Intelligent traffic management method and system based on big data

Abstract

The invention discloses an intelligent traffic management method and system based on big data, and relates to the technical field of intelligent traffic, and the method comprises the steps: generating a plurality of driving paths based on the starting point information of a target vehicle, dividing each driving path into a plurality of sub-paths based on an intersection, and carrying out the calculation of the sub-paths; calculating the initial passing time of the target vehicle based on the average vehicle passing speed and the path length in the preset time period; and the initial passing time of the target vehicle is adjusted for multiple times under the consideration of the driving environment, the road condition and the influence of the road on the vehicle passing, and finally the corrected passing time of the target vehicle and the corrected passing time based on the driving path are obtained, and the optimal driving path of the target vehicle is screened out. According to the method, the traffic historical data and the traffic real-time data are fully utilized, and the influence of the driving environment, the road condition and the road on vehicle driving is considered, so that the optimal driving path can be provided for the target vehicle more accurately.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and in particular, to a smart transportation management method and system based on big data. Background Art

[0002] Smart transportation is a new transportation development model based on a combination of networks such as the Internet and the Internet of Things, with smart road networks, smart equipment, smart travel, and smart management as important contents. It has the basic characteristics of information connectivity, real-time monitoring, management coordination, and human-in-one. It is based on intelligent transportation and integrates high-tech IT technologies such as the Internet of Things, cloud computing, big data, and mobile Internet. It collects traffic information through high-tech and provides traffic information services under real-time traffic data. It makes extensive use of data processing technologies such as data models and data mining to realize the systematicness, real-timeness, interactivity of information exchange, and extensiveness of services of smart transportation.

[0003] Smart traffic management based on big data is a traffic management model that uses big data technology to optimize the operating efficiency, safety and sustainability of the traffic system, such as traffic congestion prediction and accident warning. However, the current smart traffic management system based on big data does not closely link traffic prediction, real-time traffic and route planning. For example, when planning a route, the route is planned based on the traffic volume, traffic light waiting time and vehicle travel time on the path within a certain period of time, without considering the impact of roads, weather and environment on vehicle traffic. When a traffic accident occurs on the planned route, most of the routes are re-planned based on the above data, without considering the radiation impact caused by the traffic accident. Therefore, there is an urgent need for a smart traffic management method and system based on big data, which can closely integrate traffic prediction, real-time traffic and route planning, so as to provide vehicles with more accurate optimal route planning. Summary of the invention

[0004] In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a smart traffic management method based on big data, the method comprising: Acquire the starting point information of the target vehicle, and generate multiple driving paths based on the starting point information; Taking intersections as nodes, each driving path is divided into multiple sub-paths, and each node is included in a sub-path; Acquire the real-time traffic data and the historical traffic data of all sub-paths, establish a first data set for storing the real-time traffic data, and establish a second data set for storing the historical traffic data; Based on the first data set, an average speed of vehicles passing through a single sub-path within a preset time period is obtained and recorded as a first predicted speed of the target vehicle, and a length of the single sub-path is obtained and recorded as a first distance; The first formula is used to calculate the initial travel time of each driving path, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; Based on the second data set, a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time is established, recorded as a first curve graph, and all first curve graphs are placed in a curve graph set; Based on the curve atlas and the first data set, a first predicted speed of the target vehicle passing through the single-segment sub-path is corrected to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and based on all the second predicted speeds and all the first distances, an initial travel time of each driving path is adjusted to obtain a first corrected travel time; Based on the first data set, determine whether a traffic accident occurs in all driving paths; if so, define the accident impact area with the traffic accident point as the center and a preset distance as the radius, process the second predicted speed of the target vehicle in all sub-paths within the accident impact area to obtain a first processing result; based on the first processing result and all first distances, adjust the first corrected travel time to obtain a second corrected travel time; if not, use the first corrected travel time as the second corrected travel time; Based on the second data set, a preset method is used to obtain a slope coefficient of a single sub-path to obtain a first acquisition result; based on the first acquisition result, a first distance of each sub-path is processed to obtain a second processing result; based on the first processing result and the second processing result, the second corrected travel time is adjusted to obtain a third corrected travel time; The driving path with the shortest third corrected travel time is selected as the optimal driving path of the target vehicle.

