Two-stage operation scheduling method and system based on task coverage

Abstract

The invention discloses a two-stage operation planning and scheduling method and system based on task coverage, and relates to the technical field of intelligent scheduling. Multi-source real-time data is fused to generate a coverage confidence label, so that a scheduling scheme is automatically adapted to emergency scenes such as machine position change and meteorological disturbance, and manual intervention is reduced; through a shadow chain pre-generation and automatic switching mechanism, a shift chain is quickly reconstructed at the early stage of delay triggering, and chain resource shortage is avoided; the differentiated toughness coverage threshold ensures rigid coverage of the core task, and meanwhile, resource allocation of the auxiliary task is elastically adjusted, so that balance between safety and cost is realized; and the actual rest interval of the employees is dynamically monitored, the labor compliance is maintained by combining shadow chain switching, and the operation risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent scheduling technology, and in particular to a two-stage operations scheduling method and system based on task coverage. Background Art

[0002] Ground service support at modern large airports faces the normal challenge of high-frequency cross-day flight delays, especially affected by factors such as weather and flow control. Delays in previous flights often trigger a domino-like shortage of support resources for the next day.

[0003] In this context, mainstream two-stage operations scheduling systems employ a task grouping optimization and dynamic personnel assignment architecture. The first stage generates standardized shift chains based on historical data and flight plans, while the second stage implements labor allocation through constraint planning. While this approach optimizes labor costs and task coverage in static scenarios, it suffers from three dynamic adaptability flaws. First, it relies on rigid time anchoring: the shift start and end times preset in the grouping stage, such as the morning shift's 06:00-14:00, are decoupled from the actual flight execution times. When delays across days result in insufficient rest intervals for employees, the system relies solely on manual adjustments, which can easily trigger conflicts with subsequent shifts. Second, it suffers from fragmented decision-making in the discrete stages: the grouping stage pursues global cost optimization but fails to incorporate flexibility in personnel reuse, such as whether employee A can seamlessly switch to emergency tasks after a morning shift delay. This forces the assignment stage to be relegated to localized patching. Third, it suffers from limitations in its passive response model: existing dynamic adjustment algorithms, such as real-time rolling optimization, must wait for a delay to occur before triggering rescheduling. This makes it impossible to predict the delay's transmission path and reserve buffer resources in advance, exacerbating the domino effect.

[0004] Some solutions attempt to predict the impact of delays through reinforcement learning, or inject risk hedging strategies such as reserving 5% flexible manpower during the ring formation stage to alleviate the problem; however, the former relies on a large amount of labeled data and has high computing latency, making it difficult to meet the airport's minute-level decision-making needs; the latter lacks scenario perception due to its fixed reservation ratio, resulting in a waste of manpower in the event of minor delays and is still a drop in the bucket in the bucket in the event of severe delays; the latest development proposes "shadow flight chain" technology, which reduces adjustment costs by pre-generating alternative scheduling paths, but its static pre-generation model cannot adapt to the randomness and correlation of delay events. In actual applications, it still relies on manual selection of switching timing, failing to form a closed-loop optimization. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides a two-stage operations scheduling method and system based on task coverage to solve the problem that traditional two-stage scheduling systems are difficult to cope with domino-type resource shortages caused by cross-day delays due to rigid time anchoring, stage separation and passive response mode.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a two-stage operations scheduling method based on task coverage, which includes:

[0009] Step S1: Acquire flight support mission data, employee basic data, and dynamic operation data, including real-time flight status, aircraft stand change information, and weather warning signals;

[0010] Step S2: Based on the discretized time window, the support task is modeled in a spatiotemporal coupling manner to generate a task requirement matrix with coverage confidence labels. The coverage confidence is dynamically calculated based on the historical task deviation rate and real-time data fluctuations.

[0011] Step S3: constructing an elastic coverage cost function, wherein the function includes a dynamic weight adjustment term, wherein the understaffing cost coefficient and the overstaffing cost coefficient are dynamically updated based on the real-time operating status;

[0012] Step S4: Generate a scheduling plan through a two-stage optimization. In the first stage, a coverage-driven shift set is generated based on the task demand matrix and the elastic coverage cost function. In the second stage, personnel-shift adaptation optimization is performed by combining employee ability labels and task pressure coefficients.

