Route planning method, device and equipment for avoiding traffic congestion and storage medium

Abstract

This invention discloses a route planning method, apparatus, device, and storage medium for avoiding traffic congestion. Based on the number of vehicles passing and the time of each vehicle's passage collected by each road surface sensor on each road segment, a weighted length for each road segment is determined. Based on the weighted length of the road segments enclosing each sub-region, a weighted area for each sub-region is determined. A first weighted graph is constructed using each sub-region as a node, where the weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select a set of target sub-regions from all nodes in the first weighted graph. A second weighted graph is constructed using each road segment as a node, where the weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select a set of target road segments from nodes located in the target sub-regions in the second weighted graph. This invention can predict road segments that may experience congestion.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, specifically relating to route planning methods, devices, equipment, and storage media for avoiding traffic congestion. Background Technology

[0002] Traffic congestion is a frequent problem that plagues people's daily lives, severely wasting drivers' time and energy and causing a series of social problems. Current solutions to traffic congestion typically rely on traffic radio broadcasts or in-car or mobile navigation systems. This approach has three drawbacks: first, it only makes a judgment when traffic congestion has already occurred or is about to occur, which is usually too late; second, it focuses on individual drivers and vehicles to plan optimal routes, adopting a piecemeal approach and failing to provide a globally dynamic optimal solution from a holistic perspective; and third, radio broadcasts rely on human intervention for observation and reporting, resulting in low efficiency. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention provides a route planning method, apparatus, device, and storage medium for avoiding traffic congestion. It can predict road sections that may be congested, thereby providing vehicle navigation route suggestions and achieving global optimization of traffic flow scheduling.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0005] A route planning method to avoid traffic congestion includes:

[0006] Obtain road network information for a traffic area, the road network information including multiple road segments and multiple sub-areas enclosed by the multiple road segments, and each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle's passage;

[0007] The number of vehicles passing and the time of each vehicle passing are collected in real time by each of the road surface sensors on each road segment.

[0008] The weighted length of each road segment is determined based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment.

[0009] The weighted area of ​​each sub-region is determined based on the weighted length of the road segments that enclose each sub-region;

[0010] A first weighted graph is formed with each of the sub-regions as nodes. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target sub-region set from all nodes in the first weighted graph.

[0011] A second weighted graph is formed with each of the aforementioned road segments as nodes. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target road segment set from the nodes located in the target sub-region in the second weighted graph.

[0012] Furthermore, the weighted length of each road segment is determined based on the number of vehicles passing and the time of each vehicle's passage, collected by each road surface sensor on each road segment, using the following formula:

[0013] D[j]=(1+f(pr[j]))*d[j]

[0014] pr[j]=(ps[1]+ps[2]+...+ps[x]) / x

[0015] In the formula, D[j] is the weighted length of road segment j; f(·) is a preset adjustment function, which is a linear function or an exponential function; d[j] is the actual length of road segment j; x is the number of road surface sensors on road segment j; pr[j] is the average bearing pressure of all road surface sensors on road segment j, and the bearing pressure value ps[i] of each road surface sensor is calculated by multiplying the number of vehicles passing by per minute n and the time t for each vehicle to pass by, where t is in milliseconds.

[0016] Furthermore, it also includes:

[0017] A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time.

[0018] The time series dataset is fitted using cubic spline interpolation to obtain a prediction function with time t as the variable;

[0019] The prediction function is used to predict the bearing pressure value of each road surface sensor on each road segment at time point t+n;

[0020] The preset adjustment function is adjusted based on the prediction results.

[0021] Furthermore, it also includes:

[0022] A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time.

[0023] Predict the ratio of vehicles entering the traffic area in the current period to the same period last time based on the time series dataset;

[0024] Predict the vehicles entering the traffic area in the current period based on the aforementioned proportional relationship;

[0025] The preset adjustment function is adjusted based on the prediction results.

[0026] Furthermore, when the weighted area of ​​the sub-region is greater than a set multiple of the actual area of ​​the sub-region, the preset adjustment function is converted into an exponential function.

