Civil aviation passenger transport operation index prediction method and device based on historical data

Abstract

The invention discloses a civil aviation passenger transport operation index prediction method and device based on historical data. A visual component of the device is used for displaying historical data of a core operation index and predicting the trend of the core operation index in a period of time in the future; the load balancing component is used for sharing the access request of the visual component and sending the received access request to the prediction function component; the prediction function component is used for receiving the access request, querying historical data in a database, predicting a core operation index based on the historical data to obtain a request response result, and sending the request response result to the load balancing component; and the database is used for storing the historical data of the core operation indexes and the predicted core operation indexes. The civil aviation passenger transport operation index prediction method and device based on the historical data have the advantages that prediction is carried out by comprehensively considering various special conditions of holidays and festivals on the basis of the historical data, and prediction is rapid and accurate.

Description

Technical Field

[0001] The present invention relates to a passenger transport operation index prediction technology, in particular to a civil aviation passenger transport operation index prediction method and device based on historical data. Background Art

[0002] As an important part of the global transportation network, the efficiency and effectiveness of civil aviation passenger transport operations and management directly affect the profitability and market competitiveness of airlines. The core operating indicators of civil aviation passenger transport mainly include passenger transport volume, passenger flight volume, passenger ticket sales volume, ticket order volume, etc. The core operating indicators play a decisive role in the work of airlines in formulating flight plans, optimizing resource allocation, and formulating marketing strategies.

[0003] In the ever-changing market environment, operational efficiency and decision-making accuracy have become particularly important. Predicting core operational indicators is one of the key factors to achieve this operational efficiency and decision-making accuracy.

[0004] By predicting core operating indicators, companies can identify potential trends and risks, and make more reasonable decisions in strategic planning and resource allocation. At the same time, predicting core operating indicators can also promote cross-departmental collaboration and communication, and improve the overall team's collaborative efficiency. Forecasting core operating indicators is not only a necessary means for companies to improve management level and market adaptability, but also an important guarantee for achieving long-term sustainable development.

[0005] In the prior art, traditional passenger flow prediction methods are mainly based on historical data and simple statistical analysis, and rely on a limited set of features, such as historical passenger flow, ticket price levels, flight frequency, etc. These methods are often difficult to provide sufficiently accurate prediction results when faced with complex factors such as market fluctuations, seasonal changes, and changes in the economic environment.

[0006] Therefore, for civil aviation passenger transport companies, it is urgent to design a method and system that can achieve intelligent prediction of core operating indicators. Summary of the invention

[0007] In view of the above problems, the present invention provides a method and device for predicting civil aviation passenger operation indicators based on historical data, so as to achieve rapid prediction of operation indicators for any period in the future and improve the accuracy of prediction.

[0008] The present invention adopts the following technical solutions to solve the technical problems.

[0009] The civil aviation passenger transport operation index prediction device based on historical data of the present invention comprises a visualization component, a load balancing component, a prediction function component and a database; the civil aviation passenger transport operation index comprises a core operation index;

[0010] The visualization component is used to display the historical data of the core operating indicators and predict the trend of the core operating indicators in the future;

[0011] The load balancing component is used to distribute the access requests of the visualization component and send the received access requests to the prediction function component;

[0012] The prediction function component is used to receive and process the access request sent by the load balancing component, query the historical data in the database, predict the core operating indicators according to the access request and based on the historical data to obtain the request response result, and send the request response result to the load balancing component;

[0013] The database is used to store historical data of core operating indicators and predicted core operating indicators.

[0014] The structural features of the method and device for predicting civil aviation passenger transport operation indicators based on historical data of the present invention are also as follows:

[0015] Furthermore, the core operating indicators include passenger transport volume, passenger flight volume, passenger ticket sales volume and ticket order volume.

[0016] Furthermore, the user browses the historical data of the currently existing core operating indicators and predicts the trend of the core operating indicators in the future through the visualization component.

[0017] Furthermore, the load balancing component is an nginx server.

[0018] Furthermore, the ng inx server implements load balancing adjustment by configuring upstream in the configuration file nginx.conf.

[0019] Furthermore, the request response result includes the current daily actual value of the core operating indicator, the daily predicted value of the core operating indicator that the user wants to predict, and the daily predicted value of the core operating indicator for the next holiday.

[0020] Furthermore, the database is a mysql database.

