Holiday road passenger transport volume combination prediction method and device

Abstract

The embodiment of the application discloses a holiday highway passenger volume combination prediction method and device, the prediction method comprises the following steps: determining a prediction basis, the prediction basis is data serving as a basis for predicting a target holiday highway passenger volume, and the types of the prediction basis are at least two; determining a cross-link ratio prediction value of the target holiday highway passenger volume to be predicted and various prediction bases corresponding to an observation period according to historical data, one prediction period comprises a prediction period and an observation period, the prediction period is a period of a target holiday for which passenger volume needs to be predicted, and the observation period is a period before the prediction period; obtaining highway passenger volume prediction values corresponding to each prediction basis according to the cross-link ratio; and obtaining a final prediction value of the target holiday highway passenger volume based on the highway passenger volume prediction values corresponding to each prediction basis. The embodiment of the application is accurate in prediction.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a method and apparatus for predicting combined highway passenger traffic during holidays. Background Technology

[0002] Holidays and other special periods can lead to a surge in highway passenger traffic. This surge may affect the quality of transportation services and disrupt the smooth and orderly operation of transportation. In order to cope with the surge in passenger traffic during holidays, it is necessary to predict the highway passenger volume during holidays so that appropriate countermeasures can be taken.

[0003] Passenger volume forecasts are generally medium- to long-term forecasts, typically with a forecast period of one year, and are primarily influenced by low-frequency, slowly changing factors. Holiday passenger volume forecasts, on the other hand, are short-term forecasts, generally with a forecast period of one day or week, and are influenced by both low-frequency, slowly changing factors and rapidly changing factors. Medium- to long-term forecasting methods struggle to handle the combined effects of high- and low-frequency factors, and their application to short-term forecasts results in significant errors. Summary of the Invention

[0004] This application provides a method and apparatus for predicting combined highway passenger traffic during holidays, which can improve the accuracy of combined highway passenger traffic prediction during holidays.

[0005] In a first aspect, embodiments of this application provide a method for predicting combined highway passenger traffic during holidays, including:

[0006] The basis for prediction is determined, which is data used as the basis for predicting highway passenger traffic during target holidays, and there are at least two types of basis for prediction.

[0007] Based on historical data, the predicted value of the cross-month and cross-month ratio of the target holiday highway passenger volume to be predicted and the corresponding observation period is determined. A prediction period includes the prediction period and the observation period. The prediction period is the period of the target holiday for which passenger volume needs to be predicted, and the observation period is a period before the prediction period.

[0008] Based on the cross-month comparison, the predicted highway passenger volume values ​​corresponding to each prediction basis are obtained;

[0009] Based on the corresponding forecast values ​​of highway passenger traffic according to each forecast basis, the final forecast value of highway passenger traffic during the target holiday is obtained.

[0010] Secondly, embodiments of this application provide a holiday highway passenger volume combination prediction device, comprising:

[0011] A determining unit is used to determine the prediction basis, which is data used as the basis for predicting the target holiday highway passenger volume, and the prediction basis is of at least two types;

[0012] The calculation unit is used to determine the predicted value of the cross-month ratio of the target holiday highway passenger volume to be predicted and the corresponding observation period based on historical data. A prediction period includes the prediction period and the observation period. The prediction period is the period of the target holiday when the passenger volume needs to be predicted, and the observation period is a period before the prediction period.

[0013] The prediction unit is used to obtain the predicted value of highway passenger volume corresponding to each prediction basis according to the cross-month comparison; and to obtain the final predicted value of highway passenger volume for the target holiday based on the predicted value of highway passenger volume corresponding to each prediction basis.

[0014] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the above-mentioned embodiments.

[0015] Fourthly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the above-mentioned embodiments. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating the holiday highway passenger volume combination prediction method according to an embodiment of this application is shown.

[0018] Figure 2 This is a schematic diagram of the structure of the holiday highway passenger volume combination prediction device according to an embodiment of this application;

[0019] Figure 3 This diagram illustrates the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] 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 clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0021] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] The method described in this application can predict short-term passenger traffic such as during holidays, improve prediction accuracy, and provide support for relevant departments to deploy countermeasures.

[0024] See Figure 1 This application provides a method for predicting combined highway passenger traffic during holidays, including:

[0025] Determine the basis for forecasting. The basis for forecasting is the data used to predict highway passenger traffic during the target holiday. There should be at least two types of basis for forecasting.