[0005] The present invention is implemented through the following technical scheme: first, the starting point information of the target vehicle is obtained, and multiple driving paths are generated through the starting point information. This can be achieved based on existing technologies (such as map software), and a first data set for storing real-time traffic data and a second data set for storing historical traffic data are established. In order to ensure the timeliness of data transmission, the first data set is stored in the edge device end, and the second data set is stored in the local terminal; the average speed of the vehicle passing through the single-segment sub-path within a preset time period (such as the past 1 hour) and the distance of the single-segment sub-path are collected in the first data set to obtain the initial travel time of each driving path. However, at this time, the initial travel time is calculated based on real-time traffic data, and does not consider the influence of historical traffic data (such as weather and time), road conditions (such as traffic accidents) and the road itself (slope, curvature, etc.). Therefore, this scheme processes the initial travel time of each driving path as follows: First, based on the second data set, a first curve graph of the average speed of vehicles passing through a single-segment sub-path under different environments over time (such as within a day) is established, and placed in a curve graph set. Based on the curve graph set and the first data set, the first predicted speed of the target vehicle passing through the single-segment sub-path is corrected, that is, the curve graph set and the first data set are used to obtain the average driving speed of the target vehicle passing through the single-segment sub-path under the same time period and the same environment in the past, and the first predicted speed is corrected using the average driving speed to obtain a second predicted speed. Based on the second predicted speed, the first corrected travel time of each driving path is finally obtained by processing; In addition, this solution also considers the radiation impact caused by traffic accidents, and determines whether a traffic accident occurs in the planned path. If so, the accident site is taken as the center and the preset distance is used as the radius to determine the accident impact area. The closer the vehicle is to the center of the accident impact area, the greater the impact on the vehicle. Then, the second predicted speed of the target vehicle in all sub-paths in the accident impact area is corrected, and finally the second corrected travel time of each driving path is obtained. If not, no action is taken, and the first corrected travel time is directly used as the second corrected travel time. Then this scheme also considers the impact of the road itself on vehicle traffic. Among the paths of the same distance, the path with a larger slope coefficient has a greater impact on vehicle traffic. Therefore, based on the second data set, a preset method is used to obtain the slope coefficient of each sub-path, and each sub-path is processed by the slope coefficient, and finally the third corrected travel time of each driving path is obtained; Taking into account the driving environment, road conditions and the impact of the road itself on vehicle traffic, the initial travel time of the target vehicle is corrected multiple times to eventually obtain the third travel time of each driving path. Then, the driving path with the shortest third travel time is selected as the optimal driving path for the target vehicle.

[0006] As an optional technical solution, obtaining the average speed of vehicles passing through a single sub-path within a preset time period includes: Acquire traffic monitoring data of a single-segment sub-path within the preset time period, wherein the traffic monitoring data includes GPS trajectory data of the vehicle and object detection data; Based on all traffic monitoring data within the preset time period, the travel time of each vehicle passing through a single sub-path is calculated to obtain a first calculation result; Based on the first calculation result, an average speed of all vehicles passing through the single-segment sub-path within the preset time period is obtained.

[0007] As an optional technical solution, based on the second data set, a curve diagram of the average speed of vehicles passing through a single sub-path under different environments over time is established, including: Obtain a single-segment sub-path as a first sub-path, and obtain historical weather data of the first sub-path within one year; Based on all historical weather data, an environmental parameter of the first sub-path is calculated using a second formula, wherein the environmental parameter includes a plurality of sub-environmental parameters; The second formula includes: is the environmental parameter of the first subpath, is the coefficient of a single sub-environment parameter, is the data value of a single sub-environment parameter, and r is the number of sub-environment parameters; Based on all environmental parameters, the driving environment of the vehicle is graded to obtain a third processing result; Based on the third processing result, for each level of vehicle driving environment, an average speed of the vehicle passing through the first sub-path in one day is obtained to obtain a second acquisition result; Based on the second acquisition result, a first curve graph under each level of vehicle driving environment is established with 24 hours as the horizontal coordinate and the average speed of the vehicle passing through the first sub-path as the vertical coordinate.

[0008] As an optional technical solution, the data value acquisition of a single sub-environment parameter includes: Obtain any sub-environment parameter and record it as a first sub-environment parameter, and obtain all historical data of the first sub-environment parameter to obtain a third acquisition result; Based on the third acquisition result, all historical data of the first sub-environment parameter are divided into data intervals, and a value is assigned to each divided data interval; Based on the assigned data interval, a data value corresponding to the first sub-environment parameter is obtained.

[0009] As an optional technical solution, based on the curve atlas and the first data set, the first predicted speed of the target vehicle passing through the single-segment sub-path is corrected: Based on the first data set, the second formula is used to calculate the environmental parameters when the target vehicle passes through the first sub-path, recorded as the first environmental parameters; Based on the first environmental parameter, determining the level of the target vehicle's driving environment to obtain a first determination result; Based on the first determination result, a corresponding first curve graph is obtained by matching in the curve graph set, and recorded as a second curve graph; Based on the first predicted speed of the target vehicle, determining the start and end times of the target vehicle passing through the first sub-path in the second curve graph; Based on the start and end times and the second curve graph, an average speed of the vehicle within the start and end times is calculated and recorded as a first corrected speed; An average of the first corrected speed and the first predicted speed is calculated, and the average is used as a second predicted speed of the target vehicle.

