Construction Method of Highway Transfer Traffic Volume Prediction Model

Abstract

The present invention discloses a method for constructing a highway transfer traffic volume prediction model, which includes collecting traffic flow monitoring data and influence data of a preset highway, and preprocessing the traffic flow monitoring data and the influence data; obtaining time-varying data through time-varying screening of the traffic flow monitoring data, and performing behavior preference analysis on the time-varying data to obtain transfer probabilities; performing influence analysis on the influence data to obtain indefinite factors, and constructing a highway transfer traffic volume prediction model according to the transfer probabilities, the indefinite factors and the traffic flow monitoring data; optimizing the highway transfer traffic volume prediction model according to prediction errors, and outputting a target model. This method can not only improve the accuracy of highway transfer traffic volume prediction, but also has good interpretability and can be directly applied to highway transfer traffic volume prediction systems.

Description

Technical Field

[0001] The present invention relates to the field of prediction construction, and particularly to a method for constructing a highway transfer traffic volume prediction model. Background Art

[0002] With the acceleration of the urbanization process and the increasing complexity of the traffic network, the accurate prediction of highway traffic volume is of crucial significance for traffic management, planning, and alleviating traffic congestion. Traditional traffic flow prediction methods often rely on the statistical analysis of historical data. However, when facing a dynamically changing traffic environment, the prediction accuracy and adaptability of these methods have obvious limitations. Especially when affected by non-daily factors such as holidays, special weather, and emergencies, the prediction ability of traditional models is greatly reduced.

[0003] In order to more accurately predict the highway transfer traffic volume, that is, the behavioral changes of vehicles choosing different routes or traffic modes under different time periods and road conditions, a prediction model that can comprehensively consider various influencing factors and has the ability of self-optimization is needed. Existing research and practice have shown that simply relying on historical flow data can no longer meet this requirement, because the change of traffic flow is not only affected by periodic factors such as time and season, but also jointly affected by many uncertain factors such as weather conditions, road construction, traffic accidents, and social and economic activities.

[0004] Therefore, there is a need to invent a new highway transfer traffic volume prediction model to improve the accuracy, real-time performance, and precision of highway transfer traffic volume prediction. Summary of the Invention

[0005] The object of the present invention is to provide a method for constructing a highway transfer traffic volume prediction model.

[0006] To achieve the above object, the present invention is implemented according to the following technical solution:

[0007] The present invention includes the following steps:

[0008] Collect the flow monitoring data and influence data of the preset highway traffic, and preprocess the flow monitoring data and the influence data;

[0009] Obtain time-varying data through time-varying screening of the flow monitoring data, and perform behavioral preference analysis on the time-varying data to obtain transfer probabilities;

[0010] Perform influence analysis on the influence data to obtain uncertain factors, and construct a highway transfer traffic volume prediction model according to the transfer probabilities, the uncertain factors, and the flow monitoring data;

[0011] Optimize the highway transfer traffic volume prediction model according to the prediction error, and output the target model.

[0012] Further, a method for obtaining time-varying data by performing time-varying screening on the traffic monitoring data includes:

[0013] Calculating the linear correlation between traffic monitoring data, and clustering the traffic monitoring data according to the linear correlation to obtain classifications;

[0014] Calculating the information entropy of the traffic monitoring data:

[0015] ;

[0016] where the information entropy of the y-th traffic monitoring data is , the number of classifications is , and the proportion of the y-th traffic monitoring data in the i-th classification is ;

[0017] Calculating the value of the traffic monitoring data:

[0018] ;

[0019] where the value of the y-th dimensionality-reduced data is , the average value of the traffic monitoring data is , the y-th traffic monitoring data in the i-th classification is , the number of traffic monitoring data is , and the number of classifications is ;

[0020] Calculating the time-varying degree of the traffic monitoring data:

[0021] ;

[0022] where the y-th traffic monitoring data is , the time-varying degree of the traffic monitoring data from the s-th moment to the (s + 1)-th moment is , the y-th traffic monitoring data at the s-th moment is , the y-th traffic monitoring data at the (s + 1)-th moment is , and the regulation factor is ;

[0023] Outputting the traffic monitoring data with a time-varying degree greater than 0.3072 as time-varying data.

