Expressway traffic state prediction method and prediction device

Abstract

The invention provides an expressway traffic state prediction method and device, and the method comprises the steps: dividing a target expressway segment into a plurality of regional road segments according to the converging and shunting features of the expressway segment, and determining the features and event states of the road segments; based on the road section characteristics corresponding to each regional road section, a traffic flow detector and a flow prediction model are used to acquire the traffic flow density and / or the flow prediction value of each regional road section; determining traffic flow parameters based on the event state and historical traffic data of each regional road section; based on the traffic flow parameters and the predicted flow increment, predicted by the flow prediction model, of each regional road section, determining a predicted density value of each regional road section by using a regional traffic flow evolution formula; and comparing the predicted density value with a critical density value in the traffic flow parameters, and determining a predicted traffic state of each regional road section. Through the method, the comprehensiveness and reliability of data acquisition and the accuracy of traffic state prediction are improved.

Description

Technical Field

[0001] The present application relates to the technical field of traffic state prediction, and in particular to a method and device for predicting highway traffic state. Background Art

[0002] Traffic status prediction mainly includes data-driven prediction methods and model-driven prediction methods. Among them, the data-driven prediction method directly relies on historical data, and mainly extracts the correlation between data from historical data through data statistics or machine learning to predict traffic status; while the model-driven prediction method relies on the physical traffic flow model, which predicts traffic status based on prior knowledge of traffic dynamics and uses real-time data.

[0003] At present, for prediction methods based on data-driven and model-driven, a parameter matrix that represents the changes in road network information is introduced into the prediction scenario of traffic status, and the traffic status is predicted at the cellular level based on cellular partitioning. However, the characteristics of the parameter matrix of road network information changes in this method are relatively limited, and in order to meet the constraints of cellular partitioning, the data of the detection nodes will be reduced, making it impossible to fully utilize the data collected by each detector, reducing the comprehensiveness and reliability of data collection, and thus reducing the accuracy of predicting traffic status. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method and device for predicting the traffic status of a highway. According to the confluence and divergence characteristics of the target highway section and whether there are traffic incidents, the target highway section is divided into multiple regional sections, and the traffic flow density and / or flow prediction value of each regional section is obtained by using a traffic flow detector and a flow prediction model, and the traffic flow parameters of each regional section are further determined. Based on the traffic flow parameters and the predicted flow increment of each regional section predicted by the flow prediction model, the predicted density value of each regional section is determined, so as to determine the predicted traffic status of each regional section according to the comparison result of the predicted density value and the critical density value in the traffic flow parameters, thereby improving the comprehensiveness and reliability of data collection, and thus improving the accuracy of the predicted traffic status.

[0005] The present application embodiment provides a method for predicting highway traffic conditions, the method comprising:

[0006] According to the merging and diverging characteristics of the expressway section, the target expressway section is divided into multiple regional sections, and the section characteristics and event status corresponding to each regional section are determined; wherein the section characteristics include basic regional sections, interweaving section, merging section and diverging section; the event status includes no traffic event status and traffic event status;

[0007] Based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and a preset flow prediction model, the traffic flow density and / or flow prediction value of each regional road section is obtained;

[0008] Determine the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section;

[0009] Based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value, a predicted density value of each regional road section is determined using a preset regional traffic flow evolution formula;

[0010] The predicted density value is compared with the critical density value in the traffic flow parameter, and the predicted traffic state of each regional road section is determined according to the comparison result.

[0011] Furthermore, based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and a preset flow prediction model, obtaining the traffic flow density and / or flow prediction value of each regional road section includes:

[0012] For each of the regional road sections, when a traffic flow detector is provided for the regional road section, obtaining a first traffic flow density of the regional road section collected by the traffic flow detector;

[0013] When the regional road section is not provided with a traffic flow detector, obtaining an upstream traffic flow density detected by a traffic flow detector located upstream of the regional road section and adjacent to the regional road section, and determining the upstream traffic flow density as a second traffic flow density of the regional road section;

[0014] For the weaving area section, the merging area section and the diverging area section, the first inflow flow prediction value corresponding to the merging area section, the first outflow flow prediction value corresponding to the diverging area section, and the second inflow flow prediction value and the second outflow flow prediction value corresponding to the weaving area section output by a preset flow prediction model are respectively obtained.

[0015] Further, the traffic flow parameters include a free flow speed set, a congestion upstream propagation speed set, a critical density value, a flow rate limit value, and a blocking density value;

[0016] The determining of the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section includes:

[0017] For each of the regional road sections where the event status is a traffic event-free state, based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point;

[0018] For each regional road section where the event status is a traffic event status, based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section, the second traffic flow parameter of the regional road section is determined by utilizing a pre-established speed relationship model and detecting and analyzing speed change points.

[0019] Furthermore, the determining of the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section includes:

[0020] Determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on a speed time series and a flow time series included in the historical traffic data collected in advance for the regional road section, and determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set;

[0021] Performing mean calculation on the density value corresponding to each speed change point in the speed change point data set, and determining the obtained mean calculation result as the first critical density value of the road section in the area;

[0022] multiplying the first critical density value and the first free flow speed mean corresponding to the first free flow speed set, and determining the obtained product as the first flow rate limit value of the regional road section;

[0023] The density values ​​respectively corresponding to at least one speed value whose speed value in the speed time series is a first preset value are averaged, and the averaged calculation result is determined as the first blocking density value of the regional road section.

[0024] Furthermore, the speed time series is collected in advance by the following steps:

[0025] When a speed detector is provided in the regional road section, the speed detector is used to collect the first speed time series of the regional road section in advance;

[0026] When the road section in the area is not provided with a speed detector, a free flow state data set and a congestion state data set of the road section in the area are obtained;

[0027] Based on the free flow state data set, a preset first speed detection model is used to determine a free flow speed time series of the road section in the area;

[0028] Based on the congestion status data set, a preset second speed detection model is used to determine a time series of the congestion propagation speed upstream of the road section in the area;

[0029] The free flow speed time series and the congestion upstream propagation speed time series are determined as the second speed time series of the regional road section.

[0030] Further, the determining of a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on the speed time series and the flow time series included in the historical traffic data pre-collected for the regional road section, and determining a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set, includes:

[0031] Based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series pre-collected in the regional road section, determine whether the speed value and the flow value corresponding to each moment meet the preset conditions, and obtain a judgment result; wherein the preset conditions include that the speed value is greater than a second preset value and the flow value is less than a preset free flow value;

[0032] Based on the judgment result, at least one speed value satisfying a preset condition is selected from the speed time series, and the at least one speed value is determined as a first free flow speed set of the regional road section;

[0033] Performing mean calculation on at least one first free flow speed included in the first free flow speed set, so as to determine the obtained mean calculation result as the first free flow speed mean of the regional road section;

[0034] For a plurality of preset time intervals included in the speed time series, the first free flow speed mean is subtracted from a plurality of speed values ​​corresponding to each preset time interval to obtain a deviation calculation result, and based on the deviation calculation result and a plurality of speed values ​​and flow values ​​corresponding to each preset time interval, a plurality of congestion upstream propagation speeds corresponding to each preset time interval of the regional road section are determined to determine a first congestion upstream propagation speed set of the regional road section;

[0035] Based on the first free flow speed set and the first congestion upstream propagation speed set, a speed change point corresponding to the regional road section at each preset time interval is determined to determine a speed change point data set for the regional road section.

