A management server providing an artificial intelligence task recommendation service for optimizing ground handling personnel operations, a method therefor, and a storage medium storing a program for implementing the same

Abstract

A management server providing an artificial intelligence work recommendation service according to an embodiment of the present invention may include a ground handling operator database storing at least one of ground handling operator identification information, operation history, qualification conditions, preferences, desired working hours, evaluation information, and ground handling history details; and a control unit that, when the current location, working hours, and type of operation of the ground handling operator are input, verifies information corresponding to the ground handling operator's identification information from the ground handling operator database and generates a recommended work set based on the input information of the ground handling operator, wherein the recommended work set determines priority by combining the input information and the information stored in the ground handling operator database, and displays the recommended work set together with the work route by overlapping it on the airport's map information (GIS; Geographic Information System).

Description

Technology Field

[0001] The present invention relates to a management server and method for providing an artificial intelligence task recommendation service. More specifically, the invention relates to a management server and method for providing an artificial intelligence task recommendation service that applies an AI-based smart recommendation method to recommend optimal personnel for each operation by reflecting profile information such as the history, qualifications, proficiency, preferences, fatigue, and location of ground handling operators, thereby preventing structural manpower mismatches such as manpower shortages during peak times or manpower excesses during off-peak times, and minimizing the decline in on-time performance or cost losses caused by analog manpower management methods. Background Technology

[0003] In the aviation industry, since revenue is generated when an aircraft is flying and costs are incurred while it is on the ground, one of the key challenges for airlines worldwide is how to make ground time as efficient as possible.

[0004] Airport ground handling refers to the series of services performed by an aircraft to take off again, such as check-in, boarding, cleaning, maintenance, refueling, cabin cleaning, VIP protocol, wheelchair assistance, and loading. This industry is currently at a critical juncture for digital transformation. Because airport ground handling is a high-density work environment where the aforementioned operations occur simultaneously, the application of digital methods rather than analog methods is required.

[0005] Currently, personnel management at domestic airports remains passive and analog, leading to a structural workforce mismatch where there is a shortage of personnel during peak hours and a surplus during off-peak hours. This can directly result in lower on-time rates, unstable service quality, and increased socioeconomic costs.

[0006] To elaborate, although air travel demand has recovered to some extent since the COVID-19 pandemic, the labor supply remains at 80 to 95% of pre-pandemic levels, resulting in a structural labor shortage. While major airports in developed countries are finding solutions to this structural labor shortage by expanding the employment of foreign workers, Korea remains blocked by restrictive policies.

[0007] In particular, large airports face operational peak times where manpower demand surges by two to three times due to the hub-and-spark strategy, but existing analog systems have reached a limit where flexible response is impossible. The mismatch between manpower supply and demand across different time zones leads to increased waiting times and movement, which results in industry labor shortages or a decline in quality, ultimately incurring costs associated with reduced punctuality and quality.

[0008] Accordingly, while applying Workforce Management (WFM) systems used at major overseas airports to domestic airports could be considered, there are limitations in their utilization due to the fact that these systems do not align with the regulations and operational structures of domestic airports. Furthermore, existing WFM systems are focused on internal staffing and work efficiency, making it difficult to utilize external (on-demand) personnel; additionally, they are unable to address labor shortages and demand variability due to the lack of a spot work matching function.

[0009] Therefore, there is a need to develop a method and management server for an aviation ground handling personnel matching and job recommendation service with a new configuration that can solve the problems of manpower shortage during peak times and manpower excess during off-peak times, while minimizing the decline in on-time performance and cost losses caused by analog manpower management, and can be applied optimally to domestic airports rather than relying on overseas systems for DX.

[0011] Related prior art includes Korean Patent Registration No. 10-1985112 (Title of invention: Intelligent airport resource operation device and method thereof). The problem to be solved

[0013] An embodiment of the present invention provides a management server and a method for providing an AI-based work recommendation service that applies an AI-based smart recommendation method to recommend optimal personnel for each operation by reflecting profile information such as the history, qualifications, proficiency, preferences, fatigue, and location of ground handling operators, thereby preventing structural manpower mismatches such as manpower shortages during peak times or manpower excesses during off-peak times, and minimizing the decline in on-time performance or cost losses caused by analog manpower management methods.

