Micro-service quality traceability system for aviation catering

Abstract

The invention relates to a micro-service quality traceability system for aviation catering, and relates to the field of data processing specially suitable for administrative, commercial, financial, management, supervision or prediction purposes, the system comprises a network learning device used for obtaining an AI quality traceability model; and the quality traceability device is used for intelligently predicting whether a catering quality abnormal event exists in a future flight task of the set flight or not by adopting an AI quality traceability model based on various catering associated data of the set flight and various configuration information of the catering supplier, and carrying out traceability on a responsible party. According to the invention, in order to solve the technical problem that the catering quality of the future flight task of the flight is difficult to control in the prior art, the catering quality of the future flight task of the flight can be controlled on the basis of introducing a micro-service architecture, customizing an AI quality traceability model of a structural design and pointedly selecting various basic information; and the prediction of the catering quality abnormal event of the future flight task of any flight and the traceability of the responsible party are completed, so that the technical problems are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing specifically applicable to administrative, commercial, financial, management, supervision or prediction purposes, and particularly to a microservice-based quality traceability system for airline catering. Background Art

[0002] When providing airline catering services for each flight at the airport, in order to balance catering efficiency, passenger needs and save food ingredients, the flight will provide a limited variety of meal packages for passengers to choose from, and will also arrange specialized catering suppliers to provide production and transportation services for various meal packages for the flight. Flight staff will perform handover and loading operations for various meal packages. Thus, it can be seen that when each flight executes its daily flight mission, the actual various meal packages provided will go through the entire process of airline catering, including four events: production, transportation, handover and loading. There is a probability of abnormal events leading to delays in the final meal loading during each event of this entire airline catering process, thus affecting the overall operation of the flight.

[0003] Exemplarily, Chinese Patent Publication No. CN110641891A discloses an automatic airline meal catering system, which includes: a three-dimensional warehouse for classifying and storing boxes containing different meal packages or tableware; a meal catering conveying device for conveying the boxes and taking the meal packages or tableware in the boxes to the meal catering position; and a box recycling device for recycling the empty boxes after meal catering. The meal catering conveying device includes a first conveying line and a second conveying line arranged in parallel, and there are multiple branch conveying lines perpendicular to the first conveying line between the first conveying line and the second conveying line. A meal package picking and placing mechanism for picking and placing the meal packages or tableware onto the second conveying line is provided at one end of the branch conveying line close to the second conveying line. The box recycling device is located below the meal catering conveying device for recycling the empty boxes on the branch conveying lines. The present invention realizes the automatic loading of various foods through mechanical cooperation, improving the meal catering efficiency and accuracy.

[0004] Exemplarily, Chinese Patent Publication No. CN104865923A discloses an intelligent management system for aircraft meal trucks. The system includes a data acquisition terminal, a wired / wireless transmission network, a data receiving terminal, and a monitoring center; the data acquisition terminal and the data receiving terminal are connected through the wired / wireless transmission network; the data receiving terminal and the monitoring center are connected through a wired / wireless network. The effect of the intelligent management system for aircraft meal trucks provided by the present invention is that by effectively dispatching aircraft meal trucks, it can save manpower and material resources, improve the working efficiency of aircraft meal trucks, strengthen the monitoring and management of aircraft meal trucks at the airport, accurately count the vehicle operation time, and charge accurately according to the operation time, thereby improving the overall operation efficiency of the airport.

[0005] As can be seen, the various technical solutions in the above prior art are only limited to the conveying mechanical structure or network configuration structure of airline catering, which are used to improve the speed and accuracy of airline catering. However, it is impossible to trace the responsible party for the abnormal events of the catering quality of each flight's airline catering, let alone whether there are abnormal events in the catering quality of the airline catering for each unexecuted flight mission and trace the responsible party for the abnormal events of the catering quality, resulting in the flight management party being unable to obtain relevant quality prediction information for early processing and response, making it difficult to avoid and hold accountable for the abnormal events of the catering quality, and seriously reducing the catering quality and the operating efficiency of flights and even airports. Summary of the Invention

[0006] To solve the technical problems in the prior art, the present invention provides a microservice-based quality traceability system for airline catering, which can, on the basis of introducing a microservice architecture, a customized AI quality traceability model, and various selected basic information, for the entire process of airline catering including production, transportation, handover, and loading of various sets of meals actually provided for a set flight's daily flight mission, use the AI quality traceability model according to the catering supplier information of the set flight, the feedback data of the past catering loading of the set flight, and the catering-related data of the unexecuted daily flight mission of the set flight, to intelligently predict whether there will be abnormal events of loading delays and the responsible party number for the abnormal events of loading delays in the catering for the unexecuted daily flight mission of the set flight, thereby providing more valuable reference information for the early response and allocation of abnormal events of airline catering, maintaining the quality of airline catering, and ensuring the operating efficiency of flights and even airports.

[0007] According to the present invention, there is provided a microservice-based quality traceability system for airline catering, the system comprising: A task parsing device, configured to parse, using a microservice architecture, the respective quantities of each set of meals required for the unexecuted daily flight mission of the set flight; A configuration acquisition device, configured to acquire, using a microservice architecture, the transportation mileage, supply qualification acquisition duration, latest qualified inspection report acquisition duration, number of employees, production workshop floor area, maximum catering steaming temperature, and maximum catering steaming duration of the catering supplier providing catering services for the set flight, as the respective configuration information of the catering supplier providing catering services for the set flight; A network learning device, configured to perform each learning action on a feedforward neural network to obtain the feedforward neural network after performing each learning action and output it as an AI quality traceability model, the number of learning actions being positively correlated with the maximum passenger capacity of the set flight; The quality traceability device is respectively connected to the task parsing device, the configuration acquisition device, and the network learning device, and is used to intelligently predict, based on the AI quality traceability model, whether there are abnormal events of flight delays in the various meal packages required for the flight task of the day that has not been executed by the set flight, and the abnormal event identification and the responsible party number causing the flight delay abnormal event, according to the multiple meal loading feedback data corresponding to the flight tasks of the set flight in the past multiple days, the respective meal quantities corresponding to the various meal packages required for the flight task of the day that has not been executed by the set flight, and the respective configuration information of the meal suppliers providing meal services for the set flight.