[0027] Further, determining the weighted area of ​​each sub-region based on the weighted length of the road segments enclosing each sub-region includes:

[0028] The weighted area of ​​each sub-region is calculated using calculus based on the weighted length of the road segments that enclose each sub-region.

[0029] A route planning device for avoiding traffic congestion, comprising:

[0030] The first acquisition module is used to acquire road network information of the traffic area. The road network information includes multiple road segments and multiple sub-areas enclosed by the multiple road segments. Each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle's passage.

[0031] The second acquisition module acquires in real time the number of vehicles passing by each of the road surface sensors on each road segment and the time of each vehicle passing by.

[0032] The road segment weighted length determination module is used to determine the weighted length of each road segment based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment.

[0033] The sub-region weighted area determination module is used to determine the weighted area of ​​each sub-region based on the weighted length of the road segments that enclose each sub-region;

[0034] The target sub-region set selection module is used to form a first weighted graph with each sub-region as a node. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The target sub-region set is selected from all nodes in the first weighted graph using Dijkstra's single-source shortest path algorithm.

[0035] The target road segment set selection module is used to form a second weighted graph with each road segment as a node. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The target road segment set is selected from the nodes located in the target sub-region in the second weighted graph using Dijkstra's single-source shortest path algorithm.

[0036] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the route planning method for avoiding traffic congestion.

[0037] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the route planning method for avoiding traffic congestion.

[0038] Compared with the prior art, the present invention has at least the following beneficial effects:

[0039] This invention provides a route planning method to avoid traffic congestion. Compared to traditional methods, which use a greedy strategy to plan the optimal route for each individual, traditional navigation methods often increase the likelihood of global congestion when every individual tries to reach the optimal route. This, in turn, affects the optimal route for each individual, ultimately increasing the average congestion time for all individuals. The route planning method provided by this invention adopts a reverse approach, always prioritizing finding the globally optimal solution for the regional traffic situation. A globally optimal solution represents an average optimal solution for each individual. This invention utilizes road network information and data collected from road surface sensors, including the number of vehicles passing and the time each vehicle takes, to determine the weighted length of each road segment. This transforms the congestion status of a road segment into the length value of an edge in a graph (a larger weighted length indicates more severe congestion). Based on the weighted length of the road segments enclosing each sub-region, the weighted area of ​​each sub-region is determined, transforming the regional congestion status into the area value in a graph (a larger weighted area indicates more severe regional congestion). A first weighted graph is constructed using each sub-region as a node. The weight of each node in the first weighted graph is the weighted area of ​​its corresponding sub-region. Dijkstra's single-source shortest path algorithm is used to select the set of target sub-regions from all nodes in the first weighted graph. Finally, a second weighted graph is constructed using each road segment as a node. The weight of each node in the second weighted graph is the weighted length of its corresponding road segment. Dijkstra's single-source shortest path algorithm is used to select the set of target road segments from nodes located in the target sub-regions in the second weighted graph. In other words, prioritizing regions effectively avoids regional congestion. Finally, based on avoiding regional congestion, the optimal planned target route is found, achieving global optimization of traffic flow scheduling.

[0040] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the drawings used in the description of the specific embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a route planning method for avoiding traffic congestion according to the present invention;

[0043] Figure 2 This is a schematic diagram of traffic area road network information in a route planning method for avoiding traffic congestion according to the present invention;

[0044] Figure 3 This is a schematic diagram of traffic area road network information (selecting the target sub-region set) in a route planning method to avoid traffic congestion according to the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] As a specific embodiment of the present invention, combined with Figures 1 to 3 As shown, a route planning method to avoid traffic congestion includes the following steps:

[0047] S1. Obtain road network information of the traffic area, the road network information including multiple road segments and multiple sub-areas enclosed by the multiple road segments, and each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle passing through.