[0015] The problems that the present invention aims to solve are not limited to the problem(s) mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0017] A management server providing an artificial intelligence work recommendation service according to an embodiment of the present invention may include a ground handling operator database storing at least one of ground handling operator identification information, operation history, qualification conditions, preferences, desired working hours, evaluation information, and ground handling history details; and a control unit that, when the current location, working hours, and type of operation of the ground handling operator are input, verifies information corresponding to the ground handling operator's identification information from the ground handling operator database and generates a recommended work set based on the input information of the ground handling operator, wherein the recommended work set determines priority by combining the input information and the information stored in the ground handling operator database, and displays the recommended work set together with the work route by overlapping it on the airport's map information (GIS; Geographic Information System).

[0018] According to one aspect, the system further includes an Airport Operation Database (AODB) containing aircraft operation data, facility operation data, and information on aviation ground handling providers and ground handling operators, and the control unit can generate map information of the airport in conjunction with the Airport Operation Database.

[0019] According to one aspect, the control unit can update the recommended workset by applying an artificial intelligence (AI)-based operational route optimization algorithm to correct the shortest movement path and continuous operations within the airport by linking with the airport operation database and reflecting in real time changes in flight information, including aircraft delays, cancellations, and changes in aircraft takeoff or landing gates, as well as the ground handling operator location information.

[0020] According to one aspect, the control unit may determine the priority of the recommended workset by applying a behavioral pattern reinforcement learning algorithm that learns at least one history of repetitive actions among the ground operator's approval, rejection, or matching time for the operation type and reflects preference and feasibility in the recommendation logic.

[0021] According to one side, when the ground handling work of the ground handling operator is completed, user feedback is received to update the evaluation information of the ground handling operator and store it in the ground handling operator database, and the user feedback stored in the ground handling operator database can be reflected when determining the priority of the recommended workset.

[0022] According to one aspect, the control unit may determine the priority of the recommended workset by applying an artificial intelligence (AI)-based operation route optimization algorithm that recommends a combination ensuring the shortest route and continuous operation within the airport, taking into account at least one of operation type, operation location information, distance between operation locations, and time between operation locations.

[0023] According to one aspect, the system further includes a display unit, wherein the control unit can integrate and evaluate time efficiency, movement efficiency, and waiting efficiency among the recommended work sets based on weights and list and display a predetermined number of recommended work sets along with priority information.

[0024] According to one aspect, when a specific workset among the recommended worksets is selected, the control unit may provide at least one piece of information among a plurality of individual operations included in the specific workset, the operation path of the plurality of individual operations, the start time, end time, start and end location of the operation, and cost of the plurality of individual operations.

[0025] According to one side, the control unit can generate identification information of the ground operator and store it in the ground operator database when the ground operator inputs qualification conditions, desired type of operation, desired working hours, evaluation information, and ground operation history through initial membership registration.

[0026] According to one aspect, the control unit can update the approval, rejection, and matching time required for a specific operation of the ground operator, and the evaluation information of the ground operator through user feedback, and store them in the ground operator database.

[0027] According to one aspect, the control unit may generate a recommended workset for a recommended ground operator through an artificial intelligence (AI) smart recommendation engine that recommends optimal personnel for each operation by reflecting information stored in the ground operator database.

[0028] Meanwhile, a method for providing an artificial intelligence work recommendation service by a management server according to an embodiment of the present invention may include: a ground handling operator database storage step in which at least one of the ground handling operator's identification information, operation history, qualification conditions, preference, desired working hours, evaluation information, and ground handling history details is stored in a ground handling operator database by the management server; an input step in which the current location, working hours, and type of operation of the ground handling operator are input by the management server; a recommendation work set generation step in which information corresponding to the ground handling operator's identification information is verified from the database based on the input information input during the input step by the management server, and a recommendation work set is generated based on the input information of the ground handling operator; a priority determination step in which the priority is determined by combining the input information and the stored information stored in the ground handling operator database among the recommendation work sets generated during the recommendation work set generation step by the management server; and a display step in which the recommendation work set determined by priority is controlled to be displayed together with the work route on the airport's map information (GIS; Geographic Information System).

[0029] Meanwhile, a method for providing an artificial intelligence task recommendation service by a management server can be implemented by a program stored on a computer-readable recording medium. Effects of the invention

[0031] According to an embodiment of the present invention, an artificial intelligence-based smart recommendation method is applied to recommend optimal personnel for each operation by reflecting profile information such as the history, qualifications, proficiency, preferences, fatigue, and location of ground handling operators, thereby preventing structural personnel mismatches such as personnel shortages during peak times or personnel excesses during off-peak times, and minimizing the decline in on-time performance or cost losses caused by analog personnel management methods.

