Passenger baggage information prediction method and device

Abstract

A method and apparatus for predicting passenger checked baggage information is provided, which obtains departing passenger data and historical data of actual departing passenger checked baggage for a current flight, determines target rule data as the basis for predicting passenger checked baggage information for the current flight, and predicts the weight of departing passenger checked baggage for the current flight based on at least a part of the departing passenger data, historical data of actual departing passenger checked baggage for the current flight, and the target rule data, thereby performing weight and balance processing for the current flight. By automatically predicting the weight of departing passenger checked baggage for the current flight based on relevant data and rules, various disadvantages existing in existing artificial estimation methods can be effectively alleviated, and because the reference data as the basis for prediction is relatively comprehensive, the reference value of the predicted value of departing passenger checked baggage weight is improved and deviations in the prediction result due to individual differences are not caused, thereby avoiding risks and hidden dangers to production safety.

Description

[Technical Field]

[0001] The present disclosure relates to the technical field of air transportation, and more particularly to a method and apparatus for predicting passenger checked baggage information.

[0002] (CROSS-REFERENCE TO RELATED APPLICATIONS) This disclosure claims priority to a Chinese patent application filed with the China Patent Office on December 15, 2022, bearing application number 202211613120.X and entitled "Method and apparatus for predicting passenger checked baggage information and method thereof," the entire text of which is incorporated herein by reference. [Background technology]

[0003] Load control is an important part of flight takeoff, and the weight of checked baggage for departing flights is one of the core data points in load control operations. To obtain the actual checked baggage weight for a load-controlled flight, the actual checked baggage weight can be calculated cumulatively only after all passengers have checked in and checked their baggage. However, due to the actual load control process, the checked baggage weight for a flight must be obtained in advance. That is, this data must be obtained before passenger check-in procedures are completed, and even before passengers have checked in. Therefore, the checked baggage weight for load-controlled flights must be estimated in advance.

[0004] The existing solution for estimating checked baggage weight for load-controlled flights is for operators to directly estimate this weight based on their personal historical experience. This solution has the following drawbacks: Because operators estimate based solely on their own experience, the reference value is low, and the artificially generated estimates are often significantly different from the actual value, further posing risks and hidden dangers to production safety. Furthermore, the estimates generated by different operators are inconsistent and have large individual differences, similarly posing risks and hidden dangers to production safety. Summary of the Invention

[0005] In view of the above, the present disclosure provides a method and apparatus for predicting passenger checked baggage information, which overcomes a series of drawbacks existing in the traditional artificial estimation method by automatically determining the departing passenger checked baggage weight of the current flight based on the departing passenger data corresponding to the current flight, historical data of actual departing passenger checked baggage, and related regulation data.

[0006] The specific technical measures are as follows:

[0007] A method for predicting passenger checked baggage information, comprising: obtaining departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; determining target rule data on which to base predictions of passenger checked baggage information for the current flight; predicting a departing passenger checked baggage weight for the current flight based at least in part on the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and performing weight and balance processing for the current flight based on the predicted departing passenger checked baggage weight.

[0008] A passenger baggage information prediction device, a data acquisition module configured to acquire departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; a rule determination module configured to determine target rule data serving as a basis for predicting passenger checked baggage information for a current flight; an information prediction module configured to predict a departing passenger checked baggage weight for a current flight based at least in part on the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and to perform weight-and-balance processing for the current flight based on the departing passenger checked baggage weight.

[0009] A computer-readable medium having a computer program stored thereon, the computer program including program code for executing the method for predicting passenger checked baggage information provided by the present disclosure.

[0010] 1. A computer program product, comprising: a computer program embodied in a non-transitory computer-readable medium, the computer program including program code for executing a method for predicting passenger checked baggage information provided by the present disclosure.

[0011]

[0013] As can be seen from the above solutions, the method and apparatus for predicting passenger checked baggage information provided by the present disclosure obtains departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight, determines target rule data as the basis for predicting passenger checked baggage information for the current flight, predicts the weight of departing passenger checked baggage for the current flight based on at least a part of the departing passenger data, historical data of actual departing passenger checked baggage for the current flight, and the target rule data, and performs weight-and-balance processing for the current flight based on the predicted departing passenger checked baggage weight. By automatically predicting the weight of departing passenger checked baggage for the current flight based on relevant data and rules, the present disclosure can effectively alleviate various drawbacks of existing artificial estimation methods, and because the reference data as the basis for prediction is relatively comprehensive, the reference value of the predicted value of departing passenger checked baggage weight is improved, the predicted value is closer to the actual value, and deviations in the prediction results due to individual differences are not introduced, thereby avoiding risks and hidden dangers to production safety. [Brief explanation of the drawings]

[0012] These and other features, advantages, and aspects of each embodiment of the present disclosure will become more apparent with reference to the following specific embodiments in conjunction with the drawings. Identical or similar reference numerals represent identical or similar elements throughout the drawings. It should be understood that the drawings are schematic and that parts and elements are not necessarily drawn to scale. [Figure 1] 1 is a flowchart of a method for predicting passenger checked baggage information provided by the present disclosure. [Figure 2] FIG. 1 is a block diagram of the configuration of a passenger checked baggage estimation device for a flight with load control according to one application example provided by the present disclosure. [Figure 3] 4 is another flowchart of a method for predicting passenger checked baggage information provided by the present disclosure. [Figure 4] 1 is a flowchart of yet another method for predicting passenger checked baggage information provided by the present disclosure. [Figure 5] 1 is yet another flowchart of a method for predicting passenger checked baggage information provided by the present disclosure. [Figure 6] FIG. 3 is a schematic diagram showing the component relationships of the components included in the device according to FIG. 2 provided by the present disclosure. [Figure 7] FIG. 1 is a structural diagram of the passenger checked baggage information prediction device provided by the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the accompanying drawings show several embodiments of the present disclosure, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, it should be understood that these embodiments are provided to provide a clearer and more complete understanding of the present disclosure. It should also be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0014] As used herein, the term "comprises" and variations thereof are intended to be open inclusive, i.e., mean "including, but not limited to." The term "based on" means "based at least in part on." The term "in one embodiment" means "at least one embodiment." The term "in another embodiment" means "at least one other embodiment." The term "in some embodiments" means "at least some embodiments." Relevant definitions of other terms are provided below.

[0015] It should be noted that the concepts of "first", "second", etc. referred to in this disclosure are merely intended to distinguish different devices, modules or units, and do not limit the order or interdependence of functions performed by these devices, modules or units.

[0016] It should be noted that the modifiers "a" and "a plurality" referred to in this disclosure are intended to be exemplary rather than limiting, and those skilled in the art will understand that they should be understood as "one or more" unless the context clearly indicates otherwise.

[0017] The present disclosure provides a method, apparatus, computer readable medium and computer program product for predicting passenger checked baggage information.

[0018] Referring to the passenger checked baggage information prediction method shown in FIG. 1, the passenger checked baggage information prediction method provided in the present disclosure includes at least the following processing steps:

[0019] Step 101: Obtain the departing passenger data and the actual departing passenger checked baggage history data corresponding to the current flight.

[0020] Specifically, the departing passenger data of the current flight can be queried based on the flight information of the current flight.

[0021] Among these, flight information (FlightInfo) includes some or all of the following information, but is not limited to: airline, flight number, flight date, departure airport, arrival airport, aircraft registration number, aircraft cabin layout, weight unit, etc.

[0022] For example, a certain airline's multi-leg flight (1111): Beijing (PEK) - Shanghai (SHA) - Guangzhou (CAN) consists of two legs, Beijing-Shanghai and Shanghai-Guangzhou, and the corresponding flight information is as follows:

[0023] [Table 1]

[0024] Departing passenger information (PassengerInfo) includes some or all of the following information, but is not limited to: airline, flight number, flight date, departure airport, arrival airport, cabin class, number of booked passengers, number of checked-in passengers, etc. During the process of flight weight and balance processing, the number of booked passengers is certain information, while the number of checked-in passengers changes dynamically as passenger check-in progresses.

