Airport catering task dynamic scheduling system based on micro service and event driving

Abstract

The invention relates to an airport catering task dynamic scheduling system based on micro-service and event driving, and relates to the field of data processing specially suitable for administrative, commercial, financial, management, supervision or prediction purposes, the system comprises a catering prediction device, a catering task scheduling device, a catering task scheduling device, a catering task scheduling device, a catering task scheduling device and a catering task scheduling device, triggering the event to drive the prediction model to execute one catering prediction operation every preset time duration until the target flight actually takes off, so as to obtain the predicted consumption quantity of various foods of the target flight at the execution moment of the catering prediction operation; and a dynamic dispatch means for performing an emergency dispatch of the insufficient food based on the predicted consumption amount. According to the invention, for the technical problem that the dining demands of the same passenger group under different delay degrees of the same flight are difficult to meet, the micro-service architecture is adopted to perform intelligent prediction processing on the dining demands of the same passenger group under different delay degrees of the target flight, so that the technical problem is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing specifically suitable for administrative, commercial, financial, management, supervisory or forecasting purposes, and in particular to a dynamic scheduling system for airport catering tasks based on microservices and event-driven. Background Art

[0002] Airport catering units and airline catering departments provide catering services to aircraft operating at various parking stands, a daily task for these departments. Generally, these departments ration food items for departing flights that day based on ticket sales, the number of passengers actually traveling, and historical food consumption. Specifically, they utilize food supply warehouses located at the airport to carry out these rations. In other words, these departments primarily ration food items for each flight based on historical experience. Generally, a reserve quantity of food is always delivered to the aircraft. If, after delivering meals to the crew, the aircraft discovers a shortage before takeoff, they will contact the airport catering unit and airline catering department for additional food to meet passenger dining needs.

[0003] For example, Chinese invention patent publication CN119740846A proposes an airport catering scheduling system based on big data analysis. The system comprises a real-time data perception layer, a decision-making optimization core layer, and an execution monitoring layer. The real-time data perception layer uses airport operation databases, IoT sensors, and RFID tags to collect flight dynamics, resource status, and environmental variable data. The decision-making optimization core layer's fusion prediction module uses an improved deep learning model to predict meal demand and resource consumption. The dynamic scheduling module uses a multi-objective genetic algorithm to generate resource allocation plans. The path planning module applies an improved ant colony algorithm to determine the optimal transportation route. The execution monitoring layer monitors plan execution through a digital twin visualization platform and traces abnormal events through a blockchain traceability unit. This invention can effectively improve the rationality of airport catering resource allocation, distribution efficiency, and management reliability, effectively guaranteeing the quality of airport catering services and adapting to the operational needs of modern airports.

[0004] For example, Chinese invention patent publication CN118504950A proposes an airport catering scheduling system. By constructing an accurate three-dimensional model of the airport, the system can clearly present features such as the airport's terrain, buildings, and catering routes, providing an accurate spatial reference for catering scheduling. The positioning module on the delivery vehicle can synchronize the vehicle's position to the airport's three-dimensional model in real time, allowing the dispatch center to grasp the delivery progress in real time. The delivery planning module can reasonably allocate delivery tasks based on the catering sequence model and food truck information, ensuring that each delivery vehicle has a balanced load and avoiding situations where some vehicles are overloaded while others are idle. The flight catering analysis module, through in-depth analysis of flight historical data and ticket purchase information, can accurately estimate the number of diners on each flight, and prepare ingredients based on the catering sequence model and meal demand in subsequent time intervals, thus ensuring the timely supply of required ingredients.

[0005] Obviously, the above-mentioned existing technologies only involve the specific implementation process of airport catering services, and do not involve the analysis and scheduling of catering needs for each flight in the future. As a result, the current rough catering model still relies on historical experience and on-site manual coordination. It is easy to cause a mismatch between the quantity allocated for a certain flight and the actual quantity required by passengers, or cause waste of catering resources, or cause insufficient catering supply, causing dissatisfaction among flight passengers. Especially in the case of flight delays, because different passengers have different dining times and dining habits, even on the same flight, the dining needs of the same passenger group will be different when there are different degrees of time delays. How to dynamically obtain the different dining needs of the same passenger group under different degrees of time delays and provide key data for dynamic scheduling of airport catering tasks is one of the technical problems that need to be solved at present. Summary of the Invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a dynamic scheduling system for airport catering tasks based on microservices and event-driven, which can adopt a microservice architecture to trigger an event-driven prediction model with a customized structure to perform a catering prediction operation every preset time length when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various types of food on the target flight at the time of the catering prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold to ensure that the interval between two adjacent catering prediction operation execution times is long enough to leave enough time for the subsequent dynamic mobilization of ingredients and the response time for ingredient production at the ingredient supply warehouse end. In this way, with the microservice architecture as the operating body and flight delays as the event drive, dynamic scheduling of airport catering tasks is realized, while taking into account the two goals of saving limited ingredients and meeting passenger needs in the scenario of aircraft delays, thereby avoiding wasting catering resources or causing insufficient catering supply.

[0007] According to the present invention, a dynamic scheduling system for airport catering tasks based on microservices and event-driven is provided, and the system includes: The information parsing device uses a microservice architecture to parse the target flight's departure time, full passenger load, aircraft model number, and the distance from the aircraft parking space to the food supply warehouse as the corresponding configuration information for the target flight; The food capture device uses a microservice architecture to capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of various types of food. A model building device, configured to perform multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings are performed and output as an event-driven prediction model; a meal prediction device, connected to the information analysis device, the food capturing device, and the model establishment device, respectively, for triggering an event to drive the prediction model to perform a meal prediction operation once every preset time length when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various food items on the target flight at the time of the meal prediction operation execution, wherein the value of the preset time length is greater than or equal to a time length threshold; The dynamic scheduling device is connected to the meal distribution prediction device and is used to issue an emergency scheduling request for a certain type of food when the predicted consumption quantity of the food exceeds the actual quantity of the food on board and the difference between the two is greater than or equal to a set difference threshold.