[0032] In addition, by utilizing a reinforcement learning algorithm for the management server's behavioral patterns, the history of ground handling operators' selection, rejection, delay, and repetitive behaviors regarding the recommendation workset can be learned, allowing the operators' preferences or the feasibility of performing operations to be reflected in the recommendation logic.

[0033] In addition, the management server's AI-based operational route optimization algorithm ensures the shortest routes and continuous operations within the airport by considering operation type, work location, and travel distance / time between gates.

[0034] In addition, by establishing a real-time variable response automatic matching system on the management server, operational variables such as adverse weather conditions, flight delays, or cancellations can be detected, and the assignment plan can be automatically recalculated. Brief explanation of the drawing

[0036] FIG. 1 is a block diagram schematically illustrating the configuration of a management server providing an artificial intelligence task recommendation service according to one embodiment of the present invention. FIG. 2a is a flowchart for explaining an example of an artificial intelligence-based smart recommendation performed by the control unit of the management server of FIG. 1. FIG. 2b is a diagram illustrating the process in which a recommended workset is provided to a ground operator by the AI-based smart recommendation shown in FIG. 2a, and operation matching is performed. Figure 3 is a diagram illustrating an example of profile creation and management by the control unit of the management server of Figure 1. Figure 4 is a flowchart illustrating a profile-based filtering process by the control unit of the management server of Figure 1. Figure 5 is a diagram illustrating an example of behavioral pattern reinforcement learning performed by the control unit of the management server of Figure 1. Figure 6 is a diagram illustrating an example of artificial intelligence-based operational path optimization performed by the control unit of the management server of Figure 1. Figure 7 is a diagram illustrating an example of real-time variable correspondence automatic matching performed by the control unit of the management server of Figure 1. Figure 8 is a flowchart of a method for providing aviation ground handling personnel matching and job recommendation services by a management server. Specific details for implementing the invention

[0037] The advantages and / or features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, like reference numerals refer to like components.

[0039] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0040] FIG. 1 is a block diagram schematically illustrating the configuration of a management server providing an artificial intelligence task recommendation service according to one embodiment of the present invention.

[0041] As illustrated herein, a management server (100) providing an aviation ground handling personnel matching and recommendation service according to one embodiment of the present invention may include a ground handling database (110) that stores information about ground handling personnel, a control unit (120) that generates a recommended work set based on input information of ground handling personnel stored in the ground handling database (110), determines the priority of the recommended work set, and displays the recommended work set along with the work route on the airport map information (GIS; Geographic Information System), an airport operation database (130) that stores information about the operation of the airport, and a display unit (140).

[0042] With this configuration, it is possible to resolve the issues of manpower shortage during peak times and manpower excess during off-peak times, while minimizing the decline in on-time performance and cost losses caused by analog manpower management, and to provide ground handling personnel matching and job recommendation services that are optimized for domestic airports rather than DX that relies on overseas systems.

[0043] However, if the management server is a cloud server, unlike what is shown in Fig. 1, the display unit is not included, and the airport operation database can be linked with an external server.

[0044] To explain each configuration, first, the ground operator database (110) of the present embodiment can store information such as ground operator identification information, operation history, qualification conditions, preference, desired working hours, evaluation information, or ground operation history details.

[0045] The control unit (120) of the present embodiment can, when the ground operator's current location, working hours, and type of operation are input, check information corresponding to the ground operator's identification information from the ground operator database (110), and then generate a recommended work set based on the ground operator's input information.

[0046] At this time, the priority of the recommended work set can be determined by combining the input information and the stored information stored in the ground handling database (110), and the recommended work set determined by priority can be controlled to be displayed together with the work route on the airport's map information (GIS) by overlapping.

[0047] In the airport operation database (130) of this embodiment, aircraft operation data, facility operation data, aviation ground handling provider information, and ground handling operator information may be stored. The control unit (120) may generate airport map information in conjunction with the airport operation database (130), and as described above, recommended work sets determined by priority may be displayed overlapping with work routes on the airport map information thus generated. At this time, it may be displayed through the display unit (140).

[0048] Meanwhile, the control unit (120) of the present embodiment can control the creation of a recommended workset for a recommended ground operator through an artificial intelligence (AI) smart recommendation engine that recommends the optimal personnel for each operation by reflecting information stored in the ground operator database (110).