[0013] Step S5: pre-generate a set of shadow flight chains associated with the main schedule plan. When a domino effect is triggered by a cross-day flight delay, automatically switch to the optimal shadow flight chain to maintain coverage integrity.

[0014] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, the spatiotemporal coupling modeling in step S2 includes:

[0015] Calculate the task connection time based on the topological relationship of the aircraft position coordinates, and split the original task time window into the connection period and the effective operation period;

[0016] Based on the non-uniform time granularity division rule, compensation for docking loss time is added to remote aircraft stand missions to generate a revised mission requirement matrix;

[0017] The coverage confidence labels are generated as follows:

[0018] a. Calculate the mission volume deviation rate for each period based on historical flight support mission execution data for the same period;

[0019] b. Real-time access to aircraft stand scheduling system data. When the aircraft stand change rate exceeds a set threshold, the coverage confidence level of the associated time period is marked as downgraded;

[0020] c. For the period covered by the meteorological warning signal, the confidence value will be lowered proportionally according to the warning level.

[0021] As a preferred solution of the two-stage operation scheduling method based on task coverage described in the present invention, in step S1, the method of generating the task demand matrix with coverage confidence labels is to assign coverage confidence C to the elements of the original task demand matrix for each discrete space-time unit i according to the following process: i ;

[0022] Extract the historical deviation rate δ from the audited historical task execution system i ,

[0023] Call the flight status interface to obtain the flight delay rate fluctuation ΔS i ,

[0024] Link to the parking space scheduling system to read the parking space change rate ΔG i ,

[0025] Access the meteorological warning platform to obtain warning level L i ,

[0026] Calculate the real-time volatility factor R using historical averages and real-time volatility information i , the calculation formula is:

[0027]

[0028] Among them, a, b, c are the weights of the wavelet, ΔS i represents the fluctuation of flight delay rate in period i, represents the historical average flight delay rate, ΔG i represents the aircraft position change rate in the i-th period, represents the historical average aircraft position change rate, L i Indicates the meteorological warning level for the i-th period;

[0029] The exponential decay model is used to fuse historical and real-time information to obtain the initial value C i :

[0030] C i =exp(-(w1δ i +w2R i )),

[0031] Among them, w1 and w2 are the combined weights of historical deviation rate and real-time volatility factor, δ i is the historical task deviation rate in period i, R i is the real-time volatility factor for the i-th period;

[0032] When the aircraft position change rate exceeds the threshold θ G When the confidence level is Ci ←C i ×d G Perform downgrade of aircraft position change, where θ G is the aircraft position change rate threshold, d G is the degradation factor for the aircraft position change;

[0033] When the weather warning level exceeds the threshold θ L When the confidence level is C i ←C i ×d L Perform meteorological downgrade, where θ L is the meteorological warning level threshold, d L is the meteorological degradation factor;

[0034] The downgraded C i Append to the corresponding position of the original requirement matrix to form the final task requirement matrix with coverage confidence labels.

[0035] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, the elastic coverage cost function satisfies:

[0036] When the real-time flight delay rate exceeds the preset threshold, the weight of the insufficient staff cost coefficient is increased, while the weight of the excessive staff cost coefficient is reduced;

[0037] Differentiated resilience coverage thresholds are set for different task types, rigid coverage constraints are configured for core support task types, and dynamic coverage degradation is allowed for auxiliary task types.

[0038] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, wherein: the core support task types include aircraft refueling and passenger emergency evacuation channel maintenance;

[0039] The rigid coverage constraint requires that the actual number of people on duty during the task period is ≥ 100% of the required number of people, and the personnel qualification matching degree is ≥ 95%.

[0040] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, the employee capability label includes stress tolerance coefficient, multi-tasking score and regional mobility efficiency, and the task stress coefficient is calculated based on task duration, cross-region frequency and equipment complexity;

[0041] In the second stage of optimization, high-stress coefficient tasks are assigned first to employees with high stress tolerance coefficients, and the frequency of the same employee performing high-stress tasks continuously is limited.

[0042] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, the stress resistance coefficient is calculated using the following dimensions:

[0043] Historical high-load task completion rate;

[0044] Emergency task response time;

[0045] Cross-region mobility efficiency.

[0046] As a preferred solution of the two-stage operation and scheduling method based on task coverage described in the present invention, the generation method of the shadow shift chain set includes:

[0047] Generate at least three alternative chains for each main shift chain. The alternative chains are obtained by replacing the shift start and end times or employee combinations.