[0008] It can be seen that the present invention has at least the following multiple prominent substantial features: Substantial feature A: For the entire process of airline meal service, which includes four events: production, transportation, handover, and loading, of the various meal packages actually provided for each flight task of the set flight, the AI quality traceability model is used to intelligently predict whether there will be abnormal events of flight delays in the meals for the flight task of the day that has not been executed by the set flight and the responsible party number causing the flight delay abnormal event, according to the meal supplier information of the set flight, the past meal loading feedback data of the set flight, and the meal-related data of the flight task of the day that has not been executed by the set flight. This provides more valuable reference information for the early response and allocation of abnormal events in airline meal service. Substantial feature B: To synchronously and intelligently predict whether there will be abnormal events of flight delays in the meals for the flight task of the day of the set flight and the responsible party number causing the flight delay abnormal event, an AI quality traceability model with a customized structure design is introduced. The AI quality traceability model is a feedforward neural network after each learning action is completed, and the number of learning actions performed by the feedforward neural network is positively correlated with the maximum passenger capacity of the set flight. Thus, AI quality traceability models with different customized structures are designed for different flights, ensuring the reliability and stability of the intelligent prediction results. Substantive Feature C: For the synchronous intelligent prediction of whether there will be abnormal events of meal loading delays and the responsible party numbers leading to such abnormal events in the meal distribution for the flight mission scheduled for the current day, various basic information has been specifically selected, including multiple meal loading feedback data corresponding to the flight missions of the scheduled flight in the past several days, the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day, and the configuration information of each meal provider that provides meal distribution services for the scheduled flight. Specifically, the single meal loading feedback data corresponding to each day's flight mission of the scheduled flight is the quantity of meal distribution for various meal packages actually provided when the scheduled flight executes the flight mission on that day, the duration consumed for the production of various meal packages actually provided, the duration consumed for the transportation of various meal packages actually provided, the duration consumed for the handover of various meal packages actually provided, and the duration consumed for the loading of various meal packages actually provided. The configuration information of each meal provider that provides meal distribution services for the scheduled flight includes the transportation mileage of the meal provider that provides meal distribution services for the scheduled flight, the duration for obtaining supply qualifications, the duration for obtaining the latest qualified inspection report, the number of employees, the floor area of the production workshop, the maximum temperature for meal steaming, and the longest duration for meal steaming. The comprehensive and sufficient selection of the above-mentioned basic information further ensures the reliability and stability of the intelligent prediction results; Substantive Feature D: The microservice architecture is adopted to analyze the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day. Specifically, the first process under the microservice architecture analyzes the proportion of the quantities of meal distribution for various meal packages in the flight missions of the scheduled flight in the past several days, the second process under the microservice architecture analyzes the number of passengers in the flight mission of the scheduled flight that has not been executed on the current day, and the third process under the microservice architecture uses the average value of the proportion of the quantities of meal distribution for various meal packages in the flight missions of the scheduled flight in the past several days as the proportion of the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day. Based on the proportion of the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day and the number of passengers in the flight mission of the scheduled flight that has not been executed on the current day, the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day are obtained, thereby completing the effective calculation of the quantities of each meal type corresponding to various meal packages required for the flight mission of the scheduled flight that has not been executed on the current day; Substantive Feature E: In each learning action performed on the feedforward neural network, the anomaly event identifier indicating whether there is an abnormal event of loading delay for various packages actually provided in the flight tasks executed on a certain day in the past for the set flight, and the responsible party number causing the abnormal event of loading delay are used as two input contents of the feedforward neural network. The multiple pieces of meal loading feedback data corresponding to the flight tasks on multiple days before a certain day in the past for the set flight, the quantities of various meals corresponding to the flight tasks actually provided on a certain day in the past for the set flight, and the various configuration information of the meal suppliers providing meal services for the set flight are used as multiple input contents of the feedforward neural network, thus completing this learning action and ensuring the learning effect of each learning action of the feedforward neural network. Brief Description of the Drawings

[0009] The embodiments of the present invention will be described below in conjunction with the drawings, where: Figure 1 It is a schematic diagram of the working scenario of the microservice-based quality traceability system for airline catering according to the present invention.

[0010] Figure 2 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown in the first embodiment according to the present invention.

[0011] Figure 3 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown in the second embodiment according to the present invention.

[0012] Figure 4 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown in the third embodiment according to the present invention.

[0013] Figure 5 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown in the fourth embodiment according to the present invention.

[0014] Figure 6 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown in the fifth embodiment according to the present invention. Detailed Embodiments

[0015] As Figure 1 shown, a schematic diagram of the working scenario of a microservice-based quality traceability system for airline catering shown according to the present invention is given.

