CN117095539A

CN117095539A - Traffic jam processing method, processing system, data processing device and storage medium

Info

Publication number: CN117095539A
Application number: CN202311335113.2A
Authority: CN
Inventors: 张国林; 曾伟; 郭武
Original assignee: Jiangxi Shili Puhua Digital Technology Co ltd
Current assignee: Jiangxi Shili Puhua Digital Technology Co ltd
Priority date: 2023-10-16
Filing date: 2023-10-16
Publication date: 2023-11-21
Anticipated expiration: 2043-10-16
Also published as: CN117095539B

Abstract

The embodiment of the specification provides a traffic congestion processing method, a processing system, a data processing device and a storage medium, wherein the traffic congestion processing method comprises the following steps: determining a plurality of subareas corresponding to the target area; determining the congestion state of each subarea; determining the congestion trend of any subarea according to the congestion state of any subarea in the plurality of subareas and the congestion state of other subareas; and generating an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of subareas. By adopting the technical scheme, the problem of traffic jam can be effectively solved.

Description

Traffic jam processing method, processing system, data processing device and storage medium

Technical Field

The embodiment of the specification relates to the technical field of data processing, in particular to a traffic jam processing method, a processing system, a data processing device and a storage medium.

Background

With the rapid development of cities and the rapid increase of the quantity of automobile conservation, the problem of traffic jam is increasingly serious. Conventional traffic management methods have difficulty in coping with sudden traffic flow changes, and thus intelligent traffic systems have been developed.

The current intelligent traffic system is mainly based on fixed video cameras, vehicle-mounted sensors and navigation systems to collect data of a specific area, and then the data are analyzed and decided through a central control system.

However, the existing scheme has delay in data transmission, data processing and decision speed, and real-time response is difficult to achieve, so that the problem of traffic jam cannot be effectively solved. In this context, how to solve the traffic congestion problem remains to be solved by the person skilled in the art.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide a traffic congestion processing method, processing system, data processing apparatus, and storage medium, which can effectively solve the traffic congestion problem.

First, an embodiment of the present specification provides a traffic congestion processing method, including:

determining a plurality of subareas corresponding to the target area;

determining the congestion state of each subarea;

determining the congestion trend of any subarea according to the congestion state of any subarea in the plurality of subareas and the congestion state of other subareas;

and generating an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of subareas.

Correspondingly, the embodiment of the specification also provides a traffic jam processing system, which comprises:

A first determining unit adapted to determine a plurality of sub-areas corresponding to the target area;

a second determining unit adapted to determine a congestion status of each sub-area;

a third determining unit adapted to determine a congestion tendency of any one sub-area according to the congestion state of any one sub-area among the plurality of sub-areas and the congestion state of other sub-areas;

and the generation unit is suitable for generating an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of subareas.

The present description also provides a computer-readable storage medium having stored thereon computer instructions, which when executed perform the steps of the method of any of the previous embodiments.

By adopting the traffic congestion processing method provided by the embodiment of the specification, the accuracy of the obtained congestion state of each subarea can be improved by determining the plurality of subareas corresponding to the target area, and further, the congestion trend of any subarea can be determined according to the congestion state of any subarea and the congestion state of other subareas, and the congestion trend of any subarea can represent the possibility of congestion of the target area, and the congestion state of the target area can be determined from the global angle by correlating the execution advice corresponding to the target area with the congestion trend of each subarea instead of only considering the congestion trend of one subarea.

Further, since boundary features of each position information data can represent junctions of different areas, a plurality of corresponding sub-areas can be obtained by dividing the target area, and each position information data at least comprises position information corresponding to the target area, and therefore, through the dividing process, the instantaneity and the completeness of each obtained sub-area can be improved.

Further, by means of fusion processing of the plurality of position information data, the format of each position information data can meet the preset format requirement, the difficulty of subsequent area division is reduced, and rich data information can be provided.

Further, by configuring the identification information of each sub-area, at least the number of each sub-area can be determined, and then the congestion state of the corresponding sub-area can be determined according to the number of each sub-area, so that the accuracy of the congestion state of each sub-area can be improved, and the congestion state of each sub-area can be managed conveniently.

Further, the congestion information of each subarea for representing congestion of the traffic road at least can comprise the total area of the road network of each subarea and the total traffic flow of each subarea, and the total area of the road network and the total traffic flow of each subarea can truly reflect the actual traffic state, so that the authenticity and the accuracy of the congestion state of the corresponding subarea can be improved according to the congestion information of each subarea.

Further, according to the total traffic flow and the total area of the road network corresponding to each subarea, the traffic flow corresponding to the unit area of each subarea can be determined, and then the congestion state of each subarea can be divided through a preset flow threshold value, so that the actual congestion degree of the subarea can be determined, and corresponding measures are conveniently provided for traffic guidance and management.

Further, when any one of the sub-areas is determined to be in a congestion state, by acquiring traffic flow data of the any one of the sub-areas and sub-areas adjacent to the any one of the sub-areas, a congestion diffusion trend of the any one of the sub-areas and a congestion diffusion trend of the sub-areas adjacent to the any one of the sub-areas can be determined, and further, a preset prediction model is adopted, so that the congestion trend of any one of the sub-areas can be automatically determined, manual processing is not needed, and the determination efficiency and the accuracy of the calculated congestion trend of any one of the sub-areas can be improved.

Further, according to the predefined objective function and constraint conditions, the congestion tendency of any one sub-area can be corrected, so that the accuracy of the congestion tendency of each obtained sub-area can be further improved.

Further, according to the congestion trend of each subarea, a control instruction can be output to traffic control equipment of the subarea where the traffic control instruction is located, so that traffic congestion can be reduced to the maximum extent, and the road use efficiency is improved.

Further, before the control instruction is output to the traffic control equipment in the subarea, by checking the feasibility of the control instruction, the control instruction can be ensured not to violate traffic rules or cause potential safety hazards when being executed, and the instantaneity, safety and stability of traffic running can be further improved.

Further, according to the congestion tendency of the plurality of subareas, a driving suggestion can be provided for a driver, so that the driver can select the best or optimal driving path, and the possibility of congestion of the target area is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a traffic congestion processing method in the embodiment of the present disclosure;

FIG. 2 is a flowchart of a method for determining a plurality of sub-regions corresponding to a target region according to an embodiment of the present disclosure;

fig. 3 is a flow chart of a method for determining congestion status of a sub-area in an embodiment of the present description;

fig. 4 is a flowchart of a method for obtaining congestion information of each sub-area in the embodiment of the present disclosure;

FIG. 5 is a flow chart of a method of determining congestion status of a sub-area in an embodiment of the present disclosure;

FIG. 6 is a flow chart of a method of determining congestion tendency of any sub-area in an embodiment of the present disclosure;

FIG. 7 is a flowchart of a method for obtaining a predictive model in an embodiment of the present disclosure;

FIG. 8 is a flow chart of a method of providing travel advice to a driver in an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of a traffic congestion handling system in the embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure.

Detailed Description

As described in the background art, the current intelligent traffic system has delay in data transmission, data processing and decision speed, and real-time response is difficult to achieve, so that the problem of traffic jam cannot be effectively solved.

