CN109509548B - Outpatient medical service scheduling method, system and storage medium - Google Patents
Outpatient medical service scheduling method, system and storage medium Download PDFInfo
- Publication number
- CN109509548B CN109509548B CN201811360433.2A CN201811360433A CN109509548B CN 109509548 B CN109509548 B CN 109509548B CN 201811360433 A CN201811360433 A CN 201811360433A CN 109509548 B CN109509548 B CN 109509548B
- Authority
- CN
- China
- Prior art keywords
- patient
- time
- end time
- treatment
- examination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a medical service scheduling method, a medical service scheduling system and a storage medium for outpatients, wherein the method comprises the following steps: s100, setting algorithm parameters; s200, generating a group according to the current probability distribution model; s300, calculating the fitness value of each chromosome in the population, and selecting the chromosome with the highest fitness value from the population according to a preset proportion as a dominant solution and the chromosome with the lowest fitness value as a disadvantaged solution; s400, performing neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution; s500, judging whether the current iteration number reaches the maximum iteration number: if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution; otherwise, adding 1 to the current iteration number, and returning to S200. The invention can solve the problem of medical service scheduling of patients.
Description
Technical Field
The invention relates to the technical field of medical scheduling, in particular to a medical service scheduling method, a medical service scheduling system and a storage medium for outpatients.
Background
The medical service scheduling problem of outpatients refers to a problem of allocating patients who have previously reserved outpatients or outpatients for surgery to different medical services and arranging the order of the respective patients on the different medical services. The reasonable medical service scheduling scheme has important significance for improving the operation efficiency of the hospital and the satisfaction degree of patients and medical care personnel.
Disclosure of Invention
Technical problem to be solved
The invention provides a medical service scheduling method, a medical service scheduling system and a storage medium for outpatients, which can solve the medical service scheduling problem of the patients, save medical resources, improve medical efficiency and improve the satisfaction degree of the patients.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a method for scheduling medical services for outpatient service, comprising:
s100, setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
s200, generating a group according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
s300, calculating the fitness value of each chromosome in the population, and selecting the chromosome with the highest fitness value from the population according to a preset proportion as a dominant solution and the chromosome with the lowest fitness value as a disadvantaged solution;
s400, performing neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
s500, judging whether the current iteration number reaches the maximum iteration number:
if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution;
otherwise, adding 1 to the current iteration number, and returning to S200.
In a second aspect, the present invention provides an outpatient medical services scheduling system, comprising:
the parameter setting module is used for executing S100 and setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
the population generation module is used for executing S200 and generating a population according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
the major-minor solution acquisition module is used for executing S300, calculating the fitness value of each chromosome in the population, and selecting a chromosome with the highest fitness value from the population according to a preset proportion as a major solution and a chromosome with the lowest fitness value as a minor solution;
the model updating module is used for executing S400 and carrying out neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
a judging module, configured to execute S500, and judge whether the current iteration number reaches the maximum iteration number: if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution; otherwise, adding 1 to the current iteration number, and returning to the population generation module to execute S200.
In a third aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is operable to implement the above medical service scheduling method.
(III) advantageous effects
According to the medical service scheduling method, system and storage medium for outpatient service, the inquiry sequence of the patients under each doctor is determined, then the patients are allocated to the medical service after the inquiry service, and the sequence is arranged. And randomly generating an initial population according to the initial probability distribution model. Selecting the best feasible solutions from the initial population as dominant solutions, the worst feasible solutions as disadvantaged solutions, further determining elite solutions and non-elite solutions by using neighborhood search, updating the probability distribution model by simulating learning the elite solutions and being far away from the non-elite solutions, generating a new population according to the updated probability distribution model, and re-executing the process. By analogy, through the iterative mode, searching is carried out towards the direction where the ideal solution is most likely to occur, and finally the global optimal solution is obtained. The method avoids the problems of slow iteration and difficult direction determination caused by overlong codes, quickly determines the direction of the most probable ideal solution by learning the dominant solution and absorbing the experience of the dominant solution, and performs neighborhood search to avoid trapping in local optimization. The method provided by the invention has good performance in the aspects of convergence speed, stability, quality of solution and the like, can well solve the problem of patient medical path scheduling, saves medical resources, improves medical efficiency and improves patient satisfaction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart illustrating a medical service scheduling method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a first aspect, the present invention provides a method for outpatient medical service scheduling, which is particularly suitable for medical scheduling of ophthalmic patients and which can be performed by a computer device.
As shown in fig. 1, the medical service scheduling method includes the steps of:
s100, setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
of course, the algorithm parameters are not limited to the maximum iteration number and the initial probability distribution model, and the algorithm parameters may also include a doctor to be reserved for each patient in the same reservation period, a medical service path corresponding to each patient, the number of patients that each medical service can accommodate at the same time, a time length distribution function corresponding to each medical service, the size of the population, that is, the number of chromosomes included in the population, and the initial iteration number of 1.
It will be appreciated that the time period here, for example 10 months in 2018 and 10 am, is a time period.
Wherein the medical service path comprises at least one service or a combination of at least two services of a primary inquiry service, an examination service, a secondary inquiry service, a treatment service and a surgery service; for example, the number of the first inquiry service is set to 1, the number of the examination service is set to 2, the number of the second inquiry service is set to 3, the number of the treatment service is set to 4, the number of the surgery service is set to 5, and each medical service path roughly includes: 1; 1-4; 1-2-3; 1-2-3-4; 1-2-3-5; 1-5.
