Civil aviation route income risk early warning method and system

Abstract

The invention relates to a civil aviation route income risk early warning method and system. The method comprises the following steps: acquiring operation financial data of a civil aviation route; generating a route income trend chart according to the operation financial data; constructing a block chain; storing the operation financial data on the block chain, and storing the airline income trend chart outside the block chain; constructing a risk identification model based on a computer vision identification method; inputting the airline income trend chart into a risk identification model for risk prediction to obtain an airline income risk identification result; judging whether investment risks exist or not according to the airline income risk identification result, and if yes, outputting income risk early warning information; if not, obtaining operation financial data on the block chain through the smart contract; according to the method, the external investor can preliminarily know the operation condition of the airline company through the disclosed operation trend chart, and the investment risk of the investor is reduced while the financial data security of the company is ensured.

Description

Technical Field

[0001] The present invention relates to the field of civil aviation transportation digital technology, and in particular to a civil aviation route revenue risk early warning method and system. Background Art

[0002] With the rapid development of the aviation industry, civil aviation financial support, as a key means of promoting route opening and operation, has drawn considerable attention to its management efficiency and transparency. Investors require access to financial data to understand route operations. However, disclosing financial data effectively compromises confidential information, and excessive confidentiality can increase investment risk. Summary of the Invention

[0003] In order to solve the technical problem in the prior art that excessive confidentiality of financial data may lead to increased investment risks for investors, the present invention provides a civil aviation route profit risk warning method and system.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] A civil aviation route revenue risk early warning method comprises the following steps:

[0006] Obtain operational financial data of civil aviation routes;

[0007] generating a route revenue trend graph based on the operational financial data;

[0008] Building blockchain;

[0009] Storing the operational financial data on the blockchain and storing the route revenue trend chart outside the blockchain;

[0010] Construct risk identification model based on computer vision recognition method;

[0011] The route revenue trend graph outside the blockchain is input into the risk identification model to perform risk prediction, thereby obtaining a route revenue risk identification result;

[0012] Determine whether there is investment risk based on the route profit risk identification result. If so, output profit risk warning information; if not, obtain the operational financial data on the blockchain through a smart contract.

[0013] The beneficial effects of the present invention are: by generating a route revenue trend chart based on operational financial data, and identifying risks in the route revenue trend chart through a computer vision recognition model, investors can have a preliminary understanding of the route's revenue risk through the public network; they can also have a preliminary understanding of the airline's initial operation status based on the revenue risk, and then obtain specific operation data on the blockchain based on the smart contract to determine whether to invest; the present invention can ensure the security of the airline's specific operation data, and can also allow external investors to have a preliminary understanding of the airline's operation status through the public operation trend chart, thereby ensuring the security of the company's financial data while reducing the investment risk of investors.

[0014] On the basis of the above technical solution, the present invention can also be improved as follows.

[0015] Furthermore, the operational financial data includes monthly route profit data and route distribution data, wherein the monthly route profit data includes multiple monthly profit data, and the monthly profit data is the profit of a route in one month;

[0016] Generate a route revenue trend chart based on the operational financial data. The specific steps are as follows:

[0017] Calculating a route development potential index based on the route distribution data of each of the operational financial data;

[0018] Calculate the development potential value of the route based on the monthly profit data and development potential index of each flight;

[0019] The route revenue trend graph is generated based on the monthly development potential value of the route.

[0020] Furthermore, the route development potential index is calculated based on the route distribution data of each of the operational financial data as follows:

[0021]

[0022] Among them, u represents the route development potential index, A1 and A2 represent the GDP of the route’s starting area, and B1 represents the national GDP;

[0023] The formula for calculating the route's development potential value based on the monthly profit data of each flight and the development potential index is as follows:

[0024] D1=C1(1+u);

[0025] Wherein, D1 represents the development potential value, and C1 represents the value of the monthly profit data of the flight.

[0026] Furthermore, a risk identification model is constructed based on computer vision recognition methods, which specifically includes the following steps:

[0027] Build deep learning models based on computer vision recognition methods;

[0028] Normal profit trend graphs and abnormal profit trend graphs are collected to train the deep learning model to obtain the risk identification model; wherein, the abnormal profit trend graphs include profit stagnation trend graphs, profit stagnation trend graphs, profit decline trend graphs and profit fluctuation trend graphs.