In order to solve the above technical problems, the embodiments of the present disclosure provide a traffic congestion processing scheme, by determining a plurality of sub-areas corresponding to a target area, the accuracy of the obtained congestion state of each sub-area can be improved, and further, the congestion tendency of any sub-area can be determined according to the congestion state of any sub-area in the plurality of sub-areas and the congestion state of other sub-areas, and because the congestion tendency of any sub-area can characterize the possibility of congestion of the target area, the congestion tendency of each sub-area is associated with the execution advice corresponding to the target area, instead of considering the congestion tendency of only one sub-area, the congestion state of the target area can be determined from a global angle, so that the generated execution advice corresponding to the target area is more reasonable according to the congestion tendency of the plurality of sub-areas, and thus, the traffic congestion problem can be effectively solved.

For a better understanding and to be obtained by anyone skilled in the art to practice the embodiments of the present description, the following detailed description is of the concepts, solutions, principles and advantages of the embodiments of the present description, etc. with reference to the drawings, by way of specific examples of application.

First, the embodiments of the present disclosure provide a traffic congestion processing method, in some embodiments of the present disclosure, as shown in fig. 1, the following steps may be used to process a traffic congestion problem:

S11, determining a plurality of subareas corresponding to the target area.

In implementations, the target area may be any designated area. For example, the target area may refer to a global area of one city, i.e., the entire city; and can also be a local area of a city, such as a city center urban area, a high-new-yield garden area, a transportation junction area, a traffic accident frequent area, and the like. The embodiment of the present disclosure does not limit the target area, and may specifically determine the target area according to traffic analysis requirements.

By dividing the target area, a plurality of corresponding sub-areas can be obtained. The sub-area may be an intersection, a junction or a specific length of road, and the embodiments of the present disclosure describe the type of sub-area, so long as it can represent an actual traffic road.

S12, determining the congestion state of each subarea.

Specifically, after the target area is divided into a plurality of subareas, congestion information of each subarea for representing congestion of a traffic road can be obtained respectively, and then the congestion state of each subarea is determined.

S13, determining the congestion trend of any sub-area according to the congestion state of any sub-area in the plurality of sub-areas and the congestion state of other sub-areas.

Specifically, since each sub-area is obtained by dividing the same target area, the problem of mutual influence exists in traffic congestion among different sub-areas, and then the congestion tendency of one of the two sub-areas can be determined according to the congestion state of at least two sub-areas.

In some embodiments of the present description, the congestion tendency may include at least: the congestion diffusion trend and the congestion diffusion direction, wherein the congestion diffusion trend refers to whether the congestion of the subareas is in a deepening trend or a weakening trend; the congestion spreading direction refers to whether the congestion situation spreads in the own sub-area (i.e. the congestion situation of the own sub-area becomes more serious) or spreads to other sub-areas (i.e. the congestion situation of the own sub-area is relieved).

And S14, generating an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of sub-areas.

Specifically, by adopting steps S11 to S13, the congestion tendency of each sub-area can be determined, the congestion tendency of each sub-area can represent the congestion situation of the target area, and then the execution advice corresponding to the target area can be generated according to the congestion tendency of the plurality of sub-areas.

By adopting the steps S11 to S14, the congestion tendency of any sub-region can represent the possibility of congestion of the target region, and the congestion state of the target region can be determined from the global angle by associating the execution advice corresponding to the target region with the congestion tendency of each sub-region instead of considering the congestion tendency of only one sub-region, so that the generated execution advice corresponding to the target region is more reasonable according to the congestion tendency of a plurality of sub-regions, thereby effectively solving the traffic congestion problem.

In order to enable those skilled in the art to better understand and implement the traffic congestion processing method in the embodiments of the present disclosure, the following detailed description is provided by way of specific examples and in connection with specific application scenarios.

In some embodiments of the present disclosure, referring to fig. 2, the plurality of sub-regions corresponding to the target region may be determined by:

s21, acquiring a plurality of pieces of position information data, wherein each piece of position information data at least comprises position information corresponding to the target area.

In some embodiments of the present description, the location information data may be acquired through a variety of paths.

For example, the position information data may be acquired through a path such as a satellite image, a topography, road data, or a road network map. The road network map is a traffic route map reflecting traffic conditions, and may be displayed, for example, on a railway, a highway, a large road, a inland course, a marine course, a space course, or the like.

It should be understood that the above manner of acquiring the position information data is merely illustrative, and for example, the position information data may be acquired by manual mapping, and the embodiment of the present disclosure does not limit the manner of acquiring the position information data.

In a specific implementation, the obtained position information data may at least include position information corresponding to the target area, and then the target area may be subsequently divided to obtain a plurality of sub-areas.

S22, dividing the target area according to boundary characteristics of each position information data to obtain a plurality of corresponding sub-areas.

Specifically, since the shape, the morphological feature, and the like of the target region included in the positional information data are often irregular, the target region can be divided according to the boundary features (for example, boundary lines, boundary points, and the like) of the target region, and a plurality of sub-regions can be obtained.

The boundary features of the position information data can represent the boundary of different areas, the target area is divided to obtain a plurality of corresponding subareas, and the position information data at least comprise the position information corresponding to the target area, so that the obtained real-time performance and integrity of the subareas can be improved through the dividing process.

As described above, considering that the plurality of pieces of position information data may be obtained from different paths, the determination manners of the respective pieces of position information data may be different, and thus, the respective pieces of position information data may have differences, so that the plurality of pieces of position information data need to be preprocessed so as to reduce the difficulty of dividing the subsequent area.

In some embodiments of the present description, reference is continued to fig. 2:

S23, fusion processing is carried out on the plurality of position information data so that the format of each position information data meets the preset format requirement.

Specifically, the same processing procedure is performed on the plurality of pieces of position information data, so that the fused pieces of position information data have the same or similar format, and the format of each piece of position information data meets the preset format requirement.

As an alternative example, by fusing a plurality of position information data, it is possible to ensure that each position information data is plotted on the same coordinate system, that is, each position information data is plotted with the same scale, thereby facilitating the division of the target area.

It can be understood that after the integration process is performed on the plurality of position information data, the integration process may be performed on each position information data to obtain complete map data.

By adopting the fusion processing process, the format of each position information data can meet the preset format requirement, the difficulty of subsequent region division can be reduced, and rich data information can be provided.

In a specific implementation, the target area often includes multiple road networks, and each road network (that is, a road system formed by a plurality of roads such as a main road, an auxiliary road, a branch road, and a branch road, which are interconnected and interwoven into a grid distribution) has a large area, so that when the target area is divided, a large number of sub-areas may be obtained. For ease of administration, reference is continued to fig. 2:

S24, configuring identification information of each sub-region, wherein the identification information at least comprises the serial numbers of the sub-regions.

Specifically, the multiple subareas obtained by dividing the target area are numbered, so that the subareas are in one-to-one correspondence with the numbers, the congestion state of the corresponding subareas can be determined according to the numbers of the subareas, the accuracy of the congestion state of the subareas can be improved, and the congestion state of the subareas is convenient to manage.

It will be appreciated that in the above embodiments, some steps do not have a certain sequence, and may be performed synchronously or sequentially without contradiction, and the sequence may be exchanged.

In a specific implementation, for the above steps S21 to S24, accurate spatial localization and target area division may be performed using a Geographic Information System (GIS).

Specifically, sampling devices (e.g., sensors, cameras, etc.) are deployed in the target area to collect critical data such as traffic, vehicle speed, incoming and outgoing traffic, etc., in real-time, and these data are transmitted to the data processing arrangement in real-time using a high-speed network to ensure the real-time and integrity of the data.

Among them, the geographic information system is a system for storing, retrieving, managing, displaying, and analyzing various location information data. It contains not only software, but also hardware, data and trained users. The geographic information system is capable of capturing, editing, analyzing, managing and presenting all types of geographic data related to a location.

In some embodiments of the present description, the steps of using the geographic information system for accurate spatial localization and target area division may include (which may be considered as one specific implementation example of steps S21 to S24):

a1 Data collection: the geographic information system is provided with location information data, which may be from satellite imagery, topography, road data, and the like.

A2 Data input: these location information data are imported into the geographic information system using specific GIS software, such as ArcGIS or QGIS.

A3 Data integration: the geographic data of different sources are fused and integrated, so that the geographic data are ensured to be on the same coordinate system.

A4 Spatial analysis: and analyzing the geographic data by using a GIS tool to determine the boundary and characteristics of the target area.

A5 Target area division: the target area is subdivided into a plurality of sub-areas based on factors such as traffic flow, road network design, etc., using drawing and editing functions in the GIS tool.

A6 Attribute assignment): each sub-region is assigned a unique identifier and other related attributes such as area, expected traffic volume, etc.

A7 Data output: data and sub-block maps in the geographic information system are exported to a desired format for use by other systems or users.

Compared with the traditional technology, the accurate space positioning and target area division by using the geographic information system have the advantages that:

high-precision positioning: the geographic information system can provide high-precision geographic positioning and ensure the accuracy and the continuity of each sub-block.

Flexibility: the user can easily modify or repartition the sub-regions as desired without having to completely restart.

Multi-source data fusion: the geographic information system can integrate data from various sources, such as satellite images, sensor data, topography, and the like, and provide rich image information for analysis.

Spatial analysis tool: the geographic information system provides a series of space analysis tools which can help users to know key information such as flow patterns, bottleneck areas and the like.

And (3) visualization: the geographic information system provides an intuitive graphical interface that enables a user to clearly see the distribution of the entire target area and sub-areas, thereby better understanding the pattern of traffic flow.

Automation and optimization: many tools built into geographic information systems support automated processes such as automatic partitioning, traffic simulation, etc., which not only saves time, but also ensures consistency and reliability of partitioning results.

It should be understood that the above manner of dividing the target area into a plurality of sub-areas by using the geographic information system is merely illustrative, and is for illustrating that the target area may be divided by using the geographic information system, and is not to be construed as limiting the present invention.

After determining the plurality of sub-areas of the target area, the congestion status of each sub-area may be determined separately.

As a specific example, referring to a flowchart of a method for determining congestion status of a sub-area in the embodiment of the present specification shown in fig. 3, as shown in fig. 3, in some embodiments of the present specification, the congestion status of a sub-area may be determined in the following manner:

s31, obtaining congestion information of each subarea for representing congestion of the traffic road.

The congestion information at least comprises the total area of the road network of each subarea and the total traffic flow of each subarea.

In some embodiments of the present disclosure, congestion information for each sub-area may be obtained in a variety of ways, for example, a traffic flow sensor or a camera may be used.

In some embodiments of the present disclosure, the sub-regions refer only to the size of the division granularity, and thus, the number of sub-regions and the area size of each sub-region may be determined according to the area size of the target region or other specific analysis requirements.

As a specific example, as shown in fig. 4, the congestion information of each sub-area may be acquired in the following manner:

s311, determining critical path points in each sub-area.

The critical path point may be a path point at which vehicle information can be detected in the sub-region.

In some embodiments of the present description, critical path points may refer to intersections, road entrances, and road exits, among others.

S312, acquiring actual traffic flow of the key path points of each sub-region in a preset period.

The preset time period may be set according to various factors.

As an alternative example, the setting may be made according to the period in which traffic is located. For example, the preset period may be smaller when traffic is in an early peak or late peak period; while in other traffic periods, the preset period may be larger.

As another alternative example, the setting may be made according to weather conditions. For example, in a period in which the weather condition is good, the preset period may be larger; and in a period where the weather condition is worse (e.g., rainy or snowy weather, slippery road, rainy or foggy weather), the preset period may be smaller.

It can be understood that the embodiment of the present specification does not limit the size of the preset period, as long as it can reflect the current traffic situation. For example, in some other embodiments, the size of the preset time period may also be determined according to whether the day is a holiday.

In some embodiments, the actual traffic flow of the critical path points of each sub-area within the preset period may be obtained by employing a device (e.g., a sensor or camera) with an acquisition function.

S313, determining the total traffic flow corresponding to each subarea according to the actual traffic flow of the key path point of each subarea in the preset period.

Specifically, each sub-area often includes a plurality of critical path points, and through step S312, the actual traffic flow corresponding to any one of the critical path points can be obtained, so that the total traffic flow corresponding to each sub-area can be determined according to the actual traffic flow corresponding to each critical path point.

For example, the sum of actual traffic flows of the critical path points of each subarea in a preset period is taken as the total traffic flow of the corresponding subarea.

S314, determining the total area of the road network corresponding to each sub-region according to the distribution position of the key path points.

Specifically, the key path points are distributed at different positions of the subareas, and then the total area of the road network corresponding to the subareas can be determined according to the distribution positions of the key path points.

It will be appreciated that the total area of the road network corresponding to each sub-region may also be determined in other ways. For example, when dividing the target area, the total area of the road network for each sub-area may be set, or each sub-area may have the same total area of the road network.

It should be noted that, in some embodiments of the present disclosure, the total area of the road network corresponding to the sub-area may refer to an area available for the vehicle to travel, and does not include areas of non-road portions such as buildings, greenbelts, and the like.

By adopting the mode, the key path points can be distributed at different positions of the subareas, so that the accuracy of obtaining the total traffic flow of each moral subarea and the total area of the road network can be improved, and the accuracy of the congestion state of each subarea can be improved.

S32, determining the congestion state of the corresponding subarea according to the congestion information of each subarea.

Specifically, because the congestion information can represent whether the traffic road is currently congested, when the congestion information of each subarea is acquired, the congestion state of the corresponding subarea can be determined.

As a specific example, as shown in fig. 5, the congestion status of a sub-area may be determined in the following manner:

s321, determining the traffic flow corresponding to the unit area of each subarea according to the total traffic flow and the total area of the road network corresponding to each subarea.

As an alternative example, the ratio of the total traffic flow corresponding to the subarea to the total area of the road network may be used as the traffic flow corresponding to the unit area of the subarea.

S322, determining the congestion degree of the corresponding subarea according to the traffic flow corresponding to the unit area of each subarea and a preset flow threshold.

Specifically, different traffic flows represent actual congestion states of the current traffic road, and the congestion states corresponding to the traffic flows can be divided through a preset flow threshold value, so that the actual congestion degree of the subareas is determined, and corresponding measures can be provided for traffic guidance and management.

In some embodiments, the congestion degree of the subareas may be determined according to the magnitude between the corresponding traffic flow of the unit area of each subarea and the preset flow threshold.

For example, when it is determined that the vehicle flow rate corresponding to the unit area of each sub-area is not greater than a preset first flow rate threshold, determining the congestion degree of the corresponding sub-area as the first congestion degree.

And when the traffic flow corresponding to the unit area of each subarea is determined to be larger than the first flow threshold value and not larger than the preset second flow threshold value, determining the congestion degree of the corresponding area as a second congestion degree.

And when the traffic flow corresponding to the unit area of each subarea is determined to be larger than the second flow threshold value and not larger than a preset third flow threshold value, determining the congestion degree of the corresponding area as a third congestion degree.

The first flow threshold, the second flow threshold, and the third flow threshold may be set according to actual requirements or acquired historical data, which is not limited in the embodiment of the present disclosure.

As an implementation example, if it is determined that the ratio of the total traffic flow in a sub-area to the total area of the road network exceeds 10 vehicles per square meter, it is marked as primary congestion (i.e., a first degree of congestion), which means that there are 10 vehicles on each square meter of road surface, and traffic begins to become congested.

If it is determined that the ratio of total traffic to total area of the road network in the sub-area exceeds 15 vehicles per square meter and the difference between the incoming traffic and the outgoing traffic exceeds 200 vehicles per hour, this is marked as moderate congestion (i.e. second congestion level), which means that traffic is very slow and there are more vehicles entering the area rather than leaving.

If the ratio of the total traffic flow in the subarea to the total area of the road network exceeds 20 vehicles/square meter, the subarea is marked as heavy congestion (namely, the third congestion degree), which can be used as a critical point to indicate that traffic is almost stopped, and emergency measures are needed for traffic guidance and management.

Therefore, by adopting the method for determining the congestion state of each subarea in the embodiment, because the congestion information of each subarea for representing that the traffic road is congested at least can comprise the total area of the road network of each subarea and the total traffic flow of each subarea, and the total area of the road network and the total traffic flow of each subarea can truly reflect the actual traffic state, the reality and the accuracy of the congestion state of the corresponding subarea can be improved according to the congestion information of each subarea.

As an alternative example, for the above steps S31 and S32, the following steps may be specifically included:

b1 Data collection). At key points of each sub-area, such as intersections, road entrances and exits, etc., traffic sensors or cameras are deployed to capture the number of vehicles passing.

B2 Data summary. And summarizing traffic flow data collected by all sensors or cameras in each subarea to obtain the total traffic flow in the subarea.

B3 A road network area is obtained. The actual road network area for each sub-block is determined using a GIS system or other data source.

Wherein it is ensured that only the area available for the vehicle to travel is calculated, excluding non-road parts such as buildings, greenbelts, etc.

B4 A) calculating the ratio. The formula is used: traffic flow/road area ratio = total traffic flow of sub-area/road area of sub-area. And obtaining the ratio of the traffic flow area to the road network area of each sub-area.

B5 Data storage and update. The calculated ratio is stored in a database or other related system and ensures that the data can be updated in real time to reflect the actual traffic conditions.

By adopting the above example, the congestion tendency of any sub-area can be determined according to the congestion information of each sub-area, and then the corresponding execution suggestion can be generated.

Referring to a flowchart of a method for determining congestion tendency of any sub-area in the embodiment of the present specification shown in fig. 6, in some embodiments of the present specification, as shown in fig. 6, the method may specifically include the following steps:

and S61, when any one sub-area is determined to be in a congestion state, acquiring traffic flow data of the any one sub-area and sub-areas adjacent to the any one sub-area.

Specifically, when it is determined that any one of the sub-regions is actually in the congestion state (when the congestion degree of the sub-region can be regarded as the third congestion degree), the traffic data of that sub-region, and the traffic data of other adjacent sub-regions can be acquired.

In some embodiments of the present description, the sub-regions where the adjacency exists may be determined in the following manner.

For example, the sub-regions having the adjacent relationship may be determined according to the numbers of the sub-regions; for another example, the geographical location distribution diagram of each divided sub-region may be acquired, and sub-regions having an adjacent relationship may be determined from the geographical location distribution diagram. The embodiment of the present specification does not limit any way to determine the sub-areas where the adjacent relationship exists.

In some implementations of the present description, the traffic data may include at least: the traffic density, the traffic speed and the road network density, wherein the traffic density can represent the number of vehicles in a unit road network area; the vehicle flow speed may represent a vehicle travel speed; road network density may refer to the size of a sub-region.

And S62, determining the congestion diffusion trend of any one sub-area and the congestion diffusion trend of the sub-area adjacent to the any one sub-area according to the traffic flow data.

Specifically, the traffic flow data may represent traffic congestion conditions of the current sub-area, so according to the traffic flow data, a congestion spreading trend of any one sub-area and a congestion spreading trend of a sub-area adjacent to the any one sub-area may be determined, where the congestion spreading trend may include whether congestion of the sub-area is in a deepening trend or a weakening trend.

As a specific example, the congestion propagation trend for a sub-area may be determined in the following manner:

c1 Data collection). Real-time traffic data for each sub-zone (including sub-zones marked as congested and sub-zones adjacent) is obtained from a database or real-time sensor system.

C2 Comparing the incoming/outgoing flows. For each sub-zone, the incoming and outgoing traffic flows are compared. If the incoming traffic is significantly greater than the outgoing traffic and continues to grow, this may mean that congestion is spreading.

C3 Analyzing the state between adjacent sub-areas. Other sub-areas adjacent to the sub-area marked as congested are observed. This further confirms the tendency of congestion to spread if the flow/road area ratio of adjacent sub-areas is also increasing.

C4 A congestion propagation trend for any sub-area is determined. Comprehensively considering the factors, determining whether the congestion has a diffusion trend and a possible diffusion direction.

When the congestion diffusion trend of any subarea is determined, the diffusion trend and direction of traffic congestion can be described and predicted according to a preset model.

S63, determining the congestion tendency of any sub-area by adopting a preset prediction model according to the congestion diffusion tendency of any sub-area and the congestion diffusion tendency of the sub-area adjacent to any sub-area.

Specifically, after determining the congestion propagation trend of any sub-area, a preset prediction model can be adopted to determine the congestion trend of any sub-area, and compared with a manual processing mode, the method can automatically determine the congestion trend of any sub-area, and improves the determination efficiency and the accuracy of the calculated congestion trend of any sub-area.

In some embodiments of the present disclosure, for step S63, the following steps may be specifically included:

s631, acquiring the traffic density, the traffic speed and the road network density of any one sub-area and the sub-area adjacent to the any one sub-area in the preset period.

S632, inputting the traffic flow density, the traffic flow speed and the road network density into the prediction model to obtain traffic prediction data.

S633, determining a traffic flow change trend of any sub-region according to the traffic prediction data, wherein the traffic flow change trend is used for representing a congestion trend.

Specifically, if the traffic prediction data is larger than the set traffic prediction data, it is indicated that the traffic flow of the sub-area is increasing, and that the possibility of occurrence of traffic congestion in the sub-area is high.

As an alternative example, the embodiments of the present specification provide an achievable method for determining sub-area congestion tendency, wherein the method may predict future traffic flow based on a model of the fluid dynamics principle, as follows:

d1 Collecting real-time traffic data, such as traffic density, speed, and flow, from a plurality of traffic monitoring points (e.g., cameras, sensors, etc.).

D2 Inputting real-time data into the predictive model described above, providing initial conditions for vehicle flow density and speed.

D3 Using predictive models for traffic flow predictions over a short period of time (e.g., the next 30 minutes or 1 hour, it will be appreciated that other times are possible, and the time provided in the present embodiments is merely an example).

D4 Analyzing which road segments may be congested, and the duration and severity of the congestion potential, based on the prediction.

In particular implementations, as shown in fig. 7, the predictive model in the above example may be obtained as follows:

s71, describing traffic flow data of each subarea based on a preset fluid equation.

In particular, the flow of vehicles can be considered as a fluid and the road as a pipe. The variation and distribution of the vehicle flow is described based on an equation of fluid dynamics (e.g., navier-Stokes equation).

And using fluid dynamics to describe the variation and distribution of traffic flow, traffic flow can be considered as a continuous medium and equations similar to fluid flow can be used to describe the variation, providing a powerful tool for traffic planning.

In some embodiments of the present description, the traffic data of each sub-region may be described as follows:

s711, an analog link area of each sub-area is established.

Specifically, the road segments or areas to be simulated are determined and converted into a two-dimensional or three-dimensional lattice system.

S712, the fluid equation is simplified into a form suitable for traffic flow.

As an example, the flow may be described using a shallow water equation, where the depth variable may represent the density of the vehicle and the flow rate may represent the average speed of the vehicle.

Shallow water equations (Shallow Water Equations, SWE) are a set of partial differential equations in fluid mechanics that describe the flow of fluids at a horizontal scale that is much larger than at a vertical scale, such as air flows in rivers, coastlines, and the atmosphere. The shallow water equation is a simplified version of the Navier-Stokes equation, assuming that the fluid is incompressible and the vertical velocity is negligible with a small value.

The one-dimensional form of the shallow water equation may be:

continuity equation

；

Momentum conservation equation:

；

wherein,hindicating the depth of the fluid;uindicating the average horizontal velocity of the fluid;grepresenting gravitational acceleration;trepresenting time;xrepresenting the spatial coordinates.

This is a one-dimensional version of the shallow water equation that can be extended to two-dimensional and three-dimensional situations. In addition, other parameters such as friction, coriolis force, wind stress, etc. can be added to these equations as needed for a particular application.

S713, defining an initial traffic density and a traffic speed of the simulated road segment area.

S714, simulating the change of the traffic flow data of each subarea in a preset time step by adopting a numerical solution mode.

For example, a finite difference method or a finite element method may be employed to solve the equation and simulate the variation of the vehicle flow at each time step.

Wherein, using numerical methods to simulate traffic flow, we can consider traffic flow as a conservation fluid dynamics problem. In general, traffic flow models may involve Partial Differential Equations (PDEs), such as the Lighthill-Whitham-Richards (LWR) model.

The following are detailed steps of how PDEs can be solved and simulated using finite difference or finite element methods:

finite difference method (Finite Difference Method, FDM)

1) Space and time meshing

The grid is defined in time and space. Setting deltaxAs a spatial step size sum deltatAs a step of time.

2) Determining a discrete equation

Converting the continuous PDEs into discrete differential equations. For example, the time derivative is approximated using forward differential and the spatial derivative is approximated using backward or center differential.

3) Initial and boundary conditions

At the time oftInitial conditions were set for all spatial points when=0.

And boundary conditions may be set according to model requirements, for example, known flows at the entrance and exit of the road.

4) Time stepping

At each time steptUsing differential equation sumst-ΔtThe value of the moment in time calculates the traffic density at moment in time t.

5) Iteration

Repeating step 4) for each time step until the desired simulation time is completed.

Finite element method (Finite Element Method, FEM)

1. Defining geometry and meshing

The road or network is divided into small elements (e.g. triangles or quadrilaterals).

2. Selecting basis functions

An appropriate basis function is selected to approximate the solution on each element.

3. Weakening equation

PDEs are multiplied by the test function and integrated over each element to give a so-called weak form.

4. Assembling stiffness matrix and load vector

A local stiffness matrix and a load vector are formed on each element using the basis function and the test function, and the local stiffness matrix and the load vector are assembled into a global stiffness matrix and load vector.

5. Applying initial and boundary conditions

Initial conditions and boundary conditions are set according to model requirements.

6. Solving algebraic equations

A linear or nonlinear solver is used to solve the resulting set of algebraic equations to arrive at a solution for the next time step or spatial point.

7. Iteration

The above steps are repeated for each time step or spatial point until the desired simulation time or area is completed.

By using the numerical methods, the change of the traffic flow at each time step or space point can be simulated, and the adjustment or prediction of the traffic strategy can be performed according to the change.

S72, establishing an equation for describing traffic flow according to traffic flow data and fluid mechanics principles of each subarea.

As a specific example, step S72 may include:

1) Defining traffic variables

Density of vehicleρIs defined as the ratio of the number of vehicles on a road to the length of the road, and the traffic flow rate is calculateduDefined as the average speed of the vehicle.

2) Establishing a continuity equation

；

3) Establishing a power equation

；

Wherein,pis traffic pressure and can be related to vehicle density, e.gp=ρ ² 。

S73, processing an equation for describing traffic flow by adopting a preset analysis method to obtain the prediction model.

For example, the above equation is solved using an appropriate numerical method (finite difference method, finite element method, etc.), resulting in a predicted traffic flow pattern, specifically including:

s731, the analog segment area of each sub-area is divided into a plurality of sub-segments, and the set point of each sub-segment is taken as a grid point.

S732, the equation describing the traffic flow is converted into algebraic equations at each grid point.

S733, inputting the initial traffic density and the traffic speed of each grid point into the algebraic equation to determine a discrete equation within the preset time step, wherein the discrete equation is the prediction model.

It will be appreciated that in implementations, the resulting solution may be presented at each time step, for example, graphically or tabulated to describe the change and distribution of traffic. And the model results can be validated using real-time data.

In some embodiments, model parameters may also be calibrated, if desired. For example, the prediction model parameters can be calibrated by comparing with actual traffic data, so that the accuracy of the prediction result is ensured.

In practice, other factors that may affect traffic congestion situations need to be considered in constructing the predictive model.

For example, in some embodiments of the present specification, at least one parameter of a traffic signal, a traffic accident, a road surface state may be taken as a boundary condition of each grid point, and the boundary condition may be brought into the algebraic equation.

Specifically, by using at least one parameter of a traffic signal, a traffic accident, and a road surface state as a boundary condition of each grid point, the prediction accuracy of the prediction model can be improved.

The specific application of the above parameters is described below:

at the entrance and exit of the simulation area, the traffic signal may be a time dependent boundary condition. For example, when the signal is red, the flow at the inlet is zero; when the traffic is green, the traffic is defined according to the actual situation and the signal duration.

Traffic accidents and road conditions can be seen as sources of disturbances in the simulated area, which can be simulated by adding negative speed or density driving forces to a particular grid or area.

It will be appreciated that other external factors may also need to be considered in calculating the algebraic equation. For example, road surface wetting, wind speed, vehicle type distribution, etc., may also be incorporated into the model, as an additional term to the fluid equation or by modifying model parameters.

In some embodiments of the present description, to more intuitively capture and express various attribute information of each sub-region and relationships with other adjacent sub-regions, the initial traffic density and traffic speed of each grid point may be described in a vector form.

For ease of understanding, the congestion status of each sub-region is represented in vector form by an example detailed description.

Assume that the target area is divided into 3 sub-areas, wherein:

the state of sub-region 1 is as follows: normal state (no congestion), inflow traffic of 100 vehicles/hour, outflow traffic of 80 vehicles/hour; sub-region 2 has a congestion spreading probability of 0.5 and has no congestion spreading trend with sub-region 3, then the state vector expression of sub-region 1 may be:

V ₁ =[0，100，80，0，0.5，0]

This vector description method allows the state of each sub-region to be quickly obtained and used conveniently in a computer model or algorithm for further analysis and prediction.

In a specific implementation, the traffic congestion processing method provided in the embodiment of the present disclosure may further correct the congestion tendency of any one of the sub-areas according to a predefined objective function and constraint conditions, so that the accuracy of the obtained congestion tendency of each sub-area may be further improved.

As a specific example, an optimization algorithm may be constructed from the mathematical model described above using operational principles and optimization theory. The goal of the algorithm is to adjust the inflow and outflow traffic of each sub-block based on real-time data to minimize or avoid the spread of traffic congestion.

Among other things, operational research and optimization theory provides us with a series of tools and methods for finding optimal solutions.

To construct an optimization algorithm, we need to define the objective function and constraints. In this context, the objective function may be to minimize the degree of congestion diffusion, while the constraints may include traffic rules, road capacity, etc.

The following is a step of how to construct an optimization algorithm:

e1, define an objective function

The objective function describes the objective that we want to optimize, for example, we choose the objective function to be:

；

wherein a is _i Representing sub-regions _i Is used for the weight of the (c),f _in,i andf _out,i representing sub-regions respectivelyiIs provided for the inflow and outflow of traffic.

E2, define constraint conditions

Wherein the constraint conditions may include: traffic volume does not exceed road capacity, traffic regulations (e.g., traffic light conditions), and ensuring that the inflowing and outflowing traffic flows are balanced.

E3, selecting an optimization method

Depending on the nature of the problem, a suitable optimization method is chosen. For non-linear, integer or mixed integer problems, methods such as branch-and-bound, genetic algorithms, or simulated annealing may be required.

E4, implement algorithm

The problem is solved using the selected optimization method. This typically requires the writing of a computer program or the use of existing optimization tools.

Taking Branch and Bound as an example, this method is a common method for solving a combinatorial optimization problem, and is particularly suitable for integer linear programming.

The following is a simplified step of solving the problem using the branch-and-bound method:

e41, initialization of

A best solution found at present (which may be an estimate or a solution obtained from other methods) is set and an empty list of sub-questions to be processed is created.

E42, define

For the current problem or sub-problem, the integer requirement is ignored, and a lower bound (for minimizing the problem) or an upper bound (for maximizing the problem) is obtained using a linear programming method or other suitable method.

In some embodiments, if this limit is worse than the current best solution, the current sub-problem is discarded; otherwise, continuing the next step.

E43 branch of

A variable is selected for branching. For example, for integer linear programming problems, a variable is typically selected for which the current solution is not an integer.

A new child question is generated and added to the list to be processed, where the child question may include an upper rounding of the variable and a lower rounding of the variable.

E44, selection and repetition

At least one sub-problem is selected from the list of sub-problems to be processed for processing (e.g., based on best estimate selection), and the defining and branching steps are repeated for this sub-problem, updating the current best solution if a better solution can be found.

E45 terminate

When the to-be-processed sub-problem list is empty, the algorithm is terminated, and the optimal solution at the moment is taken as the optimal solution.

E5 verification of solution

Verifying whether the obtained solution meets all constraint conditions, and checking the quality or superiority of the solution, wherein the method specifically comprises the following steps:

E51, meet constraint conditions

Each constraint is checked to ensure that the resulting solution satisfies all constraints.

If a constraint is found not satisfied, this may indicate that there is an error in the solution process.

E52 quality inspection of solutions

Other methods or heuristics may be used to verify the superiority of the resulting solution.

For branch-and-bound methods, since it is a method that ensures that a globally optimal solution is found (although it may be very time consuming), it is often possible to rely on the results to be optimal.

In particular implementations, to enhance confidence, results obtained using other heuristics may be compared to the results of the branch-and-bound method. If the two are similar or identical, confidence in the solution is increased.

E53, sensitivity analysis

Considering the effect of small variations in certain parameters or constraints in the model on the solution helps to grasp the stability of the solution and its sensitivity to input variations.

Through the steps, not only can the accuracy of the solution be verified, but also the quality and the robustness of the solution can be evaluated.

E6, tuning and optimization

Based on the verification result of the solution, the model parameters or constraints are adjusted if necessary, and then the optimization is performed again.

E7, implementation and monitoring

And applying the optimized result to an actual traffic management system, and continuously monitoring the effect of the traffic management system to ensure the continuous performance of the system.

By adopting the mode, the method can help us to find the optimal traffic management strategy, thereby reducing the congestion and improving the traffic efficiency.

By adopting the mode in the embodiment, the congestion trend of any subarea can be determined, and then a control instruction can be output to traffic control equipment in the subarea according to the congestion trend of each subarea, so that traffic congestion can be reduced to the maximum extent, and the road use efficiency is improved.

In some embodiments of the present disclosure, it is desirable to ensure real-time, accuracy, and feasibility of data when the traffic control device outputs control instructions. The following are the detailed operation steps:

1) Converting output of predictive model into interpretable instructions

In particular, we need to translate the numerical output of the predictive model into specific traffic control strategies or instructions. For example, if the optimization results suggest reducing the inflowing traffic at an intersection, it may be desirable to adjust the signal timing at that intersection.

2) Sending instructions using a communication protocol

In particular, modern traffic control devices are often equipped with remote control functions. The control instructions are sent to the target device using a predefined communication protocol (e.g., TCP/IP, MQTT, etc.).

3) Real-time monitoring and feedback

After the control command is issued, the traffic condition needs to be monitored in real time to verify the proposed effect. If traffic conditions are not improved as expected, or new problems occur, it may be necessary to re-optimize and make new control advice.

4) Backup and recording

In particular, for analysis and improvement, all issued control advice and real-time traffic data need to be backed up. This may help us to understand the effect of each control recommendation and optimize the algorithm in the future.

5) Fault detection and emergency handling

In particular, to ensure stable operation of the traffic system, it is necessary to detect any possible equipment failure or communication interruption in real time and to have corresponding emergency treatment measures. For example, if a signal lamp failure is detected, a switch to the standby system may be made immediately, with notification to the maintenance team.

In summary, issuing control advice to traffic control devices based on the output of predictive models is a comprehensive process that requires consideration of the real-time, safety and stability of the traffic system.

In some embodiments, other factors need to be considered when executing control instructions, such as the inability to simply close a primary intersection, as this may lead to other problems.

Based on this, in some embodiments of the present disclosure, before outputting the control instruction to the traffic control device in the sub-area, the method further includes: the feasibility of the control instruction is checked. By checking the feasibility of the control instruction, the control instruction can be ensured not to violate traffic rules or cause potential safety hazards when being executed, and the real-time performance, safety and stability of traffic operation can be improved.

In implementations, control instructions corresponding to different types of traffic control devices may be output according to the traffic control devices.

For example, the control instructions in the embodiments of the present specification may include: at least one of a lighting instruction to adjust the duration of the traffic light, a control instruction to limit the flow of traffic, and a traffic control instruction to temporarily close the portal.

It is to be understood that the types of the control instructions are merely exemplary, and the embodiments of the present disclosure do not limit the types of the control instructions, so long as the traffic jam problem can be alleviated according to the control instructions. For example, in some other embodiments, control instructions to open a temporary lane may also be included.

In a specific implementation, after determining the congestion tendency of each subarea, in order to reduce the probability of congestion of the subarea, a driving suggestion may also be provided to the driver.

Specifically, the traffic congestion processing method in the embodiment of the present disclosure may further include: and providing a driving suggestion to a driver according to the congestion tendency of the plurality of subareas, so that the driver can select the best or optimal driving path, and the possibility of congestion of the target area is reduced.

In some embodiments of the present description, as shown in fig. 8, a driving advice may be provided to the driver as follows:

s81, acquiring traffic data of all subareas and expected weather conditions.

Specifically, the traffic data can reflect the congestion state of the current sub-area, and the expected weather conditions may affect the traffic state, so that the travel path of the suitable driver can be determined according to the traffic data of each sub-area and the expected weather conditions.

In some embodiments, traffic data may include traffic flow, vehicle speed, and road conditions.

In some embodiments, weather conditions may be collected by a weather provider.

In some other embodiments, traffic patterns of specific dates and times, such as holidays, rush hour, etc., may also be recorded to better provide the driver with a better travel path.

In implementations, existing data and machine learning/statistical methods may be used to predict the next traffic conditions, and the learning model may be based on time series analysis, neural networks, and the like.

For example, with continued reference to fig. 8:

s82, inputting traffic data and expected weather conditions of each subarea into a learning model for traffic jam identification, so as to determine a plurality of driving paths and driving time required by each driving path through the learning model.

Specifically, since the learning model is trained based on a plurality of pairs of training samples, and each pair of training samples includes traffic data and a corresponding expected weather condition, a plurality of travel paths and travel times required for each travel path can be determined according to the traffic data and the expected weather condition of each sub-region.

In some embodiments, all possible paths from the start point to the end point may be calculated using an algorithm in graph theory, such as Dijkstra's algorithm, and the expected travel time may be scored or calculated for each path taking into account the real-time traffic data and the predicted data.

S83, providing travel route advice to the driver according to the travel time required by each travel route.

Specifically, all possible travel paths are ranked by expected travel time or score, and the best or fastest path is selected for presentation to the driver as a travel path suggestion.

In some embodiments of the present disclosure, travel route advice may be provided to the driver via a car navigation system, a cell phone APP, or other communication means.

In particular implementations, the travel path advice should be clear, easy to understand, and provide voice guidance.

It will be appreciated that the route advice may be updated in real time as the driver's driving and traffic conditions change. For example, if a traffic accident occurs in front, resulting in a road closure, the system should immediately provide the driver with detour advice.

In a specific implementation, in accordance with the congestion tendency of the plurality of subareas, driving advice may also be provided to the driver based on the preference of the driver.

For example, some drivers may prefer a highway, while some may want to avoid a toll booth. The recommended path may be further screened or adjusted based on the driver's preferences.

In a specific implementation, the learning model may be optimized according to a driving path of the driver and an actual driving time corresponding to the driving path.

In short, providing travel path advice to the driver in combination with current traffic conditions and predictive data is a dynamic, real-time process that requires the system to continually collect, analyze, and adjust the advice based on up-to-date intelligence.

For ease of understanding, the following details of the traffic congestion processing scheme in the embodiments of the present specification are given by way of specific examples:

example 1: at a large intersection, real-time traffic data is collected through a camera and a sensor, traffic jam caused by overlarge traffic flow in a certain direction is found, the traffic jam area is determined by analyzing the data, and advice for prolonging the red light time can be sent to traffic signal lamps in opposite directions at the moment.

Example 2: in an urban area, real-time traffic data are collected through sensors, a main road is found to be seriously congested, suggestions of closing the intersection are sent to traffic lights on the upstream of the main road, and meanwhile, suggestions are sent to a navigation system to guide vehicles to bypass.

Example 3: on a bridge, data is collected through a camera and a sensor, and the traffic flow on the bridge is found to be increased, so that congestion is predicted to occur. Then, a suggestion to limit the vehicle entry is sent to the entrance of the bridge and a suggestion to adjust the duration of the signal is sent to the nearby traffic lights.

It will be appreciated that while the embodiments provided herein have been described above with respect to various embodiments, the various alternatives identified by the various embodiments may be combined with each other and cross-referenced without conflict, thereby extending what is believed to be the embodiments disclosed and disclosed herein.

The present disclosure further provides a traffic congestion processing system corresponding to the traffic congestion processing method, and the detailed description is provided by specific embodiments with reference to the accompanying drawings.

It should be noted that the traffic congestion processing system described below may be regarded as a functional module required to be set for implementing the traffic congestion processing method provided in the present specification; the contents of the traffic congestion processing system described below may be referred to in correspondence with the contents of the traffic congestion processing method described above.

Referring to fig. 9, a schematic structural diagram of a traffic congestion processing system in the embodiment of the present disclosure, as shown in fig. 9, a traffic congestion processing system 100 may include:

a first determining unit 110 adapted to determine a plurality of sub-areas corresponding to the target area;

a second determining unit 120 adapted to determine a congestion status of each sub-area;

a third determining unit 130, adapted to determine a congestion tendency of any sub-area according to the congestion status of any one sub-area of the plurality of sub-areas and the congestion status of other sub-areas;

the generating unit 140 is adapted to generate an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of sub-areas.

With the traffic congestion processing system 100 provided in the embodiment of the present disclosure, the accuracy of the congestion state of each sub-area obtained by the second determining unit 120 can be improved by determining multiple sub-areas corresponding to the target area by the first determining unit 110, and then the third determining unit 130 can determine the congestion tendency of any sub-area according to the congestion state of any sub-area in the multiple sub-areas and the congestion state of other sub-areas.

In some embodiments of the present specification, the third determining unit may determine the congestion tendency of any sub-area in the following manner:

firstly, when any one sub-area is determined to be in a congestion state, acquiring traffic flow data of the any one sub-area and sub-areas adjacent to the any one sub-area, and determining a congestion diffusion trend of the any one sub-area and a congestion diffusion trend of the sub-areas adjacent to the any one sub-area according to the traffic flow data; secondly, determining the congestion tendency of any sub-area by adopting a preset prediction model according to the congestion diffusion tendency of any sub-area and the congestion diffusion tendency of the sub-area adjacent to any sub-area. The specific process may be referred to the foregoing examples, and will not be described herein.

In some embodiments of the present specification, the second determining unit may determine the congestion status of each sub-area in the following manner: the method comprises the steps of obtaining congestion information of each subarea for representing congestion of traffic roads, and determining the congestion state of the corresponding subarea according to the congestion information of each subarea, wherein the congestion information at least comprises the total area of a road network of each subarea and the total traffic flow of each subarea. The specific analysis procedure can be found in the foregoing examples.

In some embodiments, after determining the congestion tendency of each sub-area, driving advice may also be provided to the driver in order to reduce the probability of congestion occurring in the sub-area.

Based on this, with continued reference to fig. 9, the traffic congestion processing system in the embodiment of the present specification may further include: the travel advice unit 150 provides the travel advice to the driver according to the congestion tendency of the plurality of sub-areas.

The embodiment of the present disclosure further provides a data processing apparatus, referring to the schematic structural diagram of the data processing apparatus shown in fig. 10, the data processing apparatus 200 may include a memory 210 and a processor 220, where the memory 210 stores computer instructions that may be executed on the processor 220, and when the processor 220 executes the computer instructions, the steps of the traffic congestion processing method in any one of the foregoing embodiments may be executed, and detailed descriptions of the foregoing embodiments may be omitted herein.

The embodiments of the present disclosure further provide a computer readable storage medium, on which computer instructions are stored, where the computer instructions may execute the steps of any embodiment of the foregoing traffic congestion processing method, and specific reference may be made to the detailed description of the foregoing traffic congestion processing method embodiment, which is not repeated herein.

In particular implementations, the computer-readable storage medium may include, for example, any suitable type of memory unit, memory device, memory article, memory medium, storage device, storage article, storage medium and/or storage unit, for example, memory, removable or non-removable media, erasable or non-erasable media, writeable or re-writeable media, digital or analog media, hard disk, floppy disk, compact disk read Only memory (CD-ROM), compact disk recordable (CD-R), compact disk Rewriteable (CD-RW), optical disk, magnetic media, magneto-optical media, removable memory cards or disks, various types of Digital Versatile Disk (DVD), a tape, a cassette, or the like.

Computer instructions may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, encrypted code, and the like, implemented using any suitable high-level, low-level, object-oriented, visual, compiled and/or interpreted programming language.

The specific implementation manner, working principle, specific action and effect of the system and the device in the embodiments of the present specification can be referred to in the specific description of the corresponding method embodiments.

Although the embodiments of the present specification are disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.

Claims

1. A traffic congestion processing method, characterized by comprising:

determining a plurality of subareas corresponding to the target area;

determining the congestion state of each subarea;

generating an execution suggestion corresponding to the target area according to the congestion tendency of the plurality of subareas;

the determining the congestion tendency of any sub-area according to the congestion state of any sub-area in the plurality of sub-areas and the congestion state of other sub-areas comprises the following steps:

when any one sub-area is determined to be in a congestion state, acquiring traffic flow data of the any one sub-area and sub-areas adjacent to the any one sub-area;

Determining the congestion diffusion trend of any one sub-area and the congestion diffusion trend of the sub-area adjacent to the any one sub-area according to the traffic flow data;

determining the congestion tendency of any sub-area by adopting a preset prediction model according to the congestion tendency of any sub-area and the congestion tendency of the sub-area adjacent to any sub-area;

determining the congestion tendency of any sub-area by adopting a preset prediction model according to the congestion tendency of any sub-area and the congestion tendency of the sub-area adjacent to any sub-area, including:

acquiring traffic flow density, traffic flow speed and road network density of any one sub-area and sub-areas adjacent to the any one sub-area in a preset period;

inputting the traffic flow density, the traffic flow speed and the road network density into the prediction model to obtain traffic prediction data;

determining a traffic flow change trend of any subarea according to the traffic prediction data, wherein the traffic flow change trend is used for representing a congestion trend;

the prediction model is obtained by adopting the following modes:

Describing traffic flow data of each subarea based on a preset fluid equation;

establishing an equation for describing traffic flow according to traffic flow data and fluid mechanics principles of each subarea;

and processing an equation for describing traffic flow by adopting a preset analysis method to obtain the prediction model.

2. The traffic congestion processing method according to claim 1, wherein the determining a plurality of sub-areas corresponding to the target area includes:

acquiring a plurality of pieces of position information data, wherein each piece of position information data at least comprises position information corresponding to the target area;

and dividing the target area according to boundary characteristics of each position information data to obtain a plurality of corresponding subareas.

3. The traffic congestion processing method according to claim 1, wherein said determining the congestion status of each sub-area includes:

acquiring congestion information of each subarea for representing congestion of a traffic road, wherein the congestion information at least comprises the total area of a road network of each subarea and the total traffic flow of each subarea;

and determining the congestion state of the corresponding subarea according to the congestion information of each subarea.

4. A traffic congestion processing method according to claim 3, wherein the obtaining congestion information for characterizing congestion of a traffic road for each sub-area includes:

Determining key path points in each subarea;

acquiring actual traffic flow of key path points of each subarea in a preset period;

determining the total traffic flow corresponding to each subarea according to the actual traffic flow of the key path point of each subarea in a preset period;

and determining the total area of the road network corresponding to each sub-region according to the distribution positions of the key path points.

5. The traffic congestion processing method according to claim 1, wherein the describing traffic flow data of each sub-region based on a preset fluid equation includes:

establishing an analog road section area of each subarea;

simplifying the fluid equation into a form suitable for traffic flow;

defining an initial traffic density and a traffic speed of the simulated road section area;

and simulating the change of the traffic flow data of each subarea in a preset time step by adopting a numerical solution mode.

6. The traffic congestion processing method according to claim 5, wherein the processing of the equation describing the traffic flow to obtain the predictive model using a preset analysis method includes:

dividing the analog road section area of each sub-area into a plurality of sub-road sections, and taking the set point of each sub-road section as a grid point;

Converting the equation describing the traffic flow into algebraic equations at each grid point;

and inputting the initial traffic density and the traffic speed of each grid point into the algebraic equation to determine a discrete equation within the preset time step, wherein the discrete equation is the prediction model.

7. The traffic congestion processing method according to claim 6, wherein the processing the equation for describing the traffic flow using a preset analysis method to obtain the prediction model, further comprises:

at least one parameter of traffic signals, traffic accidents and road surface states is taken as a boundary condition of each grid point, and the boundary condition is brought into the algebraic equation.

8. A traffic congestion handling system, comprising:

a generating unit adapted to generate an execution suggestion corresponding to the target area according to congestion trends of the plurality of sub-areas;

the prediction model is obtained by adopting the following modes:

describing traffic flow data of each subarea based on a preset fluid equation;

9. A data processing apparatus comprising: a memory and a processor, said memory having stored thereon computer instructions executable on said processor, characterized in that said processor executes the steps of the method according to any of claims 1 to 7 when said processor executes said computer instructions.

10. A computer readable storage medium having stored thereon computer instructions, which when run perform the steps of the method of any of claims 1 to 7.