[0025] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the arrival airports for passengers include Shanghai (SHA) and Guangzhou (CAN), it is indicated that some passengers are heading from Beijing to Shanghai, and some passengers are heading from Beijing to Guangzhou, the cabin classes include Class J and Class Y, and the passenger information is as follows:

[0026] [Table 2]

[0027] Then, according to the required historical data query conditions, the historical data of the actual departing passenger checked baggage corresponding to the current flight can be retrieved.

[0028] The actual departure passenger checked baggage history data (BaggageHistory) may include, but is not limited to, some or all of the following information: airline, flight number, flight date, departure airport, arrival airport, actual number of passengers, actual weight of checked passenger baggage, predicted weight of checked passenger baggage, baggage weight per person, and prediction error.

[0029] Here, the above-mentioned airline, flight number, flight date, takeoff airport, and arrival airport correspond to the airline, flight number, flight date, takeoff airport, and arrival airport in the above-mentioned FlightInfo. The above-mentioned actual number of passengers is the number of checked-in passengers in the above-mentioned PassengerInfo collected after the flight was closed. The above-mentioned actual weight of checked passenger baggage is the total weight of checked baggage collected after the flight was closed. The above-mentioned predicted weight of checked passenger baggage is a weight value calculated by this device. The above-mentioned baggage weight per person = actual weight of checked passenger baggage / actual number of passengers. The above-mentioned prediction error = |Predicted weight of checked passenger baggage - actual weight of checked passenger baggage| / actual weight of checked passenger baggage.

[0030] For example, in the case of the above-mentioned flight xx 1111, if the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), and the historical data is as follows:

[0031] [Table 3]

[0032] Optionally, referring to FIG. 2, an application example of the method of the present disclosure is provided. In this example, an estimation device for passenger checked baggage for a flight that performs load control according to the method of the present disclosure is realized, which at least includes a departing passenger data collection component, a historical data extraction component for actual departing passenger checked baggage, an estimation rule data maintenance component, and a departing passenger checked baggage calculation component, and each component of the device can realize the processing process of the method of the present disclosure.

[0033] The functions of each component are as follows:

[0034] Departing passenger data collection component: Its main function is to collect departing passenger information in real time based on the input flight information.

[0035] Extraction component of historical data of actual departure passenger checked baggage: its main function is to extract relevant data based on the historical data of actual departure passenger checked baggage.

[0036] Inference Rule Data Maintenance Component: Its main function is to store and maintain the data related to the inference rules.

[0037] Departure passenger checked baggage calculation component: The main function is to calculate departure passenger checked baggage weight based on departure passenger data, historical data of actual departure passenger checked baggage, and estimation rule parameters.

[0038] In this example, the departing passenger data collection component can be specifically used to collect departing passenger information in real time based on the input flight information.

[0039] Step 102: Determine target rule data that is the basis for predicting passenger checked baggage information for the current flight.

[0040] In the present disclosure, a corresponding estimation rules data set is stored and maintained, the estimation rules data set including passenger checked baggage prediction rules and related parameter data.

[0041] For the example of FIG. 2 , specifically, the estimation rule data maintenance component can store and maintain data related to estimation rules to construct an estimation rule dataset, from which required rule data can be queried to predict the weight of departing passenger checked baggage.

[0042] Optionally, the inference rule related data stored and maintained by the inference rule data maintenance component includes, but is not limited to, the following data:

[0043] 11) Passenger checked baggage prediction rule (BaggagePredictRule): Includes airline, flight number, departure airport, arrival airport, and prediction rule. The relevant data for BaggagePredictRule is input by the user, and the prediction rule has two options: history data prediction (HistoryPredict) and time series prediction (ARIMAPredict). These two options indicate that prediction is made directly using the relevant data from BaggageHistory (historical data on actual departing passenger checked baggage), and that time series prediction is made using an ARIMA model (Autoregressive Integrated Moving Average model). These are two independent sets of prediction rules, and each set of prediction rules has its own independent prediction parameters.

[0044] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), as shown below.

[0045] [Table 4]

[0046] In the present disclosure, the above-mentioned time series forecasting rules include forecasting rules characterized by a pre-constructed ARIMA (Autoregressive Integrated Moving Average) model, which is obtained by performing model training based on time series data samples of departing passenger checked baggage weight.

[0047] 12) Static data of passenger checked baggage weight (StaticBaggageWeight): This data includes the airline, departure airport, arrival airport, cabin class, and per-person baggage weight, and is entered by the user. Predictions based on prediction rules are based on the assumption that there is sufficient historical data. If there is not enough historical data, predictions must be made directly using the data in StaticBaggageWeight (static data of passenger checked baggage weight).

[0048] For example, in the case of flight xx 1111 mentioned above, if the corresponding airline is xx and the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), and the cabin classes include Class J and Class Y. Specific examples include the following:

[0049] [Table 5]

[0050] 13) Static data of passenger checked baggage density (StaticBaggageDensity): Includes airlines and average baggage density, and data is input by the user.

[0051] For example, in the case of flight xx 1111 mentioned above, the corresponding airline is xx, and specific examples include the following:

[0052] [Table 6]

[0053] 14) Unit Load Device Static Data (ULD Configuration): Data is entered by the user, including the airline, aircraft registration number, whether it is a unit loaded aircraft, default unit load device type, default unit load device volume, and default unit load device tare weight.

[0054] For example, in the case of the above-mentioned flight xx 1111, if the corresponding airline is xx and the starting airport is Beijing (PEK), the aircraft registration number is B1234, and the following specific examples are given:

[0055] [Table 7]

[0056] 15) Legal Holiday Data (Holiday): This data includes dates and whether or not a holiday is a legal holiday. At the end of each year, holiday data for the next year must be entered. Users simply enter the date range of legal holidays, and the system will automatically generate holiday data for the following year.

[0057] For example, in the case of the above-mentioned flight xx 1111, the flight date is March 1, 2022, and the following specific examples are given:

[0058] [Table 8]

[0059] When HistoryPredict is selected as the prediction rule in BaggagePredictRule (passenger checked baggage prediction rule), history data prediction parameters (HistoryPredictParameters) should be included. The user inputs data including, but not limited to, the airline, flight number, departure airport, arrival airport, date type, 30-day history data percentage, 7-day history data percentage, 7-day history data percentage, and minimum validity period for history data. The above date types include workday (Monday-Friday, excluding statutory holidays), weekend (Saturday-Sunday, excluding statutory holidays), and holiday (statutory holidays). The input data must meet the following conditions: all date types must be included for each flight (with the same airline, flight number, departure airport, and arrival airport). The sum of the 30-day history data percentage, 7-day history data percentage, and 7-day history data percentage for each record must equal 100%. The minimum validity period for history data must be greater than 0 and less than or equal to 30.

[0060] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), and specific examples include the following:

[0061] [Table 9]

[0062] When ARIMAPredict is selected as the forecasting rule in BaggagePredictRule, the time series forecast parameters (ARIMAPredictParameters) should be included. These include the airline, flight number, departure airport, arrival airport, date type, daily forecast percentage, weekly forecast percentage, and the minimum number of days of validity for historical data. The above date types include workday (Monday to Friday, excluding statutory holidays), weekend (Saturday and Sunday, excluding statutory holidays), and holiday (statutory holidays). The input data must meet the following conditions: all date types must be included for each flight (with the same airline, flight number, departure airport, and arrival airport). The sum of the daily forecast percentage and weekly forecast percentage for each record must be 100%. The minimum number of days of validity for historical data must be greater than 15 and less than or equal to 30.

[0063] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), and specific examples include the following:

[0064] [Table 10]

[0065] Based on the stored and maintained estimation rule data set, in this step 102, specifically, the departure passenger checked baggage calculation component can determine target rule data from the estimation rule data set as the basis for predicting passenger checked baggage information for the current flight, and then predict the departure passenger checked baggage weight for the current flight based on the target rule data. This process can be further achieved as follows:

[0066] 21) Based on the flight information of the current flight, determine the target prediction rule to which the current flight corresponds in the preset estimation rule dataset.

