CN117474259A - Scheduling method based on flight guarantee demand prediction and matched personnel - Google Patents
Scheduling method based on flight guarantee demand prediction and matched personnel Download PDFInfo
- Publication number
- CN117474259A CN117474259A CN202311468929.2A CN202311468929A CN117474259A CN 117474259 A CN117474259 A CN 117474259A CN 202311468929 A CN202311468929 A CN 202311468929A CN 117474259 A CN117474259 A CN 117474259A
- Authority
- CN
- China
- Prior art keywords
- flight
- scheme
- data
- personnel
- scheduling
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 64
- 230000007774 longterm Effects 0.000 claims description 24
- 230000003442 weekly effect Effects 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000001351 cycling effect Effects 0.000 claims description 9
- 238000012797 qualification Methods 0.000 claims description 8
- 230000010006 flight Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000013439 planning Methods 0.000 abstract description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000010485 coping Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063118—Staff planning in a project environment
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a flight guarantee demand prediction and matching personnel scheduling method, which is used for automatically scheduling airport ground service based on machine learning and operation planning optimization driving according to service characteristics of different departments of airport ground service, including scheduling period, scheduling mode, scheduling rules, personnel quantity and the like, so as to realize resource demand prediction according to a flight plan, thereby more accurately predicting and evaluating manpower demand and making scientific decisions.
Description
Technical Field
The invention relates to the technical field of personnel scheduling, in particular to a scheduling method based on flight guarantee demand prediction and matched personnel.
Background
The arrangement of the airport ground teams is determined according to the operating requirements of the airport and the nature of the ground work. Airport ground teams typically employ a shift schedule to ensure all-weather ground services. Common shift schedules include early shift, middle shift, late shift, and night shift. The schedule of the shifts may be adjusted based on the peak and valley times of flight operations. Post allocation: airport ground service involves a number of different posts including gate, baggage handling, security inspection, apron operation, passenger service, etc. According to the working property and the requirement of each post, the ground service team can carry out reasonable post allocation according to the skills and experience of personnel. The number of people and the allocation of the airport ground crew will be determined according to the size of the airport, the number of flights, the passenger flow and other factors. Larger airports typically require more ground crews to handle busy work environments, while smaller airports may have a smaller number of crews.
The following problems exist in the current airport ground service scheduling: an unreasonable manual arrangement may lead to situations where the human hand is insufficient or excessive. Insufficient manpower may result in overload and inefficiency of work, while excessive manpower may waste resources and increase costs. Unreasonable shift schedule: the scheduling of shift schedules may be an unreasonable situation, such as a continuous long night shift or frequent shift switches, which may have an impact on the physical health and work efficiency of the ground staff. From the perspective of a full airport, the position allocation is unbalanced, the skills and experience of ground staff can be different in different positions, and the unreasonable position allocation can cause the shortage or overage of certain position staff, so that the working efficiency and the service quality are affected. Lack of flexibility and strain capability: the arrangement of the ground teams should have a certain flexibility and strain capability to cope with emergency situations and emergency adjustments. If the arrangement is too stiff or lacks resilience, it may not be effective in handling the unexpected event or sudden demand.
Disclosure of Invention
In view of the above, the invention aims to provide a scheduling method based on flight guarantee demand prediction and matched personnel, which optimizes the arrangement of ground service groups through reasonable manpower planning, flexible shift arrangement, scientific post allocation and other measures based on artificial intelligence technology, integrates airport personnel scheduling data and flight passenger flow data, and comprehensively provides an optimal airport scheduling scheme through big data analysis, machine learning and planning optimization technology.
In order to achieve the purpose of the invention, the invention provides a scheduling method based on flight guarantee demand prediction and matched personnel, which comprises the following steps:
s1, acquiring airport resource data, task basic information and configuration data to form a metadata matrix;
s2, generating flight data and flight guarantee task information within a preset time range, and further generating a scheduling decision data matrix;
s3, preparing weight data to form decision influence constraint, target and weight value matrix;
s4, according to the flight plan, airport guarantee characteristics, the flight plan and personnel resource plan in the range of the air season/month are obtained, an ASSI model with multi-objective optimization is designed to carry out optimal scheme solving, and an optimal long-term scheduling personnel scheme is obtained;
s5, acquiring a flight plan and a personnel resource plan in a near-week range according to the flight plan and airport guarantee characteristics, identifying conflict between the weekly flight plan and the weekly personnel resource plan and between the weekly flight plan and the aviation season/month flight plan and between the weekly personnel resource plan and the aviation season/month personnel resource plan, triggering the scheme change of a long-term scheduling personnel, and calculating the scheme of the weekly scheduling personnel;
s6, acquiring a next-day flight plan and a next-day personnel resource plan according to the flight plan and airport guarantee characteristics, identifying conflict between the next-day flight plan and the next-day personnel resource plan and the week flight plan and the week personnel resource plan, triggering change of a week personnel scheme, and calculating the next-day personnel scheme;
and S7, evaluating the long-term staff scheme, the week staff scheme and the next day staff scheme in the steps S4-S6 according to preset indexes, and outputting evaluation results.