[0024] Further, a method for obtaining a transition probability by performing behavior preference analysis on the time-varying data includes:

[0025] Calculating the transportation time, transportation cost, and connection ability of the highway corresponding to the highway transfer traffic volume, and taking shorter transportation time, lower transportation cost, and convenient connection as preference types;

[0026] Use the time series analysis algorithm to perform preference analysis on time-varying data according to the preference type to obtain the preference quantity and preference weight;

[0027] Obtain the traffic data of the vehicle. When a highway has multiple preference types at the same time, use the ratio of the preference times to the on-road times of the same vehicle in different time periods as the preference weight;

[0028] Calculate the transition probability according to the preference weight and preference quantity:

[0029] ;

[0030] Among them, the transition probability of the xth preference type is , the preference weight of the xth preference type is , the preference quantity is , the highway transfer traffic volume at the s-th moment is , the upper limit of the test time .

[0031] Furthermore, a method for performing impact analysis on the impact data to obtain an indefinite factor includes:

[0032] Sort the impact data in chronological order, input the sorted impact data into the time series impact analysis model, and calculate the weighted change amount of the impact data:

[0033] ;

[0034] Among them, the weighted change amount of the a-th impact data monitored for the c-th time is , the a-th impact data at the (s + 1)-th moment is , the a-th impact data at the s-th moment is , the a-th impact data is , the impact data The average value of is , the impact data The standard deviation of is ;

[0035] Calculate the correlation degree of the impact data on the highway traffic transfer volume:

[0036] ;

[0037] Among them, the impact data is h, the upper limit of the monitoring time is , the suppression factor is , the highway traffic transfer volume at the s-th moment monitored for the c-th time is , the a-th impact data at the s-th moment monitored for the c-th time is , the highway traffic transfer volume at the (s + 1)-th moment in the c-th monitoring is , the step function is , the a-th influencing data at the (s + 1)-th moment in the c-th monitoring is , the probability is , the highway traffic transfer volume in the c-th monitoring is , the correlation degree of the influencing data to the highway traffic transfer volume is ;

[0038] Take the influencing data with a correlation degree greater than 0.2475 as key data, and calculate the indefinite factor according to the key data:

[0039] ;

[0040] where the number of influencing data in the c-th monitoring is , the square of the Euclidean norm is , the genetic factor is , the error coefficient is , the indefinite factor in the c-th monitoring is .

[0041] Furthermore, a method for constructing a highway transfer traffic volume prediction model according to the transfer probability, the indefinite factor, and the traffic volume monitoring data includes:

[0042] Construct an objective function according to the transfer probability, the indefinite factor, and the traffic volume monitoring data, and the expression is:

[0043] ;

[0044] where the loss function is , the objective function is , the indefinite factor in the c-th monitoring is , the transfer probability of the x-th preference type is , the traffic volume in the c-th monitoring is ;

[0045] The highway transfer traffic volume prediction model includes an autoencoder, a similarity-based matching algorithm, and a long short-term memory network algorithm;

[0046] The autoencoder compresses the input data into a low-dimensional representation through unsupervised learning, and then reconstructs it back to the original data to learn the useful features of the input data;

[0047] The similarity-based matching algorithm quantifies the similarity between useful features, and performs matching according to the similarity to obtain matching data and non-matching data;

[0048] The long short-term memory network algorithm predicts the future highway transfer traffic volume by capturing the long-term dependencies in time series data and utilizing the historical information of matching and non-matching data.

[0049] Further, a method for optimizing the highway transfer traffic volume prediction model according to the prediction error includes:

[0050] Introduce a particle swarm, use the prediction error as the fitness function, calculate the fitness of the particles, and take the position of the particle with the minimum fitness value as the optimal position;

[0051] Calculate the position of the particle:

[0052] ;

[0053] where the convergence coefficient is and the random numbers from 0 to 1 are respectively 、 , the optimal position of the (t + 1)-th iteration is , the position of the w-th particle in the (t + 1)-th iteration is , and the position of the w-th particle in the t-th iteration is ;

[0054] Update the particle position to obtain the search position, and the expression is:

[0055] ;

[0056] where the search position of the w-th particle in the (t + 1)-th iteration is , the current iteration number is t, the maximum iteration number is , and the random number from 0 to 1 is ;

[0057] Use the step control parameter to update the search position to obtain the step control position, and the expression is:

[0058] ;

[0059] where the step control parameter is , the step control position of the w-th particle in the (t + 1)-th iteration is , and the search position of the w-th particle in the t-th iteration is ;

[0060] Introduce an adaptive weight to update the search position to obtain the adaptive position, and the expression is:

[0061] ;

[0062] ;

[0063] where the adaptive weight of the t-th iteration is , the adjustment coefficient is , the adaptive position of the w-th particle in the (t + 1)-th iteration is , the step control position of the w-th particle in the t-th iteration is , the position of the random particle in the t-th iteration is , the random number from 0 to 1 is ;

[0064] Iterate continuously until the maximum number of iterations is reached, otherwise update the adaptive weight.

[0065] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0066] A processor; and a memory arranged to store computer-executable instructions, and the executable instructions, when executed, cause the processor to execute the method steps described in the first aspect.

[0067] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, and the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the method steps described in the first aspect.

[0068] The beneficial effects of the present invention are:

[0069] The present invention is a method for constructing a highway transfer traffic volume prediction model. Compared with the prior art, the present invention has the following technical effects:

[0070] Through steps of preprocessing, time-varying screening, behavior preference analysis, impact analysis, model construction, and model optimization, the present invention can improve the accuracy of highway transfer traffic volume prediction, thereby improving the precision of highway transfer traffic volume prediction. Optimizing the highway transfer traffic volume prediction can greatly save resources and improve work efficiency. It can realize intelligent prediction of highway transfer traffic volume, conduct behavior preference analysis and impact analysis on highway transfer traffic volume prediction in real time, and is of great significance for user intention recognition in multi-dimensional human-computer interaction scenarios. It can adapt to the construction of highway transfer traffic volume prediction models with different standards and the construction requirements of different highway transfer traffic volume prediction models, and has a certain universality. Description of the Drawings

[0071] Figure 1 is a flowchart of the steps of the method for constructing a highway transfer traffic volume prediction model of the present invention;

[0072] Figure 2 is a schematic structural diagram of an electronic device in an embodiment of the present specification. Detailed Embodiments

[0073] The present invention will be further described below through specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

[0074] The construction method of the highway transfer traffic volume prediction model of the present invention includes the following steps:

[0075] As Figure 1 shown, in this embodiment, it includes the following steps:

[0076] Collect the flow monitoring data and influence data of the preset highway traffic, and preprocess the flow monitoring data and the influence data;

[0077] In the actual evaluation, take Highway A in XXX City as the research object, and the influence data includes weather, road conditions, traffic accidents, and holidays;

[0078] Obtain time-varying data through time-varying screening of the flow monitoring data, and perform behavioral preference analysis on the time-varying data to obtain transfer probabilities;

[0079] In the actual evaluation, the time-varying data is from 7:50 a.m. to 9:05 a.m. and from 4:55 p.m. to 6:25 p.m.; the transfer probabilities for shorter transportation time, lower transportation cost, and convenient connection are 0.291, 0.227, and 0.132 respectively;

[0080] Perform influence analysis on the influence data to obtain uncertain factors, and construct a highway transfer traffic volume prediction model according to the transfer probabilities, the uncertain factors, and the flow monitoring data;

[0081] In the actual evaluation, the uncertain factors for section A from 7:50 a.m. to 9:05 a.m. and from 4:55 p.m. to 6:25 p.m. are 0.4065 and 0.3715 respectively;

[0082] Optimize the highway transfer traffic volume prediction model according to the prediction error, and output the target model.

[0083] In this embodiment, the method for obtaining time-varying data through time-varying screening of the flow monitoring data includes:

[0084] Calculate the linear correlation between the flow monitoring data, and perform clustering on the flow monitoring data according to the linear correlation to obtain classifications;

[0085] Calculate the information entropy of the flow monitoring data:

[0086] ;

[0087] where the information entropy of the y-th flow monitoring data is , and the number of classifications is The proportion of the y-th traffic monitoring data in the i-th classification is ;

[0088] Calculate the value of traffic monitoring data:

[0089] ;

[0090] Among them, the value of the y-th dimensionality-reduced data is , the traffic monitoring data The average value is , the y-th traffic monitoring data in the i-th classification is , the number of traffic monitoring data is , the number of classifications is ;

[0091] Calculate the time-varying degree of traffic monitoring data:

[0092] ;

[0093] Among them, the y-th traffic monitoring data is , the traffic monitoring data The time-varying degree from the s-th moment to the s + 1-th moment is , the y-th traffic monitoring data at the s-th moment is , the y-th traffic monitoring data at the s + 1-th moment is , the regulation factor is ;

[0094] Output the traffic monitoring data with a time-varying degree greater than 0.3072 as time-varying data.