[0021] The present invention also discloses a prediction method according to a civil aviation passenger transport operation index prediction device based on historical data, comprising the following steps:

[0022] Step 1: Log in to the browser and enter the civil aviation passenger operation index prediction system;

[0023] Step 2: Click the "Query" button to send the user's access request to the load balancing component;

[0024] Step 3: After receiving the access request, the load balancing component determines whether the access request contains the predicted time range; if not, execute step 4; if there is a predicted time range, determine whether the format of the predicted time range is correct; if the format of the predicted time range is correct, execute step 4; if the format of the predicted time range is incorrect, return an error prompt;

[0025] Step 4: The load balancing component forwards the access request to the prediction function component;

[0026] Step 5: The prediction function component receives the access request and queries the historical data of the core operation indicators in response to the access request;

[0027] Step 6: The prediction function component predicts the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's prediction time range based on the historical data of the core operating indicators;

[0028] Step 7: The prediction function component returns the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the load balancing component, and the load balancing component sends the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the visualization component;

[0029] Step 8: The visualization component displays the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's predicted time range.

[0030] Furthermore, in step 2, before clicking the "Query" button, select and input the predicted time range.

[0031] Furthermore, in step 6, the prediction function component performs prediction according to a built-in prediction algorithm; the prediction includes holiday prediction and daily prediction.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0033] The present invention discloses a method and device for predicting civil aviation passenger operation indicators based on historical data. The visualization component of the device is used to display the historical data of core operation indicators and predict the trend of core operation indicators in a future period of time; the load balancing component is used to apportion the access requests of the visualization component and send the received access requests to the prediction function component; the prediction function component is used to receive access requests, query historical data in a database, predict the core operation indicators based on the historical data to obtain request response results, and send the request response results to the load balancing component; the database is used to store the historical data of core operation indicators and the predicted core operation indicators.

[0034] The method and device for predicting civil aviation passenger transport operation indicators based on historical data of the present invention have the advantages of comprehensively considering various special circumstances of holidays on the basis of historical data to make predictions, and the predictions are fast and accurate.

[0035] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 The present invention is a structural block diagram of a device for predicting civil aviation passenger transport operation indicators based on historical data.

[0038] Figure 2 The present invention is a flowchart of a method for predicting civil aviation passenger transport operation indicators based on historical data.

[0039] The present invention will be further described below through specific implementation modes in conjunction with the accompanying drawings. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] like Figure 1 The civil aviation passenger transport operation index prediction device based on historical data of the present invention comprises a visualization component, a load balancing component, a prediction function component and a database; the civil aviation passenger transport operation index comprises a core operation index;

[0042] The visualization component is used to display the historical data of the core operating indicators and predict the trend of the core operating indicators in the future;

[0043] The load balancing component is used to distribute the access requests of the visualization component and send the received access requests to the prediction function component;

[0044] The prediction function component is used to receive and process the access request sent by the load balancing component, query the historical data in the database, predict the core operating indicators according to the access request and based on the historical data to obtain the request response result, and send the request response result to the load balancing component;

[0045] The database is used to store historical data of core operating indicators and predicted core operating indicators.

[0046] The present invention is a civil aviation passenger transport operation index prediction device based on historical data. Through visualization components, load balancing components, prediction function components and databases, the future trend of core operation indicators can be predicted according to historical data, including the trend of core operation indicators in special periods such as Spring Festival, May Day and National Day. By regularly integrating historical data, it is possible to quickly predict the operation indicators of any period in the future, and the prediction results are relatively consistent with the actual results without the need to frequently update the prediction model. At the same time, the visualization function is supported by the visualization component to display the historical data, the predicted data and the trend of the data.

[0047] In specific implementation, the core operating indicators include passenger transport volume, passenger flight volume, passenger ticket sales volume and ticket order volume.

[0048] The core operating indicators include but are not limited to passenger transport volume, passenger flight volume, passenger ticket sales volume and ticket order volume. During the operation of the system, users can adjust the core operating indicators according to their needs. Among them, passenger transport volume is positively correlated with passenger flight volume, and passenger ticket sales volume is positively correlated with ticket order volume. According to actual conditions, the trend of passenger ticket sales volume and ticket order volume will rise before the trend of passenger transport volume and passenger flight volume, that is, ticket collection comes first, and transportation comes later.

[0049] In specific implementation, the user browses the historical data of the currently existing core operating indicators and predicts the trend of the core operating indicators in the future through the visualization component.