[0010] As an optional technical solution, the second predicted speed of the target vehicle in all sub-paths within the accident impact area is processed to obtain a first processing result including: Taking the center point of the accident impact area as the center of the circle, and based on the distance between any point in the accident impact area and the center of the circle, dividing the entire accident impact area into multiple levels of sub-accident impact areas; An influence coefficient is set for each sub-accident impact area, and the influence coefficient is proportional to the distance from the single sub-accident area to the center of the circle; Obtain a single-segment sub-path within the accident impact area, recorded as a second sub-path; Calculate the distance between any point in the second sub-path and the center point of the accident impact area, and record it as the first distance; Based on the first distance, all corresponding sub-accident impact areas are acquired to obtain a fourth acquisition result; Based on the fourth acquisition result, determine whether the second sub-path contains only a single sub-accident impact area. If so, obtain the influence coefficient of the corresponding sub-accident impact area as the first influence coefficient. Based on the first influence coefficient, process the second predicted speed of the target vehicle through the second sub-path to obtain the first processing result. If not, obtain the influence coefficient corresponding to all sub-accident areas and perform a second influence coefficient. Based on all the second influence coefficients, perform segmented processing on the second predicted speed of the target vehicle through the second sub-path to obtain the first processing result.

[0011] As an optional technical solution, based on the first influence coefficient, processing the second predicted speed of the target vehicle passing through the second sub-path includes: Calculate the product of the first influence coefficient and the second predicted speed to obtain the predicted passing speed of the target vehicle passing through the second sub-path, which is recorded as the first processing result; Processing the second predicted speed of the target vehicle passing through the second subpath based on all the second influence coefficients includes: Based on the level of the sub-accident area included in the second sub-path, dividing the second sub-path into a plurality of impact paths; The second influence coefficient corresponding to each influencing path is obtained, and the product of the corresponding second influence coefficient and the second predicted speed is calculated to obtain the predicted passing speed of the target vehicle through all the influencing paths in the second sub-path, which is recorded as the first processing result.

[0012] As an optional technical solution, the preset method for obtaining the slope coefficient of a single-segment sub-path includes: Based on the second data set, obtaining plane image data and corresponding point cloud image data of a single-segment sub-path; Based on the ground morphology of the single-segment sub-path, the plane image data and the point cloud image data, a fitting surface model is determined; Determine a first feature point set from the plane image data, and determine a second feature point set based on the point cloud image data and the fitted surface model; Determine a coordinate mapping relationship based on the feature point coordinate data in the first feature point set and the second feature point set, wherein the coordinate mapping relationship is used to represent the correspondence between the two-dimensional coordinates of the feature points in the plane image data and the three-dimensional coordinates in the world coordinate system; Based on the coordinate mapping relationship, determine the three-dimensional coordinates of each pixel point in the plane image data to obtain a second determination result; Based on the second determination result, the slope coefficient of the single-segment sub-path is obtained.

[0013] As an optional technical solution, based on the first acquisition result, processing the first distance of each sub-path includes: The product of the slope coefficient of the single-segment sub-path and the corresponding first distance is calculated to obtain the second distance of the single-segment sub-path, which is recorded as the second processing result.

[0014] In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a smart traffic management system based on big data, the system comprising: An initialization unit, used to obtain the starting point information of the target vehicle, and generate multiple driving paths based on the starting point information; A division unit is used to divide each driving path into multiple sub-paths with the intersection as a node, and each node is included in a sub-path; A data set unit, used for acquiring the real-time traffic data and the historical traffic data of all sub-paths, establishing a first data set for storing the real-time traffic data, and establishing a second data set for storing the historical traffic data; An acquisition unit, configured to acquire, based on the first data set, an average speed of vehicles passing through a single-segment sub-path within a preset time period and record it as a first predicted speed of the target vehicle, and acquire a length of the single-segment sub-path and record it as a first distance; The initial travel time unit is used to calculate the initial travel time of each driving path using the first formula, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; A curve graph set unit, used to establish a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time based on the second data set, recorded as a first curve graph, and put all the first curve graphs into the curve graph set; A first corrected travel time unit is used to correct the first predicted speed of the target vehicle passing through the single-segment sub-path based on the curve atlas and the first data set to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and to adjust the initial travel time of each driving path based on all the second predicted speeds and all the first distances to obtain a first corrected travel time; A second corrected travel time unit is used to determine whether a traffic accident occurs in all driving paths based on the first data set; if so, the accident impact area is defined with the traffic accident point as the center and a preset distance as the radius, and the second predicted speed of the target vehicle in all sub-paths within the accident impact area is processed to obtain a first processing result; based on the first processing result and all first distances, the first corrected travel time is adjusted to obtain a second corrected travel time; if not, the first corrected travel time is used as the second corrected travel time; a third modified travel time unit, configured to obtain a slope coefficient of a single sub-path by a preset method based on the second data set to obtain a first acquisition result, process a first distance of each sub-path based on the first acquisition result to obtain a second processing result, and adjust the second modified travel time based on the first processing result and the second processing result to obtain a third modified travel time; The optimal driving path unit is used to select the driving path with the shortest third corrected travel time as the optimal driving path of the target vehicle.