[0048] Set the shadow chain activation conditions. When the actual employee rest interval is less than the statutory minimum or the burst task coverage rate is lower than the resilience threshold, automatic switching is triggered.

[0049] The candidate chain generation rules include:

[0050] Time offset chain: keep the original shift task type and shift the start and end time forward or backward by the set duration;

[0051] Staff replacement chain: Replace a preset proportion of employees in the original shift, giving priority to employees with the same qualifications and higher regional mobility efficiency;

[0052] Task downgrade chain: For non-core support tasks, the number of personnel covered is allowed to be reduced to free up resources for core tasks.

[0053] As a preferred solution of the two-stage operation scheduling method based on task coverage described in the present invention, in step S5, in the process of generating at least three alternative chains for each main shift chain, for any main shift chain C, an alternative chain B is generated based on the three dimensions of time offset, personnel replacement and task degradation. k (k=1,2,3), the process includes:

[0054] Shift the original start and end times of each shift j in the main chain as a whole to obtain the kth time-shifted alternative chain:

[0055] T ′s,j,k =T s,j +Δt k ,T e,j,k =T e,j +Δt k ,

[0056] Among them, T s,j 、T e,j are the original starting and ending times of the jth shift, Δt kis the time offset of the kth candidate chain, and its value set is {τ, -τ}, where τ is a fixed time step;

[0057] The original set E of employees in shift j with proportion p j When replacing members, priority is given to employees with excellent mobility efficiency and stress resistance:

[0058] Define the selection weight for each candidate employee e:

[0059] W e =λQ e +(1-λ)M e ,

[0060] Among them, Q e is the stress resistance coefficient of employee e, M e is the cross-region mobility efficiency per unit time, λ∈(0,1) is the weight parameter to balance the two,

[0061] Select a new set from the pool P of available workers:

[0062]

[0063] Among them, n j is the number of people required for the jth shift, and p is the replacement ratio;

[0064] The coverage requirement r for non-core tasks in shift j j According to the degradation factor β k Make adjustments to generate the k-th task downgrade alternative chain:

[0065] r j,k =r j ×β k ,

[0066] Among them, r j is the original coverage requirement, β k ∈(0,1) is the degradation factor of the kth alternative chain;

[0067] After completing the above three strategies, three different alternative chains {B1, B2, B3} are obtained, which can be stored in parallel with the main chain for subsequent automatic switching decisions.

[0068] In a second aspect, the present invention provides a two-stage operation and scheduling system based on task coverage, comprising:

[0069] The data fusion module is used to access flight plan data, real-time operation data, and employee capability databases, and output support task flows with time and space labels;

[0070] Overlay calculation engine, implement two-stage operation scheduling method, generate main scheduling plan and associated shadow shift chain;

[0071] The dynamic compensation module, when coverage gaps or compliance risks are detected, calls on flexible human resources pools and triggers local incremental optimization;

[0072] The compliance verification interface connects to the flight execution system in real time, monitors employees' actual rest intervals and task coverage status, and drives shadow chain switching decisions.

[0073] The beneficial effects of the present invention are as follows: the present invention significantly improves the adaptability of the scheduling system to dynamic risks such as cross-day delays through dynamic coverage confidence driving and shadow shift chain pre-embedded technology: it integrates multi-source real-time data to generate coverage confidence labels, so that the scheduling plan automatically adapts to sudden scenarios such as aircraft position changes and weather disturbances, reducing manual intervention; through shadow chain pre-generation and automatic switching mechanism, the shift chain is quickly reconstructed at the early stage of delay triggering to avoid chain resource shortages; differentiated resilience coverage thresholds ensure rigid coverage of core tasks, while flexibly adjusting the allocation of auxiliary task resources to achieve a balance between safety and cost; dynamically monitor employees' actual rest intervals, and combine shadow chain switching to maintain labor compliance and reduce operational risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 Schematic diagram of the process of the two-stage operations scheduling method based on task coverage in Example 1.

