Intelligent traffic system based on big data processing

Abstract

The invention discloses an intelligent traffic system based on big data processing, which relates to the technical field of intelligent traffic and comprises a high-precision map module, a traffic signal module, a vehicle positioning data module, a vehicle detection data module, a travel data module, a road section passing duration analysis module, a lane passing duration analysis module and a travel route planning module. The high-precision map module is used for storing a high-precision map; the traffic signal module is used for collecting traffic signal lamp data; the vehicle positioning data module is used for collecting vehicle real-time positioning data; according to the intelligent traffic system based on big data processing, the lane passing time analysis module is arranged to be matched with other modules, the passing speed and the passing time of each lane of each road section can be analyzed, and therefore the traffic speed and the passing time of each lane can be analyzed according to the situation that individual nearby lanes are congested. Several shorter-time lane driving and detouring routes are automatically planned according to nearby road conditions, and the passing efficiency is further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, in particular to an intelligent transportation system based on big data processing. BACKGROUND

[0002] With the increasing popularity of vehicles, urban road traffic is increasingly congested, so it is necessary to monitor the urban road traffic conditions to enable drivers to understand the road traffic conditions in real time and make plans in advance to improve traffic efficiency. The prior art disclosed in document CN113808391A discloses a method for improving the real-time accuracy of traffic navigation, which is based on an intelligent comprehensive traffic planning database platform, uses a traffic history big data calculation method, combines historical traffic flow data and public transportation data, can efficiently and accurately obtain real-time traffic data and historical traffic data, provides accuracy and reliability guarantee for fine traffic navigation prediction, and users can switch routes according to historical road condition prediction time, eliminate prediction deviation caused by inaccurate historical data, effectively reduce the number of big data calculation, save calculation resources, improve prediction accuracy, avoid inflexible route switching, automatically plan to include the stopover locations or stopover location types that users need to pass through, so as to make the path planning efficient, adaptively adjust the user's demand information for travel, and more accurately meet the user's demand.

[0003] However, in the road conditions of urban traffic, especially on multi-lane roads, some lanes may be slow or congested due to various reasons, which greatly affects the efficiency of traffic. SUMMARY

[0004] The purpose of the present application is to provide an intelligent transportation system based on big data processing to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: an intelligent transportation system based on big data processing, comprising a high-precision map module, a traffic signal module, a vehicle positioning data module, a vehicle detection data module, a travel data module, a road section travel time analysis module, a lane travel time analysis module and a travel route planning module. The high-precision map module is used to store a high-precision map, that is, the map contains not only road topology, but also detailed information such as lane lines, slopes, curvatures, traffic signs, signal light positions, scales, etc. The traffic signal module is used to collect traffic signal data, that is, to collect the phase and timing information of traffic signal lights, which can be obtained through V2X (Vehicle to Everything) technology; The vehicle positioning data module is used to collect vehicle real-time positioning data, wherein the vehicle real-time positioning data can be collected by a vehicle-mounted GPS, a Beidou module or a smart phone, and contains longitude and latitude, speed, heading angle, time stamp and other information; further, when collecting the vehicle real-time positioning data, the data source needs to be encrypted or blurred to prevent the privacy of the vehicle real-time positioning data source owner from being disclosed; The vehicle detection data module is used to collect vehicle detection data through a radar or a visual sensor on the vehicle, wherein the radar and the visual sensor can include a millimeter wave radar, a laser radar, an infrared camera, a high-definition camera and the like, and through the vehicle detection data, the vehicle can be more accurately positioned in a specific lane of a road section; and the vehicle type and speed near the vehicle can be recognized to judge whether the vehicle is at a turtle speed or a slow speed; through the high-definition camera, road sign information and traffic management facilities such as ice cream tubes, water horses, road maintenance warning signs and the like can also be recognized; The trip data module is used to obtain vehicle starting point and ending point information to generate vehicle trip data; The road section passing time analysis module is used to analyze and process the passing time of all road sections from the starting point to the ending point of the vehicle based on the high-precision map, the vehicle real-time positioning data and the vehicle trip data to generate a vehicle trip range road section passing time data set; The lane passing time analysis module is used to analyze and process the passing time of each lane of all road sections within a set range of the road section where the vehicle is currently located based on the high-precision map, the vehicle real-time positioning data and the vehicle detection data to generate a vehicle nearby road section lane passing time data set; The trip route planning module is used to analyze a first number of road section combinations with the shortest passing time from the starting point to the ending point of the vehicle based on the vehicle trip range road section passing time data set to generate vehicle trip route preliminary planning data; and is also used to analyze a second number of road section and lane combinations with the shortest passing time within the set range of the vehicle based on the vehicle nearby road section lane passing time data set to generate vehicle nearby route optimization data, and update the current vehicle trip route preliminary planning data based on the vehicle nearby route optimization data selected by the user.