[0050] The visualization component is the front-end static page. The front-end static page refers to the page of the core operating indicator trend chart that the user sees on the browser. The main function of the front-end static page is to display the historical data of the current core operating indicators and predict the trend of the core operating indicators in the future. The front-end static page supports users to manually enter the time range for the core operating indicator forecast, which can be used to enter the time period for the core operating indicator to be predicted according to their own needs. The front-end static page can display the existing core operating indicator forecast trend chart and the core operating indicator forecast trend chart searched by the user, and can also display the core operating indicator forecast trend chart for the next holiday.

[0051] In specific implementation, the load balancing component is an nginx server.

[0052] Load balancing is an application of cluster technology. Through load balancing, work tasks can be distributed to multiple processing units, thereby improving concurrent processing capabilities. In the present invention, if a large number of users access the visualization component at the same time, the number of requests sent from the visualization component will be very large. In order to ensure the stable use of the system, a load balancing component is used. At the same time, the load balancing component will forward the received requests to the prediction function component.

[0053] During specific implementation, the ngi nx server implements load balancing adjustment by configuring upstream in the configuration file ngi nx.conf.

[0054] The load balancing component in the device of the present invention is an NGI NX server, which realizes load balancing by configuring upstream in the NGI NX configuration file NGI NX.conf. In specific implementation, an Apache server can also be used.

[0055] In specific implementation, the request response result includes the actual daily value of the current core operating indicator, the daily predicted value of the core operating indicator that the user wants to predict, and the daily predicted value of the core operating indicator for the next holiday.

[0056] The main functions of the prediction component are: processing requests sent by the load balancing component, querying the existing historical data in the database, making predictions based on the existing data, and returning the prediction results to the load balancing component. The prediction component is responsible for receiving user requests sent by the load balancing component, parsing the prediction time range in the request, querying the existing core operating indicator historical data in the database, predicting the indicator trend within the prediction time range through algorithms based on the existing historical data, and finally returning the request response results to the load balancing component. The request response results include but are not limited to: the actual daily value of the current core operating indicator, the daily predicted value of the core operating indicator that the user wants to predict, and the daily predicted value of the core operating indicator for the next holiday.

[0057] During specific implementation, the database is a mysql database.

[0058] Database: A database is a collection of large amounts of data that is stored in a computer for a long time, organized, shareable, and uniformly managed. The database in the patented device is a MySQL database or an Oracle database. The MySQL database or Oracle database is responsible for storing the historical data of existing core operating indicators, namely, the daily real data values ​​of the four core operating indicators of passenger transportation volume, passenger flight volume, passenger ticket sales volume, and ticket order volume, as well as the forecast data of the four core operating indicators in the next holiday.

[0059] The present invention also discloses a prediction method according to a civil aviation passenger transport operation index prediction device based on historical data, comprising the following steps:

[0060] Step 1: Log in to the browser and enter the civil aviation passenger operation index prediction system;

[0061] Access the front-end static page (i.e., visualization component) that displays the trend chart of core operating indicators from the browser; set the time range to be predicted in the prediction time setting box, and then click the query button.

[0062] Step 2: Click the "Query" button to send the user's access request to the load balancing component;

[0063] Step 3: After receiving the access request, the load balancing component determines whether the access request contains the predicted time range; if not, execute step 4; if there is a predicted time range, determine whether the format of the predicted time range is correct; if the format of the predicted time range is correct, execute step 4; if the format of the predicted time range is incorrect, return an error prompt;

[0064] The load balancing component receives the user's access request and first determines whether the predicted time range in the user's access request is empty; if the predicted time range is empty, the next step is executed; if the predicted time range is not empty, the next step is executed; if the format of the predicted time range in the user's request is correct, if the format is correct, the next step is executed; if not, an error prompt message is returned.

[0065] The operations of checking whether the forecast time range is empty and checking whether the forecast time range format is correct according to the present invention can be implemented in the visualization component or in the forecast function component.

[0066] Step 4: The load balancing component forwards the access request to the prediction function component;

[0067] The load balancing component forwards the access request;

[0068] Step 5: The prediction function component receives the access request and queries the historical data of the core operation indicators in response to the access request;

[0069] The prediction function component queries the existing core operation indicator data stored in the database;

[0070] Step 6: The prediction function component predicts the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's prediction time range based on the historical data of the core operating indicators;

[0071] The forecasting component uses the built-in forecasting algorithm to forecast the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's forecast time range based on the existing historical data;

[0072] Step 7: The prediction function component returns the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the load balancing component, and the load balancing component sends the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the visualization component;

[0073] Step 8: The visualization component displays the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's predicted time range.