[0016] The specific technical process of the present invention is as follows: Technical Process 1: To perform synchronous intelligent prediction on whether there will be abnormal events of loading delays in the catering for the flight tasks scheduled on the day of a flight and the responsible party numbers causing the abnormal events of loading delays, an AI quality traceability model with a customized structure design is introduced; Specifically, the customized structure design of the AI quality traceability model is mainly manifested in the following aspects: First: The AI quality traceability model is a feedforward neural network after each learning action is completed; Second: The number of learning actions performed by the feedforward neural network used is positively correlated with the maximum passenger capacity of the scheduled flight, so as to design AI quality traceability models with different customized structures for different flights; Exemplarily, when the aircraft type used for the scheduled flight is Boeing 737 MAX9 and the corresponding maximum passenger capacity is 200 people, the number of learning actions performed by the feedforward neural network used at this time is 600 times; For another example, when the aircraft type used for the scheduled flight is Boeing 777-200 and the corresponding maximum passenger capacity is 300 people, the number of learning actions performed by the feedforward neural network used at this time is 650 times; For another example, when the aircraft type used for the scheduled flight is Boeing 777-300 and the corresponding maximum passenger capacity is 400 people, the number of learning actions performed by the feedforward neural network used at this time is 700 times; For another example, when the aircraft type used for the scheduled flight is Airbus A380 and the corresponding maximum passenger capacity is 500 people, the number of learning actions performed by the feedforward neural network used at this time is 750 times, and so on; Third: In each learning action performed by the feedforward neural network, the abnormal event identifier of whether there are abnormal events of loading delays in various meal packages actually provided for the flight tasks performed on a certain day in the past of the known scheduled flight and the responsible party number causing the abnormal event of loading delays are used as two input contents of the feedforward neural network. The multiple meal loading feedback data corresponding to the flight tasks of multiple days before a certain day in the past of the scheduled flight, the meal quantities corresponding to various meal packages actually provided for the flight tasks performed on a certain day in the past of the scheduled flight, and the various configuration information of the meal suppliers providing meal services for the scheduled flight are used as multiple input contents of the feedforward neural network to complete this learning action, thus ensuring the learning effect of each learning action of the feedforward neural network; In this way, through the above-mentioned customized structure design of the AI quality traceability model, the reliability and stability of the intelligent prediction results are ensured; Technical process 2: To perform intelligent simultaneous prediction of whether there will be an abnormal installation delay event and the number of the responsible party causing the abnormal installation delay event for the catering mission on the day of the set flight, various basic information is selected in a targeted manner. The acquisition of various basic information is performed through the microservice architecture; Specifically, the basic information includes multiple meal installation feedback data corresponding to the flight missions of the set flight in the past days, the number of meals corresponding to each type of meal set required for the flight mission of the set flight that has not been executed on the day, and the configuration information of the meal supplier providing meal service for the set flight; More specifically, the single meal preparation and installation feedback data corresponding to each day's flight mission of the set flight in the past is the number of meals of each meal set actually provided by the set flight when performing the flight mission of that day, the time actually consumed to complete the production of each meal set provided, the time actually consumed to complete the transportation of each meal set provided, the time actually consumed to complete the handover of each meal set provided, and the time actually consumed to complete the installation of each meal set provided. The various configuration information of the meal supplier providing meal preparation services for the set flight includes the transportation mileage of the meal supplier providing meal preparation services for the set flight, the time for obtaining supply qualifications, the time for obtaining the latest qualified test report, the number of employees employed, the area of ​​the production workshop, the maximum meal cooking temperature, and the maximum meal cooking time. For example, the microservice architecture is selected to analyze the number of meals corresponding to each set of meal packages required for the flight mission that has not been executed on the day of the set flight. Specifically, the first process under the microservice architecture is used to analyze the ratio of meal quantities of each set of meal packages for the flight missions of the set flight in the past multiple days, the second process under the microservice architecture is used to analyze the number of passengers for the flight mission that has not been executed on the day of the set flight, and the third process under the microservice architecture is used to take the average of the ratio of meal quantities of each set of meal packages for the flight missions of the set flight in the past multiple days as the ratio of meal quantities of each set of meal packages required for the flight mission that has not been executed on the day of the set flight, and based on the ratio of meal quantities of each set of meal packages required for the flight mission that has not been executed on the day of the set flight and the number of passengers for the flight mission that has not been executed on the day of the set flight, the number of meals corresponding to each set of meal packages required for the flight mission that has not been executed on the day of the set flight is obtained, thereby completing the effective measurement of the number of meals corresponding to each set of meal packages required for the flight mission that has not been executed on the day of the set flight; In this way, through the comprehensive and sufficient selection of the above basic information, the reliability and stability of the intelligent prediction results are further guaranteed; Technical process three: Use the basic information fully selected in technical process two as the AI ​​quality traceability model of the customized structure design in technical process one to perform synchronous intelligent prediction of whether there will be abnormal installation delays and the number of the responsible party causing the abnormal installation delays for the catering mission on the day of the set flight; Specifically, when the intelligent prediction of the abnormal event identifier indicates that there is an abnormal event of loading delay in various packages required for the flight mission on the day when the set flight has not been executed, and at the same time, the responsible party number for the abnormal event of loading delay predicted by the intelligent prediction is the number corresponding to the production workshop of the catering supplier, the number corresponding to the transportation entity of the catering supplier, the number corresponding to the catering handover personnel, or the number corresponding to the loading entity; Conversely, when the intelligent prediction of the abnormal event identifier indicates that there is no abnormal event of loading delay in various packages required for the flight mission on the day when the set flight has not been executed, and at the same time, the responsible party number for the abnormal event of loading delay predicted by the intelligent prediction is an empty character; Exemplarily, since the various packages actually provided by the airline catering for each flight mission of the set flight go through the entire airline catering process of four events: production, transportation, handover, and loading, the responsible party number may be one of the numbers corresponding to the production workshop of the catering supplier, the number corresponding to the transportation entity of the catering supplier, the number corresponding to the catering handover personnel, and the number corresponding to the loading entity; Technical process four: Determine whether to immediately display the responsible party number for the abnormal event of loading delay predicted by the intelligent prediction based on the intelligent prediction result of technical process three; Specifically, when the intelligent prediction of the abnormal event identifier indicates that there is an abnormal event of loading delay in various packages required for the flight mission on the day when the set flight has not been executed, immediately display the responsible party number for the abnormal event of loading delay predicted by the intelligent prediction. The on-site for immediate display here can be the aircraft control room or the control room at the air traffic control center; It can be seen that the present invention is directed to the entire airline catering process of four events: production, transportation, handover, and loading of the various packages actually provided by the airline catering for each flight mission of the set flight. The AI quality traceability model is used to intelligently predict whether there will be an abnormal event of loading delay in the catering for the flight mission on the day when the set flight has not been executed and the responsible party number for the abnormal event of loading delay based on the catering supplier information of the set flight, the past catering loading feedback data of the set flight, and the catering-related data of the flight mission on the day when the set flight has not been executed, thereby providing more valuable reference information for the early response and allocation of abnormal events in airline catering.

[0017] The key points of the present invention are: adopting a microservices architecture to perform targeted acquisition of various basic information, an AI quality traceability model with a customized structure design, comprehensive and sufficient selection of various basic information, and targeted design of each learning action performed by the feedforward neural network.

[0018] Next, the microservices-based quality traceability system for airline catering of the present invention will be specifically described by way of embodiments.

[0019] First Embodiment Figure 2 The internal structure diagram of a microservices-based quality traceability system for airline catering according to the first embodiment of the present invention.