Further, the step S1 specifically includes the following steps:
s101, initializing task type, post and qualification metadata, obtaining task type data, and forming a task metadata matrix;
s102, uniformly configuring flight protocol data, generating a flight task rule, setting task types to be ensured for flights to which all service airlines and machine types belong, and forming a flight task type data matrix;
s103, initializing airport security personnel data to form a personnel metadata matrix;
s104, initializing airport scheduling rule data and determining a group, a class section and a circulation mode.
Further, the step S2 specifically includes the following steps:
s201, determining daily flight plan data in a preset time range according to the aviation season information and the flight plan information;
s202, generating task data required to be ensured for each flight based on flight protocol data, and forming a flight task data matrix.
Further, the step S3 specifically includes the following steps:
s301, defining weight influence factors, wherein the weight influence factors comprise constraints and targets;
s302, based on the historical accumulated data, simulating and setting the weight values, determining each influence constraint and each target weight value, and forming the constraints, targets and the weight values under different scheduling modes of the airport, wherein the scheduling modes comprise long term, week and next day.
Further, the step S4 specifically includes the following steps:
s401, inputting the data formed in the steps S1, S2 and S3 into a preset algorithm;
s402, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s403, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s404, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s405, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
Further, the step S5 specifically includes the following steps:
s501, updating a flight task data matrix according to flight change in the scheme change of a long-term scheduling staff, updating a staff metadata matrix according to staff change in the scheme change of the long-term scheduling staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm;
s502, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s503, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s504, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s505, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
Further, the step S6 specifically includes the following steps:
s601, updating a flight task data matrix according to flight change in the scheme change of the week staff, updating a personnel metadata matrix according to personnel change in the scheme change of the week staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm;
s602, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s603, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s604, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s605, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting the scheme with the minimum punishment value for outputting.
Further, in step S7, the output evaluation result includes an evaluation index, a performance index, an operation condition, and a scenario score.
Compared with the prior art, the invention has the beneficial effects that:
according to the flight guarantee demand prediction and matching personnel scheduling method, the big data analysis and machine learning technology is used, so that data such as flight volume, passenger flow and workload can be monitored and analyzed in real time, manpower demands can be predicted and evaluated more accurately so as to make scientific decisions, the method can automatically conduct group scheduling and personnel allocation, the shift and post allocation can be automatically optimized according to factors such as real-time demands, skills of staff and working time, the working efficiency and resource utilization rate are improved, the daily on-duty condition is monitored in real time, subsequent scheduling is gradually optimized, scheduling personnel can be helped to make timely adjustment and decisions, flexible adjustment can be conducted according to the changed working demands and external factors, workers can be rearranged automatically, emergency and emergency change are adapted, the coping capacity and adaptability are improved, and the airport ground service group working efficiency, resource utilization rate and service coping quality can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic overall flow chart of a scheduling method based on flight guarantee demand prediction and matching personnel according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a distribution of the working hours per month before the optimization by using the method provided by the embodiment of the invention.
Fig. 3 is a schematic diagram of a distribution of the working hours of a person per month after the optimization by using the method provided by the embodiment of the invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the illustrated embodiments are provided for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Referring to fig. 1, the embodiment provides a scheduling method based on flight guarantee demand prediction and matching personnel, which includes the following steps:
s1, acquiring airport resource data, task basic information and configuration data to form a metadata matrix.
S2, generating flight data and flight guarantee task information within a preset time range, and further generating a flight task data matrix.
And S3, preparing weight data to form decision influence constraint, target and weight value matrix.
