A new traffic network situation analysis method, system, device and storage medium

Abstract

The present invention discloses a novel traffic network situation analysis method, system, device and storage medium. By acquiring the big data of the provincial highway network, the data can be made more complete, the prediction accuracy can be improved, and the data can be avoided from being generalized. At the same time, by extracting features from the big data of the provincial highway network, classified traffic data can be obtained, and a network situation analysis model is constructed based on the classified traffic data. The highway network data to be analyzed is analyzed according to the network situation analysis model, and the related sections can be predicted, and the prediction accuracy can be further improved, which effectively solves the defect of inaccurate prediction in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic analysis, and in particular to a novel traffic network situation analysis method, system, device and storage medium. Background Art

[0002] With the rapid economic development and the advancement of urbanization, the number of motor vehicles in my country has shown a rapid growth trend. The increasing number of vehicles has made urban traffic congestion increasingly serious. The essence of traffic congestion is the imbalance between the demand and supply of traffic capacity. In order to improve the current congestion situation, existing technologies will use a variety of modes to predict traffic flow and formulate corresponding unblocking plans, but generally have the following shortcomings:

[0003] (1) Traffic flow prediction technology based on GPS signal data, that is, GPS data open to mobile terminals or vehicle computers, such as data provided by manufacturers such as Amap and Baidu Map. Due to the bias of the data, the prediction results may be significantly different from the actual results.

[0004] (2) Limited by the security and access rights of highway toll data, most manufacturers can only make traffic flow predictions based on the data owned by the road section owners of their products, without data on the related sections. For example, Company A developed a traffic flow prediction application for the owner of Highway A based on the owner’s own data, but in fact Highways B and C are connected to Highway A (i.e., related sections), and their traffic flow data are also particularly important for the prediction of Highway A;

[0005] (3) Predicting future traffic flow by analyzing historical traffic flow data. However, the resulting data is often inaccurate when only historical data is used for analysis and prediction. Summary of the invention

[0006] In view of this, the present invention proposes a novel traffic network situation analysis method, system, device and storage medium, which can solve the defect of inaccurate prediction in the prior art.

[0007] The technical solution of the present invention is achieved in this way:

[0008] A new traffic network situation analysis method, specifically including:

[0009] Obtain big data of the province's highway network;

[0010] Extract features from the province's highway network big data to obtain classified traffic data;

[0011] Constructing a road network situation analysis model based on the classified traffic data, wherein the road network situation analysis model includes a future traffic volume prediction model, an induced traffic volume prediction model and a travel cost analysis model;

[0012] Obtain highway network data to be analyzed;

[0013] The highway network data to be analyzed is analyzed according to the road network situation analysis model to obtain the road network situation analysis results of the highway to be analyzed.

[0014] As a further optional solution of the novel traffic network situation analysis method, the feature extraction of the provincial highway network big data to obtain classified traffic data specifically includes:

[0015] The big data of the provincial highway network is processed based on the gradient boosting decision tree algorithm, and a feature decision tree of the provincial highway network big data is constructed;

[0016] Nonlinear classification is performed based on the support vector machine classifier and feature decision tree to obtain classified traffic data.

[0017] As a further optional solution of the novel traffic network situation analysis method, the future traffic volume prediction model uses the elasticity coefficient method to predict the future traffic volume. The specific formula is:

[0018]

[0019] in, represents the future traffic volume of gantry i, Indicates the current traffic volume of gantry i, It represents the transport elasticity coefficient of the transportation index of the transportation zone j to which the gantry i belongs to the economic index, It represents the GDP growth rate of traffic zone j to which gantry i belongs, and n represents the forecast period.

[0020] As a further optional solution of the new traffic network situation analysis method, the transport elasticity coefficient is used to reflect the relationship between transport development and economic growth. The specific calculation formula is:

[0021]

[0022] in, represents a certain transportation elasticity coefficient in area j, r xj represents the growth rate of a certain transportation index in area j, r GDPj represents the growth rate of GDP in region j.

