CN116137181B - Vaccination command scheduling method and system - Google Patents

Vaccination command scheduling method and system Download PDF

Info

Publication number
CN116137181B
CN116137181B CN202310220445.XA CN202310220445A CN116137181B CN 116137181 B CN116137181 B CN 116137181B CN 202310220445 A CN202310220445 A CN 202310220445A CN 116137181 B CN116137181 B CN 116137181B
Authority
CN
China
Prior art keywords
target
clinic
inoculation
vaccine
dimension
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
Application number
CN202310220445.XA
Other languages
Chinese (zh)
Other versions
CN116137181A (en
Inventor
李琦
张富斌
刘大鹏
王晶辉
刘鹏
刘曙光
王丽娜
唐强
高贵军
徐福虹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
World Window Information Co ltd
Disease Prevention And Control Center Of Hebei Province
Original Assignee
World Window Information Co ltd
Disease Prevention And Control Center Of Hebei Province
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by World Window Information Co ltd, Disease Prevention And Control Center Of Hebei Province filed Critical World Window Information Co ltd
Priority to CN202310220445.XA priority Critical patent/CN116137181B/en
Publication of CN116137181A publication Critical patent/CN116137181A/en
Application granted granted Critical
Publication of CN116137181B publication Critical patent/CN116137181B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/22—Social work
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention relates to the technical field of data processing, in particular to a vaccination command scheduling method and a vaccination command scheduling system, wherein the method comprises the following steps: obtaining the total number of vaccines to be distributed and vaccine circulation information corresponding to each target inoculation clinic; carrying out vaccine stock remaining prediction treatment on a target inoculation clinic; constructing a current vaccine dispatching distribution model; based on the pso algorithm, performing adaptive iterative solution on the current vaccine scheduling assignment model comprises: adaptively updating two acceleration parameter values of each target particle in each target dimension; performing the iteration on the current vaccine scheduling assignment model based on the updated acceleration parameter value; determining a target optimal solution; and carrying out scheduling and distributing on the vaccine to be distributed. The invention improves the rationality of vaccine distribution by carrying out data processing on the total number of vaccines to be distributed and the vaccine circulation information, and is mainly applied to the vaccination command and dispatch.