[0048] Specifically, such as Figure 2 As shown, each road within the traffic area is abstracted as a line segment (with a curvature not exceeding 15 degrees). Vehicles drive along these line segments. The outer perimeter of the traffic area is an irregular polygon with multiple entrances and exits. Each edge of the polygon represents the boundary of the area, formed by connecting the multiple entrances and exits. The line segments inside the polygon can intersect or not intersect. Traffic lights are located at intersections, allowing vehicles to turn onto another line segment at the intersection (not considering elevated or multi-level traffic).

[0049] In this invention, road network information of a traffic area is obtained through cloud services. The required road surface sensor devices are evenly deployed on each road within the traffic area, with each sensor represented by a point. The road surface sensors can detect information about vehicles passing over the road surface and upload their own location information and vehicle passage information to the cloud via a communication protocol (such as MQTT).

[0050] The cloud service stores road network information and the location information of each road sensor within the entire traffic area. These two parts are static data and remain largely unchanged over a long period of time. Let the entire traffic area be Z. The entire road network divides the traffic area Z into m atomically indivisible sub-regions {z[1], z[2]... z[m]}. There are n road segments within the traffic area, forming a set {r[1], r[2]... r[n]}. There are k sensors within the traffic area, forming a set {s[1], s[2]... s[k]}.

[0051] S2. Real-time acquisition of the number of vehicles passing by each of the road surface sensors on each road segment and the time of each vehicle's passage.

[0052] Specifically, the cloud service receives real-time information from road surface sensors about passing vehicles, including the number of vehicles and the time each vehicle takes to pass.

[0053] Preferably, the present invention further forms a time-series dataset by storing in real time the number of vehicles passing and the time of each vehicle passing through each of the road surface sensors on each road segment, and stores the time-series dataset in a time-series database.

[0054] S3. Based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment, determine the weighted length of each road segment.

[0055] The pressure value ps[i] of the road surface sensor s[i] is calculated as the product of the number of vehicles passing by per minute n and the time t (milliseconds) for each vehicle to pass by the road surface sensor. In this invention, the average pressure value of all road surface sensors on the road segment is used to reflect the distribution of vehicles on the road segment, that is, to reflect the congestion of the road segment. Assuming that there are x sensors distributed on the road segment r[j], then the average pressure value pr[j] on the road segment r[j] is equal to the average pressure value of x road surface sensors on the road segment r[j], that is, pr[j] = (ps[1] + ps[2] ... + ps[x]) / x. Let d[j] be the actual physical length of the road segment, then this invention calculates the weighted length D[j] of the road segment = (1 + f(pr[j])) * d[j], where f(·) is a preset adjustment function, which can be a linear function of the value of pr[j], an exponential function, or other configured functions.

[0056] In other words, in this invention, the weighted length of each road segment is determined based on the number of vehicles passing and the time of each vehicle's passage collected by each road surface sensor on each road segment, specifically using the following formula:

[0057] D[j]=(1+f(pr[j]))*d[j]

[0058] pr[j]=(ps[1]+ps[2]+...+ps[x]) / x

[0059] In the formula, D[j] is the weighted length of road segment j; f(·) is a preset adjustment function, which is a linear function or an exponential function; d[j] is the actual length of road segment j; x is the number of road surface sensors on road segment j; pr[j] is the average bearing pressure of all road surface sensors on road segment j, and the bearing pressure value ps[i] of each road surface sensor is calculated by multiplying the number of vehicles passing by per minute n and the time t (milliseconds) of each vehicle passing by, where t is in milliseconds.

[0060] S4. Determine the weighted area of ​​each sub-region based on the weighted length of the road segments that enclose each sub-region.

[0061] Specifically, the weighted area A[i] of the subregion z[i] is obtained by calculus from the weighted length D[j] of each side of the polygon enclosing the subregion z[i].

[0062] S5, such as Figure 3 As shown, a first weighted graph is formed with each of the sub-regions as nodes. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target sub-region set from all nodes in the first weighted graph.