And S4, designing a multi-objective optimized ASSI model to carry out optimal solution according to the flight plan, airport guarantee characteristics, and the flight plan and personnel resource plan in the range of the air season/month, so as to obtain an optimal long-term scheduling personnel scheme. The long-term scheduling is performed by optimally scheduling the scheduling of personnel for flight schedule data, personnel resource data, etc. within a predetermined time range (quarterly, monthly) in the future, and identifying the need for the guaranteed resources.
S5, acquiring a flight plan and a personnel resource plan within a near week range according to the flight plan and airport guarantee characteristics, identifying conflict between the weekly flight plan and the weekly personnel resource plan and the air season/month flight plan and between the weekly personnel resource plan and the air season/month personnel resource plan, triggering the change of a long-term scheduling personnel scheme, and calculating the weekly scheduling personnel scheme. Zhou Paiban by acquiring a future one week flight schedule, personnel resource data, etc., the optimal arrangement of personnel scheduling is performed on the basis of long-term scheduling, and the demand for guaranteed resources is identified.
S6, acquiring a next-day flight plan and a next-day personnel resource plan according to the flight plan and airport guarantee characteristics, identifying conflict between the next-day flight plan and the next-day personnel resource plan and the week flight plan and the week personnel resource plan, triggering change of a week personnel scheme, and calculating the next-day personnel scheme. The next day scheduling is performed by acquiring a future day flight schedule, personnel resource data and the like, performing optimal arrangement of personnel scheduling on the basis of week scheduling, and identifying the guarantee resource requirements.
And S7, evaluating the long-term scheduling staff schemes, the week scheduling staff schemes and the next day scheduling staff schemes in the steps S4-S6 according to preset indexes, and outputting evaluation results so as to evaluate the quality of different scheduling schemes.
In this embodiment, the step S1 specifically includes the following steps:
s101, initializing task type, post and qualification metadata, and obtaining task type data to form a task metadata matrix. The task type data includes: task code, task name, required qualification of task, required post of task, etc.
S102, uniformly configuring flight protocol data, generating a flight task rule, setting task types to be ensured for flights to which all service airlines and machine types belong, and forming a flight task type data matrix.
S103, initializing airport security personnel data to form a personnel metadata matrix. Airport security personnel data includes: personnel code, personnel name, affiliated department, affiliated post, possession qualification, etc.
S104, initializing airport scheduling rule data, and determining a group, a class section, a circulation mode and the like.
In step S2, generating flight data and flight guarantee task information within a predetermined time range, and further generating a scheduling decision data matrix, which specifically includes the following steps:
s201, determining daily flight plan data in a preset time range according to the aviation season information and the flight plan information. The flight schedule includes: flight number, flight date, airline, model, planned take-off, actual take-off, planned arrival, actual arrival, passenger number, weight of mail, etc.
S202, generating task data required to be ensured for each flight based on flight protocol data, and forming a flight task data matrix. The flight task data includes: flight number, flight date, task code, task type, task start time, task end time, task time consumption, task required qualification, task required post, and the like.
In this embodiment, the step S3 specifically includes the following steps:
s301, defining weight influence factors, wherein the weight influence factors comprise constraints and targets. In connection with the data of step S1, the weight influencing factors include constraints and targets. The constraints include: qualification, post, working time, working preference, scheduling mode, etc. The object comprises: the average working time length of a person is balanced, the total working time is minimum, the total overtime time is minimum, the equal proportion of the on-duty time and the rest time interval is balanced, the adjustment of the original scheduling scheme is minimum, and the like.
S302, based on the historical accumulated data, simulating and setting the weight values, determining each influence constraint and each target weight value, and forming the constraints, targets and the weight values under different scheduling modes of the airport, wherein the scheduling modes comprise long term, week and next day. Specifically, the platform respectively simulates long-term scheduling, zhou Paiban and next-day scheduling through historical accumulated data, outputs historical scheduling data and performance evaluation, compares the historical current-day scheduling results and performance evaluation, determines each influence constraint and target weight value, and obtains each target and weight value through a standard deviation formula, so that the constraints, targets and weight values of the airport in different scheduling modes (long-term, weekly and next-day) are formed.
In this embodiment, constraint, target and weight values set according to historical experience are used by default, and decision influence is performed so as to obtain an optimal personnel scheduling scheme. In some embodiments, the goals, weight values may also be modified online by the user to adjust the optimal personnel scheduling scheme.