[0049] FIG. 2a is a flowchart for explaining an example of an AI-based smart recommendation performed by the control unit of the management server of FIG. 1, FIG. 2b is a diagram for explaining the process in which a recommended workset is provided to a ground operator by the AI-based smart recommendation shown in FIG. 2a and operation matching is performed, FIG. 3 is a diagram illustrating an example of profile creation and management by the control unit of the management server of FIG. 1, and FIG. 4 is a flowchart showing a profile-based filtering process by the control unit of the management server of FIG. 1.

[0050] The AI ​​smart recommendation engine utilizes intelligent custom matching technology to quantify ground handling operators' qualifications, preferred tasks, working hours, location, performance, etc., and calculates and recommends the most suitable advice.

[0051] As illustrated in the flowchart of FIG. 2, when a profile of a worker (ground operator) is entered (S11), a list of operation candidates can be loaded (S13) through a profile loading process (S12). Subsequently, it is determined whether the qualification conditions are met among the list (S14), and if met, it is determined whether the working hours are met through a qualification filter (S15) (S16), and if the qualification conditions are not met, the worker is excluded from the corresponding operation (S18).

[0052] If the available working hours are satisfied, it is determined whether the work start point is accessible from the current location by passing through a time zone filter (S17) (S19). If possible, preferred and non-preferred information is loaded (S21) by passing through a location filter (S20), the degree of preference match is calculated (S22), the final recommendation score is calculated (S23), then the top N work recommendations are generated (S24), and a recommendation list is provided (S25). Then, the record of worker selection or rejection is saved (S26), and the process is terminated (S27). If the available working hours are not satisfied, the time window is excluded due to mismatch (S32).

[0053] To elaborate, if it is impossible to access the work start point from the current location, exclusion or deduction (S33) is made due to distance or time excess. If the work is excluded from the relevant operation (S18), excluded due to time window mismatch (S32), or if the distance or time excess (S33), the next operation inspection (S31) can be performed to determine whether the qualification conditions are met (S14).

[0054] To elaborate, in the step of generating the top N operation recommendations (S24), for example, one set may be recommended with the configuration of Operation A-Operation B-Operation C, and another set may be recommended with the configuration of Operation A-Operation D-Operation E-Operation C. In other words, various combinations of recommendation work sets can be configured.

[0055] The recommendation list, or recommendation work set, generated in this way is provided to a worker (ground handling worker) through, for example, the terminal (150) of worker 'B' shown in FIG. 2 (e.g., a terminal such as a smartphone), and worker 'B' is enabled to perform ground handling work while moving along the airport route following recommendation 1, thereby completing the work matching for worker 'B'. In this way, the optimal personnel for each work can be recommended by the artificial intelligence smart recommendation engine by the management server (100) of the present embodiment.

[0056] To elaborate, the profile of a ground handling operator can be as shown in the example of Fig. 3. The worker input profile can include the worker's (ground handling operator's) language skills, capabilities / experience, and available work schedule. Additionally, the manager input profile can include information on whether training has been completed, available tasks, and pass ownership, while the server-generated profile can include past operational data. Based on this, a list of operational candidates can be loaded through a profile loading process.

[0057] Based on FIG. 4, an example of a profile-based filtering process is described as follows: a list of wheelchair passengers (S110) is received from an airline. After checking whether the passenger is in the existing customer list (S111), if the passenger is in the list, it is checked whether there is a ground handling agent who has provided service to the passenger (S112). If there is, reviews are checked (S113). If the reviews are excellent, a ground handling agent who has previously provided service to the passenger is assigned (S114). If the reviews are not excellent, the factors of dissatisfaction are identified (S121), and then another ground handling agent capable of resolving the factors of dissatisfaction is assigned (S122). Meanwhile, if the passenger is not in the existing customer list, the passenger's gender and country, etc. are estimated using artificial intelligence (S131), and then a ground handling agent of the same gender who is proficient in the relevant language is assigned (S132).

[0058] Here, if there is no ground handling operator who has provided service to the passenger, the passenger's destination is confirmed (S141), experienced ground handling operators on the route are filtered (S142), specific details are checked (S143), and then a ground handling operator capable of providing the service is assigned (S144).