[0076] Figure 2 This is a schematic diagram of the framework of the two-stage operations scheduling system based on task coverage in Example 1. DETAILED DESCRIPTION

[0077] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0078] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0080] Example 1, with reference to Figure 1 and Figure 2 This embodiment provides a two-stage operation and scheduling method based on task coverage, including the following steps:

[0081] Step S1: Acquire flight support mission data, employee basic data, and dynamic operation data, including real-time flight status, aircraft stand change information, and weather warning signals;

[0082] Step S2: Based on the discretized time window, the support task is modeled in a spatiotemporal coupling manner to generate a task requirement matrix with coverage confidence labels. The coverage confidence is dynamically calculated based on the historical task deviation rate and real-time data fluctuations.

[0083] The spatiotemporal coupling modeling in step S2 includes:

[0084] Calculate the task connection time based on the topological relationship of the aircraft position coordinates, and split the original task time window into the connection period and the effective operation period;

[0085] Based on the non-uniform time granularity division rule, compensation for docking loss time is added to remote aircraft stand missions to generate a revised mission requirement matrix;

[0086] Coverage confidence labels are generated in the following way:

[0087] a. Calculate the mission volume deviation rate for each period based on historical flight support mission execution data for the same period;

[0088] b. Real-time access to aircraft stand scheduling system data. When the aircraft stand change rate exceeds a set threshold, the coverage confidence level of the associated time period is marked as downgraded;

[0089] c. For the period covered by the meteorological warning signal, the confidence value will be adjusted downward proportionally to the warning level;

[0090] In step S1, the task requirement matrix with coverage confidence labels is generated by assigning the coverage confidence C to the elements of the original task requirement matrix for each discrete spatiotemporal unit i according to the following process: i ;

[0091] Extract the historical deviation rate δ from the audited historical task execution system i ,

[0092] Call the flight status interface to obtain the flight delay rate fluctuation ΔS i ,

[0093] Link to the parking space scheduling system to read the parking space change rate ΔG i ,

[0094] Access the meteorological warning platform to obtain warning level L i ,

[0095] Calculate the real-time volatility factor R using historical averages and real-time volatility information i , the calculation formula is:

[0096]

[0097] Among them, a, b, c are the weights of the wavelet, ΔS i represents the fluctuation of flight delay rate in period i, represents the historical average flight delay rate, ΔG i represents the aircraft position change rate in the i-th period, represents the historical average aircraft position change rate, L i Indicates the meteorological warning level for the i-th period;

[0098] The exponential decay model is used to fuse historical and real-time information to obtain the initial value C i :

[0099] C i =exp(-(w1δ i +w2R i )),

[0100] Among them, w1 and w2 are the combined weights of historical deviation rate and real-time volatility factor, δ i is the historical task deviation rate in period i, R i is the real-time volatility factor for the i-th period;

[0101] When the aircraft position change rate exceeds the threshold θ G When the confidence level is C i ←C i ×d G Perform downgrade of aircraft position change, where θ G is the aircraft position change rate threshold, d G is the degradation factor for the aircraft position change;

[0102] When the weather warning level exceeds the threshold θ L When the confidence level is C i ←C i ×d L Perform meteorological downgrade, where θ L is the meteorological warning level threshold, d L is the meteorological degradation factor;

[0103] The downgraded C i Append to the corresponding position of the original demand matrix to form the final task demand matrix with coverage confidence labels;

[0104] Specifically, this process integrates historical deviations and real-time fluctuations from multiple sources at the level of each spatiotemporal unit. Adjustable weights and exponential decay ensure a smooth confidence response. Degradation rules carefully distinguish the impact of aircraft position changes and weather warnings on coverage capabilities, allowing the model to adjust promptly in the event of sudden changes. The parameterized design of dynamic factors and degradation factors enhances the model's adaptability and allows for flexible adjustment based on operational strategies.

[0105] Step S3: constructing an elastic coverage cost function, which includes a dynamic weight adjustment term, wherein the understaffing cost coefficient and the overstaffing cost coefficient are dynamically updated based on the real-time operating situation;

[0106] The elastic covering cost function satisfies:

[0107] When the real-time flight delay rate exceeds the preset threshold, the weight of the insufficient staff cost coefficient is increased, while the weight of the excessive staff cost coefficient is reduced;

[0108] Differentiated resilience coverage thresholds are set for different mission types. Rigid coverage constraints are configured for core mission types, while dynamic coverage degradation is allowed for auxiliary mission types.

