An air catering-oriented micro-service quality traceability system

Abstract

The application relates to an air catering-oriented micro-service quality traceability system, relates to the field of data processing specially applied to administrative, commercial, financial, management, supervision or prediction purposes, and the system comprises: a network learning device for acquiring an AI quality traceability model; and a quality traceability device for intelligently predicting whether a set flight has a catering quality abnormal event in future flight tasks based on various catering correlation data of the set flight and various pieces of configuration information of a catering supplier and performing responsibility party traceability by adopting the AI quality traceability model. Through the application, in the face of the technical problem that catering quality of future flight tasks of flights is difficult to control in the prior art, catering quality abnormal event prediction and responsibility party traceability of any future flight task of a flight can be completed on the basis of introduction of a micro-service architecture, customization of a structure design AI quality traceability model and targeted selection of various pieces of basic information, so that the above technical problem is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing specially applied to administrative, commercial, financial, management, supervision or prediction purposes, and in particular to a micro-service quality traceability system for airline catering. BACKGROUND

[0002] When providing airline catering services for each flight at the airport, in order to balance catering efficiency, passenger demand and save food materials, the flight will provide a limited number of meal sets for passengers to choose from, and will also arrange a dedicated catering supplier to provide production and transportation services for various meal sets for the flight, and the flight staff will perform handover and loading operations for various meal sets. As can be seen, the actual provision of various meal sets for each flight in the execution of each day's flight task will go through the entire process of airline catering, including production, transportation, handover and loading. Each event in the entire process of airline catering has a probability of causing abnormal events that delay the final catering loading, thereby affecting the overall operation of the flight.

[0003] For example, Chinese invention patent publication CN110641891A proposes an automatic airline meal catering system, which includes: a three-dimensional warehouse for storing different meal boxes or utensils; a catering delivery device for delivering meal boxes and taking or placing meal boxes or utensils in the meal boxes to a catering position; and a meal box recycling device for recycling empty meal boxes after catering. The catering delivery device includes a first conveying line and a second conveying line arranged in parallel, and a plurality of branch conveying lines arranged perpendicular to the first conveying line between the first conveying line and the second conveying line. The branch conveying line is provided with a meal box taking and placing mechanism at one end close to the second conveying line for taking or placing meal boxes or utensils onto the second conveying line. The meal box recycling device is located below the catering delivery device and is used to recycle empty meal boxes on the branch conveying line. The present application realizes automatic plating of multiple foods through mechanical cooperation, improving catering efficiency and accuracy.

[0004] For example, Chinese invention patent publication CN104865923A proposes an intelligent management system for airplane catering vehicles. 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 the wired / wireless network. The effect of the airplane catering vehicle intelligent management system provided by the present application is: through effective scheduling of airplane catering vehicles, manpower and resources can be saved, the work efficiency of airplane catering vehicles can be improved, the monitoring and management of airplane catering vehicles by the airport can be strengthened, the vehicle operation time can be accurately calculated, and accurate charges can be made according to the operation time, thereby improving the overall operation efficiency of the airport.

[0005] It can be seen that the various technical solutions in the prior art are only limited to the conveying mechanical structure or network configuration structure of the airline catering, for improving the speed and accuracy of the airline catering. However, the responsibility party of the catering quality abnormal event of the airline catering of each flight cannot be traced, not to mention whether the catering quality abnormal event exists in the flight task not yet performed by each flight and the responsibility party of the catering quality abnormal event is traced, so that the flight management party cannot obtain relevant quality prediction information for early processing and response, and the catering quality abnormal event is difficult to avoid and trace, which seriously reduces the catering quality and the operation efficiency of the flight and even the airport. SUMMARY

[0006] In order to solve the technical problems in the prior art, the present application provides an airline catering-oriented micro-service quality traceability system, which can introduce a micro-service architecture, customize an AI quality traceability model of a structural design, and select various basic information on the basis of the airline catering full process of various sets of meals actually provided by the airline catering of a set flight when performing a flight task each day, and adopt an AI quality traceability model to intelligently predict whether the catering of the set flight will appear a delay abnormal event and the responsibility party number causing the delay abnormal event according to the catering supplier information of the set flight, the past catering installation feedback data of the set flight, and the catering related data of the flight task not yet performed by the set flight on the same day, so as to provide more valuable reference information for the early response and allocation of the abnormal event of the airline catering, maintain the quality of the airline catering, and ensure the operation efficiency of the flight and even the airport.

[0007] According to the present application, an airline catering-oriented micro-service quality traceability system is provided, which comprises:

[0008] A task analysis device is used to analyze the number of each meal corresponding to each set of meal required by the flight task not yet performed by the set flight by using a micro-service architecture;

[0009] A configuration acquisition device is used to acquire the transportation mileage, the supply qualification acquisition time length, the latest qualified detection report acquisition time length, the number of employees, the production workshop floor area, the catering cooking maximum temperature, and the catering cooking maximum time length of the catering supplier providing catering services for the set flight as the configuration information of the catering supplier providing catering services for the set flight by using a micro-service architecture;

[0010] A network learning device is used to perform each learning action on the feedforward neural network to obtain the feedforward neural network after each learning action is performed and output as the AI quality traceability model, and the number of learning actions is positively correlated with the maximum number of passengers of the set flight;

[0011] The quality traceability device is connected with the task analysis device, the configuration collection device and the network learning device respectively, and is used for intelligently predicting, by using an AI quality traceability model, whether each type of meal set required by a flight task of a set flight to be executed on the day has a machine loading delay abnormal event and a responsible party number causing the machine loading delay abnormal event based on multiple pieces of meal loading feedback data corresponding to multiple flight tasks of the set flight in the past days, multiple pieces of meal quantity corresponding to each type of meal set required by the flight task of the set flight to be executed on the day, and each piece of configuration information of a meal provider providing meal service for the set flight.

