Flight carbon emission prediction method and device and storage medium

Abstract

The invention discloses a flight carbon emission prediction method and device and a storage medium. The method comprises the following steps: acquiring flight information of a target flight; obtaining a target carbon emission prediction model corresponding to the target flight, and inputting the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; extended data corresponding to the target flight are determined according to the flight information, and the extended data are used for representing weights occupied by the carbon emission information of different shipping spaces in the overall carbon emission information; according to the overall carbon emission information and the extended data, sub-region carbon emission information corresponding to the target flight is determined, and the overall carbon emission information is the sum of the multiple sub-region carbon emission information; and determining a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information. Through the flight carbon emission prediction method and device, the problem of low flight carbon emission prediction accuracy in related technologies is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a flight carbon emission prediction method and device and storage medium. BACKGROUND

[0002] Civil aviation carbon emission calculation is a key component of evaluating the environmental impact of airlines and promoting green aviation. With increasing global concern about greenhouse gas emissions, accurate prediction of aviation carbon emissions has become one of the important tasks at present.

[0003] In the prior art, civil aviation carbon emission prediction is mostly based on static fuel coefficient and flight class average allocation. The static prediction of flight class carbon emission prediction value is obtained by using a fixed emission coefficient, without considering the difference in physical space resource occupation of different cabins. Not only is the accuracy of the carbon emission prediction of the flight class low, but also the more fine-grained carbon emission prediction value of the passenger cabin class cannot be obtained.

[0004] In view of the problem of low prediction accuracy of flight carbon emission in the related art, no effective solution has been proposed so far. SUMMARY

[0005] The main purpose of the present application is to provide a flight carbon emission prediction method, device and storage medium to solve the problem of low prediction accuracy of flight carbon emission in the related art.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a flight carbon emission prediction method is provided. The method comprises: obtaining flight information of a target flight; obtaining a target carbon emission prediction model corresponding to the target flight, and inputting the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; determining extended data corresponding to the target flight according to the flight information, wherein the extended data is used to represent the weight of carbon emission information of different cabins in the overall carbon emission information; determining sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extended data, wherein the overall carbon emission information is the sum of the plurality of sub-region carbon emission information; determining the carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information.

[0007] Further, obtaining the target carbon emission prediction model corresponding to the target flight comprises: obtaining a carbon emission data set within a preset time range before the departure date of the target flight; training a preset machine learning model according to the carbon emission data set to obtain the target carbon emission prediction model.

[0008] Further, the preset time range includes a first preset time period and a second preset time period, the carbon emission dataset includes a basic pool carbon emission dataset in the first preset time period and an iteration pool carbon emission dataset in the second preset time period, the first preset time period is earlier than the second preset time period, and the training of the preset machine learning model according to the carbon emission dataset to obtain the target carbon emission prediction model includes: training the preset machine learning model according to the basic pool carbon emission dataset to obtain a first carbon emission prediction model; updating the basic pool carbon emission dataset by using the iteration pool carbon emission dataset to obtain a plurality of updated datasets; training the preset machine learning model according to the plurality of updated datasets to obtain a plurality of preset carbon emission prediction models; and selecting the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain the target carbon emission prediction model.

[0009] Further, the updating of the basic pool carbon emission dataset by using the iteration pool carbon emission dataset to obtain a plurality of updated datasets includes: moving samples in the iteration pool carbon emission dataset to the basic pool carbon emission dataset in batches to obtain a plurality of corresponding updated datasets, wherein the number of samples moved in each batch is a preset number, and an updated dataset corresponding to each batch is obtained after the movement of each batch.

[0010] Further, the determining of the extended data corresponding to the target flight according to the flight information includes: querying the cabin layout database of the target flight according to the flight information to determine a physical space factor corresponding to the target flight, wherein the physical space factor is used to represent the proportion of the cabin physical area to the reference area; obtaining an occupancy adjustment coefficient and determining an occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent the influence of the occupancy fluctuation rate on the apportioning of the sub-region carbon emission information; and determining the extended data according to the physical space factor and the occupancy elasticity factor.

[0011] Further, the determining of the sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extended data includes: determining the weight of each cabin in the target flight according to the extended data; and distributing the overall carbon emission information according to all the weights to determine the sub-region carbon emission information corresponding to the target flight.

[0012] Further, the determining of the carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information includes: obtaining the blockchain data corresponding to the target flight; performing traceability in the blockchain data according to the order of the seat number, the flight number, the oil batch number and the original origin code to obtain a full-link carbon traceability ID corresponding to the target flight; and taking the overall carbon emission information, the sub-region carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0013] In order to achieve the above object, according to another aspect of the present application, a flight carbon emission prediction device is provided. The device comprises: an information acquisition unit configured to acquire flight information of a target flight; a model prediction unit configured to acquire a target carbon emission prediction model corresponding to the target flight, and input the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; an extension data unit configured to determine extension data corresponding to the target flight according to the flight information, wherein the extension data is used to represent weights of carbon emission information of different cabins in the overall carbon emission information; an extension prediction unit configured to determine sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is a sum of the plurality of sub-region carbon emission information; and a result determination unit configured to determine a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information.

[0014] Further, the model prediction unit comprises: a data collection module configured to acquire a carbon emission data set within a preset time range before a departure date of the target flight; and a model training module configured to train a preset machine learning model according to the carbon emission data set to obtain the target carbon emission prediction model.