[0074] The load balancing component forwards the return result of the prediction function component to the visualization component, and the visualization component visualizes the data based on the received return result.

[0075] During specific implementation, in step 2, before clicking the "Query" button, select and input the predicted time range.

[0076] Before clicking the "Query" button, the user can choose whether to set the time range to be predicted in the prediction time setting box.

[0077] The logic of the load balancing component to judge the user's access request is: first, judge whether the predicted time range in the user's access request is empty. If it is empty, directly forward the user's access request; if it is not empty, then judge whether the predicted time format in the user's access request is correct. The logic of this judgment is: the start date must be after the current date, and the predicted time range is not more than 60 days. The reason why the predicted time range is set to no more than 60 days is that a too long prediction time range will cause the prediction value to be distorted, and the calculation pressure is too high, which has no practical effect. If the format is correct, forward the user's access request to the prediction function component. If the format is incorrect, the error prompt message of verification failure is returned to the browser page.

[0078] After receiving the request forwarded by the load balancing component, the prediction function component queries the historical data of the core operation indicators in the following steps:

[0079] Step 01: Query the existing core operating indicator data stored in the database;

[0080] Step 02: Determine whether the prediction time range in the user request is empty. If the prediction time range in the user request is empty, query whether the prediction data of the core operating indicators of the next holiday has been cached in the database. If the database already has the prediction data of the next holiday, return all query results; if the database does not have the prediction data of the next holiday, make a prediction based on the built-in prediction algorithm, store the prediction results in the database, and integrate the query results with the prediction results and return them to the load balancing component;

[0081] Step 03: If the forecast time range in the user request is not empty, the forecast time range in the user request is predicted separately according to the built-in forecast algorithm. Then, the database is queried to see whether the forecast number of the core operating indicators for the next holiday has been cached. The logic is consistent with the above judgment logic.

[0082] Step 04: Integrate the query results and prediction results and return them to the load balancing component.

[0083] During specific implementation, in step 6, the prediction function component performs prediction based on a built-in prediction algorithm; the prediction includes holiday prediction and daily prediction.

[0084] There are two types of built-in prediction algorithms: one is holiday prediction and the other is daily prediction. Taking the holiday prediction on New Year's Day (the New Year's Day prediction duration is 3 days) as an example, the holiday prediction logic is as follows:

[0085] 1. To predict the two core operating indicators of passenger ticket sales and ticket orders, first query the database for the data of the two core operating indicators on New Year's Day last year and the five days before and after. For each indicator, take the maximum value of the 11 values ​​as the respective predicted value for New Year's Day this year. The reason for taking the data of the five days before and after is that multiple sample points help reduce deviations and improve the accuracy and reliability of estimated data. The reason for taking the maximum value is that there are a lot of passengers during the holiday period, so taking the maximum value will be closer to the actual value rather than taking the average.

[0086] 2. To predict the two core operating indicators of passenger traffic and passenger flights, first query the database for the data of the two core operating indicators on New Year's Day last year as their respective base values. Taking passenger traffic as an example, query the database for the 10 values ​​closest to this base value in the past 13 months, and take the maximum value of these 10 values ​​as the predicted value of passenger traffic on New Year's Day this year. The logic of passenger flight volume prediction is the same. The reason for querying the data of the past 13 months instead of 12 months is that the lunar calendar is different from the solar calendar. For example, the time of the New Year is not fixed every year, and there are also leap years. Therefore, taking one more month of data, that is, 13 months of data, can include all the actual data of last year.

[0087] The daily prediction logic is the same as the holiday prediction logic, and is simpler. The reason is that the daily prediction logic only needs to find the corresponding date at this time last year as the base value. The difficulty of holiday prediction is that the date of each holiday is dynamic, such as the Spring Festival. Therefore, it is more difficult to find the corresponding date from last year's data.

[0088] The device and method for predicting civil aviation passenger transport operation indicators based on historical data of the present invention have the following characteristics.