[0015] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: The present invention discloses a smart traffic management method based on big data. First, based on the starting point information of the target vehicle, multiple driving paths are generated. Then, based on the intersection, each driving path is divided into multiple sub-paths, and based on the average speed and path length of the vehicle in the preset time period, the initial travel time of the target vehicle is calculated; and considering the driving environment, road conditions and the impact of the road itself on the vehicle's passage, the initial travel time of the target vehicle is adjusted three times, and finally the third corrected travel time of the target vehicle is obtained. Based on the third corrected travel time of the driving path, the optimal driving path of the target vehicle is screened. The present invention can provide the optimal driving path for the target vehicle more accurately by closely integrating traffic prediction (traffic history data), real-time traffic and route planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention; Figure 1 It is a flow chart of a smart traffic management method based on big data in the present invention; Figure 2 It is a schematic diagram of the composition of a smart traffic management system based on big data in the present invention. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0019] Embodiment 1 Please refer to Figure 1 , Figure 1 The figure is a flow chart of a smart traffic management method based on big data in the present invention, and the method comprises: Acquire the starting point information of the target vehicle, and generate multiple driving paths based on the starting point information; Taking intersections as nodes, each driving path is divided into multiple sub-paths, and each node is included in a sub-path; Acquire the real-time traffic data and the historical traffic data of all sub-paths, establish a first data set for storing the real-time traffic data, and establish a second data set for storing the historical traffic data; Based on the first data set, an average speed of vehicles passing through a single sub-path within a preset time period is obtained and recorded as a first predicted speed of the target vehicle, and a length of the single sub-path is obtained and recorded as a first distance; The first formula is used to calculate the initial travel time of each driving path, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; Based on the second data set, a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time is established, recorded as a first curve graph, and all first curve graphs are placed in a curve graph set; Based on the curve atlas and the first data set, a first predicted speed of the target vehicle passing through the single-segment sub-path is corrected to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and based on all the second predicted speeds and all the first distances, an initial travel time of each driving path is adjusted to obtain a first corrected travel time; Based on the first data set, determine whether a traffic accident occurs in all driving paths; if so, define the accident impact area with the traffic accident point as the center and a preset distance as the radius, process the second predicted speed of the target vehicle in all sub-paths within the accident impact area to obtain a first processing result; based on the first processing result and all first distances, adjust the first corrected travel time to obtain a second corrected travel time; if not, use the first corrected travel time as the second corrected travel time; Based on the second data set, a preset method is used to obtain a slope coefficient of a single sub-path to obtain a first acquisition result; based on the first acquisition result, a first distance of each sub-path is processed to obtain a second processing result; based on the first processing result and the second processing result, the second corrected travel time is adjusted to obtain a third corrected travel time; The driving path with the shortest third corrected travel time is selected as the optimal driving path of the target vehicle.

[0020] The specific embodiments of the present invention are as follows: comprising calculating the initial travel time of each driving path of the target vehicle, and adjusting the initial travel time multiple times; Calculate the initial travel time of each driving path of the target vehicle: The starting point information of the target vehicle is obtained, and multiple driving paths are generated based on the starting point information; each driving path is divided into multiple sub-paths with the intersection as a node, and each node is included in a sub-path. The reason for the sub-path division is to provide the vehicle with the optimal driving path more accurately; then a first data set is established to store real-time traffic data (such as traffic flow, environment, video and other data), and a second data set is established to store historical traffic data (the same data type as the real-time data); based on the first data set, the average speed of vehicles passing through a single sub-path in the past hour is obtained as the first predicted speed of the target vehicle, and the length of each sub-path is obtained as the first distance; The first formula is used to calculate the initial travel time of each driving path, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; Among them, the initial travel time of each driving path can be accurately calculated through the first formula.

[0021] Obtaining the average speed of vehicles passing through a single sub-path within a preset time period includes: Acquire traffic monitoring data of a single-segment sub-path within the preset time period, wherein the traffic monitoring data includes GPS trajectory data of the vehicle and object detection data; Based on all traffic monitoring data within the preset time period, the travel time of each vehicle passing through a single sub-path is calculated to obtain a first calculation result; Based on the first calculation result, an average speed of all vehicles passing through the single-segment sub-path within the preset time period is obtained.

[0022] The initial travel time is processed to obtain the first corrected travel time: Based on the second data set, a curve chart showing the average speed of vehicles passing through a single sub-path under different environments over time is established, including: Obtain a single-segment sub-path as a first sub-path, and obtain historical weather data of the first sub-path within one year; Based on all historical weather data, an environmental parameter of the first sub-path is calculated using a second formula, wherein the environmental parameter includes a plurality of sub-environmental parameters; The second formula includes: is the environmental parameter of the first subpath, is the coefficient of a single sub-environment parameter, is the data value of a single sub-environment parameter, and r is the number of sub-environment parameters; Based on all environmental parameters, the driving environment of the vehicle is graded to obtain a third processing result; Based on the third processing result, for each level of vehicle driving environment, an average speed of the vehicle passing through the first sub-path in one day is obtained to obtain a second acquisition result; Based on the second acquisition result, a first curve graph under each level of vehicle driving environment is established with 24 hours as the horizontal coordinate and the average speed of the vehicle passing through the first sub-path as the vertical coordinate.

[0023] The data value acquisition of a single sub-environment parameter includes: Obtain any sub-environment parameter and record it as a first sub-environment parameter, and obtain all historical data of the first sub-environment parameter to obtain a third acquisition result; Based on the third acquisition result, all historical data of the first sub-environment parameter are divided into data intervals, and a value is assigned to each divided data interval; Based on the assigned data interval, a data value corresponding to the first sub-environment parameter is obtained.