[0012] Therefore, the present application has at least the following outstanding substantial features:

[0013] Substantial feature A: for each type of meal set actually provided by the aviation meal during the whole process of the aviation meal including production, transportation, handover and machine loading for each flight task of the set flight, an AI quality traceability model is used to intelligently predict, according to meal provider information of the set flight, meal loading feedback data of the set flight in the past and meal related data of the flight task of the set flight to be executed on the day, whether the meal of the flight task of the set flight to be executed on the day will appear a machine loading delay abnormal event and a responsible party number causing the machine loading delay abnormal event, so as to provide more valuable reference information for early response and deployment of the abnormal event of the aviation meal;

[0014] Substantial feature B: for the simultaneous intelligent prediction of whether the meal of the flight task of the set flight to be executed on the day will appear a machine loading delay abnormal event and a responsible party number causing the machine loading delay abnormal event, an AI quality traceability model with a customized structure is introduced, the AI quality traceability model is a feedforward neural network after performing each learning action, and the number of learning actions performed by the feedforward neural network is positively correlated with the maximum number of passengers of the set flight, so that the AI quality traceability model with different customized structures is designed for different flights, and the reliability and stability of the intelligent prediction result are ensured;

[0015] Substantial feature C: For the synchronous intelligent prediction of meal loading delay abnormal events and the responsible party number of meal loading delay abnormal events for the flight task of the set flight on the day of execution, a plurality of basic information is selected, including a plurality of meal loading feedback data corresponding to the flight tasks of the set flight in the past days, the number of meals corresponding to each meal set required by the flight task of the set flight to be executed on the day, and the configuration information of each meal supplier providing meal services for the set flight. Specifically, the meal loading feedback data corresponding to each flight task of the set flight in the past days is the number of meals of each meal set actually provided by the set flight when executing the flight task on that day, the time consumed for completing the production of the actually provided meal sets, the time consumed for completing the transportation of the actually provided meal sets, the time consumed for completing the handover of the actually provided meal sets, and the time consumed for completing the meal loading of the actually provided meal sets. The configuration information of each meal supplier providing meal services for the set flight includes the transportation mileage of the meal supplier providing meal services for the set flight, the time for obtaining the supply qualification, the time for obtaining the latest qualified detection report, the number of employees, the production workshop area, the maximum meal cooking temperature, and the longest meal cooking time. The comprehensive and sufficient selection of the above basic information further ensures the reliability and stability of the intelligent prediction result.

[0016] Substantial feature D: The meal quantity corresponding to each meal set required by the flight task of the set flight to be executed on the day is analyzed by using a micro-service architecture. Specifically, the first process under the micro-service architecture is used to analyze the meal quantity proportion of each meal set of the flight tasks of the set flight in the past days, the second process under the micro-service architecture is used to analyze the number of passengers of the flight task of the set flight to be executed on the day, and the third process under the micro-service architecture takes the average value of the meal quantity proportion of each meal set of the flight tasks of the set flight in the past days as the meal quantity proportion of each meal set required by the flight task of the set flight to be executed on the day. Based on the meal quantity proportion of each meal set required by the flight task of the set flight to be executed on the day and the number of passengers of the flight task of the set flight to be executed on the day, the number of meals corresponding to each meal set required by the flight task of the set flight to be executed on the day is obtained, thereby completing the effective calculation of the number of meals corresponding to each meal set required by the flight task of the set flight to be executed on the day.

[0017] Essential feature E: in each learning action performed on the feedforward neural network, the abnormal event identifier of whether there is a boarding delay abnormal event for each type of meal actually provided by the flight task of the set flight on a past day and the responsible party number causing the boarding delay abnormal event are taken as two input contents of the feedforward neural network, a plurality of meal boarding feedback data corresponding to a plurality of past days before the past day of the flight task of the set flight, the number of each meal corresponding to each type of meal actually provided by the flight task of the set flight on the past day and the configuration information of each meal provider providing meal service for the set flight are taken as a plurality of input contents of the feedforward neural network, the learning action is completed, so that the learning effect of each learning action of the feedforward neural network is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0018] The embodiments of the present application will be described below in conjunction with the accompanying drawings, in which:

[0019] Figure 1 The working scene schematic diagram of the micro-service quality traceability system for aviation catering according to the present application is shown.

[0020] Figure 2 The internal structure diagram of the micro-service quality traceability system for aviation catering according to the first embodiment of the present application is shown.

[0021] Figure 3 The internal structure diagram of the micro-service quality traceability system for aviation catering according to the second embodiment of the present application is shown.

[0022] Figure 4 The internal structure diagram of the micro-service quality traceability system for aviation catering according to the third embodiment of the present application is shown.

[0023] Figure 5 The internal structure diagram of the micro-service quality traceability system for aviation catering according to the fourth embodiment of the present application is shown.

[0024] Figure 6 The internal structure diagram of the micro-service quality traceability system for aviation catering according to the fifth embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] As shown in Figure 1 , the working scene schematic diagram of the micro-service quality traceability system for aviation catering according to the present application is shown.