[0020] As Figure 2 shown, the microservices-based quality traceability system for airline catering includes the following components: A task parsing device, configured to parse the quantity of each meal corresponding to various meal packages required for the day's flight tasks that have not been executed for a set flight using a microservices architecture. Exemplarily, a targeted parsing of the quantity of each meal corresponding to various meal packages required for the day's flight tasks that have not been executed for a set flight can be selected using a process under a microservices architecture. A configuration acquisition device, configured to obtain the transportation mileage, supply qualification acquisition duration, latest qualified inspection report acquisition duration, number of employees, production workshop floor area, maximum meal steaming temperature, and maximum meal steaming duration of the meal supplier providing meal services for a set flight using a microservices architecture, as the configuration information of each meal supplier providing meal services for a set flight. Exemplarily, obtaining the transportation mileage, supply qualification acquisition duration, latest qualified inspection report acquisition duration, number of employees, production workshop floor area, maximum meal steaming temperature, and maximum meal steaming duration of the meal supplier providing meal services for a set flight using a microservices architecture, as the configuration information of each meal supplier providing meal services for a set flight includes: the maximum meal steaming temperature and maximum meal steaming duration can be obtained by accessing the device logs of the production workshop using a microservices architecture. A network learning device, configured to perform each learning action on a feedforward neural network to obtain the feedforward neural network after each learning action and output it as an AI quality traceability model, where the number of learning actions is positively correlated with the maximum passenger capacity of the set flight. Exemplarily, when the aircraft model used for a set flight is Boeing 737 MAX9 and the corresponding maximum passenger capacity is 200 people, the number of learning actions performed by the feedforward neural network used at this time is 600 times. For another example, when the aircraft model used for a set flight is Boeing 777-200 and the corresponding maximum passenger capacity is 300 people, the number of learning actions performed by the feedforward neural network used at this time is 650 times. For another example, when the aircraft model used for a set flight is Boeing 777-300 and the corresponding maximum passenger capacity is 400 people, the number of learning actions performed by the feedforward neural network used at this time is 700 times. For another example, when the aircraft model used for a scheduled flight is an Airbus A380 and the corresponding maximum passenger capacity is 500 people, the number of learning actions performed by the feedforward neural network used at this time is 750 times, and so on; The quality traceability device is respectively connected to the task analysis device, the configuration acquisition device, and the network learning device, and is used to intelligently predict whether there are abnormal event identifiers of abnormal events of flight delays in various packages required for the current day's flight task that the scheduled flight has not yet executed, and the responsible party numbers that cause the abnormal events of flight delays, based on the AI quality traceability model, using multiple sets of meal loading feedback data corresponding to the flight tasks of the scheduled flight in the past multiple days, the quantities of various packages required for the current day's flight task that the scheduled flight has not yet executed, and the configuration information of each meal delivery supplier that provides meal delivery services for the scheduled flight; Specifically, when the abnormal event identifier predicted intelligently indicates that there are abnormal events of flight delays in various packages required for the current day's flight task that the scheduled flight has not yet executed, the responsible party number predicted intelligently for the abnormal event of flight delay is one of the numbers corresponding to the production workshop of the meal delivery supplier, the number corresponding to the transportation entity of the meal delivery supplier, the number corresponding to the meal transfer personnel, and the number corresponding to the aircraft loading entity; Among them, when the scheduled flight executes the flight tasks of each day in the past, the various packages actually provided go through the entire process of airline meal delivery, including four events: production, transportation, transfer, and aircraft loading; Among them, the single set of meal loading feedback data corresponding to the flight task of each day in the past of the scheduled flight is the quantity of meals in various packages actually provided when the scheduled flight executes the flight task of that day, the duration consumed for the actual production of various packages provided, the duration consumed for the actual transportation of various packages provided, the duration consumed for the actual transfer of various packages provided, and the duration consumed for the actual aircraft loading of various packages provided; Among them, when the abnormal event identifier predicted intelligently indicates that there are abnormal events of flight delays in various packages required for the current day's flight task that the scheduled flight has not yet executed, the responsible party number predicted intelligently for the abnormal event of flight delay is the number corresponding to the production workshop of the meal delivery supplier, the number corresponding to the transportation entity of the meal delivery supplier, the number corresponding to the meal transfer personnel, or the number corresponding to the aircraft loading entity; Exemplarily, when the anomaly event identifier predicted by the intelligent prediction indicates that there is an anomaly event of loading delay for various packages required for the flight mission on the day when the scheduled flight has not been executed, and at the same time, the responsible party number causing the loading delay anomaly event predicted by the intelligent prediction is the number corresponding to the production workshop of the catering supplier, the number corresponding to the transportation entity of the catering supplier, the number corresponding to the catering handover personnel, or the number corresponding to the loading entity, it includes: using different numerical values with the same bit length to represent the number corresponding to the production workshop of the catering supplier, the number corresponding to the transportation entity of the catering supplier, the number corresponding to the catering handover personnel, or the number corresponding to the loading entity respectively; Among them, when the anomaly event identifier predicted by the intelligent prediction indicates that there is no anomaly event of loading delay for various packages required for the flight mission on the day when the scheduled flight has not been executed, and at the same time, the responsible party number causing the loading delay anomaly event predicted by the intelligent prediction is an empty character; Exemplarily, when the anomaly event identifier predicted by the intelligent prediction indicates that there is no anomaly event of loading delay for various packages required for the flight mission on the day when the scheduled flight has not been executed, and at the same time, the responsible party number causing the loading delay anomaly event predicted by the intelligent prediction is an empty character, it includes: the empty character is NULL; In each learning action performed on the feedforward neural network, the anomaly event identifier indicating whether there is an anomaly event of loading delay for various packages actually provided for the flight mission on a certain day in the past of the scheduled flight and the responsible party number causing the loading delay anomaly event are used as two input contents of the feedforward neural network, and multiple input contents of the feedforward neural network are the multiple pieces of catering loading feedback data corresponding to the flight missions of the scheduled flight in multiple days before a certain day in the past, the respective catering quantities corresponding to the various packages actually provided for the flight mission on a certain day in the past of the scheduled flight, and the respective configuration information of the catering suppliers providing catering services for the scheduled flight, to complete this learning action; Among them, using the AI quality traceability model to intelligently predict the anomaly event identifier indicating whether there is an anomaly event of loading delay for various packages required for the flight mission on the day when the scheduled flight has not been executed and the responsible party number causing the loading delay anomaly event based on the multiple pieces of catering loading feedback data corresponding to the flight missions of the scheduled flight in multiple days in the past, the respective catering quantities corresponding to the various packages required for the flight mission on the day when the scheduled flight has not been executed, and the respective configuration information of the catering suppliers providing catering services for the scheduled flight includes: the number of days in the past selected is positively correlated with the sailing mileage of the scheduled flight; Exemplarily, the number of days of the selected past multiple days being positively correlated with the flight mileage of the set flight includes: when the flight mileage of the set flight is 500 kilometers, the number of days of the selected past multiple days is 10 days; when the flight mileage of the set flight is 600 kilometers, the number of days of the selected past multiple days is 12 days; when the flight mileage of the set flight is 700 kilometers, the number of days of the selected past multiple days is 14 days; when the flight mileage of the set flight is 800 kilometers, the number of days of the selected past multiple days is 16 days, and so on.