Description

Vaccination command scheduling method and system
Technical Field
The invention relates to the technical field of data processing, in particular to a vaccination command scheduling method and a vaccination command scheduling system.
Background
People often vaccinate at vaccination clinics, however vaccination clinics often fail to produce vaccines, often requiring the transportation of vaccines from vaccine production sites to multiple vaccination clinics. Since the locations of multiple vaccination clinics are different, the number of vaccines that need to be vaccinated at the same time is often different. When the number of vaccines is limited, if the vaccination command and the dispatch are not reasonable, the unreasonable vaccine distribution to a plurality of vaccination clinics is often caused, the residual vaccine is possibly caused in some vaccination clinics, and the emergency vaccine is absent in some vaccination clinics, so that the local people are inconvenient to vaccinate, if the residual vaccine is transported to the vaccination clinic with the emergency vaccine from the vaccination clinic with the residual vaccine, compared with the situation that the vaccine is reasonably distributed at the beginning, the transportation resource is often wasted, wherein the vaccination command and the dispatch can be the distribution of the number of the vaccines to a plurality of vaccination clinics. Therefore, reasonable partitioning of the vaccine is critical.
Currently, when a vaccine is distributed and scheduled, the following methods are generally adopted: the manual mode is adopted to determine the vaccine distribution quantity of a plurality of vaccination clinics, so as to realize the distribution of the vaccine. When distributing vaccines in an artificial manner, the determination of the number of vaccine distributions for a plurality of vaccination clinics is often subject to human subjectivity, often resulting in an unreasonable number of vaccines distributed for a plurality of vaccination clinics. There is also a way to distribute vaccines: and constructing an objective function of vaccine distribution scheduling, solving the objective function through a pso (particle swarm optimization ) algorithm, and distributing the vaccine according to the obtained solution, wherein the acceleration parameter value adopted when the solution is carried out through the pso algorithm is usually a preset fixed value. However, when the acceleration parameter value is fixed, the solution result may be trapped in a locally optimal solution, and solution fluctuation may be too large, so that vaccine allocation is often unreasonable, and if the objective function is set unreasonably, reasonability of vaccine allocation is also often low.
Disclosure of Invention
The summary of the invention is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. The summary of the invention is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In order to solve the technical problem of low rationality of vaccine distribution, the invention provides a vaccination command scheduling method and a vaccination command scheduling system.
In a first aspect, the present invention provides a vaccination command and dispatch method comprising:
obtaining the total number of vaccines to be distributed, and obtaining vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set according to the preset target circulation aging time;
according to vaccine circulation information corresponding to each target inoculation clinic, carrying out vaccine inventory remaining prediction processing on the target inoculation clinic to obtain inventory remaining indexes corresponding to the target inoculation clinic;
constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and inventory remaining indexes corresponding to each target inoculation clinic in the target inoculation clinic set;
based on a pso algorithm and a preset target iteration number, carrying out self-adaptive iteration solution on the current vaccine scheduling distribution model to obtain a target optimal solution, wherein the self-adaptive iteration solution on the current vaccine scheduling distribution model comprises the following steps: initializing a target parameter set required by solving by using a pso algorithm; according to the initialized target parameter set, performing first iteration on the current vaccine scheduling and distributing model to obtain a first iteration result; each iteration, except the first iteration, in the iterations of the target number of iterations includes: according to the last iteration result, adaptively updating two acceleration parameter values of each target particle in each target dimension, wherein the acceleration parameter values are included in the target parameter set; according to the last iteration result and the updated two acceleration parameter values of each target particle in each target dimension, carrying out the iteration on the current vaccine dispatching distribution model to obtain the iteration result; determining the target optimal solution according to each obtained iteration result;
And dispatching and distributing the vaccine to be distributed according to the target optimal solution.
Further, the obtaining, according to the preset target circulation aging time, vaccine circulation information corresponding to each target inoculation clinic in the target inoculation clinic set includes:
determining the number of target unit time lengths contained in the target circulation aging time length as a target number;
obtaining vaccine delivery quantity of the target vaccination outpatient service in each target unit time period in a preset target historical time period, and taking the vaccine delivery quantity as historical vaccine delivery quantity to obtain a historical vaccine delivery quantity set corresponding to the target vaccination outpatient service;
acquiring vaccine delivery amounts in a reference number of target unit time periods which are adjacent to the current target unit time period and are in front of the current target unit time period of the target inoculation clinic as target historical delivery amounts, and acquiring a target historical delivery amount set corresponding to the target inoculation clinic, wherein the reference number is the target number minus one;
acquiring the vaccine stock quantity of the target vaccination outpatient service at the end of a target unit time period of a first target quantity before the current target unit time period as a target historical stock quantity corresponding to the target vaccination outpatient service;
Respectively predicting the current target unit time period and vaccine demand in a reference number of target unit time periods which are adjacent to the current target unit time period after the current target unit time period according to the historical vaccine delivery volume set corresponding to the target vaccination clinic, and obtaining a target prediction demand set corresponding to the target vaccination clinic;
and forming the target historical warehouse-out quantity set, the target historical warehouse-out quantity and the target predicted demand quantity set corresponding to the target inoculation clinic into vaccine circulation information corresponding to the target inoculation clinic.
Further, according to the vaccine circulation information corresponding to each target inoculation clinic, performing vaccine inventory remaining prediction processing on the target inoculation clinic to obtain inventory remaining indexes corresponding to the target inoculation clinic, including:
determining the quantity of the vaccines to be distributed, which are required to be distributed to the target inoculation clinic in the current target unit time period, as the quantity to be distributed corresponding to the target inoculation clinic;
determining the sum of the target historical stock quantity corresponding to the target inoculation clinic and the quantity to be distributed as the quantity to be circulated corresponding to the target inoculation clinic;
Determining the sum of all elements in a target historical inventory set and a target predicted demand set corresponding to the target inoculation clinic as the overall estimated inventory corresponding to the target inoculation clinic;
determining the difference value of the quantity to be circulated and the overall estimated inventory corresponding to the target inoculation clinic as the overall residual quantity corresponding to the target inoculation clinic;
and determining the ratio of the total residual quantity corresponding to the target inoculation clinic to the quantity to be circulated as an inventory residual index corresponding to the target inoculation clinic.
Further, the constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and the inventory remaining indexes corresponding to each target vaccination clinic in the target vaccination clinic set includes:
determining the difference value between the maximum value and the minimum value in the inventory standby residual indexes corresponding to each target inoculation clinic in the target inoculation clinic set as the target function value of the current vaccine dispatching distribution model;
determining the number to be distributed corresponding to the target inoculation clinic to be greater than or equal to zero and less than or equal to the total number of vaccines to be distributed as a first condition which is required to be met by the target function;
And determining the accumulated value of the quantity to be distributed corresponding to each target inoculation clinic to be equal to the total quantity of vaccines to be distributed as a second condition which is required to be met by the target function.
Further, according to the previous iteration result, adaptively updating two acceleration parameter values of each target particle in each target dimension, where the two acceleration parameter values are included in the target parameter set, including:
determining an absolute value of a difference value between a global optimal solution of the target dimension and a current solution of the target particle in the target dimension, which is included in a last iteration result, as a first difference of the target particle in the target dimension;
determining an absolute value of a difference value between a current solution of the target particle in the target dimension and an individual historical optimal solution included in a last iteration result as a second difference of the target particle in the target dimension;
performing positive correlation mapping on the first difference of the target particles in the target dimension, and performing negative correlation mapping on the second difference of the target particles in the target dimension to obtain a target change index of the target particles in the target dimension;
performing two classifications on target change indexes of each target particle in the target dimension, and determining classification thresholds;
Normalizing the difference value between the target change index of the target particle in the target dimension and the classification threshold value to obtain an acceleration change index of the target particle in the target dimension;
determining the current speed variation of each target particle in the target dimension, and screening the largest current speed variation from the current speed variation of each target particle in the target dimension to be used as the current maximum speed variation of the target dimension;
and determining the product of the current maximum speed variation of the target dimension and the acceleration variation index of the target particle in the target dimension as two updated acceleration parameter values of the target particle in the target dimension.