[0059] Meanwhile, the control unit (120) of the present embodiment can determine the priority of the recommended workset using a behavioral pattern reinforcement learning algorithm that learns at least one of the repeated behavioral history of the ground operator's approval, rejection, or matching time for the operation type and reflects the preference and feasibility in the recommendation logic.

[0060] To elaborate, the control unit (120) receives user feedback when the ground handling work of the ground handling operator is completed, updates the ground handling operator's evaluation information, stores it in the ground handling operator database (110), and can reflect the user feedback stored in the ground handling operator database (110) when determining the priority of the recommended work set.

[0061] Figure 5 is a diagram illustrating an example of behavioral pattern reinforcement learning performed by the control unit of the management server of Figure 1.

[0062] The control unit (120) of the present embodiment can quantitatively model the repetitive selection or non-preference behavior of ground handling operators using a behavioral pattern reinforcement learning algorithm, and can improve the accuracy of recommendations based on preferences for each worker.

[0063] As illustrated in Figure 5, worker behavioral patterns may include acceptance or rejection of operations, and there is a tendency to select the type of work. Optimization based on behavioral pattern reinforcement learning can be performed using the job type vector, time zone vector, mobility vector, and operator preference vector of the behavior embedding layer, where the work completion rate, preference, and mobility efficiency can be calculated through a reward function. This can be applied to personalized recommendations, which can achieve high recommendation accuracy, reduce rejection rates, provide faster acceptance speeds, and adapt to daily patterns.

[0064] The following explains the case where behavioral pattern reinforcement learning is applied to worker 'A', for example. It is assumed that worker 'A' is a worker who tends to avoid long work sets when fatigue accumulates.

[0065] Worker 'A' showed a tendency to refuse cabin cleaning operations after cleaning the aircraft cabin three times in a row, while maintaining acceptance of wheelchair services with short movement paths. In the case of the existing method that does not apply the behavioral pattern reinforcement learning algorithm, the same set of operations was recommended without considering Worker 'A's' fatigue or preference.

[0066] However, after learning the behavioral pattern of worker 'A' who refuses cabin cleaning as the number of cabin cleanings already performed increases, personalized recommendations can be applied in a different way. For example, if worker 'A' has already performed 3 to 4 cabin cleanings, the management server (100) can recommend wheelchair services or other tasks with short movement paths first. Through this, the accumulated fatigue of worker 'A' can be alleviated, claims can be reduced, and safety and work quality can also be improved.

[0067] Meanwhile, the control unit (120) of the present embodiment can update the recommended workset by applying an artificial intelligence (AI)-based operational route optimization algorithm to correct the shortest movement route and continuous operations within the airport by linking with the aforementioned airport operation database (130) and reflecting in real time changes in flight information, including aircraft delays, cancellations, and changes in aircraft takeoff or landing gates, as well as ground handling operator location information.

[0068] In addition, the control unit (120) of the present embodiment can generate identification information of a ground operator and store it in a ground operator database when a ground operator inputs qualification conditions, desired type of operation, desired working hours, evaluation information, and ground operation history through initial membership registration.

[0069] In addition, the control unit (120) can determine the priority of the recommended work set by applying an artificial intelligence (AI)-based operation route optimization algorithm that recommends a combination that guarantees the shortest route and continuous operation within the airport, taking into account the operation type, operation location information, distance between operation locations, and time between operation locations.

[0070] Figure 6 is a diagram illustrating an example of artificial intelligence-based operational path optimization performed by the control unit of the management server of Figure 1.

[0071] Through GIS-based spatial modeling, airport structures such as terminals, ramps, and gates can be constructed as nodes and paths, the location and status of workers such as ground handling personnel can be visualized on a map, and travel distance, path, and ETA can be calculated based on spatial information.

[0072] In addition, it is possible to integrate real-time flight and baggage data from the EAI. It can reflect real-time events from the airport authority's EAI, such as gate changes and baggage arrivals, and automatically recalculate routes and travel times upon the occurrence of events, while enabling the construction of a structure with higher security and stability compared to APIs.

[0073] In addition, prior research data such as actual movement speed, congestion, and operation time can be utilized through big data combination by the management server (100) of this embodiment. Furthermore, the accuracy of GIS and EAI-based ETA models can be improved, impossible combinations can be automatically excluded, and feasible operation sets can be generated.

[0074] This enables the optimization of AI-based operational routes. It allows for the selection of only operational sets that are actually movable and can be executed within the timeframe, and enables real-time re-recommendation of work sets in the event of events such as flight delays or gate changes.