[0063] Specifically, assume that vehicle c enters from point p1 in region Z and the target exit is point p2. Then, firstly, a first weighted graph G1 is formed with each sub-region z as a node. The weight of each node in the first weighted graph G1 is the weighted area A of the sub-region z. Neighboring points are selected from the sub-region set {z[1], z[2]... z[m]}. The target sub-region set {z[i]... z[j]} is obtained from all nodes of the first weighted graph G1 using Dijkstra's single-source shortest path algorithm.

[0064] Using the first weighted graph G1 to find the shortest path prioritizes the region and can effectively avoid regional congestion.

[0065] S6. A second weighted graph is formed with each of the road segments as nodes. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target road segment set from the nodes located in the target sub-region in the second weighted graph.

[0066] Specifically, a second weighted graph G2 is formed with each road segment r as a node. The weight of each node in the second weighted graph G2 is the weighted length D of road segment r. The Dijkstra single-source shortest path algorithm is used to find the target road segment set {r[i]...r[j]} from the nodes located on the target sub-region set {z[i]...z[j]} in the second weighted graph G2. That is, the target road segment set {r[i]...r[j]} is found in the target sub-region set {z[i]...z[j]} and the road segment set {r[1],r[2]...r[n]}. This target road segment set is the target road segment of vehicle c, which is the planned route to avoid regional traffic congestion.

[0067] Based on avoiding regional congestion, the shortest path is then found in the second weighted graph G2 to determine the optimal route for a specific vehicle c, demonstrating that the method of this invention is a global priority algorithm.

[0068] Assuming each vehicle traveling within the traffic area has an onboard system (or the driver's mobile phone) capable of uploading its location information to the cloud and receiving control commands from the cloud, this invention, after determining the target road segment set, generates navigation commands recognizable by vehicle c based on the target road segment set {r[i]...r[j]}, and sends them to the onboard system or the driver's smartphone via a communication protocol (such as MQTT). This completes the navigation of vehicle c for the current time period d(t) (a planned route that avoids regional traffic congestion). In the next time period d(t+1), starting from the vehicle's real-time location p1, steps S2 to S5 are repeated to continuously generate and update the vehicle's optimal route.

[0069] Based on the above embodiments, as a more preferred embodiment, the present invention provides a route planning method for avoiding traffic congestion, which further includes:

[0070] A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time.

[0071] The time series dataset is fitted using cubic spline interpolation to obtain a prediction function with time t as the variable;

[0072] The prediction function is used to predict the bearing pressure value of each road surface sensor on each road segment at time point t+n;

[0073] The preset adjustment function is adjusted based on the prediction results.

[0074] Specifically, the cloud stores all historical data sets of ps[i] reported by road surface sensors, which constitute the time-series dataset. Cubic spline interpolation is used to fit this historical dataset, yielding a prediction function F1[i](t) with time t as the variable. F1[i] is then used to predict the ps[i] values ​​of all road surface sensors at time t+n in the traffic area. Substituting the new predicted ps[i] into S3 and S4 to recalculate D[j] and A[j], the predicted traffic conditions for the entire traffic area Z at time t+n can be obtained, thereby correcting the adjustment function f in S3 to avoid potential congestion.

[0075] In other words, the cloud stores historical data needed to calculate the bearing capacity values ​​of road surface sensors. Using big data calculations and cubic spline interpolation, a prediction function F[i] can be calculated to show how the bearing capacity value ps[i] of each road surface sensor s[i] changes with time t. Based on this prediction function, ps[i] at the next time point t+n can be predicted, and then D[i] = (1 + f(pr[i])) x d[i]. Therefore, traffic congestion in the future can be predicted in advance, and the form of the adjustment function f can be adjusted according to the prediction results to avoid regional traffic congestion.

[0076] Based on the above embodiments, as a more preferred embodiment, the present invention provides a route planning method for avoiding traffic congestion, which further includes:

[0077] A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time.

[0078] Predict the ratio of vehicles entering the traffic area in the current period to the same period last time based on the time series dataset;

[0079] Predict the vehicles entering the traffic area in the current period based on the aforementioned proportional relationship;

[0080] The preset adjustment function is adjusted based on the prediction results.