[0023] As a further optional solution of the novel traffic network situation analysis method, the induced traffic volume prediction model is used to predict the induced traffic volume of the expressway, specifically including:

[0024] Obtain the road network structure of the highway to be analyzed;

[0025] Analyze the proportion of expressway traffic volume to the road network structure traffic volume;

[0026] The strategy of road network balancing is adopted to analyze the proportion of traffic volume shared by the new road section.

[0027] As a further optional solution of the novel traffic network situation analysis method, the travel cost analysis model uses a utility function to evaluate the comprehensive cost of traveling on a road section. The specific formula is:

[0028]

[0029] Among them, C represents the travel cost, Time represents the travel time of the road section, μ represents the vehicle travel cost per kilometer, Dist represents the travel distance, Toll represents the toll station fee, and vot represents the time value.

[0030] A novel traffic network situation analysis system, the system comprising a data layer, an interface layer and an application layer, the data layer using any one of the novel traffic network situation analysis methods, the data layer communicating with the application layer via the interface layer, the application layer comprising:

[0031] The road network information module is used to display the basic situation of the expressway network, including the number of expressways, network mileage, traffic density, facility statistics, real-time traffic statistics and passenger-cargo ratio;

[0032] Daily events module, used to display real-time daily events of the road network, including vehicle accidents and construction, and display the location on an electronic map superimposed with simulated road conditions;

[0033] Special event module, used to display special events that interrupt the expressway and display the location on an electronic map with simulated road conditions superimposed;

[0034] Highway event module, used to display congestion events and service area events in the road network;

[0035] Event report module, used to automatically generate event reports;

[0036] Traffic flow monitoring module, used to display the real-time traffic flow of the road network and display it on an electronic map superimposed with simulated road conditions;

[0037] The traffic flow prediction module is used to predict the traffic flow in any section of the road network within the next two hours, and compare it with the real-time traffic flow, and issue an alarm when the threshold is exceeded;

[0038] The holiday prediction module is used to make predictions one week before holidays and compare them with the data of the same period of the previous year, as well as to make predictions for congested road sections and congested toll stations;

[0039] The area trend module is used to divide the road network into multiple areas and display the traffic flow data in and out of each area;

[0040] The congested road section module is used to display the road network conditions of the entire province, and to make congestion rankings and congested traffic lengths;

[0041] The inter-provincial channel module is used to display the traffic volume of each exit and entry highway channel;

[0042] The cross-river channel module is used to display the traffic volume and road conditions of the cross-river expressway;

[0043] The congestion-prone area module is used to display the congestion situation of the road network from a regional perspective

[0044] Daily statistics module, used to automatically generate daily graphic reports;

[0045] Tracking module, used to track special vehicles such as two passenger vehicles, one hazardous vehicle, and one heavy vehicle in real time, and predict their exit toll stations;

[0046] The vehicle trajectory module is used to query the vehicle's driving trajectory based on the license plate, and can predict the exit toll station for real-time vehicles on the way.

[0047] A computing device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned novel traffic network situation analysis methods when executing the computer program.

[0048] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above-mentioned novel traffic network situation analysis methods.

[0049] The beneficial effects of the present invention are as follows: by acquiring the big data of the provincial highway network, the data can be made more complete, the prediction accuracy can be improved, and the data can be avoided from being generalized. At the same time, by extracting features from the big data of the provincial highway network, classified traffic data can be obtained, and a network situation analysis model can be constructed based on the classified traffic data. The highway network data to be analyzed is analyzed according to the network situation analysis model, and the related sections can be predicted, and the prediction accuracy can be further improved, effectively solving the defect of inaccurate prediction in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0051] Figure 1 The present invention is a flow chart of a novel traffic network situation analysis method. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only 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.

[0053] refer to Figure 1 , a new type of traffic network situation analysis method, specifically including:

[0054] Obtain big data of the province's highway network;

[0055] Extract features from the province's highway network big data to obtain classified traffic data;

[0056] Constructing a road network situation analysis model based on the classified traffic data, wherein the road network situation analysis model includes a future traffic volume prediction model, an induced traffic volume prediction model and a travel cost analysis model;

[0057] Obtain highway network data to be analyzed;

[0058] The highway network data to be analyzed is analyzed according to the road network situation analysis model to obtain the road network situation analysis results of the highway to be analyzed.