[0026] The specific technical process of the present application is as follows:

[0027] The technical process one is to set the synchronization intelligent prediction of whether the meal loading delay abnormal event occurs in the flight task of the execution day of the flight and the number of the responsible party causing the meal loading delay abnormal event, and introduces the AI quality traceability model with customized structure design;

[0028] Specifically, the customized structure design of the AI quality traceability model mainly reflects in the following aspects:

[0029] Firstly, the AI quality traceability model is a feedforward neural network after performing each learning action;

[0030] Secondly, the number of learning actions performed by the feedforward neural network used is positively correlated with the maximum number of passengers of the set flight, so that the AI quality traceability model with different customized structures is designed for different flights;

[0031] For example, when the aircraft model used by the set flight is Boeing 737 MAX9, and the corresponding maximum number of passengers is 200, the number of learning actions performed by the feedforward neural network used is 600;

[0032] For example, when the aircraft model used by the set flight is Boeing 777-200, and the corresponding maximum number of passengers is 300, the number of learning actions performed by the feedforward neural network used is 650;

[0033] For example, when the aircraft model used by the set flight is Boeing 777-300, and the corresponding maximum number of passengers is 400, the number of learning actions performed by the feedforward neural network used is 700;

[0034] For example, when the aircraft model used by the set flight is Airbus A380, and the corresponding maximum number of passengers is 500, the number of learning actions performed by the feedforward neural network used is 750, and so on;

[0035] Thirdly, in each learning action performed on the feedforward neural network, the abnormal event identifier of whether the meal loading delay abnormal event occurs in the actual meal provided by the set flight on a certain day and the number of the responsible party causing the meal loading delay abnormal event are used as two input contents of the feedforward neural network, and the meal loading feedback data of the set flight on multiple days before a certain day, the number of meals corresponding to each type of meal provided by the set flight on a certain day, and the configuration information of the meal supplier providing meal service for the set flight are used as multiple input contents of the feedforward neural network, so as to complete this learning action, thereby ensuring the learning effect of each learning action of the feedforward neural network;

[0036] In this way, the reliability and stability of the intelligent prediction result are ensured through the customized structure design of the AI quality traceability model.

[0037] The second technical process is to perform synchronous intelligent prediction on whether the meal loading delay abnormal event will occur for the flight task of the set flight and the responsible party number causing the meal loading delay abnormal event, and to select the basic information accordingly. The acquisition of the basic information is performed through the micro-service architecture.

[0038] Specifically, the basic information includes meal loading feedback data corresponding to past flight tasks of the set flight, meal quantities corresponding to various meal sets required for the flight task of the set flight to be performed, and configuration information of meal suppliers providing meal services for the set flight.

[0039] Further specifically, the meal loading feedback data corresponding to each past flight task of the set flight includes meal quantities of various meal sets actually provided for the set flight, time consumed for producing the various meal sets, time consumed for transporting the various meal sets, time consumed for handing over the various meal sets, and time consumed for loading the various meal sets, and the configuration information of the meal suppliers providing meal services for the set flight includes transportation mileage, qualification acquisition time, latest qualified detection report acquisition time, number of employees, production workshop area, maximum meal cooking temperature, and maximum meal cooking time of the meal suppliers providing meal services for the set flight.

[0040] For example, the meal quantities corresponding to various meal sets required for the flight task of the set flight to be performed are analyzed by using the micro-service architecture. Specifically, a first process under the micro-service architecture is used to analyze meal quantity proportions of various meal sets of past flight tasks of the set flight, a second process under the micro-service architecture is used to analyze passenger quantities of the flight task of the set flight to be performed, a third process under the micro-service architecture is used to take an average value of the meal quantity proportions of various meal sets of past flight tasks of the set flight as a meal quantity proportion of various meal sets required for the flight task of the set flight to be performed, and the meal quantities corresponding to various meal sets required for the flight task of the set flight to be performed are obtained based on the meal quantity proportion of various meal sets required for the flight task of the set flight to be performed and the passenger quantities of the flight task of the set flight to be performed, so as to complete effective calculation of the meal quantities corresponding to various meal sets required for the flight task of the set flight to be performed.

[0041] In this way, the reliability and stability of the intelligent prediction result are further ensured through comprehensive and sufficient selection of the basic information.

[0042] Technical process three: using the full and sufficient selection of each item of basic information in technical process two as an AI quality traceability model for technical process design, to perform synchronous intelligent prediction of whether meal loading delay abnormal events will occur for the set flight on the day of the flight task and the responsible party number causing the meal loading delay abnormal events;

[0043] Specifically, when the intelligent predicted abnormal event identifier indicates that the various types of meals required for the set flight on the day of the flight task that has not yet been performed have meal loading delay abnormal events, the intelligent predicted responsible party number causing the meal loading delay abnormal events is the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the meal loading subject;

[0044] Conversely, when the intelligent predicted abnormal event identifier indicates that the various types of meals required for the set flight on the day of the flight task that has not yet been performed do not have meal loading delay abnormal events, the intelligent predicted responsible party number causing the meal loading delay abnormal events is a null character;

[0045] For example, since the various types of meals actually provided by the airline meal for each day of flight task performed for the set flight go through the entire process of airline meals of production, transportation, handover, and loading, the responsible party number can be one of the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, and the number corresponding to the meal loading subject;

[0046] Technical process four: determining whether the intelligent predicted responsible party number causing the meal loading delay abnormal events needs to be displayed in real time based on the intelligent prediction result of technical process three;

[0047] Specifically, when the intelligent predicted abnormal event identifier indicates that the various types of meals required for the set flight on the day of the flight task that has not yet been performed have meal loading delay abnormal events, the intelligent predicted responsible party number causing the meal loading delay abnormal events is displayed in real time, and the real-time display site can be the aircraft control room or the control room at the air traffic control center;

[0048] Therefore, the present application, for the various types of meals actually provided by the airline meal for each day of flight task performed for the set flight, goes through the entire process of airline meals of production, transportation, handover, and loading, and uses an AI quality traceability model to intelligently predict, based on the meal supplier information for the set flight, the past meal loading feedback data for the set flight, and the meal-related data for the set flight on the day of the flight task that has not yet been performed, whether meal loading delay abnormal events will occur for the set flight on the day of the flight task and the responsible party number causing the meal loading delay abnormal events, thereby providing more valuable reference information for the advance response and deployment of abnormal events of airline meals.

[0049] The key point of the present application is that the micro-service architecture is adopted to perform targeted acquisition of various basic information, a customized structure design of an AI quality traceability model, comprehensive and sufficient selection of various basic information, and targeted design of each learning action performed by a feedforward neural network.