[0029] Furthermore, the route revenue risk identification results include revenue halt, revenue stagnation, revenue decline and revenue fluctuation; the revenue halt, revenue stagnation, revenue decline and revenue fluctuation correspond to the revenue halt trend graph, the revenue stagnation trend graph, the revenue decline trend graph and the revenue fluctuation trend graph respectively.

[0030] Furthermore, whether there is investment risk is determined based on the route revenue risk identification result, and the specific steps are as follows:

[0031] If the route revenue risk identification result includes any one of the revenue stop, the revenue stagnation, the revenue decline and the revenue fluctuation, it is determined that there is investment risk.

[0032] Furthermore, outputting the profit risk warning information includes the following steps:

[0033] Calculate a risk score based on the route revenue risk identification result;

[0034] The risk level is determined based on the risk score value; wherein the risk level includes low risk, medium risk and high risk.

[0035] Furthermore, the risk score is calculated based on the route revenue risk identification result, and the calculation formula is as follows:

[0036] Risk_Score=w1·Confidence+w2·Deviation;

[0037] Among them, Risk_Score represents the risk score value, Confidence represents the prediction confidence of the risk identification model, Deviation represents the route revenue risk identification result, w1 represents the confidence index, and w2 represents the prediction result index.

[0038] In order to solve the above technical problems, the present invention also provides a civil aviation route revenue risk early warning system, the specific technical contents of which are as follows:

[0039] A civil aviation route revenue risk early warning system, comprising:

[0040] A data processing module is used to obtain the operational financial data of civil aviation routes; and generate a route revenue trend chart based on the operational financial data;

[0041] A risk prediction module is configured to construct a blockchain; store the operational financial data on the blockchain and store the route revenue trend chart outside the blockchain; construct a risk identification model based on a computer vision recognition method; and perform risk prediction by inputting the route revenue trend chart outside the blockchain into the risk identification model to obtain a route revenue risk identification result.

[0042] The risk determination module is used to determine whether there is investment risk based on the route profit risk identification result. If so, it outputs profit risk warning information; if not, it obtains the operational financial data on the blockchain through a smart contract.

[0043] In order to solve the above technical problems, the present invention further provides a storage medium, the specific technical contents of which are as follows:

[0044] A storage medium stores a computer program or computer instructions, which, when executed by a computer processor, implements the steps of the above-mentioned civil aviation route revenue risk warning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of a flow chart of a civil aviation route revenue risk early warning method according to an embodiment of the present invention;

[0046] Figure 2 The figure is a schematic structural diagram of a civil aviation route revenue risk early warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0048] like Figure 1 As shown, this embodiment provides a civil aviation route revenue risk early warning method, including the following steps:

[0049] S1. Obtain operational financial data of civil aviation routes;

[0050] To obtain the operational financial data of civil aviation routes, the specific steps are as follows:

[0051] Revenue data of multiple routes of an airline are obtained, and corresponding multiple operating financial data are obtained.

[0052] S2. generating a route revenue trend chart based on the operational financial data;

[0053] The operational financial data includes monthly route profit data and route distribution data. The monthly route profit data includes multiple months of profit data. The monthly profit data is the profit of a route in one month.

[0054] Generate a route revenue trend chart based on the operational financial data. The specific steps are as follows:

[0055] S201. Calculating a route development potential index based on route distribution data of each of the operational financial data;

[0056] The formula for calculating the route development potential index based on the route distribution data of each of the above-mentioned operating financial data is as follows:

[0057]

[0058] Among them, u represents the route development potential index, A1 and A2 represent the GDP of the starting area of the route respectively, and B1 represents the national GDP; for example, the two places on a route are place A and place B, and the GDP (regional gross domestic product) of place A, then the route development potential index of this route is the sum of the GDP of place A and place B divided by the national GDP (gross domestic product), and the national GDP (gross domestic product) is the GDP of the country where the airline operating the route is located or registered.