[0021] Second Embodiment Figure 3 FIG. is an internal structure diagram of a microservice-based quality traceability system for airline catering according to the second embodiment of the present invention.

[0022] As Figure 3 shown, compared with Figure 2 , the microservice-based quality traceability system for airline catering further includes: An encryption and on-chain device, connected to the catering collection device, for receiving each piece of configuration information of the catering supplier providing catering services for the set flight, performing data encryption processing on each piece of configuration information of the catering supplier providing catering services for the set flight, and wirelessly transmitting each piece of configuration information of the catering supplier providing catering services for the set flight after data encryption processing to the blockchain monitoring node for catering task monitoring; Exemplarily, the encryption and on-chain device, connected to the catering collection device, for receiving each piece of configuration information of the catering supplier providing catering services for the set flight, performing data encryption processing on each piece of configuration information of the catering supplier providing catering services for the set flight, and wirelessly transmitting each piece of configuration information of the catering supplier providing catering services for the set flight after data encryption processing to the blockchain monitoring node for catering task monitoring includes: the wireless transmission is based on a time-division duplex communication link.

[0023] Third Embodiment Figure 4 FIG. is an internal structure diagram of a microservice-based quality traceability system for airline catering according to the third embodiment of the present invention.

[0024] As Figure 4 shown, compared with Figure 3 , the microservice-based quality traceability system for airline catering further includes: A satellite positioning device, connected to the quality traceability device, for providing positioning services for obtaining feedback data of multiple pieces of catering loaded for each of the flight tasks of the set flight in the past multiple days; Exemplarily, the satellite positioning device is built with a navigation and positioning unit, a timing unit, and a power supply unit. The navigation and positioning unit is used to provide positioning services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days. Among them, the satellite positioning device, which is connected to the quality traceability device, is used to provide positioning services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days, including: providing positioning services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days based on the GPS positioning system or the Beidou positioning system.

[0025] The fourth embodiment Figure 5 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown according to the fourth embodiment of the present invention.

[0026] As Figure 5 shown, compared with Figure 4 , the microservice-based quality traceability system for airline catering further includes: A timing server device, which is connected to the quality traceability device, is used to provide timing services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days; Among them, the timing server device, which is connected to the quality traceability device, is used to provide timing services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days, including: the timing server device is built with a quartz oscillation unit, which is used to generate a reference clock pulse to provide timing services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days; Specifically, the timing server device is built with a quartz oscillation unit, which is used to generate a reference clock pulse to provide timing services for obtaining the feedback data of multiple sets of meal loadings corresponding to the flight tasks of a set flight over multiple days, including: the reference clock pulse is a square waveform.

[0027] The fifth embodiment Figure 6 It is an internal structure diagram of a microservice-based quality traceability system for airline catering shown according to the fifth embodiment of the present invention.

[0028] As Figure 6 shown, compared with Figure 5 , the microservice-based quality traceability system for airline catering further includes: An instant display device, which is connected to the quality traceability device, is used to instantaneously display the responsible party number that causes the abnormal event of loading delay while instantaneously predicting that there is an abnormal event of loading delay for various meal packages required for the flight task of the day that the set flight has not yet executed when the intelligent prediction of the abnormal event identifier indicates such a situation. Specifically, an LED display array or an LCD display array can be selected to implement the instant display device, which is connected to the quality traceability device and is used to instantaneously display the responsible party number that causes the abnormal event of loading delay predicted by intelligence when the abnormal event identification of the intelligent prediction indicates that there is an abnormal event of loading delay in various packages required for the flight tasks of the set flight on the day when the set flight has not been executed.

[0029] Next, further description will be continued for each embodiment of the present invention.

[0030] Optionally, in each of the above embodiments, in the microservices-based quality traceability system for airline catering: Using a microservices architecture to analyze the respective quantities of each meal package corresponding to the flight tasks of the set flight on the day when the set flight has not been executed includes: using a first process under the microservices architecture to analyze the proportion of the quantities of meal packages for various meal packages of the set flight's flight tasks in the past multiple days, using a second process under the microservices architecture to analyze the number of passengers for the flight tasks of the set flight on the day when the set flight has not been executed, and obtaining the respective quantities of each meal package corresponding to the flight tasks of the set flight on the day when the set flight has not been executed based on the proportion of the quantities of meal packages for various meal packages of the set flight's flight tasks in the past multiple days and the number of passengers for the flight tasks of the set flight on the day when the set flight has not been executed; Among them, obtaining the respective quantities of each meal package corresponding to the flight tasks of the set flight on the day when the set flight has not been executed based on the proportion of the quantities of meal packages for various meal packages of the set flight's flight tasks in the past multiple days and the number of passengers for the flight tasks of the set flight on the day when the set flight has not been executed includes: taking the average value of the proportion of the quantities of meal packages for various meal packages of the set flight's flight tasks in the past multiple days as the proportion of the quantities of meal packages for various meal packages required for the flight tasks of the set flight on the day when the set flight has not been executed, and obtaining the respective quantities of each meal package corresponding to the flight tasks of the set flight on the day when the set flight has not been executed based on the proportion of the quantities of meal packages for various meal packages required for the flight tasks of the set flight on the day when the set flight has not been executed and the number of passengers for the flight tasks of the set flight on the day when the set flight has not been executed; Exemplarily, when the proportion of the quantities of beef meal packages, chicken meal packages, and vegetarian meal packages required for the flight tasks of the set flight on the day when the set flight has not been executed is 2:2:1, and the number of passengers for the flight tasks of the set flight on the day when the set flight has not been executed is 200, then the respective quantities of beef meal packages, chicken meal packages, and vegetarian meal packages required for the flight tasks of the set flight on the day when the set flight has not been executed are 80 portions, 80 portions, and 40 portions.