[0050] In the following, the micro-service quality traceability system for aviation catering according to the present application will be described in detail in the form of an embodiment.

[0051] First embodiment

[0052] Figure 2 An internal structure diagram of a micro-service quality traceability system for aviation catering according to the first embodiment of the present application is shown.

[0053] As shown in Figure 2 The micro-service quality traceability system for aviation catering includes the following components:

[0054] A task analysis device is configured to analyze the number of meals corresponding to each type of meal required for the flight task to be performed on the day of the set flight by using the micro-service architecture;

[0055] For example, the number of meals corresponding to each type of meal required for the flight task to be performed on the day of the set flight can be analyzed by using the micro-service architecture;

[0056] A configuration acquisition device is configured to acquire the transportation mileage, the acquisition time length of the supply qualification, the acquisition time length of the latest qualified detection report, the number of employees, the production workshop floor area, the maximum cooking temperature, and the maximum cooking time of the catering supplier providing catering services for the set flight by using the micro-service architecture, as the configuration information of the catering supplier providing catering services for the set flight;

[0057] For example, the acquisition of the transportation mileage, the acquisition time length of the supply qualification, the acquisition time length of the latest qualified detection report, the number of employees, the production workshop floor area, the maximum cooking temperature, and the maximum cooking time of the catering supplier providing catering services for the set flight by using the micro-service architecture, as the configuration information of the catering supplier providing catering services for the set flight includes that the maximum cooking temperature and the maximum cooking time can be acquired by accessing the equipment log of the production workshop by using the micro-service architecture;

[0058] A network learning device is configured to perform each learning action on the feedforward neural network to obtain the feedforward neural network after each learning action is performed and output as an AI quality traceability model, and the number of learning actions is positively correlated with the maximum number of passengers of the set flight;

[0059] For example, when the aircraft model used by the flight is Boeing 737 MAX9, and the corresponding maximum number of passengers is 200, the number of learning actions performed by the feedforward neural network used is 600;

[0060] For example, when the aircraft model used by the flight is Boeing 777-200, and the corresponding maximum number of passengers is 300, the number of learning actions performed by the feedforward neural network used is 650;

[0061] For example, when the aircraft model used by the flight is Boeing 777-300, and the corresponding maximum number of passengers is 400, the number of learning actions performed by the feedforward neural network used is 700;

[0062] For example, when the aircraft model used by the flight is Airbus A380, and the corresponding maximum number of passengers is 500, the number of learning actions performed by the feedforward neural network used is 750, and so on.

[0063] The quality traceability device is connected with the task analysis device, the configuration collection device, and the network learning device, respectively, and is used to intelligently predict, based on an AI quality traceability model, whether there is a loading delay abnormal event for each type of meal required by the flight task to be performed by the flight on the same day, and the responsible party number causing the loading delay abnormal event, by using multiple pieces of meal loading feedback data corresponding to multiple flight tasks performed by the flight in the past, the number of each piece of meal corresponding to each type of meal required by the flight task to be performed by the flight on the same day, and each piece of configuration information of the meal supplier providing meal service for the flight.

[0064] Specifically, when the intelligently predicted abnormal event identifier indicates that there is a loading delay abnormal event for each type of meal required by the flight task to be performed by the flight on the same day, and the intelligently predicted responsible party number causing the loading delay abnormal event is one of the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, and the number corresponding to the loading subject.

[0065] The actual meal provided by the flight when performing each day of the flight task in the past has gone through the whole process of air meal, including production, transportation, handover, and loading.

[0066] The single meal loading feedback data corresponding to each day of the flight task in the past of the flight is the number of meals of each type actually provided by the flight when performing the flight task, the time consumed for completing production of the meals actually provided, the time consumed for completing transportation of the meals actually provided, the time consumed for completing handover of the meals actually provided, and the time consumed for completing loading of the meals actually provided.

[0067] In the case that the intelligent prediction of the abnormal event identifier indicates that the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been performed exist the loading delay abnormal event, and the intelligent prediction of the responsible party number causing the loading delay abnormal event is the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the loading subject.

[0068] For example, in the case that the intelligent prediction of the abnormal event identifier indicates that the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been performed exist the loading delay abnormal event, and the intelligent prediction of the responsible party number causing the loading delay abnormal event is the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the loading subject, the different numerical values with the same bit length are respectively used to represent the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the loading subject.

[0069] In the case that the intelligent prediction of the abnormal event identifier indicates that the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been performed do not exist the loading delay abnormal event, and the intelligent prediction of the responsible party number causing the loading delay abnormal event is a null character.

[0070] For example, in the case that the intelligent prediction of the abnormal event identifier indicates that the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been performed do not exist the loading delay abnormal event, and the intelligent prediction of the responsible party number causing the loading delay abnormal event is a null character, the null character is NULL.

[0071] In each learning action performed on the feedforward neural network, the known abnormal event identifier indicating whether the various types of meal sets actually provided by the flight task of the set flight performed on a certain day in the past exist the loading delay abnormal event and the responsible party number causing the loading delay abnormal event are taken as two input contents of the feedforward neural network, and the meal loading feedback data corresponding to the meal sets of the set flight performed on a certain day in the past, the meal quantity corresponding to the meal sets actually provided by the flight task of the set flight performed on a certain day in the past, and the configuration information of the meal supplier providing the meal service for the set flight are taken as multiple input contents of the feedforward neural network, so as to complete the learning action.

[0072] The AI quality traceability model is used to intelligently predict whether the meal sets required by the flight task to be performed by the set flight on the same day have a loading delay abnormal event and the responsible party number of the loading delay abnormal event based on the meal loading feedback data of the set flight corresponding to the meal sets of the flight tasks of multiple days, the meal set numbers corresponding to the meal sets required by the flight task to be performed by the set flight on the same day, and the configuration information of the meal suppliers providing meal services for the set flight. The number of days of the selected past days is positively correlated with the flight distance of the set flight.