Further, the performing positive correlation mapping on the first difference of the target particle in the target dimension, and performing negative correlation mapping on the second difference of the target particle in the target dimension, to obtain a target change index of the target particle in the target dimension, includes:
determining a difference value of a first difference and a second difference of the target particles in the target dimension as a first change index of the target particles in the target dimension;
And determining the first change index power of the target particles with natural constants in the target dimension as a target change index of the target particles in the target dimension.
Further, the method further comprises:
determining the number of target inoculation clinics with the target historical stock quantity being greater than zero in the target inoculation clinic set as a stock base;
determining the sum of each target historical delivery volume in a target historical delivery volume set corresponding to each target inoculation clinic and the vaccine delivery volume of the target inoculation clinic in the current target unit time period as an aging delivery volume corresponding to the target inoculation clinic;
when the time-effect stock quantity corresponding to the target inoculation outpatient service is greater than or equal to the target historical stock quantity corresponding to the target inoculation outpatient service, determining the target inoculation outpatient service as a cleared outpatient service;
determining the ratio of the number of the clear clinics to the inventory base number as a clear ratio;
the cleared proportion is stored in the target database.
Further, the scheduling and distributing the vaccine to be distributed according to the target optimal solution includes:
and controlling a target vehicle, and transporting the number of the vaccines to be distributed, which are included in the target optimal solution, to a corresponding target inoculation clinic.
In a second aspect, the present invention provides a vaccination commanding and dispatching system comprising a processor and a memory, said processor being adapted to process instructions stored in said memory to implement a vaccination commanding and dispatching method as described above.
The invention has the following beneficial effects:
according to the vaccination command scheduling method, the technical problem of low rationality of vaccine distribution is solved and the rationality of vaccine distribution is improved by processing the total number of vaccines to be distributed and the vaccine circulation information. Firstly, obtaining the total number of vaccines to be distributed, and obtaining vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set according to the preset target circulation aging time. The total number of the vaccines to be distributed and the vaccine circulation information are acquired, so that the subsequent data processing can be conveniently carried out on the total number of the vaccines to be distributed and the vaccine circulation information, and the vaccines to be distributed are distributed. And then, according to vaccine circulation information corresponding to each target inoculation clinic, carrying out vaccine inventory remaining prediction processing on the target inoculation clinic to obtain inventory remaining indexes corresponding to the target inoculation clinic. In practical situations, for the target vaccination outpatient service, the smaller the vaccine inventory remains, the smaller the vaccine remaining of the target vaccination outpatient service is often indicated, so that the inventory remaining index can often represent the vaccine remaining condition of the target vaccination outpatient service, and the subsequent vaccine to be distributed can be conveniently distributed. And then, constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and inventory standby residual indexes corresponding to each target vaccination clinic in the target vaccination clinic set. The total number of the vaccines to be distributed and the residual indexes of the stock are comprehensively considered, so that the construction rationality of the current vaccine dispatching distribution model can be improved, and the follow-up rationality of the vaccines to be distributed can be improved. Then, based on a pso algorithm and a preset target iteration number, performing adaptive iteration solution on the current vaccine scheduling distribution model to obtain a target optimal solution, wherein the method comprises the following steps: according to the last iteration result, adaptively updating two acceleration parameter values of each target particle in each target dimension; according to the last iteration result and the updated two acceleration parameter values of each target particle in each target dimension, carrying out the iteration on the current vaccine scheduling distribution model; and determining a target optimal solution. It should be noted that, the accelerating parameter values involved in iteration are updated in real time, so that the problem that the solving result is trapped in a local optimal solution and the fluctuation is too large is often avoided, the possibility that the determined target optimal solution is an actual optimal solution is often improved, the target optimal solution is often more approximate to the actual optimal solution, and therefore the rationality of vaccine allocation is improved. And finally, dispatching and distributing the vaccine to be distributed according to the target optimal solution. Therefore, the invention realizes the real-time update of the acceleration parameter value by carrying out data processing on the total number of the vaccines to be distributed and the vaccine circulation information, thereby avoiding the problem that the solving result is trapped in the local optimal solution and the fluctuation is overlarge, avoiding the interference of human factors and further improving the rationality of vaccine distribution.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a vaccination command and dispatch method of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of the specific implementation, structure, features and effects of the technical solution according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a vaccination commanding and dispatching method, which comprises the following steps:
obtaining the total number of vaccines to be distributed, and obtaining vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set according to the preset target circulation aging time;
according to the vaccine circulation information corresponding to each target inoculation clinic, carrying out vaccine inventory remaining prediction processing on the target inoculation clinic to obtain inventory remaining indexes corresponding to the target inoculation clinic;
constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and inventory remaining indexes corresponding to each target inoculation clinic in the target inoculation clinic set;
based on a pso algorithm and preset target iteration times, carrying out self-adaptive iteration solution on a current vaccine scheduling distribution model to obtain a target optimal solution;
and dispatching and distributing the vaccine to be distributed according to the target optimal solution.
The following detailed development of each step is performed:
referring to fig. 1, a flow chart of some embodiments of a vaccination command scheduling method of the present invention is shown. The vaccination commanding and dispatching method comprises the following steps:
step S1, obtaining the total number of vaccines to be distributed, and obtaining vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set according to the preset target circulation aging time.
In some embodiments, the total number of vaccines to be distributed may be obtained, and the vaccine circulation information corresponding to each target vaccination clinic in the target vaccination clinic set may be obtained according to a preset target circulation aging time.
The vaccine to be dispensed may be a vaccine that needs to be dispensed to the target vaccination clinic, i.e. a vaccine that needs to be transported to the target vaccination clinic. The target vaccination clinic is a vaccination clinic where vaccination is possible. In order to facilitate the distribution management of the vaccine, the vaccine is often distributed once at intervals of a certain period, so that the target circulation aging period can be a period corresponding to a preset time interval between any two adjacent vaccine distributions. For example, the target flow aging period may be 2 days, i.e., 48 hours. The vaccine circulation information may be circulation information of a target vaccine in a target vaccination clinic. For example, vaccine circulation information may characterize the ex-warehouse, in-warehouse, and inventory conditions of the vaccine of interest. The vaccine of interest may be of the same specification type as the vaccine to be dispensed. The vaccine to be dispensed may be the target vaccine to be dispensed. For example, the vaccine of interest may be a new crown vaccine. The target vaccination clinic may be a new crown vaccination clinic. The vaccine to be dispensed may be the vaccine that needs to be dispensed to the new crown vaccination clinic.
Generally, the shorter the period of time between the start of storage of the vaccine at the vaccination clinic and the time of vaccination, the more the vaccine tends to be more circulating and time-efficient at the vaccination clinic. Therefore, the ideal storage time of the vaccine in the vaccination clinic can be set according to actual situations, the vaccinated vaccine in the ideal storage time can be considered as the vaccine meeting the timeliness of the vaccine, and the ideal storage time can be also called as the expected storage time. Thus, the ideal storage period may be set to a period corresponding to the time interval between two adjacent vaccine dispensations.
As an example, this step may include the steps of:
in a first step, the total number of vaccines to be dispensed is obtained.
And a second step of determining the number of the target unit time lengths contained in the target circulation aging time length as a target number.
The target flow aging time period may include at least one target unit time period. The ratio of the target flow aging time period to the target unit time period may be an integer. The target unit time length may be a preset unit time length. For example, the target unit time period may be one day, that is, 24 hours.
For example, when the target unit time period is 1 day and the target circulation aging time period is 2 days, the target number may be 2.
Thirdly, acquiring the vaccine delivery quantity of the target vaccination outpatient in each target unit time period in a preset target historical time period, and taking the vaccine delivery quantity as a historical vaccine delivery quantity to obtain a historical vaccine delivery quantity set corresponding to the target vaccination outpatient.
The vaccine delivery amount may be the delivery amount of the target vaccine, i.e. the amount of the target vaccine to be vaccinated at the target vaccination clinic. The target historical period may be a historical period when the vaccine is sufficient. The duration corresponding to the target history period may be a preset duration. For example, the duration corresponding to the target history period may be 30 days.