[0008] According to a second aspect of the present invention, a microservices- and event-driven-based dynamic scheduling system for airport catering tasks is provided. The system includes a memory and multiple processors. The memory stores a computer program, and the computer program is configured to be executed by the multiple processors to perform the following steps: The microservice architecture is used to analyze the target flight's departure time, full passenger load, aircraft model number, and the distance from the aircraft parking space to the food supply warehouse as the corresponding configuration information for the target flight; A microservices architecture is used to capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of various types of food. Performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the result as an event-driven prediction model; When the target flight takes off later than the scheduled departure time of the day, the prediction model is triggered to execute a meal prediction operation every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food for the target flight at the time of the meal prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold; When the predicted consumption quantity of a certain type of food exceeds the actual quantity of that type of food on board and the difference between the two is greater than or equal to the set difference threshold, an emergency dispatch request for that type of food is issued.

[0009] It can be seen that the present invention has at least the following outstanding substantive features: Substantive Feature A: The microservice architecture is used to trigger an event-driven prediction model to perform a meal prediction operation every preset time length when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various foods of the target flight at the time of the meal prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold to ensure that the interval between two adjacent meal prediction operation execution times is long enough to leave enough time for the subsequent dynamic mobilization of ingredients and the response time of ingredient production at the ingredient supply warehouse. In this way, with the microservice architecture as the operating body and flight delays as the event-driven, dynamic scheduling of airport meal tasks is achieved, while meeting the needs of passengers in the scenario of flight delays. Substantive Feature B: Each meal distribution prediction operation is completed using a custom-designed event-driven prediction model. This event-driven prediction model is a feedforward neural network that has undergone multiple training cycles. The number of training cycles is positively correlated with the delay duration of the target flight the previous day, ensuring that the dynamic accuracy requirements of the event-driven prediction model are met. This customized structural design ensures the stability and effectiveness of each meal distribution prediction result of the event-driven prediction model. Substantive Feature C: Various basic data are introduced to complete each meal prediction operation. Specifically, the basic data include the meal prediction execution time, various configuration information corresponding to the target flight, and multiple food-related data corresponding to the target flight in the past several days. More specifically, the configuration information corresponding to the target flight includes the target flight's on-time departure time, the number of fully loaded passengers, the aircraft model number, and the distance from the configured aircraft parking space to the food supply warehouse. The food-related data corresponding to each day of the target flight in the past includes the target flight's delay duration, the actual number of passengers, and the consumption of various food items on that day. Crucially, the number of days selected in the past is positively correlated with the target flight's mileage. The comprehensive and full introduction of the above basic data further ensures the stability and effectiveness of each meal prediction result of the event-driven prediction model. Substantive Feature D: During each training session of the feedforward neural network, the predicted meal preparation execution time closest to the target flight's actual takeoff time on a particular day, between its actual takeoff time and its scheduled departure time, is used as the reference execution time. The known consumption quantities of each type of food item on the target flight on a particular day are used as the predicted consumption quantities of each type of food item for the target flight at the reference execution time and serve as the single output of the feedforward neural network. The reference execution time, various configuration information corresponding to the target flight, and multiple sets of food item-related data corresponding to the target flight on the previous days prior to the aforementioned day are used as the inputs of the feedforward neural network one by one to complete the training of the feedforward neural network, thereby ensuring the effectiveness of each training session of the feedforward neural network. Substantive Feature E: The specific architecture of the feedforward neural network used is as follows: the feedforward neural network has a network architecture including multiple hidden layers, a single input layer and a single output layer, the multiple hidden layers are located between the single input layer and the single output layer, and the number of hidden layers of the feedforward neural network is positively correlated with the mileage of the target flight. At the same time, an information conversion formula is selected to express the information conversion relationship between the number of hidden layers of the feedforward neural network and the mileage of the target flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which: Figure 1 The figure is a schematic diagram of the working principle of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the present invention.

[0011] Figure 2 The figure shows the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the first embodiment of the present invention.

[0012] Figure 3 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the second embodiment of the present invention.

[0013] Figure 4 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the third embodiment of the present invention.

[0014] Figure 5 This is a diagram showing the internal structure of a microservice- and event-driven-based airport catering task dynamic scheduling system according to the fourth embodiment of the present invention.

[0015] Figure 6 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the fifth embodiment of the present invention.

[0016] Figure 7 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the sixth embodiment of the present invention. DETAILED DESCRIPTION

[0017] like Figure 1 As shown, a schematic diagram of the working principle of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the present invention is given.