[0026] Based on historical data, the predicted value of the cross-month and cross-month ratio of the target holiday highway passenger volume to be predicted and the corresponding observation period is determined. A prediction period includes the prediction period and the observation period. The prediction period is the period of the target holiday for which passenger volume needs to be predicted, and the observation period is a period before the prediction period.

[0027] The predicted highway passenger volume is obtained based on the cross-month comparison and the corresponding prediction basis.

[0028] Based on the corresponding forecast values ​​of highway passenger traffic according to each forecast basis, the final forecast value of highway passenger traffic during the target holiday is obtained.

[0029] In this embodiment, at least two prediction bases are used, each predicting the highway passenger volume independently, and the predictions are combined based on the errors of the independent predictions of each base to improve the prediction accuracy.

[0030] In an optional embodiment, determining the prediction basis includes: obtaining the correlation coefficient between the associated data of highway passenger volume and the highway passenger volume; and selecting the associated data as the prediction basis based on the correlation coefficient. The prediction basis can be selected from the associated data of highway passenger volume. In specific implementation, the prediction basis can be selected based on the correlation between the associated data and the highway passenger volume; if the correlation between the associated data and the highway passenger volume is high, it is used as the prediction basis.

[0031] The level of correlation can be determined based on the correlation coefficient. In practice, a certain number of related data points can be selected as the basis for prediction, ranked from highest to lowest correlation coefficient. For example, at least two related data points can be selected as the basis for prediction, ranked from highest to lowest correlation coefficient. The specific basis for prediction can be 3, 4, or 5 types.

[0032] In this embodiment, correlation data with a correlation coefficient greater than a selection threshold can also be used as the basis for prediction. The selection threshold can be 0.8, 0.85, 0.86, etc.

[0033] In optional embodiments, the prediction basis includes at least two of the following: highway passenger volume, trunk highway section bus traffic volume, and online ticket sales volume. For example, from January 2018 to July 2023, the correlation coefficient between highway passenger volume and trunk highway section bus traffic volume was 0.883, and the correlation coefficient between highway passenger volume and online ticket sales volume was 0.876. Bus traffic volume and online ticket sales volume can be used as prediction basis. By using strongly correlated data such as highway section bus traffic volume and online ticket sales volume as prediction basis, passenger volume can be predicted independently. Based on the errors of the independent predictions using each basis, a combined prediction is performed to improve prediction accuracy. Of course, other data strongly correlated with passenger volume can also be used as prediction basis.

[0034] The method in this application embodiment can be used to predict passenger volume during holidays. The same holiday is celebrated once a year, such as the May Day holiday, the Dragon Boat Festival holiday, and the National Day holiday. Therefore, the prediction of passenger volume for the same holiday is only done once a year, that is, the prediction cycle for passenger volume for the same holiday can be one year.

[0035] A forecasting period consists of an observation period and a forecasting period. The forecasting period is the holiday to be predicted, and the observation period is the period preceding the forecasting period. The observation period can be adjacent to the forecasting period, or it can be several days, a week, several weeks, or even a month apart. Specifically, the observation period can be one month or two months. Taking the forecasting of highway passenger traffic during the National Day holiday as an example, the forecasting period is the National Day holiday period, and the observation period is August. In practice, the forecasting basis of the observation period within the same forecasting period is used to predict the highway passenger traffic during the forecasting period. For example, the highway passenger traffic during the National Day holiday can be predicted separately using the highway passenger traffic volume, the highway cross-section bus traffic volume, and the highway online ticket sales volume in August of the same year, and then combined to obtain the final predicted value of highway passenger traffic. The highway passenger traffic volume used as the basis for the prediction can be obtained from monitoring data.

[0036] In an optional embodiment, the predicted value of the cross-month-plus ratio of the target holiday highway passenger volume with various prediction bases for the corresponding observation period is determined based on historical data, including:

[0037] Assuming the daily average of highway passenger traffic during the forecast period and the daily average used for forecasting during the observation period are... ,in Represents the prediction period number. These represent the first, second, and third cycles preceding the current cycle, respectively. These represent the observation period and the prediction period within the same prediction cycle, respectively. These represent different forecasting bases; for example, when forecasting highway passenger traffic during the National Day holiday, j=1 represents August, and j=2 represents the National Day holiday.

[0038] The cross-month ratio for each forecast period is obtained by determining the ratio of the passenger volume in the forecast period to the value of the forecast basis in the observation period within the same forecast period based on historical data.