[0109] Core support mission types include aircraft refueling and passenger emergency evacuation route maintenance;

[0110] The rigid coverage constraint requires that the actual number of people on duty during the task period must be ≥ 100% of the required number of people, and the personnel qualification matching degree must be ≥ 95%;

[0111] Step S4: Generate a scheduling plan through a two-stage optimization. In the first stage, a coverage-driven shift set is generated based on the task demand matrix and the elastic coverage cost function. In the second stage, personnel-shift adaptation optimization is performed by combining employee ability labels and task pressure coefficients.

[0112] Employee capability labels include stress tolerance, multi-tasking score, and regional mobility efficiency. The task stress coefficient is calculated based on task duration, cross-region frequency, and equipment complexity.

[0113] In the second phase of optimization, high-stress tasks are assigned first to employees with high stress tolerance, and the frequency of the same employee performing high-stress tasks consecutively is limited;

[0114] The compressive strength coefficient is calculated using the following dimensions:

[0115] Historical high-load task completion rate, such as the percentage of tasks exceeding 8 hours completed on time in the past 30 days;

[0116] Emergency task response time, that is, the deviation between the average arrival time at the work point and the standard time;

[0117] Cross-zone movement efficiency, that is, the number of inter-station moves completed per unit time;

[0118] Step S5: pre-generate a set of shadow flight chains associated with the main schedule. When a domino effect is detected due to a flight delay across multiple days, automatically switch to the optimal shadow flight chain to maintain coverage integrity.

[0119] The shadow shift chain set is generated in the following ways:

[0120] Generate at least three alternative chains for each main shift chain. The alternative chains are obtained by replacing the shift start and end times or employee combinations.

[0121] Set the shadow chain activation conditions. When the actual employee rest interval is less than the statutory minimum or the burst task coverage rate is lower than the resilience threshold, automatic switching is triggered.

[0122] The alternative chain generation rules include:

[0123] Time offset chain: keep the original shift task type and shift the start and end time forward or backward by the set duration;

[0124] Staff replacement chain: Replace a preset proportion of employees in the original shift, giving priority to employees with the same qualifications and higher regional mobility efficiency;

[0125] Mission downgrade chain: For non-core support missions, the number of personnel covered is allowed to be reduced to free up resources for core missions;

[0126] In step S5, in the process of generating at least three alternative chains for each main shift chain, for any main shift chain C, an alternative chain B is generated by three dimensions: time offset, personnel replacement and task degradation. k (k=1,2,3), the process includes:

[0127] Shift the original start and end times of each shift j in the main chain as a whole to obtain the kth time-shifted alternative chain:

[0128] T s,j,k =T s,j +Δt k ,T e,j,k =T e,j +Δt k ,

[0129] Among them, T s,j 、T e,j are the original starting and ending times of the jth shift, Δt kis the time offset of the kth candidate chain, and its value set is {τ, -τ}, where τ is a fixed time step;

[0130] The original set E of employees in shift j with proportion p j When replacing members, priority is given to employees with excellent mobility efficiency and stress resistance:

[0131] Define the selection weight for each candidate employee e:

[0132] W e =λQ e +(1-λ)M e ,

[0133] Among them, Q e is the stress resistance coefficient of employee e, M e is the cross-region mobility efficiency per unit time, λ∈(0,1) is the weight parameter to balance the two,

[0134] Select a new set from the pool P of available workers:

[0135]

[0136] Among them, n j is the number of people required for the jth shift, and p is the replacement ratio;

[0137] The coverage requirement r for non-core tasks in shift j j According to the degradation factor β k Make adjustments to generate the k-th task downgrade alternative chain:

[0138] r j,k =r j ×β k ,

[0139] Among them, r j is the original coverage requirement, β k ∈(0,1) is the degradation factor of the kth alternative chain;

[0140] After completing the above three strategies, three different alternative chains {B1, B2, B3} are obtained, which can be stored in parallel with the main chain for subsequent automatic switching decisions;

[0141] Specifically, through the above three-dimensional alternative chain generation method, the system has multiple response plans when facing cross-day delays or sudden gaps. The time offset strategy can quickly adjust the overall operation window to respond to lagging or advanced flight dynamics. The personnel replacement strategy combines employee stress resistance and mobility efficiency to ensure continuous coverage of key positions with the optimal combination. The task downgrade strategy allows limited resources to be concentrated on core tasks when resources are tight to maintain safety and compliance.