[0036] Furthermore, the method of determining the second traffic flow parameter of the regional road section based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section by using a pre-established speed relationship model and detecting and analyzing speed change points includes:

[0037] Based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section, a second free flow speed set and a second congestion upstream propagation speed set for the regional road section are determined by using a pre-established speed relationship model;

[0038] Determine the time corresponding to the conversion of the second free flow speed set into the second congestion upstream propagation speed set as the speed change point time of the regional road section, and determine the density value corresponding to the speed change point time as the second critical density value of the regional road section;

[0039] Multiplying the second critical density value and the second free flow speed, and determining the obtained product as the second flow rate limit value of the regional road section;

[0040] The density values ​​respectively corresponding to at least one second free flow whose speed value is the first preset value included in the second free flow speed set are averaged, and the obtained average calculation result is determined as the second blocking density value of the regional road section.

[0041] Furthermore, the predicted density value is compared with the critical density value in the traffic flow parameter, and the predicted traffic state of each regional road section is determined according to the comparison result, including:

[0042] Comparing the predicted density value with the critical density value in the traffic flow parameter to determine whether the predicted density value is greater than the critical density value, and obtaining a comparison result;

[0043] If the comparison result is that the predicted density value is greater than the critical density value, determining that the predicted traffic state of the road section in the area is a congested state;

[0044] If the comparison result is that the predicted density value is less than or equal to the critical density value, it is determined that the predicted traffic state of the road section in the area is a free flow state.

[0045] The embodiment of the present application also provides a prediction device for highway traffic status, the prediction device comprising:

[0046] A road segmentation module is used to divide the target highway section into multiple regional sections according to the merging and diverging characteristics of the highway section, and determine the section characteristics and event status corresponding to each regional section; wherein the section characteristics include basic regional sections, interweaving section sections, merging section sections and diverging section sections; the event status includes a state without traffic events and a state with traffic events;

[0047] A data acquisition module, configured to acquire the traffic flow density and / or traffic flow prediction value of each regional road section based on the road section features corresponding to each regional road section and using the traffic flow detectors provided in the target highway section and a preset traffic flow prediction model;

[0048] A parameter determination module, configured to determine a traffic flow parameter of each regional road section based on an event state of each regional road section and historical traffic data collected in advance for each regional road section;

[0049] A prediction module, configured to determine the predicted density value of each regional road section by using a preset regional traffic flow evolution formula based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value;

[0050] A comparison module is used to compare the predicted density value with the critical density value in the traffic flow parameter, and determine the predicted traffic state of each regional road section according to the comparison result.

[0051] Furthermore, when the data acquisition module is used to acquire the traffic flow density and / or flow prediction value of each regional road section based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and the preset flow prediction model, the data acquisition module is used to:

[0052] For each of the regional road sections, when a traffic flow detector is provided for the regional road section, obtaining a first traffic flow density of the regional road section collected by the traffic flow detector;

[0053] When the regional road section is not provided with a traffic flow detector, obtaining an upstream traffic flow density detected by a traffic flow detector located upstream of the regional road section and adjacent to the regional road section, and determining the upstream traffic flow density as a second traffic flow density of the regional road section;

[0054] For the weaving area section, the merging area section and the diverging area section, the first inflow flow prediction value corresponding to the merging area section, the first outflow flow prediction value corresponding to the diverging area section, and the second inflow flow prediction value and the second outflow flow prediction value corresponding to the weaving area section output by a preset flow prediction model are respectively obtained.

[0055] Further, the traffic flow parameters include a free flow speed set, a congestion upstream propagation speed set, a critical density value, a flow rate limit value, and a blocking density value;

[0056] When the parameter determination module is used to determine the traffic flow parameter of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section, the parameter determination module is used to:

[0057] For each of the regional road sections where the event status is a traffic event-free state, based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point;

[0058] For each regional road section where the event status is a traffic event status, based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section, the second traffic flow parameter of the regional road section is determined by utilizing a pre-established speed relationship model and detecting and analyzing speed change points.

[0059] Furthermore, when the parameter determination module is used to determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, the parameter determination module is used to:

[0060] Determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on a speed time series and a flow time series included in the historical traffic data collected in advance for the regional road section, and determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set;

[0061] Performing mean calculation on the density value corresponding to each speed change point in the speed change point data set, and determining the obtained mean calculation result as the first critical density value of the road section in the area;

[0062] multiplying the first critical density value and the first free flow speed mean corresponding to the first free flow speed set, and determining the obtained product as the first flow rate limit value of the regional road section;

[0063] The density values ​​respectively corresponding to at least one speed value whose speed value in the speed time series is a first preset value are averaged, and the averaged calculation result is determined as the first blocking density value of the regional road section.

[0064] Further, when the parameter determination module is used to pre-collect the speed time series, the parameter determination module is used to:

[0065] When a speed detector is provided in the regional road section, the speed detector is used to collect the first speed time series of the regional road section in advance;

[0066] When the road section in the area is not provided with a speed detector, a free flow state data set and a congestion state data set of the road section in the area are obtained;

[0067] Based on the free flow state data set, a preset first speed detection model is used to determine a free flow speed time series of the road section in the area;

[0068] Based on the congestion status data set, a preset second speed detection model is used to determine a time series of the congestion propagation speed upstream of the road section in the area;

[0069] The free flow speed time series and the congestion upstream propagation speed time series are determined as the second speed time series of the regional road section.

[0070] Further, when the parameter determination module is used to determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on the speed time series and the flow time series included in the historical traffic data pre-collected for the regional road section, and to determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set, the parameter determination module is used to:

[0071] Based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series pre-collected in the regional road section, determine whether the speed value and the flow value corresponding to each moment meet the preset conditions, and obtain a judgment result; wherein the preset conditions include that the speed value is greater than a second preset value and the flow value is less than a preset free flow value;

[0072] Based on the judgment result, at least one speed value satisfying a preset condition is selected from the speed time series, and the at least one speed value is determined as a first free flow speed set of the regional road section;

[0073] Performing mean calculation on at least one first free flow speed included in the first free flow speed set, so as to determine the obtained mean calculation result as the first free flow speed mean of the regional road section;

[0074] For a plurality of preset time intervals included in the speed time series, the first free flow speed mean is subtracted from a plurality of speed values ​​corresponding to each preset time interval to obtain a deviation calculation result, and based on the deviation calculation result and a plurality of speed values ​​and flow values ​​corresponding to each preset time interval, a plurality of congestion upstream propagation speeds corresponding to each preset time interval of the regional road section are determined to determine a first congestion upstream propagation speed set of the regional road section;

[0075] Based on the first free flow speed set and the first congestion upstream propagation speed set, a speed change point corresponding to the regional road section at each preset time interval is determined to determine a speed change point data set for the regional road section.

[0076] Furthermore, when the parameter determination module is used to determine the second traffic flow parameter of the regional road section based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section by using a pre-established speed relationship model and detecting and analyzing speed change points, the parameter determination module is used to:

[0077] Based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section, a second free flow speed set and a second congestion upstream propagation speed set for the regional road section are determined by using a pre-established speed relationship model;

[0078] Determine the time corresponding to the conversion of the second free flow speed set into the second congestion upstream propagation speed set as the speed change point time of the regional road section, and determine the density value corresponding to the speed change point time as the second critical density value of the regional road section;

[0079] multiplying the second critical density value and the second free flow speed, and determining the obtained product as the second flow rate limit value of the regional road section;

[0080] The density values ​​respectively corresponding to at least one second free flow whose speed value is the first preset value included in the second free flow speed set are averaged, and the obtained average calculation result is determined as the second blocking density value of the regional road section.