[0015] Further, the preset time range comprises a first preset time period and a second preset time period, the carbon emission data set comprises a basic pool carbon emission data set within the first preset time period and an iteration pool carbon emission data set within the second preset time period, the first preset time period is earlier than the second preset time period, and the model training module comprises: a first training submodule configured to train the preset machine learning model according to the basic pool carbon emission data set to obtain a first carbon emission prediction model; a data updating submodule configured to update the basic pool carbon emission data set by using the iteration pool carbon emission data set to obtain a plurality of updated data sets; a second training submodule configured to train the preset machine learning model according to the plurality of updated data sets to obtain a plurality of preset carbon emission prediction models; and a model selection submodule configured to select the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain the target carbon emission prediction model.

[0016] Further, the data updating submodule comprises: a batch updating component configured to move samples in the iteration pool carbon emission data set to the basic pool carbon emission data set in a plurality of batches to obtain a plurality of corresponding updated data sets, wherein the number of samples moved in each batch is a preset number, and one updated data set corresponding to each batch is obtained after movement of each batch.

[0017] Further, the extension data unit comprises: a physical space factor module configured to query a cabin layout database of the target flight according to the flight information to determine a physical space factor corresponding to the target flight, wherein the physical space factor is used to represent a proportion of a cabin physical area to a reference area; an occupancy elasticity factor module configured to obtain an occupancy adjustment coefficient and determine an occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and an occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent an influence of the occupancy fluctuation rate on the allocation of the sub-region carbon emission information; and a data determination module configured to determine the extension data according to the physical space factor and the occupancy elasticity factor.

[0018] Further, the extension prediction unit comprises: a weight prediction module configured to determine a weight of each cabin in the target flight according to the extension data; and a weight distribution module configured to distribute the overall carbon emission information according to all the weights to determine the sub-region carbon emission information corresponding to the target flight.

[0019] Further, the result determination unit comprises: a first determination module configured to obtain the blockchain data corresponding to the target flight; a second determination module configured to trace the blockchain data according to an order of a seat number, a flight number, an oil product batch number and an original origin code to obtain a full-link carbon traceability ID corresponding to the target flight; and a third determination module configured to take the overall carbon emission information, the sub-region carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0020] According to another aspect of the present application, a computer-readable storage medium is provided, which comprises a stored program, wherein the program, when executed, controls a device in which the computer-readable storage medium is located to perform any one of the flight carbon emission prediction methods.

[0021] According to another aspect of the present application, an electronic device is provided, which comprises one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for performing any one of the flight carbon emission prediction methods.

[0022] In the embodiment of the present application, the flight information of the target flight is obtained, the target carbon emission prediction model corresponding to the target flight is obtained, and the flight information is input into the target carbon emission prediction model to predict the overall carbon emission information corresponding to the target flight. The extension data corresponding to the target flight is determined according to the flight information, wherein the extension data is used to represent the weight of the carbon emission information of different cabins in the overall carbon emission information. The sub-regional carbon emission information corresponding to the target flight is determined according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is the sum of the plurality of sub-regional carbon emission information. The carbon emission prediction result of the target flight is determined according to the overall carbon emission information and the sub-regional carbon emission information, which solves the technical problem of low prediction accuracy of flight carbon emission in the prior art.

[0023] By using the target carbon emission prediction model corresponding to the target flight for prediction, the timeliness of the target carbon emission prediction model is ensured, the prediction accuracy of the overall carbon emission information is improved, and the extension data of the target flight is obtained, thereby realizing comprehensive and accurate prediction of the sub-regional carbon emission information of the target flight. Therefore, the accuracy of the flight carbon emission information prediction is improved. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application, and are incorporated herein for purposes of explanation and are not intended to limit the application. In the drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal for implementing the flight carbon emission prediction method is shown;

[0026] Figure 2 A flowchart of the flight carbon emission prediction method provided by the embodiment of the present application is shown;

[0027] Figure 3 A schematic diagram of the flight carbon emission prediction device provided by the embodiment of the present application is shown;

[0028] Figure 4 A structure block diagram of an electronic device according to the embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second" and the like in the description and in the claims of the present application are used to distinguish between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of these terms herein is to be construed as interchangeable in order to describe the embodiments of the present application described herein as potentially capable of attaining orders of execution other than those illustrated or otherwise described herein. Furthermore, the terms "comprise" and "comprising" and any variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, system, product or apparatus that comprises a list of steps or units not necessarily limited to those steps or units that are clearly recited, but can include other steps or units not expressly listed or inherent to such process, method, product or apparatus.

[0031] First, some of the nouns or terms that appear in the description of the embodiments of the present application are applicable to the following explanations:

[0032] It should be noted that the information collected in the present application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, analyzed data, etc.) are authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant laws, regulations and standards, take necessary security measures, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal. For example, the system and the interface between the related users or institutions provide the user with a corresponding operation portal for the user to choose to agree or refuse the automatic decision result; if the user chooses to refuse, the expert decision process is entered.

[0033] Embodiment 1

[0034] According to the embodiments of the present application, a method for predicting flight carbon emissions is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0035] The method provided by the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for predicting flight carbon emissions is shown. As Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the flight carbon emission prediction method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned flight carbon emission prediction method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is configured to receive or send data via a network. The network can include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) that can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module configured to communicate with the Internet wirelessly.

[0039] The display can be a liquid crystal display (LCD) that is touch screen type, for example, which can enable a user to interact with a user interface of the computer terminal 10 (or a mobile device).

[0040] In the above operating environment, the present application provides a flight carbon emission prediction method as shown in Figure 2 Figure 2 is a flowchart of the flight carbon emission prediction method according to Embodiment 1 of the present application.

[0041] In step S201, flight information of a target flight is obtained.

[0042] Optionally, the flight information is operation data of the target flight, and the flight information can be obtained by querying a database of an airline company to which the target flight belongs according to a two-letter code of the airline company, so as to obtain the flight information. The flight information can include ASTD (a data standard) standard data (for example, flight schedule, seat booking, operation) provided by an ICS system (information system), and physical area parameters of a cabin layout database (the parameters can be accurate to 0.1 m 2 ), real-time climb throttle opening, and aviation fuel blockchain batch number.