[0006] Further, the road section passing time analysis module generates a vehicle trip range road section passing time data set, including the following steps: Divide the high-precision map into road sections to generate a plurality of high-precision road section maps; Based on the position corresponding to the vehicle real-time positioning data, a virtual vehicle data point is constructed on the corresponding high-precision road section map; Based on the position change of the virtual vehicle data points on the high-precision road segment map, the average speed of the virtual vehicle data points with the latest setting time length on each high-precision road segment map is calculated and processed to generate road segment vehicle latest average speed data; Based on the high-precision road segment map and the road segment vehicle latest average speed data, the time length of the vehicle passing through the high-precision road segment map is calculated and processed to generate road segment latest passing time length data; The starting point and the ending point in the vehicle trip data, and both ends of all high-precision road segment maps are taken as nodes, the corresponding road segment of the high-precision road segment map, and the connection between the starting point or the ending point on the road segment and the two nodes of the road segment are taken as edges to construct a trip route graph set; In the trip route graph set, all high-precision road segment maps corresponding to all paths with a path length less than a set multiple of the straight-line distance from the starting point to the ending point are searched to generate a trip road segment path set; Based on the road segment latest passing time length data and the corresponding trip road segment path in the trip road segment path set, the passing time length of all trip road segment paths is calculated and processed respectively to generate a vehicle trip range road segment passing time length data set.

[0007] Further, the generation of the trip road segment path set includes the following steps: a. Initialize the number of path search ants, pheromone factor, heuristic factor, pheromone evaporation coefficient, pheromone constant, and maximum iteration number; b. Calculate and process the heuristic information of all edges in the trip route graph set, and initialize the pheromone matrix, wherein the heuristic information of the edge is equal to the reciprocal of the distance between the two nodes of the edge, and the pheromone matrix is generally initialized to a small constant such as 0.1 on all edges; c. For each path search ant, place the path search ant in the node where the starting point is located, and the path search ant selects the next node of the path based on the state transition probability rule until the path search ant reaches the node where the ending point is located to obtain a trip road segment path; d. Calculate the length of the trip road segment path of all path search ants to obtain trip road segment path length data, and calculate a set multiple of the straight-line distance from the starting point to the ending point to obtain a path maximum value; e. Determine whether the trip road segment path length data is less than or equal to the path maximum value, if yes, add the trip road segment path length data and the corresponding trip road segment path to the constructed trip road segment path set; if not, discard; f. Reduce the pheromone of all edges by a set proportion; g. Add pheromone increment to the pheromone of all edges corresponding to the travel segments generated in this iteration in the travel segment path set, where the pheromone increment = pheromone constant / travel segment path length data; h. Determine if the maximum number of iterations has been reached. If yes, output the set of travel segments; otherwise, return to step c.

[0008] Furthermore, the lane travel time analysis module generates a set of lane travel time data for road sections near the vehicle, including the following steps: The high-precision map is divided into road segments to generate several high-precision road segment lane maps; Based on vehicle detection data, the vehicle's lane is located, and vehicle lane data is generated; Based on the real-time vehicle positioning data and the vehicle lane data, virtual vehicle data points are constructed on the corresponding lanes on the high-precision road segment lane map. Based on the position changes of the virtual vehicle data points on the high-precision road segment lane map, the average speed of the virtual vehicle data points of the most recently set time in each lane on each high-precision road segment lane map is calculated and processed to generate the most recent average speed data of vehicles in the road segment lane. Based on its own vehicle's real-time positioning data and vehicle detection data, the system performs positioning analysis on the current road segment and lane of the vehicle, and generates the current road segment and lane data of the vehicle. The system searches and collects the most recent average speed data of vehicles in the road segments and lanes within the set range of the current road segment lane data of the vehicle, and generates a set of road segment lane travel time data near the vehicle.