The step S4 specifically comprises the following steps:
s401, inputting the data formed in the steps S1, S2 and S3 into a preset algorithm.
S402, initializing input data by a preset algorithm, and initializing the input data into ASSI model data.
S403, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization. Specifically, a target value is determined according to a penalty value rule of each target, upper and lower limit constraints of the target value are set, and the following steps are carried out: the model penalty value is given by the formula of penalty value= (actual value-target value) ×target penalty weight coefficient×1. The smaller the penalty value, the better the solution.
S404, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy. Generally, the longer the search time, the more the number of searches, the better the searched scheme.
For the first solution searching strategy, the ASSI model searches the initial feasible solution according to the first solution searching strategy. Possible solution outputs include: the initial task-personnel allocation matrix data and the punishment value of the scheme can be used for knowing whether the scheme meets the constraint and the target of the ASSI model or not through analysis of the task-personnel allocation Gantt chart and related indexes (such as qualification post matching, personnel working time length and the like). The first scheme search strategy is optional: GLOBAL_CHEAPEST_ARC, LOCAL_CHEAPEST_ARC, PATH_CHEAPEST_ARC, PATH_MOST_CONSTREAMINSERT_ARC, ALL_ UNPERFORMED, BEST _INSERT,
PARALLEL_CHEAPEST_INSERTION、LOCAL_CHEAPEST_INSERTION、SAVINGS、FIRST_UNBOUND_MIN_VALUE、CHRISTOFIDES。
For the meta-heuristic search strategy, the ASSI model starts a meta-heuristic algorithm on the basis of an initial feasible solution of the first scheme search strategy to search out the optimal resource scheduling scheme. The best resource scheduling scheme output includes: task-personnel assign matrix data, penalty values for the scheme. Enabling meta-heuristic SEARCH refers to the model searching for the optimal solution of the output problem by building a heuristic (e.g., green DESCENT, GUIDED LOCAL SEARCH, SIMULATED ANNEALING, TABU SEARCH, GENERIC tab SEARCH, etc.) input.
S405, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
After the algorithm is solved to obtain the optimal personnel scheduling scheme, the overall scheme data is output through statistical integration, and the method comprises the following steps: the team-class section-person-circulation mode scheduling data matrix, overtime staff, each person overtime period, time length, solving used constraint, target, weight value, scheme penalty value and the like.
In this embodiment, the step S5 specifically includes the following steps:
s501, updating a flight task data matrix according to flight change in the scheme change of the long-term staff, updating a personnel metadata matrix according to personnel change in the scheme change of the long-term staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm.
S502, initializing input data by a preset algorithm, and initializing the input data into ASSI model data.
S503, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization.
S504, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy.
S505, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
In this embodiment, the step S6 specifically includes the following steps:
s601, updating a flight task data matrix according to flight changes in the scheme change of the week staff, updating a personnel metadata matrix according to personnel changes in the scheme change of the week staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm.
S602, initializing input data by a preset algorithm, and initializing the input data into ASSI model data.
S603, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization.
S604, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy.
S605, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting the scheme with the minimum punishment value for outputting.
In a preferred embodiment, in step S7, the output evaluation result includes an evaluation index, a performance index, an operation condition, and a scenario score.
Wherein, the evaluation index includes: standard deviation of the working time length of each month, total overtime time length of each month, rest time length of each month, number of delayed flights, total delay time length and the like.
The performance indicators include: the working time of people per month, the interval time of people per shift, the task time rate, the flight punctuation rate and the like. Wherein: task time rate = 1-number of delayed tasks/total number of tasks, flight punctuation rate = 1-number of delayed flights/total number of flights.
The operation conditions comprise: the number and details of the plan changes, including weekly versus long-term plan, next day versus weekly plan; a class section scheduling Gantt chart of a class group; staff shift Gantt chart; a working time length statistical chart of each staff in the month, and the like.
The scheme score is calculated by integrating various indexes, and the calculation formula is as follows: scheme score = working time score + total time score for overtime + delay number score + delay time score + task time score + flight quasi-point score, wherein: working time length fraction=100-1 x and average month working time length standard deviation sum, overtime total time length fraction=100-1 x overtime total time length, delay times fraction=100-50 x delay times, delay time length fraction
Total delay time length =100-2; task time score = 100-100 task time score; the job efficiency score = 100-100 x flight punctuation rate.