[0073] For example, the number of days of the selected past days is positively correlated with the flight distance of the set flight, including: the flight distance of the set flight is 500 kilometers, the number of days of the selected past days is 10 days, the flight distance of the set flight is 600 kilometers, the number of days of the selected past days is 12 days, the flight distance of the set flight is 700 kilometers, the number of days of the selected past days is 14 days, the flight distance of the set flight is 800 kilometers, the number of days of the selected past days is 16 days, and so on.

[0074] Second embodiment

[0075] Figure 3 An internal structure diagram of an air catering-oriented micro-service quality traceability system according to the second embodiment of the present application is shown.

[0076] As shown in Figure 3 , compared with Figure 2 , the air catering-oriented micro-service quality traceability system further includes:

[0077] The encryption and chaining device is connected with the meal collection device, configured to receive the configuration information of the meal suppliers providing meal services for the set flight, and perform data encryption processing on the configuration information of the meal suppliers providing meal services for the set flight. The configuration information of the meal suppliers providing meal services for the set flight after data encryption processing is wirelessly transmitted to the blockchain monitoring node for meal task monitoring.

[0078] For example, the encryption and chaining device is connected with the meal collection device, configured to receive the configuration information of the meal suppliers providing meal services for the set flight, and perform data encryption processing on the configuration information of the meal suppliers providing meal services for the set flight. The configuration information of the meal suppliers providing meal services for the set flight after data encryption processing is wirelessly transmitted to the blockchain monitoring node for meal task monitoring. The wireless transmission is based on a time division duplex communication link.

[0079] Third embodiment

[0080] Figure 4An internal structure diagram of an air catering-oriented micro-service quality traceability system according to a third embodiment of the present application is shown.

[0081] As shown in Figure 4 , compared with Figure 3 , the air catering-oriented micro-service quality traceability system further comprises:

[0082] A satellite positioning device connected with the quality traceability device, configured to provide positioning service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively;

[0083] For example, the satellite positioning device is internally provided with a navigation positioning unit, a timing unit and a power supply unit, and the navigation positioning unit is configured to provide positioning service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively;

[0084] In the embodiment, the satellite positioning device connected with the quality traceability device, configured to provide positioning service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively includes: providing positioning service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively based on a GPS positioning system or a Beidou positioning system.

[0085] Fourth embodiment

[0086] Figure 5 An internal structure diagram of an air catering-oriented micro-service quality traceability system according to a fourth embodiment of the present application is shown.

[0087] As shown in Figure 5 , compared with Figure 4 , the air catering-oriented micro-service quality traceability system further comprises:

[0088] A timing server connected with the quality traceability device, configured to provide timing service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively;

[0089] In the embodiment, the timing server connected with the quality traceability device, configured to provide timing service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively includes: the timing server is internally provided with a quartz oscillation unit, configured to generate a reference clock pulse to provide timing service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively.

[0090] Specifically, the timing server is internally provided with a quartz oscillation unit, configured to generate a reference clock pulse to provide timing service for acquisition of the multiple sets of catering feedback data corresponding to the multiple flight tasks of the set flight respectively includes: the reference clock pulse is a square waveform.

[0091] Fifth embodiment

[0092] Figure 6 An internal structure diagram of an air catering-oriented micro-service quality traceability system according to a fifth embodiment of the present application is shown.

[0093] As Figure 6 shown, compared with Figure 5 , the air catering-oriented micro-service quality traceability system further comprises:

[0094] An instant display device connected with the quality traceability device, used for instantaneously displaying the number of the responsible party causing the boarding delay abnormal event when the intelligent-predicted abnormal event identification indicates that there is a boarding delay abnormal event for each type of meal required by the flight task of the day when the set flight has not been performed.

[0095] Specifically, the instant display device connected with the quality traceability device, used for instantaneously displaying the number of the responsible party causing the boarding delay abnormal event when the intelligent-predicted abnormal event identification indicates that there is a boarding delay abnormal event for each type of meal required by the flight task of the day when the set flight has not been performed can be implemented by selecting an LED display array or an LCD display array.

[0096] Next, the various embodiments of the present application will be further described.

[0097] Optionally, in the air catering-oriented micro-service quality traceability system in the above various embodiments:

[0098] The micro-service architecture is adopted to analyze the respective meal quantities corresponding to each type of meal required by the flight task of the day when the set flight has not been performed, including: a first process under the micro-service architecture is adopted to analyze the meal quantity proportion of each type of meal for the past multiple days of flight tasks of the set flight, a second process under the micro-service architecture is adopted to analyze the passenger quantity of the flight task of the day when the set flight has not been performed, and the respective meal quantities corresponding to each type of meal required by the flight task of the day when the set flight has not been performed are obtained based on the meal quantity proportion of each type of meal for the past multiple days of flight tasks of the set flight and the passenger quantity of the flight task of the day when the set flight has not been performed;

[0099] Wherein, obtaining the quantity of each meal corresponding to each set of meal packages required for the flight mission that has not yet been executed on the day of the set flight based on the ratio of the quantity of each set of meal packages for the flight missions of the set flight in the past multiple days and the number of passengers on the flight mission that has not yet been executed on the day of the set flight includes: taking the average of the ratio of the quantity of each meal packages for the flight missions of the set flight in the past multiple days as the ratio of the quantity of each meal packages required for the flight mission that has not yet been executed on the day of the set flight, and obtaining the quantity of each meal corresponding to each set of meal packages required for the flight mission that has not yet been executed on the day of the set flight based on the ratio of the quantity of each meal packages required for the flight mission that has not yet been executed on the day of the set flight and the number of passengers on the flight mission that has not yet been executed on the day of the set flight;

[0100] For example, if the ratio of the number of beef meal, chicken meal and vegetarian meal required for the flight mission of the day that has not yet been executed is set to 2:2:1, and the number of passengers on the flight mission of the day that has not yet been executed is set to 200, then the number of each corresponding meal of the beef meal, chicken meal and vegetarian meal required for the flight mission of the day that has not yet been executed is set to 80, 80 and 40 respectively.