[0075] To illustrate with an example using Fig. 6, a ground handling operator may depart from GATE 38 (starting location: Airside) at an expected start time of 08:00 for VIP protocol and finish operations at exit E (ending location: 1st floor Landside) at an expected end time of 09:00. A ground handling operator may depart from M19 (starting location: 3rd floor Landside) at an expected start time of 09:00 for wheelchair services and finish operations at GATE 49 (ending location: 2nd floor Airside) at an expected end time of 10:00. Additionally, a ground handling operator may depart from GATE 42 (starting location: 2nd floor Airside) at an expected start time of 10:00 for other wheelchair services and finish operations at exit E (ending location: 1st floor Landside) at an expected end time of 11:00. Afterwards, there may be a movement and waiting time of approximately 1 hour and 30 minutes, and then a ground handling operator may depart from GATE 49 (starting location: 2nd floor Airside) at an expected start time of 12:30 for another wheelchair service and finish the operation at exit E (ending location: 1st floor Landside) at an expected end time of 13:30.

[0076] In this way, AI-based operational workflows can be optimized, thereby resolving the issues of labor shortages during peak times and excess manpower during off-peak times, while minimizing the decline in on-time performance and cost losses caused by analog workforce management.

[0077] In addition, the control unit (120) of the present embodiment can automatically match the response to variables that may occur in real time.

[0078] Figure 7 is a diagram illustrating an example of real-time variable correspondence automatic matching performed by the control unit of the management server of Figure 1.

[0079] In the case of this embodiment, the response to real-time variables is automatically matched, and through this, operational variables such as adverse weather, flight delays or cancellations, absenteeism, and tardiness can be detected to automatically recalculate the assignment plan.

[0080] Referring to the flowchart of FIG. 7, for example, when a change in an airplane schedule (S210) occurs, ground handling operators who have applied for handling of the airplane with the changed schedule are filtered (S220), and then a better set of handling is calculated only for the filtered ground handling operators (S230). Next, an app or app push message is sent (S241), and at the same time, a web-mobile message or mobile message, SMS, LMS, MMS, etc. text message is sent (S242), and the ground handling operator is made to confirm (S250) that the handling information has changed.

[0081] Then, the ground operator (worker 'Eul') can check the change information through their terminal (150), for example, confirming that the travel and waiting time has been changed from 1 hour and 30 minutes to 3 hours and thus the time of the wheelchair service has been changed. In addition, they can apply for a change in operation, and can complete the change in operation by selecting Recommendation 1 from Recommendations 1 to 4.

[0082] Meanwhile, the management server (100) of the present embodiment further includes a display unit (140), and the control unit can display a predetermined number of recommended work sets on the display unit (140) by evaluating time efficiency, movement efficiency, and waiting efficiency among the recommended work sets based on weights and listing them together with priority information.

[0083] In the display unit (140) of this embodiment, an airport structure can be displayed. Node / edge networks such as gates, counters, ramps, shuttle stops, security passages, and elevators can be visualized in 2D / 3D.

[0084] In addition, the UI of the display unit (140) may display recommended work sets of priority using various colors, icons, popups, etc. Different icons, colors, and shapes may be assigned and displayed for each operation. Additionally, an ETA label may be displayed, and the scheduled start time may be displayed in the form of a time bar when tapped or hovered, thereby drawing attention to the ETA by displaying it as a border dot or scale-up when the ETA is imminent.

[0085] In addition, a detailed popup may be displayed on the display unit (140), and the start / end location, ETA / End, salary, required qualifications, estimated travel time, location within the set, etc. may be displayed. A recommended route may also be displayed. Operations included in the operation set are displayed as connecting lines, and visibility may be enhanced by using different patterns for each mode.

[0086] Additionally, a filter channel may be displayed on the display unit (140). UI elements can be immediately filtered by time zone, terminal, type of operation, qualification requirements, etc. Additionally, a support button may be displayed. Applications can be made for a set of operations at once, and the status after application can be immediately reflected as an assignment.

[0087] Meanwhile, the control unit (120) of the present embodiment may provide at least one piece of information among a plurality of individual operations included in the specific work set, an operation path of the plurality of individual operations, a start time, an end time, an operation start and end location, and a cost when a specific work set is selected among the recommended work sets.