[0067] Optionally, the departure passenger baggage calculation component obtains the target prediction rule by searching for a passenger baggage prediction rule (BaggagePredictRule) based on the airline, flight number, departure airport, and arrival airport in the current flight information (FlightInfo).

[0068] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include Shanghai (SHA) and Guangzhou (CAN), and the search results are as follows:

[0069] [Table 11]

[0070] 22) If the target prediction rule is a historical data prediction rule in the passenger checked baggage prediction rule, determine whether the historical data prediction condition is met. If YES, determine that the target rule data includes the historical data prediction rule and the rule parameters corresponding to the rule in the estimation rule dataset; if NO, determine that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset.

[0071] For example, if the prediction rule is a history data prediction rule HistoryPredict, the following process can be followed to determine whether the history data prediction condition is met, and then determine the corresponding target rule data if it is met or not.

[0072] 2.1 Obtaining effective days (effectiveDays): Based on the airline, flight number, departure airport, arrival airport, and [flight date-30, flight date-1] in the current flight information (FlightInfo), extract the effective days from the historical data extraction component of actual departing passenger checked baggage described above.

[0073] 2.2 Get date type (dateType): Search for Holiday based on the flight date in the current flight information (FlightInfo) to determine whether it is a Holiday, and if not, determine whether it is a workday or weekend.

[0074] 2.3 Obtaining the minimum valid data days (validDataMin): Obtain the minimum valid data days by searching HistoryPredictParameters based on the airline, flight number, departure airport, arrival airport, and date type (dateType) in the current flight information (FlightInfo).

[0075] 2.4 If effectiveDays≧validDataMin, perform prediction based on historical data, in other words, determine that in this case the target rule data includes the historical data prediction rule and the rule parameters corresponding to the rule in the estimation rule dataset; otherwise, perform prediction based on static data of passenger checked baggage weight (StaticBaggageWeight), in other words, determine that in this case the target rule data includes the static data of passenger checked baggage weight in the estimation rule dataset.

[0076] For example, in the case of the above-mentioned flight xx 1111, if the departure airport at this time is Beijing (PEK), the prediction rule HistoryPredict is satisfied when the baggage arrival airport is SHA, and the next process is executed.

[0077] Obtaining the number of effective days: As a result of searching historical data based on xx, 1111, PEK, SHA, 2022 / 1 / 30-2022 / 2 / 28, the historical data that matches the conditions is as follows, and as shown in the table below, a total of 2 records are searched, so effectiveDays=2.

[0078] [Table 12]

[0079] Obtaining the date type: Searching for Holiday on the flight date of March 1, 2022 does not result in holiday, and after further searching, we finally get dateType=workday because March 1, 2022 is a Tuesday.

[0080] Obtaining the minimum number of days valid for historical data: The result of searching HistoryPredictParameters based on xx, 1111, PEK, SHA, and workday is as follows, and validDataMin=1.

[0081] [Table 13]

[0082] Since effectiveDays=2, validDataMin=1, and effectiveDays>validDataMin, it can be determined that prediction is based on historical data, and accordingly, the target rule data includes the historical data prediction rule and the rule parameters corresponding to the rule in the estimated rule dataset.

[0083] 23) If the target prediction rule is a time series prediction rule in the passenger checked baggage prediction rule, determine whether the time series prediction condition is met. If YES, determine that the target rule parameters include the time series prediction rule and the rule parameters corresponding to the rule in the estimation rule dataset; if NO, determine that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset.

[0084] For example, if the prediction rule is the time series prediction rule ARIMAPredict, the following process can be used to determine whether the time series prediction conditions are met, and then determine the corresponding target rule data if they are met or not.

[0085] 3.1 Obtaining the predicted effective by day: Based on the airline, flight number, departure airport, arrival airport, and [flight date -30, flight date -1] in the current flight information (FlightInfo), extract the effective by day from the historical data extraction component of the actual departing passenger checked baggage mentioned above.

[0086] 3.2 Obtaining the predicted effective days per week (effectiveByWeek): Based on the airline, flight number, departure airport, arrival airport, and flight date in the current flight information (FlightInfo), extract the effective days from the historical data extraction component of actual departing passenger checked baggage described above based on the corresponding dates of the same 30 weeks prior to the flight date.

[0087] 3.3 Get date type (dateType): Search for Holiday based on the flight date in the current flight information (FlightInfo) to determine whether it is a holiday, and if not, determine whether it is a workday or weekend.

[0088] 3.4 Obtaining the minimum valid data number of days (validDataMin) for historical data: Obtain the minimum valid data number of days for historical data by searching ARIMAPredictParameters based on the airline, flight number, departure airport, arrival airport, and date type (dateType) in the current flight information (FlightInfo).

[0089] 3.5 If effectiveByDay≧validData and effectiveByWeek≧validData, perform prediction based on time series, in other words, determine that in this case the target rule data includes a time series prediction rule and the rule parameters corresponding to the rule in the estimation rule dataset. Otherwise, perform prediction based on static data of passenger checked baggage weight (StaticBaggageWeight), in other words, determine that in this case the target rule data includes the static data of passenger checked baggage weight in the estimation rule dataset.

[0090] For example, in the case of the above-mentioned flight xx 1111, if the departure airport at this time is Beijing (PEK), and the baggage arrival airport is CAN, the prediction rule ARIMAPredict is satisfied, and the next process is executed.

[0091] Obtaining the predicted number of effective days in daily units: When searching historical data based on xx, 1111, PEK, SHA, 2022 / 1 / 30-2022 / 2 / 28, the historical data that matches the conditions is as follows. As shown in the table below, a total of 2 records are searched, so effectiveByDay=2.

[0092] [Table 14]

[0093] Obtaining the predicted number of effective days in one week: xx, 1111, PEK, CAN, When searching historical data based on {2021 / 8 / 3,2021 / 8 / 10,...2022 / 2 / 15,2022 / 2 / 22}, no historical data matching the conditions was found, so effectiveByWeek=0.

[0094] Date type acquisition: As a result of searching for Holiday with the flight date of March 1, 2022, it is not a holiday. Then, as a result of continuous judgment, since March 1, 2022 is a Tuesday, finally dateType = workday is obtained.

[0095] Acquisition of the minimum value of the valid days of historical data: The results of searching for ARIMAPredictParameters based on xx, 1111, PEK, CAN, and workday are as follows, and validDataMin = 20.

[0096]

Table 15

[0097] Since effectiveByDay = 2, effectiveByWeek = 0, validDataMin = 20, effectiveByDay < validDataMin, and effectiveByWeek < validDataMin, prediction is performed based on the static data of the passenger checked baggage weight (StaticBaggageWeight), and accordingly, it can be determined that the target rule data includes the static data of the passenger checked baggage weight in the estimated rule dataset.

[0098] Step 103: Predict the departure passenger checked baggage weight of the current flight based on at least a part of the departure passenger data, the historical data of the actual departure passenger checked baggage, and the target rule data, and perform weight and balance processing on the current flight based on the predicted departure passenger checked baggage weight.

[0099] After that, further predict the departure passenger checked baggage weight for the current flight based on at least a part of the departure passenger data, the historical data of the actual departure passenger checked baggage, and the target rule data corresponding to the current flight. Specifically, the predicted value is the total weight of the departure passenger checked baggage of the predicted current flight.

[0100] This process can be further accomplished as follows:

[0101] 31) If the target rule data includes the historical data prediction rule and related rule parameters, extract historical parameter data required by the historical data prediction rule from the historical data of actual departing passenger checked baggage, and predict the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical parameter data, the historical data prediction rule and its rule parameters.

[0102] Here, referring to the example of Figure 2, specifically, the historical data extraction component of actual departing passenger checked baggage can extract historical parameter data required by the historical data prediction rule from the historical data of actual departing passenger checked baggage corresponding to the current flight, thereby achieving the extraction of required historical parameter data, including but not limited to:

[0103] Average baggage weight per person for 30 days (avgWeight30): Based on the airline, flight number, departure airport, arrival airport, [flight date -30, flight date -1] in the current flight information (FlightInfo), the actual departure passenger checked baggage history data extraction component extracts the average baggage weight per person.