It will be appreciated that the time required for different patients varies even for the same medical service, for example, an initial visit, with some patients requiring 5 minutes and some patients requiring 20 minutes. The time required for each patient for the same medical service conforms to a particular profile, which can be expressed as a time-consuming profile function. The time required for each patient to be at each medical service can be determined using the time duration distribution function.
It will be appreciated that the patient's medical service path may be determined based on what the patient described at the time of the appointment. The medical service path of the individual patient can therefore also be predicted in advance before the execution of the method.
It is understood that the number of chromosomes included in the population generated in step S200 can be determined according to the set population size.
S200, generating a group according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
the solution corresponding to each chromosome in the population is represented as a coding matrix, and in the coding matrix, a row of inquiry service scheduling data, b row of examination service scheduling data, c row of treatment service scheduling data and d row of operation service scheduling data are included; a is the number of preset doctors, b is the number of examination devices, c is the number of treatment devices, and d is the number of operating rooms; each line of inquiry service scheduling data represents the inquiry sequence of each patient under the corresponding doctor; each row of examination service scheduling data represents the examination sequence of each patient under the corresponding examination equipment; each line of treatment service scheduling data represents the treatment sequence of each patient under the corresponding treatment equipment; each operation service scheduling data represents the operation sequence of each patient in the corresponding operation room; the ones of the elements in each row of scheduling data are numbers corresponding to the medical services of the row in which the elements are located; the data for the remaining bits is the patient's number.
For example, with 3 doctors, 2 examination devices, 1 treatment device, 2 operating rooms, i.e. a is 3, b is 2, c is 1, d is 2, and there are 6 patients in a certain period of time, the encoding matrix of the solution corresponding to one chromosome in the generated population is as follows:
where the ones of each element represent the patient's healthcare corresponding number and the tens represent the patient's number, e.g., 21 represents patient 2 undergoing the initial interrogation service.
In the coding matrix, the first three rows are the inquiry orders of three patients under doctors, for example, the first element 21 indicates that the first doctor gives the first inquiry service (primary inquiry service) to the patient 2, and 33 indicates that the second doctor gives the third inquiry service (secondary inquiry service) to the patient 3; the fourth and fifth rows are the examination order of patients under two examination devices, e.g., 52 for a second examination service for patient 5 on the first examination device and 42 for a first examination service for patient 4 on the second examination device; a sixth action treatment sequence for the patient under treatment device, e.g., 44, to provide treatment services for a second one of the patients 4 under treatment device; the seventh and eighth rows are the surgical sequence for two patients under the operating room, e.g., 62 is the surgical service for the 1 st patient 6 in the second operating room.
It can be seen that the ordering of each patient in each medical service of its medical service path can be derived from the above coding matrices, one coding matrix representing one medical service scheduling scheme.
From the above, each patient needs to make an appointment with the doctor in advance, and arrives at the beginning of the appointment period, so that the patients in the same appointment period arrive in batches; the number of reserved doctors is known; patient knowledge of each doctor for each appointment period; the medical service path for each patient is known; each medical service path is required to be carried out according to the determined medical service sequence; when the previous medical service is not finished, the next medical service cannot be started; the patient is not interruptible while receiving a medical service; each medical service can be viewed as a plurality of parallel machines. More importantly, the above scheme is based on the following assumptions: first, the first stage of each patient is the initial interrogation service; second, if the patient requires a secondary inquiry, the patient's secondary and primary inquiries are the same person; third, the examination service and the secondary inquiry service of the patient are bound, that is, the patient to be examined must make a secondary inquiry because the patient needs to give the examination result to a doctor for consultation again. Fourth, the rest time is not considered when calculating the fitness value.
S300, calculating the fitness value of each chromosome in the population, and selecting the chromosome with the highest fitness value from the population according to a preset proportion as a dominant solution and the chromosome with the lowest fitness value as a disadvantaged solution;
the fitness value of each chromosome may be an inverse of a maximum value of the final completion time of each medical service in the solution corresponding to the chromosome, and the maximum value may become the maximum completion time. The larger the fitness value, the smaller the maximum completion time, meaning that the smaller the span between the final completion times of the medical services under the solution, the more advantageous the solution.
When the fitness value is the maximum completion time, the calculation process of the fitness value of each chromosome may include the following processes:
s301, determining the time required by each medical service of each patient in the medical service path according to the time length distribution function corresponding to each medical service;
s302, calculating the initial diagnosis end time of each patient of each doctor according to the inquiry service scheduling data of each row in the coding matrix and the time required by the initial diagnosis service of each patient;
for example, assume that the inquiry time of 6 patients in the above coding matrix is 10min, the examination time is 30min, the treatment time is 20min, and the operation time is 5 min. The first line data 21 shows a first diagnosis end time of 10 and 11 shows a first diagnosis end time of 20.
In practice, since one doctor does not only perform the primary inquiry but also performs the secondary inquiry, in the calculation process, if the medical service number of the element is the number corresponding to the secondary inquiry service, the calculation of the primary diagnosis end time of the rest of patients under the corresponding doctor is suspended, and the primary diagnosis end time of each patient under the next doctor is calculated until the primary diagnosis end time of all the patients under all the doctors is calculated.