As can be seen from fig. 2 and 3, before the method provided by the present embodiment is not used to optimize the staff scheduling, the staff working time is unbalanced; and after the method provided by the embodiment is used for optimizing the personnel scheduling, the personnel average working time is relatively balanced. The method provided by the embodiment can realize personnel scheduling in three stages of long-term scheduling (season/month), zhou Paiban and next day scheduling, and realizes resource demand prediction according to a flight plan according to the business characteristics of different departments posts of the airport ground service, including scheduling period, scheduling mode, scheduling rules, personnel number and the like, and the airport ground service scheduling driven by machine learning and operation optimization.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A scheduling method based on flight guarantee demand prediction and matching personnel is characterized by comprising the following steps:
s1, acquiring airport resource data, task basic information and configuration data to form a metadata matrix;
s2, generating flight data and flight guarantee task information within a preset time range, and further generating a scheduling decision data matrix;
s3, preparing weight data to form decision influence constraint, target and weight value matrix;
s4, according to the flight plan, airport guarantee characteristics, the flight plan and personnel resource plan in the range of the air season/month are obtained, a ASSI (Airport Staff Scheduling Issues) model with multi-objective optimization is designed to carry out optimal scheme solving, and an optimal long-term scheduling personnel scheme is obtained;
s5, acquiring a flight plan and a personnel resource plan in a near-week range according to the flight plan and airport guarantee characteristics, identifying conflict between the weekly flight plan and the weekly personnel resource plan and between the weekly flight plan and the aviation season/month flight plan and between the weekly personnel resource plan and the aviation season/month personnel resource plan, triggering the scheme change of a long-term scheduling personnel, and calculating the scheme of the weekly scheduling personnel;
s6, acquiring a next-day flight plan and a next-day personnel resource plan according to the flight plan and airport guarantee characteristics, identifying conflict between the next-day flight plan and the next-day personnel resource plan and the week flight plan and the week personnel resource plan, triggering change of a week personnel scheme, and calculating the next-day personnel scheme;
and S7, evaluating the long-term staff scheme, the week staff scheme and the next day staff scheme in the steps S4-S6 according to preset indexes, and outputting evaluation results.
2. The method for forecasting and matching personnel scheduling based on flight guarantee requirements as claimed in claim 1, wherein the step S1 specifically comprises the following steps:
s101, initializing task type, post and qualification metadata, obtaining task type data, and forming a task metadata matrix;
s102, uniformly configuring flight protocol data, generating a flight task rule, setting task types to be ensured for flights to which all service airlines and machine types belong, and forming a flight task type data matrix;
s103, initializing airport security personnel data to form a personnel metadata matrix;
s104, initializing airport scheduling rule data and determining a group, a class section and a circulation mode.
3. The method for forecasting and matching personnel scheduling based on flight guarantee requirements as claimed in claim 2, wherein the step S2 specifically comprises the following steps:
s201, determining daily flight plan data in a preset time range according to the aviation season information and the flight plan information;
s202, generating task data required to be ensured for each flight based on flight protocol data, and forming a flight task data matrix.
4. A flight support demand prediction and matching personnel scheduling method according to claim 3, wherein the step S3 specifically comprises the following steps:
s301, defining weight influence factors, wherein the weight influence factors comprise constraints and targets;
s302, based on the historical accumulated data, simulating and setting the weight values, determining each influence constraint and each target weight value, and forming the constraints, targets and the weight values under different scheduling modes of the airport, wherein the scheduling modes comprise long term, week and next day.
5. The method for scheduling people based on the prediction of flight protection requirements and matching according to claim 4, wherein the step S4 specifically comprises the following steps:
s401, inputting the data formed in the steps S1, S2 and S3 into a preset algorithm;
s402, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s403, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s404, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s405, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
6. The method for scheduling people based on the prediction of flight protection requirements and matching according to claim 5, wherein the step S5 specifically comprises the following steps:
s501, updating a flight task data matrix according to flight change in the scheme change of a long-term scheduling staff, updating a staff metadata matrix according to staff change in the scheme change of the long-term scheduling staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm;
s502, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s503, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s504, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s505, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting a scheme with the minimum punishment value for outputting.