[0039] Based on the cross-month ratios for each forecast period, a filter is used to obtain the predicted values ​​of the cross-month ratios between the target holiday highway passenger volume and various forecast bases for the corresponding observation period. Cross-month ratios for multiple forecast periods are obtained from historical data. Based on these, a filter is used to obtain the predicted value of the cross-month ratio for the current forecast period. Based on the predicted value of the cross-month ratio for the current forecast period and the forecast bases for the observation period of the current forecast period, the predicted values ​​of highway passenger volume corresponding to each forecast base can be obtained.

[0040] In an optional embodiment, the formula for calculating the cross-month ratio for each forecast period is shown in equation (1):

[0041] (1), where , For passenger volume and the first The forecast is based on cross-month comparisons; historical highway passenger traffic can be obtained through monitoring.

[0042] The formula for calculating the predicted value of the cross-link ratio is shown in equation (2) below:

[0043] (2)

[0044] in, This is the predicted value for the cross-month ratio. For a filter, the input is the nearest continuous... One prediction period The filter window width can be, for example, 3, 5, 7, etc.

[0045] In an optional embodiment, the predicted value of highway passenger volume corresponding to each prediction basis is obtained based on the cross-month comparison. The calculation formula for the predicted value of highway passenger volume is shown in equation (3).

[0046] (3)

[0047] in To use the current forecast period The forecast is based on the predicted highway passenger volume. For the current forecast period, the [number]th The prediction is based on the observed values.

[0048] In an optional embodiment, the final predicted value of the highway passenger volume for the target holiday is obtained based on the predicted value of the highway passenger volume corresponding to each prediction basis, including:

[0049] The mean square error of each prediction is calculated based on the independent prediction. The formula for calculating the mean square error is shown in equation (4).

[0050] (4)

[0051] in ; To use the first The prediction is based on the mean square error of the predicted highway passenger volume. To achieve the desired result, the sequence length used is... ; For the first The actual value of passenger volume for the forecast period of each forecast cycle. The predicted highway passenger volume is obtained using the cross-linking method based on a single forecast basis; for example, the predicted highway passenger volume is obtained by using the online ticket sales volume of road passenger transport and the average daily traffic volume of large passenger vehicles on trunk highway sections based on the corresponding cross-linking forecast values.

[0052] The final predicted value of the highway passenger volume during the holiday is obtained by linearly weighting the single prediction basis based on the mean square error. The calculation formula is shown in equation (5).

[0053] (5);

[0054] in For the first Each prediction is based on the weights of the prediction results. .

[0055] In some embodiments, the weight of the prediction result based on a single prediction basis is obtained from the mean square error of the independent prediction of each prediction basis. The formula for calculating the weight of the prediction result based on a single prediction basis is shown in equation (6).

[0056] (6).

[0057] Application examples

[0058] The following describes the method and effects of the embodiments of this application through a specific application in the forecasting of highway passenger traffic during holidays.

[0059] Data and parameters

[0060] Using three types of prediction criteria These represent highway passenger volume, online ticket sales for road passenger transport, and average daily traffic volume of large passenger vehicles on trunk highway sections, respectively. The time period is from 2018 to 2023, and the scope is the national highway network. The observation period is August each year, and the prediction period is the National Day holiday, with the holiday passenger volume predicted one month in advance. The prediction object is the average daily highway passenger volume during the 2023 National Day holiday. In formula (2) Linear regression is used; the filter window width in equation (2) In equation (4), the sequence length L = 2.

[0061] Prediction results

[0062] Using the cross-reference method, the national highway passenger volume during the 2023 National Day holiday was independently predicted using highway passenger volume, online ticket sales volume of road passenger transport, and average daily traffic volume of large passenger vehicles on trunk highway sections according to formula (3), and then combined according to formula (5). The three predicted values ​​were compared with the passenger volume monitoring values ​​obtained after the holiday, as shown in Table 1. It can be seen that due to the impact of the epidemic control policies, the prediction error based on a single basis is relatively large, while the combined prediction based on multiple bases reduces the prediction error.

[0063] Table 1 Comparison of forecast results based on single forecasting basis and combination of multiple forecasting basis (unit: 10,000 people / day)

[0064]

[0065] Table 2 compares the prediction results of various methods, including multi-prediction combination prediction, linear regression, exponential smoothing, and grey system, using highway passenger traffic during the 2023 National Day holiday as the prediction target.

