a fixed constant.

[0146] In step S40, the selection probability of an individual is calculated according to formula (33) and formula (34):

[0147]

[0148] Among them, p i is the selection probability, f i is the fitness value of the i-th individual, fit i is the calculation factor;

[0149] In step S41, the Levy flight guidance operation is performed on other individuals in the current population according to the selection probability and formulas (35) to (37).

[0150]

[0151]

[0152] Among them, s is the rotation factor, R r is a random matrix, μ and ν follow a normal distribution,

[0153] In this Figure 4 In the method shown, step S31 can be used to obtain the migration operator of the current population. The specific method for obtaining the migration operator can be various forms known to those skilled in the art. In one example of the present invention, the method for obtaining the migration operator can be to obtain the migration operator of the current population according to formula (18):

[0154]

[0155] Among them, t max is the maximum number of iterations, and t is the current number of iterations.

[0156] When performing local search in the later stage of the Archimedes algorithm iteration, the way for individuals to converge to the current optimal solution is to jump directly to the vicinity of the current optimal position, rather than moving to the optimal position like the particle swarm optimization algorithm. This is a blind follow-up behavior, which causes the Archimedes algorithm to easily fall into the local optimum. As the number of iterations increases, the density factor will show a linear decreasing trend from 1 to 0. A density factor that is too small will lead to the loss of individual information, thereby resulting in a reduction in population diversity. Therefore, step S32 can be used to obtain the adaptive feedback adjustment factor of the current population. The density factor is improved by using the population evolution success rate and the normalized fitness of the individual as feedback adjustment parameters, so that the individual can be dynamically adjusted according to the actual environment of the population and its own fitness. The specific method for obtaining the adaptive feedback adjustment factor can be a variety of forms known to those skilled in the art. In one example of the present invention, the method for obtaining the adaptive feedback adjustment factor may include the following: Figure 5 Specifically:

[0157] In step S51, the success value of individuals in the current population is determined according to formula (29):

[0158]

[0159] Among them, S(i,t) is the success value of the i-th individual in the current population in the t-th iteration, is the historical optimal position of individual i at the tth iteration, is the historical optimal position of individual i at the t+1th iteration;

[0160] In step S52, the success rate of the current population is determined according to formula (30):

[0161]

[0162] Among them, P s (t) is the success rate of the population in the tth iteration, and N is the population size;

[0163] In step S53, the normalized fitness coefficient of the individual is determined according to formula (31):

[0164]

[0165] Among them, F i is the normalized fitness coefficient of the ith individual, f(X i ) is the individual fitness value of the i-th generation population, f min is the minimum fitness value of the individual, and ε is a very small rational number;

[0166] In step S54, the adaptive feedback adjustment factor is determined according to formula (32):

[0167]

[0168] in, is the adaptive feedback adjustment factor of the i-th generation population, α is the importance coefficient of the population evolution success rate, and β is the normalized fitness coefficient F of the i-th individual i The importance coefficient of .

[0169] The adaptive feedback adjustment factor will dynamically adjust its size according to the change of fitness. If the current individual fitness is close to the optimal fitness, the adaptive feedback adjustment factor will maintain the original density factor and accelerate the convergence of the algorithm. For individuals with poor fitness, their adaptive adjustment factor is close to the maximum value, which retains more information about themselves and ensures the local development ability of the algorithm.

[0170] In step S33 to step S39, by judging whether the current migration operator is less than or equal to 0.5, the algorithm performs a global search or a local search. When the migration operator is less than or equal to 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (21), and the accelerations of other individuals are normalized according to formula (23), and the positions of the individuals are updated according to formula (24). When judging that the current migration operator is greater than 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (22), and the accelerations of other individuals are normalized according to formula (23), and the positions of the individuals are updated according to formulas (25) to (28).

[0171] On the basis of maintaining the population diversity of the Archimedean algorithm, in order to improve the exploration ability of individuals and avoid the phenomenon of the population falling into the local optimum in the later stage of iteration, a Levy flight guidance strategy is proposed. With the Levy step length as the radius and the optimal individual as the center, the individual is subjected to the Levy flight guidance operation to improve the diversity and convergence speed of the population. The Levy flight guidance operator can transform the individual at a certain angle to avoid generating repeated individuals to the maximum extent; and it combines the characteristics of the alternating short-distance step length and long-distance step length of the Levy step length to expand the search range of the group and assist the algorithm to jump out of the local optimum when necessary to improve the search performance of the algorithm. Specifically, the selection probability of the individual is calculated according to formula (33) and formula (34) in step S40, and the Levy flight guidance operation is performed on other individuals in the current population according to the selection probability and formulas (35) to (37).