[0104] Effective date of 7-day historical data (effective7): Based on the airline, flight number, departure airport, arrival airport, and [flight date-7, flight date-1] in the current flight information (FlightInfo), the effective date is extracted using the historical data extraction component for actual departing passenger checked baggage.

[0105] Average baggage weight per person for 7 days (avgWeight7): Based on the airline, flight number, departure airport, arrival airport, [flight date -7, flight date -1] in the current flight information (FlightInfo), the average baggage weight per person is extracted using the actual departure passenger checked baggage history data extraction component.

[0106] Effective date of historical data 7 days ago (effectiveAt7): Based on the airline, flight number, departure airport, arrival airport, and flight date-7 in the current flight information (FlightInfo), the effective date is extracted by the historical data extraction component of the actual departing passenger checked baggage.

[0107] Average baggage weight per person for 7 days prior (avgWeightAt7): Based on the airline, flight number, departure airport, arrival airport, and flight date-7 in the current flight information (FlightInfo), the actual departure passenger checked baggage history data extraction component extracts the average baggage weight per person.

[0108] In addition, for predicting the departure passenger checked baggage weight of the current flight in this method, it is also necessary to obtain relevant rule parameters of the historical data prediction rule from the estimation rule dataset, including but not limited to:

[0109] Historical data prediction parameters: By searching HistoryPredictParameters based on the airline, flight number, departure airport, arrival airport, and date type (dateType) in the current flight information (FlightInfo), the percentage of 30-day historical data (percentage30), the percentage of 7-day historical data (percentage7), and the percentage of 7-day-ago historical data (percentage At7) are obtained.

[0110] Furthermore, the number of booked passengers (bookNum) in the departing passenger information for the current flight is obtained: based on the airline, flight number, flight date, departure airport, and arrival airport in the current flight information (FlightInfo), records that match the conditions are searched for in the departing passenger information (PassengerInfo), and the number of booked passengers in all records is added up.

[0111] Based on this, the departure passenger checked baggage calculation component can calculate the departure passenger checked baggage weight bagEstWeight of the current flight based on the acquired various data according to the historical data prediction rule, thereby achieving the prediction of the departure passenger checked baggage weight. An exemplary prediction process is as follows:

[0112] If effective7=0, bagEstWeight=avgWeight30×bookNum.

[0113] If effective7>0 and effectiveAt7=0, bagEstWeight=(avgWeight30×percentage30+avgWeight7×percentage7) / (percentage30+percentage7)×bookNum.

[0114] If effective7>0 and effectiveAt7>0, bagEstWeight=(avgWeight30×percentage30+avgWeight7×percentage7+avgWeightAt7×percentageAt7)×bookNum.

[0115] For example, for the above flight xx 1111, if the departure airport is Beijing (PEK) and the arrival airport is SHA, the passenger checked baggage weight (bagEstWeight) needs to be calculated based on historical data. In other words, the departure passenger checked baggage weight for the current flight is predicted based on historical data prediction rules. The process is as follows:

[0116] Obtaining the average baggage weight per person (avgWeight30) of 30-day historical data: Searching historical data based on xx, 1111, PEK, SHA, 2022 / 1 / 30-2022 / 2 / 28, the historical data that matches the conditions is as follows, therefore, avgWeight30=(10.77+10.71) / 2=10.74.

[0117] [Table 16]

[0118] Obtaining the number of effective days (effective7) of 7-day historical data: As a result of searching historical data based on xx, 1111, PEK, SHA, 2022 / 2 / 22-2022 / 2 / 28, the historical data that matches the conditions is the same as that in 1), so effective7 = 2.

[0119] Obtaining the average baggage weight per person (avgWeight7) of 7-day historical data: Searching historical data based on xx, 1111, PEK, SHA, 2022 / 2 / 22-2022 / 2 / 28, the historical data that matches the conditions is the same as that in 1), therefore avgWeight7 = (10.77 + 10.71) / 2 = 10.74.

[0120] Obtaining the number of valid days (effectiveAt7) of historical data 7 days ago: When searching historical data based on xx, 1111, PEK, SHA, 2022 / 2 / 22, no historical data matching the conditions was found, so effectiveAt7 = 0.

[0121] Obtaining the average baggage weight per person (avgWeightAt7) for historical data from 7 days ago: When searching historical data based on xx, 1111, PEK, SHA, 2022 / 2 / 22, no historical data matching the conditions was found, so there is no value for avgWeightAt7.

[0122] Obtaining historical data prediction parameters: Searching HistoryPredictParameters based on xx, 1111, PEK, SHA, workday results in the following records, therefore percentage30=40%, percentage7=40%, percentage At7=20%.

[0123] [Table 17]

[0124] Obtaining the number of reservations (bookNum): Searching PassengerInfo based on xx, 1111, 2022 / 3 / 1, PEK, SHA results in the following record, therefore bookNum=3+88=91.

[0125] [Table 18]

[0126] Calculating bagEstWeight: Since effective7 = 2, if effective7 > 0 and effectiveAt7 = 0, bagEstWeight = (avgWeight30 × percentage30 + avgWeight7 × percentage7) / (percentage30 + percentage7) × bookNum = (10.74 × 40% + 10.74 × 40%) / (40% + 40%) × 91 = 977.34.

[0127] 32) If the target rule data includes the time series prediction rule and its rule parameters, extract historical time series parameter data required for the time series prediction rule from the historical data of actual departing passenger checked baggage, and predict the departing passenger checked baggage weight of the current flight based on the departing passenger data, historical time series parameter data, the time series prediction rule and its rule parameters.

[0128] Here, for the example of FIG. 2, the method 32) specifically uses the historical data extraction component of actual departing passenger checked baggage to extract historical time series parameter data required for the time series prediction rule from the historical data of actual departing passenger checked baggage corresponding to the current flight; and if the historical time series parameter data is missing, the time series is complemented by linear interpolation, which includes but is not limited to:

[0129] Obtaining the time series (timeSeriesByDay) of predicted baggage weight per person on a daily basis: Based on the airline, flight number, departure airport, arrival airport, and [flight date -30, flight date -1] in the current flight information (FlightInfo), extract the time series of baggage weight per person from the above-mentioned component extracting historical data of actual departing passenger checked baggage. Then, the time series is completed by linear interpolation. If there is missing data at the beginning or end of the time series, the valid data from the nearest date is used directly.

[0130] For example, the extracted time series is as follows, and data from 2020 / 1 / 1 to 2020 / 1 / 6 needs to be obtained. However, the database only has data for two days, 2020 / 1 / 2 and 2020 / 1 / 5. In this case, other data needs to be supplemented.

[0131] [Table 19]

[0132] First, we fill in the missing dates to get the following data:

[0133] [Table 20]

[0134] Next, the missing data at the beginning and end is supplemented, and since Value1 is the first data and the closest valid data is the data for 2020 / 1 / 2, Value1 = 15, and similarly, Value4 = 13. The data with the first and last data supplemented is as follows:

[0135] [Table 21]

[0136] Finally, the missing data is interpolated using linear interpolation to calculate Value2 as follows: (2020 / 1 / 5-2020 / 1 / 3) / (2020 / 1 / 3-2020 / 1 / 2)=(13-Value2) / (Value2-15), or 2 / 1=(13-Value2) / (Value2-15). The resulting value is Value2=43 / 3=14.33, and similarly, Value3=41 / 3=13.67. The final time series with the interpolated data is as follows:

[0137] [Table 22]

[0138] Obtaining the time series (timeSeriesByWeek) of predicted baggage weight per person on a weekly basis: Based on the airline, flight number, departure airport, arrival airport, and 30 dates corresponding to the same week prior to the flight date in the current flight information (FlightInfo), the time series of baggage weight per person is extracted from the above-mentioned component extracting historical data of actual departing passenger checked baggage. The time series is then completed using linear interpolation. If there is missing data at the beginning or end of the time series, the valid data from the closest date is used directly.

[0139] For example, the extracted time series is as follows, and the data to be obtained is {2022 / 3 / 1, 2022 / 3 / 8, 2022 / 3 / 15, 2022 / 3 / 22, 2022 / 3 / 29}. However, the database only has data for two dates, 2022 / 3 / 15 and 2022 / 3 / 29, so in this case, other data must be added.

[0140] [Table 23]

[0141] By supplementing the example of daily forecasts given above, the following data is obtained:

[0142] [Table 24]

[0143] Besides, for predicting the departure passenger checked baggage weight of the current flight in this method, it is also necessary to obtain the relevant rule parameters of the time series prediction rule from the estimation rule dataset, including but not limited to:

[0144] Obtaining time series forecast parameters: By searching ARIMAPredictParameters based on the airline, flight number, departure airport, arrival airport, and date type (dateType) in the current flight information (FlightInfo), the percentage predicted by day (percentageByDay) and the percentage predicted by week (percentageByWeek) are obtained.

[0145] Furthermore, the number of reservations in the departing passenger information for the current flight is obtained: based on the airline, flight number, flight date, departure airport, and passenger arrival airport in the current flight information (FlightInfo), records that match the conditions are searched for in the departing passenger information (PassengerInfo), and the number of reservations in all records is added up.

[0146] Based on this, the departure passenger checked baggage calculation component can calculate the departure passenger checked baggage weight bagEstWeight of the current flight based on the various acquired data according to the time series prediction rules, thereby achieving the prediction of the departure passenger checked baggage weight. An exemplary prediction process is as follows:

[0147] Calculation of ARIMA model parameters P1, D1, Q1 for daily forecasting: If the value range of D1 is 1, 2, the value range of P1 is 1-5, and the value range of Q1 is 1-5, traversal of all values ​​of P1, D1, Q1 is carried out, and based on the data of the first 25 days in timeSeriesByDay and the corresponding model parameters P1, D1, Q1, it is introduced into the ARIMA model to predict the passenger checked baggage weight for the next 5 days, and by comparing it with the actual value, it is possible to find the group consisting of P1, D1, Q1 that minimizes the residual sum of squares.

[0148] A simple example is the following time series:

[0149] [Table 25]

[0150] Suppose D1=1, P1 has a value range of 2, 3, and Q1 has a value range of 1, 2. We traverse all values ​​of P1, D1, and Q1, and based on the first three values ​​in the example time series and the corresponding model parameters P1, D1, and Q1, we feed them into an ARIMA model to forecast the next two days' data, and the results are as follows:

[0151] [Table 26]

[0152] The results of calculating the sum of squares of the prediction residuals corresponding to each group consisting of P1, D1, and Q1 are as follows. When D1=1, P1=3, and Q1=1, the sum of squares of the prediction residuals is smallest, so it can be seen that D1=1, P1=3, and Q1=1 are ultimately determined.

[0153] [Table 27]

[0154] Calculating ARIMA model parameters P2, D2, and Q2 for weekly forecasting: If the value range of D2 is 1, 2, the value range of P2 is 1 to 5, and the value range of Q2 is 1 to 5, traverse all values ​​of P2, D2, and Q2, and based on the data for the first 25 days in timeSeriesByWeek and the corresponding model parameters P2, D2, and Q2, feed them into the ARIMA model to predict the passenger checked baggage weight for the next 5 days, and then compare it with the actual value to find the group consisting of P2, D2, and Q2 that minimizes the sum of squared residuals.

[0155] Obtaining the predicted daily baggage weight per person (avgWeightByDay): Based on the data in timeSeriesByDay and the corresponding model parameters P1, D1, Q1, we feed it into an ARIMA model to predict the baggage weight per person for the current flight.

[0156] Obtaining the predicted weekly baggage weight per person (avgWeightByWeek): Based on the data in timeSeriesByWeek and the corresponding model parameters P2, D2, Q2, we feed it into an ARIMA model to predict the baggage weight per person for the current flight.

[0157] Calculating bagEstWeight based on time series forecasting rules: bagEstWeight = (avgWeightByDay × percentageByDay + avgWeightByWeek × percentageByWeek) × bookNum.

[0158] 33) If the target rule data includes static data of the passenger checked baggage weight, predict the departing passenger checked baggage weight of the current flight based on the departing passenger data and the static data of the passenger checked baggage weight.

[0159] In this method, optionally obtaining static data of required passenger checked baggage weight and departing passenger data includes, but is not limited to:

[0160] Obtaining per-person baggage weight (avgWeight) for different cabin classes: Based on the airline, departure airport, and arrival airport in the current flight information (FlightInfo), search for static data (StaticBaggageWeight) for passenger checked baggage weight to obtain the corresponding cabin class and per-person baggage weight.

[0161] Obtaining the number of booked passengers (bookNum) for different cabin classes: Based on the airline, flight number, flight date, takeoff airport, and passenger arrival airport in the current flight information (FlightInfo), search for the corresponding cabin class and number of booked passengers from the departing passenger information (PassengerInfo).

[0162] Based on this, the departure passenger checked baggage calculation component calculates the departure passenger checked baggage weight bagEstWeight of the current flight based on the acquired static data of the number of departure passengers and the weight of passenger checked baggage, thereby achieving the prediction of the departure passenger checked baggage weight, as follows:

[0163] Calculating bagEstWeight: Calculate the sum of avgWeight x bookNum for all cabins of the same class.

[0164] For example, for the above flight xx 1111, if the departure airport is Beijing (PEK) and the arrival airport is CAN, the weight of the checked baggage (bagEstWeight) needs to be calculated based on the static data of the checked baggage weight. The process is as follows:

[0165] Get the per-person baggage weight (avgWeight) for different cabin classes. Searching for StaticBaggageWeight based on xx, PEK, and CAN yields the following records:

[0166] [Table 28]

[0167] Obtaining the number of reservations (bookNum) for different cabin classes: Searching based on xx, 1111, 2022 / 3 / 1, PEK, and CAN yields the following records.

[0168] [Table 29]

[0169] Calculating bagEstWeight: bagEstWeight = 20 x 4 + 16 x 66 = 1136.

[0170]

[0013] As can be seen from the above technical solutions, the method for predicting passenger checked baggage information provided in the present disclosure obtains departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight, determines target rule data as the basis for predicting passenger checked baggage information for the current flight, predicts the weight of departing passenger checked baggage for the current flight based on at least a part of the departing passenger data, historical data of actual departing passenger checked baggage for the current flight, and the target rule data, and performs weight-and-balance processing for the current flight based on the predicted departing passenger checked baggage weight. By automatically predicting the weight of departing passenger checked baggage for the current flight based on relevant data and rules, the present disclosure can effectively alleviate various disadvantages existing in existing artificial estimation means, and because the reference data as the basis for prediction is relatively comprehensive, the reference value of the predicted value of departing passenger checked baggage weight is improved, the predicted value is closer to the actual value, and there is no deviation in the prediction result due to individual differences, thereby avoiding risks and hidden dangers to production safety.

[0171] In one embodiment, optionally, referring to the flowchart of the passenger checked baggage information prediction method shown in FIG. 3, the passenger checked baggage information prediction method provided by the present disclosure may further include the following steps:

[0172] Step 104: Determine the total weight of the departing passenger checked baggage and unit load device for the current flight based on the predicted departing passenger checked baggage weight.

[0173] Wherein, if the current flight is a unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the sum of the departing passenger checked baggage weight and the unit load device weight; whereas, if the current flight is a non-unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the departing passenger checked baggage weight.

[0174] Alternatively, the static data of the unit load device (ULDConfiguration) can be searched based on the airline and aircraft registration number in the flight information (FlightInfo) corresponding to the current flight to determine whether the current flight is a unit loaded aircraft. If the current flight is a unit loaded aircraft, the weight of the unit load device (uldEstWeight) also needs to be calculated, and the total weight of the departure passenger checked baggage and the unit load device is calculated based on the predicted departure passenger checked baggage weight and the weight of the unit load device, i.e., totalEstWeight=bagEstWeight+uldEstWeight. On the other hand, if the current flight is a non-unit loaded aircraft, the total weight of the departure passenger checked baggage and the unit load device is the departure passenger checked baggage weight, i.e., totalEstWeight=bagEstWeight.

[0175] For example, in the case of the above-mentioned flight xx 1111, the corresponding airline is xx, the departure airport is Beijing (PEK), the aircraft registration number is B1234, and by searching ULDConfiguration based on xx and B1234, the following record is obtained. Since the aircraft of the flight is a unit load aircraft, the weight of the unit load device needs to be calculated additionally.

[0176] [Table 30]

[0177] Here, an exemplary calculation process for the unit load device weight (uldEstWeight) is as follows:

[0178] Obtaining passenger checked baggage density (baggageDensity): Based on the airline currently in flight information (FlightInfo), the corresponding average baggage density is obtained by searching static data (StaticBaggageDensity) for passenger checked baggage density.

[0179] Obtaining unit load device volume (uldPerVolumn) and weight (uldPerWeight): Obtain the default unit load device volume and default unit load device weight by searching the static data (ULDConfiguration) of the unit load device based on the airline and aircraft registration number in the current flight information (FlightInfo).

[0180] Calculate the number of required unit load devices (uldNum): uldNum = (bagEstWeight / baggageDensity) / uldPerVolumn, and round up the result to the nearest integer.

[0181] Calculate the weight of the unit load device (uldEstWeight): uldEstWeight = uldNum x uldPerWeight.

[0182] In this embodiment, by determining the total weight of the departing passenger checked baggage and unit load device of the current flight, a data basis can be provided for the load control of the current flight; and when determining the total weight of the departing passenger checked baggage and unit load device, the weight of the departing passenger checked baggage of the current flight is automatically predicted based on relevant data and rules, so that the reference value of the predicted value of the departing passenger checked baggage weight is improved, and accordingly the reference value of the total weight of the departing passenger checked baggage and unit load device is also improved, so that the predicted value is closer to the actual value, and risks and hidden dangers to production safety are avoided.

[0183] In one embodiment, optionally, referring to the flowchart of the passenger checked baggage information prediction method shown in FIG. 4, the passenger checked baggage information prediction method provided by the present disclosure may further include the following steps:

[0184] Step 105: Obtain the actual departing passenger checked baggage data of the current flight, and update and store the data obtained after the current flight is closed into the historical data of the actual departing passenger checked baggage of the current flight.

[0185] 2, the load control flight passenger checked baggage estimation device realized by the method of the present disclosure can add an actual departure passenger checked baggage data processing combo network, as shown in FIG. 2, which can collect passenger checked baggage data in real time and store the related data in the actual departure passenger checked baggage history data after the flight is closed.

[0186] For example, if the current flight is xx 1111 and the date is 2022 / 3 / 1, after the flight is closed, the actual departing passenger checked baggage data for the current flight date 2022 / 3 / 1 is updated in BaggageHistory, and the updated BaggageHistory data is as follows:

[0187] [Table 31]

[0188] In this embodiment, the actual departing passenger checked baggage data of the current flight is obtained, and the data obtained after the current flight is closed is updated and stored as the historical data of the actual departing passenger checked baggage of the current flight, thereby realizing the chronological updating of the historical data of the actual departing passenger checked baggage corresponding to the current flight, and thereby providing support for the historical data of passenger checked baggage information for the flight in the future.

[0189] In one embodiment, optionally, referring to the flowchart of the passenger checked baggage information prediction method shown in FIG. 5, the passenger checked baggage information prediction method provided by the present disclosure may further include the following steps:

[0190] Step 106: Determine the deviation of the predicted value of the departing passenger checked baggage weight for the current flight from the actual value.

[0191] Step 107: If the deviation reaches a preset threshold, perform an alarm process, adjust the corresponding rule parameters in the estimation rule dataset based on the alarm process, and predict the departure passenger checked baggage weight of the current flight based on the adjusted rule parameters at a subsequent time.

[0192] 2, a real-time alarm component can be added to the load control flight passenger checked baggage estimation device implemented by the method of the present disclosure, as shown in FIG. 2. By executing the process of this embodiment using the combo network, an alarm can be generated in real time when the deviation of the predicted value of the departure passenger checked baggage weight from the actual value reaches a preset threshold.

[0193] Referring to FIG. 6, a component relationship diagram of each component in the load controlled flight passenger checked baggage estimation device according to FIG. 2 is provided.

[0194] The real-time warning component sets prewarning parameters (PrewarningParameters), including but not limited to airline, flight number, departure airport, arrival airport, number of days, maximum average error, and previous warning date. The previous warning date is automatically generated by the system (each time a record is generated, the current date is automatically written into the previous warning date, and then the corresponding warning date is written as long as a warning occurs for the corresponding flight), and the remaining data is input by the user.

[0195] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include SHA and CAN, and specific examples include the following:

[0196] [Table 32]

[0197] One exemplary alerting process by the real-time alerting component is as follows (assuming this process is executed automatically once the flight is closed and the BaggageHistory has been updated by the actual departing passenger checked baggage data processing component):

[0198] 41) Determining whether the warning time has been reached: By searching for the warning parameters (PrewarningParameters) based on the airline, aircraft registration number, flight number, takeoff airport, and arrival airport in the current flight information (FlightInfo), the corresponding number of days (days), maximum average error (avgDiffMaxValue), and previous warning date are obtained. Furthermore, if the current flight date is greater than or equal to (previous warning date + days), it indicates that the warning time has been reached and the subsequent process continues; otherwise, it indicates that the warning time has not been reached and the subsequent process ends.

[0199] 42) Obtaining the average value of the prediction error (avgDiff): Based on the airline, flight number, departure airport, arrival airport, [flight date - days + 1, flight date] in the current flight information (FlightInfo), extract the average value of the prediction error from the historical data extraction component of actual departing passenger checked baggage described above.

[0200] 43) Determining whether an alert is necessary: ​​If avgDiff>avgDiffMaxValue, an alert is necessary. The alert information is sent to the user, and the previous alert date in the corresponding PrewarningParameters record is changed to the current flight date. On the other hand, if avgDiff≦avgDiffMaxValue, no processing is performed.

[0201] For example, in the case of flight xx 1111 mentioned above, if the departure airport is Beijing (PEK), the baggage arrival airports include SHA and CAN, so a separate determination must be made as follows:

[0202] Determining whether the warning time has been reached: If the baggage arrival airport is SHA, searching PrewarningParameters based on xx, 1111, PEK, and SHA results in the first record in the table below, which is days=5, avgDiffMaxValue=5%, and previous warning date=2022 / 1 / 1. Furthermore, the current flight date is 2022 / 3 / 1, and (previous warning date + days) is 2022 / 1 / 6, so the warning time has been reached and subsequent determinations continue. On the other hand, if the baggage arrival airport is CAN, searching PrewarningParameters based on xx, 1111, PEK, and CAN results in the second record in the table below, which is days=10, avgDiffMaxValue=5%, and previous warning date=2022 / 2 / 25. Furthermore, the current flight date is 2022 / 3 / 1, and (previous warning date + days) is 2022 / 3 / 7, so the warning time has not been reached and subsequent processes are terminated.

[0203] [Table 33]

[0204] Obtaining the average prediction error (avgDiff): Since a subsequent decision is only required when the arrival airport is SHA, searching BaggageHistory based on xx, 1111, PEK, SHA, 2022 / 2 / 25-2022 / 3 / 1 results in the following records, therefore avgDiff=(7.14%+6.67%+8.56%) / 3=7.46%.

[0205] [Table 34]

[0206] Determining whether an alert is necessary: ​​avgDiff=7.46%, avgDiffMaxValue=5%, i.e., avgDiff>avgDiffMaxValue, so the alert information is sent to the user and at the same time the previous alert date in the corresponding PrewarningParameters record must be changed to the current flight date. The changed record is as follows ("2022 / 3 / 1" is the changed part):

[0207] [Table 35]

[0208] If the relevant parameters of the estimation rules are not set properly, there will be a large deviation between the predicted result and the actual value. Based on this, in this embodiment, an alarm process is used to promptly notify the user that the estimation rule parameters should be changed, and the user changes the relevant rule parameters in the estimation rule data set based on the alarm information, and then predicts the departing passenger checked baggage information based on the changed rule parameters, thereby achieving the effect of effectively reducing the deviation of the predicted value from the actual value.

[0209] The present disclosure further provides a passenger checked baggage information prediction device corresponding to the above-mentioned passenger checked baggage information prediction method, and referring to FIG. 7, the device includes: a data acquisition module 10 configured to acquire departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; a rule determination module 20 configured to determine target rule data on which prediction of passenger checked baggage information is based for the current flight; and an information prediction module 30 configured to predict a departing passenger checked baggage weight for the current flight based on at least a portion of the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and to perform weight-and-balance processing for the current flight based on the departing passenger checked baggage weight.

[0210] In one embodiment, the rule determination module 20 specifically: Determine a target prediction rule corresponding to the current flight in a preset estimation rule dataset according to flight information of the current flight, where the estimation rule dataset includes a passenger checked baggage prediction rule and its related parameter data; If the target prediction rule is a historical data prediction rule in the passenger checked baggage prediction rule, determine whether a historical data prediction condition is satisfied, and if YES, determine that the target rule data includes the historical data prediction rule and its corresponding rule parameters in the estimation rule dataset; while if NO, determine that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset; If the target prediction rule is a time series prediction rule in the passenger checked baggage prediction rule, it is used to determine whether the time series prediction condition is met, and if YES, it is determined that the target rule parameters include the time series prediction rule and the rule parameters corresponding to the rule in the estimation rule dataset, while if NO, it is determined that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset.

[0211] In one embodiment, the information prediction module 30 specifically: If the target rule data includes the historical data prediction rule and its rule parameters, extract historical parameter data required for the historical data prediction rule from the historical data of the actual departing passenger checked baggage, and predict the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical parameter data, the historical data prediction rule and its rule parameters; If the target rule data includes the time series prediction rule and its rule parameters, extracting historical time series parameter data required for the time series prediction rule from the historical data of the actual departing passenger checked baggage, and predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical time series parameter data, the time series prediction rule and its rule parameters; When the target rule data includes the static data of the passenger checked baggage weight, the target rule data is used to predict the departing passenger checked baggage weight of the current flight based on the departing passenger data and the static data of the passenger checked baggage weight.

[0212] In one embodiment, the time series forecasting rules include forecasting rules characterized by a pre-built ARIMA model; The ARIMA model is obtained by performing model training based on time series data samples of departure passenger checked baggage weight.

[0213] In one embodiment, the information prediction module 30 is further used to determine the total weight of the departing passenger checked baggage and unit load device for the current flight based on the predicted departing passenger checked baggage weight.

[0214] Wherein, if the current flight is a unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the sum of the departing passenger checked baggage weight and the unit load device weight; whereas, if the current flight is a non-unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the departing passenger checked baggage weight.

[0215] In one embodiment, the device described above comprises: The flight control device further includes a historical data update module configured to acquire actual departing passenger checked baggage data of the current flight, and update and store the acquired data after the current flight is closed into historical data of actual departing passenger checked baggage of the current flight.

[0216] In one embodiment, the device described above comprises: The system further includes an alarm module configured to determine a deviation of a predicted value of a departing passenger checked baggage weight of a current flight from an actual value, and if the deviation reaches a preset threshold, perform an alarm process, adjust corresponding rule parameters in the estimation rule dataset based on the alarm process, and predict a departing passenger checked baggage weight of the current flight at a subsequent time based on the adjusted rule parameters.

[0217] The units / modules according to the embodiments of the present disclosure may be implemented in the form of software or hardware, but the names of the units / modules may not necessarily limit the units themselves, for example, the first acquiring unit may be described as a "unit for acquiring at least two Internet Protocol addresses."

[0218] The functionality described herein above may be performed, at least in part, by one or more hardware logic components. Non-limiting example types of hardware logic components that may be used include, for example, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Parts (ASSPs), Systems on a Chip (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0219] The present disclosure further provides a computer-readable medium having a computer program stored thereon, the computer program including a program code for performing the method for predicting passenger checked baggage information disclosed in the method embodiments above.

[0220] In the context of this disclosure, a computer-readable medium (machine-readable medium) may be a tangible medium that contains or stores a program for use in or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections of one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0221] It should be noted that the computer-readable medium referred to in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above. The computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer-readable storage media include, but are not limited to, an electrical connection using one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used in or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, having computer-readable program code carried therein. Such propagated data signals may take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may be any computer-readable medium, separate from a computer-readable storage medium, capable of transmitting, propagating, or transporting a program for use in or in connection with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium may be transported by any suitable medium, including, but not limited to, electrical wire, optical cable, RF (radio frequency), or the like, or any suitable combination of the foregoing.

[0222] The computer-readable medium may be included in an electronic device, or may exist independently of an electronic device.

[0223] The present disclosure further provides a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, the computer program including program code for performing the method for predicting passenger checked baggage information disclosed in the method embodiment above.

[0224] In particular, according to the embodiments of the present disclosure, each of the processes described above with reference to the flowcharts can be embodied as a computer software program. In such embodiments, the computer program is downloaded and installed from a network by a communication device, or installed from a storage device, or installed from ROM. When the computer program is executed by a processing device, the above-mentioned functions limited to the method according to the embodiments of the present disclosure are performed.

[0225] In summary, in accordance with one or more embodiments of the present disclosure, the present disclosure provides a method for predicting passenger checked baggage information, the method comprising: obtaining departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; determining target rule data on which to base predictions of passenger checked baggage information for the current flight; predicting a departing passenger checked baggage weight for the current flight based on at least a portion of the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and performing weight and balance processing for the current flight based on the predicted departing passenger checked baggage weight.

[0226] According to one or more embodiments of the present disclosure, in the above-described method, the step of determining target rule data serving as a basis for predicting passenger checked baggage information for the current flight comprises: determining a target prediction rule corresponding to the current flight in a preset estimation rule dataset based on flight information of the current flight, where the estimation rule dataset includes a passenger checked baggage prediction rule and its related parameter data; If the target prediction rule is a historical data prediction rule in the passenger checked baggage prediction rule, determining whether a historical data prediction condition is satisfied, and if YES, determining that the target rule data includes the historical data prediction rule and its corresponding rule parameters in the estimation rule dataset, while if NO, determining that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset; If the target prediction rule is a time series prediction rule in the passenger checked baggage prediction rule, determining whether a time series prediction condition is satisfied, and if YES, determining that the target rule parameters include the time series prediction rule and its corresponding rule parameters in the estimation rule dataset, while if NO, determining that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset.

[0227] According to one or more embodiments of the present disclosure, in the method described above, the step of predicting departing passenger checked baggage weight for a current flight based at least in part on the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data includes: If the target rule data includes the historical data prediction rule and its rule parameters, extracting historical parameter data required for the historical data prediction rule from the historical data of actual departing passenger checked baggage, and predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical parameter data, the historical data prediction rule and its rule parameters; If the target rule data includes the time series prediction rule and its rule parameters, extracting historical time series parameter data required for the time series prediction rule from the historical data of actual departing passenger checked baggage, and predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical time series parameter data, the time series prediction rule and its rule parameters; If the target rule data includes static data of the passenger checked baggage weight, predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data and the static data of the passenger checked baggage weight.

[0228] According to one or more embodiments of the present disclosure, in the method described above, the time series forecasting rules include forecasting rules characterized by a pre-constructed ARIMA model; The ARIMA model is obtained by performing model training based on time series data samples of departure passenger checked baggage weight.

[0229] According to one or more embodiments of the present disclosure, in the method described above, after the step of predicting the departing passenger checked baggage weight of the current flight, determining a total weight of the departing checked passenger baggage and unit load device for the current flight based on the predicted departing checked passenger baggage weight; Wherein, if the current flight is a unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the sum of the departing passenger checked baggage weight and the unit load device weight; whereas, if the current flight is a non-unit load aircraft, the total weight of the departing passenger checked baggage and the unit load device is the departing passenger checked baggage weight.

[0230] In accordance with one or more embodiments of the present disclosure, the method described above comprises: The method further includes a step of acquiring actual departing passenger checked baggage data of the current flight, and updating and storing the acquired data after the current flight is closed as historical data of actual departing passenger checked baggage of the current flight.

[0231] In accordance with one or more embodiments of the present disclosure, the method described above comprises: determining the deviation of a predicted value of departing passenger checked baggage weight for the current flight from an actual value; The method further includes the steps of: performing an alarm process when the deviation reaches a preset threshold; adjusting corresponding rule parameters in the estimation rule dataset based on the alarm process; and predicting the departure passenger checked baggage weight of the current flight at a subsequent time based on the adjusted rule parameters.

[0232] According to one or more embodiments of the present disclosure, the present disclosure further provides a passenger checked baggage information prediction device, the device comprising: a data acquisition module configured to acquire departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; a rule determination module configured to determine target rule data serving as a basis for predicting passenger checked baggage information for a current flight; and an information prediction module configured to predict a departing passenger checked baggage weight for the current flight based on at least a portion of the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and to perform weight-and-balance processing for the current flight based on the departing passenger checked baggage weight.

[0233] According to one or more embodiments of the present disclosure, the present disclosure further provides a computer-readable medium having stored thereon a computer program, the computer program including program code for performing the above-described method for predicting passenger checked baggage information.

[0234] In accordance with one or more embodiments of the present disclosure, the present disclosure further provides a computer program product, the computer program product including a computer program embodied in a non-transitory computer-readable medium, the computer program including program code for performing the method for predicting passenger checked baggage information as described above.

[0235] The passenger checked baggage information prediction method, apparatus, computer-readable medium, and computer program product provided in the present disclosure have at least the following technical advantages:

[0236] a) In this disclosure, the calculation is based on the historical data of the actual departing passenger checked baggage of the flight and the departing passenger data of the current flight, and not only refers to the historical baggage data but also refers to the existing passenger data, so that the data reference is comprehensive, the calculated value obtained is more convincing, the reference value is higher, the predicted value is closer to the actual value, and the risks and hidden dangers to production safety are avoided.

[0237] b) In the present disclosure, the historical data of the actual departing passengers' checked baggage of the flight and the departing passenger data of the current flight are input, and are applied to the corresponding estimation rules for calculation. The calculated value of the baggage weight obtained is fixed, and the calculated value obtained will not differ depending on the operator using the system, thereby eliminating hidden risks due to individual differences.

[0238] c) In the present disclosure, an alarm function is set, and when there is a large deviation between the calculation result and the actual value due to an improper setting of the relevant parameters of the estimation rule, the alarm function notifies the user that the estimation rule parameters should be changed, and after the user changes the relevant parameters, the calculation is then performed using the new rule parameters, thereby effectively reducing the deviation of the calculated value from the actual value.

[0239] Although, by way of specificity, the present subject matter has been described in language specific to structural features and / or methodological logical operations, it should be understood that the limited subject matter is not necessarily limited to the specific features or operations described above. On the contrary, the specific features and operations described above are merely exemplary forms for implementing the limited subject matter.

[0240] Although the above description includes details of several implementations, these should not be construed as limitations on the scope of the present disclosure. Some features that are described in the context of a single embodiment can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments alone or in any suitable subcombination.

[0241] The above description merely describes preferred embodiments of the present disclosure and the technical principles used. It should be understood by those skilled in the art that the scope of the present disclosure is not limited to the specific combination of the above-described technical features, but should also include other technical means formed by any combination of the above-described technical features or equivalent features without departing from the concept of the above-described disclosure. For example, technical means formed by replacing the above-described features with technical features having similar functions to those disclosed in the present disclosure (but not limited to these).

Claims

1. A method for predicting passenger checked baggage information, comprising: obtaining departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; determining target rule data on which to base predictions of passenger checked baggage information for the current flight; predicting a departing passenger checked baggage weight for the current flight based at least in part on the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and performing weight and balance processing for the current flight based on the predicted departing passenger checked baggage weight.

2. The step of determining target rule data serving as a basis for predicting passenger checked baggage information for a current flight includes: determining a target prediction rule corresponding to the current flight in a preset estimation rule dataset based on flight information of the current flight, where the estimation rule dataset includes a passenger checked baggage prediction rule and its related parameter data; If the target prediction rule is a history data prediction rule in the passenger checked baggage prediction rule, determining whether a history data prediction condition is satisfied, and if yes, determining that the target rule data includes the history data prediction rule and rule parameters corresponding to the rule in the estimation rule dataset, while if no, determining that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset; 2. The method of claim 1, further comprising: if the target prediction rule is a time series prediction rule in the passenger checked baggage prediction rule, determining whether a time series prediction condition is satisfied; if yes, determining that the target rule parameters include the time series prediction rule and its corresponding rule parameters in the estimation rule dataset; and if no, determining that the target rule data includes static data of passenger checked baggage weight in the estimation rule dataset.

3. predicting a departing passenger checked baggage weight for a current flight based at least in part on the departing passenger data, the actual departing passenger checked baggage history data, and the targeting rule data, If the target rule data includes the historical data prediction rule and its rule parameters, extracting historical parameter data required for the historical data prediction rule from the historical data of actual departing passenger checked baggage, and predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical parameter data, the historical data prediction rule and its rule parameters; If the target rule data includes the time series prediction rule and its rule parameters, extracting historical time series parameter data required for the time series prediction rule from the historical data of actual departing passenger checked baggage, and predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data, the historical time series parameter data, the time series prediction rule and its rule parameters; 3. The method of claim 2, further comprising: if the target rule data includes static data of the passenger checked baggage weight, predicting the departing passenger checked baggage weight of the current flight based on the departing passenger data and the static data of the passenger checked baggage weight.

4. the time series forecasting rules include forecasting rules characterized by a pre-built ARIMA model; 3. The method of claim 2, wherein the ARIMA model is obtained by model training based on time series data samples of departure passenger checked baggage weight.

5. After the step of predicting the weight of checked baggage for the current flight, determining a total weight of the departing checked passenger baggage and unit load device for the current flight based on the predicted departing checked passenger baggage weight; The method according to claim 1, wherein, if the current flight is a unit load aircraft, the total weight of the departing checked baggage and the unit load device is the sum of the weight of the departing checked baggage and the weight of the unit load device; and if the current flight is a non-unit load aircraft, the total weight of the departing checked baggage and the unit load device is the weight of the departing checked baggage.

6. 2. The method of claim 1, further comprising the steps of: acquiring actual departing passenger checked baggage data for the current flight; and updating the historical data of actual departing passenger checked baggage for the current flight with the acquired data after the current flight is closed.

7. determining the deviation of a predicted value of departing passenger checked baggage weight for the current flight from an actual value; 3. The method of claim 2, further comprising: performing an alarm process when the deviation reaches a preset threshold; adjusting corresponding rule parameters in the estimated rule dataset based on the alarm process; and predicting the departure passenger checked baggage weight of the current flight at a subsequent time based on the adjusted rule parameters.

8. A passenger baggage information prediction device, a data acquisition module configured to acquire departing passenger data and historical data of actual departing passenger checked baggage corresponding to the current flight; a rule determination module configured to determine target rule data serving as a basis for predicting passenger checked baggage information for a current flight; an information prediction module configured to predict a departing passenger checked baggage weight for a current flight based at least in part on the departing passenger data, the historical data of actual departing passenger checked baggage, and the target rule data, and to perform weight and balance processing for the current flight based on the departing passenger checked baggage weight.

9. 1. A computer-readable medium, comprising: A computer program is stored 8. A computer-readable medium, comprising a computer program comprising program code for executing the method for predicting passenger checked baggage information according to any one of claims 1 to 7.

10. 1. A computer program product comprising: A computer program embodied on a non-transitory computer-readable medium, A computer program product, characterized in that the computer program contains a program code for executing the method for predicting passenger checked baggage information according to any one of claims 1 to 7.

Images