[0081] Furthermore, when the comparison module is used to compare the predicted density value with the critical density value in the traffic flow parameter and determine the predicted traffic state of each regional road section according to the comparison result, the comparison module is used to:

[0082] Comparing the predicted density value with the critical density value in the traffic flow parameter to determine whether the predicted density value is greater than the critical density value, and obtaining a comparison result;

[0083] If the comparison result is that the predicted density value is greater than the critical density value, determining that the predicted traffic state of the road section in the area is a congested state;

[0084] If the comparison result is that the predicted density value is less than or equal to the critical density value, it is determined that the predicted traffic state of the road section in the area is a free flow state.

[0085] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for predicting highway traffic conditions as described above are performed.

[0086] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for predicting the highway traffic status as described above are executed.

[0087] The prediction method and prediction device of the highway traffic status provided by the embodiment of the present application, the prediction method comprises: dividing the target highway section into multiple regional sections according to the merging and diverging characteristics of the highway section, and determining the section characteristics and event status corresponding to each regional section; wherein the section characteristics include basic regional sections, interweaving section sections, merging section sections and diverging section sections; the event status includes a state without traffic events and a state with traffic events; based on the section characteristics corresponding to each regional section, using the traffic flow detector set in the target highway section and the preset flow prediction model, obtaining the traffic flow of each regional section traffic flow density and / or flow prediction value; determining the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section; determining the predicted density value of each regional road section using a preset regional traffic flow evolution formula based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value; comparing the predicted density value with the critical density value in the traffic flow parameters, and determining the predicted traffic state of each regional road section according to the comparison result.

[0088] Compared with the data-driven and model-driven prediction methods in the prior art, a parameter matrix that represents the changes in road network information is introduced into the prediction scenario of traffic status, and a cellular-level prediction method for traffic status is performed based on cellular partitioning. According to the confluence and divergence characteristics of the target highway section and whether there are traffic incidents, the target highway section is divided into multiple regional sections, and the traffic flow density and / or flow prediction value of each regional section is obtained by using a traffic flow detector and a flow prediction model, and the traffic flow parameters of each regional section are further determined. Based on the traffic flow parameters and the predicted flow increment of each regional section predicted by the flow prediction model, the predicted density value of each regional section is determined, so as to determine the predicted traffic status of each regional section according to the comparison result of the predicted density value and the critical density value in the traffic flow parameters, thereby improving the comprehensiveness and reliability of data collection, and thus improving the accuracy of predicting traffic status.

[0089] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0091] Figure 1 A flowchart of a method for predicting highway traffic conditions provided in an embodiment of the present application;

[0092] Figure 2 A schematic diagram of the division of regional road sections provided in an embodiment of the present application;

[0093] Figure 3 A schematic diagram of obtaining traffic flow density and flow prediction values ​​of a regional road section provided in an embodiment of the present application;

[0094] Figure 4 A curve diagram of a traffic flow parameter provided in an embodiment of the present application;

[0095] Figure 5 A schematic diagram of detecting a speed change point provided in an embodiment of the present application;

[0096] Figure 6 A schematic diagram of the structure of a device for predicting highway traffic conditions provided in an embodiment of the present application;

[0097] Figure 7A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0098] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0099] Research has found that at present, for data-driven and model-driven prediction methods, a parameter matrix that represents the changes in road network information is introduced into the prediction scenario of traffic status, and the traffic status is predicted at the cellular level based on cellular partitioning. However, the characteristics of the parameter matrix of road network information changes in this method are relatively limited, and in order to meet the constraints of cellular partitioning, the data of the detection nodes will be reduced, making it impossible to fully utilize the data collected by each detector.

[0100] As an example of the prior art of a prediction method based on data-driven and model-driven, the basic map of the road section is calibrated using historical data, and targeted cell division is performed based on road structure information and video point pile numbers. State estimation and observation are further performed based on the cellular transmission model, and finally the cellular state is updated based on the Kalman filter. This method introduces a road network information change parameter matrix for traffic state prediction scenarios. The shortcomings include: the basic map of the road section is not considered in the changes in the road section characteristics and the basic map of the road section caused by traffic events (accidents, construction, etc.); in order to meet the constraints, the cellular division will reduce the detection node data, so that the data collected by each detector cannot be fully utilized, which reduces the comprehensiveness and reliability of data collection, and thus reduces the accuracy of the predicted traffic state.

[0101] Based on this, an embodiment of the present application provides a method for predicting the traffic status of a highway. According to the confluence and divergence characteristics of the target highway section and whether there are traffic incidents, the target highway section is divided into multiple regional sections. The traffic flow density and / or flow prediction value of each regional section is obtained by using a traffic flow detector and a flow prediction model, and the traffic flow parameters of each regional section are further determined. The predicted density value of each regional section is determined based on the traffic flow parameters and the predicted flow increment of each regional section predicted by the flow prediction model, so as to determine the predicted traffic status of each regional section based on the comparison result of the predicted density value and the critical density value in the traffic flow parameters, thereby improving the comprehensiveness and reliability of data collection, and thereby improving the accuracy of the predicted traffic status.

[0102] See also Figure 1 , Figure 1 This is a flow chart of a method for predicting highway traffic conditions provided by an embodiment of the present application. Figure 1 As shown in , the method for predicting highway traffic status provided by the embodiment of the present application includes:

[0103] S100. Divide the target highway section into multiple regional sections according to the merging and diverging characteristics of the highway section, and determine the section characteristics and event status corresponding to each regional section; wherein the section characteristics include basic regional sections, interweaving section, merging section and diverging section; and the event status includes a state without traffic events and a state with traffic events.

[0104] In this step, the target highway section is divided into a plurality of regional sections according to the divergence characteristic intersections and merging characteristic intersections set in the target highway.

[0105] Among them, the regional road section including a merging characteristic intersection is determined as the regional road section with the section characteristic of the merging area section; the regional road section including a diverging characteristic intersection is determined as the regional road section with the section characteristic of the diverging area section; the regional road section with neither merging characteristic intersections nor diverging characteristic intersections is determined as the regional road section with the section characteristic of the basic regional section; the regional road section with both merging characteristic intersections and diverging characteristic intersections is determined as the regional road section with the section characteristic of the weaving area section.

[0106] Furthermore, the event status of each regional road section is determined according to whether there is a traffic event in each regional road section; the event status includes a state without a traffic event and a state with a traffic event.

[0107] In the embodiment of the present application, the traffic events may include but are not limited to road construction, traffic accidents, temporary controls and abnormal events.

[0108] Here, a plurality of traffic flow detectors are arranged in the target expressway section, and the traffic flow detectors can be arranged in the regional sections corresponding to any section characteristics of the basic regional sections, the interweaving section, the merging section and the diverging section.

[0109] For example, see Figure 2 , Figure 2 A schematic diagram of the division of regional road sections provided in an embodiment of the present application.

[0110] like Figure 2 As shown in, according to the divergence characteristic intersections and merging characteristic intersections set in the target expressway section, the target expressway section is divided from left to right into section characteristics of a merging area section, a first basic area section, a divergence area section, a second basic area section, an interweaving area section and a third basic area section; wherein the merging area section, the divergence area section and the third basic area section are respectively provided with a traffic flow detector; there is a traffic event manifested as road construction in the divergence area section, and there is a traffic event manifested as a traffic accident in the third basic area section.

[0111] S200. Based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and a preset flow prediction model, obtain the traffic flow density and / or flow prediction value of each regional road section.

[0112] In an embodiment of the present application, the traffic flow detector can detect the traffic flow density value of the road section in the area where the traffic flow detector is located; the traffic flow density value is used to describe the number of vehicles per unit length on a section of road within a certain time period to reflect the density of vehicles on the road.