It should be noted that, since the historical vaccine delivery amount set is obtained to predict the vaccine demand amount in the future time period, when the target historical time period is a historical time period when the vaccine is sufficient, a case that the historical vaccine delivery amount cannot characterize the vaccine demand amount in the corresponding target unit time period due to insufficient vaccine can be eliminated, so that the accuracy of the subsequent prediction can be improved. And the longer the duration corresponding to the target historical time period, the more accurate the subsequent predictions tend to be.
Fourth, obtaining vaccine delivery amounts in a reference number of target unit time periods which are adjacent to the current target unit time period and are in front of the current target unit time period, and taking the vaccine delivery amounts as target historical delivery amounts to obtain target historical delivery amount sets corresponding to the target vaccination clinics.
Wherein the reference number may be the target number minus one. When the duration corresponding to the target unit time period is 1 day, the current target unit time period may be today.
For example, when the target number is 2 and the current target unit time period is today, the vaccine out-warehouse amount before today and within 1 day adjacent to today may be the vaccine out-warehouse amount yesterday. At this time, the target historical inventory set may have 1 target historical inventory, and the target historical inventory may be yesterday's vaccine inventory.
And fifthly, acquiring the vaccine stock quantity of the target vaccination outpatient before the current target unit time and at the end of the target unit time of the first target quantity, and taking the vaccine stock quantity as the target historical stock quantity corresponding to the target vaccination outpatient.
The stock of vaccine may be, among other things, the stock of the vaccine of interest, i.e. the number of vaccines of interest stored in the vaccination clinic of interest.
For example, when the target number is 2 and the current target unit time period is the present day, the stock quantity at the end of the 2 nd target unit time period before the present day may be the vaccine stock quantity at the end of the previous day.
And sixthly, respectively predicting the current target unit time period and vaccine demand in a reference number of target unit time periods which are adjacent to the current target unit time period after the current target unit time period according to the historical vaccine delivery volume set corresponding to the target inoculation clinic, and obtaining a target prediction demand set corresponding to the target inoculation clinic.
For example, when the target number is 2 and the current target unit time period is today, a nonlinear fit may be performed on the historical vaccine delivery volume set using a least squares method, and based on the fit results, the vaccine demands today and tomorrow may be predicted. At this time, the target predicted demand set may include: predicted today's vaccine requirements and predicted tomorrow's vaccine requirements.
Seventh, the target historical warehouse quantity set, the target historical warehouse quantity and the target predicted demand quantity set corresponding to the target inoculation clinic are combined to form vaccine circulation information corresponding to the target inoculation clinic.
The vaccine circulation information corresponding to the target inoculation clinic can include: the target inoculation clinic corresponds to a target historical warehouse-out amount set, a target historical warehouse-out amount set and a target forecast demand amount set.
The total number of the vaccines to be distributed and the vaccine circulation information are acquired, so that the subsequent data processing can be conveniently carried out on the total number of the vaccines to be distributed and the vaccine circulation information, and the vaccines to be distributed are distributed.
And S2, performing vaccine inventory remaining prediction processing on the target inoculation outpatient service according to the vaccine circulation information corresponding to each target inoculation outpatient service, and obtaining inventory remaining indexes corresponding to the target inoculation outpatient service.
In some embodiments, the vaccine inventory remaining prediction process may be performed on the target vaccination outpatient service according to the vaccine circulation information corresponding to each target vaccination outpatient service, so as to obtain an inventory remaining index corresponding to the target vaccination outpatient service.
As an example, this step may include the steps of:
and determining the quantity of the vaccine to be distributed, which is required to be distributed to the target inoculation clinic in the current target unit time period, as the quantity to be distributed corresponding to the target inoculation clinic.
The quantity to be distributed corresponding to the target inoculation clinic is the quantity to be solved by the invention.
And secondly, determining the sum of the target historical stock quantity and the quantity to be distributed corresponding to the target inoculation clinic as the quantity to be circulated corresponding to the target inoculation clinic.
And thirdly, determining the sum of all elements in the target historical warehouse-out quantity set and the target predicted demand quantity set corresponding to the target inoculation clinic as the overall estimated warehouse-out quantity corresponding to the target inoculation clinic.
And step four, determining the difference value between the quantity to be circulated and the overall estimated inventory corresponding to the target inoculation clinic as the overall residual quantity corresponding to the target inoculation clinic.
And fifthly, determining the ratio of the total residual quantity corresponding to the target inoculation clinic to the quantity to be circulated as the stock residual index corresponding to the target inoculation clinic.
For example, when the target number is 2 and the current target unit time period is today, the number of target historical ex-warehouse amounts in the target historical ex-warehouse amount set may be 1, the target predicted demand amount in the target predicted demand amount set may be 2, the target historical ex-warehouse amount set may include yesterday's vaccine ex-warehouse amount, the target predicted demand amount set may include predicted today's and tomorrow's vaccine demand amounts, and the formula corresponding to the inventory reserve index corresponding to the determined target vaccination clinic may be:
wherein, the liquid crystal display device comprises a liquid crystal display device,is the first in the target inoculation clinic setiAnd (5) corresponding inventory standby residual indexes of the target inoculation clinics.iIs the serial number of the target inoculation clinic in the target inoculation clinic set. />Is the first in the target inoculation clinic setiThe target historical stock corresponding to each target vaccination clinic may be the stock of vaccine at the end of the previous day. />Is the first in the target inoculation clinic setiThe number to be distributed corresponding to the target inoculation clinic is also the number to be solved. / >Is the first in the target inoculation clinic setiThe target historical inventory set corresponding to each target vaccination clinic includes yesterday's vaccine inventory. />Is the first in the target inoculation clinic setiThe set of target predicted requirements for each target vaccination clinic includes predicted today's vaccine requirements. />Is the first in the target inoculation clinic setiThe set of target predicted requirements for each target vaccination clinic includes a predicted tomorrow's vaccine requirements. />Is the first in the target inoculation clinic setiThe number of to-be-transferred corresponding to each target inoculation clinic. />Is the first in the target inoculation clinic setiAnd (5) overall estimated warehouse out quantity corresponding to each target inoculation clinic. />Is the first in the target inoculation clinic setiOverall remaining number for each target vaccination clinic.
It should be noted that the number of the substrates,the number of target vaccines in the current target unit time period can be characterized.The number of target vaccines that need to be vaccinated before the next vaccine dispense can be characterized.The residual amount of the target vaccine before the next vaccine dispense can be characterized.The remaining proportion of the target vaccine prior to the next vaccine dispense can be characterized. Thus, when->The larger the tends to explain the first iThe greater the remaining proportion of target vaccine before the vaccine is dispensed from the individual target vaccination clinic, the less target vaccine may be dispensed to the first placeiThe individual target inoculation clinics. In this example, the last vaccine dispensing time may be the previous day, the current vaccine dispensing time may be today, and the next vaccine dispensing time may be the next day.
And S3, constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and inventory remaining indexes corresponding to each target inoculation clinic in the target inoculation clinic set.
In some embodiments, the current vaccine dispatch allocation model may be constructed according to the total number of vaccines to be allocated and the inventory reserve indicators corresponding to each target vaccination clinic in the target vaccination clinic set.
The current vaccine dispatching distribution model can be used for determining the corresponding quantity to be distributed of each target inoculation clinic.
As an example, this step may include the steps of:
and a first step of determining the difference value between the maximum value and the minimum value in the inventory standby residual indexes corresponding to each target inoculation clinic in the target inoculation clinic set as the target function value of the current vaccine dispatching distribution model.
The number to be distributed corresponding to the target inoculation clinic can be the amount to be determined in the target function.
For example, the objective function of the current vaccine schedule allocation model may be:
wherein, the liquid crystal display device comprises a liquid crystal display device,is the objective function value of the current vaccine dispatch allocation model. />Is the object ofInventory waiting remaining indexes corresponding to the 1 st target inoculation clinic in the inoculation clinic set. />Is the stock waiting remaining index corresponding to the 2 nd target inoculation clinic in the target inoculation clinic set. />Is the first in the target inoculation clinic setiAnd (5) corresponding inventory standby residual indexes of the target inoculation clinics. />Is the first in the target inoculation clinic setnAnd (5) corresponding inventory standby residual indexes of the target inoculation clinics.iIs the serial number of the target inoculation clinic in the target inoculation clinic set.iThe range of values of (2) may be 1,n]is an integer of (a).nIs the number of target vaccination clinics in the target vaccination outpatient set. />The inventory standby remaining index corresponding to each target inoculation clinic in the target inoculation clinic set can be represented. />Taking the maximum value of the stock remaining indexes corresponding to each target inoculation clinic in the target inoculation clinic set. />The minimum value of the inventory standby residual indexes corresponding to each target inoculation clinic in the target inoculation clinic set is taken.