[0043] In step S202, a target carbon emission prediction model corresponding to the target flight is obtained, and the flight information is input into the target carbon emission prediction model, so as to predict overall carbon emission information corresponding to the target flight.

[0044] ​Optionally, the target flight corresponding target carbon emission prediction model can be a model obtained by training a preset machine learning model using flight operation history data and carbon emission data of the target flight. The target carbon emission prediction model can be obtained by acquiring model parameters and calling a model interface. The machine learning model can be a linear regression model, or other regression models such as ridge regression and partial least squares regression. The regression model quickly fits the corresponding overall carbon emission information based on multiple features in the full flight information, thereby laying a foundation for quickly training and obtaining the model. The overall carbon emission information is also referred to as flight class carbon emission information. The flight operation history data includes ASTD standard data of multiple times, physical area parameters of a cabin layout database, ACARS real-time climb throttle opening, aviation oil blockchain batch number, and overall carbon emission true values corresponding to the times.

[0045] Optionally, after inputting the flight information into the target carbon emission prediction model to predict the overall carbon emission information corresponding to the target flight, the climb throttle opening corresponding to the target flight can be acquired, and the overall carbon emission information can be corrected according to the climb throttle opening. The climb throttle opening is the percentage of the engine throttle opening in the climb phase obtained through the aircraft communication addressing and reporting system, and can correct the overall carbon emission information based on the fuel consumption in the cruise climb and descent phase. The overall carbon emission information can be corrected according to the climb throttle opening by multiplying the overall carbon emission information by a preset correction coefficient to obtain corrected overall carbon emission information. For example, the climb throttle opening can be an increase of 5% of the throttle, and the fuel consumption is increased by 3%, that is, the actual throttle value is increased by a certain percentage compared with the model reference value, and the percentage is multiplied by 0.6 as the correction amplitude, and the preset correction coefficient is 1 plus 0.6, that is, 1.6.

[0046] Step S203, determining the extension data corresponding to the target flight according to the flight information, wherein the extension data is used to represent the weight of the carbon emission information of different cabins in the overall carbon emission information.

[0047] Optionally, the extension data can be the dynamic cabin weight (i.e., passenger level carbon emission allocation weight value) of different cabins of the target flight. For example, the target flight has 20 cabins, and the overall carbon emission information of the target flight is X. The dynamic cabin weight of a specific cabin is w, and the passenger level carbon emission information of the specific cabin is the product of the overall carbon emission information X and the dynamic cabin weight w.

[0048] Step S204, determining the sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is the sum of the multiple sub-region carbon emission information.

[0049] Optionally, the overall carbon emission information can be multiplied by the extended data of different cabins in the target flight to obtain a plurality of sub-regional carbon emission information. The sub-regional carbon emission information, i.e., passenger-level carbon emission information or cabin-level carbon emission information, refers to the carbon emission amount of each passenger cabin accurately predicted and allocated according to the cabin grade, physical space ratio, and seat fluctuation of the cabin, etc. in the flight carbon emission prediction. In other words, the sub-regional carbon emission information represents the carbon emission amount of one seat of a passenger on the target flight. By predicting the sub-regional carbon emission information, it is beneficial for the airline and the passenger to understand and quantify the specific impact of individual flight travel on carbon emission, and to promote individual carbon footprint tracking and carbon benefit plan of the civil aviation industry.

[0050] In step S205, the overall carbon emission information and the sub-regional carbon emission information are used to determine the carbon emission prediction result of the target flight.

[0051] Optionally, the overall carbon emission information and the plurality of sub-regional carbon emission information can be integrated as the carbon emission prediction result.

[0052] In summary, by using the target carbon emission prediction model corresponding to the target flight for prediction, the prediction accuracy of the overall carbon emission information is improved, and the extended data of the target flight is obtained, thereby achieving comprehensive and accurate prediction of the sub-regional carbon emission information of the target flight. Therefore, the accuracy of the carbon emission information prediction of the flight is improved.

[0053] To improve the accuracy of the target carbon emission prediction model, the target carbon emission prediction model corresponding to the target flight can be obtained by: obtaining a carbon emission data set within a preset time range before the departure date of the target flight; and training a preset machine learning model based on the carbon emission data set to obtain the target carbon emission prediction model.

[0054] Optionally, different target flights correspond to different target carbon emission prediction models, and the carbon emission data set includes a plurality of samples, each sample including flight operation data and corresponding carbon emission data. For example, the target flight with a departure date of July 20, 2024 can use the carbon emission data set from July 20, 2023 to July 19, 2024 to train the preset machine learning model to obtain the corresponding target carbon emission prediction model; and the target flight with a departure date of September 20, 2024 can use the carbon emission data set from September 20, 2023 to September 19, 2024 to train the preset machine learning model to obtain the corresponding target carbon emission prediction model. To ensure the training efficiency of the model, the preset machine learning model is a linear regression model.

[0055] In summary, by using flight operation history data in a preset time range before the target flight to train the corresponding target carbon emission prediction model, it can be ensured that the model learns the rules closest to the target flight operation conditions, so that the model can more accurately reflect the carbon emission characteristics of the target flight when predicting, improving the timeliness of the target carbon emission prediction model and the accuracy of prediction using the target carbon emission prediction model.

[0056] To improve the accuracy of the target carbon emission prediction model, optionally, the preset time range includes a first preset time period and a second preset time period, the carbon emission data set includes a basic pool carbon emission data set in the first preset time period and an iterative pool carbon emission data set in the second preset time period, the first preset time period is earlier than the second preset time period, and training the preset machine learning model according to the carbon emission data set to obtain the target carbon emission prediction model includes: training the preset machine learning model according to the basic pool carbon emission data set to obtain a first carbon emission prediction model; updating the basic pool carbon emission data set using the iterative pool carbon emission data set to obtain a plurality of updated data sets; training the preset machine learning model according to the plurality of updated data sets to obtain a plurality of preset carbon emission prediction models; and selecting the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain the target carbon emission prediction model.

[0057] For example, if the departure date of the target flight is 2025-07-08, the first preset time period can be 2023-01-01 to 2024-07-07, and the second preset time period can be 2024-07-08 to 2025-07-07, that is, the basic pool carbon emission data set in the first preset time period is an earlier historical sample, and the iterative pool carbon emission data set in the second preset time period is a recent sample other than the basic pool carbon emission data set.

[0058] Optionally, the base pool carbon emission dataset is updated by using the iteration pool carbon emission dataset, which can be moving the samples in the iteration pool carbon emission dataset to the base pool carbon emission dataset. For example, before the update, the samples in the base pool carbon emission dataset are x1-x365, and the samples in the iteration pool carbon emission dataset are x366-x400. Then, the samples x366-x370 can be moved to the base pool carbon emission dataset. At this time, the samples in the updated dataset (i.e., the updated base pool carbon emission dataset) are x1-x370, and the samples in the iteration pool carbon emission dataset are x371-x400. The updated dataset is used to train the plurality of preset carbon emission prediction models, and the updated iteration pool carbon emission dataset corresponding to the updated dataset is used to verify the accuracy of the plurality of preset carbon emission prediction models. Each time the update is performed, a preset carbon emission prediction model is added. The first carbon emission prediction model and the plurality of preset carbon emission prediction models are selected, which can be selecting the model with the smallest prediction error as the target carbon emission prediction model.

[0059] In summary, the base pool carbon emission dataset covers historical data with a long time interval, providing a comprehensive learning background for the model to ensure that it can master long-term trends and seasonal patterns. The iteration pool carbon emission dataset focuses on more recent patterns. Therefore, by updating the base pool with the iteration pool, the model can be continuously fine-tuned and optimized. The above scheme realizes multi-stage model training and model selection through the dynamic updating of the carbon emission dataset (base pool + iteration pool) with double preset time periods and the model optimization strategy, which can capture recent trends, reduce prediction lag, and thus improve the accuracy of the target carbon emission prediction model.

[0060] To improve the accuracy of the target carbon emission prediction model, the base pool carbon emission dataset is updated by using the iteration pool carbon emission dataset to obtain a plurality of updated datasets, including: moving the samples in the iteration pool carbon emission dataset to the base pool carbon emission dataset in a plurality of batches to obtain a plurality of corresponding updated datasets, wherein the number of samples moved in each batch is a preset number, and each batch is moved to obtain an updated dataset corresponding to the batch.

[0061] For example, when the preset quantity is 1, the sample moved in each batch can be the earliest sample in time in the iterative pool carbon emission dataset. Taking samples x1-x365 in the basic pool carbon emission dataset and samples x366-x400 in the iterative pool carbon emission dataset as examples, the first batch moves x366 to the basic pool carbon emission dataset to obtain an updated dataset (samples x1-x366), an updated iterative pool carbon emission dataset (samples x367-x400), and a first preset carbon emission prediction model obtained after training; the second batch moves x368 to the basic pool carbon emission dataset to obtain an updated dataset (samples x1-x367), an updated iterative pool carbon emission dataset (samples x368-x400), and a second preset carbon emission prediction model obtained after training. It should be noted that in the above updating, the original samples in the basic pool carbon emission dataset can be retained, or the preset quantity of the earliest samples in time in the basic pool carbon emission dataset can be deleted correspondingly.

[0062] Optionally, the stop condition of the updating can be stopping when the number of updates reaches a preset number threshold (for example, 10 updates are performed, and a total of 10 preset carbon emission prediction models are obtained), or stopping when the number of samples in the iterative pool carbon emission dataset is emptied.

[0063] Optionally, the first carbon emission prediction model and the plurality of preset carbon emission prediction models can be selected by selecting the model with the smallest prediction error as the target carbon emission prediction model. The prediction error of the first carbon emission prediction model and the plurality of preset carbon emission prediction models can be calculated based on the iteration pool carbon emission dataset corresponding to the batch to which the model belongs. For example, the training dataset used by the first carbon emission prediction model is the original base pool carbon emission dataset (samples x1 to x365), and the batch to which the model belongs is the 0th batch (i.e., no movement occurs), and the iteration pool carbon emission dataset (x366 to x400) corresponding to the 0th batch. The training dataset used by the first preset carbon emission prediction model is the updated dataset (samples x1 to x366), and the batch to which the model belongs is the 1st batch (i.e., the first batch of updated models), and the iteration pool carbon emission dataset (x367 to x400) corresponding to the 1st batch. In other words, after each batch is updated, the corresponding updated dataset is obtained, the preset machine learning model is trained using the updated dataset to obtain a preset carbon emission prediction model corresponding to the batch, and the prediction error of the preset carbon emission prediction model is calculated using the samples in the corresponding iteration pool carbon emission dataset. For example, the first preset carbon emission prediction model corresponds to the iteration pool carbon emission dataset (x367 to x400), and the error of a single sample is the quotient obtained by dividing the preset difference (the difference between the predicted value and the true value) by the true value. There are 34 samples from x367 to x400, so the error of each sample is calculated, and the average of all errors is obtained to obtain the prediction error of the preset carbon emission prediction model. The above error calculation method uses the actual future data corresponding to each preset carbon emission prediction model, so it can reflect the prediction ability of each preset carbon emission prediction model.

[0064] Optionally, before recalculating the prediction error of the preset carbon emission prediction model, the overall carbon emission information in the updated dataset (i.e., the flight class carbon emission true value in the sample) can be corrected based on the climb throttle opening, and the prediction error can be calculated based on the corrected overall carbon emission information. This makes the prediction error more consistent with the actual error.

[0065] In summary, by updating the plurality of updated datasets by batch, the base pool carbon emission dataset gradually incorporates the samples in the iteration pool carbon emission dataset, and the target carbon emission prediction model is selected from the plurality of preset carbon emission prediction models based on the error, which improves the sensitivity and adaptability of the target carbon emission prediction model to recent changes in carbon emission patterns, thereby improving the accuracy of the target carbon emission prediction model.

[0066] To improve the accuracy of predicting the sub-regional carbon emission information, optionally, determining the extended data corresponding to the target flight according to the flight information comprises: querying the cabin layout database of the target flight according to the flight information to determine a physical space factor corresponding to the target flight, wherein the physical space factor is used to represent the proportion of the cabin physical area to the reference area; obtaining an occupancy adjustment coefficient and determining an occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent the influence of the occupancy fluctuation rate on the allocation of the sub-regional carbon emission information; and determining the extended data according to the physical space factor and the occupancy elasticity factor.

[0067] Optionally, the physical space factor is the quotient obtained by dividing the cabin physical area by the reference area, wherein the cabin physical area is the physical area of the target cabin extracted from the cabin layout database, and the reference area is the reference area of the economy class of the model of the target flight, and the reference area of the economy class is the average floor area of a single seat in the standard layout (the area includes seats, aisle allocation, and service space).

[0068] Optionally, determining the occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight comprises: obtaining a cabin occupancy fluctuation rate; obtaining a total flight occupancy fluctuation rate; taking the quotient obtained by dividing the cabin occupancy fluctuation rate by the total flight occupancy fluctuation rate as a preset quotient value; obtaining the product of the occupancy adjustment coefficient and the preset quotient value, and taking the sum obtained by adding the product and 1 as the occupancy elasticity factor. Wherein, the cabin occupancy represents the occupancy of each cabin; the cabin occupancy fluctuation rate is the standard deviation of the number of bookings of a specific cabin class (such as first class F) in a preset statistical period, which is used to represent the instability of the demand of the cabin, and the higher the cabin occupancy fluctuation rate, the greater the cabin occupancy fluctuation, and the more carbon emission responsibility needs to be borne; the total flight occupancy fluctuation rate is the standard deviation of the total number of bookings of all cabins of the entire aircraft in the historical statistical period, which is used to represent the stability of the overall flight demand; and the occupancy adjustment coefficient is a parameter pre-configured by the airline, which is used to represent the amplification strength of the occupancy fluctuation on the carbon emission weight.

[0069] Optionally, determining the extended data according to the physical space factor and the occupancy elasticity factor can be multiplying the physical space factor and the occupancy elasticity factor, and taking the product as the extended data.

[0070] In summary, the extended data is obtained through the physical space factor and the occupancy elasticity factor, which is equivalent to a dynamic cabin weight, avoiding the errors that may be caused by the average allocation method, and improving the accuracy of predicting the sub-regional carbon emission information.

[0071] To improve the accuracy of predicting the sub-regional carbon emission information, optionally, determining the sub-regional carbon emission information corresponding to the target flight according to the overall carbon emission information and the extended data comprises: determining the weight of each cabin in the target flight according to the extended data; and distributing the overall carbon emission information according to all the weights to determine the sub-regional carbon emission information corresponding to the target flight.

[0072] For example, after obtaining the overall carbon emission information, since the weights of all the cabins are included in the extended data, the weight of any cabin can be divided by the total weight of all the cabins in the extended data to obtain a cabin weight value corresponding to the cabin, and the cabin weight value is multiplied by the overall carbon emission information to obtain the sub-regional carbon emission information corresponding to the cabin.

[0073] In summary, by obtaining the weight through the extended data and distributing according to the weight, the sub-regional carbon emission information corresponding to the target flight is obtained, and the accuracy of predicting the sub-regional carbon emission information is improved.

[0074] To improve the accuracy of the carbon emission prediction result, optionally, determining the carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-regional carbon emission information comprises: obtaining the blockchain data corresponding to the target flight; and tracing the blockchain data according to the order of the seat number, the flight number, the oil product batch number and the original origin code to obtain a full-link carbon traceability ID corresponding to the target flight; and taking the overall carbon emission information, the sub-regional carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0075] Optionally, the full-link carbon traceability ID is used to identify a unique code for the whole process from crude oil exploration to passenger seat, and the data structure can be crude oil origin code (2 bits)-oil product batch number (8 bits)-flight number (6 bits)-seat number (3 bits). For example, after tracing, the full-link carbon traceability ID can be ME (original origin code)-FJ2024WTI (oil product batch number)-CA123 (flight number)-23K (seat number).

[0076] In summary, by tracing in the blockchain data using the sub-regional carbon emission information, the combination of dynamic cabin weight and full-link traceability is realized, thereby obtaining the full-link carbon traceability ID, and the comprehensiveness and accuracy of the carbon emission prediction result are improved.

[0077] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0078] Embodiment 2

[0079] The embodiment of the present application further provides a flight carbon emission prediction device. It should be noted that the flight carbon emission prediction device of the embodiment of the present application can be used to execute the flight carbon emission prediction method provided by the embodiment of the present application. The flight carbon emission prediction device provided by the embodiment of the present application is introduced as follows.

[0080] According to the embodiment of the present application, a device for implementing the flight carbon emission prediction method is further provided, as shown in the following Figure 3 The device comprises:

[0081] The information acquisition unit 301 is configured to acquire flight information of a target flight.

[0082] The model prediction unit 302 is configured to acquire a target carbon emission prediction model corresponding to the target flight, and input the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight.

[0083] The extension data unit 303 is configured to determine extension data corresponding to the target flight according to the flight information, wherein the extension data is used to represent weights of carbon emission information of different cabins in the overall carbon emission information.

[0084] The extension prediction unit 304 is configured to determine sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is a sum of the plurality of sub-region carbon emission information.

[0085] The result determination unit 305 is configured to determine a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information.

[0086] The flight carbon emission prediction device provided by the embodiment of the present application acquires flight information of a target flight through the information acquisition unit 301, acquires a target carbon emission prediction model corresponding to the target flight through the model prediction unit 302, and inputs the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight. The extension data unit 303 determines extension data corresponding to the target flight according to the flight information, wherein the extension data is used to represent weights of carbon emission information of different cabins in the overall carbon emission information. The extension prediction unit 304 determines sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is a sum of the plurality of sub-region carbon emission information. The result determination unit 305 determines a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information, thereby solving the problem of low prediction accuracy of flight carbon emission in the related art. Furthermore, the effect of improving the prediction accuracy of flight carbon emission is achieved.

[0087] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the model prediction unit 302 comprises: a data acquisition module, configured to acquire a carbon emission data set within a preset time range before a departure date of the target flight; and a model training module, configured to train the preset machine learning model according to the carbon emission data set to obtain the target carbon emission prediction model.

[0088] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the preset time range comprises a first preset time period and a second preset time period, the carbon emission data set comprises a basic pool carbon emission data set in the first preset time period and an iteration pool carbon emission data set in the second preset time period, the first preset time period is earlier than the second preset time period, and the model training module comprises: a first training submodule, configured to train the preset machine learning model according to the basic pool carbon emission data set to obtain a first carbon emission prediction model; a data updating submodule, configured to update the basic pool carbon emission data set by using the iteration pool carbon emission data set to obtain a plurality of updated data sets; a second training submodule, configured to train the preset machine learning model according to the plurality of updated data sets to obtain a plurality of preset carbon emission prediction models; and a model selection submodule, configured to select the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain the target carbon emission prediction model.

[0089] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the data updating submodule comprises: a batch updating component, configured to move samples in the iteration pool carbon emission data set to the basic pool carbon emission data set in a plurality of batches to obtain a plurality of corresponding updated data sets, wherein the number of samples moved in each batch is a preset number, and one updated data set corresponding to each batch is obtained after movement of each batch.

[0090] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the extension data unit 303 comprises: a physical space factor module, configured to query the cabin layout database of the target flight according to the flight information to determine a physical space factor corresponding to the target flight, wherein the physical space factor is used to represent the proportion of the cabin physical area to the reference area; an occupancy elasticity factor module, configured to acquire an occupancy adjustment coefficient and determine an occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent the influence of the occupancy fluctuation rate on the apportioning of the sub-region carbon emission information; and a data determination module, configured to determine the extension data according to the physical space factor and the occupancy elasticity factor.

[0091] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the extended prediction unit 304 comprises: a weight prediction module configured to determine the weight of each cabin in the target flight according to the extended data; and a weight distribution module configured to distribute the overall carbon emission information according to all the weights to determine the sub-region carbon emission information corresponding to the target flight.

[0092] Optionally, in the flight carbon emission prediction device provided by the embodiment of the application, the result determination unit 305 comprises: a first determination module configured to obtain the blockchain data corresponding to the target flight; a second determination module configured to trace the blockchain data according to the order of the seat number, the flight number, the oil product batch number and the original origin code to obtain the full-link carbon traceability ID corresponding to the target flight; and a third determination module configured to take the overall carbon emission information, the sub-region carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0093] It should be noted that the information acquisition unit 301, the model prediction unit 302, the extended data unit 303, the extended prediction unit 304 and the result determination unit 305 correspond to steps S201 to S205 in Embodiment 1, and the units have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware components or software components stored in the memory (for example, the memory 104) and processed by one or more processors (for example, the processors 102a, 102b, …, 102n), and the above modules can also be run in the computer terminal 10 provided in Embodiment 1 as a part of the device.

[0094] Embodiment 3

[0095] The embodiments of the application can provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the application. As Figure 4 shown, the electronic device can include one or more (only one is shown in the figure) processors 1002, a memory 1004, a storage controller, and a peripheral interface, wherein the peripheral interface is connected with a radio frequency module, an audio module and a display. Figure 4

[0096] ​The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the method and device in the embodiments of the present application. The processor executes various functions and data processing by running the software programs and modules stored in the memory, that is, implements the above method. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0097] The processor can call information and applications stored in the memory through the transmission device to perform the following steps: obtaining flight information of a target flight; obtaining a target carbon emission prediction model corresponding to the target flight, and inputting the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; determining extended data corresponding to the target flight according to the flight information, wherein the extended data is used to represent the weight of carbon emission information of different cabins in the overall carbon emission information; determining sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extended data, wherein the overall carbon emission information is the sum of the plurality of sub-region carbon emission information; and determining a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information.

[0098] The processor can also call information and applications stored in the memory through the transmission device to perform the following steps: obtaining a carbon emission data set within a preset time range before the departure date of a target flight; training a preset machine learning model according to the carbon emission data set to obtain a target carbon emission prediction model.

[0099] The processor can also call information and applications stored in the memory through the transmission device to perform the following steps: training a preset machine learning model according to the basic pool carbon emission data set to obtain a first carbon emission prediction model; updating the basic pool carbon emission data set using the iterative pool carbon emission data set to obtain a plurality of updated data sets; training the preset machine learning model according to the plurality of updated data sets to obtain a plurality of preset carbon emission prediction models; and selecting the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain the target carbon emission prediction model.

[0100] The processor can further call information and application programs stored in the memory through the transmission device to perform the following steps: moving samples in the iteration pool carbon emission data set to the base pool carbon emission data set in batches to obtain a plurality of updated data sets corresponding to the batches, wherein the number of samples moved in each batch is a preset number, and each batch is moved to obtain an updated data set corresponding to the batch.

[0101] The processor can further call information and application programs stored in the memory through the transmission device to perform the following steps: querying the cabin layout database of the target flight according to the flight information to determine the physical space factor corresponding to the target flight, wherein the physical space factor is used to represent the proportion of the cabin physical area to the reference area; obtaining the occupancy adjustment coefficient and determining the occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent the influence of the occupancy fluctuation rate on the allocation of the sub-region carbon emission information; determining the expansion data according to the physical space factor and the occupancy elasticity factor.

[0102] The processor can further call information and application programs stored in the memory through the transmission device to perform the following steps: determining the weight of each cabin in the target flight according to the expansion data; distributing the overall carbon emission information according to all the weights to determine the sub-region carbon emission information corresponding to the target flight.

[0103] The processor can further call information and application programs stored in the memory through the transmission device to perform the following steps: obtaining the blockchain data corresponding to the target flight; tracing the target flight according to the order of the seat number, the flight number, the oil batch number and the original origin code in the blockchain data to obtain the full-link carbon traceability ID corresponding to the target flight; taking the overall carbon emission information, the sub-region carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0104] By obtaining flight information of a target flight; obtaining a target carbon emission prediction model corresponding to the target flight, and inputting the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; determining expansion data corresponding to the target flight according to the flight information, wherein the expansion data is used to represent the weight of carbon emission information of different cabins in the overall carbon emission information; determining sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the expansion data, wherein the overall carbon emission information is the sum of a plurality of sub-region carbon emission information; and determining a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information, the technical problem of low prediction accuracy of flight carbon emission in the prior art is solved.

[0105] Those skilled in the art can understand that, Figure 4The structure shown is only schematic, and the electronic device can also be a smart phone, a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or other terminal device. Figure 4 It does not limit the structure of the electronic device described above. For example, the electronic device can further include more or less components (such as a network interface, a display device, etc.) than those shown in the middle or have a different configuration from that shown. Figure 4 The structure shown is only schematic, and the electronic device can also be a smart phone, a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or other terminal device. Figure 4 The structure shown is only schematic, and the electronic device can also be a smart phone, a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or other terminal device.

[0106] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the terminal device related hardware through programs, and the programs can be stored in a computer readable storage medium, which can include a flash disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, etc.

[0107] Embodiment 4

[0108] The embodiments of the present application also provide a storage medium. Optionally, in the present embodiment, the above-mentioned storage medium can be used to save the program code executed by the flight carbon emission prediction method provided in Embodiment 1.

[0109] Optionally, in the present embodiment, the above-mentioned storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0110] Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the following steps: obtaining flight information of a target flight; obtaining a target carbon emission prediction model corresponding to the target flight, and inputting the flight information into the target carbon emission prediction model to predict overall carbon emission information corresponding to the target flight; determining extension data corresponding to the target flight according to the flight information, wherein the extension data is used to represent the weight of carbon emission information of different cabins in the overall carbon emission information; determining sub-region carbon emission information corresponding to the target flight according to the overall carbon emission information and the extension data, wherein the overall carbon emission information is the sum of the plurality of sub-region carbon emission information; and determining a carbon emission prediction result of the target flight according to the overall carbon emission information and the sub-region carbon emission information.

[0111] Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: obtaining a carbon emission data set within a preset time range before a departure date of a target flight; and training a preset machine learning model according to the carbon emission data set to obtain a target carbon emission prediction model.

[0112] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: training the preset machine learning model according to the basic pool carbon emission dataset to obtain a first carbon emission prediction model; updating the basic pool carbon emission dataset by using the iterative pool carbon emission dataset to obtain a plurality of updated datasets; training the preset machine learning model according to the plurality of updated datasets to obtain a plurality of preset carbon emission prediction models; and selecting the first carbon emission prediction model and the plurality of preset carbon emission prediction models to obtain a target carbon emission prediction model.

[0113] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: moving samples in the iterative pool carbon emission dataset to the basic pool carbon emission dataset in batches to obtain a plurality of corresponding updated datasets, wherein the number of samples moved in each batch is a preset number, and each batch is moved to obtain an updated dataset corresponding to the batch.

[0114] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: querying the cabin layout database of the target flight according to the flight information to determine the physical space factor corresponding to the target flight, wherein the physical space factor is used to represent the proportion of the cabin physical area to the reference area; obtaining the occupancy adjustment coefficient and determining the occupancy elasticity factor corresponding to the target flight according to the occupancy adjustment coefficient and the occupancy fluctuation rate of the target flight, wherein the occupancy elasticity factor is used to represent the influence of the occupancy fluctuation rate on the allocation of the sub-region carbon emission information; and determining the expansion data according to the physical space factor and the occupancy elasticity factor.

[0115] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: determining the weight of each cabin in the target flight according to the expansion data; and distributing the overall carbon emission information according to all the weights to determine the sub-region carbon emission information corresponding to the target flight.

[0116] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: obtaining the blockchain data corresponding to the target flight; and tracing the order of the seat number, the flight number, the oil batch number and the original origin code in the blockchain data to obtain the full-link carbon traceability ID corresponding to the target flight; and taking the overall carbon emission information, the sub-region carbon emission information and the full-link carbon traceability ID as the carbon emission prediction result.

[0117] Optionally, in the embodiment, the computer readable storage medium is further configured to store program code for performing the following steps: parsing the text material information in the material information according to a preset parser to obtain first text material; inputting the non-text material information in the material information into a visual language model, and determining second text material corresponding to the non-text material information according to the visual language model; and determining the material text according to the first text material and the second text material.

[0118] The application also provides a computer program product adapted to perform the steps of the method for predicting flight carbon emissions when executed on a data processing device.

[0119] The above-mentioned sequence numbers of the embodiments of the application are only for description, and do not represent advantages or disadvantages of the embodiments.

[0120] In the above-mentioned embodiments of the application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0121] In several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit embodiment described above is only schematic. For example, the division of the units is only a logical function division. There can be another division manner for actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interface, electrical or other form.

[0122] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment.

[0123] In addition, each functional unit in each embodiment of the application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0124] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0125] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. A method for predicting carbon emissions from flights, characterized in that, include: Obtain flight information for the target flight; Obtain the target carbon emission prediction model corresponding to the target flight, and input the flight information into the target carbon emission prediction model to predict the overall carbon emission information corresponding to the target flight; Based on the flight information, the extended data corresponding to the target flight is determined, wherein the extended data is used to characterize the weight of carbon emission information of different cabin classes in the overall carbon emission information; The carbon emission information of the target flight is determined based on the overall carbon emission information and extended data, wherein the overall carbon emission information is the sum of the carbon emission information of multiple sub-regions; The carbon emission prediction result for the target flight is determined based on the overall carbon emission information and the sub-regional carbon emission information.

2. The method according to claim 1, characterized in that, Obtaining the target carbon emission prediction model corresponding to the target flight includes: Obtain the carbon emissions dataset within a preset time range prior to the departure date of the target flight; The target carbon emission prediction model is obtained by training a preset machine learning model based on the carbon emission dataset.

3. The method according to claim 2, characterized in that, The preset time range includes a first preset time period and a second preset time period. The carbon emission dataset includes a base pool carbon emission dataset within the first preset time period and an iterative pool carbon emission dataset within the second preset time period. The first preset time period is earlier than the second preset time period. The preset machine learning model is trained based on the carbon emission dataset to obtain the target carbon emission prediction model, including: The preset machine learning model is trained based on the basic pool carbon emission dataset to obtain the first carbon emission prediction model; The carbon emission dataset of the basic pool is updated using the carbon emission dataset of the iterative pool to obtain multiple updated datasets; The preset machine learning model is trained based on multiple updated datasets to obtain multiple preset carbon emission prediction models; The target carbon emission prediction model is obtained by selecting from the first carbon emission prediction model and multiple preset carbon emission prediction models.

4. The method according to claim 3, characterized in that, The base pool carbon emission dataset is updated using the iterative pool carbon emission dataset to obtain multiple updated datasets, including: Samples from the iterative pool carbon emission dataset are moved to the base pool carbon emission dataset in multiple batches to obtain multiple updated datasets. The number of samples moved in each batch is a preset number, and an updated dataset corresponding to each batch is obtained after the movement.

5. The method according to claim 1, characterized in that, The extended data corresponding to the target flight determined based on the flight information includes: Based on the flight information, the cabin layout database of the target flight is queried to determine the physical space factor corresponding to the target flight, wherein the physical space factor is used to characterize the proportion of cabin physical area to the base area; Obtain the occupancy adjustment coefficient, and determine the occupancy elasticity factor corresponding to the target flight based on the occupancy adjustment coefficient and the occupancy volatility of the target flight, wherein the occupancy elasticity factor is used to characterize the impact of occupancy volatility on the allocation of carbon emission information in the sub-region. The extended data is determined based on the physical space factor and the occupancy elasticity factor.

6. The method according to claim 5, characterized in that, Determining the sub-regional carbon emission information corresponding to the target flight based on the overall carbon emission information and extended data includes: The weight of each cabin class in the target flight is determined based on the extended data; The overall carbon emission information is allocated according to all the weights to determine the carbon emission information of the sub-region corresponding to the target flight.

7. The method according to claim 1, characterized in that, The carbon emission prediction results for the target flight, determined based on the overall carbon emission information and the sub-regional carbon emission information, include: Obtain the blockchain data corresponding to the target flight; The blockchain data is traced according to the order of seat number, flight number, oil batch number and original place of origin code to obtain the full-chain carbon traceability ID corresponding to the target flight; The overall carbon emission information, the sub-regional carbon emission information, and the full-link carbon traceability ID are used as the carbon emission prediction results.

8. A device for predicting carbon emissions from flights, characterized in that, include: The information acquisition unit is used to acquire flight information of the target flight; The model prediction unit is used to obtain the target carbon emission prediction model corresponding to the target flight, and input the flight information into the target carbon emission prediction model to predict the overall carbon emission information corresponding to the target flight. An extended data unit is used to determine the extended data corresponding to the target flight based on the flight information, wherein the extended data is used to characterize the weight of carbon emission information of different cabin classes in the overall carbon emission information; An extended prediction unit is used to determine the sub-regional carbon emission information corresponding to the target flight based on the overall carbon emission information and extended data, wherein the overall carbon emission information is the sum of the carbon emission information of multiple sub-regions; The result determination unit is used to determine the carbon emission prediction result of the target flight based on the overall carbon emission information and the sub-regional carbon emission information.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the flight carbon emission prediction method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for predicting flight carbon emissions according to any one of claims 1 to 7.

Images