7. The method for scheduling people based on the prediction of flight protection requirements and matching according to claim 6, wherein the step S6 specifically comprises the following steps:
s601, updating a flight task data matrix according to flight change in the scheme change of the week staff, updating a personnel metadata matrix according to personnel change in the scheme change of the week staff, and inputting the updated metadata matrix, the flight task data matrix, the constraint, the target and the weight value matrix into a preset algorithm;
s602, initializing input data by a preset algorithm, and initializing the input data into ASSI model data;
s603, constructing constraints and targets by a preset algorithm, constructing ASSI model constraints and targets according to ASSI model data, and giving punishment values to the targets for control and optimization;
s604, setting model search parameters including search time limit, search times, a first scheme search strategy and a meta heuristic search strategy;
s605, forming a pairwise matching matrix according to a first scheme searching strategy and a meta heuristic searching strategy supported by an ASSI model, forming two-dimensional array combinations of 1 first scheme searching strategy corresponding to 1 meta heuristic searching strategy, cycling the array, starting 1 thread for scheme searching each time to obtain schemes of each combination, and finally selecting the scheme with the minimum punishment value for outputting.
8. The method for forecasting and matching personnel scheduling based on flight guarantee requirements as claimed in claim 1, wherein in the step S7, the output evaluation result includes an evaluation index, a performance index, a running condition and a scheme score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468929.2A CN117474259A (en) | 2023-11-06 | 2023-11-06 | Scheduling method based on flight guarantee demand prediction and matched personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468929.2A CN117474259A (en) | 2023-11-06 | 2023-11-06 | Scheduling method based on flight guarantee demand prediction and matched personnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117474259A true CN117474259A (en) | 2024-01-30 |
Family
ID=89639230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311468929.2A Pending CN117474259A (en) | 2023-11-06 | 2023-11-06 | Scheduling method based on flight guarantee demand prediction and matched personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474259A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134225A (en) * | 2024-05-10 | 2024-06-04 | 民航成都信息技术有限公司 | Airport check-in personnel scheduling method, device, equipment and medium based on random event scene |
-
2023
- 2023-11-06 CN CN202311468929.2A patent/CN117474259A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134225A (en) * | 2024-05-10 | 2024-06-04 | 民航成都信息技术有限公司 | Airport check-in personnel scheduling method, device, equipment and medium based on random event scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751681B (en) | Statistical learning model based gate position allocation method | |
| Pellegrini et al. | SOSTA: An effective model for the Simultaneous Optimisation of airport SloT Allocation | |
| CN109584638B (en) | Regional network-oriented advanced flight time collaborative optimization method | |
| CN117474259A (en) | Scheduling method based on flight guarantee demand prediction and matched personnel | |
| Zhao et al. | An integrated approach of train scheduling and rolling stock circulation with skip-stopping pattern for urban rail transit lines | |
| CN113222238B (en) | Method and system for optimizing check-in resource allocation of hub airport | |
| CN109741638B (en) | Integrated collaborative operation method for entering and leaving field management system | |
| CN110428665B (en) | Random double-layer planning method for collaborative allocation of air route and airport time slot | |
| CN113112874B (en) | Collaborative optimization allocation method for air route time slot and height layer | |
| CN116934046A (en) | Intelligent scheduling method based on machine learning and operation planning optimization | |
| CN112951004A (en) | Multi-objective multi-period flight guarantee resource dynamic optimization allocation method | |
| CN109215400A (en) | March into the arena flight quicksort and Optimization Scheduling based on compound dispatching rules | |
| Rodič et al. | Airport ground crew scheduling using heuristics and simulation | |
| CN112862258B (en) | Limited-nature flight recovery method considering passenger preference | |
| CN117273305A (en) | Method and equipment for scheduling controller based on competence | |
| Zhang et al. | Improved ant colony optimization for the operational aircraft maintenance routing problem with cruise speed control | |
| Yan et al. | Airport gate reassignment following temporary airport closures | |
| Fairbrother et al. | On the development of a fair and efficient slot scheduling mechanism at congested airports | |
| CN113947296A (en) | Flight delay recovery method based on multi-agent system | |
| Cavada et al. | A workforce planning and allocation model for the outbound baggage loading area at Santiago International Airport | |
| Alfares | A simulation approach for stochastic employee days-off scheduling | |
| Geng et al. | Research on flight schedule configuration model of branch line based on dynamic programming | |
| Bayliss | Airline reserve crew scheduling under uncertainty | |
| Liu et al. | Optimizing aircrew recovery considering long connections: a column generation based approach | |
| CN117789538B (en) | Rule engine-based flight dynamic linking method |
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 |