[0059] In this embodiment, by obtaining the big data of the provincial highway network, the data can be made more complete, the prediction accuracy can be improved, and the data can be avoided from being generalized. At the same time, by extracting features from the big data of the provincial highway network, classified traffic data can be obtained, and a network situation analysis model can be constructed based on the classified traffic data. The highway network data to be analyzed is analyzed according to the network situation analysis model, and related sections can be predicted, and the prediction accuracy can be further improved, effectively solving the defect of inaccurate prediction in the prior art.

[0060] It should be noted that after obtaining the big data of the province's highway network, the data is cleaned using database and storage technologies. The main technologies include: processing missing values, deleting duplicates, processing outliers, format and type conversion, data simplification, data structuring, data synchronization, and storage.

[0061] Preferably, the feature extraction of the provincial highway network big data to obtain classified traffic data specifically includes:

[0062] The big data of the provincial highway network is processed based on the gradient boosting decision tree algorithm, and a feature decision tree of the provincial highway network big data is constructed;

[0063] Nonlinear classification is performed based on the support vector machine classifier and feature decision tree to obtain classified traffic data.

[0064] In this embodiment, feature extraction mainly uses three methods based on statistical features, time domain features, and frequency domain features. The technical means used are: gradient boosting decision tree algorithm and support vector machine classifier. The gradient boosting decision tree algorithm is used to construct a data sample feature decision tree, such as vehicle entry time, driving speed, etc. The support vector machine classifier is used to perform nonlinear classification of data samples.

[0065] Preferably, the future traffic volume prediction model uses the elasticity coefficient method to predict future traffic volume, and the specific formula is:

[0066]

[0067] in, represents the future traffic volume of gantry i, Indicates the current traffic volume of gantry i, It represents the transport elasticity coefficient of the transportation index of the transportation zone j to which the gantry i belongs to the economic index, It represents the GDP growth rate of traffic zone j to which gantry i belongs, and n represents the forecast period.

[0068] In this embodiment, the traditional elasticity coefficient method is used to predict future traffic volume, because the elasticity coefficient method can directly reflect the impact of economic growth on highway traffic, and can better grasp the impact of regional productivity improvement and industrial structure adjustment on traffic growth in terms of total volume. It is easy to integrate qualitative factors and quantify them, and it has good practicality and reliability for medium- and long-term prediction of traffic volume. The principle is to study the elastic relationship between social and economic and transportation indicators, and determine the growth rate of future traffic volume of each gantry through the prediction of social and economic development of each transportation community and the prediction of passenger and freight transportation elasticity coefficient, thereby predicting future traffic volume.

[0069] Preferably, the transport elasticity coefficient is used to reflect the relationship between transport development and economic growth, and the specific calculation formula is:

[0070]

[0071] in, represents a certain transportation elasticity coefficient in area j, r xj represents the growth rate of a certain transportation index in area j, r GDPj represents the growth rate of GDP in region j.

[0072] Preferably, the induced traffic volume prediction model is used to predict the induced traffic volume of a highway, and specifically includes:

[0073] Obtain the road network structure of the highway to be analyzed;

[0074] Analyze the proportion of expressway traffic volume to the road network structure traffic volume;

[0075] The strategy of road network balancing is adopted to analyze the proportion of traffic volume shared by the new road section.

[0076] In this embodiment, induced traffic volume refers to the traffic volume transfer caused by the opening of the highway, which improves the road network structure, increases the transportation supply capacity and improves the service level, thereby affecting the regional economy and industrial layout, and changing the land use nature on both sides of the road. Therefore, it is necessary to first analyze what proportion of the traffic volume in the road network is borne by the expressway and its destination and source, and then adopt a road network balancing strategy based on the location of the newly planned section to analyze the proportion of the new section.