[0031] Optionally, in each of the above embodiments, in the microservices-based quality traceability system for airline catering: Perform each learning action on the feedforward neural network to obtain the feedforward neural network after each learning action and output it as the AI quality traceability model. The number of learning actions is positively correlated with the maximum passenger capacity of the scheduled flight, including: representing the information mapping relationship between the number of learning actions and the maximum passenger capacity of the scheduled flight using an information mapping formula; Specifically, it is possible to select to complete the simulation and testing of the information mapping process of representing the information mapping relationship between the number of learning actions and the maximum passenger capacity of the scheduled flight using the information mapping formula in a numerical simulation mode; Among them, representing the information mapping relationship between the number of learning actions and the maximum passenger capacity of the scheduled flight using the information mapping formula includes: in the information mapping formula, the maximum passenger capacity of the scheduled flight is the input information of the information mapping formula; And among them, representing the information mapping relationship between the number of learning actions and the maximum passenger capacity of the scheduled flight using the information mapping formula further includes: in the information mapping formula, the number of learning actions positively correlated with the maximum passenger capacity of the scheduled flight is the output information of the information mapping formula.

[0032] And in each of the above embodiments, optionally, in the microservice-based quality traceability system for airline catering: Using the AI quality traceability model to intelligently predict the anomaly event identifier of whether there is an abnormal event of loading delay for various packages required for the current day's flight task that the scheduled flight has not yet executed, and the responsible party number causing the abnormal event of loading delay, based on multiple pieces of meal loading feedback data corresponding to the past multiple days' flight tasks of the scheduled flight, the quantities of various packages required for the current day's flight task that the scheduled flight has not yet executed, and the configuration information of the meal suppliers providing meal services for the scheduled flight, further includes: parallelly inputting the multiple pieces of meal loading feedback data corresponding to the past multiple days' flight tasks of the scheduled flight, the quantities of various packages required for the current day's flight task that the scheduled flight has not yet executed, and the configuration information of the meal suppliers providing meal services for the scheduled flight into the AI quality traceability model; Exemplarily, parallelly inputting the multiple pieces of meal loading feedback data corresponding to the past multiple days' flight tasks of the scheduled flight, the quantities of various packages required for the current day's flight task that the scheduled flight has not yet executed, and the configuration information of the meal suppliers providing meal services for the scheduled flight into the AI quality traceability model includes: parallelly inputting the multiple pieces of meal loading feedback data corresponding to the past multiple days' flight tasks of the scheduled flight, the quantities of various packages required for the current day's flight task that the scheduled flight has not yet executed, and the configuration information of the meal suppliers providing meal services for the scheduled flight into the input port of the AI quality traceability model; Among them, the AI quality traceability model is used to intelligently predict the abnormal event identifier of whether there is an abnormal event of loading delay for various packages required for the flight mission of the day that the set flight has not yet executed, and the responsible party number for the abnormal event of loading delay, based on multiple pieces of meal loading feedback data corresponding to the flight missions of the set flight in the past multiple days, the quantities of various packages corresponding to the flight mission of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal service for the set flight. It also includes: executing the AI quality traceability model to obtain the abnormal event identifier of whether there is an abnormal event of loading delay for various packages required for the flight mission of the day that the set flight has not yet executed, and the responsible party number for the abnormal event of loading delay output by the AI quality traceability model; Among them, parallel input of multiple pieces of meal loading feedback data corresponding to the flight missions of the set flight in the past multiple days, the quantities of various packages corresponding to the flight mission of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal service for the set flight into the AI quality traceability model includes: performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight missions of the set flight in the past multiple days, the quantities of various packages corresponding to the flight mission of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal service for the set flight respectively, and then parallel inputting them into the AI quality traceability model; Among them, executing the AI quality traceability model to obtain the abnormal event identifier of whether there is an abnormal event of loading delay for various packages required for the flight mission of the day that the set flight has not yet executed, and the responsible party number for the abnormal event of loading delay includes: the abnormal event identifier of whether there is an abnormal event of loading delay for various packages required for the flight mission of the day that the set flight has not yet executed, and the responsible party number for the abnormal event of loading delay output by the AI quality traceability model are both in the form of numerical representations after numerical normalization processing; Among them, performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight missions of the set flight in the past multiple days, the quantities of various packages corresponding to the flight mission of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal service for the set flight respectively, and then parallel inputting them into the AI quality traceability model includes: the numerical normalization processing is hexadecimal numerical conversion processing; Among them, after performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, and then parallelly inputting them into the AI quality traceability model, it further includes: using a first programmable logic device to perform numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight respectively; Among them, after performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, and then parallelly inputting them into the AI quality traceability model, it further includes: using a second programmable logic device to parallelly input multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, which have respectively undergone numerical normalization processing, into the AI quality traceability model; Specifically, the first programmable logic device and the second programmable logic device can share the same parameter configuration interface and the same power supply; And among them, using a second programmable logic device to parallelly input multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, which have respectively undergone numerical normalization processing, into the AI quality traceability model includes: the first programmable logic device and the second programmable logic device are different models of FPGA chips designed in VHDL language and the first programmable logic device is connected to the second programmable logic device.

[0033] In addition, in the microservice-based quality traceability system for airline meal distribution according to the present invention: Using an AI quality traceability model, based on multiple sets of meal loading feedback data corresponding to the flight missions of a set flight over the past multiple days, the quantities of various meal packages required for the flight mission of the set flight that has not been executed on the current day, and each set of configuration information of the meal suppliers providing meal services for the set flight, it intelligently predicts the anomaly event identifier of whether there are any abnormal events of meal loading delays for the various meal packages required for the flight mission of the set flight that has not been executed on the current day, and the responsible party number causing the abnormal event of meal loading delays. It also includes: selecting a data mapping function to represent the data mapping relationship in which the number of days in the past multiple days is positively correlated with the sailing mileage of the set flight; For example, the MATLAB toolbox can be used to complete the simulation and testing of the data mapping process of using a data mapping function to represent the data mapping relationship in which the number of days in the past multiple days is positively correlated with the sailing mileage of the set flight; Among them, selecting a data mapping function to represent the data mapping relationship in which the number of days in the past multiple days is positively correlated with the sailing mileage of the set flight includes: in the data mapping function, the sailing mileage of the set flight is the input data of the data mapping function; And among them, selecting a data mapping function to represent the data mapping relationship in which the number of days in the past multiple days is positively correlated with the sailing mileage of the set flight also includes: in the data mapping function, the number of days in the past multiple days that is positively correlated with the sailing mileage of the set flight is the output data of the data mapping function.