[0113] Here, the traffic prediction value includes an outflow traffic prediction value and an inflow traffic prediction value; wherein, a regional section whose road section feature is a diversion area section corresponds to an outflow traffic prediction value; a regional section whose road section feature is a merging area section corresponds to an inflow traffic prediction value; and a regional section whose road section feature is an interweaving area section corresponds to an inflow traffic prediction value and an outflow traffic prediction value.

[0114] In this step, a traffic flow detector installed in the target highway section is used to detect the first traffic flow density corresponding to the regional section where the traffic flow detector is located; wherein, for a regional section where no traffic flow detector is installed, the traffic flow density detected by the traffic flow detector installed at an adjacent position upstream of the regional section is determined as the second traffic flow density of the regional section.

[0115] Furthermore, for the weaving area sections, merging area sections and diverging area sections, the preset flow prediction model is used to obtain the flow prediction values ​​of the above-mentioned area sections.

[0116] In one implementation of the present application, during specific implementation, step S200 may include:

[0117] S210 . For each of the regional road sections, when a traffic flow detector is provided for the regional road section, obtaining a first traffic flow density of the regional road section collected by the traffic flow detector.

[0118] In this step, when a traffic flow detector is provided on the regional road section, a first traffic flow density of the regional road section collected by the traffic flow detector is obtained.

[0119] S220. When no traffic flow detector is provided for the regional road section, an upstream traffic flow density detected by a traffic flow detector located upstream of the regional road section and adjacent to the regional road section is obtained, and the upstream traffic flow density is determined as a second traffic flow density for the regional road section.

[0120] In this step, when the regional road section is not equipped with a traffic flow detector, first, determine the traffic flow detector located upstream of the regional road section and adjacent to (closest to) the regional road section in position; then, obtain the upstream traffic flow density detected by the traffic flow detector (that is, the first traffic flow density of the regional road section with the traffic flow detector); finally, determine the upstream traffic flow density as the second traffic flow density of the regional road section.

[0121] S230. For the weaving area section, the merging area section and the diverging area section, respectively obtain a first inflow flow prediction value corresponding to the merging area section, a first outflow flow prediction value corresponding to the diverging area section, and a second inflow flow prediction value and a second outflow flow prediction value corresponding to the weaving area section output by a preset flow prediction model.

[0122] In this step, for the second divergence characteristic intersection and the second merging characteristic intersection included in the weaving area section, the first merging characteristic intersection included in the merging area section, and the first divergence characteristic intersection included in the divergence area section, the first inflow flow prediction value corresponding to the first merging characteristic intersection output by a preset flow prediction model, the first outflow flow prediction value corresponding to the first divergence characteristic intersection, and the second outflow flow prediction value and the second inflow flow prediction value corresponding to the second divergence characteristic intersection and the second merging characteristic intersection, respectively, are obtained.

[0123] It should be noted that, in one possible implementation mode of the present application, the predicted inflow flow value includes the sum of the predicted inflow flow value and the change in regional flow within the predicted time period.

[0124] In an embodiment of the present application, the preset traffic prediction model may include a model based on deep learning. For example, the deep learning model may include but is not limited to a recurrent neural network model (GRU, Gated Recurrent Unit), a graph convolutional network and a temporal convolutional network model (T-GCN, Temporal Graph Convolutional Network) and an attention mechanism-spatial convolution-temporal convolution model (AST-GCN, Attention-based Spatial-Temporal GraphConvolutional Network).

[0125] For example, see Figure 3 , Figure 3 A schematic diagram for obtaining traffic flow density and flow prediction values ​​for a regional road section provided in an embodiment of the present application.

[0126] like Figure 3 As shown in , it is assumed that the target expressway section includes 8 regional sections, wherein the first regional section is a merging area section provided with a traffic flow detector (F1); the third regional section is a diverging area section; the seventh regional section is an interweaving area section provided with a traffic flow detector (F5); the second regional section, the fourth regional section, the sixth regional section and the eighth regional section are basic regional sections in a state without traffic incidents respectively; and the fifth regional section is a basic regional section in a state with traffic incidents.

[0127] Specifically, Figure 3 As shown in the figure, the traffic flow detector (F1) and the traffic flow detector (F5) can respectively detect the first traffic flow density (ρ1 and ρ7) corresponding to the first area road segment and the seventh area road segment, respectively, and the second traffic flow density (ρ2, ρ3, ρ4, ρ5, ρ6) corresponding to the second area road segment, the third area road segment, the fourth area road segment, the fifth area road segment and the sixth area road segment, respectively, is ρ1 detected by the traffic flow detector (F1); the second traffic flow density (ρ8) corresponding to the eighth area road segment is ρ7 detected by the traffic flow detector (F5).

[0128] Further, such as Figure 3 As shown in the figure, a preset traffic prediction model is used to obtain a first incoming traffic prediction value (I1) corresponding to a first merging characteristic entrance included in the first area section, a first outgoing traffic prediction value (O3) corresponding to a first diverging characteristic entrance included in the third area section, and a second outgoing traffic prediction value (O5) and a second inflow traffic prediction value (I5) corresponding to a second diverging characteristic intersection and a second merging characteristic intersection included in the seventh area section.

[0129] S300: Determine the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section.

[0130] In the embodiment of the present application, the traffic flow parameters include a free flow speed set, a congestion upstream propagation speed set, a critical density value, a flow rate limit value and a blocking density value.

[0131] It should be noted that by analyzing the regional traffic status of the highway section, the basic section map of the regional section can be determined; wherein, the basic section map may include a curve of the corresponding relationship between traffic flow density value and flow rate, so as to determine the traffic flow parameters of the regional section through the basic section map, and then determine the corresponding free flow state or congestion state corresponding to the regional section.

[0132] For example, see Figure 4 , Figure 4 A curve diagram of a traffic flow parameter provided in an embodiment of the present application.

[0133] like Figure 4 As shown in FIG. 1 , in a curve diagram of an exemplary traffic flow parameter represented as a basic diagram of a road segment, the abscissa represents the density value (ρ), the ordinate represents the flow rate (Q), and Q M is the flow rate limit value (maximum flow rate) under free flow state; ρ M is the critical density value (maximum density value) corresponding to the flow rate limit; if the density value is greater than the critical density value ρ M , then the traffic state corresponding to the density value of the regional road section is determined to be congested. If the density value is less than ρ M , then the traffic state corresponding to the density value part of the regional road section is determined to be a free flow state; v is the free flow speed set; w is the congestion upstream propagation speed set; ρJ is the blocking density value.

[0134] Here, due to the existence of various external interference factors in the real environment, such as measurement errors, different density calculation methods, large vehicles, complex weather, road alignment and slope, traffic accidents and vehicle lane changing behavior, the traffic flow parameters are not fixed values, that is, the actual values ​​of the traffic flow parameters are different due to the interference of external factors.

[0135] Based on this, the embodiment of the present application can obtain more accurate traffic flow parameters by establishing a corresponding relationship model between interference factors and traffic flow parameters, thereby making the prediction of traffic status more accurate.

[0136] In this step, for whether there is a traffic event in the event status of each regional road section, the traffic flow parameters of each regional road section are determined in two ways based on the historical traffic data pre-collected for each regional road section.

[0137] Here, the historical traffic data includes a speed time series and a flow time series corresponding to each regional road section whose event status is a no-traffic-event status, and a road attribute parameter of each regional road section.

[0138] The road attribute parameters include, but are not limited to, the number of lanes, lane width, horizontal and vertical alignment parameters, and design speed.

[0139] In one implementation of the present application, during specific implementation, step S300 may include:

[0140] S310. For each regional road section where the event status is a no-traffic-event status, based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point.

[0141] In the embodiment of the present application, the speed change point may indicate that the speed corresponding to the position of the point is converted from the free flow speed to the congestion upward propagation speed.