When the following is performedThe smaller the time, the more similar the target vaccine remaining proportion of each target vaccination clinic before the next vaccine distribution is, the more likely the target vaccine remaining of each target vaccination clinic before the next vaccine distribution is balanced, and the more reasonable the distribution is.
And secondly, determining the number to be distributed corresponding to the target inoculation clinic to be greater than or equal to zero and less than or equal to the total number of vaccines to be distributed as a first condition which is required to be met by the target function.
Thirdly, determining the accumulated value of the quantity to be distributed corresponding to each target inoculation clinic to be equal to the total quantity of vaccines to be distributed as a second condition which is required to be met by the target function.
And S4, carrying out self-adaptive iterative solution on the current vaccine scheduling distribution model based on a pso algorithm and preset target iteration times to obtain a target optimal solution.
In some embodiments, the adaptive iterative solution may be performed on the current vaccine scheduling assignment model based on a pso (particle swarm optimization ) algorithm and a preset target iteration number, to obtain a target optimal solution.
The target iteration number may be a preset iteration number. For example, the target number of iterations may be 100. The objective optimal solution may be a solution when the objective function value is minimum.
It should be noted that, the acceleration parameter values involved in the solution are updated in real time, so that the problem that the solution result is trapped in a local optimal solution and the fluctuation is too large is often avoided, the possibility that the determined target optimal solution is an actual optimal solution is often improved, and thus the rationality of vaccine distribution is improved.
As an example, this step may include the steps of:
the first step is to initialize the target parameter set needed when solving by using the pso algorithm.
Wherein the set of target parameters may include: the number of target particles, the target dimensions, the acceleration parameters, the inertia factor, the speed and the position of the target particles. The target particles and target dimensions may be particles and dimensions when solved using the pso algorithm. The acceleration parameters are also called learning factors, acceleration coefficients and acceleration factors. The inertial factor is also called inertial weight.
For example, when initializing the target parameter set, the number of target particles may be set to 50, the number to be allocated corresponding to each target inoculation clinic is set to one target dimension, both acceleration parameter values are set to 2, the inertia factor is set to 1.2, and the speed and position of the target particles may be randomly initialized. In each iteration, the two acceleration parameter values involved in the solution of the pso algorithm may be the same. The value range of the acceleration parameter value may be set to 0, 4. The range of values for the inertia factor may be [0.4,2].
And secondly, performing first iteration on the current vaccine scheduling and distributing model according to the initialized target parameter set to obtain a first iteration result.
Wherein, each iteration result can be the result obtained in the iteration process. The iterative result may include: a global optimal solution of each target dimension, a current solution and an individual history optimal solution of each target particle in each target dimension, a target global optimal solution, and a target individual optimal solution of each target particle. The global optimal solution for each target dimension may be the historical optimal position of the target dimension for a target particle swarm in a certain iteration. For example, the global optimal solution of the first target dimension included in the first iteration result may be a historical optimal position of the first target dimension of the target particle swarm in the first iteration. The current solution for each target particle in each target dimension may be the solution for that target particle in that target dimension in a certain iteration. For example, the first iteration result may include a current solution of the first target particle in the first target dimension that is a solution of the first target particle in the first target dimension in the first iteration. The individual historical optimal solution for each target particle in each target dimension may be the historical optimal position for that target particle in that target dimension in a certain iteration. For example, the first iteration result may include an individual historical optimal solution for the first target particle in the first target dimension that is the historical optimal position for the first target particle in the first target dimension in the first iteration. The target global optimal solution may be a total solution for each target dimension. The target global optimal solution may be a historical optimal position of the target particle swarm in a certain iteration. For example, the target global optimal solution included in the first iteration result may be a historical optimal position of the target particle swarm in the first iteration. The target individual optimal solution for each target particle may be the historical optimal position of the target particle in a certain iteration. For example, the first iteration result may include a target individual optimal solution for the first target particle that may be a historical optimal position for the first target particle in the first iteration.
For example, according to the initialized target parameter set, performing first iteration on the current vaccine scheduling distribution model by using a pso algorithm, so as to obtain a global optimal solution of each target dimension, a current solution and an individual history optimal solution of each target particle in each target dimension, a target global optimal solution, and a target individual optimal solution of each target particle.
Third, each iteration other than the first iteration in the target number of iterations may include: according to the last iteration result, adaptively updating two acceleration parameter values of each target particle in each target dimension, wherein the acceleration parameter values are included in the target parameter set; according to the last iteration result and the updated two acceleration parameter values of each target particle in each target dimension, carrying out the iteration on the current vaccine dispatching distribution model to obtain the iteration result; and determining the target optimal solution according to each obtained iteration result.
For example, based on the last iteration result, adaptively updating the two acceleration parameter values for each target particle in each target dimension included in the set of target parameters may comprise the sub-steps of:
and a first sub-step of determining an absolute value of a difference between a global optimal solution of the target dimension included in the last iteration result and a current solution of the target particle in the target dimension as a first difference of the target particle in the target dimension.
And a second sub-step of determining the absolute value of the difference between the current solution of the target particle in the target dimension and the individual history optimal solution included in the last iteration result as a second difference of the target particle in the target dimension.
And a third sub-step of performing positive correlation mapping on the first difference of the target particles in the target dimension and performing negative correlation mapping on the second difference of the target particles in the target dimension to obtain a target change index of the target particles in the target dimension.
For example, performing positive correlation mapping on the first difference of the target particle in the target dimension and performing negative correlation mapping on the second difference of the target particle in the target dimension may include the following steps:
first, a difference between a first difference and a second difference of the target particles in the target dimension is determined as a first change index of the target particles in the target dimension.
Then, the first change index power of the target particle in the target dimension of the natural constant is determined as a target change index of the target particle in the target dimension.
For example, the formula corresponding to the target change index of each target particle in each target dimension may be:
Wherein, the liquid crystal display device comprises a liquid crystal display device,is the firsttIn the iterative process, the firstjThe target particle is at the firstiTarget change index for each target dimension. />Is the firsttIn the iterative process, the firstjThe target particle is at the firstiA first difference in the respective target dimensions. />Is the firsttIn the iterative process, the firstjThe target particle is at the firstiA second difference in the respective target dimensions. />Is the firsttIn the course of a number of iterations,first, thejThe target particle is at the firstiA first variation index for each target dimension. />Is of natural constantTo the power. />Is the firsttIn the iterative process, the firstiGlobal optimal solutions for individual target dimensions. />Is the firsttIn the iterative process, the firstjThe target particle is at the firstiA current solution for each target dimension. />Is->Is the absolute value of (c). />Is the firsttIn the iterative process, the firstjThe target particle is at the firstiIndividual history optimal solutions for individual target dimensions. />Is thatIs the absolute value of (c).tIs the sequence number of the iteration number.jIs the sequence number of the target particle. Since the number to be distributed corresponding to each target inoculation clinic is set to be one target dimension during initialization, andiis the serial number of the target inoculation clinic in the target inoculation clinic set, thusiBut also the sequence number of the target dimension. />
It should be noted that the number of the substrates,can characterize the firsttIn the second iteration process iIndividual targetsGlobally optimal solution and first dimensionjThe target particle is at the firstiThe larger the difference between the current solutions for the individual target dimensions, the larger the value thereof tends to account for the larger the difference.Can characterize the firsttIn the second iteration processjThe target particle is at the firstiThe larger the difference between the current solution of the individual target dimension and the individual history optimal solution, the larger the value thereof tends to be, which is explained. />Can realize the followingjThe target particle is at the firstiThe first difference of each target dimension is subjected to positive correlation mapping, and the first difference can be subjected tojThe target particle is at the firstiThe second difference of the respective target dimensions is mapped negatively, in practice not more than +.>It is possible to realize a positive correlation mapping of the first difference and a negative correlation mapping of the second difference>Can also be realized, wherein->Is a preset number greater than 0, mainly to prevent the denominator from being 0. So the firsttIn the iterative process, the firstjThe target particle is at the firstiThe target change index of the individual target dimensions can also be expressed as +.>. Thus (S)>The larger the current solution, the more unsuitable it is for convergence, and the more suitable it is for finding new solutions that vary widely, the more random it should be. />Smaller tends to indicate that the current solution is more suitable for convergence The method is more suitable for searching the approximate global optimal solution, so that the randomness degree of the solution is smaller.