[0088] In addition, the control unit (120) of the present embodiment can update the approval, rejection, and matching time required for a specific operation of a ground operator, and the ground operator's evaluation information through user feedback, and store them in the ground operator database.

[0089] Meanwhile, the following describes a method for providing aviation ground handling personnel matching and job recommendation services via a management server using the aforementioned configuration.

[0090] Figure 8 is a flowchart of a method for providing aviation ground handling personnel matching and job recommendation services by a management server.

[0091] As illustrated herein, the method of providing aviation ground handling personnel matching and job recommendation services by the management server (100) of the present embodiment may include a ground handling personnel database storage step (S310), an input step (S320), a recommendation workset generation step (S330), a priority determination step (S340), and a display step (S350).

[0092] First, during the ground handling operator database storage step (S310) of the present embodiment, as described above, the ground handling operator's identification information, operation history, qualification conditions, preference, desired working hours, evaluation information, and ground handling history details can be stored in the ground handling operator database (110) by the management server (100).

[0093] In the input step (S320) of this embodiment, the current location, working hours, and type of operation of the ground operator can be received by the control unit (120) of the management server (100) described above.

[0094] In the step (S330) of the recommended workset generation of the present embodiment, the control unit (120) of the management server (100) can identify information corresponding to the identification information of a ground operator from the ground operator database (110) based on the input information entered during the input step, and generate a recommended workset based on the input information of the ground operator.

[0095] Meanwhile, during the priority determination step (S340) of the present embodiment, the priority of the recommended workset can be determined by combining the input information and the stored information stored in the ground operator database (110) among the recommended worksets generated during the recommended workset generation step by the control unit (120) of the management server (100).

[0096] In the display step (S350) of this embodiment, the recommended workset determined by priority can be controlled to be displayed together with the work route by overlapping it on the airport's map information (GIS; Geographic Information System).

[0097] Accordingly, according to the present embodiment, an AI-based smart recommendation method is applied to recommend optimal personnel for each operation by reflecting profile information such as the history, qualifications, proficiency, preferences, fatigue, and location of ground handling operators, thereby preventing structural personnel mismatches such as personnel shortages during peak times or personnel excesses during off-peak times, and minimizing the decline in on-time performance or cost losses caused by analog personnel management methods.

[0098] In addition, the history of ground handling operators' selection, rejection, delay, and repetition of actions regarding the recommended work set can be learned by using the behavioral pattern reinforcement learning algorithm of the management server (100), so that the ground handling operator's preference or the possibility of performing operations can be reflected in the recommendation logic.

[0099] In addition, the shortest route and continuous operation within the airport can be ensured by considering the type of operation, work location, and distance / time between gates through the artificial intelligence-based operation route optimization algorithm of the management server (100).

[0100] In addition, by establishing a real-time variable response automatic matching system of the management server (100), operational variables such as weather deterioration, flight delays or cancellations can be detected and the allocation plan can be automatically recalculated.

[0102] Meanwhile, in the aforementioned embodiment, a management server providing an artificial intelligence task recommendation service was described in detail, and here, the management server can be provided in various forms, such as a hardware server or a cloud server.

[0103] In addition, the method for providing aviation ground handling personnel matching and job recommendation services of the above-described embodiment can be implemented by a program stored on a computer-readable recording medium.

[0104] Although specific embodiments according to the present invention have been described so far, it is obvious that various modifications are possible within the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims set forth below as well as equivalents thereof.

[0105] As described above, although the present invention has been explained by limited embodiments and drawings, the present invention is not limited to the above embodiments, and various modifications and variations are possible from this description by those skilled in the art to which the present invention belongs. Accordingly, the concept of the present invention should be understood only by the claims set forth below, and all equivalent or analogous variations thereof shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0107] 100: Management Server 110: Ground Handling Agent Database 120: Control unit 130: Airport Operations Database 140: Display section 150: Terminal