[0095] In this embodiment, the method for obtaining the transition probability by performing behavioral preference analysis on the time-varying data includes:

[0096] Calculate the transportation time, transportation cost, and connection ability of the highway corresponding to the highway transfer traffic volume, and take the shorter transportation time, lower transportation cost, and convenient connection as the preference types;

[0097] Use the time series time analysis algorithm to perform preference analysis on the time-varying data according to the preference types to obtain the preference quantity and preference weight;

[0098] Obtain the traffic data of the vehicle. When a highway has multiple preference types at the same time, take the ratio of the preference times to the on-road times of the same vehicle in different time periods as the preference weight;

[0099] Calculate the transition probability according to the preference weight and preference quantity:

[0100] ;

[0101] The transition probability of the x-th preference type is , and the preference weight of the x-th preference type is , the preference quantity is , the highway transfer traffic volume at the s-th moment is , the upper limit of the test time ;

[0102] In the actual evaluation, the number of trips is the number of different highways used during the transportation process, and the number of preference times is the number of times the vehicle selects the same road.

[0103] In this embodiment, the method for obtaining the indefinite factor by performing impact analysis on the impact data includes:

[0104] Sort the impact data in chronological order, input the sorted impact data into the time series impact analysis model, and calculate the weighted change amount of the impact data:

[0105] ;

[0106] Among them, the weighted change amount of the a-th impact data monitored for the c-th time is , the a-th impact data at the (s + 1)-th moment is , the a-th impact data at the s-th moment is , the a-th impact data is , the impact data The average value of is , the impact data The standard deviation of is ;

[0107] Calculate the correlation degree of the impact data on the highway traffic transfer volume:

[0108] ;

[0109] Among them, the impact data is h, the upper limit of the monitoring time is , the suppression factor is , the highway traffic transfer volume at the s-th moment monitored for the c-th time is , the a-th impact data at the s-th moment monitored for the c-th time is , the highway traffic transfer volume at the (s + 1)-th moment monitored for the c-th time is , the step function is , the a-th impact data at the (s + 1)-th moment monitored for the c-th time is , the probability is , the highway traffic transfer volume monitored for the c-th time is , the correlation degree of the impact data on the highway traffic transfer volume is ;

[0110] Take the impact data with a correlation degree greater than 0.2475 as key data, and calculate the indefinite factor according to the key data:

[0111] ;

[0112] Among them, the number of impact data in the c-th monitoring is , the square of the Euclidean norm is , the genetic factor is , the error coefficient is , and the indefinite factor in the c-th monitoring is .

[0113] In this embodiment, the method for constructing a highway transfer traffic volume prediction model based on the transfer probability, the indefinite factor, and the traffic volume monitoring data includes:

[0114] Construct an objective function according to the transfer probability, the indefinite factor, and the traffic volume monitoring data, and the expression is:

[0115] ;

[0116] Among them, the loss function is , the objective function is , the indefinite factor in the c-th monitoring is , the transfer probability of the x-th preference type is , and the traffic volume in the c-th monitoring is ;

[0117] The highway transfer traffic volume prediction model includes an autoencoder, a similarity-based matching algorithm, and a long short-term memory network algorithm;

[0118] The autoencoder compresses the input data into a low-dimensional representation through unsupervised learning, and then reconstructs it back to the original data to learn the useful features of the input data;

[0119] The similarity-based matching algorithm quantifies the similarity between useful features, and performs matching according to the similarity to obtain matching data and non-matching data;

[0120] The long short-term memory network algorithm captures the long-term dependencies in the time series data, and uses the historical information of the matching data and the non-matching data to predict the future highway transfer traffic volume.