[0034] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present disclosure, and are not intended to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present disclosure, and they should all be covered by the scope of the claims and the description of the present disclosure.

Claims

1. A microservices-based quality traceability system for airline catering, characterized in that, The system includes: A task parsing device, which is used to parse, by adopting a microservice architecture, the respective distribution meal quantities corresponding to various packages required for the flight tasks that have not been executed on the current day for a set flight; A configuration acquisition device, which is used to acquire, by adopting a microservice architecture, the transportation mileage, the acquisition duration of supply qualifications, the acquisition duration of the latest qualified inspection report, the number of employees, the floor area of the production workshop, the maximum temperature for meal steaming, and the longest duration for meal steaming of the meal supplier providing meal services for the set flight, so as to use them as the respective configuration information of the meal supplier providing meal services for the set flight; A network learning device, which is used to perform each learning action on a feedforward neural network to obtain the feedforward neural network after each learning action and output it as an AI quality traceability model, and the number of learning actions is positively correlated with the maximum passenger capacity of the set flight; A quality traceability device, which is respectively connected to the task parsing device, the configuration acquisition device, and the network learning device, and is used to use the AI quality traceability model to intelligently predict, based on the multiple meal loading feedback data corresponding to the flight tasks of the set flight in the past multiple days, the respective distribution meal quantities corresponding to various packages required for the flight tasks that have not been executed on the current day for the set flight, and the respective configuration information of the meal supplier providing meal services for the set flight, the abnormal event identifier indicating whether there is an abnormal event of flight delay in various packages required for the flight tasks that have not been executed on the current day for the set flight and the responsible party number causing the abnormal event of flight delay; 2. The microservice-based quality traceability system for airline catering according to claim 1, wherein: When the set flight executes the flight tasks of each past day, the various packages actually provided go through the entire process of airline catering including four events: production, transportation, handover, and loading; Among them, the single meal loading feedback data corresponding to the flight tasks of each past day of the set flight is the meal quantity of the various packages actually provided by the set flight when executing the flight tasks on that day, the duration consumed for the actual production of the various packages provided, the duration consumed for the actual transportation of the various packages provided, the duration consumed for the actual handover of the various packages provided, and the duration consumed for the actual loading of the various packages provided; Among them, when the abnormal event identifier indicates that there is an abnormal event of flight delay in the various packages required for the flight tasks that have not been executed on the current day for the set flight, the responsible party number causing the abnormal event of flight delay is the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation entity of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the loading entity; Among them, when the abnormal event identifier indicates that there is no abnormal event of flight delay in the various packages required for the flight tasks that have not been executed on the current day for the set flight, the responsible party number causing the abnormal event of flight delay is an empty character; 3. The microservice-based quality traceability system for airline catering according to claim 2, wherein: In each learning operation performed on the feedforward neural network, the anomaly event identifier indicating whether there is an abnormal event of loading delay for various packages actually provided in the flight tasks performed on a certain day in the past of the known set flight and the responsible party number causing the abnormal event of loading delay are used as two input contents of the feedforward neural network. The multiple input contents of the feedforward neural network include multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days before a certain day in the past, the quantities of various catering packages actually provided in the flight tasks performed by the set flight on a certain day in the past, and the respective configuration information of the catering suppliers providing catering services for the set flight, thus completing this learning operation. Among them, using the AI quality traceability model to intelligently predict the anomaly event identifier indicating whether there is an abnormal event of loading delay for various packages required for the flight tasks of the set flight on the day not yet executed and the responsible party number causing the abnormal event of loading delay based on multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past, the quantities of various catering packages required for the flight tasks of the set flight on the day not yet executed, and the respective configuration information of the catering suppliers providing catering services for the set flight includes: The number of days of the selected multiple days in the past is positively correlated with the sailing mileage of the set flight.

4. The microservice-based quality traceability system for airline catering according to claim 3, characterized in that, The system further includes: An encryption and on-chain device, connected to the catering collection device, for receiving the respective configuration information of the catering suppliers providing catering services for the set flight, performing data encryption processing on the respective configuration information of the catering suppliers providing catering services for the set flight, and wirelessly transmitting the data-encrypted respective configuration information of the catering suppliers providing catering services for the set flight to the blockchain monitoring node for catering task monitoring.

5. The microservice-based quality traceability system for airline catering as claimed in claim 3, wherein The system further includes: A satellite positioning device, connected to the quality traceability device, for providing positioning services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past. Among them, the satellite positioning device, connected to the quality traceability device, for providing positioning services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past includes: Providing positioning services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past based on the GPS positioning system or the Beidou positioning system.

6. The microservice-based quality traceability system for airline catering according to claim 3, characterized in that, The system further includes: A timing server device, connected to the quality traceability device, for providing timing services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past. Among them, the timing server device, connected to the quality traceability device, for providing timing services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past includes: The timing server device has a built-in quartz oscillation unit for generating reference clock pulses to provide timing services for obtaining multiple catering loading feedback data respectively corresponding to the flight tasks of the set flight in multiple days in the past.

7. The microservice-based quality traceability system for airline catering according to claim 3, characterized in that The system further includes: An instant display device, connected to a quality traceability device, is used to instantaneously display the responsible party number that is simultaneously intelligently predicted to cause the abnormal event of loading delay when the intelligent prediction of the abnormal event identification indicates that there is an abnormal event of loading delay in various packages required for the flight tasks on the day when the scheduled flight has not been executed.