[0009] Furthermore, the route planning module generates preliminary route planning data for the vehicle, including the following steps: Based on traffic light data, travel route set, and vehicle travel range road segment passage time data set, the vehicle travel range road segment passage time data corresponding to all travel route paths in the travel route set are summed with the waiting time required to pass through traffic lights to generate a total travel route path time data set; Sort the total duration data of the trip segments and routes in the dataset in ascending order of duration; Extract the travel segment paths corresponding to the travel time data of the first number of vehicle travel range road segments from the set of travel segment paths and the total travel time data set of the arranged travel segment paths, and generate preliminary planning data for vehicle travel routes.

[0010] Furthermore, the route planning module generates optimized route data near the vehicle, including the following steps: Based on the path search ants, with the vehicle's current position as the new starting point, any point on all edges corresponding to the preliminary planning data of the current vehicle's route within the set range of the current road segment where the vehicle is currently located is the new ending point. Search for all paths whose path length is less than a set multiple of the straight-line distance from the new starting point to the new ending point, and generate an optimized path set near the vehicle. Based on the data set of traffic lights and lane passage time of road segments near vehicles, the passage time of each optimized path near vehicles and the sum of waiting time at traffic lights are calculated to generate a data set of passage time of optimized paths near vehicles. The optimized routes near the vehicle are arranged in ascending order of duration, and the optimized routes near the vehicle corresponding to the duration data of the optimized routes near the vehicle are selected first, and the optimized routes near the vehicle are generated.

[0011] Furthermore, the system also includes a route selection module, which is used by the user to select preliminary planning data for the vehicle's journey route and optimized route data near the vehicle, including the following steps; The user selects one of the generated preliminary vehicle route planning data as the current preliminary vehicle route planning data. Determine whether the absolute value of the difference between the shortest path in the optimized path passage time data set near the vehicle and the current path is greater than the set path optimization threshold; If so, notify the user to select one route optimization data point from all vehicle-side route optimization data to update the current preliminary route planning data.

[0012] 1. Compared with the prior art, the present invention provides an intelligent transportation system based on big data processing. By setting up a high-precision map module, a traffic signal module, a vehicle positioning data module, a vehicle detection data module, a trip data module, a road segment travel time analysis module, and a trip route planning module, it can obtain the travel speed and travel time of each road segment on the map based on big data, and automatically plan the shortest routes for users to choose from based on its own starting point and destination, so as to ensure the user's travel efficiency.

[0013] 2. Compared with the prior art, the present invention provides an intelligent transportation system based on big data processing. By setting up a lane travel time analysis module in conjunction with other modules, it can analyze the travel speed and travel time of each lane on each road segment. In this way, it can automatically plan several lanes with shorter travel times and detour routes based on the nearby road conditions when individual lanes are congested, thereby further improving traffic efficiency. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0015] Figure 1 This is a system structure block diagram provided for an embodiment of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0017] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0018] Exemplary embodiments will be described more fully below with reference to the accompanying drawings; however, these exemplary embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will enable those skilled in the art to fully understand the scope of this disclosure.

[0019] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0020] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded.

[0022] The embodiments described herein can be described with reference to plan views and / or cross-sectional views using the ideal schematic diagrams of this disclosure. Therefore, the example illustrations can be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to those shown in the drawings, but include modifications to configurations formed based on manufacturing processes. Therefore, the areas illustrated in the drawings are schematic in nature, and the shapes of the areas shown in the figures illustrate specific shapes of areas of an element, but are not intended to be limiting.