[0066] Table 2 Comparison of results from various forecasting methods (unit: 10,000 people / day)

[0067]

[0068] As shown in Table 2, passenger volume is influenced by many factors. Traditional methods do not utilize the periodicity of predictions during key holidays, resulting in significant errors. Cross-correlation analysis leverages the correlation between passenger volume and the predicted data to extract the rapidly changing characteristics of the periodicity, reducing errors caused by slowly changing factors. The error is further reduced after fusing multiple prediction results.

[0069] The changes in passenger volume during holidays include slow-changing components and fast-changing components. The method in this application proposes the concept of cross-month ratio, and extracts the periodic fast-changing components by referring to different prediction criteria, which reduces the complexity of modeling a large number of slow-changing factors and improves prediction performance.

[0070] The method in this application calculates the characteristic parameters of the periodic fast-changing component and predicts the parameters of the fast-changing component based on the slow-changing property, which can improve the adaptability of short-term forecasts to different volatility factors.

[0071] The method combination prediction in the embodiments of this application can be a combination of prediction results from different methods, or a combination of prediction results from the same method using different criteria, which can reduce the prediction error of a single method or a single criterion.

[0072] This application provides a holiday highway passenger volume combination prediction device. The device of this application can implement the method of the above embodiment. The above method embodiment can be used to understand the device of this application, and the description of the device embodiment below can also be used to understand the method of the above embodiment.

[0073] See Figure 2 The holiday highway passenger volume combination prediction device of this application includes a determining unit, a calculation unit, and a prediction unit. The determining unit is used to determine the prediction basis, which is data used as the basis for predicting the highway passenger volume of the target holiday. There are at least two types of prediction basis. The calculation unit is used to determine the predicted value of the cross-month ratio of the highway passenger volume of the target holiday to be predicted with the corresponding observation period based on historical data. A prediction period includes a prediction period and an observation period. The prediction period is the period of the target holiday for which the passenger volume needs to be predicted, and the observation period is a period before the prediction period. The prediction unit is used to obtain the predicted value of the highway passenger volume corresponding to each prediction basis based on the cross-month ratio. Based on the predicted value of the highway passenger volume corresponding to each prediction basis, the final predicted value of the highway passenger volume of the target holiday is obtained.

[0074] This application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the methods described above.

[0075] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, terminal 600 may include: at least one processor 601, at least one network interface 604, user interface 603, memory 605, and at least one communication bus 602.

[0076] The communication bus 602 is used to enable communication between these components.

[0077] The user interface 603 may include a display screen and a camera. Optionally, the user interface 603 may also include a standard wired interface and a wireless interface.

[0078] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0079] The processor 601 may include one or more processing cores. The processor 601 connects to various parts within the terminal 600 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 605, and by calling data stored in the memory 605. Optionally, the processor 601 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 601 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 601.

[0080] The memory 605 may include random access memory (RAM) or read-only memory. Optionally, the memory 605 may include a non-transitory computer-readable storage medium. The memory 605 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 605 may also be at least one storage device located remotely from the aforementioned processor 601. Figure 3 As shown, the memory 605, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs.

[0081] exist Figure 3 In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 601 can be used to call the application stored in the memory 605 and specifically execute the operations of any of the above method embodiments.

[0082] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0083] This application also provides a computer program product including a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0084] Those skilled in the art will clearly understand that the technical solutions of this application can be implemented using software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware capable of independently performing or cooperating with other components to perform specific functions. Hardware may include, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0085] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0086] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0090] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0091] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0092] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for combined prediction of holiday road passenger traffic volume, characterized in that, The method comprises the following steps: determining prediction basis, which is data serving as basis for predicting target holiday road passenger volume, and the types of the prediction basis are at least two; determining, according to historical data, prediction values of cross-link ratios of the target holiday road passenger volume and corresponding observation periods with respect to various prediction basis, wherein one prediction cycle comprises a prediction period and an observation period, the prediction period is a period of the target holiday for which passenger volume needs to be predicted, and the observation period is a period before the prediction period; obtaining, according to the cross-link ratios, prediction values of road passenger volume corresponding to each prediction basis; obtaining, based on the prediction values of road passenger volume corresponding to each prediction basis, a final prediction value of the target holiday road passenger volume; determining, according to historical data, prediction values of cross-link ratios of the target holiday road passenger volume and corresponding observation periods with respect to various prediction basis, comprising: Assume that the daily average of the highway passenger volume in the prediction period and the daily average of the prediction basis in the observation period are wherein represents the prediction cycle number, respectively represent the first cycle, the second cycle and the third cycle before the current cycle; respectively represent the observation period and the prediction period in the same prediction cycle; represents different prediction bases; determining, according to historical data, a ratio of a value of the prediction period passenger volume to a value of the observation period prediction basis to obtain a cross-link ratio of each prediction cycle; obtaining, according to the cross-link ratios of each prediction cycle, prediction values of cross-link ratios of the target holiday road passenger volume and corresponding observation periods with respect to various prediction basis by using a filter; a calculation formula of the cross-link ratio of each prediction cycle is shown in formula (1): (1), wherein , is the cross-ring ratio of the passenger volume and the first forecasted basis; a calculation formula of the prediction value of the cross-link ratio is shown in formula (2): （2） wherein, is the forecast value for the cross-ring ratio, is the filter, Using linear regression, the input is the last consecutive periods of ; obtaining, according to the cross-link ratios, prediction values of road passenger volume corresponding to each prediction basis, shown in formula (3), （3） wherein is the predicted highway passenger traffic for the current prediction period, is the observed value for the current prediction period, is the observed value for the current prediction period.​ 2. The method of claim 1, wherein, determining prediction basis, comprising: obtaining correlation data of road passenger volume and a correlation coefficient of road passenger volume; selecting the correlation data as prediction basis according to the correlation coefficient.