And a fourth sub-step, performing two classification on the target change index of each target particle in the target dimension, and determining a classification threshold.
For example, first, a classification algorithm of k-means, k=2 may be used to perform a two-classification on the target change index of each target particle in the target dimension, so as to obtain two target classes. Then, the average value of the target change index in each target category may be determined as the change average value corresponding to the target category. Finally, the smallest target change index in the target category with a larger average value of the two target categories can be determined as the classification threshold.
And a fifth substep, normalizing the difference value between the target change index of the target particle in the target dimension and the classification threshold value to obtain the acceleration change index of the target particle in the target dimension.
For example, a sigmoid function may be used to normalize the difference between the target change index of each target particle in each target dimension and the classification threshold value, so as to obtain the acceleration change index of the target particle in the target dimension.
And a sixth substep, determining the current speed variation of each target particle in the target dimension, and screening the largest current speed variation from the current speed variation of each target particle in the target dimension as the current maximum speed variation of the target dimension.
The current speed variation of a certain target particle in a certain target dimension determined by adopting a certain iteration result can be the speed variation of the target particle in the target dimension in the iteration process. The speed variation may be a vector.
And a seventh substep, determining the product of the current maximum speed variation of the target dimension and the acceleration variation index of the target particle in the target dimension as two updated acceleration parameter values of the target particle in the target dimension.
It should be noted that the value range of the acceleration parameter value may be set to [0,4], and when the determined acceleration parameter value is greater than 4, the acceleration parameter value may be set to 4, and when the determined acceleration parameter value is less than 0, the acceleration parameter value may be set to 0.
For another example, according to the last iteration result and the updated two acceleration parameter values of each target particle in each target dimension, the current vaccine scheduling and distributing model is iterated for the time to obtain the iteration result, wherein a speed update formula of the iteration process can be as follows:
Wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstjThe target particle is at the firstt+1 iteration of the processiThe speed of the individual target dimensions.wIs an inertial factor. />Is the firstjThe target particle is at the firsttIn the second iterationiThe speed of the individual target dimensions. />And->Is an acceleration parameter value, updated in real time at each iteration, wherein +.>。/>And->Is [0,1 ]]The random number in the memory can take different values. />Is the firstjThe target particle is at the firsttIn the second iterationiHistorical optimal position of individual target dimensions, i.e. the firsttIn the iterative process, the firstjThe target particle is at the firstiThe individual history optimal solution of the individual target dimension, i.e. equivalent to +.>。/>Is the firstjThe target particle is at the firsttIn the second iterationiThe location of the individual target dimensions. />Is the target particle group in the firsttIn the second iterationiHistorical optimal position of individual target dimensions, i.e. the firsttIn the iterative process, the firstiGlobally optimal solutions for the individual target dimensions, i.e. equivalent to +.>。tIs the sequence number of the iteration number.jIs the sequence number of the target particle. In the formulaiIs the sequence number of the target dimension.
The location update formula of the iterative process may be:
wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstjThe target particle is at the firstt+1 iteration of the processiThe location of the individual target dimensions. />Is the firstjThe target particle is at the first tIn the second iterationiThe location of the individual target dimensions. />Is the firstjThe target particle is at the firstt+1 iteration of the processiTarget dimensionThe speed of the degrees.
It should be noted that, because the acceleration parameter may be used to balance the convergence speed and the search effect, the acceleration parameter value is updated in real time based on the convergence condition of the current solution, so that the determination of the acceleration parameter value may be more accurate, and further the possibility that the determined target optimal solution is an actual optimal solution may be improved, and the target optimal solution may be more close to the actual optimal solution.
For another example, determining the target optimal solution according to each obtained iteration result may include: and finally, iterating to obtain a target global optimal solution, and determining the target global optimal solution as the target optimal solution.
And S5, dispatching and distributing the vaccine to be distributed according to the target optimal solution.
In some embodiments, the vaccine to be dispensed may be scheduled for dispensing according to the target optimal solution described above.
Wherein the target vehicle may be a vehicle for transporting the vaccine to be dispensed.
As an example, the target vehicle may be controlled to transport the respective number of vaccines to be dispensed, which are included in the target optimal solution, to the corresponding target vaccination clinic.
For example, the number of vaccine to be dispensed corresponding to the target vaccination clinic may be transported to the target vaccination clinic by the target vehicle.
The target vehicle may be used to dispense the vaccine to be dispensed.
Optionally, the zeroed proportion may be determined and stored in a target database, where the zeroed proportion may be a proportion of the target inoculation clinic that has zeroed the inventory, and the target database may be a database for storing the zeroed proportion, and specifically may include the following steps:
first, determining the number of target inoculation clinics with the target historical stock quantity being greater than zero in the target inoculation clinic set as the stock base.
For example, when the target number is 2 and the current target unit time period is the present day, the target historical stock amount may be the vaccine stock amount at the end of the previous day. The target inoculation clinic with a target historical stock of greater than zero in the target inoculation clinic set may be a target inoculation clinic with stock at the end of the previous day. The inventory base may be the number of target inoculation clinics in inventory.
And secondly, determining the sum of each target historical delivery quantity in a target historical delivery quantity set corresponding to each target inoculation clinic and the vaccine delivery quantity of the target inoculation clinic in the current target unit time period as the time-effect delivery quantity corresponding to the target inoculation clinic.
The vaccine delivery amount in the current target unit time period can be the vaccine delivery amount in the current target unit time period which is actually recorded.
For example, when the target number is 2 and the current target unit time period is today, the number of target historical ex-warehouse amounts in the target historical ex-warehouse amount set may be 1, and the target historical ex-warehouse amount set may include yesterday's vaccine ex-warehouse amount. The corresponding aged out-warehouse quantity for the target vaccination clinic at this time may be the total vaccine out-warehouse quantity yesterday and today.
And thirdly, determining the target inoculation outpatient service as a cleared outpatient service when the time-dependent warehouse quantity corresponding to the target inoculation outpatient service is greater than or equal to the target historical warehouse quantity corresponding to the target inoculation outpatient service.
When the time-lapse inventory quantity corresponding to the target inoculation clinic is equal to the target historical inventory quantity corresponding to the target inoculation clinic, the target inoculation clinic can be considered to just clear the vaccine in inventory. When the time-out stock quantity corresponding to the target inoculation clinic is larger than the target historical stock quantity corresponding to the target inoculation clinic, the target inoculation clinic can be considered to clear the vaccine in stock, and some new target vaccines are newly supplemented for inoculation.
And fourthly, determining the ratio of the number of the zeroed out clinics to the inventory base as a zeroed out ratio.
And fifthly, storing the cleared proportion into a target database.
It should be noted that, the cleared proportion is stored in the target database, so that the cleared proportion can be conveniently queried later.
Based on the same inventive concept as the above method embodiments, the present invention provides a vaccination commanding and dispatching system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, implements the steps of a vaccination commanding and dispatching method.
In summary, the total number of the vaccines to be distributed and the vaccine circulation information are firstly obtained, so that the subsequent vaccine to be distributed can be conveniently distributed. And for the target inoculation clinic, the smaller the vaccine stock is, which usually indicates the target inoculation clinic has the smaller vaccine residual, so the stock remaining index can often represent the vaccine remaining condition of the target inoculation clinic, and the subsequent vaccine to be distributed can be conveniently distributed. Then, the total number of the vaccines to be distributed and the residual indexes of the stock are comprehensively considered, so that the construction rationality of the current vaccine dispatching distribution model can be improved, and the follow-up rationality of the vaccines to be distributed can be improved. Secondly, because the acceleration parameter can be used for balancing the convergence speed and the search effect, based on the convergence condition of the current solution, the acceleration parameter value is updated in real time, so that the determination of the acceleration parameter value is more accurate, the possibility that the determined target optimal solution is an actual optimal solution can be improved, the target optimal solution can be more approximate to the actual optimal solution, and the rationality of vaccine allocation can be improved.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.

