WO2022143549A1

WO2022143549A1 - Expressway road condition monitoring method and apparatus based on toll collection data

Info

Publication number: WO2022143549A1
Application number: PCT/CN2021/141732
Authority: WO
Inventors: 郭胜敏; 董彪; 苏欣; 李智; 杨珍珍; 李运才; 夏曙东
Original assignee: 北京千方科技股份有限公司; 北京掌行通信息技术有限公司
Priority date: 2020-12-31
Filing date: 2021-12-27
Publication date: 2022-07-07
Also published as: CN112785735B; CN112785735A

Abstract

An expressway road condition monitoring method and apparatus based on toll collection data, and a computer device and a storage medium, which relate to the technical field of big data. The monitoring method comprises: determining whether the current traveling vehicle reaches a target point within an estimated arrival time point; and if it is determined that the current traveling vehicle reaches the target point within the estimated arrival time point, detecting that the current traveling vehicle is not stuck on a target traveling path, otherwise, detecting that the current traveling vehicle is stuck on a road section which is within the target traveling path and is associated with at least one target point (S104). A road network topological graph for expressway toll collection is introduced, such that it can not only be accurately detected whether congestion occurs on a target traveling path, but a road section which is specifically within the target traveling path and is associated with a specific target point and on which the congestion occurs can also be detected.

Description

A method and device for monitoring highway road conditions based on toll data

priority information

This application claims the priority of the Chinese patent application filed on December 31, 2020 with the application number 202011640800.1 and the invention titled "A method and device for monitoring highway road conditions based on toll data", the entire contents of which are Incorporated herein by reference.

technical field

The present application relates to the technical field of traffic big data, and in particular, to a method and device for monitoring highway road conditions based on toll data.

Background technique

At present, the dynamic traffic information service is mainly based on mobile location data and floating car technology. By collecting and processing data such as the position and driving speed of sampled vehicles on the expressway, the average traffic speed information on the road is calculated and released. It has high information accuracy and granularity. It is widely used because of its advantages such as fineness and fast refresh rate. It should be pointed out that the mobile location data is limited by the essential characteristics of its sampling data, and its spatial and temporal distribution is extremely unbalanced. Generally speaking, the inventor realizes that the sampling rate of mobile location data on highways is lower than 10% on average, which makes many roads pass by vehicles, but show no data because they are not sampled. This phenomenon occurs at night. Especially during off-peak hours. The above problems can also be remedied by methods such as historical data mining in general scenarios, but if the road is blocked and not detected in time in extreme scenarios such as accidents and disasters, it will lead to more serious consequences. To this end, dynamic traffic information service providers, highway management departments, etc. are actively exploring the introduction of other data sources and multi-source data fusion methods to solve the problem of low highway information coverage.

With the popularization of sensing equipment such as toll networking, ETC toll collection, and video detection, nearly full-traffic road network operation monitoring scenarios are provided on expressways. However, whether it is ETC charging or video detection equipment, the distribution of the deployed gantry points is limited after all. For example, the distance between two adjacent gantry is generally ten kilometers, dozens of highways or even farther, which means data collection The frequency and timeliness of information, the granularity of information expression, etc. have been greatly challenged.

The existing monitoring methods applied to highway road conditions often use GPS technology, but GPS technology randomly samples and monitors the driving conditions of vehicles driving on the highway. Vehicle monitoring makes it even more impossible to accurately predict the road congestion that may occur for each driving vehicle.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a method, device, computer equipment, and storage medium for monitoring highway road conditions based on toll data. In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be an extensive review, nor is it intended to identify key/critical elements or delineate the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the detailed description that follows.

In a first aspect, an embodiment of the present application provides a method for monitoring highway road conditions based on toll data, the method comprising:

A road network topology map for expressway toll collection is constructed, the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a driving path path used to identify each traveling vehicle A segmented mesotopological map having identified intersections between individual path segments;

Estimating the preset distance between the current driving speed of the vehicle and the target point on the target travel path, the target point includes the target downstream gantry point marked on the macro topology map and the target point marked on the meso topology map. the target intersection;

According to the estimated traveling speed of the currently traveling vehicle and the preset distance, the time required for the currently traveling vehicle to travel the preset distance at the traveling speed is predicted; and the initial value determined based on the charging data of the currently traveling vehicle the time point and the duration, and predict the estimated arrival time point of the currently traveling vehicle traveling to the target point;

Determine whether the current driving vehicle travels to the target point within the estimated arrival time point, and if it is determined that the current driving vehicle travels to the target point within the estimated arrival time point, it is detected that the current driving vehicle is at the target point. There is no congestion on the target travel path, otherwise, it is detected that the road segment that is currently traveling in the target travel path and is associated with the at least one target point is congested.

In a second aspect, an embodiment of the present application provides a device for monitoring highway road conditions based on toll data, the device comprising:

A building module for constructing a road network topology map for expressway tolling, the road network topology map including a macro topology map used to identify the upstream and downstream relationships between the various gantry on each path and a macro topology map used to identify each travel a meso-topological map of path segments of the vehicle's travel path, the meso-topological map having identified intersections between the individual path segments;

Estimation module, used for estimating the preset distance between the current driving vehicle speed and the target point on the target travel path, the target point includes the target downstream identified on the macro topology map constructed by the building module a gantry point and a target intersection identified in the mesotopographic map constructed by the building block;

A prediction module, configured to predict the time required for the current vehicle to travel the preset distance at the travel speed according to the travel speed of the current vehicle and the preset distance estimated by the prediction module; and Based on the initial time point and the duration determined by the charging data of the current driving vehicle, predict the estimated arrival time point when the currently driving vehicle travels to the target point;

The processing module is used to judge whether the current driving vehicle travels to the target point within the estimated arrival time point predicted by the prediction module, and if it is determined that the current driving vehicle travels to the target arrival time point within the estimated arrival time point. For the target point, it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and is associated with the at least one target point. congestion.

In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor causes the processor to Perform the following steps:

In a fourth aspect, an embodiment of the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:

The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

In the embodiment of the present application, according to the estimated travel speed and preset distance of the currently traveling vehicle, the time required for the current traveling vehicle to travel the preset distance at the traveling speed is predicted; and the charging data determined based on the current traveling vehicle Initial time point and duration, predict the estimated arrival time point of the current driving vehicle to the target point; and determine whether the current driving vehicle travels to the target point within the estimated arrival time point, if it is determined that the current driving vehicle arrives at the estimated arrival time point If the vehicle travels to the target point within the time point, it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and that the road section associated with at least one target point is congested. In the embodiment of the present application, due to the introduction of the constructed road network topology map for expressway toll collection, it is not only possible to accurately detect whether congestion occurs on the target driving path, but also to monitor the specific location within the target driving path, and where it is connected to. A road segment associated with a destination point is congested.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

1 is a schematic flowchart of a method for monitoring highway road conditions based on toll data provided by an embodiment of the present application;

2 is a schematic diagram of a scenario difference analysis of charging data and mobile location data under a specific application scenario provided by an embodiment of the present application;

3 is a schematic diagram of a macro topology map and a meso topology map in a road network topology map for expressway toll collection constructed under a specific application scenario provided by an embodiment of the present application;

4 is a schematic diagram of a traffic coupling analysis unit under a specific application scenario provided by an embodiment of the present application;

5 is a schematic diagram of a meso link monitoring module under a specific application scenario provided by an embodiment of the present application;

6 is a schematic diagram of an inferred relationship between path segmentation validity and macro link validity under a specific application scenario provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an apparatus for monitoring highway road conditions based on toll data provided by an embodiment of the present application.

Detailed ways

The following description and drawings sufficiently illustrate specific embodiments of the application to enable those skilled in the art to practice them.

It should be clear that the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The inventor realized that the monitoring method based on the existing highway road conditions cannot monitor every driving vehicle equipped with on-board unit equipment, and it is even more impossible to accurately predict the traffic congestion phenomenon that may occur in each driving vehicle. Problem, for this reason, the present application provides a method, device, computer equipment and storage medium for monitoring highway road conditions based on toll data, so as to solve the problems existing in the above-mentioned related technical problems. In the technical solution provided by the present application, according to the estimated travel speed and preset distance of the currently traveling vehicle, the time required for the current traveling vehicle to travel the preset distance at the traveling speed is predicted; and the charging data of the current traveling vehicle is determined based on the the initial time point and duration, predict the estimated arrival time point of the currently traveling vehicle traveling to the target point; and determine whether the current traveling vehicle travels to the target point within the estimated arrival time point, if it is determined that the current traveling vehicle is within the estimated time point of arrival If the vehicle travels to the target point within the arrival time point, it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and that the road section associated with at least one target point is congested. In the embodiment of the present application, due to the introduction of the constructed road network topology map for expressway toll collection, it is not only possible to accurately detect whether congestion occurs on the target driving path, but also to monitor the specific location within the target driving path, and where it is connected to. A road section associated with a target point is congested, which will be described in detail below using an exemplary embodiment.

The method for monitoring highway road conditions based on toll data provided by the embodiment of the present application will be described in detail below with reference to FIG. 1 to FIG. 6 . The method for monitoring highway road conditions based on toll data can be implemented by relying on a computer program, and can be run on a device for monitoring highway road conditions based on toll data.

As shown in FIG. 1 , it is a schematic flowchart of a method for monitoring highway road conditions based on toll data provided by an embodiment of the present application, and the method for monitoring highway road conditions based on massive toll data is applied to a server, especially the cloud; As shown in FIG. 1 , the method for monitoring highway road conditions based on toll data according to the embodiment of the present application may include the following steps:

S101, constructing a road network topology map for expressway toll collection, where the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a driving path path used to identify each traveling vehicle A segmented meso topology map with identified intersections between individual path segments.

As shown in FIG. 2 , it is a schematic diagram of a scenario difference analysis of charging data and mobile location data under a specific application scenario provided by an embodiment of the present application.

As shown in Figure 2, A, B, and C are three tolling gantry, and gantry B and gantry C are downstream of gantry A. Vehicles Car1 and Car2 travel from gantry A to gantry B and gantry C respectively, and the points in Figure 2 can be regarded as their moving position point sequence. Whether it is based on ETC charging or video recognition, the mechanism is that when the vehicle passes through the gantry, the vehicle information is collected by the gantry and uploaded to the background and recorded. Only when the vehicle passes through the gantry B or C, the gantry B and C know that a vehicle starts from the gantry A and arrives at B and C. Therefore, relative to the moving position data, all driving details between A→B and A→C can be expressed. For example, when a block occurs at f between A→C, the moving position point of Car2 can be clearly expressed, while The charging data can only be known when Car2 reaches the gantry C through the blocking point. The above example can well illustrate the latency disadvantage of fixed-point sensing data compared to mobile data. For example, when Car2 breaks through f and reaches gantry C, it is observed. At this time, the blocking detection at the position f has a long delay. In extreme cases, if Car2 cannot break through f, gantry C will never be known. The existence of Car2 also cannot sense the blocking of the link between A→C.

To solve the above problems, the conventional method is to monitor the flow change at the gantry C. If there is a problem in the link between A→C, the flow at C will drop significantly. The inventor realizes that the premise of this method is that the flow rate is stable, and the flow coupling relationship between the masts during vehicle running is ignored. For example, if vehicles starting from A all drive past B at a certain moment, it is normal for the flow of gantry C to decrease; make the problem more complicated. In fact, the toll road network is a network topology, and the coupling between the upstream and downstream gantry will make the monitoring method based on traffic changes extremely challenging, but it also provides certain convenience for locating link problems.

The method for monitoring highway road conditions based on toll data according to the embodiment of the present application, based on massive highway toll data, uses the flow coupling between different gantry to find out the problems existing in the link between the upstream and downstream gantry, and in the mesoscopic view The scale further locates the space of the link problem and provides data support for the operation and monitoring of the expressway network.

In the embodiment of the present application, charging data is introduced, and the charging data of the traveling vehicle can be used to directly know whether the traveling vehicle passes through each downstream gantry smoothly (for example, the downstream gantry B, or the downstream gantry C as shown in FIG. 2 ) ), or smoothly pass through the intersection between the paths (for example, as shown in FIG. 2 , the intersection g between the path DC and the path AC). Charge data is different from mobile location data, which is essentially mobile data, whereas charge data is a fixed-point data.

As shown in FIG. 3 , it is a schematic diagram of a macro topology map and a meso topology map in a road network topology map for expressway toll collection constructed under a specific application scenario provided by an embodiment of the present application.

In order to facilitate the description of the flow coupling relationship between different gantry, the method for monitoring highway road conditions based on massive toll data in the embodiment of the present application first abstracts the macro-level and meso-level two-layer topology relationships of the highway toll road network, as shown in Figure 3 shown. The macro-topological relationship refers to the upstream and downstream topological relationship between the gantry, and the meso-topological relationship is based on the macro-topological relationship, and important sub-confluence points are inserted to express the influence of the sub-confluence on the flow coupling. The monitoring method provided by the embodiment of the present application predicts possible problems on the meso-topology link by defining the traffic coupling relationship between the gantry of the macro-topology layer. In the example shown in FIG. 2 , the monitoring method provided by the embodiment of the present application can detect that there is a problem in the link between e→g at the mesoscale based on the charging data, although it cannot locate the problem at the microscale. f, this is caused by the limitation of macro data such as toll data, but at least it can be accurately determined that the road section between e→g as shown in Figure 2 and Figure 3 is congested, which makes the monitored vehicle unable to smoothly The above-mentioned point g shown in FIGS. 2 and 3 is reached.

In the embodiment of the present application, the above-mentioned charging data is recorded in the following manner, and the details are as follows:

The toll data record is a data record associated with the vehicle and the gantry generated by ETC equipment or video recognition when the vehicle passes through the high-speed toll gantry, which is expressed by the following five-tuple:

CR=<Pid,Cid,Ctype,t>, where CR is a charging record, Pid is the unique identifier of the gantry, Cid is the unique identifier of the vehicle, and Ctype records the type of the vehicle, which is obtained by calling the registration information of the vehicle in the background. , or based on image recognition; t is the time when the vehicle passes through the gantry.

It should be noted that the monitoring method provided in the embodiment of the present application is also applicable to other application scenarios of road network operation monitoring based on fixed-point data, and details are not described herein again.

In the embodiment of the present application, the road network topology map includes a macro topology map used to represent the upstream and downstream relationships between the various gantry on each path and a meso topology map used to represent the travel path segments of each traveling vehicle, The meso-topological map has the identified intersections between the paths; constructing the road network topology map for high-speed charging according to the path information includes the following steps:

A macro-topology map for expressway toll collection is constructed according to the path information, and a meso-topology map for expressway toll collection is constructed according to the path information.

Specifically, constructing a macro topology map for expressway toll collection according to the path information includes the following steps:

Acquiring each path information corresponding to each traveling vehicle, each path information includes the gantry information set on each path and the upstream and downstream relationship information between each gantry set on each path;

According to the information of the gantry set on each path and the upstream and downstream relationship information between the gantry set on each path, a macro topology map that can be used for expressway toll collection is constructed. It can be understood that the macro topology map is not limited to For highway tolls.

Specifically, constructing a mesotopological map for expressway toll collection according to the path information includes the following steps:

Obtain each path information corresponding to each traveling vehicle, and each path information also includes the intersection between each path;

A meso-topological map for highway tolling is constructed based on the macro-topological map and the intersections between individual paths.

In a specific application scenario, the method steps for constructing a road network topology map for expressway toll collection are as follows:

Step a1: Mark the gantry on the expressway electronic map G, and obtain a two-tuple pl=<Pid, linkid> composed of each gantry and its link, and the set of pl is denoted as Ω.

Step a2: For any pl ∈ Ω, take the link where the gantry pl is located as the starting point, perform depth-first traversal on the electronic map G, and obtain all the downstream gantry sets Φ pl of the gantry _pl (with

). Might as well set one of the downstream gantry _pl′∈Φpl , then their macro-topological relationship is recorded as

topo _macro (pl,pl')=<rela(pl,pl'),path(pl,pl'),dis(pl,pl'),t(pl,pl')>.

Among them, rela(pl,pl') uniquely identifies the upstream and downstream relationship between the gantry pl.Pid and pl'.Pid;

path(pl,pl')=pl.linkid→...→pl'.linkid gives the path between gantry pl.Pid and pl'.Pid;

dis(pl,pl') gives the length of the path path(pl,pl');

t(pl,pl') gives the time required for the path path(pl,pl') to travel at an estimated normal speed (eg 80km/h).

After the above operations, a macro map G _macro is constructed with the gantry pl and pl' as the nodes and the macro topological relation topo _macro (pl, pl') as the edges.

Step a3: Mark the upstream and downstream relationship rela(pl,pl') of the gantry to all the sections of the electronic map G that path(pl,pl') passes through. Taking Figure 2 as an example, all links on the path A→B will be Mark rela(pl _A ,pl _B ), all links on A→C path will be marked rela(pl _A ,pl _C ), all links on D→C path will be marked rela(pl _D ,pl _C );

Step a4: Perform topological clustering on all links marked with the same rela(,), and use the clustered path segments as elements of the meso-topology of the toll road network. Still taking Figure 2 as an example, all links on the path segment A→e are marked as rela(pl _A , pl _B ) and rela(pl _A , pl _C ); all links on the e→B path are marked as rela ( pl _A , pl _B ); all links on the e→g path are marked as rela(pl _A , pl _C ); all links on the g→C path are marked as rela(pl _A , pl _C ) and rela(pl _D , pl _C ); all links on the D→g path are marked as rela(pl _D ,pl _C ). After the above clustering operations, some important sub-confluence points (e, g in Figure 2) will be screened out to form a meso-scale map G _meco with the gantry and the sub-confluence points as nodes and path segments as edges. In G _meco , we use topo _meso (pl,pl') to record the set of path segments between the gantry gantry pl and pl'. For example, topo _meso (pl _A , pl _C )={A→e, e→g, g→C}, as shown in FIG. 3 .

In a possible implementation manner, the monitoring method provided by the embodiment of the present application further includes the following steps: constructing a flow coupling analysis unit based on the macro map G _macro .

As shown in FIG. 4 , it is a schematic diagram of a traffic coupling analysis unit in a specific application scenario provided by an embodiment of the present application.

In order to capture the flow coupling relationship between the upstream and downstream gantry, and between different downstream gantry of the same upstream gantry, the monitoring method provided by the embodiment of the present application defines a flow coupling analysis unit with the upstream gantry as the calculation core ,As shown in Figure 4.

In the macro map G _macro , for any gantry pl∈Ω, extract its downstream gantry set _Φpl to construct a flow coupling analysis unit. As shown in Figure 4, the upstream gantry pl is composed of a master communication module and a link monitoring module, and each downstream gantry pl' is composed of a slave communication module and a timing module. It can be seen from Fig. 4 that the flow coupling analysis unit is formed around the upstream gantry. Therefore, the upstream gantry pl can be used to uniquely identify a flow coupling analysis unit.

The working mechanism of the flow coupling analysis unit in Figure 4 is explained as follows:

1) For the upstream gantry pl, if there is a vehicle c1 passing through the gantry pl at the time t0 in the charging data record <pl.Pid, c1, Ctype, t0>, the main communication module will send each downstream gantry pl′. The slave communication module with ∈Φ _pl sends a message <c1,t0+t(pl,pl′)+Δt>, that is, notifies the downstream gantry pl′, which is expected to be sent before time t0+t(pl,pl′)+Δt There is a vehicle c1 passing through the gantry pl', please monitor it; t(pl, pl') is the normal time taken for the vehicle to pass through the gantry pl and pl', and Δt is a time-consuming tolerance;

2) in the link monitoring module of the upstream gantry pl, add c1 to the monitoring task set of each downstream gantry link topo _macro (pl, pl');

3) For any downstream gantry _pl′∈Φpl , when it receives the information <c1,t0+t(pl,pl′)+Δt> sent by the main communication module from the communication module, establish the tracking of the vehicle c1 Task, if it is detected that the vehicle c1 has passed the gantry pl' before the time t0+t(pl,pl')+Δt, it will reply to the main communication module and inform the link monitoring module of pl to monitor the vehicle c1 normally; otherwise, reply Vehicle c1 is not detected;

4) If the link monitoring module of pl receives the message that the vehicle c1 is successfully monitored by the gantry pl', it will set the link of topo _macro (pl,pl') as valid; Remove it from the monitoring task set of the gantry pl″ (pl″∈Φpl and _pl ″≠pl′); if it receives the message that the monitoring of the vehicle c1 failed to be replied by the gantry pl′, the topo _macro (pl,pl′ ) The task of the vehicle c1 in the monitoring task set is set to fail;

5) The link monitoring module of pl regularly counts the number of failed tasks in each downstream gantry link topo _macro (pl, pl') monitoring task set n(pl, pl') = topo _macro (pl, pl') Number and proportion of failed vehicle monitoring tasks

If n(pl,pl') or δ(pl,pl') exceeds a certain threshold, the output link topo _macro (pl,pl') fails, and the probability of failure is δ(pl,pl').

By constructing the above flow coupling unit, especially the link monitoring module established around the upstream gantry, the data exchange and flow coupling analysis between the upstream and downstream gantry and different downstream gantry of the same upstream gantry can be well realized. The theoretical delay of detection is t(pl,pl′)+Δt, which effectively solves the problem of large detection delay or even ineffective detection of traditional solutions when the link fails, as well as the problem of flow-based detection accuracy.

Further, in the case of link blockage, if the downstream gantry pl' finally detects the vehicle c1 at time t2, then t2-t0 is the time consuming of the link topo _macro (pl,pl'), which can be used as a link. The analysis of the driving cost will not be repeated here.

As shown in FIG. 5 , it is a schematic diagram of a meso link monitoring module in a specific application scenario provided by an embodiment of the present application.

Through the traffic coupling analysis unit constructed based on the macro map G _macro , the validity of each macro link topo _macro (pl, pl') can be obtained. The qualitative relationship between the effectiveness of macro links in G _macro and the effectiveness of path segments in G _meco is that when the macro link is valid, it can be inferred that all corresponding path segments are valid, and if the macro link fails, each path segment is valid. All path segments may fail; its quantitative relationship is that when certain macroscopic link validity conditions are met, the conditional probability of path segment failure is calculated, and the specific probability of the failed path segment is estimated as p(path segment failure). |{topo _macro (pl,pl')validity judgment}).

In a possible implementation manner, the monitoring method provided in the embodiment of the present application further includes the following steps:

The mesoscopic link monitoring module is constructed based on the mesoscopic map G _meco .

In a specific application scenario, the method steps for constructing a meso link monitoring module based on the meso map G _meco are as follows:

Step b1: Establish an inference relationship between the validity of the path segment in the G _meco and the validity of the macro link in the G _macro .

As shown in FIG. 6 , it is a schematic diagram of the inference relationship between path segment validity and macro link validity under a specific application scenario provided by an embodiment of the present application. When a path segment validity assumption is given, the macro Link validity relationship. As shown in Figure 3, a total of 5 path segments are defined, namely A→e, e→B, e→g, g→C and D→g; and 3 macro links are defined, respectively are A→B, A→C, and D→C.

According to the validity condition setting of the path segment, the validity conclusion of the corresponding macro link can be deduced. Assuming that there are 5 path segments, and each path segment is valid or invalid, ²⁵ validity condition settings can be defined, and there are ²³ corresponding macro link validity result spaces. However, on the premise that the validity of some macro links is known, the space for setting the conditions and the corresponding result space for the validity of the macro links can be compressed. For example, if the macro link A→B is known to be valid, the validity of the path segments A→e and e→B can be determined, as shown in Figure 6, thereby compressing the validity condition space of the path segments to 2 ³ , which are respectively identified by μ ₁ , μ ₂ ... μ ₈ , and the corresponding macro link validity result space is compressed to ²² .

Step b2: Infer the probability of failure of each path segment under the given macro link validity determination result.

In the embodiments of the present application, in order to facilitate investigation and disposal, the monitoring method provided in the embodiments of the present application further includes the following steps:

Given the results of the macro link validity determination, based on the meso link monitoring model, establish the inferred relationship between the effectiveness of the path segment in the meso topology map and the macro link effectiveness in the macro topology map, and based on the inference The relationship inversely deduces the priority order of each path segment failure in the meso-topology diagram for troubleshooting and disposal.

Specifically, given the macro link validity judgment result, based on the meso link monitoring algorithm, the inference relationship between the topological path segmentation validity in G _meco and the macro link validity in G _macro is established, and based on The above inferred relationship inversely deduces the priority order of each topology path segment failure in the meso-topological graph G _meco , so as to facilitate investigation and disposal.

It should be noted that the meso-link monitoring model is a model established based on the meso-link monitoring algorithm, and the adopted method for constructing the model is a conventional method, which will not be repeated here. Assuming a given path segment tps, the macro link validity judgment condition is Ψ, then the conditional probability of tps failure is defined as:

Among them, k is the space capacity of the path segment validity condition; μ _k uniquely identifies a path segment validity condition; p(μ _k ) is the probability of the path segment validity condition μ _k appearing, set each path segment The probability of failure is τ(τ<0.5), then p(μ _k )=τ ^a ×(1-τ) ^b , where a is the number of tps=0 in μ _k , and b is tps=1 in μ _k The number of , in an embodiment of the present application, set τ=0.2.

f ₁ (tps, μ _k ) gives the judgment of whether the path segment tps fails in the path segment validity condition μ _k , which is defined as follows:

σ _k is the macro link validity identifier corresponding to the path segment validity condition μ _k , and f ₂ (σ _k ,Ψ) gives the judgment of whether σ _k is consistent with the macro link validity condition Ψ, which is defined as follows:

Based on the above formula, as shown in Figure 2, when topo _macro (pl _A , pl _B ) is valid, topo _macro (pl _D , pl _C ) is valid and topo _macro (pl _A , pl _C ) is invalid,

There are: p(e→g=0|(A→C=0, D→C=1))=p(e→g=0|μ ₄ )=p(μ ₄ )=0.8×0.2×0.2=0.032 ;

Similarly there are:

p(g→C=0|(A→C=0, D→C=1))=0,

p(D→g=0|(A→C=0, D→C=1))=0.

After normalization, p(e→g=0|(A→C=0, D→C=1))=1, that is, the problem occurs on the path segment e→g with probability 1. It is understandable, The probability of failure of path segment e→g is 1;.

As another example,

When topo _macro (pl _A ,pl _B ) is valid, topo _macro (pl _D ,pl _C ) and topo _macro (pl _A ,pl _C ) are invalid, there are:

p(e→g=0|(A→C=0, D→C=0))=p(μ ₁ )+p(μ ₂ )+p(μ ₃ )=0.072; p(g→C=0 |(A→C=0, D→C=0))=p(μ ₁ )+p(μ ₂ )+p(μ ₅ )+p(μ ₆ )=0.2; p(D→g=0| (A→C=0, D→C=0))=p(μ ₁ )+p(μ ₂ )+p(μ ₅ )+p(μ ₆ )=0.072.

After normalization,

p(g→C=0|(A→C=0, D→C=0))=0.582,

p(e→g=0|(A→C=0, D→C=0))=0.209;

p(D→g=0|(A→C=0, D→C=0))=0.209.

It means that the problem occurs on the path segment g→C with a probability of 0.582. Of course, the possibility of failure of D→g and e→g cannot be ruled out, but the probability is low. It is understandable that the path segment e→ The probability of g failure is 0.582.

Based on the calculation of the above-mentioned meso-link monitoring module, the probability of failure of each path segment can be given, so as to help the management department to investigate and deal with the failure probability according to the size of the failure probability, and improve the efficiency of problem location and treatment.

In the embodiment of the present application, the method for monitoring highway road conditions based on toll data provided by the embodiment of the present application further includes the following steps:

In response to the specified user's viewing request for viewing the road network topology map, the road network topology map shown in the graphical form is pushed to the terminal device of the specified user; in this way, the specified user can intuitively see the diagram shown in Figure 2 and Figure 3. The road network topology map shown in the figure is easy to select the driving route in advance.

Obtain the preset distance between the estimated driving speed of the current driving vehicle and the target point on the target travel path. The target point includes the target downstream gantry point marked on the macro topology map and the target intersection point marked on the meso topology map .

In this embodiment of the present application, the target point may be the downstream gantry point B or the downstream gantry point C as shown in FIG. 2 and FIG. 3 , or the target point may also be the intersection as shown in FIG. 2 and FIG. 3 . e, or intersection g.

S102, estimating the preset distance between the current traveling speed of the vehicle and the target point on the target travel path, where the target point includes the target downstream gantry point marked on the macro topology map and the target intersection marked on the meso topology map .

In this step, for the detailed description of the macro-topology map and the meso-topology map, refer to the descriptions in the same or similar parts described above, which will not be repeated here.

S103, according to the estimated travel speed and preset distance of the current traveling vehicle, predict the duration required for the current traveling vehicle to travel the preset distance at the traveling speed; and the initial time point and duration determined based on the charging data of the current traveling vehicle , and predict the estimated time of arrival of the current vehicle traveling to the target point.

For the description of the charging data, refer to the description of the same or similar part in the foregoing S101, and details are not repeated here.

S104, determine whether the current traveling vehicle travels to the target point within the estimated time of arrival, and if it is determined that the current traveling vehicle travels to the target point within the estimated time of arrival, it is detected that the current traveling vehicle does not occur on the target travel path Congestion, otherwise, it is detected that the current driving vehicle is in the target travel path and the road section associated with at least one target point is congested.

In a possible implementation manner, monitoring that the current driving vehicle is in the target driving route and the road segment associated with at least one target point is congested includes the following steps:

If the target point is the target downstream gantry point, it is detected that the current traveling vehicle is within the target travel path and the road section associated with at least one gantry point downstream of the target is congested.

If the target point is the target intersection, it is detected that the currently traveling vehicle is within the target travel path and the road section associated with at least one target intersection is congested.

In the embodiment of the present application, according to the estimated travel speed and preset distance of the currently traveling vehicle, the time required for the current traveling vehicle to travel the preset distance at the estimated traveling speed is predicted; The charging data records the determined initial time point and duration, and predicts the estimated arrival time point of the currently traveling vehicle traveling to the target point; and judges whether the current traveling vehicle travels to the target point within the estimated arrival time point, and The vehicle travels to the target point within the estimated arrival time point, and it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and is associated with at least one target point. The road is congested. In the embodiment of the present application, due to the introduction of the constructed road network topology map for expressway toll collection, it is not only possible to accurately detect whether the vehicle is congested on the target driving path, but also to detect whether the vehicle is congested on the target driving path. The road segment associated with which destination point is congested.

The following is the embodiment of the monitoring device of the highway road condition based on the toll data of the present application, which can be used to execute the embodiment of the monitoring method of the highway road condition based on the toll data of the present application. For details that are not disclosed in the embodiments of the monitoring device for expressway road conditions based on toll data in the present application, please refer to the embodiments of the method for monitoring expressway road conditions based on toll data in the present application.

Please refer to FIG. 7 , which shows a schematic structural diagram of an apparatus for monitoring highway road conditions based on toll data provided by an exemplary embodiment of the present application. The device for monitoring highway road conditions based on toll data is applied to a server, especially the cloud. The device for monitoring highway road conditions based on toll data includes a construction module 701 , an estimation module 702 , a prediction module 703 and a processing module 704 .

Specifically, the building module 701 is used to build a road network topology map for expressway toll collection, the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a map used for a meso-topological map identifying the path segments of the travel path of each traveling vehicle, the meso-topological map having intersections between the identified respective path segments;

Estimation module 702 is used for estimating the preset distance between the current traveling speed of the vehicle and the target point on the target travel path, and the target point includes the target downstream gantry point and The target intersection identified in the mesotopological map constructed by the building module 701;

The prediction module 703 is used to predict the time required for the current driving vehicle to travel the preset distance at the driving speed according to the driving speed and the preset distance of the current driving vehicle estimated by the estimation module 702; and the charging based on the current driving vehicle The initial time point and duration determined by the data can predict the estimated arrival time point of the current vehicle traveling to the target point;

The processing module 704 is used for judging whether the current traveling vehicle travels to the target point within the estimated arrival time point predicted by the prediction module 703, and if it is determined that the current traveling vehicle travels to the target point within the estimated arrival time point, monitoring The currently traveling vehicle is not congested on the target traveling path, otherwise, it is detected that the currently traveling vehicle is in the target traveling path and the road section associated with at least one target point is congested.

Optionally, the processing module 704 is used to:

Optionally, the road network topology map includes a macro topology map used to represent the upstream and downstream relationships between the various portals on each path and a meso topology map used to represent the travel path segments of each traveling vehicle. The graph has intersections between individual paths identified; building block 701 is used to:

Optionally, the device further includes:

The first acquisition module (not shown in FIG. 7 ) is used to acquire each path information corresponding to each traveling vehicle, and each path information includes the gantry information set on each path and the difference between each gantry set on each path. The upstream and downstream relationship information between them;

Building module 701, specifically for:

A macro topology map for expressway toll collection is constructed according to the information of the gantry provided on each path and the upstream and downstream relationship information between each gantry provided on each path acquired by the first acquisition module.

Optionally, the device further includes:

The second acquisition module (not shown in FIG. 7 ) is used to acquire each path information corresponding to each traveling vehicle, and each path information further includes the intersection between each path;

Building module 701, specifically for:

According to the macro topology map and the intersections between the paths acquired by the second acquisition module, a meso topology map for expressway toll collection is constructed.

Optionally, the processing module 704 is further configured to:

It should be noted that, when the device for monitoring highway road conditions based on toll data provided by the above embodiments executes the method for monitoring highway road conditions based on toll data, only the division of the above-mentioned functional modules is used for illustration. In practical applications, The above-mentioned function allocation can be completed by different function modules according to requirements, that is, the internal structure of the device is divided into different function modules, so as to complete all or part of the functions described above. In addition, the device for monitoring highway road conditions based on toll data provided by the above embodiments and the embodiment of the method for monitoring highway road conditions based on toll data belong to the same concept, and the implementation process of which is embodied in the method for monitoring highway road conditions based on toll data. Examples are not repeated here.

In the embodiment of the present application, the estimation module is configured to predict, according to the estimated traveling speed and preset distance of the currently traveling vehicle, the duration required for the currently traveling vehicle to travel the preset distance at the traveling speed; and based on the currently traveling vehicle The initial time point and duration determined by the charging data, predict the estimated arrival time point of the current driving vehicle traveling to the target point; the processing module is used to determine whether the current driving vehicle travels to the target point within the estimated arrival time point, and if it is determined If it is found that the current driving vehicle travels to the target point within the estimated arrival time point, it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and is connected with at least one The road segment associated with the point is congested. In the embodiment of the present application, due to the introduction of the constructed road network topology map for expressway toll collection, it is not only possible to accurately detect whether congestion occurs on the target driving path, but also to monitor the specific location within the target driving path, and where it is connected to. A road segment associated with a destination point is congested.

The present application also provides a computer-readable medium, wherein the computer-readable storage medium may be non-volatile or volatile, and program instructions are stored thereon, and when the program instructions are executed by a processor, each of the above methods is implemented Embodiments provide a method for monitoring highway road conditions based on toll data.

The present application also provides a computer program product containing instructions, which, when run on a computer, enables the computer to execute the method for monitoring highway road conditions based on toll data described in each of the above method embodiments.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and the program is During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, or a random storage memory, and the like.

The above disclosures are only the preferred embodiments of the present application, and of course, the scope of the rights of the present application cannot be limited by this. Therefore, equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

A method for monitoring highway road conditions based on toll data, wherein the method comprises:

A road network topology map for expressway toll collection is constructed, the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a driving path path used to identify each traveling vehicle A segmented mesotopological map having identified intersections between individual path segments;

Estimating the preset distance between the current driving speed of the vehicle and the target point on the target travel path, the target point includes the target downstream gantry point marked on the macro topology map and the target point marked on the meso topology map. the target intersection;

According to the estimated traveling speed of the currently traveling vehicle and the preset distance, the time required for the currently traveling vehicle to travel the preset distance at the traveling speed is predicted; and the initial value determined based on the charging data of the currently traveling vehicle the time point and the duration, and predict the estimated arrival time point of the currently traveling vehicle traveling to the target point;

Determine whether the current driving vehicle travels to the target point within the estimated arrival time point, and if it is determined that the current driving vehicle travels to the target point within the estimated arrival time point, it is detected that the current driving vehicle is at the target point. There is no congestion on the target travel path, otherwise, it is detected that the road segment that is currently traveling in the target travel path and is associated with the at least one target point is congested.
The method according to claim 1, wherein the monitoring that the current driving vehicle is within the target driving route and the road section associated with the at least one target point is congested comprises:

If the target point is the target downstream gantry point, it is detected that the current traveling vehicle is in the target travel path and the road section associated with at least one gantry point downstream of the target is congested.
The method according to claim 1, wherein the monitoring that the current driving vehicle is within the target driving route and the road section associated with the at least one target point is congested comprises:

If the target point is the target intersection, it is detected that the current driving vehicle is within the target travel path and the road section associated with the at least one target intersection is congested.
The method according to claim 1, wherein the road network topology map includes a macro topology map used to characterize the upstream and downstream relationships between the various gantry on each route and a travel path segment used to represent each traveling vehicle The meso-topological map of , the meso-topological map has the intersections between the identified paths; the construction of the road network topology map for high-speed charging according to the path information includes:

constructing the macro-topology map for expressway tolling based on the path information, and

The meso-topological map for expressway toll collection is constructed according to the path information.
The method of claim 4, wherein the constructing the macro topology map for expressway toll collection according to the path information comprises:

Acquiring each path information corresponding to each traveling vehicle, each path information includes the gantry information set on each path and the upstream and downstream relationship information between each gantry set on each path;

The macro topology map for expressway toll collection is constructed according to the information of the gantry arranged on each route and the upstream and downstream relationship information between the gantry arranged on each route.
The method of claim 4, wherein the constructing the meso-topological map for expressway tolling according to the path information comprises:

Obtain each path information corresponding to each traveling vehicle, and each path information also includes the intersection between each path;

The meso-topological map for expressway toll collection is constructed according to the macro-topological map and the intersections between the various paths.
The method of claim 1, wherein the method further comprises:

Given the macroscopic link validity judgment result, based on the mesoscopic link monitoring model, the inferred relationship between the path segment validity in the mesoscopic topology graph and the macroscopic link validity in the macroscopic topology graph is established. According to the above inference relationship, the priority order of each path segment failure in the meso-topology graph is inversely deduced, so as to be checked and dealt with.
A device for monitoring highway road conditions based on toll data, wherein the device comprises:

A building module for constructing a road network topology map for expressway tolling, the road network topology map including a macro topology map used to identify the upstream and downstream relationships between the various gantry on each path and a macro topology map used to identify each travel a meso-topological map of path segments of the vehicle's travel path, the meso-topological map having identified intersections between the individual path segments;

Estimation module, used for estimating the preset distance between the current driving vehicle speed and the target point on the target travel path, the target point includes the target downstream identified on the macro topology map constructed by the building module a gantry point and a target intersection identified in the mesotopographic map constructed by the building block;

A prediction module, configured to predict the time required for the current vehicle to travel the preset distance at the travel speed according to the travel speed of the current vehicle and the preset distance estimated by the prediction module; and Based on the initial time point and the duration determined by the charging data of the current driving vehicle, predict the estimated arrival time point when the currently driving vehicle travels to the target point;

The processing module is used to judge whether the current driving vehicle travels to the target point within the estimated arrival time point predicted by the prediction module, and if it is determined that the current driving vehicle travels to the target arrival time point within the estimated arrival time point. For the target point, it is detected that the current driving vehicle is not congested on the target driving path; otherwise, it is detected that the current driving vehicle is within the target driving path and is associated with the at least one target point. congestion.
A computer device includes a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, causes the processor to perform the following steps:

A road network topology map for expressway toll collection is constructed, the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a driving path path used to identify each traveling vehicle A segmented mesotopological map having identified intersections between individual path segments;

Estimating the preset distance between the current driving speed of the vehicle and the target point on the target travel path, the target point includes the target downstream gantry point marked on the macro topology map and the target point marked on the meso topology map. the target intersection;

According to the estimated traveling speed of the currently traveling vehicle and the preset distance, the time required for the currently traveling vehicle to travel the preset distance at the traveling speed is predicted; and the initial value determined based on the charging data of the currently traveling vehicle the time point and the duration, and predict the estimated arrival time point of the currently traveling vehicle traveling to the target point;

Determine whether the current driving vehicle travels to the target point within the estimated arrival time point, and if it is determined that the current driving vehicle travels to the target point within the estimated arrival time point, it is detected that the current driving vehicle is at the target point. There is no congestion on the target travel path, otherwise, it is detected that the road segment that is currently traveling in the target travel path and is associated with the at least one target point is congested.
The computer device according to claim 9, wherein, when the processor performs the monitoring that the current driving vehicle is within the target driving route and the road section associated with the at least one target point is congested, the process specifically includes:

If the target point is the target downstream gantry point, it is detected that the current traveling vehicle is in the target travel path and the road section associated with at least one gantry point downstream of the target is congested.
The computer device according to claim 9, wherein, when the processor performs the monitoring that the current driving vehicle is within the target driving route and the road section associated with the at least one target point is congested, the process specifically includes:

If the target point is the target intersection, it is detected that the current driving vehicle is within the target travel path and the road section associated with the at least one target intersection is congested.
The computer device according to claim 9, wherein the road network topology map includes a macro-topology map used to characterize the upstream and downstream relationships between the various gantry on each route and a travel path distribution map used to represent each traveling vehicle. The middle-level topology map of the segment, the meso-level topology map has intersections between the identified paths; when the processor executes the construction of the road network topology map for high-speed charging according to the path information, the specific include:

constructing the macro-topology map for expressway tolling based on the path information, and

The meso-topological map for expressway toll collection is constructed according to the path information.
The computer device according to claim 12, wherein, when the processor executes the construction of the macro topology map for expressway tolling according to the path information, it specifically includes:

Acquiring each path information corresponding to each traveling vehicle, each path information includes the gantry information set on each path and the upstream and downstream relationship information between each gantry set on each path;

The macro topology map for expressway toll collection is constructed according to the information of the gantry arranged on each route and the upstream and downstream relationship information between the gantry arranged on each route.
The computer device according to claim 12, wherein, when the processor executes the construction of the macro topology map for expressway tolling according to the path information, it specifically includes:

Obtain each path information corresponding to each driving vehicle, and each path information also includes the intersection between each path;

The meso-topological map for expressway toll collection is constructed according to the macro-topological map and the intersections between the various paths.
A storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps:

A road network topology map for expressway toll collection is constructed, the road network topology map includes a macro topology map used to identify the upstream and downstream relationships between each gantry on each path and a driving path path used to identify each traveling vehicle A segmented mesotopological map having identified intersections between individual path segments;

Estimating the preset distance between the current driving speed of the vehicle and the target point on the target travel path, the target point includes the target downstream gantry point marked on the macro topology map and the target point marked on the meso topology map. the target intersection;

According to the estimated traveling speed of the currently traveling vehicle and the preset distance, the time required for the currently traveling vehicle to travel the preset distance at the traveling speed is predicted; and the initial value determined based on the charging data of the currently traveling vehicle the time point and the duration, and predict the estimated arrival time point of the currently traveling vehicle traveling to the target point;

Determine whether the current driving vehicle travels to the target point within the estimated arrival time point, and if it is determined that the current driving vehicle travels to the target point within the estimated arrival time point, it is detected that the current driving vehicle is at the target point. There is no congestion on the target travel path, otherwise, it is detected that the road segment that is currently traveling in the target travel path and is associated with the at least one target point is congested.
The storage medium storing computer-readable instructions according to claim 15, wherein the computer-readable instructions are executed by one or more processors to cause the one or more processors to execute the monitoring that the current driving vehicle is in When congestion occurs on the road section within the target driving route and associated with the at least one target point, the specific method includes:

If the target point is the target downstream gantry point, it is detected that the current traveling vehicle is in the target travel path and the road section associated with at least one gantry point downstream of the target is congested.
The storage medium storing computer-readable instructions according to claim 15, wherein the computer-readable instructions are executed by one or more processors to cause the one or more processors to execute the monitoring that the current driving vehicle is in When congestion occurs on the road section within the target driving route and associated with the at least one target point, the specific method includes:

If the target point is the target intersection, it is detected that the current driving vehicle is within the target travel path and the road section associated with the at least one target intersection is congested.
The storage medium storing computer-readable instructions according to claim 15, wherein the road network topology map comprises a macro-topology map for representing upstream and downstream relationships between various gantry on each path and a macro-topology map for representing A mid-level topology map of the travel path segments of each traveling vehicle, the meso topology map having identified intersections between the various paths; the computer-readable instructions are executed by one or more processors to cause one or more When the multiple processors execute the construction of the road network topology map for high-speed charging according to the path information, the process specifically includes:

constructing the macro-topology map for expressway tolling based on the path information, and

The meso-topological map for expressway toll collection is constructed according to the path information.
The storage medium storing computer-readable instructions according to claim 18, wherein the computer-readable instructions are executed by one or more processors to cause the one or more processors to execute the constructing according to the path information When used for the macro topology map of expressway toll collection, it specifically includes:

Acquiring each path information corresponding to each traveling vehicle, each path information includes the gantry information set on each path and the upstream and downstream relationship information between each gantry set on each path;

The macro topology map for expressway toll collection is constructed according to the information of the gantry arranged on each route and the upstream and downstream relationship information between the gantry arranged on each route.
The storage medium storing computer-readable instructions according to claim 18, wherein the computer-readable instructions are executed by one or more processors to cause the one or more processors to execute the constructing according to the path information When used for the macro topology map of expressway toll collection, it specifically includes:

Obtain each path information corresponding to each traveling vehicle, and each path information also includes the intersection between each path;

The meso-topological map for expressway toll collection is constructed according to the macro-topological map and the intersections between the various paths.