3. The method of claim 2, wherein, The prediction basis comprises at least two of road passenger volume, trunk road section large bus traffic volume and road passenger network ticket sales volume.

4. The method of claim 1, wherein, obtaining, based on the prediction values of road passenger volume corresponding to each prediction basis, a final prediction value of the target holiday road passenger volume, comprising: calculating mean square errors of independent prediction of each prediction basis, a calculation formula of the mean square error is shown in formula (4), （4） wherein ; is the mean square error of the prediction of the road passenger traffic volume using the first ; is the mean square error of the prediction of the road passenger traffic volume using the first ; is the actual value of the predicted period passenger traffic volume for the first ; is the predicted value of the road passenger traffic volume obtained using the single prediction basis cross-link ratio method; linearly weighting road passenger volume predicted by a single prediction basis according to the mean square error to obtain a final prediction value of the target holiday road passenger volume, a calculation formula is shown in formula (5), （5）； wherein is the th prediction result, ; a calculation formula of the weight of the prediction result of the single prediction basis is shown in formula (6), （6）。 5. A device for combined prediction of highway passenger traffic volume on holidays, characterized in that The method comprises the following steps: a determination unit is configured to determine prediction basis, which is data serving as basis for predicting target holiday road passenger volume, and the types of the prediction basis are at least two; The computing unit is used for determining the predicted value of the cross-link ratio of the various prediction bases of the target holiday road passenger volume and the corresponding observation period according to historical data, wherein one prediction period contains a prediction period and an observation period, the prediction period is the period of the target holiday for which the passenger volume needs to be predicted, and the observation period is a period before the prediction period; the predicted value of the cross-link ratio of the target holiday road passenger volume and the corresponding observation period is determined according to historical data, which comprises: assuming that the daily average of the road passenger volume in the prediction period and the daily average of the prediction basis in the observation period are , wherein represents the serial number of the prediction period, respectively represent a first period, a second period and a third period before the current period; respectively represent the observation period and the prediction period in the same prediction period; represents different prediction bases; the cross-link ratio of each prediction period is obtained according to the ratio of the passenger volume in the prediction period to the value of the prediction basis in the observation period in the same prediction period according to historical data; the predicted value of the cross-link ratio of the various prediction bases of the target holiday road passenger volume and the corresponding observation period is obtained by using a filter according to the cross-link ratio of each prediction period; the calculation formula of the cross-link ratio of each prediction period is shown in formula (1): (1), wherein , is the cross-ring ratio of the passenger volume and the first forecasted basis; a calculation formula of the prediction value of the cross-link ratio is shown in formula (2): （2） wherein, is the forecast value of the cross-ring ratio, is the filter, linear regression is used, with the input being the last consecutive periods of a prediction unit is configured to obtain, according to the cross-link ratios, prediction values of road passenger volume corresponding to each prediction basis; obtain, based on the prediction values of road passenger volume corresponding to each prediction basis, a final prediction value of the target holiday road passenger volume; wherein the prediction values of road passenger volume corresponding to each prediction basis are obtained according to the cross-link ratios, shown in formula (3), （3） wherein is the predicted highway passenger traffic for the current prediction period, is the predicted highway passenger traffic for the current prediction period, is the predicted highway passenger traffic for the current prediction period, is the observed value for the current prediction period.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method in any one of claims 1-4.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method in any one of claims 1-4.

Images