[0172] In steps S25 to S28, after updating other individuals in the iterative population according to the optimal individual, the number of iterations is updated, and it is determined whether the number of iterations of the current population is greater than or equal to the iteration threshold. When it is determined that the number of iterations of the current population is greater than or equal to the iteration threshold, the global optimal solution is output. When it is determined that the number of iterations of the current population is less than the iteration threshold, the step of calculating the fitness value of each individual in the population is returned.

[0173] Through the above technical scheme, the present invention provides a scheduling optimization method for elderly medical escorts considering the uncertainty of medical consultation time, by obtaining the elderly medical escort demand information, medical escort information and hospital information, obtaining the initial population according to the acquired medical escort demand information, medical escort information and hospital information, and using the Archimedes optimization algorithm to search for the optimal solution with the highest scheduling efficiency according to the initial population. The scheduling optimization method aims at the scheduling problem of elderly medical escorts, and establishes a target optimization model with the highest search scheduling efficiency considering the uncertainty of medical consultation time. On the basis of the standard Archimedes optimization algorithm, the Chebyshev mapping initial population is used, and the Levy flight guidance strategy is used to improve the algorithm's local optimization ability. The proposed improved Archimedes optimization algorithm can effectively solve the scheduling problem of medical escorts under the condition of clustered distribution of the elderly.

[0174] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0179] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0180] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0181] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0182] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A scheduling optimization method for elderly patients' companions considering the uncertainty of consultation time, characterized in that: The optimization method comprises: Obtain information on the elderly's need for medical companionship, medical companion information, and hospital information; Acquire an initial population according to the accompanying medical consultation demand information, accompanying medical consultation personnel information and hospital information; According to the initial population, the Archimedean optimization algorithm is used to search for the optimal solution with the highest scheduling efficiency, wherein the fitness function of the Archimedean optimization algorithm is the following formula (1) to formula (6): f=min(TC+LC+PC), (1) Among them, f is the fitness value, TC is the total driving cost, LC is the accompanying cost during the consultation, and PC is the penalty cost for the accompanying person not serving within the service time window for the elderly. Where n is the total number of elderly people, i and j are the elderly numbers, h is the hospital number, z is the total number of hospitals, m is the total number of accompanying personnel, M is the type of accompanying service, k is the number of accompanying personnel, s is the number of accompanying service type, c is the travel cost per unit time, T ij T is the travel time required for the accompanying person to travel from elderly person i to elderly person j, hi is the one-way travel time required for the accompanying person to travel from the elderly person's location i to the hospital's location h, The time that the accompanying personnel spend with the elderly in the hospital, p ks is the unit time service cost of accompanying service s, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i, e i is the start time of the service window for the elderly, TS ik is the time when the accompanying staff k starts to serve the elderly i, σ is the penalty coefficient, which is used to calculate the penalty cost of serving earlier than the time window, and is a fixed constant, d ij is the distance between elderly i and elderly j, x ijks is the decision variable used to determine whether the companion k provides services to another elderly person j after the elderly person i, v is the driving speed, d hi is the distance between elderly person i and hospital h, y iks is a decision variable used to determine whether the accompanying attendant k provides services to the elderly i.

2. The method for optimizing the scheduling of elderly medical companions according to claim 1, characterized in that: The initial population is obtained according to the accompanying medical consultation requirement information, the accompanying medical consultation personnel information and the hospital information, including: According to formula (7) and formula (16), the constraints of the population are determined. TS ik ≤l i ,i∈[1,n],k∈[1,m], (10) x ijks ＝{0,1}， (15) y iks ＝{0,1}， (16) Among them, TS jk is the time it takes for the accompanying person k to arrive at the elderly person j, x ieks The number of times the accompanying attendant k leaves the elderly person i to serve the next elderly person, x ejks is the number of times that the accompanying attendant k leaves the last elderly person and comes to serve the elderly person j, e is the elderly person's number, l is i The latest time of the service window for the elderly, x jiks is a decision variable used to determine whether the attendant k provides services to another elderly person j after the elderly person i, x 0jks is the decision variable, which determines the number of times the medical escort k leaves the medical escort service center, x j0ks is the decision variable, determining the number of times the patient escort k returns to the accompanying service center, T k setting working hours for nursing staff; The initial population is generated by using Chebyshev chaotic mapping.

3. The method for optimizing the scheduling of elderly medical companions according to claim 2, characterized in that: The initial population is generated by using Chebyshev chaotic mapping, including: Initialize the population according to formula (17): x i+1 =cos(a×cos -1 x i ),a=8,x∈[-1,1], (17) Among them, x i+1 is the population generated by the i-th generation population through the Chebyshev chaotic map, a is the order of the Chebyshev chaotic map, x i is the i-th generation population.