[0121] In this embodiment, the method for optimizing the highway transfer traffic volume prediction model according to the prediction error includes:

[0122] Introduce a particle swarm, use the prediction error as the fitness function, calculate the fitness of the particles, and take the particle position with the minimum fitness value as the best position;

[0123] Calculate the position of the particles:

[0124] ;

[0125] where the convergence coefficient is , and the random numbers from 0 to 1 are respectively , , the best position at the (t + 1)-th iteration is , the position of the w-th particle at the (t + 1)-th iteration is , and the position of the w-th particle at the t-th iteration is ;

[0126] Update the particle position to obtain the search position, and the expression is:

[0127] ;

[0128] where the search position of the w-th particle at the (t + 1)-th iteration is , the current iteration number is t, the maximum iteration number is , and the random number from 0 to 1 is ;

[0129] Adopt the step control parameter to update the search position to obtain the step control position, and the expression is:

[0130] ;

[0131] where the step control parameter is , the step control position of the w-th particle at the (t + 1)-th iteration is , and the search position of the w-th particle at the t-th iteration is ;

[0132] Introduce the adaptive weight to update the search position to obtain the adaptive position, and the expression is:

[0133] ;

[0134] ;

[0135] where the adaptive weight at the t-th iteration is , the adjustment coefficient is , the adaptive position of the w-th particle at the (t + 1)-th iteration is , the step control position of the w-th particle at the t-th iteration is , the position of the random particle at the t-th iteration is , and the random number from 0 to 1 is ;

[0136] Iterate continuously until the maximum iteration number is reached, otherwise update the adaptive weight.

[0137] Figure 2 This is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 2 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0138] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 2 only a bidirectional arrow is used in

[0139] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0140] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, and forms a construction device for a highway transfer traffic volume prediction model at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the foregoing construction methods for a highway transfer traffic volume prediction model.

[0141] As described above in the present application Figure 1The method for constructing the highway transfer traffic volume prediction model disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor or instructions in software form. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0142] The electronic device can also execute Figure 1 the method for constructing the highway transfer traffic volume prediction model in Figure 1 and implement the functions of the illustrated embodiments, which are not elaborated herein in the embodiments of the present application.

[0143] The embodiments of the present application also propose a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, execute any of the foregoing methods for constructing the highway transfer traffic volume prediction model.

[0144] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0145] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0146] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0148] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0149] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0150] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0151] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0152] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for constructing a highway transfer traffic volume prediction model, characterized in that: The following steps are involved: Collecting flow monitoring data and impact data of preset highway traffic, and preprocessing the flow monitoring data and impact data; Performing time-varying screening on the traffic monitoring data to obtain time-varying data, and performing behavior preference analysis on the time-varying data to obtain a transfer probability; Performing an impact analysis on the impact data to obtain uncertain factors, and constructing a highway transfer traffic volume prediction model based on the transfer probability, the uncertain factors and the flow monitoring data; Optimizing the highway transfer traffic volume prediction model according to the prediction error and outputting a target model; The method of performing behavior preference analysis on the time-varying data to obtain the transition probability comprises: Calculate the transportation time, transportation cost and connection capacity of the highway corresponding to the highway transfer traffic volume, and take shorter transportation time, lower transportation cost and convenient connection as the preferred type; The time series time analysis algorithm is used to perform preference analysis on time-varying data according to preference types to obtain preference quantities and preference weights; Obtain vehicle traffic data. When a road has multiple preference types, the ratio of the number of preferences to the number of times the same vehicle is on the road in different time periods is used as the preference weight. Calculate the transition probability based on the preference weight and preference amount: The transition probability of the xth preference type is P x , the preference weight of the xth preference type is l x , the preference quantity is Q x , the highway transfer traffic volume at time s is Q s , the upper limit E of the test time; Sort the impact data in chronological order, input the sorted impact data into the temporal impact analysis model, and calculate the weighted change of the impact data: The weighted change of the ath influencing data in the cth monitoring is Δh c,a , the ath influencing data at the s+1th moment is h a (s+1), the ath influencing data at the sth time is h a (s), the ath influencing data is h a , affecting data h a The average value of Impact data a The standard deviation of a ); Calculate the relevance of impact data to highway traffic transfer volume: The impact data is h, and the upper limit of the monitoring time is T s , the suppression factor is μ, and the highway traffic transfer volume at the cth monitoring time is B c (s), the ath impact data at the cth monitoring time s is h c,a (s), the highway traffic transfer volume at the cth monitoring time s+1 is B c (s+1), the step function is δ(·), and the ath influencing data at the cth monitoring time s+1 is h c,a (s+1), the probability is p(·), and the traffic transfer volume of the cth monitoring is B c , the correlation degree of influencing data on highway traffic transfer volume is The influencing data with a correlation greater than 0.2475 is taken as the key data, and the uncertainty factor is calculated based on the key data: The number of impact data for the cth monitoring is M c , the square of the Euclidean norm is The genetic factor is μ, the error coefficient is τ, and the uncertainty factor of the cth monitoring is 2. The method for constructing a highway transfer traffic volume prediction model according to claim 1, characterized in that: The method for obtaining time-varying data by performing time-varying screening on the flow monitoring data comprises: Calculate the linear correlation between the flow monitoring data, and cluster the flow monitoring data according to the linear correlation to obtain classification; Calculate the information entropy of traffic monitoring data: The information entropy of the yth flow monitoring data is θ y , the number of categories is N i , the proportion of the yth flow monitoring data of the i-th category is b iy ; Calculate the value of traffic monitoring data: The value of the yth dimension reduction data is Flow monitoring data iy The average value is The yth flow monitoring data of the i-th category is f iy , the number of flow monitoring data is N y , the number of categories is M i ; Calculate the time variation of flow monitoring data: The yth flow monitoring data is f y , flow monitoring data f y The time variation from the sth moment to the s+1th moment is The yth flow monitoring data at the sth time is f y.s , the yth flow monitoring data at the s+1th time is f y.s+1 , the regulatory factor is ζ; The flow monitoring data with a time variation greater than 0.3072 is output as time-varying data.