Claims (7)

1. A vaccination commanding and dispatching method, comprising the steps of:
obtaining the total number of vaccines to be distributed, and obtaining vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set according to the preset target circulation aging time;
according to vaccine circulation information corresponding to each target inoculation clinic, carrying out vaccine inventory remaining prediction processing on the target inoculation clinic to obtain inventory remaining indexes corresponding to the target inoculation clinic;
constructing a current vaccine dispatching and distributing model according to the total number of the vaccines to be distributed and inventory remaining indexes corresponding to each target inoculation clinic in the target inoculation clinic set;
Based on a pso algorithm and a preset target iteration number, carrying out self-adaptive iteration solution on the current vaccine scheduling distribution model to obtain a target optimal solution, wherein the self-adaptive iteration solution on the current vaccine scheduling distribution model comprises the following steps: initializing a target parameter set required by solving by using a pso algorithm; according to the initialized target parameter set, performing first iteration on the current vaccine scheduling and distributing model to obtain a first iteration result; each iteration, except the first iteration, in the iterations of the target number of iterations includes: according to the last iteration result, adaptively updating two acceleration parameter values of each target particle in each target dimension, wherein the acceleration parameter values are included in the target parameter set; according to the last iteration result and the updated two acceleration parameter values of each target particle in each target dimension, carrying out the iteration on the current vaccine dispatching distribution model to obtain the iteration result; determining the target optimal solution according to each obtained iteration result;
scheduling and distributing vaccine to be distributed according to the target optimal solution;
according to a preset target circulation aging time length, acquiring vaccine circulation information corresponding to each target inoculation clinic in a target inoculation clinic set, including:
Determining the number of target unit time lengths contained in the target circulation aging time length as a target number;
obtaining vaccine delivery quantity of the target vaccination outpatient service in each target unit time period in a preset target historical time period, and taking the vaccine delivery quantity as historical vaccine delivery quantity to obtain a historical vaccine delivery quantity set corresponding to the target vaccination outpatient service;
acquiring vaccine delivery amounts in a reference number of target unit time periods which are adjacent to the current target unit time period and are in front of the current target unit time period of the target inoculation clinic as target historical delivery amounts, and acquiring a target historical delivery amount set corresponding to the target inoculation clinic, wherein the reference number is the target number minus one;
acquiring the vaccine stock quantity of the target vaccination outpatient service at the end of a target unit time period of a first target quantity before the current target unit time period as a target historical stock quantity corresponding to the target vaccination outpatient service;
respectively predicting the current target unit time period and vaccine demand in a reference number of target unit time periods which are adjacent to the current target unit time period after the current target unit time period according to the historical vaccine delivery volume set corresponding to the target vaccination clinic, and obtaining a target prediction demand set corresponding to the target vaccination clinic;
Forming vaccine circulation information corresponding to the target inoculation clinic by the target historical warehouse quantity set, the target historical warehouse quantity and the target predicted demand quantity set corresponding to the target inoculation clinic;
the step of carrying out vaccine inventory remaining prediction processing on the target inoculation outpatient service according to the vaccine circulation information corresponding to each target inoculation outpatient service to obtain inventory remaining indexes corresponding to the target inoculation outpatient service, comprises the following steps:
determining the quantity of the vaccines to be distributed, which are required to be distributed to the target inoculation clinic in the current target unit time period, as the quantity to be distributed corresponding to the target inoculation clinic;
determining the sum of the target historical stock quantity corresponding to the target inoculation clinic and the quantity to be distributed as the quantity to be circulated corresponding to the target inoculation clinic;
determining the sum of all elements in a target historical inventory set and a target predicted demand set corresponding to the target inoculation clinic as the overall estimated inventory corresponding to the target inoculation clinic;
determining the difference value of the quantity to be circulated and the overall estimated inventory corresponding to the target inoculation clinic as the overall residual quantity corresponding to the target inoculation clinic;
And determining the ratio of the total residual quantity corresponding to the target inoculation clinic to the quantity to be circulated as an inventory residual index corresponding to the target inoculation clinic.
2. The vaccination command and dispatch method according to claim 1, wherein the constructing a current vaccine dispatch and dispatch model according to the total number of the vaccines to be dispatched and the inventory remaining index corresponding to each target vaccination clinic in the target vaccination clinic set comprises:
determining the difference value between the maximum value and the minimum value in the inventory standby residual indexes corresponding to each target inoculation clinic in the target inoculation clinic set as the target function value of the current vaccine dispatching distribution model;
determining the number to be distributed corresponding to the target inoculation clinic to be greater than or equal to zero and less than or equal to the total number of vaccines to be distributed as a first condition which is required to be met by the target function;
and determining the accumulated value of the quantity to be distributed corresponding to each target inoculation clinic to be equal to the total quantity of vaccines to be distributed as a second condition which is required to be met by the target function.
3. A vaccination commanding and dispatching method according to claim 1, wherein said adaptively updating two acceleration parameter values for each target particle in each target dimension included in the set of target parameters based on the previous iteration result comprises:
Determining an absolute value of a difference value between a global optimal solution of the target dimension and a current solution of the target particle in the target dimension, which is included in a last iteration result, as a first difference of the target particle in the target dimension;
determining an absolute value of a difference value between a current solution of the target particle in the target dimension and an individual historical optimal solution included in a last iteration result as a second difference of the target particle in the target dimension;
performing positive correlation mapping on the first difference of the target particles in the target dimension, and performing negative correlation mapping on the second difference of the target particles in the target dimension to obtain a target change index of the target particles in the target dimension;
performing two classifications on target change indexes of each target particle in the target dimension, and determining classification thresholds;
normalizing the difference value between the target change index of the target particle in the target dimension and the classification threshold value to obtain an acceleration change index of the target particle in the target dimension;
determining the current speed variation of each target particle in the target dimension, and screening the largest current speed variation from the current speed variation of each target particle in the target dimension to be used as the current maximum speed variation of the target dimension;
And determining the product of the current maximum speed variation of the target dimension and the acceleration variation index of the target particle in the target dimension as two updated acceleration parameter values of the target particle in the target dimension.
4. A vaccination commanding and dispatching method according to claim 3, wherein said positive correlation mapping of a first difference of said target particles in said target dimension and negative correlation mapping of a second difference of said target particles in said target dimension to obtain a target variation index of said target particles in said target dimension comprises:
determining a difference value of a first difference and a second difference of the target particles in the target dimension as a first change index of the target particles in the target dimension;
and determining the first change index power of the target particles with natural constants in the target dimension as a target change index of the target particles in the target dimension.
5. A vaccination command and dispatch method according to claim 1, wherein the method further comprises:
determining the number of target inoculation clinics with the target historical stock quantity being greater than zero in the target inoculation clinic set as a stock base;
Determining the sum of each target historical delivery volume in a target historical delivery volume set corresponding to each target inoculation clinic and the vaccine delivery volume of the target inoculation clinic in the current target unit time period as an aging delivery volume corresponding to the target inoculation clinic;
when the time-effect stock quantity corresponding to the target inoculation outpatient service is greater than or equal to the target historical stock quantity corresponding to the target inoculation outpatient service, determining the target inoculation outpatient service as a cleared outpatient service;
determining the ratio of the number of the clear clinics to the inventory base number as a clear ratio;
the cleared proportion is stored in the target database.
6. The vaccination commanding and dispatching method according to claim 1, wherein said dispatching and distributing the vaccine to be distributed according to the target optimal solution comprises:
and controlling a target vehicle, and transporting the number of the vaccines to be distributed, which are included in the target optimal solution, to a corresponding target inoculation clinic.
7. A vaccination commanding and dispatching system comprising a processor and a memory, the processor for processing instructions stored in the memory to implement a vaccination commanding and dispatching method according to any of claims 1-6.
CN202310220445.XA 2023-03-09 2023-03-09 Vaccination command scheduling method and system Active CN116137181B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310220445.XA CN116137181B (en) 2023-03-09 2023-03-09 Vaccination command scheduling method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310220445.XA CN116137181B (en) 2023-03-09 2023-03-09 Vaccination command scheduling method and system