[0023] Please see Figure 1 A smart transportation system based on big data processing includes a high-precision map module, a traffic signal module, a vehicle positioning data module, a vehicle detection data module, a trip data module, a road segment travel time analysis module, a lane travel time analysis module, and a trip route planning module. The high-precision map module is used to store high-precision maps, which include not only road topology but also detailed information such as lane lines, slope, curvature, traffic signs, traffic light locations, and scale. The traffic signal module is used to collect traffic light data, that is, to collect the phase and timing information of traffic lights. It can acquire traffic light data through V2X (Vehicle to Everything) technology. The vehicle positioning data module is used to collect real-time vehicle positioning data, which can be collected through vehicle GPS, Beidou module or smartphone, and includes information such as latitude and longitude, speed, heading angle, and timestamp. Furthermore, when collecting real-time vehicle positioning data, the data source needs to be encrypted or obscured to prevent the disclosure of the privacy of the vehicle owner from whom the real-time vehicle positioning data is sourced. The vehicle detection data module is used to collect vehicle detection data through radar or vision sensors on the vehicle. The radar and vision sensors can include millimeter-wave radar, lidar, infrared cameras, high-definition cameras, etc. The vehicle detection data can more accurately locate the specific lane of the vehicle on the road segment; it can also identify the type and speed of vehicles in the vicinity of the vehicle to determine whether the vehicle is moving slowly; the high-definition camera can also identify road signs and traffic management facilities, such as traffic cones, water barriers, road maintenance warning signs, etc. The trip data module is used to obtain vehicle origin and destination information and generate vehicle trip data; The road segment travel time analysis module uses high-precision maps, real-time vehicle location data, and vehicle travel data to analyze and process the travel time of all road segments from the origin to the destination, generating a data set of road segment travel time within the vehicle's travel range. This includes the following steps: (1) Divide the high-precision map into road segments and generate several high-precision road segment maps; (2) Based on the location corresponding to the real-time vehicle positioning data, construct virtual vehicle data points on the corresponding high-precision road segment map; (3) Based on the position change of virtual vehicle data points on the high-precision road segment map, calculate and process the average speed of the virtual vehicle data points with the most recent set time on each high-precision road segment map to generate the most recent average speed data of vehicles on the road segment. (4) Based on the high-precision road segment map and the most recent average speed data of vehicles on the road segment, calculate and process the time taken for vehicles to pass through the high-precision road segment map to generate the most recent passage time data of the road segment; (5) Take the starting point and ending point in the vehicle trip data, as well as the two ends of all high-precision road segment maps, as nodes, the road segments corresponding to the high-precision road segment maps, and the lines connecting the starting point or ending point on the road segment to the two nodes of the road segment as edges, and construct a trip route map set. (6) Search the trip route map set for all paths whose length is less than a multiple of the set straight-line distance from the start point to the end point, and generate a trip route map set, including the following steps: a. Initialize the number of ants used for pathfinding, pheromone factor, heuristic factor, pheromone evaporation coefficient, pheromone constant, and maximum number of iterations; b. Calculate and process the heuristic information of all edges in the route map set, and initialize the pheromone matrix. The heuristic information of an edge is equal to the reciprocal of the distance between the two nodes of the edge. The pheromone matrix is ​​generally initialized to a small constant such as 0.1 for all edges. c. For each pathfinder ant, place the pathfinder ant at the starting node. The pathfinder ant selects the next node of the path based on the state transition probability rule until the pathfinder ant reaches the ending node, thus obtaining the travel route path. d. Calculate the length of the travel segments of all path-searching ants, obtain the travel segment length data, and calculate the set multiple of the straight-line distance from the starting point to the end point to obtain the maximum path value; e. Determine if the route segment length data is less than or equal to the maximum path value. If yes, add the route segment length data and the corresponding route segment path to the constructed route segment path set; otherwise, discard it. f. Reduce the pheromone levels of all edges according to the set ratio; g. Add pheromone increment to the pheromone of all edges corresponding to the travel segments generated in this iteration in the travel segment path set, where the pheromone increment = pheromone constant / travel segment path length data; h. Determine if the maximum number of iterations has been reached. If yes, output the set of travel segments; otherwise, return to step c.

[0024] (7) Based on the most recent passage time data of road segments and the corresponding travel road segment paths in the travel road segment path set, calculate and process the passage time of all travel road segment paths respectively to generate a data set of road segment passage time data within the vehicle travel range.

[0025] The lane travel time analysis module is used to analyze and process the travel time of each lane on all road segments within a set range of the vehicle's current location, based on high-precision maps, real-time vehicle positioning data, and vehicle detection data. This generates a dataset of lane travel time data for road segments near the vehicle, including the following steps: (1) Divide the high-precision map into road segments and generate several high-precision road segment lane maps; (2) Based on vehicle detection data, locate the lane where the vehicle is located and generate vehicle lane data; In vehicle lane location based on vehicle detection data, millimeter-wave radar can accurately measure the straight-line distance between the target and the radar by calculating the time difference (ToF) between electromagnetic wave transmission and reception. It can also directly and accurately measure the target's relative velocity in the radar's radial direction using the Doppler effect. Through DBF (Digital Beamforming) or MIMO (Multiple-Input Multiple-Output) technology, it can calculate the phase difference of the target echo arriving at different antenna elements to estimate the target's angle. Then, by tracking stationary known objects (such as streetlights and signs) in a high-precision map as reference points, it indirectly helps correct the target's pose and determine the vehicle's lane. LiDAR can use ToF, iterative nearest-point algorithms, and point cloud map matching techniques to correct the location and determine the vehicle's lane.