[0018] The specific technical process of the present invention is as follows: Technical Process 1: Design a custom event-driven prediction model to predict meal delivery every preset time interval in the event of a flight delay. Specifically, the structural customization design of the event-driven prediction model is mainly reflected in the following four aspects: Aspect 1: The event-driven prediction model is a feedforward neural network that has been trained multiple times; Aspect 2: The number of times the feedforward neural network is trained is positively correlated with the delay duration of the target flight the previous day to ensure that the dynamic accuracy requirements of the event-driven prediction model are met; Aspect 3: The specific architecture of the feedforward neural network used is as follows: the feedforward neural network has a network architecture including multiple hidden layers, a single input layer, and a single output layer, the multiple hidden layers being located between the single input layer and the single output layer, and the number of hidden layers in the feedforward neural network being positively correlated with the flight mileage of the target flight. An information conversion formula is selected to represent the information conversion relationship of the positive correlation between the number of hidden layers in the feedforward neural network and the flight mileage of the target flight; Aspect 4: During each training session of the feedforward neural network, the meal preparation prediction execution time closest to the actual takeoff time of the target flight on a certain day is used as the reference execution time. The known consumption quantities of various types of food for the target flight on a certain day are used as the predicted consumption quantities of various types of food for the target flight at the reference execution time, and are used as the single output of the feedforward neural network. The reference execution time, various configuration information corresponding to the target flight, and multiple food-related data corresponding to the target flight in the past multiple days before the said day are used as the input of the feedforward neural network one by one to complete the training of the feedforward neural network, thereby ensuring the effectiveness of each training session of the feedforward neural network. In this way, through the above customized structural design, the stability and effectiveness of each meal prediction result of the event-driven prediction model are guaranteed; Technical Process 2: In order to complete the meal prediction operation triggered every preset time period in the case of a target flight delay, various basic data are introduced; Specifically, if Figure 1 As shown, the basic data introduced include the meal prediction operation execution time, the configuration information corresponding to the target flight, and the multiple ingredient association data corresponding to the target flight in the past few days; More specifically, the configuration information corresponding to the target flight includes the target flight's on-time departure time, the number of fully loaded passengers, the aircraft model number, and the distance between the configured aircraft parking space and the food supply warehouse. The food-related data corresponding to each day of the target flight's past includes the target flight's delay duration, the actual number of passengers, and the amount of each type of food consumed on that day. Crucially, the number of days selected in the past is positively correlated with the flight mileage of the target flight; In this way, by fully introducing the above basic data, the stability and effectiveness of each meal distribution prediction result of the event-driven prediction model are further guaranteed; Technical Process 3: Utilizing the custom-designed event-driven prediction model from Technical Process 1, and based on the comprehensive and comprehensive data from Technical Process 2, this model completes meal predictions every time a predetermined delay occurs in the event of a target flight delay. Specifically, a microservice architecture is used to trigger an event-driven prediction model to perform a meal prediction operation every preset time period when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various foods on the target flight at the time of the meal prediction operation execution, such as Figure 1 As shown; The preset time length is greater than or equal to the time length threshold to ensure that the interval between two consecutive meal prediction operations is long enough to leave enough time for the subsequent dynamic mobilization of ingredients and the response time for ingredient preparation at the ingredient supply warehouse. Technical process four: Determine whether to implement emergency dispatch for a certain type of food in short supply based on the prediction results of technical process three; For example, in the prediction results of technical process three, if the predicted consumption quantity of a certain type of food exceeds the actual quantity of the food on board, and the difference between the two is greater than or equal to the set difference threshold, an emergency dispatch request for the food is issued, such as Figure 1 As shown; On the contrary, in the forecast results of Technical Process 3, if the forecast consumption quantity of a certain type of food does not exceed the actual quantity of that type of food on board, or if it does but the difference between the two is less than the set difference threshold, there is no need to issue an emergency dispatch request for any type of food; It can be seen that the present invention uses a microservice architecture as the operating body and flight delays as event-driven, intelligently predicts the different dining needs of the same passenger group under different degrees of time delay, provides key data for dynamic scheduling of airport catering tasks, and realizes dynamic scheduling of airport catering tasks, while taking into account the two goals of saving limited ingredients and meeting passenger needs in the scenario of flight delays.

[0019] The key points of the present invention are: a directional intelligent prediction mechanism for different degrees of flight delays formulated for the same flight and the same passenger group in the flight delay scenario, the introduction of a microservice architecture, the multiple customized structural designs of the event-driven prediction model, and the comprehensive and sufficient introduction of various basic data for intelligent prediction.

[0020] Below, a microservice- and event-driven airport catering task dynamic scheduling system of the present invention will be specifically described in the form of an embodiment.

[0021] First embodiment Figure 2 The figure shows the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the first embodiment of the present invention.

[0022] like Figure 2 As shown, the microservice- and event-driven airport catering task dynamic scheduling system includes the following components: The information parsing device uses a microservice architecture to parse the target flight's departure time, full passenger load, aircraft model number, and the distance from the aircraft parking space to the food supply warehouse as the corresponding configuration information for the target flight; Specifically, microservices (or microservice architecture) is a cloud-native architectural approach that includes many loosely coupled and independently deployable small components or services in a single application. These services usually have their own technology stack, including databases and data management models; communicate with each other through a combination of REST APIs, event streams, and message brokers; and are organized according to business capabilities, with service separation lines usually called bounded contexts. Specifically, microservices are characterized by easier code updates. New features or functionality can be added without having to update the entire application, and teams can use different technology stacks and programming languages for different components. Components can scale independently of each other, reducing the waste and cost associated with having to scale the entire application (because a single function might face excessive load). The food capture device uses a microservice architecture to capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of various types of food. For example, a microservice architecture is used to capture multiple sets of food-related data corresponding to a target flight over multiple days in the past. The food-related data corresponding to each day of the target flight in the past includes the delay duration of the target flight on that day, the actual number of passengers, and the consumption quantity of various types of food. The method includes: using multiple processes under the microservice architecture to respectively obtain multiple sets of food-related data corresponding to the target flight over multiple days in the past; A model building device, configured to perform multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings are performed and output as an event-driven prediction model; For example, performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the feedforward neural network as the event-driven prediction model includes: selecting a numerical simulation mode to complete the testing and simulation of a model establishment process of performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the feedforward neural network as the event-driven prediction model; a meal prediction device, connected to the information analysis device, the food capturing device, and the model establishment device, respectively, for triggering an event to drive the prediction model to perform a meal prediction operation once every preset time length when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various food items on the target flight at the time of the meal prediction operation execution, wherein the value of the preset time length is greater than or equal to a time length threshold; For example, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold, including: the scheduled departure time of the target flight every day is 12:00 noon, and if the target flight has not taken off after 12:00 noon on the same day, it is considered that the target flight has entered a delayed scenario. At this time, the event-driven prediction model is triggered to perform a meal prediction operation every 15 minutes until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution. The preset time length, i.e., 20 minutes, is greater than or equal to the time length threshold, i.e., 15 minutes. Specifically, the preset time length is greater than or equal to the time length threshold in order to ensure that the interval between two consecutive meal prediction operations is long enough to allow sufficient time for the subsequent dynamic mobilization of ingredients and the response time for ingredient production at the ingredient supply warehouse. For example, the interval between two consecutive meal prediction operations is 15 minutes. A dynamic scheduling device, connected to the meal distribution prediction device, is used to issue an emergency scheduling request for a certain type of food when the predicted consumption quantity of the food exceeds the actual quantity of the food on board and the difference between the two is greater than or equal to a set difference threshold; For example, when the predicted consumption quantity of a certain type of food exceeds the actual onboard quantity of the food and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the food includes: when the predicted consumption quantity of a beef set meal exceeds the actual onboard quantity of the beef set meal and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the beef set meal; On the contrary, when the predicted consumption quantity of each type of food does not exceed the actual onboard quantity of each type of food, or even if it does, but the difference between the two is greater than or equal to the set difference threshold, there is no need to issue an emergency dispatch request for any type of food; For example, when the predicted consumption quantity of a certain type of food exceeds the actual quantity of the food on board, and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the food may further include: setting the difference threshold to be 10 portions; if the difference between the two is less than 10 portions, it indicates that on-site coordination on the aircraft is easy, and no emergency dispatch request for the food is required; In each meal prediction operation performed by the event-driven prediction model, the event-driven prediction model is used to intelligently predict the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution based on the meal prediction operation execution time, the configuration information corresponding to the target flight, and the multiple food ingredient association data corresponding to the target flight in the past few days; For example, when the target flight is delayed, an event is triggered every 15 minutes to drive the prediction model to execute a meal prediction operation until the target flight actually takes off. This shows that there is more than one meal prediction operation execution time and the execution time is gradually increasing. For example, the meal prediction operation execution time can be 12:20, 12:40, 13:00, 13:20, and 13:40. If the target flight takes off at 13:50, there is no meal prediction operation execution time at 14:00. If the target flight takes off at 14:15, there is a meal prediction operation execution time at 14:00. The feedforward neural network is trained multiple times to obtain a feedforward neural network after the multiple trainings and output as an event-driven prediction model, including: the number of times the feedforward neural network is trained is positively correlated with the delay duration of the target flight the previous day; For example, a positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight the day before includes: if the delay duration of the target flight the day before is 15 minutes, the feedforward neural network performs training 600 times; if the delay duration of the target flight the day before is 20 minutes, the feedforward neural network performs training 700 times; if the delay duration of the target flight the day before is 25 minutes, the feedforward neural network performs training 800 times; if the delay duration of the target flight the day before is 30 minutes, the feedforward neural network performs training 900 times, and so on; In each training run of the feedforward neural network, the meal prediction execution time closest to the actual takeoff time of the target flight on a certain day is used as the reference execution time. The known consumption quantities of various types of food on the target flight on a certain day are used as the predicted consumption quantities of various types of food on the target flight at the reference execution time and serve as the single output of the feedforward neural network. The reference execution time, various configuration information corresponding to the target flight, and multiple food-related data corresponding to the target flight in the past multiple days before the said day are used as the input of the feedforward neural network one by one to complete the training of the feedforward neural network. Among them, a microservice architecture is used to capture multiple sets of food-related data corresponding to the target flight in the past. The food-related data corresponding to each day of the target flight in the past include the delay duration of the target flight on that day, the actual number of passengers, and the consumption of various types of food. The number of days selected in the past is positively correlated with the flight mileage of the target flight; For example, the positive correlation between the selected number of days in the past and the mileage of the target flight includes: the mileage of the target flight is 500 kilometers, the selected number of days in the past is 7 days, the mileage of the target flight is 600 kilometers, the selected number of days in the past is 9 days, the mileage of the target flight is 700 kilometers, the selected number of days in the past is 11 days, the mileage of the target flight is 800 kilometers, the selected number of days in the past is 13 days, the mileage of the target flight is 900 kilometers, the selected number of days in the past is 15 days, and so on.