For example, in the second line data, 41 has a first diagnosis end time of 10, 31 has a first diagnosis end time of 20, and when 33 is encountered, 33 needs to perform a second inquiry because the medical service number indicated by the single digit number of 33 is 3, and at this time, the calculation of the first diagnosis end times of the remaining patients by the 2 nd doctor is suspended, and the calculation of the first diagnosis end times of the respective patients by the 3 rd doctor is suspended, and in the 3 rd line data, 51 has a first diagnosis end time of 10, 61 has a first diagnosis end time of 20, and when 53 is encountered, the calculation of the first diagnosis end times of the remaining patients by the 3 rd doctor is suspended.
S303, searching a patient number of the checking service from left to right in each row of checking service scheduling data of the coding matrix, and jumping to S305 if the patient number does not appear in each row of checking service scheduling data; otherwise, acquiring the examination ending time of the previous patient on the corresponding examination equipment; if the examination end time of the previous patient is later than the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the examination end time of the previous patient and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number; if the examination end time of the previous patient is earlier than or equal to the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the initial diagnosis end time of the patient corresponding to the patient number and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number;
in practical applications, if the examination end time of the previous patient and/or the initial diagnosis end time of the patient corresponding to the patient number are unknown, the calculation of the examination end time of the patient corresponding to the patient number is suspended, and the examination end time of the next patient is calculated until the examination end time calculation of all patients under all examination devices is completed.
In this case, the patient 3 is first subjected to examination service on the first examination apparatus, and therefore the examination start time of the patient 3 on the first examination apparatus is the initial examination end time of the patient 3.
S304, searching the number of the patient of the secondary inquiry service from left to right in each row of inquiry service scheduling data of the coding matrix, and if the inquiry time of the previous patient is later than the examination end time of the patient corresponding to the patient number, taking the sum of the inquiry end time of the previous patient and the secondary inquiry time of the patient corresponding to the patient number as the secondary inquiry end time of the patient corresponding to the patient number;
if the inquiry end time of the previous patient is unknown, suspending the calculation of the secondary inquiry time of the patient corresponding to the patient number, and calculating the secondary inquiry end time of the next patient until the secondary inquiry end time of all the patients needing secondary inquiry is calculated;
s305, searching a patient number of a treatment service from left to right in each row of treatment service scheduling data of the coding matrix, and jumping to S306 if the patient number does not appear in each row of treatment service scheduling data; otherwise, acquiring the treatment ending time of the previous patient on the corresponding treatment equipment, and if the treatment ending time of the previous patient is later than the final inquiry ending time of the patient corresponding to the patient number, using the sum of the treatment ending time of the previous patient and the treatment required time of the patient corresponding to the patient number as the treatment ending time of the patient corresponding to the patient number; and if the treatment end time of the previous patient is earlier than or equal to the final inquiry end time of the patient corresponding to the patient number, using the sum of the final inquiry end time of the patient corresponding to the patient number and the treatment required time as the treatment end time of the patient corresponding to the patient number.
It can be understood that if the patient has only the first diagnosis and does not have the second diagnosis, the final diagnosis end time is the first diagnosis end time, and if the patient has the second diagnosis, the final diagnosis end time is the second diagnosis end time.
In practical applications, if the treatment end time of the previous patient and/or the final inquiry time of the patient corresponding to the patient number are unknown, the calculation of the treatment end time of the patient corresponding to the patient number is suspended, and the treatment end time of the next patient is calculated until the calculation of the treatment end time of all patients under all treatment devices is completed.
The first patient 2 to be treated is on the treatment device, i.e. the treatment start time of patient 2 is the end time of the initial visit of patient 2.
S306, searching a patient number of the surgical service from left to right in each row of surgical service scheduling data of the coding matrix, and if the patient number does not appear in each row of surgical service scheduling data, outputting the end time of each medical service of the patient corresponding to the patient number; otherwise, acquiring the operation ending time of the previous patient in the corresponding operating room, and if the operation ending time of the previous patient is later than the final inquiry time of the patient corresponding to the patient number, taking the sum of the operation ending time of the previous patient and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number; if the operation ending time of the previous patient is earlier than or equal to the final inquiry time of the patient corresponding to the patient number, taking the sum of the final inquiry time of the patient corresponding to the patient number and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number, and calculating the operation ending time of the next patient until the operation ending time of all patients in all operating rooms is calculated.
Wherein, in the second operating room, the patient 6 is the first to perform the operation service, and the operation start time of the patient 6 is the initial diagnosis end time of the patient 6.
For example, if there is no patient 1 in the 4 th and 5 th rows for patient 1, the process jumps to step S305, and if there is no patient 1 in the 6 th row, the process jumps to step S306, and if there is no patient 1 in the 7 th and 8 th rows, the first visit end time 20 of patient 1 on the first doctor is output. For patient 2, no patient 2 is present in rows 4 and 5, then step S305 is skipped and the treatment end time for patient 2 is calculated: if 30 is equal to 10+20, and no patient 2 is present in lines 7 and 8, the initial visit end time 10 of the patient 2 at the first doctor and the treatment end time 30 at the treatment device are output. Similarly, for patient 3, the initial diagnosis end time of patient 3 on the second doctor is 20, the examination end time on the first examination apparatus is 20+ 30-50, and the secondary diagnosis end time is 50+ 10-60. For patient 4, the initial diagnosis end time is 10, the examination end time on the second examination apparatus is 10+ 30-40, the second examination end time on patient 4 is 60+ 10-70 since examination end time 40 on patient 4 is earlier than second examination end time 60 on patient 3, and the treatment end time on patient 4 is 70+ 20-90 since treatment end time 20 on patient 2 is earlier than second examination end time 70 on patient 4. For the patient 5, the initial diagnosis end time is 10, the examination end time 50 of the patient 3 is later than the initial diagnosis end time 10 of the patient 5, and therefore the examination end time of the patient 5 is 50+ 30-80, and since the examination end time 80 of the patient 5 is later than the initial diagnosis end time 20 of the patient 6, the secondary inquiry end time of the patient 5 is 80+ 10-90, and the operation end time of the patient 5 is 90+ 5-95. For patient 6, the initial diagnosis end time was 20, and the operation end time was 20+5 — 25.