[0059] By setting the route development potential index, the larger the route development potential index is, the greater the development potential of the route is, which can improve the investment reference value.

[0060] S201. Calculate the development potential value of the route based on the monthly profit data and development potential index of each flight;

[0061] The formula for calculating the route's development potential value based on the monthly profit data of each flight and the development potential index is as follows:

[0062] D1=C1(1+u);

[0063] Wherein, D1 represents the development potential value, and C1 represents the value of the monthly profit data of the flight.

[0064] S203. Generate the route revenue trend chart based on the monthly development potential value of the route. S3. Build a blockchain;

[0065] S4. Storing the operational financial data on the blockchain and storing the route revenue trend chart outside the blockchain;

[0066] S5. Construct a risk identification model based on computer vision recognition methods;

[0067] Building a risk identification model based on computer vision recognition methods includes the following steps:

[0068] S501. Build a deep learning model based on computer vision recognition methods. The backbone network of this deep learning model uses ResNet-18 as a feature extractor, adapting to the local structural characteristics of chart images. It also embeds a CBAM module (channel + spatial attention) to enhance sensitivity to key areas. The output layer outputs an anomaly model using SoftMax.

[0069] S502: Collect normal and abnormal revenue trend graphs to train the deep learning model and obtain the risk identification model. The abnormal revenue trend graphs include revenue stagnation trend graphs, revenue stagnation trend graphs, revenue decline trend graphs, and revenue fluctuation trend graphs. The normal revenue trend graphs, abnormal revenue trend graphs, and route revenue trend graphs can all be trend graphs such as line graphs, bar graphs, or pie charts.

[0070] The dataset was constructed by collecting 10,000 annotated charts (normal: abnormal = 7:3), including line charts and bar charts. The annotations include anomaly type, bounding box coordinates, and confidence labels. Data was augmented using affine transformations (rotation ±15°, scaling 0.8-1.2 times), Gaussian noise addition (o = 0.05), and random occlusion (simulating label overlap). A FocalLoss loss function (α = 0.25, γ = 2) was used to mitigate class imbalance. Training was performed with an initial learning rate of 0.001, Cosine annealing scheduling, and a batch size of 32. The revenue fluctuation trend chart shows significant fluctuations in revenue trends.

[0071] The route revenue risk identification results include revenue halt, revenue stagnation, revenue decline and revenue fluctuation; the revenue halt, revenue stagnation, revenue decline and revenue fluctuation correspond to the revenue halt trend graph, the revenue stagnation trend graph, the revenue decline trend graph and the revenue fluctuation trend graph respectively.

[0072] S6. Inputting the route revenue trend graph outside the blockchain into the risk identification model to perform risk prediction, thereby obtaining a route revenue risk identification result.

[0073] Capture the route revenue trend chart generated by ECharts in real time and scale it to a fixed size (e.g., 512×512 pixels) to maintain the aspect ratio and avoid distortion. Export the chart to PNG format using HTML5 Canvas, preserving the original vector information. Convert the color chart to grayscale to simplify computational complexity using the formula: Gray = 0.299R + 0.587G + 0.114B, where Gray represents the grayscale value of the grayscale image, and R, G, and B represent the values of the red, green, and blue channels, respectively, in the color model. Use the Ostu algorithm to automatically determine the threshold value and separate the foreground (chart lines and text) from the background.

[0074] S7. Determine whether there is investment risk based on the route revenue risk identification result. If so, output revenue risk warning information; if not, obtain the operational financial data on the blockchain through a smart contract.

[0075] Based on the results of the route income risk identification, determine whether there is investment risk. The specific steps are as follows:

[0076] If the route revenue risk identification result includes any one of the revenue stop, the revenue stagnation, the revenue decline and the revenue fluctuation, it is determined that there is investment risk.

[0077] Outputting income risk warning information includes the following steps:

[0078] Calculate a risk score based on the route revenue risk identification result;

[0079] The risk level is determined based on the risk score value; wherein the risk level includes low risk, medium risk and high risk.