3. The method for constructing a highway transfer traffic volume prediction model according to claim 1, characterized in that: The method for constructing a highway transfer traffic volume prediction model according to the transfer probability, the uncertain factor and the flow monitoring data comprises: The objective function is constructed based on the transfer probability, uncertain factors and flow monitoring data, and the expression is: The loss function is The objective function is The uncertainty factor of the cth monitoring is The transition probability of the xth preference type is P x , the traffic volume monitored for the cth time is g c ; The highway transfer traffic volume prediction model includes autoencoder, similarity-based matching algorithm, and long short-term memory network algorithm; The autoencoder compresses the input data into a low-dimensional representation through unsupervised learning, and then reconstructs it back to the original data to learn useful features of the input data; The similarity-based matching algorithm quantifies the similarity between useful features, matches according to the similarity, and obtains matching data and unmatched data; The LSTM network algorithm predicts future highway transfer traffic volume by capturing long-term dependencies in time series data and utilizing historical information of matching and unmatched data.

4. The method for constructing a highway transfer traffic volume prediction model according to claim 1, characterized in that: The method for optimizing the highway transfer traffic volume prediction model according to the prediction error comprises: Introduce particle swarm, take prediction error as fitness function, calculate particle fitness, and take the particle position with the smallest fitness value as the optimal position; Calculate the position of the particle: Z w (t+1)=Z best (t)-β·(2r1-1)·|2r2·Z best (t)-Z w (t)| The convergence coefficient is β, the random numbers from 0 to 1 are r1 and r2 respectively, and the best position of the t+1th iteration is Z best (t), the position of the wth particle in the t+1th iteration is Z w (t+1), the position of the wth particle in the tth iteration is Z w (t); Update the particle position to obtain the search position. The expression is: The search position of the wth particle in the t+1th iteration is The current number of iterations is t, and the maximum number of iterations is t max , a random number between 0 and 1 is r3; The step control position is obtained by updating the search position using the step control parameters. The expression is: The step control parameter is ζ, and the step control position of the wth particle in the t+1th iteration is The search position of the wth particle in the tth iteration is Adaptive weights are introduced to update the search position to obtain the adapted position. The expression is: The adaptive weight of the tth iteration is The adjustment coefficient is α, and the adaptation position of the wth particle in the t+1th iteration is The step control position of the wth particle in the tth iteration is The position of the random particle at the tth iteration is Z rand (t), a random number between 0 and 1 is r4; Continue to iterate until the maximum number of iterations is reached, otherwise update the adaptive weights.

5. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1 to 4.

6. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 4.

Images