Claims

Claim 1 A management server providing an AI work recommendation service comprising: a ground handling operator database storing at least one of ground handling operator identification information, operation history, qualification conditions, preferences, desired working hours, evaluation information, and ground handling history details; and a control unit that, when the current location, working hours, and type of operation of the ground handling operator are input, verifies information corresponding to the identification information of the ground handling operator from the ground handling operator database, generates a recommended work set based on the input information of the ground handling operator, determines the priority of the recommended work set by combining the input information and the information stored in the ground handling operator database, and displays the recommended work set together with the work route by overlapping it on the airport's map information (GIS; Geographic Information System); wherein the control unit determines the priority of the recommended work set by applying an AI-based operation route optimization algorithm that recommends a combination ensuring the shortest route and continuous operation within the airport by considering at least one of the operation type, operation location information, distance between operation locations, and time between operation locations. Claim 2 A management server providing an artificial intelligence job recommendation service, wherein, in claim 1, it further includes an Airport Operation Database (AODB) comprising aircraft operation data, facility operation data, aviation ground handling providers, and ground handling operators; and wherein the control unit generates map information of the airport in conjunction with the Airport Operation Database. Claim 3 A management server providing an artificial intelligence work recommendation service, wherein, in paragraph 2, the control unit updates the recommended workset by applying an artificial intelligence (AI)-based operational route optimization algorithm to correct the shortest movement route and continuous work within the airport by linking with the airport operation database and reflecting in real time changes in flight information, including aircraft delays, cancellations, and changes in aircraft takeoff or landing gates, and the ground handling operator location information. Claim 4 A management server providing an artificial intelligence work recommendation service, wherein, in claim 1, the control unit determines the priority of the recommended work set by applying a behavioral pattern reinforcement learning algorithm that learns at least one repetitive behavior history among the ground handling operator's approval, rejection, or matching time for the operation type and reflects preference and feasibility in the recommendation logic. Claim 5 A management server providing an artificial intelligence work recommendation service, wherein, in paragraph 4, the control unit receives user feedback when the ground handling work of the ground handling operator is completed, updates the evaluation information of the ground handling operator and stores it in the ground handling operator database, and reflects the user feedback stored in the ground handling operator database when determining the priority of the recommended work set. Claim 6 delete Claim 7 A management server providing an artificial intelligence work recommendation service, wherein, in claim 1, it further includes a display unit; and the control unit integrates and evaluates time efficiency, movement efficiency, and waiting efficiency among the recommended work sets based on weights and lists and displays a predetermined number of recommended work sets along with priority information. Claim 8 A management server providing an artificial intelligence work recommendation service, wherein, in claim 7, the control unit provides at least one piece of information among a plurality of individual operations included in the specific work set, the operation path of the plurality of individual operations, the start time, end time, operation start and end location, and cost of the plurality of individual operations when a specific work set among the recommended work sets is selected. Claim 9 A management server providing an artificial intelligence job recommendation service, wherein, in claim 1, the control unit generates identification information of the ground handling operator and stores it in the ground handling operator database when the ground handling operator inputs qualification conditions, desired type of operation, desired working hours, evaluation information, and ground handling history through initial membership registration. Claim 10 A management server providing an artificial intelligence job recommendation service according to claim 1, wherein the control unit updates the approval, rejection, and matching time required for a specific operation of the ground operator and the evaluation information of the ground operator through user feedback and stores it in the ground operator database. Claim 11 A management server providing an artificial intelligence work recommendation service, wherein, in claim 1, the control unit generates a recommended work set for a recommended ground handling operator through an artificial intelligence (AI) smart recommendation engine that recommends optimal personnel for each operation by reflecting information stored in the ground handling operator database. Claim 12 A method for providing aviation ground handling personnel matching and job recommendation services by a management server comprises: a ground handling database storage step in which the management server stores at least one of the ground handling operator's identification information, operation history, qualifications, preferences, desired working hours, evaluation information, and ground handling history details in a ground handling operator database; an input step in which the management server receives input of the ground handling operator's current location, working hours, and type of operation; a recommended workset generation step in which the management server verifies information corresponding to the ground handling operator's identification information from the database based on the input information received during the input step and generates a recommended workset based on the ground handling operator's input information; and a priority determination step in which the management server determines a priority among the recommended worksets generated during the recommended workset generation step by combining the input information and the stored information stored in the ground handling operator database. A method for providing an AI work recommendation service, comprising: a display step for controlling the recommended work set determined by priority to be displayed together with the work route on the airport's map information (GIS; Geographic Information System); wherein the priority determination step determines the priority of the recommended work set by applying an AI-based operational route optimization algorithm that recommends a combination ensuring the shortest route and continuous work within the airport by considering at least one of the operational type, operational location information, distance between operational locations, and time between operational locations. Claim 13 A program stored on a computer-readable recording medium for implementing the method of providing an artificial intelligence business recommendation service as described in paragraph 12.

Images