S307, determining the final inquiry end time of the last patient of each doctor according to the inquiry end time of each patient on each doctor; determining the examination and treatment time of the last patient on each examination device according to the examination and treatment time of each patient on each examination device; determining the treatment ending time of the last patient on each treatment device according to the treatment ending time of each patient on each treatment device; determining the operation ending time of the last patient in each operation room according to the operation ending time of each patient in the operation room;
for example, the final end-of-visit time for the last patient of the first doctor is 20, the final end-of-visit time for the last patient of the second doctor is 70, and the final end-of-visit time for the last doctor of the third doctor is 90; the examination end time of the last patient on the first examination apparatus is 80, and the examination end time of the last patient on the second examination apparatus is 40; the treatment end time for the last patient of the treatment apparatus is 90, the operation end time for the first operating room is 95, and the operation end time for the second operating room is 25.
And S308, the maximum value of the final inquiry end time of the last patient of each doctor, the examination end time of the last patient on each examination device, the treatment end time of the last patient on each treatment device and the operation end time of the last patient in each operating room is inverted to be the fitness value of the chromosome.
For example, the completion time in each medical service is (20, 70, 90, 80, 40, 90, 95, 25), and the maximum value is found to be 95, so the fitness value of the chromosome is 1/95.
As can be seen, the fitness values corresponding to the chromosomes in the population can be calculated in the steps S301 to S308.
The preset ratio k (e.g., 0< k <0.33) in step S300 may be set as needed, for example, 10%, and assuming that the number of chromosomes in the population is 100, 10 chromosomes with the highest fitness value and 10 chromosomes with the lowest fitness value may be selected according to the preset ratio, where the 10 chromosomes with the highest fitness value are dominant solutions and the 10 chromosomes with the lowest fitness value are disadvantaged solutions.
S400, performing neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
understandably, the elite solutions and the dominant solutions are in one-to-one correspondence, and each elite solution is generated by the corresponding dominant solution through a VNS algorithm; likewise, the non-elite solutions and the disadvantaged solutions are also in one-to-one correspondence, and each non-elite solution is generated by the corresponding disadvantaged solution through the VNS algorithm.
After the elite solution and the non-elite solution are obtained, the probability distribution model is updated according to the elite solution and the non-elite solution to realize the simulation learning of the elite solution and the separation of the non-elite solution, so that the fitness value of chromosomes in a population generated according to the updated probability distribution model is higher, and the corresponding solution has more advantages.
It is understood that, according to the initial probability distribution model, the selection probability of each value at each position of each chromosome is p ═ 1/n, where n is the number of patients with medical services corresponding to the position in the same appointment period. That is, the probability of any patient appearing in row i and column j of the coding matrix is 1/n.
However, the process of updating the current probability distribution model based on the elite solution and the non-elite solution may comprise the steps of:
s401, calculating the probability of each patient at each position in the coding matrix according to the number of the elite solutions and the number of the non-elite solutions of each patient at each position in the coding matrix;
in practical applications, the probability that the u patient appears in the ith row and the jth column of the coding matrix can be calculated as follows:
pu＝1/n+[(m1u-m2u)/m]α
in the formula, puThe probability of the occurrence of the u patient in the ith row and the jth column of the coding matrix is shown, n is the number of the patients of the medical service corresponding to the ith row, m1uNumber of elite solutions, m, for the u patient appearing in the ith row and j column of the assembled matrix2uThe number of non-elite solutions for the u-th patient to appear in the ith row and the jth column of the assembly matrix, 2m being the total number of elite solutions and non-elite solutions, each of the number of elite solutions and non-elite solutions being m, α being a constant greater than 0 and less than 1. Where α is a learning rate, and can be understood as an acceptance rate of the solution. The high acceptance rate indicates that the probability is greatly influenced by the situations of the elite solutions and the non-elite solutions, and the low acceptance rate indicates that the probability is slightly influenced by the situations of the elite solutions and the non-elite solutions.
For example, if the first row of the coding matrix is the first patient of the first doctor, the number of patients of the first doctor is n, and the first column of the first row is the first patient of the first doctor, the patient at the position can be any one patient according to the initial probability distribution model, and thus the initial probability of each patient is 1/n. Since the total number of elite and non-elite solutions is 2m, patient 1 presented with an elite solution in the first row and the first column in a number of m11Patient 1 presented with a number of non-elite solutions m in the first row and column21Then the updated probability of patient 1 appearing in the first column on the first row is:
p1＝1/n+[(m11-m21)/m]α。
therefore, the probability of each patient appearing at each position of the coding matrix can be calculated by the above formula, and the selection probability of each position of the chromosome to each value can be further known.
S402, updating the probability distribution model according to the probability of each position of each patient in the coding matrix.
It can be understood that the process of updating the probability distribution model is the process of updating the parameters in the model, so that the probability calculated by the updated probability distribution model is consistent with the probability calculated in step S401.
S500, judging whether the current iteration number reaches the maximum iteration number:
if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution;
otherwise, adding 1 to the current iteration number, and returning to S200.