[0023] Second embodiment Figure 3 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the second embodiment of the present invention.

[0024] like Figure 3 As shown, compared with Figure 2 The microservice- and event-driven airport catering task dynamic scheduling system also includes: An event response component, provided at the food supply warehouse and connected to the dynamic scheduling component, is configured to receive an emergency scheduling request for a certain type of food from a target flight using a microservice architecture, and determine the quantity of the certain type of food that needs to be urgently replenished for the target flight based on the difference between the predicted consumption quantity of the certain type of food and the actual quantity of the certain type of food on board; For example, using a microservice architecture to receive an emergency dispatch request for a certain type of food from a target flight, and determining the quantity of the certain type of food that needs to be urgently replenished for the target flight based on a difference between a predicted consumption quantity of the certain type of food and an actual quantity of the certain type of food on board, includes: using a first process in the microservice architecture to receive an emergency dispatch request for the certain type of food from a target flight, and using a second process in the microservice architecture to determine the quantity of the certain type of food that needs to be urgently replenished for the target flight based on a difference between the predicted consumption quantity of the certain type of food and the actual quantity of the certain type of food on board; Among them, a microservice architecture is adopted to receive an emergency dispatch request for a certain type of food from a target flight, and determine the number of products of a certain type of food that need to be urgently replenished for the target flight based on the difference between the predicted consumption quantity of the certain type of food and the actual quantity of the certain type of food on board. The method includes: the emergency dispatch request for a certain type of food from the target flight includes the predicted consumption quantity of the certain type of food, the actual quantity of the certain type of food on board, and the flight number of the target flight.

[0025] Third embodiment Figure 4 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the third embodiment of the present invention.

[0026] like Figure 4 As shown, compared with Figure 3 The microservice- and event-driven airport catering task dynamic scheduling system also includes: a response execution device, provided at the food supply warehouse and connected to the event response device, configured to set the quantity of a certain type of food that needs to be urgently supplied to the target flight as the target product quantity, and to initiate the production of the certain type of food when the production time of the target product quantity of the certain type of food is less than a preset time length; For example, the quantity of a certain type of food that needs to be urgently resupplied on a target flight is used as the target product quantity. When the preparation time of the target product quantity of the certain type of food is less than the preset time length, the preparation of the certain type of food is initiated. This includes: when the difference between the predicted consumption quantity of beef combo and the actual number of beef combo on board is 15 pieces, that is, when the quantity of beef combo that needs to be urgently resupplied on the target flight is determined to be 15 pieces, and because the preparation time of 15 pieces of beef combo is 18 minutes, which is less than the preset time length of 20 minutes, the preparation of the beef combo can be initiated. On the other hand, if the preparation time for a 15-piece beef meal is 28 minutes, which is longer than the preset time of 20 minutes, there is no need to start preparing the beef meal. This is because it is not yet finished and the next meal prediction operation will start again. The passenger's demand for each food item may change. At this time, it is likely meaningless to continue preparing the beef meal. The response execution device is provided at the food supply warehouse end and connected to the event response device, and is used to set the quantity of a certain type of food that needs to be urgently supplied to the target flight as the target product quantity, and when the production time of the certain type of food of the target product quantity is less than the preset time length, start the production of the certain type of food, including: the response execution device is connected to the microservice architecture network of the event response device through the microservice architecture; Among them, the response execution device is also used to temporarily suspend the start of the production of a certain type of food when the production time of a certain type of food with a target product quantity is greater than or equal to a preset time length to wait for the intelligent prediction result of the next meal prediction operation execution time.