[0101] In each of the above embodiments, optionally, in the microservice-based quality traceability system for airline catering:

[0102] Executing each learning action on the feedforward neural network to obtain a feedforward neural network after executing each learning action and outputting the feedforward neural network as the AI ​​quality traceability model, wherein the number of learning actions is positively correlated with the maximum passenger capacity of the set flight, including: using an information mapping formula to express the information mapping relationship of the positive correlation between the number of learning actions and the maximum passenger capacity of the set flight;

[0103] Specifically, a numerical simulation mode may be selected to complete the simulation and testing of the information mapping process using an information mapping formula to express the information mapping relationship of the number of learning actions and the maximum number of passengers on a set flight;

[0104] The information mapping relationship of using an information mapping formula to express the positive correlation between the number of learning actions and the maximum number of passengers on a set flight includes: in the information mapping formula, the maximum number of passengers on a set flight is used as input information of the information mapping formula;

[0105] And wherein, the information mapping relationship using the information mapping formula to express the positive correlation between the number of learning actions and the maximum passenger capacity of the set flight also includes: in the information mapping formula, the number of learning actions positively correlated with the maximum passenger capacity of the set flight is the output information of the information mapping formula.

[0106] And in each of the above embodiments, optionally, in the microservice-based quality traceability system for airline catering:

[0107] The AI quality traceability model is used to intelligently predict, based on the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the meal quantity corresponding to each type of meal required by the flight task to be performed by the set flight on the same day, and the configuration information of each meal provided by the meal supplier providing meal service for the set flight, whether each type of meal required by the flight task to be performed by the set flight on the same day has a loading delay abnormal event, and the responsible party number causing the loading delay abnormal event, and the method further comprises: inputting the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the meal quantity corresponding to each type of meal required by the flight task to be performed by the set flight on the same day, and the configuration information of each meal provided by the meal supplier providing meal service for the set flight into the AI quality traceability model in parallel;

[0108] For example, inputting the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the meal quantity corresponding to each type of meal required by the flight task to be performed by the set flight on the same day, and the configuration information of each meal provided by the meal supplier providing meal service for the set flight into the AI quality traceability model in parallel comprises: inputting the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the meal quantity corresponding to each type of meal required by the flight task to be performed by the set flight on the same day, and the configuration information of each meal provided by the meal supplier providing meal service for the set flight into the input port of the AI quality traceability model in parallel.

[0109] The AI quality traceability model is used to intelligently predict, based on the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the meal quantity corresponding to each type of meal required by the flight task to be performed by the set flight on the same day, and the configuration information of each meal provided by the meal supplier providing meal service for the set flight, whether each type of meal required by the flight task to be performed by the set flight on the same day has a loading delay abnormal event, and the responsible party number causing the loading delay abnormal event, and the method further comprises: executing the AI quality traceability model to obtain the abnormal event identifier of whether each type of meal required by the flight task to be performed by the set flight on the same day has a loading delay abnormal event and the responsible party number causing the loading delay abnormal event output by the AI quality traceability model.

[0110] The AI quality traceability model is executed to obtain an abnormal event identifier of whether there is a loading delay abnormal event of the types of meals required by the flight task of the set flight on the same day that has not been executed and a responsible party number causing the loading delay abnormal event output by the AI quality traceability model.

[0111] The AI quality traceability model is executed to obtain an abnormal event identifier of whether there is a loading delay abnormal event of the types of meals required by the flight task of the set flight on the same day that has not been executed and a responsible party number causing the loading delay abnormal event output by the AI quality traceability model.

[0112] The AI quality traceability model is executed to obtain an abnormal event identifier of whether there is a loading delay abnormal event of the types of meals required by the flight task of the set flight on the same day that has not been executed and a responsible party number causing the loading delay abnormal event output by the AI quality traceability model.

[0113] The AI quality traceability model is executed to obtain an abnormal event identifier of whether there is a loading delay abnormal event of the types of meals required by the flight task of the set flight on the same day that has not been executed and a responsible party number causing the loading delay abnormal event output by the AI quality traceability model.

[0114] The AI quality traceability model is input in parallel with the multiple meal loading feedback data corresponding to the past multi-day flight tasks of the set flight, the meal quantities corresponding to the various meal sets required by the current flight task of the set flight, and the configuration information of the meal suppliers providing meal services for the set flight after performing value normalization on the meal loading feedback data, the meal quantities, and the configuration information of the meal suppliers, and the second programmable logic device is used to input the meal loading feedback data, the meal quantities, and the configuration information of the meal suppliers into the AI quality traceability model in parallel.

[0115] Specifically, the first programmable logic device and the second programmable logic device can share the same parameter configuration interface and the same power supply.

[0116] 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 and the second programmable logic device are connected.

[0117] In addition, in the micro-service quality traceability system for aviation meals according to the present application:

[0118] The AI quality traceability model is input in parallel with the multiple meal loading feedback data corresponding to the past multi-day flight tasks of the set flight, the meal quantities corresponding to the various meal sets required by the current flight task of the set flight, and the configuration information of the meal suppliers providing meal services for the set flight after performing value normalization on the meal loading feedback data, the meal quantities, and the configuration information of the meal suppliers, and the second programmable logic device is used to input the meal loading feedback data, the meal quantities, and the configuration information of the meal suppliers into the AI quality traceability model in parallel.

[0119] For example, the MATLAB toolbox can be used to simulate and test the data mapping process of using the data mapping function to represent the positive correlation between the number of days and the flight distance of the set flight.