It can be understood that the reference standard of the solution is the fitness value, and the higher the fitness value is, the better the solution is, so that the optimal elite solution is the elite solution with the highest fitness value.
It can be appreciated that the present invention aims to rank the patients of each doctor and assign the individual patients to different service resources and rank them to minimize the span between the end times of all medical services.
The invention is very suitable for the characteristics of rapid circulation and multiple steps of an ophthalmic clinic.
The method provided by the invention comprises the steps of firstly determining the inquiry sequence of patients under each doctor, then distributing the patients to medical services after the inquiry services, and arranging the sequence. And randomly generating an initial population according to the initial probability distribution model. Selecting the best feasible solutions from the initial population as dominant solutions, the worst feasible solutions as disadvantaged solutions, further determining elite solutions and non-elite solutions by using neighborhood search, updating the probability distribution model by simulating learning the elite solutions and being far away from the non-elite solutions, generating a new population according to the updated probability distribution model, and re-executing the process. By analogy, through the iterative mode, searching is carried out towards the direction where the ideal solution is most likely to occur, and finally the global optimal solution is obtained. The method avoids the problems of slow iteration and difficult direction determination caused by overlong codes, quickly determines the direction of the most probable ideal solution by learning the dominant solution and absorbing the experience of the dominant solution, and performs neighborhood search to avoid trapping in local optimization. The method provided by the invention has good performance in the aspects of convergence speed, stability, quality of solution and the like, can well solve the problem of patient medical path scheduling, saves medical resources, improves medical efficiency and improves patient satisfaction.
In addition, the invention considers the actual situation in the process of seeing a doctor, particularly the process of calculating the adaptability value, and limits the calculation process of the adaptability value according to the actual situation, so that the scheduling method provided by the invention is more consistent with the actual situation. In addition, because the patient has a designated doctor in the inquiry stage due to doctor reservation, and does not have a designated medical service device in other stages, the patient is coded by adopting a distribution and sequencing mode, and the calculation of the fitness value is very convenient.
In a second aspect, the present invention provides an outpatient medical services scheduling system, comprising:
the parameter setting module is used for executing S100 and setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
the population generation module is used for executing S200 and generating a population according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
the major-minor solution acquisition module is used for executing S300, calculating the fitness value of each chromosome in the population, and selecting a chromosome with the highest fitness value from the population according to a preset proportion as a major solution and a chromosome with the lowest fitness value as a minor solution;
the model updating module is used for executing S400 and carrying out neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
a judging module, configured to execute S500, and judge whether the current iteration number reaches the maximum iteration number: if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution; otherwise, adding 1 to the current iteration number, and returning to the population generation module to execute S200.
In a third aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is operable to implement the above medical service scheduling method.
It is to be understood that the systems and storage media provided in the second and third aspects, relevant contents thereof can refer to corresponding parts in the first aspect, and are not repeated herein.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for scheduling medical services for an outpatient, comprising:
s100, setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
s200, generating a group according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
s300, calculating the fitness value of each chromosome in the population, and selecting the chromosome with the highest fitness value from the population according to a preset proportion as a dominant solution and the chromosome with the lowest fitness value as a disadvantaged solution;
wherein calculating the fitness value of each chromosome in the population comprises:
s301, determining the time required by each medical service of each patient in the medical service path according to the time length distribution function corresponding to each medical service;
s302, calculating the initial diagnosis end time of each patient of each doctor according to the inquiry service scheduling data of each row in the coding matrix and the time required by the initial diagnosis service of each patient; in the calculation process, if the patient number of the element is the number corresponding to the secondary inquiry service, the calculation of the initial diagnosis end time of the rest of patients under the corresponding doctor is suspended, and the initial diagnosis end time of each patient under the next doctor is calculated until the initial diagnosis end time calculation of all the patients under all the doctors is completed;
s303, searching a patient number of the checking service from left to right in each row of checking service scheduling data of the coding matrix, and jumping to S305 if the patient number does not appear in each row of checking service scheduling data; otherwise, acquiring the examination ending time of the previous patient on the corresponding examination equipment; if the examination end time of the previous patient is later than the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the examination end time of the previous patient and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number; if the examination end time of the previous patient is earlier than or equal to the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the initial diagnosis end time of the patient corresponding to the patient number and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number; if the examination end time of the previous patient and/or the initial diagnosis end time of the patient corresponding to the patient number are unknown, the examination end time of the patient corresponding to the patient number is temporarily calculated, and the examination end time of the next patient is calculated until the examination end time of all patients under all examination equipment is calculated;
s304, searching the number of the patient of the secondary inquiry service from left to right in each row of inquiry service scheduling data of the coding matrix, and if the inquiry time of the previous patient is later than the examination end time of the patient corresponding to the patient number, taking the sum of the inquiry end time of the previous patient and the secondary inquiry time of the patient corresponding to the patient number as the secondary inquiry end time of the patient corresponding to the patient number; if the inquiry end time of the previous patient is unknown, suspending the calculation of the secondary inquiry time of the patient corresponding to the patient number, and calculating the secondary inquiry end time of the next patient until the secondary inquiry end time of all the patients needing secondary inquiry is calculated;