[0027] Fourth embodiment Figure 5 This is a diagram showing the internal structure of a microservice- and event-driven-based airport catering task dynamic scheduling system according to the fourth embodiment of the present invention.

[0028] like Figure 5 As shown, compared with Figure 2 The microservice- and event-driven airport catering task dynamic scheduling system also includes: The timing server component is connected to the meal prediction device, the information analysis device, the food material acquisition device, and the model establishment device, respectively, and is used to provide the meal prediction device, the information analysis device, the food material acquisition device, and the model establishment device with the timing services required by each of them; Specifically, the timing server component is connected to the meal prediction device, the information analysis device, the food capture device and the model establishment device, respectively, and is used to provide the meal prediction device, the information analysis device, the food capture device and the model establishment device with the timing services they need respectively, including: the timing server component uses a built-in quartz oscillation component to provide a reference clock pulse, which is used to provide the meal prediction device, the information analysis device, the food capture device and the model establishment device with the timing services they need respectively.

[0029] Fifth embodiment Figure 6 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the fifth embodiment of the present invention.

[0030] like Figure 6 As shown, compared with Figure 2 The microservice- and event-driven airport catering task dynamic scheduling system also includes: A model storage device, connected to the model establishment device, for receiving and storing the event-driven prediction model; For example, a TF memory chip, an MMC memory chip or a FLASH memory chip may be selected to implement the model storage device for receiving and storing the event-driven prediction model; Among them, the model storage device is connected to the model establishment device and is used to receive and store the event-driven prediction model, including: the model storage device completes the model storage of the event-driven prediction model by storing various model parameters of the event-driven prediction model.

[0031] Next, various embodiments of the present invention will be further described.

[0032] In each of the above embodiments, optionally, in the microservice- and event-driven-based airport catering task dynamic scheduling system: The positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight on the previous day includes: using a numerical mapping function to represent the numerical mapping relationship of the positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight on the previous day; For example, the MATLAB toolbox may be used to complete the testing and simulation of a numerical mapping process that uses a numerical mapping function to represent a numerical mapping relationship that is positively correlated between the number of times a feedforward neural network performs training and the delay duration of a target flight the previous day. The method of using a numerical mapping function to represent a numerical mapping relationship in which the number of times a feedforward neural network performs training is positively correlated with the delay duration of the target flight on the previous day comprises: in the numerical mapping function, using the delay duration of the target flight on the previous day as an input value of the numerical mapping function, and using the number of times the feedforward neural network performs training that is positively correlated with the delay duration of the target flight on the previous day as an output value of the numerical mapping function; The microservice architecture is used to capture multiple sets of food-related data corresponding to the target flight over the past several days. The food-related data corresponding to each day of the target flight include the target flight's delay duration, the actual number of passengers, and the consumption quantity of various food items. The consumption quantity of various food items on the target flight on that day includes the number of beef meal sets consumed, the number of chicken meal sets consumed, the number of bottles of mineral water consumed, and the number of snacks consumed by the target flight on that day. Among them, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation once every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of various types of food on the target flight at the time when the meal prediction operation is executed, and the value of the preset time length is greater than or equal to the time length threshold. The method includes: adopting a microservice architecture to, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation once every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of various types of food on the target flight at the time when the meal prediction operation is executed, and the value of the preset time length is greater than or equal to the time length threshold; And wherein, when the predicted consumption quantity of a certain type of food exceeds the actual quantity of this type of food on board and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for this type of food includes: using a microservice architecture to issue an emergency dispatch request for this type of food when the predicted consumption quantity of a certain type of food exceeds the actual quantity of this type of food on board and the difference between the two is greater than or equal to a set difference threshold.

[0033] And in each of the above embodiments, optionally, in the microservice- and event-driven-based airport catering task dynamic scheduling system: In each meal prediction operation executed by the event-driven prediction model, the event-driven prediction model is used to intelligently predict the predicted consumption quantity of each type of food on the target flight at the time when the meal prediction operation is executed based on the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days. This includes: in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model and obtain the predicted consumption quantity of each type of food on the target flight at the time when the meal prediction operation is executed, as output by the event-driven prediction model; For example, a process within a microservices architecture can be used to synchronously input the meal prediction execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight over the past several days into an event-driven prediction model. Another process within the microservices architecture can then be used to run the event-driven prediction model to obtain the predicted consumption quantity of each food item for the target flight at the meal prediction execution time, as output by the event-driven prediction model. In each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model and obtain the predicted consumption quantity of various food items of the target flight at the meal prediction operation execution time output by the event-driven prediction model, including: using a synchronous control device to synchronously input the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model; wherein, in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model, and obtain the predicted consumption quantity of various food items of the target flight at the meal prediction operation execution time output by the event-driven prediction model, further comprising: before synchronously inputting the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model using a synchronous control device, performing binary value conversion processing on the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days; wherein, in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model, and obtaining the predicted consumption quantity of each food item of the target flight at the meal prediction operation execution time output by the event-driven prediction model further includes: the obtained predicted consumption quantity of each food item of the target flight at the meal prediction operation execution time is represented in the form of a binary value; Wherein, before synchronously inputting the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model using the synchronous control device, performing binary value conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, includes: selecting a value conversion device for performing binary value conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, before synchronously inputting the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, using the synchronous control device; And wherein, selecting to use a numerical conversion device for performing binary numerical conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days before synchronously inputting the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model using the synchronous control device includes: the numerical conversion device is connected to the synchronous control device and shares the same serial configuration bus; For example, the numerical value conversion device is connected to the synchronous control device and shares a same serial configuration bus, which includes: the shared same serial configuration bus may be an IIC configuration bus.