[0120] The data mapping function is used to represent the data mapping relationship between the number of days in the past and the flight distance of the set flight in a positive correlation, and the flight distance of the set flight is input data of the data mapping function.

[0121] The data mapping function is used to represent the data mapping relationship between the number of days in the past and the flight distance of the set flight in a positive correlation, and the flight distance of the set flight is input data of the data mapping function.

[0122] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present disclosure, but not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part 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 be covered in the scope of the claims and the specification of the present disclosure.

Claims

1. An air catering oriented micro-service based quality traceability system, characterized in that, The system comprises: a task analysis device configured to analyze, using a microservice architecture, the number of each type of meal corresponding to each meal set required for a flight task to be performed on the same day as a set flight; a configuration acquisition device configured to acquire, using a microservice architecture, the transport mileage, the time length for obtaining the supply qualification, the time length for obtaining the latest qualified detection report, the number of employees, the production workshop area, the maximum cooking temperature, and the maximum cooking time of a meal supplier providing meal services for the set flight as the configuration information of the meal supplier; 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 is performed and output as an AI quality traceability model, and the number of learning actions is positively correlated with the maximum number of passengers of the set flight; a quality traceability device connected with the task analysis device, the configuration acquisition device, and the network learning device, and configured to intelligently predict, using the AI quality traceability model, whether each type of meal set required for the flight task to be performed on the same day as the set flight exists a loading delay abnormal event and the responsible party number causing the loading delay abnormal event based on the multiple meal loading feedback data corresponding to the multiple flight tasks in the past days of the set flight, the number of each meal corresponding to each type of meal set required for the flight task to be performed on the same day as the set flight, and the configuration information of the meal supplier providing meal services for the set flight; wherein, when the set flight performs each flight task in the past days, the actual meal sets of each type provided by the set flight go through the whole process of aviation meals including production, transportation, handover, and loading; wherein, the single meal loading feedback data corresponding to each flight task in the past days of the set flight includes the number of meals of each type actually provided by the set flight when performing the flight task, the time length consumed for completing the production of the meal sets of each type actually provided, the time length consumed for completing the transportation of the meal sets of each type actually provided, the time length consumed for completing the handover of the meal sets of each type actually provided, and the time length consumed for completing the loading of the meal sets of each type actually provided; wherein, when the abnormal event identifier indicates that each type of meal set required for the flight task to be performed on the same day as the set flight exists a loading delay abnormal event, the responsible party number causing the loading delay abnormal event is the number corresponding to the production workshop of the meal supplier, the number corresponding to the transportation subject of the meal supplier, the number corresponding to the meal handover personnel, or the number corresponding to the loading subject; wherein, when the abnormal event identifier indicates that each type of meal set required for the flight task to be performed on the same day as the set flight does not exist a loading delay abnormal event, the responsible party number causing the loading delay abnormal event is an empty character.

2. The microservice quality traceability system for aviation meals according to claim 1, wherein: In each learning action performed on the feedforward neural network, the abnormal event identifier of whether there is a boarding delay abnormal event and the responsible party number causing the boarding delay abnormal event of each type of meal actually provided by the set flight on a past day are taken as two input contents of the feedforward neural network, and multiple meal loading feedback data corresponding to multiple past days before the past day of the set flight, the number of each meal corresponding to each type of meal actually provided by the set flight on the past day, and the configuration information of each meal service provider providing meal service for the set flight are taken as multiple input contents of the feedforward neural network, and the learning action is completed; Wherein, the AI quality traceability model is used to intelligently predict the abnormal event identifier of whether there is a boarding delay abnormal event and the responsible party number causing the boarding delay abnormal event of each type of meal required by the set flight on the day when the flight has not been performed based on the multiple meal loading feedback data corresponding to the multiple past days of the set flight, the number of each meal corresponding to each type of meal required by the set flight on the day when the flight has not been performed, and the configuration information of each meal service provider providing meal service for the set flight, including: the number of past days selected is positively correlated with the flight distance of the set flight.

3. The microservices-based quality traceability system for airline catering of claim 2, wherein, The system further comprises: The encryption chaining device is connected with the meal collection device, and is used to receive the configuration information of each meal service provider providing meal service for the set flight, and to perform data encryption processing on the configuration information of each meal service provider providing meal service for the set flight, and to wirelessly transmit the configuration information of each meal service provider providing meal service for the set flight after data encryption processing to the blockchain monitoring node for meal task monitoring.

4. The microservices-based quality traceability system for airline catering of claim 2, wherein, The system further comprises: The satellite positioning device is connected with the quality traceability device, and is used to provide positioning service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight; Wherein, the satellite positioning device, connected with the quality traceability device, is used to provide positioning service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight, including: providing positioning service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight based on the GPS positioning system or the Beidou positioning system.

5. The microservices-based quality traceability system for airline catering of claim 2, wherein, The system further comprises: The timing server device is connected with the quality traceability device, and is used to provide timing service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight; Wherein, the timing server device, connected with the quality traceability device, is used to provide timing service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight, including: the timing server device is internally provided with a quartz oscillation unit, which is used to generate a reference clock pulse to provide timing service for the acquisition of the multiple meal loading feedback data corresponding to the multiple past days of the set flight.

6. The microservices-based quality traceability system for airline catering of claim 2, wherein, The system further comprises: The instant display device, connected with the quality traceable device, is used for instant display of the intelligent predicted responsibility number of the abnormal event causing the installation delay abnormal event when the intelligent predicted abnormal event identification indicates that the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed exist installation delay abnormal events.