[0142] This embodiment also provides a two-stage operations scheduling system based on task coverage, including:

[0143] The data fusion module is used to access flight plan data, real-time operation data, and employee capability databases, and output support task flows with time and space labels;

[0144] Overlay calculation engine, implement two-stage operation scheduling method, generate main scheduling plan and associated shadow shift chain;

[0145] The dynamic compensation module, when coverage gaps or compliance risks are detected, calls on flexible human resources pools and triggers local incremental optimization;

[0146] The compliance verification interface connects to the flight execution system in real time, monitors employees' actual rest intervals and task coverage status, and drives shadow chain switching decisions.

[0147] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A two-stage operation scheduling method based on task coverage, characterized in that: include, Step S1: Acquire flight support mission data, employee basic data, and dynamic operation data, including real-time flight status, aircraft stand change information, and weather warning signals; Step S2: Based on the discretized time window, the support task is modeled in a spatiotemporal coupling manner to generate a task requirement matrix with coverage confidence labels. The coverage confidence is dynamically calculated based on the historical task deviation rate and real-time data fluctuations. Step S3: constructing an elastic coverage cost function, wherein the function includes a dynamic weight adjustment term, wherein the understaffing cost coefficient and the overstaffing cost coefficient are dynamically updated based on the real-time operating status; Step S4: Generate a scheduling plan through a two-stage optimization. In the first stage, a coverage-driven shift set is generated based on the task demand matrix and the elastic coverage cost function. In the second stage, personnel-shift adaptation optimization is performed by combining employee ability labels and task pressure coefficients. Step S5: pre-generate a set of shadow flight chains associated with the main schedule plan. When a domino effect is triggered by a cross-day flight delay, automatically switch to the optimal shadow flight chain to maintain coverage integrity.

2. A two-stage operation and scheduling method based on task coverage as claimed in claim 1, characterized in that: The spatiotemporal coupling modeling in step S2 includes: Calculate the task connection time based on the topological relationship of the aircraft position coordinates, and split the original task time window into the connection period and the effective operation period; Based on the non-uniform time granularity division rule, compensation for docking loss time is added to remote aircraft stand missions to generate a revised mission requirement matrix; The coverage confidence labels are generated as follows: a. Calculate the mission volume deviation rate for each period based on historical flight support mission execution data for the same period; b. Real-time access to aircraft stand scheduling system data. When the aircraft stand change rate exceeds a set threshold, the coverage confidence level of the associated time period is marked as downgraded; c. For the period covered by the meteorological warning signal, the confidence value will be lowered proportionally according to the warning level.

3. A two-stage operation and scheduling method based on task coverage as claimed in claim 2, characterized in that: In step S1, the method of generating the task requirement matrix with coverage confidence labels is to assign the coverage confidence C to the elements of the original task requirement matrix for each discrete spatiotemporal unit i according to the following process: i ; Extract the historical deviation rate δ from the audited historical task execution system i , Call the flight status interface to obtain the flight delay rate fluctuation ΔS i , Link to the parking space scheduling system to read the parking space change rate ΔG i , Access the meteorological warning platform to obtain warning level L i , Calculate the real-time volatility factor R using historical averages and real-time volatility information i , the calculation formula is: Among them, a, b, c are the weights of the wavelet, ΔS i represents the fluctuation of flight delay rate in period i, represents the historical average flight delay rate, ΔG i represents the aircraft position change rate in the i-th period, represents the historical average aircraft position change rate, L i Indicates the meteorological warning level for the i-th period; The exponential decay model is used to fuse historical and real-time information to obtain the initial value C i : C i =exp(-(w1δ i +w2R i )), Among them, w1 and w2 are the combined weights of historical deviation rate and real-time volatility factor, δ i is the historical task deviation rate in period i, R i is the real-time volatility factor for the i-th period; When the aircraft position change rate exceeds the threshold θ G When the confidence level is C i ←C i ×d G Perform downgrade of aircraft position change, where θ G is the aircraft position change rate threshold, d G is the degradation factor for the aircraft position change; When the weather warning level exceeds the threshold θ L When the confidence level is C i ←C i ×d L Perform meteorological downgrade, where θ L is the meteorological warning level threshold, d L is the meteorological degradation factor; The downgraded C i Append to the corresponding position of the original requirement matrix to form the final task requirement matrix with coverage confidence labels.