[0024] Based on the curve atlas and the first data set, a first predicted speed of the target vehicle passing through a single-segment sub-path is corrected: Based on the first data set, the second formula is used to calculate the environmental parameters when the target vehicle passes through the first sub-path, recorded as the first environmental parameters; Based on the first environmental parameter, determining the level of the target vehicle's driving environment to obtain a first determination result; Based on the first determination result, a corresponding first curve graph is obtained by matching in the curve graph set, and recorded as a second curve graph; Based on the first predicted speed of the target vehicle, determining the start and end times of the target vehicle passing through the first sub-path in the second curve graph; Based on the start and end times and the second curve graph, an average speed of the vehicle within the start and end times is calculated and recorded as a first corrected speed; An average of the first corrected speed and the first predicted speed is calculated, and the average is used as a second predicted speed of the target vehicle.

[0025] Among them, this embodiment obtains historical weather data, uses environmental parameters to represent the driving environment of the vehicle, and uses the second formula to calculate the environmental parameters, and statistics all environmental parameters obtained based on the historical weather data, and classifies the driving environment of the vehicle. Then, for each level of driving environment, a first curve chart of the average speed of vehicles passing through a single sub-path changing with time (24h) is established and placed in a curve chart set; then based on the first data set, the current environmental parameters of the target vehicle are obtained, and the environmental parameters represent the current driving environment of the target vehicle. The data interval in which the environmental parameters of the current target vehicle are located is determined, so as to obtain the driving environment of the corresponding level, and then in the curve chart set, the first curve chart corresponding to the single-segment sub-path under the driving environment of the level is obtained, which is recorded as the second curve chart; based on the first predicted speed of the target vehicle passing through the single-segment sub-path, the start and end times are determined in the second curve chart, and then the average speed of the vehicle passing within the start and end times is calculated by mathematical software such as MATLAB, which is recorded as the first corrected speed, and the average of the first corrected speed and the first predicted speed is calculated as the second predicted speed of the target vehicle. Finally, based on the second predicted speed and the first distance corresponding to the sub-path, the first corrected travel time is obtained. By integrating historical traffic data and real-time traffic data, the second predicted speed of the target vehicle is obtained, which can more accurately predict the speed of the target vehicle passing through the corresponding sub-path.

[0026] The first corrected travel time is processed to obtain the second corrected travel time: Based on the first data set, determine whether a traffic accident occurs in all driving paths; if so, define the accident impact area with the traffic accident point as the center and a preset distance as the radius, process the second predicted speed of the target vehicle in all sub-paths within the accident impact area to obtain a first processing result; based on the first processing result and all first distances, adjust the first corrected travel time to obtain a second corrected travel time; if not, use the first corrected travel time as the second corrected travel time; Processing a second predicted speed of the target vehicle passing through the second sub-path based on the first influence coefficient includes: Calculate the product of the first influence coefficient and the second predicted speed to obtain the predicted passing speed of the target vehicle passing through the second sub-path, which is recorded as the first processing result; Processing the second predicted speed of the target vehicle passing through the second subpath based on all the second influence coefficients includes: Based on the level of the sub-accident area included in the second sub-path, dividing the second sub-path into a plurality of impact paths; The second influence coefficient corresponding to each influencing path is obtained, and the product of the corresponding second influence coefficient and the second predicted speed is calculated to obtain the predicted passing speed of the target vehicle through all the influencing paths in the second sub-path, which is recorded as the first processing result.

[0027] Among them, this embodiment fully considers the impact of traffic accidents on vehicle traffic, and further distinguishes this impact, that is, the closer to the point where the traffic accident occurs, the greater the impact on vehicle traffic. If a traffic accident occurs at point A, the accident impact area is circled with a preset distance B as the radius, and the accident impact area is further subdivided. Based on the distance from any point in the accident impact area to point A, the entire accident impact area is divided into 5 sub-accident impact areas (i.e. concentric circles). The impact coefficients of the 5 sub-accident impact areas from point A to the outside are C1, C2, C3, C4 and C5, respectively, and C1>C2>C3>C4>C5. If there is a second sub-path D in the driving path within the accident impact area, and the second predicted speed of the target vehicle passing through the second sub-path D is E, when the second sub-path D only contains a single sub-accident impact area, If it only includes the third sub-accident area from point A, then the predicted speed of the target vehicle passing through the second sub-path is equal to the product of E·C3; when the second sub-path D includes multiple sub-accident impact areas, such as including the fourth sub-accident area and the fifth sub-accident area from point A, then it is necessary to segment the second sub-path D, and record the section containing the fourth sub-accident area as D1, and the section containing the fifth sub-accident area as D2. The predicted speed of the target vehicle passing through the section D1 is equal to the product of E·C4, and the predicted speed of the target vehicle passing through the section D2 is equal to the product of E·C5. It should be noted that the above data is only for explanation and can be adjusted according to actual conditions.