[0081] Specifically, for data with periodic (yearly, monthly, weekly) characteristics, such as predicting based on statistical data that the number of vehicles entering traffic area Z in the current period is N times that of the same period last time (for example, the number of vehicles entering the traffic area during the National Day holiday in 2021 is N times that of the National Day holiday in 2020), then the data from the previous historical period can be directly taken and substituted into S3 and S4. At the same time, the coefficient of the adjustment function can be adjusted by multiplying by N to predict the regional traffic conditions at time t in the current period, thereby adjusting the actual adjustment function f to avoid congestion.

[0082] As a more preferred implementation, when the weighted area of ​​a sub-region is greater than a set multiple of the actual area of ​​that sub-region, the preset adjustment function is converted into an exponential function. Specifically, when the weighted area of ​​a sub-region z[i] is greater than N (e.g., 10) times its actual area, a congestion alarm is triggered for sub-region z[i], and the adjustment function f is adjusted to an exponential function to prevent vehicles from entering this region. When the weighted area of ​​the entire traffic area Z is greater than N (e.g., 10) times its actual area, a congestion alarm is triggered for the entire traffic area, thereby limiting the flow of vehicles entering traffic area Z at the entrance.

[0083] This invention provides a route planning device for avoiding regional traffic congestion, comprising:

[0084] The first acquisition module is used to acquire road network information of the traffic area. The road network information includes multiple road segments and multiple sub-areas enclosed by the multiple road segments. Each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle's passage.

[0085] The second acquisition module acquires in real time the number of vehicles passing by each of the road surface sensors on each road segment and the time of each vehicle passing by.

[0086] The road segment weighted length determination module is used to determine the weighted length of each road segment based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment.

[0087] The sub-region weighted area determination module is used to determine the weighted area of ​​each sub-region based on the weighted length of the road segments that enclose each sub-region;

[0088] The target sub-region set selection module is used to form a first weighted graph with each sub-region as a node. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The target sub-region set is selected from all nodes in the first weighted graph using Dijkstra's single-source shortest path algorithm.

[0089] The target road segment set selection module is used to form a second weighted graph with each road segment as a node. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The target road segment set is selected from the nodes located in the target sub-region in the second weighted graph using Dijkstra's single-source shortest path algorithm.

[0090] All modules of this invention are deployed in the cloud, forming a real-time twin model of regional traffic conditions, enabling vehicles, roads, and the cloud to collaborate. This invention establishes a cloud-based twin model of traffic conditions, modeling the road network as a weighted directed graph that dynamically changes with the pressure values ​​of road surface sensors, creating a concise mathematical model for easy optimization of the optimal path. Traditional traffic flow management schemes first detect congestion, then alleviate and prevent further congestion, resulting in a time lag. This invention utilizes the cloud-based twin model to predict congestion points in advance, thereby preventing congestion.

[0091] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used to implement a route planning method for avoiding traffic congestion.

[0092] In one embodiment of the present invention, a route planning method for avoiding traffic congestion, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data.

[0093] The computer storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical storage (e.g., CD, DVD, BD, HVD), and semiconductor storage (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0094] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0096] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0098] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A route planning method to avoid traffic congestion, characterized in that, include: Obtain road network information for a traffic area, the road network information including multiple road segments and multiple sub-areas enclosed by the multiple road segments, and each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle's passage; The number of vehicles passing and the time of each vehicle passing are collected in real time by each of the road surface sensors on each road segment. Based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment, the weighted length of each road segment is determined, specifically using the following method: D[j] = (1 + f(pr[j])) * d[j] pr[j]=(ps[1] + ps[2]+...+ps[x]) / x In the formula, D[j] is the weighted length of road segment j; f(·) is a preset adjustment function, which is a linear function or an exponential function; d[j] is the actual length of road segment j; and x is the number of road surface sensors on road segment j. pr[j] is the average bearing pressure of all road surface sensors on road segment j. The bearing pressure value ps[i] of each road surface sensor is calculated as the product of the number of vehicles passing by per minute n and the time t for each vehicle to pass by, where t is in milliseconds. Based on the weighted length of the road segments enclosing each sub-region, the weighted area of ​​each sub-region is determined, including: The weighted area of ​​each sub-region is calculated using calculus based on the weighted length of the road segments that enclose each sub-region. A first weighted graph is formed with each of the sub-regions as nodes. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target sub-region set from all nodes in the first weighted graph. A second weighted graph is formed with each of the aforementioned road segments as nodes. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The Dijkstra single-source shortest path algorithm is used to select the target road segment set from the nodes located in the target sub-region in the second weighted graph.