8. The microservice-based quality traceability system for airline catering according to any one of claims 3-7, characterized in that: Using a microservice architecture to analyze the respective quantities of each meal package corresponding to the flight tasks on the day when the scheduled flight has not been executed includes: using the first process under the microservice architecture to analyze the proportion of the meal package quantities of various meal packages for the flight tasks of the scheduled flight in the past multiple days, using the second process under the microservice architecture to analyze the number of passengers for the flight tasks on the day when the scheduled flight has not been executed, and obtaining the respective quantities of each meal package corresponding to the flight tasks on the day when the scheduled flight has not been executed based on the proportion of the meal package quantities of various meal packages for the flight tasks of the scheduled flight in the past multiple days and the number of passengers for the flight tasks on the day when the scheduled flight has not been executed; Among them, obtaining the respective quantities of each meal package corresponding to the flight tasks on the day when the scheduled flight has not been executed based on the proportion of the meal package quantities of various meal packages for the flight tasks of the scheduled flight in the past multiple days and the number of passengers for the flight tasks on the day when the scheduled flight has not been executed includes: taking the average value of the proportion of the meal package quantities of various meal packages for the flight tasks of the scheduled flight in the past multiple days as the proportion of the meal package quantities of various meal packages required for the flight tasks on the day when the scheduled flight has not been executed, and obtaining the respective quantities of each meal package corresponding to the flight tasks on the day when the scheduled flight has not been executed based on the proportion of the meal package quantities of various meal packages required for the flight tasks on the day when the scheduled flight has not been executed and the number of passengers for the flight tasks on the day when the scheduled flight has not been executed.

9. The microservice-based quality traceability system for airline catering according to any one of claims 3-7, characterized in that: Performing each learning action on the feedforward neural network to obtain the feedforward neural network after performing each learning action and outputting it as the AI quality traceability model, and the number of learning actions is positively correlated with the maximum passenger capacity of the scheduled flight includes: using an information mapping formula to represent the information mapping relationship in which the number of learning actions is positively correlated with the maximum passenger capacity of the scheduled flight; Among them, using an information mapping formula to represent the information mapping relationship in which the number of learning actions is positively correlated with the maximum passenger capacity of the scheduled flight includes: in the information mapping formula, the maximum passenger capacity of the scheduled flight is the input information of the information mapping formula; Among them, using an information mapping formula to represent the information mapping relationship in which the number of learning actions is positively correlated with the maximum passenger capacity of the scheduled flight further includes: in the information mapping formula, the number of learning actions that is positively correlated with the maximum passenger capacity of the scheduled flight is the output information of the information mapping formula.

10. The microservice-based quality traceability system for airline catering according to any one of claims 3-7, characterized in that: Using the AI quality traceability model, based on multiple sets of catering loading feedback data corresponding to the flight tasks of a specified flight over the past multiple days, the quantities of various catering packages corresponding to the flight tasks of the specified flight that have not been executed on the current day, and the configuration information of each catering supplier providing catering services for the specified flight, to intelligently predict the anomaly event identifier indicating whether there are any loading delay anomaly events for the various catering packages required for the flight tasks of the specified flight that have not been executed on the current day, and the responsible party number causing the loading delay anomaly event. It also includes: parallelly inputting the multiple sets of catering loading feedback data corresponding to the flight tasks of the specified flight over the past multiple days, the quantities of various catering packages corresponding to the flight tasks of the specified flight that have not been executed on the current day, and the configuration information of each catering supplier providing catering services for the specified flight into the AI quality traceability model; Among them, using the AI quality traceability model, based on multiple sets of catering loading feedback data corresponding to the flight tasks of a specified flight over the past multiple days, the quantities of various catering packages corresponding to the flight tasks of the specified flight that have not been executed on the current day, and the configuration information of each catering supplier providing catering services for the specified flight, to intelligently predict the anomaly event identifier indicating whether there are any loading delay anomaly events for the various catering packages required for the flight tasks of the specified flight that have not been executed on the current day, and the responsible party number causing the loading delay anomaly event. It also includes: executing the AI quality traceability model to obtain the anomaly event identifier indicating whether there are any loading delay anomaly events for the various catering packages required for the flight tasks of the specified flight that have not been executed on the current day, and the responsible party number causing the loading delay anomaly event output by the AI quality traceability model; Among them, parallelly inputting the multiple sets of catering loading feedback data corresponding to the flight tasks of a specified flight over the past multiple days, the quantities of various catering packages corresponding to the flight tasks of the specified flight that have not been executed on the current day, and the configuration information of each catering supplier providing catering services for the specified flight into the AI quality traceability model includes: respectively performing numerical normalization processing on the multiple sets of catering loading feedback data corresponding to the flight tasks of the specified flight over the past multiple days, the quantities of various catering packages corresponding to the flight tasks of the specified flight that have not been executed on the current day, and the configuration information of each catering supplier providing catering services for the specified flight, and then parallelly inputting them into the AI quality traceability model; Among them, executing the AI quality traceability model to obtain the anomaly event identifier indicating whether there are any loading delay anomaly events for the various catering packages required for the flight tasks of the specified flight that have not been executed on the current day, and the responsible party number causing the loading delay anomaly event output by the AI quality traceability model includes: both the anomaly event identifier indicating whether there are any loading delay anomaly events for the various catering packages required for the flight tasks of the specified flight that have not been executed on the current day and the responsible party number causing the loading delay anomaly event output by the AI quality traceability model are in the form of numerical representations after numerical normalization processing; Among them, after performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, and then parallelly inputting them into the AI quality traceability model, the numerical normalization processing is hexadecimal numerical conversion processing; Among them, after performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, and then parallelly inputting them into the AI quality traceability model further includes: using a first programmable logic device to perform numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight; Among them, after performing numerical normalization processing on multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, and then parallelly inputting them into the AI quality traceability model further includes: using a second programmable logic device to parallelly input the multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, which have respectively undergone numerical normalization processing, into the AI quality traceability model; Among them, using a second programmable logic device to parallelly input the multiple pieces of meal loading feedback data corresponding to the flight tasks of a set flight over multiple days, the quantities of various meal packages corresponding to the flight tasks of the day that the set flight has not yet executed, and the configuration information of each meal supplier providing meal services for the set flight, which have respectively undergone numerical normalization processing, into the AI quality traceability model includes: the first programmable logic device and the second programmable logic device are different models of FPGA chips designed in VHDL language and the first programmable logic device is connected to the second programmable logic device.

Images