[0028] The second revised travel time is processed to obtain the third revised travel time: Based on the second data set, a preset method is used to obtain a slope coefficient of a single sub-path to obtain a first acquisition result; based on the first acquisition result, a first distance of each sub-path is processed to obtain a second processing result; based on the first processing result and the second processing result, the second corrected travel time is adjusted to obtain a third corrected travel time; The preset method to obtain the slope coefficient of a single-segment sub-path includes: Based on the second data set, obtaining plane image data and corresponding point cloud image data of a single-segment sub-path; Based on the ground morphology of the single-segment sub-path, the plane image data and the point cloud image data, a fitting surface model is determined; Determine a first feature point set from the plane image data, and determine a second feature point set based on the point cloud image data and the fitted surface model; Determine a coordinate mapping relationship based on the feature point coordinate data in the first feature point set and the second feature point set, wherein the coordinate mapping relationship is used to represent the correspondence between the two-dimensional coordinates of the feature points in the plane image data and the three-dimensional coordinates in the world coordinate system; Based on the coordinate mapping relationship, determine the three-dimensional coordinates of each pixel point in the plane image data to obtain a second determination result; Based on the second determination result, the slope coefficient of the single-segment sub-path is obtained.

[0029] Based on the first acquisition result, processing the first distance of each sub-path includes: The product of the slope coefficient of the single-segment sub-path and the corresponding first distance is calculated to obtain the second distance of the single-segment sub-path, which is recorded as the second processing result.

[0030] The fitted surface model is determined by acquiring the plane image data and point cloud image data of a single-segment sub-path, and the three-dimensional coordinates of each pixel in the plane image data are determined by matching feature points. The slope coefficient (i.e., slope data) of the sub-path is calculated by these three-dimensional coordinates. For example, if the slope coefficient of the single-segment sub-path is F1 and the first distance of the single-segment sub-path is H1, then the second distance of the single-segment sub-path is equal to the product of F1·H1.

[0031] Furthermore, this embodiment adjusts the second corrected time based on the first processing result and the second processing result to obtain a third corrected travel time, and selects a driving path with the shortest third corrected travel time as the optimal driving path for the target vehicle, including: Get a sub-path in any driving path, record it as sub-path G, the second predicted speed of the target vehicle passing through sub-path G is I, the first distance of sub-path G is M, and the slope coefficient of sub-path G is N. Then the first corrected travel time of the target vehicle passing through sub-path G is the ratio of I / M. If sub-path G is located in the accident impact area, and the impact coefficients of the corresponding sub-accident area are K1 and K2 respectively, and the corresponding first distance M is divided into M1 and M2, then the second corrected travel time of the target vehicle passing through sub-path G is (K1·I / M1+K2·I / M2), and the third corrected travel time of passing through sub-path G is (K1·I / NM1+K2·I / NM2). It should be noted that the above data only serve as an explanation and can be adjusted according to actual conditions.

[0032] Embodiment 2 Please refer to Figure 2 , Figure 2 It is a schematic diagram of the composition of a smart traffic management system based on big data in the present invention, wherein the initial unit is used to obtain the starting point information of the target vehicle and generate multiple driving paths based on the starting point information; A division unit is used to divide each driving path into multiple sub-paths with intersections as nodes, and each node is included in at most one sub-path; A data set unit, used for acquiring the real-time traffic data and the historical traffic data of all sub-paths, establishing a first data set for storing the real-time traffic data, and establishing a second data set for storing the historical traffic data; An acquisition unit, configured to acquire, based on the first data set, an average speed of vehicles passing through a single-segment sub-path within a preset time period and record it as a first predicted speed of the target vehicle, and acquire a length of the single-segment sub-path and record it as a first distance; The initial travel time unit is used to calculate the initial travel time of each driving path using the first formula, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; A curve graph set unit, used to establish a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time based on the second data set, recorded as a first curve graph, and put all the first curve graphs into the curve graph set; A first corrected travel time unit is used to correct the first predicted speed of the target vehicle passing through the single-segment sub-path based on the curve atlas and the first data set to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and to adjust the initial travel time of each driving path based on all the second predicted speeds and all the first distances to obtain a first corrected travel time; A second corrected travel time unit is used to determine whether a traffic accident occurs in all driving paths based on the first data set; if so, the accident impact area is defined with the traffic accident point as the center and a preset distance as the radius, and the second predicted speed of the target vehicle in all sub-paths within the accident impact area is processed to obtain a first processing result; based on the first processing result and all first distances, the first corrected travel time is adjusted to obtain a second corrected travel time; if not, the first corrected travel time is used as the second corrected travel time; a third modified travel time unit, configured to obtain a slope coefficient of a single sub-path by a preset method based on the second data set to obtain a first acquisition result, process a first distance of each sub-path based on the first acquisition result to obtain a second processing result, and adjust the second modified travel time based on the first processing result and the second processing result to obtain a third modified travel time; The optimal driving path unit is used to select the driving path with the shortest third corrected travel time as the optimal driving path of the target vehicle.