s305, searching a patient number of a treatment service from left to right in each row of treatment service scheduling data of the coding matrix, and jumping to S306 if the patient number does not appear in each row of treatment service scheduling data; otherwise, acquiring the treatment ending time of the previous patient on the corresponding treatment equipment, and if the treatment ending time of the previous patient is later than the final inquiry ending time of the patient corresponding to the patient number, using the sum of the treatment ending time of the previous patient and the treatment required time of the patient corresponding to the patient number as the treatment ending time of the patient corresponding to the patient number; if the treatment end time of the previous patient is earlier than or equal to the final inquiry end time of the patient corresponding to the patient number, taking the sum of the final inquiry end time of the patient corresponding to the patient number and the treatment required time as the treatment end time of the patient corresponding to the patient number; if the treatment end time of the previous patient and/or the final inquiry time of the patient corresponding to the patient number are unknown, the calculation of the treatment end time of the patient corresponding to the patient number is suspended, and the treatment end time of the next patient is calculated until the calculation of the treatment end time of all patients under all treatment equipment is completed;
s306, searching a patient number of the surgical service from left to right in each row of surgical service scheduling data of the coding matrix, and if the patient number does not appear in each row of surgical service scheduling data, outputting the end time of each medical service of the patient corresponding to the patient number; otherwise, acquiring the operation ending time of the previous patient in the corresponding operating room, and if the operation ending time of the previous patient is later than the final inquiry time of the patient corresponding to the patient number, taking the sum of the operation ending time of the previous patient and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number; if the operation ending time of the previous patient is earlier than or equal to the final inquiry time of the patient corresponding to the patient number, taking the sum of the final inquiry time of the patient corresponding to the patient number and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number, and calculating the operation ending time of the next patient until the operation ending time of all patients in all operating rooms is calculated;
s307, determining the final inquiry end time of the last patient of each doctor according to the inquiry end time of each patient on each doctor; determining the examination and treatment time of the last patient on each examination device according to the examination and treatment time of each patient on each examination device; determining the treatment ending time of the last patient on each treatment device according to the treatment ending time of each patient on each treatment device; determining the operation ending time of the last patient in each operation room according to the operation ending time of each patient in the operation room;
s308, taking the reciprocal of the maximum value of the final inquiry end time of the last patient of each doctor, the examination end time of the last patient on each examination device, the treatment end time of the last patient on each treatment device and the operation end time of the last patient in each operating room as the fitness value of the chromosome;
s400, performing neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
s500, judging whether the current iteration number reaches the maximum iteration number:
if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution;
otherwise, adding 1 to the current iteration number, and returning to S200.
2. The method of claim 1, wherein the algorithm parameters further include a doctor appointment for each patient during the same appointment period, a medical service route corresponding to each patient, a number of patients that can be admitted simultaneously by each medical service, and a time length distribution function corresponding to each medical service; wherein the medical service path comprises at least one of a primary inquiry service, an examination service, a secondary inquiry service, a treatment service and a surgery service; if the medical service path of the patient comprises the secondary inquiry service, the reservation doctor corresponding to the secondary inquiry service and the primary inquiry service of the patient is the same person; if the medical service path of the patient comprises the examination service, the medical service path of the patient also comprises a secondary inquiry service; in the medical service path of each patient, at most one of the treatment service and the surgical service appears;
correspondingly, a solution corresponding to each chromosome in the population is represented as a coding matrix, and in the coding matrix, a row of inquiry service scheduling data, b row of examination service scheduling data, c row of treatment service scheduling data and d row of operation service scheduling data are included; a is the number of preset doctors, b is the number of examination devices, c is the number of treatment devices, and d is the number of operating rooms; each line of inquiry service scheduling data represents the inquiry sequence of each patient under the corresponding doctor; each row of examination service scheduling data represents the examination sequence of each patient under the corresponding examination equipment; each line of treatment service scheduling data represents the treatment sequence of each patient under the corresponding treatment equipment; each operation service scheduling data represents the operation sequence of each patient in the corresponding operation room; the ones of the elements in each row of scheduling data are numbers corresponding to the medical services of the row in which the elements are located; the remaining bits of data are patient numbers.
3. The method of claim 2, wherein the fitness value for each chromosome is the inverse of the maximum of the final completion times of the medical services in the solution for that chromosome.
4. The method of claim 2, wherein said updating the probability distribution model based on the elite solution and the non-elite solution comprises:
s401, calculating the probability of each patient at each position in the coding matrix according to the number of the elite solutions and the number of the non-elite solutions of each patient at each position in the coding matrix;
s402, updating the probability distribution model according to the probability of each position of each patient in the coding matrix.
5. The method of claim 4, wherein the probability that the u patient is present in the ith row and the jth column of the coding matrix is:
pu＝1/n+[(m1u-m2u)/m]α
in the formula, puThe probability of the occurrence of the u patient in the ith row and the jth column of the coding matrix is shown, n is the number of the patients of the medical service corresponding to the ith row, m1uElite appearing in ith row and jth column of the assembly matrix for the u patientNumber of solutions, m2uThe number of non-elite solutions for the u-th patient appearing in the ith row and the jth column of the assembled matrix, the number of elite solutions and non-elite solutions each being m, α being a constant greater than 0 and less than 1.