[0080] The risk score is calculated based on the route revenue risk identification results. The calculation formula is as follows:

[0081] Risk_Score=w1·Confidence+w2·Deviation;

[0082] Where Risk_Score represents the risk score, Confidence represents the prediction confidence of the risk identification model, Deviation represents the route revenue risk identification result, w1 represents the confidence index, and w2 represents the prediction result index. By scoring risk identification, it is easier to determine the risk prediction level based on the risk score.

[0083] w1 and w2 are adjustable. The results are divided into three levels: low risk (Risk_Score range: 0-0.3: yellow prompt, suggesting observation), medium risk (Risk_Score range: 0.3-0.7: orange warning, triggering manual review), and high risk (Risk_Score > 0.7: red alert). Alerts can be highlighted on the front-end page, for example, by overlaying a semi-transparent block on the original echarts chart (e.g., red indicates a high-risk area).

[0084] Collectively, a 30-day return trend line chart for a particular route was input and preprocessed (grayscaling, Otsu binarization, and morphological denoising). Keypoint detection and curvature analysis identified the extreme curvature on the 25th day (k = 0.12). Model inference: ResNet-18 output anomaly type = "sudden drop," confidence = 0.94, and the route return risk identification result was set to a value of 0.4; w1 = 0.6, w2 = 0.45, with the w2 bounding box coordinates (23, 150) - (27, 180). Risk assessment: Risk score = 0.94 * 0.6 + 0.4 * 0.45 = 0.82, indicating a red alert.

[0085] The embodiment of the present invention generates a route revenue trend chart based on operational financial data, and identifies risks in the route revenue trend chart through a computer vision recognition model, so that investors can have a preliminary understanding of the route's revenue risk through the public network; it can also initially understand the initial operation status of the airline based on the revenue risk, and then obtain specific operation data on the blockchain based on the smart contract to determine whether to invest; the present invention can ensure the security of the airline's specific operation data, and also allow external investors to have a preliminary understanding of the airline's operation status through the public operation trend chart, thereby ensuring the security of the company's financial data while reducing the investment risk of investors.

[0086] like Figure 2 As shown, in some other embodiments, a civil aviation route revenue risk early warning system is provided, including:

[0087] A data processing module is used to obtain the operational financial data of civil aviation routes; and generate a route revenue trend chart based on the operational financial data;

[0088] A risk prediction module is configured to construct a blockchain; store the operational financial data on the blockchain and store the route revenue trend chart outside the blockchain; construct a risk identification model based on a computer vision recognition method; and perform risk prediction by inputting the route revenue trend chart outside the blockchain into the risk identification model to obtain a route revenue risk identification result.

[0089] The risk determination module is used to determine whether there is investment risk based on the route profit risk identification result. If so, it outputs profit risk warning information; if not, it obtains the operational financial data on the blockchain through a smart contract.

[0090] Example 2

[0091] Based on Example 1, this embodiment provides a storage medium, which stores a computer program or computer instructions. When the computer program or the computer instructions are executed by a computer processor, the steps of the above-mentioned civil aviation route revenue risk warning method are implemented.

[0092] The storage medium may be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The storage medium may also be an external storage device of any device with data processing capabilities, such as a plug-in hard disk, smart memory card, SD card, flash memory card, etc. equipped on the device. Furthermore, the storage medium may also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and may also be used to temporarily store data that has been output or is to be output.

[0093] Example 3

[0094] Based on Example 1, this embodiment provides a computer, including a memory and one or more processors, wherein the memory stores executable code, and when one or more processors execute the executable code, the steps of a civil aviation route revenue risk warning method in Example 1 are implemented.

[0095] The memory may be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The memory may also be an external storage device of any device with data processing capabilities, such as a plug-in hard disk, smart memory card, SD card, flash memory card, etc. equipped on the device. Furthermore, the memory may include both an internal storage unit and an external storage device of any device with data processing capabilities. The memory is used to store the computer program and other programs and data required by any device with data processing capabilities, and may also be used to temporarily store data that has been output or is to be output.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the concept and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A civil aviation route revenue risk early warning method, characterized by: The steps include: Obtain operational financial data of civil aviation routes; generating a route revenue trend graph based on the operational financial data; Building blockchain; Storing the operational financial data on the blockchain and storing the route revenue trend chart outside the blockchain; Construct risk identification model based on computer vision recognition method; The route revenue trend graph outside the blockchain is input into the risk identification model to perform risk prediction, thereby obtaining a route revenue risk identification result; Determine whether there is investment risk based on the route revenue risk identification result, and if so, output revenue risk warning information; If not, the operational financial data on the blockchain is obtained through a smart contract.