2. The route planning method for avoiding traffic congestion according to claim 1, characterized in that, Also includes: A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time. The time series dataset is fitted using cubic spline interpolation to obtain a prediction function with time t as the variable; The prediction function is used to predict the bearing pressure value of each road surface sensor on each road segment at time point t+n; The preset adjustment function is adjusted based on the prediction results.

3. The route planning method for avoiding traffic congestion according to claim 1, characterized in that, Also includes: A time-series dataset is formed by storing the number of vehicles passing and the time of each vehicle passing through each road surface sensor on each road segment in real time. Predict the ratio of vehicles entering the traffic area in the current period to the same period last time based on the time series dataset; Predict the vehicles entering the traffic area in the current period based on the aforementioned proportional relationship; The preset adjustment function is adjusted based on the prediction results.

4. The route planning method for avoiding traffic congestion according to claim 1, characterized in that, When the weighted area of ​​the sub-region is greater than a set multiple of the actual area of ​​the sub-region, the preset adjustment function is converted into an exponential function.

5. A route planning device for avoiding traffic congestion, characterized in that, include: The first acquisition module is used to acquire road network information of the traffic area. The road network information includes multiple road segments and multiple sub-areas enclosed by the multiple road segments. Each of the road segments is equipped with road surface sensors for collecting the number of vehicles passing through and the time of each vehicle's passage. The second acquisition module acquires in real time the number of vehicles passing by each of the road surface sensors on each road segment and the time of each vehicle passing by. The road segment weighted length determination module is used to determine the weighted length of each road segment based on the number of vehicles passing and the time of each vehicle passing, collected by each road surface sensor on each road segment. Specifically, the following method is used: D[j] = (1 + f(pr[j])) * d[j] pr[j]=(ps[1] + ps[2]+...+ps[x]) / x In the formula, D[j] is the weighted length of road segment j; f(·) is a preset adjustment function, which is a linear function or an exponential function; d[j] is the actual length of road segment j; and x is the number of road surface sensors on road segment j. pr[j] is the average bearing pressure of all road surface sensors on road segment j. The bearing pressure value ps[i] of each road surface sensor is calculated as the product of the number of vehicles passing by per minute n and the time t for each vehicle to pass by, where t is in milliseconds. The sub-region weighted area determination module is used to determine the weighted area of ​​each sub-region based on the weighted length of the road segments enclosing each sub-region, including: The weighted area of ​​each sub-region is calculated using calculus based on the weighted length of the road segments that enclose each sub-region. The target sub-region set selection module is used to form a first weighted graph with each sub-region as a node. The weight of each node in the first weighted graph is the weighted area of ​​the sub-region corresponding to that node. The target sub-region set is selected from all nodes in the first weighted graph using Dijkstra's single-source shortest path algorithm. The target road segment set selection module is used to form a second weighted graph with each road segment as a node. The weight of each node in the second weighted graph is the weighted length of the road segment corresponding to that node. The target road segment set is selected from the nodes located in the target sub-region in the second weighted graph using Dijkstra's single-source shortest path algorithm.

6. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a route planning method for avoiding traffic congestion as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a route planning method for avoiding traffic congestion as described in any one of claims 1 to 4.

Images