[0077] Preferably, the travel cost analysis model uses a utility function to evaluate the comprehensive cost of traveling on a road section, and the specific formula is:

[0078]

[0079] Among them, C represents the travel cost, Time represents the travel time of the road section, μ represents the vehicle travel cost per kilometer, Dist represents the travel distance, Toll represents the toll station fee, and vot represents the time value.

[0080] In this embodiment, travelers follow the principle of maximum utility when choosing the best route. The greater the utility, the greater the possibility of being selected. The utility function is used to evaluate the comprehensive cost of a vehicle traveling on a road section, which takes into account the actual driving time of the vehicle, the fuel consumption of the vehicle, the toll fee, etc.

[0081] A novel traffic network situation analysis system, the system comprising a data layer, an interface layer and an application layer, the data layer using any one of the novel traffic network situation analysis methods, the data layer communicating with the application layer via the interface layer, the application layer comprising:

[0082] The road network information module is used to display the basic situation of the expressway network, including the number of expressways, network mileage, traffic density, facility statistics, real-time traffic statistics and passenger-cargo ratio;

[0083] Daily events module, used to display real-time daily events of the road network, including vehicle accidents and construction, and display the location on an electronic map superimposed with simulated road conditions;

[0084] Special event module, used to display special events that interrupt the expressway and display the location on an electronic map with simulated road conditions superimposed;

[0085] Highway event module, used to display congestion events and service area events in the road network;

[0086] Event report module, used to automatically generate event reports;

[0087] Traffic flow monitoring module, used to display the real-time traffic flow of the road network and display it on an electronic map superimposed with simulated road conditions;

[0088] The traffic flow prediction module is used to predict the traffic flow in any section of the road network within the next two hours, and compare it with the real-time traffic flow, and issue an alarm when the threshold is exceeded;

[0089] The holiday prediction module is used to make predictions one week before holidays and compare them with the data of the same period of the previous year, as well as to make predictions for congested road sections and congested toll stations;

[0090] The area trend module is used to divide the road network into multiple areas and display the traffic flow data in and out of each area;

[0091] The congested road section module is used to display the road network conditions of the entire province, and to make congestion rankings and congested traffic lengths;

[0092] The inter-provincial channel module is used to display the traffic volume of each exit and entry highway channel;

[0093] The cross-river channel module is used to display the traffic volume and road conditions of the cross-river expressway;

[0094] The congestion-prone area module is used to display the congestion situation of the road network from a regional perspective

[0095] Daily statistics module, used to automatically generate daily graphic reports;

[0096] Tracking module, used to track special vehicles such as two passenger vehicles, one hazardous vehicle, and one heavy vehicle in real time, and predict their exit toll stations;

[0097] The vehicle trajectory module is used to query the vehicle's driving trajectory based on the license plate, and can predict the exit toll station for real-time vehicles on the way.

[0098] In this embodiment, the traffic flow in any area of ​​the provincial expressway network in the future can be predicted to provide managers with a basis for decision-making. At the same time, the holiday traffic flow in any area of ​​the provincial expressway network can be predicted 7 days in advance to provide support for business managers to formulate plans to ensure smooth and safe traffic during holidays. In addition, future congestion intervals can be predicted to provide managers with congestion management plans and real-time traffic flow forecasts, which can be compared with the predicted results as evaluation parameters of the algorithm model. In addition, vehicle flow tracing can be achieved to provide source information for congestion management, which can effectively grasp the situation of the provincial expressway network and provide a scientific basis for congestion management and traffic plan formulation, thereby achieving the effect of reducing carbon emissions.

[0099] A computing device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned novel traffic network situation analysis methods when executing the computer program.