7. The micro-service oriented in-flight meal quality traceable system according to any one of claims 2-6, characterized in that: The micro-service architecture is adopted to analyze the respective meal quantities corresponding to the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed, including: a first process under the micro-service architecture is adopted to analyze the meal quantity proportions of the various types of meal sets of the flight task of the set flight in the past days, a second process under the micro-service architecture is adopted to analyze the passenger quantity of the flight task of the set flight on the day when the set flight has not been executed, and the respective meal quantities corresponding to the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed are obtained based on the meal quantity proportions of the various types of meal sets of the flight task of the set flight in the past days and the passenger quantity of the flight task of the set flight on the day when the set flight has not been executed; wherein, the respective meal quantities corresponding to the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed are obtained based on the meal quantity proportions of the various types of meal sets of the flight task of the set flight in the past days and the passenger quantity of the flight task of the set flight on the day when the set flight has not been executed, including: taking the average value of the meal quantity proportions of the various types of meal sets of the flight task of the set flight in the past days as the meal quantity proportions of the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed, and obtaining the respective meal quantities corresponding to the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed based on the meal quantity proportions of the various types of meal sets required by the flight task of the set flight on the day when the set flight has not been executed and the passenger quantity of the flight task of the set flight on the day when the set flight has not been executed.

8. The micro-service oriented in-flight meal quality traceable system according to any one of claims 2-6, characterized in that: The respective learning actions are performed on the feedforward neural network to obtain the feedforward neural network after the respective learning actions are performed and output as the AI quality traceable model, and the number of learning actions is positively correlated with the maximum passenger capacity of the set flight, including: an information mapping formula is adopted to represent the information mapping relationship between the number of learning actions and the maximum passenger capacity of the set flight; wherein, the information mapping relationship between the number of learning actions and the maximum passenger capacity of the set flight is represented by the information mapping formula, including: in the information mapping formula, the maximum passenger capacity of the set flight is input information of the information mapping formula; wherein, the information mapping relationship between the number of learning actions and the maximum passenger capacity of the set flight is represented by the information mapping formula, further including: in the information mapping formula, the number of learning actions positively correlated with the maximum passenger capacity of the set flight is output information of the information mapping formula.

9. The micro-service oriented in-flight meal quality traceable system according to any one of claims 2-6, characterized in that: The AI quality traceability model is used to intelligently predict the abnormal event identifier of whether the meal sets required by the flight task of the set flight on the day have the meal loading delay abnormal event and the responsible party number causing the meal loading delay abnormal event based on the meal loading feedback data of the meal sets corresponding to the flight tasks of the set flight on multiple days, the meal set numbers corresponding to the meal sets required by the flight task of the set flight on the day, and the configuration information of the meal suppliers providing meal services for the set flight. The AI quality traceability model is used to intelligently predict the abnormal event identifier of whether the meal sets required by the flight task of the set flight on the day have the meal loading delay abnormal event and the responsible party number causing the meal loading delay abnormal event based on the meal loading feedback data of the meal sets corresponding to the flight tasks of the set flight on multiple days, the meal set numbers corresponding to the meal sets required by the flight task of the set flight on the day, and the configuration information of the meal suppliers providing meal services for the set flight. The AI quality traceability model is used to intelligently predict the abnormal event identifier of whether the meal sets required by the flight task of the set flight on the day have the meal loading delay abnormal event and the responsible party number causing the meal loading delay abnormal event based on the meal loading feedback data of the meal sets corresponding to the flight tasks of the set flight on multiple days, the meal set numbers corresponding to the meal sets required by the flight task of the set flight on the day, and the configuration information of the meal suppliers providing meal services for the set flight. The AI quality traceability model is used to intelligently predict the abnormal event identifier of whether the meal sets required by the flight task of the set flight on the day have the meal loading delay abnormal event and the responsible party number causing the meal loading delay abnormal event based on the meal loading feedback data of the meal sets corresponding to the flight tasks of the set flight on multiple days, the meal set numbers corresponding to the meal sets required by the flight task of the set flight on the day, and the configuration information of the meal suppliers providing meal services for the set flight. The AI quality traceability model is used to intelligently predict the abnormal event identifier of whether the meal sets required by the flight task of the set flight on the day have the meal loading delay abnormal event and the responsible party number causing the meal loading delay abnormal event based on the meal loading feedback data of the meal sets corresponding to the flight tasks of the set flight on multiple days, the meal set numbers corresponding to the meal sets required by the flight task of the set flight on the day, and the configuration information of the meal suppliers providing meal services for the set flight. The AI quality traceability model is input in parallel after the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the multiple meal quantities corresponding to the different types of meal sets required by the current flight task not yet performed by the set flight, and the multiple configuration information of the meal suppliers providing meal services for the set flight are respectively subjected to numerical normalization processing, and the numerical normalization processing is hexadecimal numerical conversion processing. The AI quality traceability model is input in parallel after the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the multiple meal quantities corresponding to the different types of meal sets required by the current flight task not yet performed by the set flight, and the multiple configuration information of the meal suppliers providing meal services for the set flight are respectively subjected to numerical normalization processing, and the numerical normalization processing is hexadecimal numerical conversion processing. The AI quality traceability model is input in parallel after the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the multiple meal quantities corresponding to the different types of meal sets required by the current flight task not yet performed by the set flight, and the multiple configuration information of the meal suppliers providing meal services for the set flight are respectively subjected to numerical normalization processing, and the numerical normalization processing is hexadecimal numerical conversion processing. The AI quality traceability model is input in parallel after the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the multiple meal quantities corresponding to the different types of meal sets required by the current flight task not yet performed by the set flight, and the multiple configuration information of the meal suppliers providing meal services for the set flight are respectively subjected to numerical normalization processing, and the numerical normalization processing is hexadecimal numerical conversion processing. The AI quality traceability model is input in parallel after the multiple meal loading feedback data corresponding to the past multiple flight tasks of the set flight, the multiple meal quantities corresponding to the different types of meal sets required by the current flight task not yet performed by the set flight, and the multiple configuration information of the meal suppliers providing meal services for the set flight are respectively subjected to numerical normalization processing, and the numerical normalization processing is hexadecimal numerical conversion processing.

Images