6. An outpatient medical services scheduling system, comprising:
the parameter setting module is used for executing S100 and setting algorithm parameters, wherein the algorithm parameters comprise maximum iteration times and an initial probability distribution model;
the population generation module is used for executing S200 and generating a population according to the current probability distribution model; the population comprises a plurality of chromosomes, each chromosome corresponds to a solution, the solution comprises medical service scheduling data of all patients in the same appointment period, and the medical service scheduling data comprises the patients distributed by all medical services and the sequence of serving the distributed patients;
the major-minor solution acquisition module is used for executing S300, calculating the fitness value of each chromosome in the population, and selecting a chromosome with the highest fitness value from the population according to a preset proportion as a major solution and a chromosome with the lowest fitness value as a minor solution;
wherein calculating the fitness value of each chromosome in the population comprises:
s301, determining the time required by each medical service of each patient in the medical service path according to the time length distribution function corresponding to each medical service;
s302, calculating the initial diagnosis end time of each patient of each doctor according to the inquiry service scheduling data of each row in the coding matrix and the time required by the initial diagnosis service of each patient; in the calculation process, if the patient number of the element is the number corresponding to the secondary inquiry service, the calculation of the initial diagnosis end time of the rest of patients under the corresponding doctor is suspended, and the initial diagnosis end time of each patient under the next doctor is calculated until the initial diagnosis end time calculation of all the patients under all the doctors is completed;
s303, searching a patient number of the checking service from left to right in each row of checking service scheduling data of the coding matrix, and jumping to S305 if the patient number does not appear in each row of checking service scheduling data; otherwise, acquiring the examination ending time of the previous patient on the corresponding examination equipment; if the examination end time of the previous patient is later than the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the examination end time of the previous patient and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number; if the examination end time of the previous patient is earlier than or equal to the initial diagnosis end time of the patient corresponding to the patient number, taking the sum of the initial diagnosis end time of the patient corresponding to the patient number and the examination time of the patient corresponding to the patient number as the examination end time of the patient corresponding to the patient number; if the examination end time of the previous patient and/or the initial diagnosis end time of the patient corresponding to the patient number are unknown, the examination end time of the patient corresponding to the patient number is temporarily calculated, and the examination end time of the next patient is calculated until the examination end time of all patients under all examination equipment is calculated;
s304, searching the number of the patient of the secondary inquiry service from left to right in each row of inquiry service scheduling data of the coding matrix, and if the inquiry time of the previous patient is later than the examination end time of the patient corresponding to the patient number, taking the sum of the inquiry end time of the previous patient and the secondary inquiry time of the patient corresponding to the patient number as the secondary inquiry end time of the patient corresponding to the patient number; if the inquiry end time of the previous patient is unknown, suspending the calculation of the secondary inquiry time of the patient corresponding to the patient number, and calculating the secondary inquiry end time of the next patient until the secondary inquiry end time of all the patients needing secondary inquiry is calculated;
s305, searching a patient number of a treatment service from left to right in each row of treatment service scheduling data of the coding matrix, and jumping to S306 if the patient number does not appear in each row of treatment service scheduling data; otherwise, acquiring the treatment ending time of the previous patient on the corresponding treatment equipment, and if the treatment ending time of the previous patient is later than the final inquiry ending time of the patient corresponding to the patient number, using the sum of the treatment ending time of the previous patient and the treatment required time of the patient corresponding to the patient number as the treatment ending time of the patient corresponding to the patient number; if the treatment end time of the previous patient is earlier than or equal to the final inquiry end time of the patient corresponding to the patient number, taking the sum of the final inquiry end time of the patient corresponding to the patient number and the treatment required time as the treatment end time of the patient corresponding to the patient number; if the treatment end time of the previous patient and/or the final inquiry time of the patient corresponding to the patient number are unknown, the calculation of the treatment end time of the patient corresponding to the patient number is suspended, and the treatment end time of the next patient is calculated until the calculation of the treatment end time of all patients under all treatment equipment is completed;
s306, searching a patient number of the surgical service from left to right in each row of surgical service scheduling data of the coding matrix, and if the patient number does not appear in each row of surgical service scheduling data, outputting the end time of each medical service of the patient corresponding to the patient number; otherwise, acquiring the operation ending time of the previous patient in the corresponding operating room, and if the operation ending time of the previous patient is later than the final inquiry time of the patient corresponding to the patient number, taking the sum of the operation ending time of the previous patient and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number; if the operation ending time of the previous patient is earlier than or equal to the final inquiry time of the patient corresponding to the patient number, taking the sum of the final inquiry time of the patient corresponding to the patient number and the operation required time of the patient corresponding to the patient number as the operation ending time of the patient corresponding to the patient number, and calculating the operation ending time of the next patient until the operation ending time of all patients in all operating rooms is calculated;
s307, determining the final inquiry end time of the last patient of each doctor according to the inquiry end time of each patient on each doctor; determining the examination and treatment time of the last patient on each examination device according to the examination and treatment time of each patient on each examination device; determining the treatment ending time of the last patient on each treatment device according to the treatment ending time of each patient on each treatment device; determining the operation ending time of the last patient in each operation room according to the operation ending time of each patient in the operation room;