2. The civil aviation route revenue risk early warning method according to claim 1, characterized in that: The operational financial data includes monthly route profit data and route distribution data. The monthly route profit data includes multiple months of profit data. The monthly profit data is the profit of a route in one month. Generate a route revenue trend chart based on the operational financial data. The specific steps are as follows: Calculating a route development potential index based on the route distribution data of each of the operational financial data; Calculate the development potential value of the route based on the monthly profit data and development potential index of each flight; The route revenue trend graph is generated based on the monthly development potential value of the route.

3. The civil aviation route revenue risk early warning method according to claim 2, characterized in that: The formula for calculating the route development potential index based on the route distribution data of each of the above-mentioned operating financial data is as follows: Among them, u represents the route development potential index, A1 and A2 represent the GDP of the route’s starting area, and B1 represents the national GDP; The formula for calculating the route's development potential value based on the monthly profit data of each flight and the development potential index is as follows: D1=C1(1+u); Wherein, D1 represents the development potential value, and C1 represents the value of the monthly profit data of the flight.

4. The civil aviation route revenue risk early warning method according to claim 3, characterized in that: Building a risk identification model based on computer vision recognition methods includes the following steps: Build deep learning models based on computer vision recognition methods; Normal profit trend graphs and abnormal profit trend graphs are collected to train the deep learning model to obtain the risk identification model; wherein, the abnormal profit trend graphs include profit stagnation trend graphs, profit stagnation trend graphs, profit decline trend graphs and profit fluctuation trend graphs.

5. The civil aviation route revenue risk early warning method according to claim 4, characterized in that: The route revenue risk identification results include revenue halt, revenue stagnation, revenue decline and revenue fluctuation; the revenue halt, revenue stagnation, revenue decline and revenue fluctuation correspond to the revenue halt trend graph, the revenue stagnation trend graph, the revenue decline trend graph and the revenue fluctuation trend graph respectively.

6. The civil aviation route revenue risk early warning method according to claim 5, characterized in that: Based on the results of the route income risk identification, determine whether there is investment risk. The specific steps are as follows: If the route revenue risk identification result includes any one of the revenue stop, the revenue stagnation, the revenue decline and the revenue fluctuation, it is determined that there is investment risk.

7. The civil aviation route revenue risk early warning method according to claim 6, characterized in that: Outputting income risk warning information includes the following steps: Calculate a risk score based on the route revenue risk identification result; The risk level is determined based on the risk score value; wherein the risk level includes low risk, medium risk and high risk.

8. The civil aviation route revenue risk early warning method according to claim 7, characterized in that: The formula for calculating the risk score based on the route revenue risk identification results is as follows: Risk_Score=w1·Confidence+w2·Deviation; Among them, Risk_Score represents the risk score value, Confidence represents the prediction confidence of the risk identification model, Deviation represents the route revenue risk identification result, w1 represents the confidence index, and w2 represents the prediction result index.

9. A civil aviation route revenue risk early warning system, characterized by: include: Data processing module, used to obtain operational financial data of civil aviation routes; generating a route revenue trend graph based on the operational financial data; Risk prediction module, used to build blockchain; Storing the operational financial data on the blockchain and storing the route revenue trend chart outside the blockchain; Construct risk identification model based on computer vision recognition method; The route revenue trend graph outside the blockchain is input into the risk identification model to perform risk prediction, thereby obtaining a route revenue risk identification result; a risk determination module, configured to determine whether there is an investment risk based on the route revenue risk identification result, and if so, output revenue risk warning information; If not, the operational financial data on the blockchain is obtained through a smart contract.

10. A storage medium, characterized in that: The storage medium stores a computer program or computer instructions, and when the computer program or the computer instructions are executed by a computer processor, the steps of the civil aviation route revenue risk warning method according to any one of claims 1 to 8 are implemented.

Images