Publications (2)

Publication Number Publication Date
CN116137181A CN116137181A (en) 2023-05-19
CN116137181B true CN116137181B (en) 2023-09-05

Family

ID=86326860

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310220445.XA Active CN116137181B (en) 2023-03-09 2023-03-09 Vaccination command scheduling method and system

Country Status (1)

Country Link
CN (1) CN116137181B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665212A (en) * 2018-05-03 2018-10-16 贝医信息科技（上海）有限公司 inventory management system based on cloud platform
CN109242327A (en) * 2018-09-20 2019-01-18 姜龙训 vaccine management system
CN110046761A (en) * 2019-04-11 2019-07-23 北京工业大学 A kind of ethyl alcohol inventory's Replenishment Policy based on multi-objective particle
CN110503320A (en) * 2019-08-07 2019-11-26 卓尔智联(武汉)研究院有限公司 Vaccine resource allocation method, device and storage medium
CN111340345A (en) * 2020-02-20 2020-06-26 中北大学 Cutter scheduling method based on improved particle swarm optimization
CN112017013A (en) * 2020-10-29 2020-12-01 北京每日优鲜电子商务有限公司 Target item information display method and device, electronic equipment and computer readable medium
CN113034090A (en) * 2021-05-26 2021-06-25 北京每日优鲜电子商务有限公司 Transportation equipment scheduling method and device, electronic equipment and computer readable medium
CN114496198A (en) * 2022-04-06 2022-05-13 成都秦川物联网科技股份有限公司 Smart city vaccine scheduling method and system based on Internet of things
CN114723363A (en) * 2022-03-29 2022-07-08 河北省疾病预防控制中心 Vaccine inoculation commanding and dispatching platform
CN114819831A (en) * 2022-04-27 2022-07-29 南京希音电子商务有限公司 Advance method, device and storage medium based on amazon FBA warehouse

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220245566A1 (en) * 2021-02-04 2022-08-04 Aleran Software, Inc. Systems and methods for distributed drop shipping

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665212A (en) * 2018-05-03 2018-10-16 贝医信息科技（上海）有限公司 inventory management system based on cloud platform
CN109242327A (en) * 2018-09-20 2019-01-18 姜龙训 vaccine management system
CN110046761A (en) * 2019-04-11 2019-07-23 北京工业大学 A kind of ethyl alcohol inventory's Replenishment Policy based on multi-objective particle
CN110503320A (en) * 2019-08-07 2019-11-26 卓尔智联(武汉)研究院有限公司 Vaccine resource allocation method, device and storage medium
CN111340345A (en) * 2020-02-20 2020-06-26 中北大学 Cutter scheduling method based on improved particle swarm optimization
CN112017013A (en) * 2020-10-29 2020-12-01 北京每日优鲜电子商务有限公司 Target item information display method and device, electronic equipment and computer readable medium
CN113034090A (en) * 2021-05-26 2021-06-25 北京每日优鲜电子商务有限公司 Transportation equipment scheduling method and device, electronic equipment and computer readable medium
CN114723363A (en) * 2022-03-29 2022-07-08 河北省疾病预防控制中心 Vaccine inoculation commanding and dispatching platform
CN114496198A (en) * 2022-04-06 2022-05-13 成都秦川物联网科技股份有限公司 Smart city vaccine scheduling method and system based on Internet of things
CN114819831A (en) * 2022-04-27 2022-07-29 南京希音电子商务有限公司 Advance method, device and storage medium based on amazon FBA warehouse

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于加速参数自调整粒子群算法的物流配送优化模型;黄日胜;计算机应用与软件;第32卷(第10期);全文 *

Also Published As

Publication number Publication date
CN116137181A (en) 2023-05-19

Similar Documents

Publication Publication Date Title
CN110712206B (en) Multitask allocation method, multitask allocation device, multitask allocation equipment and storage medium of intelligent robot
CN109272276B (en) Inventory replenishment management method and device
CN109345091B (en) Ant colony algorithm-based whole vehicle logistics scheduling method and device, storage medium and terminal
CN109787855A (en) Server Load Prediction method and system based on Markov chain and time series models
CN109214756B (en) Vehicle logistics scheduling method and device, storage medium and terminal
CN112801430B (en) Task issuing method and device, electronic equipment and readable storage medium
CN113191619B (en) Dynamic optimization method for emergency rescue material distribution and vehicle dispatching
CN111695842B (en) Distribution scheme determining method, distribution scheme determining device, electronic equipment and computer storage medium
CN115168027A (en) Calculation power resource measurement method based on deep reinforcement learning
CN112764893A (en) Data processing method and data processing system
CN116307961A (en) Logistics capacity storage and scheduling solving method and system for interruption risk
CN110210666B (en) Intelligent recommendation method, system and storage medium based on vehicle and goods matching
CN116137181B (en) Vaccination command scheduling method and system
CN111260275A (en) Method and system for distributing inventory
CN113641445B (en) Cloud resource self-adaptive configuration method and system based on depth deterministic strategy
US20200334618A1 (en) Forecasting system
CN109767094B (en) Smart cloud manufacturing task scheduling device
Römer et al. Future Demand Uncertainty In Personnel Scheduling: Investigating Deterministic Lookahead Policies Using Optimization And Simulation.
CN116069473A (en) Deep reinforcement learning-based Yarn cluster workflow scheduling method
CN112632615B (en) Scientific workflow data layout method based on hybrid cloud environment
CN113205391B (en) Historical order matching degree based order dispatching method, electronic equipment and computer readable medium
CN114896070A (en) GPU resource allocation method for deep learning task
CN111722925B (en) Collaborative scheduling method, system and device for dynamic edge calculation
CN114090239A (en) Model-based reinforcement learning edge resource scheduling method and device
CN114912647A (en) Apparatus, method and machine-readable storage medium for decision making

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