[0033] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0034] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart traffic management method based on big data, characterized in that: The method comprises: Acquire the starting point information of the target vehicle, and generate multiple driving paths based on the starting point information; Taking intersections as nodes, each driving path is divided into multiple sub-paths, and each node is included in a sub-path; Acquire the real-time traffic data and the historical traffic data of all sub-paths, establish a first data set for storing the real-time traffic data, and establish a second data set for storing the historical traffic data; Based on the first data set, an average speed of vehicles passing through a single sub-path within a preset time period is obtained and recorded as a first predicted speed of the target vehicle, and a length of the single sub-path is obtained and recorded as a first distance; The first formula is used to calculate the initial travel time of each driving path, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; Based on the second data set, a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time is established, recorded as a first curve graph, and all first curve graphs are placed in a curve graph set; Based on the curve atlas and the first data set, a first predicted speed of the target vehicle passing through the single-segment sub-path is corrected to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and based on all the second predicted speeds and all the first distances, an initial travel time of each driving path is adjusted to obtain a first corrected travel time; Based on the first data set, determine whether a traffic accident occurs in all driving paths; if so, define the accident impact area with the traffic accident point as the center and a preset distance as the radius, process the second predicted speed of the target vehicle in all sub-paths within the accident impact area to obtain a first processing result; based on the first processing result and all first distances, adjust the first corrected travel time to obtain a second corrected travel time; if not, use the first corrected travel time as the second corrected travel time; Based on the second data set, a preset method is used to obtain a slope coefficient of a single sub-path to obtain a first acquisition result; based on the first acquisition result, a first distance of each sub-path is processed to obtain a second processing result; based on the first processing result and the second processing result, the second corrected travel time is adjusted to obtain a third corrected travel time; The driving path with the shortest third corrected travel time is selected as the optimal driving path of the target vehicle.

2. According to the big data-based intelligent traffic management method of claim 1, it is characterized in that: Obtaining the average speed of vehicles passing through a single sub-path within a preset time period includes: Acquire traffic monitoring data of a single-segment sub-path within the preset time period, wherein the traffic monitoring data includes GPS trajectory data of the vehicle and object detection data; Based on all traffic monitoring data within the preset time period, calculating the travel time of each vehicle passing through a single-segment sub-path to obtain a first calculation result; Based on the first calculation result, an average speed of all vehicles passing through the single-segment sub-path within the preset time period is obtained.

3. The intelligent traffic management method based on big data according to claim 1 is characterized in that: Based on the second data set, a curve diagram of the average speed of vehicles passing through a single sub-path under different environments over time is established, including: Obtain a single-segment sub-path as a first sub-path, and obtain historical weather data of the first sub-path within one year; Based on all historical weather data, an environmental parameter of the first sub-path is calculated using a second formula, wherein the environmental parameter includes a plurality of sub-environmental parameters; The second formula includes: is the environmental parameter of the first subpath, is the coefficient of a single sub-environment parameter, is the data value of a single sub-environment parameter, and r is the number of sub-environment parameters; Based on all environmental parameters, the driving environment of the vehicle is graded to obtain a third processing result; Based on the third processing result, for each level of vehicle driving environment, an average speed of the vehicle passing through the first sub-path in one day is obtained to obtain a second acquisition result; Based on the second acquisition result, a first curve graph under each level of vehicle driving environment is established with 24 hours as the horizontal coordinate and the average speed of the vehicle passing through the first sub-path as the vertical coordinate.

4. The intelligent traffic management method based on big data according to claim 3 is characterized in that: The data value acquisition of a single sub-environment parameter includes: Obtain any sub-environment parameter and record it as a first sub-environment parameter, and obtain all historical data of the first sub-environment parameter to obtain a third acquisition result; Based on the third acquisition result, all historical data of the first sub-environment parameter are divided into data intervals, and a value is assigned to each divided data interval; Based on the assigned data interval, a data value corresponding to the first sub-environment parameter is obtained.

5. The intelligent traffic management method based on big data according to claim 3 is characterized in that: Based on the curve atlas and the first data set, a first predicted speed of the target vehicle passing through a single-segment sub-path is corrected: Based on the first data set, the second formula is used to calculate the environmental parameters when the target vehicle passes through the first sub-path, recorded as the first environmental parameters; Based on the first environmental parameter, determining the level of the target vehicle's driving environment to obtain a first determination result; Based on the first determination result, a corresponding first curve graph is obtained by matching in the curve graph set, and recorded as a second curve graph; Based on the first predicted speed of the target vehicle, determining the start and end times of the target vehicle passing through the first sub-path in the second curve graph; Based on the start and end times and the second curve graph, an average speed of the vehicle within the start and end times is calculated and recorded as a first corrected speed; An average of the first corrected speed and the first predicted speed is calculated, and the average is used as a second predicted speed of the target vehicle.

6. The method for intelligent traffic management based on big data according to claim 1 is characterized in that: Processing the second predicted speed of the target vehicle in all sub-paths in the accident impact area to obtain a first processing result includes: Taking the center point of the accident impact area as the center of the circle, and based on the distance between any point in the accident impact area and the center of the circle, dividing the entire accident impact area into multiple levels of sub-accident impact areas; An influence coefficient is set for each sub-accident impact area, and the influence coefficient is proportional to the distance from the single sub-accident area to the center of the circle; Obtain a single-segment sub-path within the accident impact area, recorded as a second sub-path; Calculate the distance between any point in the second sub-path and the center point of the accident impact area, and record it as the first distance; Based on the first distance, all corresponding sub-accident impact areas are acquired to obtain a fourth acquisition result; Based on the fourth acquisition result, determine whether the second sub-path contains only a single sub-accident impact area. If so, obtain the influence coefficient of the corresponding sub-accident impact area as the first influence coefficient. Based on the first influence coefficient, process the second predicted speed of the target vehicle through the second sub-path to obtain the first processing result. If not, obtain the influence coefficient corresponding to all sub-accident areas and perform a second influence coefficient. Based on all the second influence coefficients, perform segmented processing on the second predicted speed of the target vehicle through the second sub-path to obtain the first processing result.

7. The method for intelligent traffic management based on big data according to claim 6 is characterized in that: Processing a second predicted speed of the target vehicle passing through the second sub-path based on the first influence coefficient includes: Calculate the product of the first influence coefficient and the second predicted speed to obtain the predicted passing speed of the target vehicle passing through the second sub-path, which is recorded as the first processing result; Processing the second predicted speed of the target vehicle passing through the second subpath based on all the second influence coefficients includes: Based on the level of the sub-accident area included in the second sub-path, dividing the second sub-path into a plurality of impact paths; The second influence coefficient corresponding to each influencing path is obtained, and the product of the corresponding second influence coefficient and the second predicted speed is calculated to obtain the predicted passing speed of the target vehicle through all the influencing paths in the second sub-path, which is recorded as the first processing result.

8. The intelligent traffic management method based on big data according to claim 1 is characterized in that: The preset method to obtain the slope coefficient of a single-segment sub-path includes: Based on the second data set, obtaining plane image data and corresponding point cloud image data of a single-segment sub-path; Based on the ground morphology of the single-segment sub-path, the plane image data and the point cloud image data, a fitting surface model is determined; Determine a first feature point set from the plane image data, and determine a second feature point set based on the point cloud image data and the fitted surface model; Determine a coordinate mapping relationship based on the feature point coordinate data in the first feature point set and the second feature point set, wherein the coordinate mapping relationship is used to represent the correspondence between the two-dimensional coordinates of the feature points in the plane image data and the three-dimensional coordinates in the world coordinate system; Based on the coordinate mapping relationship, determine the three-dimensional coordinates of each pixel point in the plane image data to obtain a second determination result; Based on the second determination result, the slope coefficient of the single-segment sub-path is obtained.

9. The intelligent traffic management method based on big data according to claim 1 is characterized in that: Based on the first acquisition result, processing the first distance of each sub-path includes: The product of the slope coefficient of the single-segment sub-path and the corresponding first distance is calculated to obtain the second distance of the single-segment sub-path, which is recorded as the second processing result.

10. A smart traffic management system based on big data, characterized in that: The system comprises: An initialization unit, used to obtain the starting point information of the target vehicle, and generate multiple driving paths based on the starting point information; A division unit is used to divide each driving path into multiple sub-paths with the intersection as a node, and each node is included in a sub-path; A data set unit, used for acquiring the real-time traffic data and the historical traffic data of all sub-paths, establishing a first data set for storing the real-time traffic data, and establishing a second data set for storing the historical traffic data; An acquisition unit, configured to acquire, based on the first data set, an average speed of vehicles passing through a single-segment sub-path within a preset time period and record it as a first predicted speed of the target vehicle, and acquire a length of the single-segment sub-path and record it as a first distance; The initial travel time unit is used to calculate the initial travel time of each driving path using the first formula, including: is the initial travel time of each driving path, is the first distance of a single-segment sub-path in each driving path, is the first predicted speed of the target vehicle passing through a single sub-path in each driving path, is the number of segments containing sub-paths in each driving path; A curve graph set unit, used to establish a curve graph of the average speed of vehicles passing through a single sub-path under different environments over time based on the second data set, recorded as a first curve graph, and put all the first curve graphs into the curve graph set; A first corrected travel time unit is used to correct the first predicted speed of the target vehicle passing through the single-segment sub-path based on the curve atlas and the first data set to obtain a second predicted speed of the target vehicle passing through the single-segment sub-path, and to adjust the initial travel time of each driving path based on all the second predicted speeds and all the first distances to obtain a first corrected travel time; A second corrected travel time unit is used to determine whether a traffic accident occurs in all driving paths based on the first data set; if so, the accident impact area is defined with the traffic accident point as the center and a preset distance as the radius, and the second predicted speed of the target vehicle in all sub-paths within the accident impact area is processed to obtain a first processing result; based on the first processing result and all first distances, the first corrected travel time is adjusted to obtain a second corrected travel time; if not, the first corrected travel time is used as the second corrected travel time; a third modified travel time unit, configured to obtain a slope coefficient of a single sub-path by a preset method based on the second data set to obtain a first acquisition result, process a first distance of each sub-path based on the first acquisition result to obtain a second processing result, and adjust the second modified travel time based on the first processing result and the second processing result to obtain a third modified travel time; The optimal driving path unit is used to select the driving path with the shortest third corrected travel time as the optimal driving path of the target vehicle.

Images