[0034] Sixth embodiment Figure 7 This is a diagram showing the internal structure of a dynamic scheduling system for airport catering tasks based on microservices and event-driven according to the sixth embodiment of the present invention.

[0035] like Figure 7 As shown, the system for automatically generating and publishing all-media content includes a memory and multiple processors, wherein the memory stores a computer program, and the computer program is configured to be executed by the multiple processors to complete the following steps: Step 701: Using the microservice architecture, the target flight's departure time, fully loaded passenger number, aircraft model number, and the distance between the aircraft parking space and the food supply warehouse are parsed to obtain configuration information corresponding to the target flight. Specifically, microservices (or microservice architecture) is a cloud-native architectural approach that includes many loosely coupled and independently deployable small components or services in a single application. These services usually have their own technology stack, including databases and data management models; communicate with each other through a combination of REST APIs, event streams, and message brokers; and are organized according to business capabilities, with service separation lines usually called bounded contexts. Specifically, microservices are characterized by easier code updates. New features or functionality can be added without having to update the entire application, and teams can use different technology stacks and programming languages for different components. Components can scale independently of each other, reducing the waste and cost associated with having to scale the entire application (because a single function might face excessive load). Step 702: Using a microservice architecture, capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of each type of food. For example, a microservice architecture is used to capture multiple sets of food-related data corresponding to a target flight over multiple days in the past. The food-related data corresponding to each day of the target flight in the past includes the delay duration of the target flight on that day, the actual number of passengers, and the consumption quantity of various types of food. The method includes: using multiple processes under the microservice architecture to respectively obtain multiple sets of food-related data corresponding to the target flight over multiple days in the past; Step 703: Perform multiple training on the feedforward neural network to obtain a feedforward neural network after the multiple trainings and output it as an event-driven prediction model; For example, performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the feedforward neural network as the event-driven prediction model includes: selecting a numerical simulation mode to complete the testing and simulation of a model establishment process of performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the feedforward neural network as the event-driven prediction model; Step 704: When the target flight departs later than the scheduled departure time of the day, trigger an event every predetermined time period to drive the prediction model to execute a meal prediction operation, until the target flight actually takes off, to obtain the predicted consumption quantity of each food item on the target flight at the time of the meal prediction operation execution. The predetermined time period is greater than or equal to the time period threshold. For example, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold, including: the scheduled departure time of the target flight every day is 12:00 noon, and if the target flight has not taken off after 12:00 noon on the same day, it is considered that the target flight has entered a delayed scenario. At this time, the event-driven prediction model is triggered to perform a meal prediction operation every 15 minutes until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution. The preset time length, i.e., 20 minutes, is greater than or equal to the time length threshold, i.e., 15 minutes. Specifically, the preset time length is greater than or equal to the time length threshold in order to ensure that the interval between two consecutive meal prediction operations is long enough to allow sufficient time for the subsequent dynamic mobilization of ingredients and the response time for ingredient production at the ingredient supply warehouse. For example, the interval between two consecutive meal prediction operations is 15 minutes. Step 705: When the predicted consumption quantity of a certain type of food exceeds the actual quantity of the food on board and the difference between the two is greater than or equal to a set difference threshold, an emergency dispatch request for the food is issued; For example, when the predicted consumption quantity of a certain type of food exceeds the actual onboard quantity of the food and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the food includes: when the predicted consumption quantity of a beef set meal exceeds the actual onboard quantity of the beef set meal and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the beef set meal; On the contrary, when the predicted consumption quantity of each type of food does not exceed the actual onboard quantity of each type of food, or even if it does, but the difference between the two is greater than or equal to the set difference threshold, there is no need to issue an emergency dispatch request for any type of food; For example, when the predicted consumption quantity of a certain type of food exceeds the actual quantity of the food on board, and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for the food may further include: setting the difference threshold to be 10 portions; if the difference between the two is less than 10 portions, it indicates that on-site coordination on the aircraft is easy, and no emergency dispatch request for the food is required; In each meal prediction operation performed by the event-driven prediction model, the event-driven prediction model is used to intelligently predict the predicted consumption quantity of each type of food on the target flight at the time of the meal prediction operation execution based on the meal prediction operation execution time, the configuration information corresponding to the target flight, and the multiple food ingredient association data corresponding to the target flight in the past few days; For example, when the target flight is delayed, an event is triggered every 15 minutes to drive the prediction model to execute a meal prediction operation until the target flight actually takes off. This shows that there is more than one meal prediction operation execution time and the execution time is gradually increasing. For example, the meal prediction operation execution time can be 12:20, 12:40, 13:00, 13:20, and 13:40. If the target flight takes off at 13:50, there is no meal prediction operation execution time at 14:00. If the target flight takes off at 14:15, there is a meal prediction operation execution time at 14:00. The feedforward neural network is trained multiple times to obtain a feedforward neural network after the multiple trainings and output as an event-driven prediction model, including: the number of times the feedforward neural network is trained is positively correlated with the delay duration of the target flight the previous day; For example, a positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight the day before includes: if the delay duration of the target flight the day before is 15 minutes, the feedforward neural network performs training 600 times; if the delay duration of the target flight the day before is 20 minutes, the feedforward neural network performs training 700 times; if the delay duration of the target flight the day before is 25 minutes, the feedforward neural network performs training 800 times; if the delay duration of the target flight the day before is 30 minutes, the feedforward neural network performs training 900 times, and so on; In each training run of the feedforward neural network, the meal prediction execution time closest to the actual takeoff time of the target flight on a certain day is used as the reference execution time. The known consumption quantities of various types of food on the target flight on a certain day are used as the predicted consumption quantities of various types of food on the target flight at the reference execution time and serve as the single output of the feedforward neural network. The reference execution time, various configuration information corresponding to the target flight, and multiple food-related data corresponding to the target flight in the past multiple days before the said day are used as the input of the feedforward neural network one by one to complete the training of the feedforward neural network. Among them, a microservice architecture is used to capture multiple sets of food-related data corresponding to the target flight in the past. The food-related data corresponding to each day of the target flight in the past include the delay duration of the target flight on that day, the actual number of passengers, and the consumption of various types of food. The number of days selected in the past is positively correlated with the flight mileage of the target flight; For example, the positive correlation between the selected number of days in the past and the mileage of the target flight includes: the mileage of the target flight is 500 kilometers, the selected number of days in the past is 7 days, the mileage of the target flight is 600 kilometers, the selected number of days in the past is 9 days, the mileage of the target flight is 700 kilometers, the selected number of days in the past is 11 days, the mileage of the target flight is 800 kilometers, the selected number of days in the past is 13 days, the mileage of the target flight is 900 kilometers, the selected number of days in the past is 15 days, and so on.