4. The method for optimizing the scheduling of elderly medical companions according to claim 1, characterized in that: The Archimedean optimization algorithm includes: Obtaining the initial population; Calculating the fitness value of each individual in the population respectively; Selecting the best individual in the population according to the fitness value; Iterate and update other individuals in the population according to the optimal individual; Update the number of iterations; Determine whether the number of iterations of the current population is greater than or equal to an iteration threshold; When it is determined that the number of iterations of the current population is greater than or equal to the iteration threshold, outputting a global optimal solution; When it is determined that the current number of iterations of the population is less than the iteration threshold, return to the step of respectively calculating the fitness value of each individual in the population.

5. The method for optimizing the scheduling of elderly medical companions according to claim 4, characterized in that: Updating and iterating other individuals in the population according to the optimal individual includes: Obtain the migration operator of the current population; Obtaining an adaptive feedback adjustment factor of the current population; Determine whether the current migration operator is less than or equal to 0.5; When it is determined that the current migration operator is less than or equal to 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (21). in, is the density of the i-th individual in the t+1th iteration, is the density of the i-th individual in the t-th iteration, rand is a random number between 0 and 1, and den best is the density of the optimal individual in the current iteration number, is the volume of the i-th individual in the t+1th iteration, is the volume of the i-th individual in the t-th iteration, vol best is the volume of the optimal individual in the current iteration number, is the acceleration of the ith individual in the t+1th iteration, den mr is the density of individuals randomly selected in the current iteration, vol mr is the volume of the randomly selected individual in the current iteration, acc mr is the acceleration of the randomly selected individual in the current iteration; According to formula (23), the acceleration of other individuals is normalized. in, is the normalized acceleration of the ith individual in the t+1 iteration, u is the upper limit of acceleration, l is the lower limit of acceleration, min(acc) is the minimum acceleration of the individual, and max(acc) is the maximum acceleration of the individual; According to formula (24), the position of the individual is updated. in, is the position of the i-th individual in the t+1 iteration, is the position of the i-th individual in the t-th iteration, C1 is a fixed constant, d is the density factor, x rand is the position of the random individual in the current iteration; When it is determined that the current migration operator is greater than 0.5, other individuals in the current population are updated and iterated according to formulas (19), (20), and (22). Among them, acc best is the acceleration of the best individual in the current iteration; The acceleration of other individuals is normalized according to formula (23); The individual position is updated according to formula (25) to formula (28), T=C3×TF,T∈[C3×0.3,1], (26) P = 2 × rand - C4, (28) Among them, F is the direction factor, TF is the migration operator, C2 is a fixed constant, T is the calculation factor, x best is the position of the best individual in the current iteration, C3 is a fixed constant, P is the judgment calculation factor that determines the update direction of the iteration position, and C4 is a fixed constant.

6. The method for optimizing the scheduling of elderly medical companions according to claim 5, characterized in that: Get the migration operator of the current population, including: According to formula (18), the migration operator of the current population is obtained: Among them, t max is the maximum number of iterations, and t is the current number of iterations.

7. The method for optimizing the scheduling of elderly medical companions according to claim 5, characterized in that: Obtaining the adaptive feedback adjustment factor of the current population, including: According to formula (29), the success value of individuals in the current population is determined: Among them, S(i,t) is the success value of the i-th individual in the current population in the t-th iteration, is the historical optimal position of individual i at the tth iteration, is the historical optimal position of individual i at the t+1th iteration; According to formula (30), the success rate of the current population is determined. Among them, P s (t) is the success rate of the population in the tth iteration, and N is the population size; According to formula (31), the normalized fitness coefficient of the individual is determined: Among them, F i is the normalized fitness coefficient of the ith individual, f(X i ) is the fitness value of the individual in the i-th generation population, f min is the minimum fitness value of the individual, and ε is a very small rational number; Determine the adaptive feedback adjustment factor according to formula (32): in, is the adaptive feedback adjustment factor of the i-th generation population, α is the importance coefficient of the population evolution success rate, and β is the normalized fitness coefficient F of the i-th individual i The importance coefficient of .

8. The method for optimizing the scheduling of elderly medical companions according to claim 4, characterized in that: Selecting the best individual in the population according to the fitness value also includes: According to formula (33) and formula (34), the individual selection probability is calculated. Among them, p i is the selection probability, f i is the fitness value of the i-th individual, fit i is the calculation factor; According to the selection probability and formula (35) to formula (37), other individuals in the current population are subjected to Levy flight guidance operation. Among them, s is the rotation factor, R r is a random matrix, μ and ν follow a normal distribution,

Images