[0089] 1. In the built-in prediction algorithm, the judgment of complex situations has been considered and designed. For example, there is the Mid-Autumn Festival before the National Day and the Double Ninth Festival after the National Day. At this time, the prediction logic will first determine whether the interval between this year's Mid-Autumn Festival and the National Day is less than 7 days. If the interval is less than 7 days, the data of the two festivals will be comprehensively predicted; if the interval is more than 7 days, only the festival data that needs to be displayed will be predicted. The judgment logic of the Double Ninth Festival is the same. The reason for choosing a 7-day interval in practice is that according to historical experience, when the interval between the Mid-Autumn Festival or the Double Ninth Festival and the National Day is less than 7 days, most people will choose to take a week off and connect multiple festivals, that is, take a "long vacation". At this time, the probability of traveling within the time range is very high, so the core operating indicators such as ticket sales and passenger transportation volume will fluctuate greatly compared with usual times.

[0090] 2. The time interval and time range of the prediction logic in the built-in prediction algorithm program are configured as environmental parameters, which can be adjusted and modified according to actual conditions and experience. The time range of the prediction logic refers to, for example, judging that the Spring Festival travel season is 40 days and judging that the May Day holiday is 5 days. The time interval of the prediction logic refers to, for example, judging that the interval between the Mid-Autumn Festival and the National Day holiday is compared with 7 days.

[0091] In summary, the device and method for predicting civil aviation passenger operation indicators based on historical data of the present invention have the advantages of making predictions based on historical data in consideration of various special circumstances during holidays and festivals, and the predictions are fast and accurate.

[0092] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0093] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0094] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A civil aviation passenger transport operation index prediction device based on historical data, characterized in that: It includes a visualization component, a load balancing component, a prediction function component and a database; the civil aviation passenger transport operation indicators include core operation indicators; The visualization component is used to display the historical data of the core operating indicators and predict the trend of the core operating indicators in the future; The load balancing component is used to distribute the access requests of the visualization component and send the received access requests to the prediction function component; The prediction function component is used to receive and process the access request sent by the load balancing component, query the historical data in the database, predict the core operating indicators according to the access request and based on the historical data to obtain the request response result, and send the request response result to the load balancing component; The database is used to store historical data of core operating indicators and predicted core operating indicators.

2. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 1, characterized in that: The core operating indicators include passenger transport volume, passenger flight volume, passenger ticket sales volume and ticket order volume.

3. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 1, characterized in that: The user can browse the historical data of the currently existing core operating indicators and predict the trend of the core operating indicators in the future through the visualization component.

4. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 1, characterized in that: The load balancing component is the nginx server.

5. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 4 is characterized in that: The nginx server implements load balancing adjustment by configuring upstream in the configuration file nginx.conf.

6. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 1, characterized in that: The request response result includes the current daily actual value of the core operating indicator, the daily predicted value of the core operating indicator that the user wants to predict, and the daily predicted value of the core operating indicator for the next holiday.

7. The device for predicting civil aviation passenger transport operation indicators based on historical data according to claim 1, characterized in that: The database is a MySQL database.

8. A prediction method of the civil aviation passenger transport operation index prediction device based on historical data according to claim 1, characterized in that: The steps include: Step 1: Log in to the browser and enter the civil aviation passenger operation index prediction system; Step 2: Click the "Query" button to send the user's access request to the load balancing component; Step 3: After receiving the access request, the load balancing component determines whether the access request contains the predicted time range; if not, execute step 4; if there is a predicted time range, determine whether the format of the predicted time range is correct; if the format of the predicted time range is correct, execute step 4; if the format of the predicted time range is incorrect, return an error prompt; Step 4: The load balancing component forwards the access request to the prediction function component; Step 5: The prediction function component receives the access request and queries the historical data of the core operation indicators in response to the access request; Step 6: The prediction function component predicts the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's prediction time range based on the historical data of the core operating indicators; Step 7: The prediction function component returns the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the load balancing component, and the load balancing component sends the core operating indicator trend of the next holiday and the core operating indicator trend within the user's prediction time range to the visualization component; Step 8: The visualization component displays the trend of the core operating indicators for the next holiday and the trend of the core operating indicators within the user's predicted time range.

9. A prediction method of the civil aviation passenger transport operation index prediction device based on historical data according to claim 7, characterized in that: In step 2, before clicking the "Query" button, select the time range for input prediction.

10. A prediction method of the civil aviation passenger transport operation index prediction device based on historical data according to claim 7, characterized in that: In step 6, the prediction function component performs prediction according to a built-in prediction algorithm; the prediction includes holiday prediction and daily prediction.

Images