[0100] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above-mentioned novel traffic network situation analysis methods.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A new traffic network situation analysis method, characterized in that: Specifically include: Obtain big data of the province's highway network; Extract features from the province's highway network big data to obtain classified traffic data; Constructing a road network situation analysis model based on the classified traffic data, wherein the road network situation analysis model includes a future traffic volume prediction model, an induced traffic volume prediction model and a travel cost analysis model; Obtain highway network data to be analyzed; Analyze the highway network data to be analyzed according to the road network situation analysis model to obtain the road network situation analysis results of the highway to be analyzed; The travel cost analysis model uses a utility function to evaluate the comprehensive cost of traveling on a road section. The specific formula is: Among them, C represents the travel cost, Time represents the travel time of the road section, μ represents the vehicle travel cost per kilometer, Dist represents the travel distance, Toll represents the toll station fee, and vot represents the time value; The induced traffic volume prediction model is used to predict the induced traffic volume of the expressway, and specifically includes: Obtain the road network structure of the highway to be analyzed; Analyze the proportion of expressway traffic volume to the road network structure traffic volume; The strategy of road network balancing is adopted to analyze the proportion of traffic volume shared by the new road section.

2. A new traffic network situation analysis method according to claim 1, characterized in that: The feature extraction of the provincial highway network big data to obtain classified traffic data specifically includes: The big data of the provincial highway network is processed based on the gradient boosting decision tree algorithm, and a feature decision tree of the provincial highway network big data is constructed; Nonlinear classification is performed based on the support vector machine classifier and feature decision tree to obtain classified traffic data.

3. A new traffic network situation analysis method according to claim 2, characterized in that: The future traffic volume prediction model adopts the elasticity coefficient method to predict the future traffic volume. The specific formula is: in, represents the future traffic volume of gantry i, Indicates the current traffic volume of gantry i, It represents the transport elasticity coefficient of the transportation index of the transportation zone j to which the gantry i belongs to the economic index, It represents the GDP growth rate of traffic zone j to which gantry i belongs, and n represents the forecast period.

4. A new type of traffic network situation analysis method according to claim 3, characterized in that: The transport elasticity coefficient is used to reflect the relationship between transport development and economic growth. The specific calculation formula is: in, represents a certain transportation elasticity coefficient in area j, r xj represents the growth rate of a certain transportation index in area j, r GDPj represents the growth rate of GDP in region j.

5. A new type of traffic network situation analysis system, characterized in that: The system comprises a data layer, an interface layer and an application layer, wherein the data layer applies any one of the novel traffic network situation analysis methods in claims 1 to 4, the data layer is connected to the application layer through the interface layer, and the application layer comprises: The road network information module is used to display the basic situation of the expressway network, including the number of expressways, network mileage, traffic density, facility statistics, real-time traffic statistics and passenger-cargo ratio; Daily events module, used to display real-time daily events of the road network, including vehicle accidents and construction, and display the location on an electronic map superimposed with simulated road conditions; Special event module, used to display special events that interrupt the expressway and display the location on an electronic map with simulated road conditions superimposed; Highway event module, used to display congestion events and service area events in the road network; Event report module, used to automatically generate event reports; Traffic flow monitoring module, used to display the real-time traffic flow of the road network and display it on an electronic map superimposed with simulated road conditions; The traffic flow prediction module is used to predict the traffic flow in any section of the road network within the next two hours, and compare it with the real-time traffic flow, and issue an alarm when the threshold is exceeded; The holiday prediction module is used to make predictions one week before holidays and compare them with the data of the same period of the previous year, as well as to make predictions for congested road sections and congested toll stations; The area trend module is used to divide the road network into multiple areas and display the traffic flow data in and out of each area; The congested road section module is used to display the road network conditions of the entire province, and to make congestion rankings and congested traffic lengths; The inter-provincial channel module is used to display the traffic volume of each exit and entry highway channel; The cross-river channel module is used to display the traffic volume and road conditions of the cross-river expressway; The congestion-prone area module is used to display the congestion situation of the road network from a regional perspective Daily statistics module, used to automatically generate daily graphic reports; Tracking module, used to track two passenger vehicles, one hazardous vehicle, and one heavy vehicle in real time, and predict their exit toll stations; The vehicle trajectory module is used to query the vehicle's driving trajectory based on the license plate, and can predict the exit toll station for real-time vehicles on the way.

6. A computing device, characterized in that The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the novel traffic network situation analysis methods in claims 1-4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the novel traffic network situation analysis methods in claims 1-4.

Images