4. The two-stage operation and scheduling method based on task coverage as claimed in claim 1, characterized in that: The elastic cover cost function satisfies: When the real-time flight delay rate exceeds the preset threshold, the weight of the insufficient staff cost coefficient is increased, while the weight of the excessive staff cost coefficient is reduced; Differentiated resilience coverage thresholds are set for different task types, rigid coverage constraints are configured for core support task types, and dynamic coverage degradation is allowed for auxiliary task types.

5. A two-stage operation and scheduling method based on task coverage as claimed in claim 4, characterized in that: The core support mission types mentioned include aircraft refueling and passenger emergency evacuation route maintenance; The rigid coverage constraint requires that the actual number of people on duty during the task period is ≥ 100% of the required number of people, and the personnel qualification matching degree is ≥ 95%.

6. The two-stage operation and scheduling method based on task coverage according to claim 1, characterized in that: The employee capability label includes stress tolerance coefficient, multi-tasking score and regional mobility efficiency. The task stress coefficient is calculated based on task duration, cross-region frequency and equipment complexity. In the second stage of optimization, high-stress coefficient tasks are assigned first to employees with high stress tolerance coefficients, and the frequency of the same employee performing high-stress tasks continuously is limited.

7. A two-stage operation and scheduling method based on task coverage as claimed in claim 6, characterized in that: The compressive strength coefficient is calculated using the following dimensions: Historical high-load task completion rate; Emergency task response time; Cross-region mobility efficiency.

8. The two-stage operation and scheduling method based on task coverage as claimed in claim 1, characterized in that: The generation method of the shadow shift chain set includes: Generate at least three alternative chains for each main shift chain. The alternative chains are obtained by replacing the shift start and end times or employee combinations. Set the shadow chain activation conditions. When the actual employee rest interval is less than the statutory minimum or the burst task coverage rate is lower than the resilience threshold, automatic switching is triggered. The candidate chain generation rules include: Time offset chain: keep the original shift task type and shift the start and end time forward or backward by the set duration; Staff replacement chain: Replace a preset proportion of employees in the original shift, giving priority to employees with the same qualifications and higher regional mobility efficiency; Task downgrade chain: For non-core support tasks, the number of personnel covered is allowed to be reduced to free up resources for core tasks.

9. The two-stage operation and scheduling method based on task coverage as claimed in claim 8, characterized in that: In step S5, in the process of generating at least three alternative chains for each main shift chain, for any main shift chain C, an alternative chain B is generated by three dimensions: time offset, personnel replacement and task degradation. k (k=1,2,3), the process includes: Shift the original start and end times of each shift j in the main chain as a whole to obtain the kth time-shifted alternative chain: T s,j,k =T s,j +Δt k ,T e,j,k =T e,j +Δt k , Among them, T s,j 、T e,j are the original starting and ending times of the jth shift, Δt k is the time offset of the kth candidate chain, and its value set is {τ, -τ}, where τ is a fixed time step; The original set E of employees in shift j with proportion p j When replacing members, priority is given to employees with excellent mobility efficiency and stress resistance: Define the selection weight for each candidate employee e: W e =λQ e +(1-λ)M e , Among them, Q e is the stress resistance coefficient of employee e, M e is the cross-region mobility efficiency per unit time, λ∈(0,1) is the weight parameter to balance the two, Select a new set from the pool P of available workers: Among them, n j is the number of people required for the jth shift, and p is the replacement ratio; The coverage requirement r for non-core tasks in shift j j According to the degradation factor β k Make adjustments to generate the k-th task downgrade alternative chain: r j,k ＝r j ×β k ， Among them, r j is the original coverage requirement, β k ∈(0,1) is the degradation factor of the kth alternative chain; After completing the above three strategies, three different alternative chains {B1, B2, B3} are obtained, which can be stored in parallel with the main chain for subsequent automatic switching decisions.

10. A two-stage operation and scheduling system based on task coverage, based on the two-stage operation and scheduling method based on task coverage according to any one of claims 1 to 9, characterized in that: include: The data fusion module is used to access flight plan data, real-time operation data, and employee capability databases, and output support task flows with time and space labels; Overlay calculation engine, implement two-stage operation scheduling method, generate main scheduling plan and associated shadow shift chain; The dynamic compensation module, when coverage gaps or compliance risks are detected, calls on flexible human resources pools and triggers local incremental optimization; The compliance verification interface connects to the flight execution system in real time, monitors employees' actual rest intervals and task coverage status, and drives shadow chain switching decisions.

Images