[0036] In addition, in a microservice- and event-driven-based airport catering task dynamic scheduling system according to the present invention: The number of times the feedforward neural network performs training is positively correlated with the delay duration of the target flight on the previous day, including: the feedforward neural network has a network architecture including multiple hidden layers, a single input layer, and a single output layer, and the number of hidden layers of the feedforward neural network is positively correlated with the flight mileage of the target flight; For example, the feedforward neural network has a network architecture including a plurality of hidden layers, a single input layer, and a single output layer, and the number of hidden layers of the feedforward neural network is positively correlated with the flight mileage of the target flight, including: using an information conversion formula to express the information conversion relationship of the positive correlation between the number of hidden layers of the feedforward neural network and the flight mileage of the target flight; Specifically, in the information conversion formula, the flight mileage of the target flight is the input information of the information conversion formula, and the number of hidden layers of the feedforward neural network that is positively correlated with the flight mileage of the target flight is the output information of the information conversion formula; And wherein the feedforward neural network has a network architecture including multiple hidden layers, a single input layer and a single output layer, and the number of hidden layers of the feedforward neural network is positively correlated with the mileage of the target flight, further comprising: in the feedforward neural network, the multiple hidden layers are located between the single input layer and the single output layer.

[0037] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0038] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the relevant technology can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device to execute the methods described in each embodiment or certain parts of the embodiments.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A dynamic scheduling system for airport catering tasks based on microservices and event-driven, characterized by: The system comprises: The information parsing device uses a microservice architecture to parse the target flight's departure time, full passenger load, aircraft model number, and the distance from the aircraft parking space to the food supply warehouse as the corresponding configuration information for the target flight; The food capture device uses a microservice architecture to capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of various types of food. A model building device, configured to perform multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings are performed and output as an event-driven prediction model; a meal prediction device, connected to the information analysis device, the food capturing device, and the model establishment device, respectively, for triggering an event to drive the prediction model to perform a meal prediction operation once every preset time length when the target flight takes off later than the scheduled departure time of the day until the target flight actually takes off, so as to obtain the predicted consumption quantity of various food items on the target flight at the time of the meal prediction operation execution, wherein the value of the preset time length is greater than or equal to a time length threshold; The dynamic scheduling device is connected to the meal distribution prediction device and is used to issue an emergency scheduling request for a certain type of food when the predicted consumption quantity of the food exceeds the actual quantity of the food on board and the difference between the two is greater than or equal to a set difference threshold.

2. The microservices- and event-driven airport catering task dynamic scheduling system according to claim 1, characterized in that: In each meal prediction operation executed by the event-driven prediction model, the event-driven prediction model is used to intelligently predict the predicted consumption quantity of each food item on the target flight at the time of the meal prediction operation execution, the configuration information corresponding to the target flight, and the associated data of multiple ingredients corresponding to the target flight over the past few days; The feedforward neural network is trained multiple times to obtain a feedforward neural network after the multiple trainings and output as an event-driven prediction model, including: the number of times the feedforward neural network is trained is positively correlated with the delay duration of the target flight the previous day.

3. The microservice-based and event-driven airport catering task dynamic scheduling system according to claim 2, characterized in that: In each training run of the feedforward neural network, the meal preparation prediction execution time closest to the actual takeoff time of the target flight on a certain day between the actual takeoff time and the scheduled takeoff time is used as the reference execution time. The known consumption quantities of various types of food for the target flight on a certain day are used as the predicted consumption quantities of various types of food for the target flight at the reference execution time and serve as the single output of the feedforward neural network. The reference execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days before the said day are used as the inputs of the feedforward neural network one by one to complete the training of the feedforward neural network. Among them, a microservice architecture is used to capture multiple food-related data corresponding to the target flight in the past few days. The food-related data corresponding to each day of the target flight in the past are the delay duration of the target flight on that day, the actual number of passengers and the consumption of various types of food, including: the number of days selected in the past few days is positively correlated with the flight mileage of the target flight.

4. The airport catering task dynamic scheduling system based on microservices and event-driven as claimed in claim 3 is characterized in that: The system further comprises: An event response component, provided at the food supply warehouse and connected to the dynamic scheduling component, is configured to receive an emergency scheduling request for a certain type of food from a target flight using a microservice architecture, and determine the quantity of the certain type of food that needs to be urgently replenished for the target flight based on the difference between the predicted consumption quantity of the certain type of food and the actual quantity of the certain type of food on board; Among them, a microservice architecture is adopted to receive an emergency dispatch request for a certain type of food from a target flight, and determine the number of products of a certain type of food that need to be urgently replenished for the target flight based on the difference between the predicted consumption quantity of the certain type of food and the actual quantity of the certain type of food on board. The method includes: the emergency dispatch request for a certain type of food from the target flight includes the predicted consumption quantity of the certain type of food, the actual quantity of the certain type of food on board, and the flight number of the target flight.

5. The airport catering task dynamic scheduling system based on microservices and event-driven as claimed in claim 4 is characterized in that: The system further comprises: a response execution device, provided at the food supply warehouse and connected to the event response device, configured to set the quantity of a certain type of food that needs to be urgently supplied to the target flight as the target product quantity, and to initiate the production of the certain type of food when the production time of the target product quantity of the certain type of food is less than a preset time length; The response execution device is provided at the food supply warehouse end and connected to the event response device, and is used to set the quantity of a certain type of food that needs to be urgently supplied to the target flight as the target product quantity, and when the production time of the certain type of food of the target product quantity is less than the preset time length, start the production of the certain type of food, including: the response execution device is connected to the microservice architecture network of the event response device through the microservice architecture; Among them, the response execution device is also used to temporarily suspend the start of the production of a certain type of food when the production time of a certain type of food with a target product quantity is greater than or equal to a preset time length to wait for the intelligent prediction result of the next meal prediction operation execution time.

6. The airport catering task dynamic scheduling system based on microservices and event-driven as claimed in claim 3 is characterized in that: The system further comprises: The timing server component is connected to the meal matching prediction device, the information analysis device, the food material capture device and the model establishment device respectively, and is used to provide the meal matching prediction device, the information analysis device, the food material capture device and the model establishment device with the timing services they need respectively.

7. The airport catering task dynamic scheduling system based on microservices and event-driven as claimed in claim 3 is characterized in that: The system further comprises: A model storage device, connected to the model establishment device, for receiving and storing the event-driven prediction model; Among them, the model storage device is connected to the model establishment device and is used to receive and store the event-driven prediction model, including: the model storage device completes the model storage of the event-driven prediction model by storing various model parameters of the event-driven prediction model.

8. The microservice-based and event-driven airport catering task dynamic scheduling system according to any one of claims 3 to 7, characterized in that: The positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight on the previous day includes: using a numerical mapping function to represent the numerical mapping relationship of the positive correlation between the number of times the feedforward neural network performs training and the delay duration of the target flight on the previous day; The method of using a numerical mapping function to represent a numerical mapping relationship in which the number of times a feedforward neural network performs training is positively correlated with the delay duration of the target flight on the previous day comprises: in the numerical mapping function, using the delay duration of the target flight on the previous day as an input value of the numerical mapping function, and using the number of times the feedforward neural network performs training that is positively correlated with the delay duration of the target flight on the previous day as an output value of the numerical mapping function; The microservice architecture is used to capture multiple sets of food-related data corresponding to the target flight over the past several days. The food-related data corresponding to each day of the target flight include the target flight's delay duration, the actual number of passengers, and the consumption quantity of various food items. The consumption quantity of various food items on the target flight on that day includes the number of beef meal sets consumed, the number of chicken meal sets consumed, the number of bottles of mineral water consumed, and the number of snacks consumed by the target flight on that day. Among them, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation once every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of various types of food on the target flight at the time when the meal prediction operation is executed, and the value of the preset time length is greater than or equal to the time length threshold. The method includes: adopting a microservice architecture to, when the target flight takes off later than the scheduled departure time of the day, the event-driven prediction model is triggered to perform a meal prediction operation once every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of various types of food on the target flight at the time when the meal prediction operation is executed, and the value of the preset time length is greater than or equal to the time length threshold; Among them, when the predicted consumption quantity of a certain type of food exceeds the actual quantity of this type of food on board and the difference between the two is greater than or equal to a set difference threshold, issuing an emergency dispatch request for this type of food includes: using a microservice architecture to issue an emergency dispatch request for this type of food when the predicted consumption quantity of a certain type of food exceeds the actual quantity of this type of food on board and the difference between the two is greater than or equal to a set difference threshold.

9. The microservice-based and event-driven airport catering task dynamic scheduling system according to any one of claims 3 to 7, characterized in that: In each meal prediction operation executed by the event-driven prediction model, the event-driven prediction model is used to intelligently predict the predicted consumption quantity of each type of food on the target flight at the time when the meal prediction operation is executed based on the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days. This includes: in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model and obtain the predicted consumption quantity of each type of food on the target flight at the time when the meal prediction operation is executed, as output by the event-driven prediction model; In each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model and obtain the predicted consumption quantity of various food items of the target flight at the meal prediction operation execution time output by the event-driven prediction model, including: using a synchronous control device to synchronously input the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model; wherein, in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model, and obtain the predicted consumption quantity of various food items of the target flight at the meal prediction operation execution time output by the event-driven prediction model, further comprising: before synchronously inputting the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model using a synchronous control device, performing binary value conversion processing on the meal prediction operation execution time, various configuration information corresponding to the target flight, and a plurality of food-related data corresponding to the target flight in the past multiple days; wherein, in each meal prediction operation executed by the event-driven prediction model, the meal prediction operation execution time, various configuration information corresponding to the target flight, and multiple food ingredient association data corresponding to the target flight in the past multiple days are synchronously input into the event-driven prediction model to run the event-driven prediction model, and obtaining the predicted consumption quantity of each food item of the target flight at the meal prediction operation execution time output by the event-driven prediction model further includes: the obtained predicted consumption quantity of each food item of the target flight at the meal prediction operation execution time is represented in the form of a binary value; Wherein, before synchronously inputting the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days into the event-driven prediction model using the synchronous control device, performing binary value conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, includes: selecting a value conversion device for performing binary value conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, before synchronously inputting the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days, respectively, using the synchronous control device; Among them, selecting to use a numerical conversion device for performing binary numerical conversion processing on the meal prediction operation execution time, the various configuration information corresponding to the target flight, and the multiple food-related data corresponding to the target flight in the past multiple days before synchronously inputting them into the event-driven prediction model using a synchronous control device includes: a scheduling system, the system including a memory and a plurality of processors, the memory storing a computer program, the computer program being configured to be executed by the plurality of processors to complete the following steps: The microservice architecture is used to analyze the target flight's departure time, full passenger load, aircraft model number, and the distance from the aircraft parking space to the food supply warehouse as the corresponding configuration information for the target flight; A microservices architecture is used to capture multiple sets of food-related data corresponding to the target flight over multiple days. The food-related data corresponding to each day of the target flight includes the target flight's delay duration, the actual number of passengers, and the consumption of various types of food. Performing multiple training on the feedforward neural network to obtain the feedforward neural network after the multiple trainings and outputting the result as an event-driven prediction model; When the target flight takes off later than the scheduled departure time of the day, the prediction model is triggered to execute a meal prediction operation every preset time length until the target flight actually takes off, so as to obtain the predicted consumption quantity of each type of food for the target flight at the time of the meal prediction operation execution. The value of the preset time length is greater than or equal to the time length threshold; When the predicted consumption quantity of a certain type of food exceeds the actual quantity of that type of food on board and the difference between the two is greater than or equal to the set difference threshold, an emergency dispatch request for that type of food is issued.

Images