s308, taking the reciprocal of the maximum value of the final inquiry end time of the last patient of each doctor, the examination end time of the last patient on each examination device, the treatment end time of the last patient on each treatment device and the operation end time of the last patient in each operating room as the fitness value of the chromosome; the model updating module is used for executing S400 and carrying out neighborhood search on the dominant solution to obtain an elite solution; performing neighborhood search on the disadvantage solution to obtain a non-elite solution; updating the probability distribution model according to the elite solution and the non-elite solution;
a judging module, configured to execute S500, and judge whether the current iteration number reaches the maximum iteration number: if so, taking the optimal elite solution in the last iteration process as a global optimal solution and outputting the global optimal solution; otherwise, adding 1 to the current iteration number, and returning to the population generation module to execute S200.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811360433.2A CN109509548B (en) | 2018-11-15 | 2018-11-15 | Outpatient medical service scheduling method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811360433.2A CN109509548B (en) | 2018-11-15 | 2018-11-15 | Outpatient medical service scheduling method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109509548A CN109509548A (en) | 2019-03-22 |
| CN109509548B true CN109509548B (en) | 2021-08-24 |
Family
ID=65748638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811360433.2A Active CN109509548B (en) | 2018-11-15 | 2018-11-15 | Outpatient medical service scheduling method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109509548B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651657B (en) * | 2020-12-31 | 2023-06-27 | 杭州电子科技大学 | Health physical examination service flow optimization scheduling method |
| CN113066568B (en) * | 2021-04-13 | 2022-09-16 | 安徽医科大学第二附属医院 | PETCT inspection scheduling method based on GVNS-OP algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096728A (en) * | 2010-11-29 | 2011-06-15 | 中山大学 | Power electronic circuit optimizing method based on estimation of distribution algorithms |
| CN104516785A (en) * | 2014-12-19 | 2015-04-15 | 上海电机学院 | Cloud computing resource scheduling system and method |
| CN104537425A (en) * | 2014-11-20 | 2015-04-22 | 昆明理工大学 | Optimized scheduling method for production and assembly process of automobile air conditioner air outlet |
| CN105512755A (en) * | 2015-11-30 | 2016-04-20 | 清华大学 | Decomposition-based multi-objective distribution estimation optimization method |
| CN107578178A (en) * | 2017-09-11 | 2018-01-12 | 合肥工业大学 | Based on the dispatching method and system for becoming neighborhood search and gravitation search hybrid algorithm |
| CN107590603A (en) * | 2017-09-11 | 2018-01-16 | 合肥工业大学 | Based on the dispatching method and system for improving change neighborhood search and differential evolution algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10446265B2 (en) * | 2015-09-25 | 2019-10-15 | Varian Medical Systems International Ag | Clinical goal treatment planning and optimization |
-
2018
- 2018-11-15 CN CN201811360433.2A patent/CN109509548B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096728A (en) * | 2010-11-29 | 2011-06-15 | 中山大学 | Power electronic circuit optimizing method based on estimation of distribution algorithms |
| CN104537425A (en) * | 2014-11-20 | 2015-04-22 | 昆明理工大学 | Optimized scheduling method for production and assembly process of automobile air conditioner air outlet |
| CN104516785A (en) * | 2014-12-19 | 2015-04-15 | 上海电机学院 | Cloud computing resource scheduling system and method |
| CN105512755A (en) * | 2015-11-30 | 2016-04-20 | 清华大学 | Decomposition-based multi-objective distribution estimation optimization method |
| CN107578178A (en) * | 2017-09-11 | 2018-01-12 | 合肥工业大学 | Based on the dispatching method and system for becoming neighborhood search and gravitation search hybrid algorithm |
| CN107590603A (en) * | 2017-09-11 | 2018-01-16 | 合肥工业大学 | Based on the dispatching method and system for improving change neighborhood search and differential evolution algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于变邻域分布估计算法的数传资源配置优化;常飞等;《系统工程理论与实践》;20110831;第31卷(第8期);第1546-1553页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109509548A (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tsai et al. | A stochastic appointment scheduling system on multiple resources with dynamic call-in sequence and patient no-shows for an outpatient clinic | |
| Wang | Patient flow modeling and optimal staffing for emergency departments: A Petri net approach | |
| CN109509548B (en) | Outpatient medical service scheduling method, system and storage medium | |
| CN105913846A (en) | Method, device and system for realizing voice registration | |
| CN111009311A (en) | Medical resource recommendation method, device, medium and equipment | |
| US20160350499A1 (en) | System and method for optimizing allocation of medical units for patient treatment | |
| CN113792920B (en) | Single-consulting-room-oriented hospital consultation sequence optimization method and device | |
| Jayasuriya et al. | Experimental study on an efficient dengue disease management system: planning and optimizing hospital staff allocation | |
| CN107067117A (en) | A kind of distribution method to the medical treatment project implementation time | |
| US20230154599A1 (en) | System and method for identifying optimal appointment times of patients | |
| Huang et al. | Decision support system for rehabilitation scheduling to enhance the service quality and the effectiveness of hospital resource management | |
| CN111160607A (en) | Medical maintenance institution scheduling method, system, equipment and medium based on evolutionary algorithm | |
| Xiao et al. | A column generation-based heuristic for a rehabilitation patient scheduling and routing problem | |
| CN116153475A (en) | Medical treatment and triage queuing method, device, equipment and storage medium | |
| Bruballa et al. | Scheduling model for non-critical patients admission into a hospital emergency department | |
| US20090254360A1 (en) | Systems and Methods For Healthcare Asset Allocation | |
| Ma et al. | A MOEA/D based approach for hospital department layout design | |
| CN113506602B (en) | Remote medical platform doctor scheduling method and device | |
| Koeleman et al. | Appointment scheduling using optimisation via simulation | |
| CN115885300A (en) | Task scheduling method, device, computing processing equipment, computer program and computer readable medium | |
| Hulshof et al. | Tactical planning in healthcare using approximate dynamic programming | |
| Frimodig et al. | A Column Generation Approach for Radiation Therapy Patient Scheduling with Planned Machine Unavailability and Uncertain Future Arrivals | |
| CN112016979A (en) | User grouping method, device, equipment and computer readable storage medium | |
| CN115512816A (en) | Treatment scheduling method, device, equipment and storage medium | |
| Santoso et al. | Operating room scheduling using hybrid clustering priority rule and genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |