Metro crew scheduling plan compilation optimization method and system based on algorithm

Abstract

The invention discloses a metro crew scheduling plan compilation optimization method and system based on an algorithm, relates to the technical field of metro scheduling, and is used for solving the problem that a conventional metro crew scheduling system is not timely in peak allocation. In the prior art, traffic roads are directly matched with aircrafts one by one, but the adaptability between the traffic roads and the aircrafts is not fully considered, and optimization is not carried out aiming at special requirements in peak hours. In the peak period, the demand is far greater than that in the low peak period, more aircraft shifts are possibly needed for support, and in the peak period, the important demand is that the route and the aircraft shifts with high matching degree need to be preferentially matched. According to the method, through matching optimization of the route and the locomotive crew and combination of historical passenger flow data, efficient subway team scheduling is achieved, and it is ensured that the shift demand in the peak period is preferentially met.

Description

Technical Field

[0001] The present invention relates to the technical field of subway scheduling, and more specifically, to a scheduling method for a subway crew management system. Background Art

[0002] With the continuous growth of urban population and the expansion of economic activities, traditional road traffic often faces serious congestion problems. Subways provide an efficient public transportation mode that can transport a large number of passengers at a high density in underground or elevated routes, reducing the pressure on ground transportation. As an efficient, environmentally friendly, safe and convenient means of transportation, subways have become an indispensable and important infrastructure for modern metropolises. From alleviating traffic congestion, reducing air pollution, and improving urban competitiveness to providing efficient transportation services and enhancing intelligent management, the value and role of subways far exceed traditional public transportation. It is not only the skeleton of urban transportation, but also an important force in promoting sustainable development and modernization of cities.

[0003] The prior art has the following deficiencies:

[0004] In the past, the subway crew scheduling system directly matched routes and machine shifts one by one during traditional dispatching and scheduling management, but did not fully consider the compatibility between routes and machine shifts, nor did it optimize for special needs during peak hours. The demand during peak hours is much greater than that during off-peak hours, and more machine shifts may be needed for support. During peak hours, it is more important to prioritize matching routes and machine shifts with high compatibility. In the traditional scheduling method, if this is not taken into account, it is difficult to ensure the timeliness of the allocation during peak hours.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an algorithm-based subway crew scheduling optimization method and system to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An algorithm-based subway crew scheduling optimization method includes the following steps:

[0009] Step S1, collecting the work expertise of route and flight attendants, and obtaining historical passenger flow data of the subway;

[0010] Step S2, adding the routes and the shifts to the set respectively, matching the first route, obtaining the number of matches according to the fitness, and calculating the passenger flow difference between the average passenger flow during the historical peak period and the average passenger flow during the non-peak period;

[0011] Step S3, calculating whether the peak-period route group needs to be matched first based on the number of times the route is matched to a suitable machine and the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period;

[0012] Step S4: After the first route is matched successfully, the route required during the peak period is matched first, and the match is determined based on the adaptability. If the match meets the standard, the route is executed; if not, the route is rematched.

[0013] In a preferred embodiment, step S1 includes the following contents:

[0014] The crew's years of service data are used to divide the various stages, and then each stage is scored; the records of automatic ticket machines and passenger entry and exit gates are obtained, and the original passenger flow data is obtained based on the records of automatic ticket machines and passenger entry and exit gates, and the original passenger flow data is stored separately; the outliers of the original passenger flow data are corrected, and then the multi-source data are integrated.

[0015] In a preferred embodiment, step S2 includes the following contents:

[0016] Construct the route set R and the machine set C. For the first route R1, match it with the machine set C and judge it based on the adaptability. If successful, record the number of matches. If all the machines cannot be adapted, record the number of unmatched matches. After the matching is completed, determine whether to give priority to the peak route requirements based on the number of matches.

[0017] The fitness function is expressed as: Fit(Ri, Cj) = f(Match Time (R i , C j ), Match Satisfaction (R i , C j );

[0018] Calculate the time overlap between the departure time of the route and the start time of the machine shift until the end time of the route and the end time of the machine shift. The calculation formula is: t overlap =max(0,min(t endtrain ,t endshift )-max(t starttrain , t startshift )); The overlap is measured by the ratio of the crossing time to the machine-shift overlap time. Points are assigned based on the calculated degree of overlap;

[0019] Calculate the passenger flow difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours: Filter the historical passenger flow data during peak hours through the historical passenger flow data of the subway, calculate the average passenger flow per hour during peak hours and non-peak hours respectively, subtract the average passenger flow during non-peak hours from the average passenger flow during peak hours to obtain the passenger flow difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours.

[0020] In a preferred embodiment, step S3 includes the following contents:

[0021] Set a threshold ΔC for the passenger flow difference ΔC before and after the peak period threshold , the difference in passenger flow before and after the peak period exceeds a certain set threshold, ΔC>ΔC threshold , then it is necessary to prioritize routes and flights with higher adaptability to meet passenger flow, ΔC≤ΔC threshold ; The passenger flow difference before and after the peak period does not reach the threshold, ΔC ≤ ΔC threshold , then arrange according to the conventional scheduling plan;

[0022] Set a scheduling difficulty threshold M for the number of route matching times M threshold , M>M threshold : It is considered that the scheduling difficulty is relatively large and priority matching is also required, M≤M threshold : If the number of route matching times does not exceed the threshold, it means that the scheduling difficulty is relatively small, the scheduling process is relatively smooth, and there is no need to prioritize matching;

[0023] If the difference in passenger flow before and after the peak period ΔC and the number of route matching times M are both less than the corresponding set thresholds, it means that priority matching is not required during the peak period. The specific decision rule is expressed as:

[0024] Priority matching conditions: If one or both of ΔC or M exceeds the set threshold, it means that the demand increase during the peak period is large or the scheduling difficulty is large, and the routes and shifts need to be matched first;

[0025] Conditions for not prioritizing matching: If ΔC ≤ ΔC threshold And M≤M threshold , it means that the passenger flow during peak hours does not change much, and the route scheduling is relatively simple, and it is arranged according to the regular scheduling.

[0026] In a preferred embodiment, step S4 includes the following contents:

[0027] Sort the routes according to their calculation expertise, select the corresponding routes according to the peak demand and add them to set R for priority matching, add all available routes to set F, match the routes in set R with the routes in set F one by one, and judge whether the compatibility between the routes and the routes meets the preset standards; if the match is successful, continue to judge whether the special route set R is empty. If R is empty, it means that all routes have been matched and the scheduling process ends. If R is not empty, it means that there are still routes that have not been matched successfully and it is necessary to continue to process the next route;

[0028] If the current flight does not match the route, continue to try to match the next flight in the F set. If the set R is empty, it means that all routes have been successfully matched to suitable flights, and the scheduling process ends. If all flights F have been tried to match and there are still routes that cannot be matched, it is necessary to roll back or adjust the strategy.

[0029] The algorithm-based subway crew scheduling optimization system includes: information acquisition module, data processing module, statistical analysis module and capacity matching module.

[0030] Information acquisition module: collects the crew's working years to obtain the crew's professionalism and the subway's historical passenger flow data, and passes the specific information to the data processing module as the basis for subsequent data processing;

[0031] Data processing module: pre-processes the obtained data, filters the historical passenger flow data and calculates the passenger flow difference, uses the professional degree to calculate whether the route and the machine class match and the number of times the first route needs to match, and passes the obtained data set to the statistical analysis module;

[0032] Statistical analysis module: establish a priority matching mechanism, and analyze whether the peak-hour shifts need to be matched first based on the data obtained by the data processing module;

[0033] Capacity matching module: prioritizes the routes required during peak hours, determines whether they are a match based on the degree of adaptability, completes the operation of the scheduling system, and achieves smooth system processing.

[0034] Technical effects and advantages of the algorithm-based subway crew scheduling optimization method and system of the present invention:

[0035] The subway operation is optimized mainly through refined scheduling, using historical passenger flow data, the adaptability of routes and machines, and the professionalism of crew members. By making targeted arrangements for different demands during peak and non-peak periods, the resources of each shift can be maximized through adaptability matching and multiple adjustments. Peak demand is prioritized based on historical data to ensure that there will be no operational bottlenecks during periods of high passenger flow. The systematic matching and judgment mechanism reduces the possibility of manual intervention, which not only reduces the probability of operational errors, but also improves the real-time response capability of operations. In a complex subway scheduling system, excessive reliance on manual scheduling may lead to delays or unreasonable resource allocation, while the automated system can make decisions based on data in real time to maintain flexibility and efficiency. This approach combines data-driven scheduling optimization with a flexible matching mechanism to significantly improve the efficiency and service quality of subway operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a flow chart of the algorithm-based subway crew scheduling method of the present invention.

[0037] Figure 2 It is a structural schematic diagram of the algorithm-based subway crew scheduling system of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] The present invention Figure 1 As shown, a method for preparing a subway crew scheduling plan is provided, comprising the following steps:

[0041] Step S1, collect the work expertise of route and machine crew members, and obtain historical passenger flow data of the subway.

[0042] Step S2, adding the routes and the machine shifts to the set respectively, matching the first route, obtaining the number of matches according to the degree of fitness, and calculating the passenger flow difference between the average passenger flow during the historical peak period and the average passenger flow during the non-peak period.

[0043] Step S3, calculate whether the peak period route group needs to be matched first based on the number of times the route is matched to the appropriate machine group and the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period.

[0044] Step S4, after the first route is matched successfully, the routes required during the peak period are matched first, and a judgment is made based on the adaptability. If the standard is met, the route is executed; if not, the route is matched again.

[0045] The specific implementation is as follows:

[0046] In step S1, the goal of this stage is to collect the professionalism of the route and machine crew members and obtain the historical passenger flow data of the subway, including:

[0047] Professionalism of route and engine crew: The present invention uses the working years of route and engine crew to judge their professionalism. Working years are the key indicator for judging professionalism. The longer the working years, the stronger the crew's ability to handle emergencies, ensure passenger safety, and optimize work efficiency. Therefore, by analyzing the working years of the crew, their professionalism can be quantitatively evaluated, and the working years can be divided into several stages. Each stage is scored, and the scores are input into the system to generate a professionalism report for route and engine crew.

[0048] For example, the working years are divided into the following stages: 1-2 years, 2-3 years, 3-5 years, 5-10 years, 10 years and above, etc. Points are assigned to them, 1 point is assigned to flight attendants with 1-2 years of service, 2 points are assigned to flight attendants with 2-3 years of service, and so on.

[0049] Historical passenger flow data: First, obtain the original passenger flow data by obtaining the records of the automatic ticket vending machine (AFC) and the passenger entry and exit gates, and store the data in two CSV files. You can use pandas to read and import them into the files respectively. After obtaining the data, you need to clean and format the data, remove invalid data, duplicate data, and process outliers. Through pandas operations, delete null values ​​or duplicate rows. For some outliers that may exist in the data (such as negative passenger flow, missing data, etc.), you can use conditional filtering to correct them. After cleaning and processing the data, data from different sources can be merged together for analysis and further processing. For example, data from different sources can be merged according to "passenger ID" or "gate ID". The final cleaning results can be output in Excel format for subsequent analysis.

[0050] In step S2, at this stage, it is necessary to obtain the number of matches of the first intersection and calculate the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period:

[0051] Construct routes and flight sets:

[0052] The intersection set R = {R1, R2, ..., Rn}, where Ri represents the i-th intersection.

[0053] The machine shift set C = {C1, C2, ..., Cm}, where Cj represents the jth machine shift.

[0054] The fitness is an indicator to measure the quality of the match between the route and the crew. When evaluating the match between the route and the crew, factors such as the crew's skills, experience, working hours, and the route schedule are considered. The higher the fitness, the better the matching effect. The fitness function can be expressed as: Fit(Ri, Cj) = f(Match Time (R i , C j ), Match Satisfaction (R i , C j );

[0055] Among them, f is a function that comprehensively considers multiple factors. Factors such as time matching and professional matching can be combined through weighted summation or other appropriate methods.

[0056] The first route R1 is matched with the first flight C1.

[0057] Determine based on the degree of adaptability: If the adaptability of the first shift meets the adaptability standard, the match is determined to be successful, and the number of matches is 1. If it is not suitable, try the second shift C2. If the working adaptability of the second shift meets the adaptability standard, the match is determined to be successful, and the number of matches is 2. If the second shift is still not suitable, try to match with the third shift C3, the fourth shift C4, and so on in turn. If the adaptation standard is met in any match, the number of matches is recorded. If the match between a certain route and multiple shifts cannot meet the adaptability standard, the match is stopped and the number of unmatched times is recorded. After all routes and shifts are matched, the number of matches is used to determine whether the route requirements during peak hours need to be given priority.

[0058] The suitability can be considered from the following two aspects:

[0059] Professional matching degree: whether the professional requirements of the machine team are consistent with the requirements of the route. Some routes may require a machine team with specific professional requirements to match.

[0060] Time matching: whether the working time of the machine shift matches the time arrangement of the route, for example, whether the operation time period of the route overlaps with the available time period of the machine shift. Calculate the time overlap between the route and the machine shift, and assign a score.

[0061] Calculate the time overlap between the departure time of the route and the start time of the machine shift until the end time of the route and the end time of the machine shift.

[0062] Calculate the overlap time period: Assume that the time interval of the intersection is [t starttrain ,t endtrain], the time interval of the machine shift is [t startsift ,t endsift ], then their overlapping time interval can be calculated by the following formula: t overlap =max(0,min(t endtrain ,t endsift )-max(t starttrain , t startsift ));

[0063] Among them, t overlap Indicates the overlap time of the route and the machine shift. If there is no overlap, the result is 0. The overlap degree can be measured by the ratio of the route time to the machine shift overlap time:

[0064] This indicates what proportion of the route time is the overlap of the machine shift's working time.

[0065] According to the calculated overlap, a score can be given. Assume that the scoring criteria are as follows:

[0066] Overlap degree is above 90%: the score is 5, which means that the route and machine shift time are highly matched and the work arrangement of the staff is very reasonable.

[0067] Overlap 80%-89%: A score of 4 points indicates that the route and machine times are relatively matched, but there may be some slight time differences.

[0068] Overlap degree 60%-79%: The score is 3 points, indicating that there is a certain gap between the handover time and the machine shift time, which may affect the work efficiency or rest of the staff.

[0069] Overlap degree 30%-59%: The score is 2 points, indicating that there is a large gap between the route and machine shift times, which may lead to some scheduling difficulties.

[0070] Overlap below 30%: A score of 1 or 0 indicates that the route and machine shift times do not match, which may lead to serious work inconsistency or waste of resources.

[0071] Calculate the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period: Filter the historical passenger flow data during the peak period by using the data obtained in S1, calculate the average passenger flow per hour during the peak period and the non-peak period respectively, and subtract the average passenger flow during the non-peak period from the average passenger flow during the peak period to obtain the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period;

[0072] The calculation formula can be expressed as: the difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours = the average passenger flow during the morning peak hours - the average passenger flow during the non-peak hours;

[0073] For example, the average passenger flow during peak hours (07:30-09:30, 17:30-19:30) is 5000 people / hour, and the average passenger flow during non-peak hours is 1500 people / hour. The passenger flow difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours = 5000-1500 = 3500 people / hour;

[0074] In step S3, whether the peak-period route group needs to be matched first is calculated based on the number of times the route is matched to the appropriate machine and the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period:

[0075] Set a threshold ΔC for the passenger flow difference ΔC before and after the peak period threshold , if the difference in passenger flow before and after the peak period exceeds a certain set threshold, ΔC>ΔC threshold , which means that the demand during peak hours increases sharply, and it is necessary to prioritize routes and flights with higher adaptability to meet passenger flow. ΔC≤ΔΔC threshold ,If the passenger flow difference before and after the peak period does not reach the threshold, it ,indicates that the demand is relatively stable and can be ,arranged according to the conventional scheduling plan.

[0076] Set a scheduling difficulty threshold M for the number of route matching times M threshold , if in order to meet the peak demand, it is necessary to frequently match the route shifts beyond the scheduling difficulty threshold, M>M threshold : It means that the current shift resources are insufficient or the scheduling is more complicated, so it is considered that the scheduling is difficult and priority matching is also required. M≤M threshold : If the number of route matching does not exceed the threshold, it means that the scheduling difficulty is relatively small and the scheduling process is relatively smooth.

[0077] If the difference in passenger flow before and after the peak period ΔC and the number of route matching times M are both less than the corresponding set thresholds, it means that priority matching is not required during the peak period. The specific decision rule can be expressed as:

[0078] Priority matching conditions: If one or both of ΔC or M exceeds the set threshold, it means that the demand increase during the peak period is large or the scheduling difficulty is large, and priority matching of routes and shifts is required.

[0079] Conditions for not prioritizing matching: If ΔC ≤ ΔC threshold And M≤M threshold , it means that the passenger flow during peak hours does not change much, and the route scheduling is relatively simple, so it can be arranged according to the regular scheduling.

[0080] In step S4, after the first route is matched successfully, the route required during the peak period is matched first, and the match is judged according to the adaptability. If the standard is met, it is executed; if not, it is re-matched.

[0081] First, sort the routes according to the professionalism calculated in S1, select the corresponding routes according to the peak demand and add them to the set R for priority matching, add all available shifts to the set F, match the routes in the set R with the shifts in the set F one by one, and judge whether the adaptability of the routes and shifts meets the preset standards. If the match is successful, continue to judge whether the special route set R is empty. If R is empty, it means that all routes have been matched and the scheduling process can be ended. If R is not empty, it means that there are still routes that have not been matched successfully and the next route needs to be processed. If the current shift does not match the route, continue to try to match the next shift in the F set. If the result is that the set R is empty, it means that all routes have been successfully matched to the appropriate shift, and the scheduling process ends. If all shifts F have been tried to match, and there are still routes that cannot be matched, you may need to fall back or adjust the strategy.

[0082] Example 2

[0083] Figure 2 The invention provides an algorithm-based subway crew scheduling optimization system, which includes an information acquisition module, a data processing module, a statistical analysis module and a transportation capacity matching module.

[0084] Information acquisition module: By collecting the crew's years of service, the professionalism of the crew and the historical passenger flow data of the subway are obtained, and the specific information is passed to the data processing module as the basis for subsequent data processing.

[0085] Data processing module: pre-process the data obtained, filter the historical passenger flow data and calculate the passenger flow difference, use professionalism to calculate whether the route and machine class match and the number of times the first route needs to match, and pass the obtained data set to the statistical analysis module.

[0086] Statistical analysis module: Establish a priority matching mechanism, and analyze whether peak-hour shifts need to be matched first based on the data obtained by the data processing module.

[0087] Capacity matching module: prioritizes the routes required during peak hours, determines whether they are a match based on the degree of adaptability, completes the operation of the scheduling system, and achieves smooth system processing.

[0088] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0089] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0090] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0091] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0092] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0093] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0094] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An algorithm-based subway crew scheduling optimization method, characterized in that: Includes steps: Step S1, collecting the work expertise of route and flight attendants, and obtaining historical passenger flow data of the subway; Step S2, adding the routes and the shifts to the set respectively, matching the first route, obtaining the number of matches according to the fitness, and calculating the passenger flow difference between the average passenger flow during the historical peak period and the average passenger flow during the non-peak period; Step S3, calculating whether the peak-period route group needs to be matched first based on the number of times the route is matched to a suitable machine and the passenger flow difference between the average passenger flow during the peak period and the average passenger flow during the non-peak period; Step S4, after the first route is matched successfully, the routes required during the peak period are matched first, and a judgment is made based on the adaptability. If the standard is met, the route is executed; if not, the route is matched again.

2. The algorithm-based subway crew scheduling optimization method according to claim 1 is characterized by: Step S1 includes the following contents: The crew's years of service data are used to divide the various stages, and then each stage is scored; the records of automatic ticket machines and passenger entry and exit gates are obtained, and the original passenger flow data is obtained based on the records of automatic ticket machines and passenger entry and exit gates, and the original passenger flow data is stored separately; the outliers of the original passenger flow data are corrected, and then the multi-source data are integrated.

3. The algorithm-based subway crew scheduling optimization method according to claim 2 is characterized by: Construct the route set R and the machine set C. For the first route R1, match it with the machine set C and judge it based on the adaptability. If successful, record the number of matches. If all the machines cannot be adapted, record the number of unmatched matches. After the matching is completed, determine whether to give priority to the peak route requirements based on the number of matches. The fitness function is expressed as: Fit(Ri, Cj) = f(Match Time (R i , C j ), Match Satisfaction (R i ,C j ); Calculate the time overlap between the departure time of the route and the start time of the machine shift until the end time of the route and the end time of the machine shift. The calculation formula is: t overlap =max(0,min(t endtrain ,t endshift )-max(t starttrain , t startshift )); The overlap is measured by the ratio of the crossing time to the machine-shift overlap time. Points are assigned based on the calculated degree of overlap; Calculate the passenger flow difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours: Filter the historical passenger flow data during peak hours through the historical passenger flow data of the subway, calculate the average passenger flow per hour during peak hours and non-peak hours respectively, subtract the average passenger flow during non-peak hours from the average passenger flow during peak hours to obtain the passenger flow difference between the average passenger flow during peak hours and the average passenger flow during non-peak hours.

4. The algorithm-based subway crew scheduling optimization method according to claim 3 is characterized by: Set a threshold ΔC for the passenger flow difference ΔC before and after the peak period threshold , the difference in passenger flow before and after the peak period exceeds a certain set threshold, ΔC>ΔC threshold , then it is necessary to prioritize routes and flights with higher adaptability to meet passenger flow, ΔC≤ΔC threshold ; The passenger flow difference before and after the peak period does not reach the threshold, ΔC ≤ ΔC threshold , then arrange according to the conventional scheduling plan; Set a scheduling difficulty threshold M for the number of route matching times M threshold , M>M threshold : It is considered that the scheduling difficulty is relatively large and priority matching is also required, M≤M threshold : If the number of route matching does not exceed the threshold, it means that the scheduling difficulty is relatively small, the scheduling process is relatively smooth, and there is no need to prioritize matching; If the difference in passenger flow before and after the peak period ΔC and the number of route matching times M are both less than the corresponding set thresholds, it means that priority matching is not required during the peak period. The specific decision rule is expressed as: Priority matching conditions: If one or both of ΔC or M exceeds the set threshold, it means that the demand increase during the peak period is large or the scheduling difficulty is large, and the routes and shifts need to be matched first; Conditions for not prioritizing matching: If ΔC≤ΔC threshold And M≤M threshold , it means that the passenger flow during peak hours does not change much, and the route scheduling is relatively simple, and it is arranged according to the regular scheduling.

5. The algorithm-based subway crew scheduling optimization method according to claim 4 is characterized in that: Sort the routes according to their calculation expertise, select the corresponding routes according to the peak demand and add them to set R for priority matching, add all available flights to set F, match the routes in set R with the flights in set F one by one, and determine whether the compatibility between the routes and flights meets the preset standards; If the match is successful, continue to determine whether the special intersection set R is empty. If R is empty, it means that all intersections have been matched and the scheduling process ends. If R is not empty, it means that there are still intersections that have not been matched successfully and it is necessary to continue processing the next intersection. If the current flight does not match the route, continue to try to match the next flight in the F set. If the set R is empty, it means that all routes have been successfully matched to suitable flights, and the scheduling process ends. If all flights F have been tried to match and there are still routes that cannot be matched, it is necessary to roll back or adjust the strategy.

6. An algorithm-based subway crew scheduling optimization system, used to implement the algorithm-based subway crew scheduling optimization method according to any one of claims 1 to 5, characterized in that: include: Information acquisition module, data processing module, statistical analysis module and capacity matching module; Information acquisition module: collects the crew's working years to obtain the crew's professionalism and the subway's historical passenger flow data, and passes the specific information to the data processing module as the basis for subsequent data processing; Data processing module: pre-processes the obtained data, filters the historical passenger flow data and calculates the passenger flow difference, uses the professional degree to calculate whether the route and the machine class match and the number of times the first route needs to match, and passes the obtained data set to the statistical analysis module; Statistical analysis module: establish a priority matching mechanism, and analyze whether the peak-hour shifts need to be matched first based on the data obtained by the data processing module; Capacity matching module: prioritizes the routes required during peak hours, determines whether they are a match based on the degree of adaptability, completes the operation of the scheduling system, and achieves smooth system processing.

Images