[0142] For example, see Figure 5 , Figure 5 A schematic diagram of detecting a speed change point provided in an embodiment of the present application.

[0143] like Figure 5 As shown in , the speed time series detected by the traffic flow detector is v = {v t , v t+1 , ..., v t+n}, a two-dimensional plane coordinate curve graph is established with the horizontal axis being time and the vertical axis being speed. The flow time series detected by the traffic flow detector is f = {f t , f t+1 , ..., f t+n}, where when the traffic state changes from free flow to saturated flow, the speed changes from free flow speed to saturated flow speed, resulting in Figure 5 The velocity change point shown in , where the density value corresponding to the velocity change point is the critical density ρ M .

[0144] In one embodiment of the present application, in a specific implementation, the step of determining the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section in step S310 may include:

[0145] S311. Determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, and determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set.

[0146] In one embodiment of the present application, in a specific implementation, the step of pre-collecting the speed time series in step S311 may include:

[0147] Step A: When a speed detector is provided in the regional road section, the speed detector is used to collect the first speed time series of the regional road section in advance.

[0148] Step B: when no speed detector is set on the road section in the area, a free flow state data set and a congestion state data set of the road section in the area are obtained.

[0149] In this step, the data set is divided according to the change point position corresponding to the road section in the area, and the data located before the change point position is determined as free flow state data to form a free flow state data set; the data located after the change point position is determined as congestion state data to form a congestion state data set.

[0150] Step C: Based on the free flow state data set, a preset first speed detection model is used to determine the free flow speed time series of the regional road section.

[0151] Step D: Based on the congestion status data set, a preset second speed detection model is used to determine the time series of the congestion propagation speed upstream of the regional road section.

[0152] Step E: Determine the free flow speed time series and the congestion upstream propagation speed time series as the second speed time series of the regional road section.

[0153] In the embodiment of the present application, the first speed detection model and the second speed detection model are pre-set through the following steps: first, extract weather characteristics (for example, heavy rain, moderate rain, light rain, heavy snow, moderate snow, light snow, heavy fog, moderate fog, light fog, etc.) and distinguish characteristic values ​​of weather characteristics, and extract road characteristics (for example, number of lanes, lane width, horizontal and vertical alignment parameters and design speed, etc.); then, take the above characteristics as input and the free flow speed time series as output, and use the neural network method to establish the first speed detection model; finally, take the above characteristics as input and the congestion upstream propagation speed time series as output, and use the neural network method to establish the second speed detection model.

[0154] In one implementation of the present application, during specific implementation, step S311 may include:

[0155] S3111. Based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series pre-collected for the regional road section, determine whether the speed value and the flow value corresponding to each moment meet preset conditions, and obtain a judgment result; wherein the preset conditions include that the speed value is greater than a second preset value and the flow value is less than a preset free flow value.

[0156] In this step, based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series, it is judged whether each speed value is greater than the second preset value, and whether each flow value is less than the preset free flow value, so as to obtain the judgment result of whether the speed value and flow value corresponding to each moment meet the preset conditions.

[0157] The corresponding data of speed and time included in the speed time series correspond to at least one month's data.

[0158] In one possible implementation mode of the present application, the second preset value can be set to 10, or it can be specifically calibrated according to the actual application scenario and the road conditions of the target highway section; the preset free flow value is pre-calibrated according to the actual application scenario and the road conditions of the target highway section.

[0159] S3112: Based on the judgment result, at least one speed value that meets a preset condition is screened out from the speed time series, and the at least one speed value is determined as a first free flow speed set for the regional road section.

[0160] In this step, at least one speed value whose speed value is greater than the second preset value and whose flow value is less than the preset free flow value is determined as the first free flow speed set of the regional road section.

[0161] S3113: Perform mean calculation on at least one first free flow speed included in the first free flow speed set, and determine the obtained mean calculation result as the first free flow speed mean of the regional road section.

[0162] S3114. For multiple preset time intervals included in the speed time series, the first free flow speed mean is subtracted from the multiple speed values ​​corresponding to each preset time interval to obtain a deviation calculation result, and based on the deviation calculation result and the multiple speed values ​​and flow values ​​corresponding to each preset time interval, the multiple congestion upstream propagation speeds corresponding to the regional road section at each preset time interval are determined to determine the first congestion upstream propagation speed set for the regional road section.

[0163] In this step, it is determined whether the deviation calculation result is greater than the first congestion upstream propagation speed corresponding to the first free flow speed mean, whether the speed value corresponding to each preset time interval is greater than the calibration value, and whether the flow value corresponding to each preset time interval is greater than the preset free flow value, to obtain a judgment result.

[0164] Furthermore, according to the judgment result, the first congestion upstream propagation speed corresponding to the first free flow speed mean when the deviation calculation result is greater than the first congestion upstream propagation speed, the speed value corresponding to each preset time interval is greater than the calibration value, and the flow value corresponding to each preset time interval is greater than the preset free flow value, at least one speed value corresponding to the speed value is determined as the first congestion upstream propagation speed set for the regional road section.

[0165] In the embodiment of the present application, the preset time interval may be set to one day, or may be specifically calibrated according to the actual application scenario and the road conditions of the target highway section.

[0166] S3115. Based on the first free flow speed set and the first congestion upstream propagation speed set, determine the speed change point corresponding to the regional road section at each preset time interval to determine a speed change point data set for the regional road section.

[0167] In this step, the moment when the first free flow speed in each preset time interval is converted into the first congestion upstream propagation speed set is determined as the speed change point corresponding to each preset time interval, thereby determining the speed change point data set of the regional road section.

[0168] S312, performing mean calculation on the density value corresponding to each speed change point in the speed change point data set, and determining the obtained mean calculation result as the first critical density value of the road section in the area;

[0169] S313: multiply the first critical density value and the first free flow speed mean corresponding to the first free flow speed set, and determine the obtained product as the first flow rate limit value of the regional road section.

[0170] In this step, during specific implementation, first, the first free flow speed mean corresponding to the first free flow speed set is calculated; then the first critical density value and the first free flow speed mean are input into a preset calculation formula for the first flow rate limit value; finally, the first flow rate limit value of the regional section is calculated by the formula.

[0171] Specifically, the calculation formula of the preset first flow rate limit value is expressed as follows.

[0172] Q M =ρ M *v mean .

[0173] Among them, Q M is the first flow rate limit; ρ M is the first critical density value; v mean is the first free flow speed mean.

[0174] S314, performing mean calculation on the density values ​​respectively corresponding to at least one speed value whose speed value in the speed time series is the first preset value, and determining the obtained mean calculation result as the first congestion density value of the regional road section.

[0175] S320. For each regional road section where the event status is a traffic event status, based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section, determine the second traffic flow parameter of the regional road section by utilizing a pre-established speed relationship model and detecting and analyzing speed change points.

[0176] In this step, for each regional road section with a traffic event status, the second free flow speed set and the second congestion upstream propagation speed set are determined based on the road attribute parameters and using a pre-established speed relationship model, and the second traffic flow parameters of the regional road section are further determined by detecting and analyzing speed change points.

[0177] In one embodiment of the present application, in a specific implementation, the step of determining the second traffic flow parameter of the regional road section by using a pre-established speed relationship model and detecting and analyzing speed change points based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section in step S320 may include:

[0178] S321. Based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section, determine the second free flow speed set and the second congestion upstream propagation speed set for the regional road section by using a pre-established speed relationship model.

[0179] In an embodiment of the present application, the speed relationship model includes a free flow speed relationship model and a congestion upstream propagation speed relationship model.

[0180] Specifically, the speed relationship model is pre-established through the following steps: first, the data set is divided according to the position of the speed change point, the speed data before the speed change point is determined as the free flow state data, and the speed data after the speed change point that meets the preset change point condition and the flow value is greater than the preset free flow value is extracted as the congestion state data to form a free flow state data set and a congestion state data set; then, road features (for example, the number of lanes, lane width, horizontal and vertical alignment parameters and design speed, etc.) are extracted from the free flow state data set and the congestion state data set; finally, with the road features as input and using the neural network method, when the free flow speed is used as the output, a free flow speed relationship model is established, and when the congestion upstream propagation speed is used as the output, a congestion upstream propagation speed relationship model is established.

[0181] S322. Determine the time corresponding to converting the second free flow speed set into the second congestion upstream propagation speed set as the speed change point time of the regional road section, and determine the density value corresponding to the speed change point time as the second critical density value of the regional road section.

[0182] S323: Multiply the second critical density value and the second free flow speed, and determine the obtained product as the second flow rate limit value of the regional section.

[0183] S324: Calculate the average of the density values ​​corresponding to at least one second free flow whose speed value is the first preset value and is included in the second free flow speed set, and determine the average calculation result as the second congestion density value of the regional road section.

[0184] Among them, the description of S322 to S324 can refer to the description of S312 to S314, and can achieve the same technical effect, which will not be repeated here.

[0185] S400, based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value, determine the predicted density value of each regional road section using a preset regional traffic flow evolution formula.

[0186] In this step, during the specific implementation, first, based on the traffic flow density and the flow prediction value, the predicted flow increment of each regional road section is obtained using a preset flow prediction model; then, the free flow speed set, congestion upstream propagation speed set, flow rate limit value, blocking density value and predicted flow increment of each regional road section are input into the preset regional traffic flow evolution formula; finally, the predicted density value of each regional road section output by the regional traffic flow evolution formula is obtained.

[0187] In the embodiment of the present application, the regional traffic flow evolution formula is pre-set through the regional traffic flow parameter evolution mechanism. Specifically, the relevant formula of the regional traffic flow parameter evolution mechanism is as follows.

[0188]

[0189] q i (k) = min{S i-1 (k), R i (k)}.

[0190] S i-1 (k) = min{vρ i-1 (k), Q M，i-1}.

[0191] R i (k) = min{w(ρ J -ρ i (k)), Q M，i}.

[0192] Among them, T S is the time window; k is the time index; l i is the length of the road section in the ith area; q i (k) is the flow rate value of the road section i entering the area in the time period [k, k+1). i-1 (k) is the flow rate value of the previous regional section into the regional section i; R i (k) is the flow value that the regional road section i can receive; q i (k) is the minimum value of the upstream input flow and the acceptable flow value of regional section i, q i+1 (k) is the minimum value of the output flow value of the regional road section i and the downstream acceptable flow value; v is the free flow speed set; w is the congestion propagation speed set upstream; Q M is the flow rate limit; ρ J is the blocking density value.

[0193] Based on the relevant formulas of the regional traffic flow parameter evolution mechanism, it can be seen that the traffic state of each regional road section depends on the current road section state, input flow value and outflow flow value of the regional road section.

[0194] Here, based on the relevant formulas of the regional traffic flow parameter evolution mechanism, the regional traffic flow evolution formula can be obtained through inference evolution. Specifically, the expression of the regional traffic flow evolution formula is as follows.

[0195]

[0196] Among them, ρ i (k+1) is the predicted density value of each regional road section; ρi (k) is the density value of each area section; T S is the time window; k is the time index; l i is the length of the road section in the ith area; q i (k) is the flow value of the road section i entering the area in the time period [k, k+1); v is the free flow speed set; w is the congestion propagation speed set upstream; Q M is the flow rate limit; ρ J is the blocking density value.

[0197] Among them, Figure 3 Taking the target highway section including 8 regional sections shown in as an example, an exemplary expression of C(k+1) and O(k+1) is shown as follows.

[0198] C1(k+1)=I1(k+1)+q1(k+1)-q1(k), O1(k+1)=0.

[0199] C2(k+1)=q2(k+1)-q2(k), O2(k+1)=0.

[0200] C3(k+1)=q3(k+1)-q3(k), O3(k+1)=O3(k+1).

[0201] C7(k+1)=I7(k+1)+q7(k+1)-q7(k), O7(k+1)=O7(k+1).

[0202] Among them, I1(k+1) and I7(k+1) are the first predicted inflow flow increment and the second predicted inflow flow increment respectively; O1(k+1) and O7(k+1) are the first predicted outflow flow increment and the second predicted outflow flow increment respectively.

[0203] S500: Compare the predicted density value with the critical density value in the traffic flow parameter, and determine the predicted traffic state of each regional road section according to the comparison result.

[0204] In one implementation of the present application, during specific implementation, step S500 may include:

[0205] S510: Compare the predicted density value with the critical density value in the traffic flow parameter to determine whether the predicted density value is greater than the critical density value, and obtain a comparison result.

[0206] In the embodiment of the present application, since the critical density value represents the density value corresponding to the critical point where the free flow state is converted into the congested state, by judging whether the predicted density value is greater than the critical density value, the predicted traffic state of each area section can be determined.

[0207] S520: If the comparison result is that the predicted density value is greater than the critical density value, it is determined that the predicted traffic state of the road section in the area is a congested state.

[0208] S530: If the comparison result is that the predicted density value is less than or equal to the critical density value, determine that the predicted traffic state of the road section in the area is a free flow state.

[0209] In an embodiment of the present application, when the predicted density value is greater than the critical density value, the predicted traffic state of the road section in the area is determined to be a congested state; when the predicted density value is less than or equal to the critical density value, the predicted traffic state of the road section in the area is determined to be a free flow state.

[0210] Among them, the free flow state refers to the state in which vehicles on the roads of the regional section can travel freely at a higher speed without external interference; the congestion state refers to the situation in which vehicles cannot travel at a normal speed because the traffic volume of the regional section exceeds the carrying capacity of the roads of the regional section.

[0211] The method for predicting the traffic status of a highway provided in an embodiment of the present application divides a target highway section into multiple regional sections according to the confluence and divergence characteristics of the target highway section and whether there are traffic incidents, uses a traffic flow detector and a flow prediction model to obtain the traffic flow density and / or flow prediction value of each regional section, and further determines the traffic flow parameters of each regional section, and determines the predicted density value of each regional section based on the traffic flow parameters and the predicted flow increment of each regional section predicted by the flow prediction model, so as to determine the predicted traffic status of each regional section according to the comparison result of the predicted density value and the critical density value in the traffic flow parameters, thereby improving the comprehensiveness and reliability of data collection, and thereby improving the accuracy of predicting traffic status.

[0212] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of a device for predicting highway traffic conditions provided by an embodiment of the present application. Figure 6 As shown in , the prediction device 600 includes:

[0213] The road segment division module 610 is used to divide the target highway section into multiple regional sections according to the merging and diverging characteristics of the highway section, and determine the section characteristics and event status corresponding to each regional section; wherein the section characteristics include basic regional sections, interweaving section, merging section and diverging section; the event status includes no traffic event status and traffic event status;

[0214] The data acquisition module 620 is used to acquire the traffic flow density and / or traffic flow prediction value of each regional road section based on the road section characteristics corresponding to each regional road section and using the traffic flow detector set in the target highway section and the preset traffic flow prediction model;

[0215] A parameter determination module 630, configured to determine a traffic flow parameter of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section;

[0216] A prediction module 640, configured to determine the predicted density value of each regional road section using a preset regional traffic flow evolution formula based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value;

[0217] The comparison module 650 is used to compare the predicted density value with the critical density value in the traffic flow parameter, and determine the predicted traffic state of each regional road section according to the comparison result.

[0218] Further, when the data acquisition module 620 is used to acquire the traffic flow density and / or flow prediction value of each regional road section based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and the preset flow prediction model, the data acquisition module 620 is used to:

[0219] For each of the regional road sections, when a traffic flow detector is provided for the regional road section, obtaining a first traffic flow density of the regional road section collected by the traffic flow detector;

[0220] When the regional road section is not provided with a traffic flow detector, obtaining an upstream traffic flow density detected by a traffic flow detector located upstream of the regional road section and adjacent to the regional road section, and determining the upstream traffic flow density as a second traffic flow density of the regional road section;

[0221] For the weaving area section, the merging area section and the diverging area section, the first inflow flow prediction value corresponding to the merging area section, the first outflow flow prediction value corresponding to the diverging area section, and the second inflow flow prediction value and the second outflow flow prediction value corresponding to the weaving area section output by a preset flow prediction model are respectively obtained.

[0222] Further, the traffic flow parameters include a free flow speed set, a congestion upstream propagation speed set, a critical density value, a flow rate limit value, and a blocking density value;

[0223] When the parameter determination module 630 is used to determine the traffic flow parameter of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section, the parameter determination module 630 is used to:

[0224] For each of the regional road sections where the event status is a traffic event-free state, based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point;

[0225] For each regional road section where the event status is a traffic event status, based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section, the second traffic flow parameter of the regional road section is determined by utilizing a pre-established speed relationship model and detecting and analyzing speed change points.

[0226] Further, when the parameter determination module 630 is used to determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, the parameter determination module 630 is used to:

[0227] Determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on a speed time series and a flow time series included in the historical traffic data collected in advance for the regional road section, and determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set;

[0228] Performing mean calculation on the density value corresponding to each speed change point in the speed change point data set, and determining the obtained mean calculation result as the first critical density value of the road section in the area;

[0229] multiplying the first critical density value and the first free flow speed mean corresponding to the first free flow speed set, and determining the obtained product as the first flow rate limit value of the regional road section;

[0230] The density values ​​respectively corresponding to at least one speed value whose speed value in the speed time series is a first preset value are averaged, and the averaged calculation result is determined as the first blocking density value of the regional road section.

[0231] Furthermore, when the parameter determination module 630 is used to pre-collect the speed time series, the parameter determination module 630 is used to:

[0232] When a speed detector is provided in the regional road section, the speed detector is used to collect the first speed time series of the regional road section in advance;

[0233] When the road section in the area is not provided with a speed detector, a free flow state data set and a congestion state data set of the road section in the area are obtained;

[0234] Based on the free flow state data set, a preset first speed detection model is used to determine a free flow speed time series of the road section in the area;

[0235] Based on the congestion status data set, a preset second speed detection model is used to determine a time series of the congestion propagation speed upstream of the road section in the area;

[0236] The free flow speed time series and the congestion upstream propagation speed time series are determined as the second speed time series of the regional road section.

[0237] Further, when the parameter determination module 630 is used to determine a first free flow speed set and a first congestion upstream propagation speed set of the regional road section based on the speed time series and the flow time series included in the historical traffic data pre-collected for the regional road section, and to determine a speed change point data set of the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set, the parameter determination module 630 is used to:

[0238] Based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series pre-collected in the regional road section, determine whether the speed value and the flow value corresponding to each moment meet the preset conditions, and obtain a judgment result; wherein the preset conditions include that the speed value is greater than a second preset value and the flow value is less than a preset free flow value;

[0239] Based on the judgment result, at least one speed value satisfying a preset condition is selected from the speed time series, and the at least one speed value is determined as a first free flow speed set of the regional road section;

[0240] Performing mean calculation on at least one first free flow speed included in the first free flow speed set, so as to determine the obtained mean calculation result as the first free flow speed mean of the regional road section;

[0241] For a plurality of preset time intervals included in the speed time series, the first free flow speed mean is subtracted from a plurality of speed values ​​corresponding to each preset time interval to obtain a deviation calculation result, and based on the deviation calculation result and a plurality of speed values ​​and flow values ​​corresponding to each preset time interval, a plurality of congestion upstream propagation speeds corresponding to each preset time interval of the regional road section are determined to determine a first congestion upstream propagation speed set of the regional road section;

[0242] Based on the first free flow speed set and the first congestion upstream propagation speed set, a speed change point corresponding to the regional road section at each preset time interval is determined to determine a speed change point data set for the regional road section.

[0243] Further, when the parameter determination module 630 is used to determine the second traffic flow parameter of the regional road section based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section by using a pre-established speed relationship model and detecting and analyzing speed change points, the parameter determination module 630 is used to:

[0244] Based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section, a second free flow speed set and a second congestion upstream propagation speed set for the regional road section are determined by using a pre-established speed relationship model;

[0245] Determine the time corresponding to the conversion of the second free flow speed set into the second congestion upstream propagation speed set as the speed change point time of the regional road section, and determine the density value corresponding to the speed change point time as the second critical density value of the regional road section;

[0246] Multiplying the second critical density value and the second free flow speed, and determining the obtained product as the second flow rate limit value of the regional road section;

[0247] The density values ​​respectively corresponding to at least one second free flow whose speed value is the first preset value included in the second free flow speed set are averaged, and the obtained average calculation result is determined as the second blocking density value of the regional road section.

[0248] Furthermore, when the comparison module 650 is used to compare the predicted density value with the critical density value in the traffic flow parameter and determine the predicted traffic state of each regional road section according to the comparison result, the comparison module 650 is used to:

[0249] Comparing the predicted density value with the critical density value in the traffic flow parameter to determine whether the predicted density value is greater than the critical density value, and obtaining a comparison result;

[0250] If the comparison result is that the predicted density value is greater than the critical density value, determining that the predicted traffic state of the road section in the area is a congested state;

[0251] If the comparison result is that the predicted density value is less than or equal to the critical density value, it is determined that the predicted traffic state of the road section in the area is a free flow state.

[0252] The device for predicting the traffic status of a highway provided in an embodiment of the present application divides a target highway section into multiple regional sections according to the confluence and divergence characteristics of the target highway section and whether there are traffic incidents, uses a traffic flow detector and a flow prediction model to obtain the traffic flow density and / or flow prediction value of each regional section, and further determines the traffic flow parameters of each regional section, and determines the predicted density value of each regional section based on the traffic flow parameters and the predicted flow increment of each regional section predicted by the flow prediction model, so as to determine the predicted traffic status of each regional section according to the comparison result of the predicted density value and the critical density value in the traffic flow parameters, thereby improving the comprehensiveness and reliability of data collection, and further improving the accuracy of predicting the traffic status.

[0253] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown in , the electronic device 700 includes a processor 710 , a memory 720 and a bus 730 .

[0254] The memory 720 stores machine-readable instructions executable by the processor 710. When the electronic device 700 is running, the processor 710 communicates with the memory 720 via the bus 730. When the machine-readable instructions are executed by the processor 710, the above-mentioned Figure 1 The specific implementation of the steps of the method for predicting the highway traffic status in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0255] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The specific implementation of the steps of the method for predicting the highway traffic status in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0256] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0257] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0258] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0259] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0260] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0261] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for predicting highway traffic conditions, characterized in that: The prediction method comprises: According to the merging and diverging characteristics of the expressway section, the target expressway section is divided into multiple regional sections, and the section characteristics and event status corresponding to each regional section are determined; wherein the section characteristics include basic regional sections, interweaving section, merging section and diverging section; the event status includes no traffic event status and traffic event status; Based on the road section features corresponding to each regional road section, using the traffic flow detector set in the target highway section and a preset flow prediction model, the traffic flow density and / or flow prediction value of each regional road section is obtained; Determine the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section; Based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value, a predicted density value of each regional road section is determined using a preset regional traffic flow evolution formula; The predicted density value is compared with the critical density value in the traffic flow parameter, and the predicted traffic state of each regional road section is determined according to the comparison result.

2. The method according to claim 1, characterized in that The method of obtaining the traffic flow density and / or traffic flow prediction value of each regional road section based on the road section features corresponding to each regional road section and using the traffic flow detector set in the target highway section and a preset traffic flow prediction model includes: For each of the regional road sections, when a traffic flow detector is provided for the regional road section, obtaining a first traffic flow density of the regional road section collected by the traffic flow detector; When the regional road section is not provided with a traffic flow detector, obtaining an upstream traffic flow density detected by a traffic flow detector located upstream of the regional road section and adjacent to the regional road section, and determining the upstream traffic flow density as a second traffic flow density of the regional road section; For the weaving area section, the merging area section and the diverging area section, the first inflow flow prediction value corresponding to the merging area section, the first outflow flow prediction value corresponding to the diverging area section, and the second inflow flow prediction value and the second outflow flow prediction value corresponding to the weaving area section output by a preset flow prediction model are respectively obtained.

3. The method according to claim 1, characterized in that The traffic flow parameters include a free flow speed set, a congestion upstream propagation speed set, a critical density value, a flow rate limit value, and a blocking density value; The determining of the traffic flow parameters of each regional road section based on the event status of each regional road section and the historical traffic data collected in advance for each regional road section includes: For each of the regional road sections where the event status is a traffic event-free state, based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section, determine the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point; For each regional road section where the event status is a traffic event status, based on the road attribute parameters included in the historical traffic data pre-collected for the regional road section, the second traffic flow parameter of the regional road section is determined by utilizing a pre-established speed relationship model and detecting and analyzing speed change points.

4. The method according to claim 3, characterized in that The method of determining the first traffic flow parameter of the regional road section by detecting and analyzing the speed change point based on the speed time series and flow time series included in the historical traffic data pre-collected for the regional road section includes: Determine a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on a speed time series and a flow time series included in the historical traffic data collected in advance for the regional road section, and determine a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set; Performing mean calculation on the density value corresponding to each speed change point in the speed change point data set, and determining the obtained mean calculation result as the first critical density value of the road section in the area; Multiplying the first critical density value and the first free flow speed mean corresponding to the first free flow speed set, and determining the obtained product as the first flow rate limit value of the regional road section; The density values ​​respectively corresponding to at least one speed value whose speed value in the speed time series is a first preset value are averaged, and the averaged calculation result is determined as the first blocking density value of the regional road section.

5. The method according to claim 4, characterized in that The speed time series is pre-collected by the following steps: When a speed detector is provided in the regional road section, the speed detector is used to collect the first speed time series of the regional road section in advance; When the road section in the area is not provided with a speed detector, a free flow state data set and a congestion state data set of the road section in the area are obtained; Based on the free flow state data set, a preset first speed detection model is used to determine a free flow speed time series of the road section in the area; Based on the congestion status data set, a preset second speed detection model is used to determine a time series of the congestion propagation speed upstream of the road section in the area; The free flow speed time series and the congestion upstream propagation speed time series are determined as the second speed time series of the regional road section.

6. The method according to claim 4, characterized in that The method of determining a first free flow speed set and a first congestion upstream propagation speed set for the regional road section based on the speed time series and the flow time series included in the historical traffic data pre-collected for the regional road section, and determining a speed change point data set for the regional road section based on the first free flow speed set and the first congestion upstream propagation speed set, comprises: Based on the multiple speed values ​​included in the speed time series and the multiple flow values ​​included in the flow time series pre-collected in the regional road section, determine whether the speed value and the flow value corresponding to each moment meet the preset conditions, and obtain a judgment result; wherein the preset conditions include that the speed value is greater than a second preset value and the flow value is less than a preset free flow value; Based on the judgment result, at least one speed value satisfying a preset condition is selected from the speed time series, and the at least one speed value is determined as a first free flow speed set of the regional road section; Performing mean calculation on at least one first free flow speed included in the first free flow speed set, so as to determine the obtained mean calculation result as the first free flow speed mean of the regional road section; For a plurality of preset time intervals included in the speed time series, the first free flow speed mean is subtracted from a plurality of speed values ​​corresponding to each preset time interval to obtain a deviation calculation result, and based on the deviation calculation result and a plurality of speed values ​​and flow values ​​corresponding to each preset time interval, a plurality of congestion upstream propagation speeds corresponding to each preset time interval of the regional road section are determined to determine a first congestion upstream propagation speed set of the regional road section; Based on the first free flow speed set and the first congestion upstream propagation speed set, a speed change point corresponding to the regional road section at each preset time interval is determined to determine a speed change point data set for the regional road section.

7. The method according to claim 3, characterized in that The method of determining the second traffic flow parameter of the regional road section based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section by using a pre-established speed relationship model and detecting and analyzing speed change points includes: Based on the road attribute parameters included in the historical traffic data collected in advance for the regional road section, a second free flow speed set and a second congestion upstream propagation speed set for the regional road section are determined by using a pre-established speed relationship model; Determine the time corresponding to the conversion of the second free flow speed set into the second congestion upstream propagation speed set as the speed change point time of the regional road section, and determine the density value corresponding to the speed change point time as the second critical density value of the regional road section; Multiplying the second critical density value and the second free flow speed, and determining the obtained product as the second flow rate limit value of the regional road section; The density values ​​respectively corresponding to at least one second free flow whose speed value is the first preset value included in the second free flow speed set are averaged, and the obtained average calculation result is determined as the second blocking density value of the regional road section.

8. The method according to claim 1, characterized in that The step of comparing the predicted density value with the critical density value in the traffic flow parameter and determining the predicted traffic state of each regional road section according to the comparison result includes: Comparing the predicted density value with the critical density value in the traffic flow parameter to determine whether the predicted density value is greater than the critical density value, and obtaining a comparison result; If the comparison result is that the predicted density value is greater than the critical density value, determining that the predicted traffic state of the road section in the area is a congested state; If the comparison result is that the predicted density value is less than or equal to the critical density value, it is determined that the predicted traffic state of the road section in the area is a free flow state.

9. A device for predicting highway traffic conditions, characterized in that: The prediction device comprises: A road segmentation module is used to divide the target highway section into multiple regional sections according to the merging and diverging characteristics of the highway section, and determine the section characteristics and event status corresponding to each regional section; wherein the section characteristics include basic regional sections, interweaving section sections, merging section sections and diverging section sections; the event status includes a state without traffic events and a state with traffic events; A data acquisition module, configured to acquire the traffic flow density and / or traffic flow prediction value of each regional road section based on the road section features corresponding to each regional road section and using the traffic flow detectors provided in the target highway section and a preset traffic flow prediction model; A parameter determination module, configured to determine a traffic flow parameter of each regional road section based on an event state of each regional road section and historical traffic data collected in advance for each regional road section; A prediction module, configured to determine the predicted density value of each regional road section by using a preset regional traffic flow evolution formula based on the traffic flow parameters and the predicted flow increment of each regional road section predicted by a preset flow prediction model based on the traffic flow density and the flow prediction value; A comparison module is used to compare the predicted density value with the critical density value in the traffic flow parameter, and determine the predicted traffic state of each regional road section according to the comparison result.

10. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are run by the processor, the steps of the method for predicting highway traffic conditions as described in any one of claims 1 to 8 are executed.

Images