[0026] (3) Based on the location and lane data corresponding to the real-time vehicle positioning data, construct virtual vehicle data points on the corresponding lanes on the lane map of the corresponding high-precision road section; (4) Based on the position change of virtual vehicle data points on the high-precision road segment lane map, calculate and process the average speed of the virtual vehicle data points of each lane on each high-precision road segment lane map for the most recent set time, and generate the most recent average speed data of vehicles in the road segment lane. (5) Based on the real-time vehicle positioning data and vehicle detection data of its own vehicle, the vehicle's current road segment and lane are located and analyzed to generate the vehicle's current road segment and lane data. (6) Search and collect the most recent average speed data of vehicles in the road segment within the setting range of the current road segment lane data of the vehicle, and generate a set of road segment lane passage time data near the vehicle.

[0027] The route planning module is used to analyze a set of road segment combinations that minimize the travel time from the origin to the destination of a vehicle, based on a data set of travel time data for road segments within the vehicle's travel range. This analysis generates preliminary route planning data for the vehicle, including the following steps: (1) Based on traffic light data, travel route set and vehicle travel range road segment passage time data set, sum the vehicle travel range road segment passage time data corresponding to all travel route paths in the travel route set and the waiting time required to pass through traffic lights to generate a total travel route path time data set; (2) Sort the total duration data of the travel segment path in the data set in ascending order according to the length of the travel segment path; (3) Extract the travel segment paths from the travel segment path set and set the travel segment path total time data set before the first number of vehicle travel range road segment travel time data to generate preliminary vehicle travel route planning data.

[0028] The route planning module is also used to analyze the second number of road segments and lane combinations with the shortest travel time within the vehicle's set range, based on the data set of lane travel time data of road segments near the vehicle, to generate optimized route data near the vehicle, and to update the current preliminary route planning data based on the optimized route data near the vehicle selected by the user, including the following steps: (1) Based on path search ants, take the current position of the vehicle as the new starting point, and any point on all edges corresponding to the preliminary planning data of the current vehicle's route within the set range of the current road segment where the vehicle is currently located as the new endpoint. Search for all paths whose path length is less than the set multiple of the straight-line distance from the new starting point to the new endpoint, and generate a set of optimized paths near the vehicle. (2) Based on the number of traffic lights and the data set of lane passage time of road sections near vehicles, calculate the sum of passage time and waiting time of passing traffic lights for each optimized path near vehicles in the optimized path near vehicle set, and generate a data set of passage time of optimized path near vehicles. (3) Arrange the vehicle-near optimized path passage time data set in ascending order of duration, and select the vehicle-near optimized path corresponding to the second number of vehicle-near optimized path passage time data to generate vehicle-near route optimization data.

[0029] This step analyzes the traffic speed and transit time of each lane on each road segment. Based on the congestion in individual lanes nearby, it can automatically plan several shorter driving and detour routes according to the surrounding traffic conditions. For example, if the red light for going straight and turning left is long, and there are too many vehicles waiting to turn left, and a left turn is still needed, the analysis shows that turning right and then going straight and making a U-turn to return to the original planned route takes less time than waiting directly in the left-turn lane. In this case, the user can be advised to turn right first and then make a U-turn to further improve traffic efficiency.

[0030] The system also includes a route selection module, which allows users to select preliminary route planning data and optimized route data near the vehicle, including the following steps; (1) The user selects one of the generated preliminary vehicle route planning data as the current preliminary vehicle route planning data; (2) Determine whether the absolute value of the difference between the shortest path in the optimized path passage time data set near the vehicle and the current path is greater than the set path optimization threshold; (3) If so, the user is notified to select one vehicle-near route optimization data from all vehicle-near route optimization data to update the current preliminary vehicle route planning data. The system defaults to using the vehicle-near route optimization data with the shortest duration to update the current preliminary vehicle route planning data. If the user does not make a selection within the specified time, the system's default selection will be used.

[0031] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An intelligent transportation system based on big data processing, characterized in that, It includes a high-precision map module, a traffic signal module, a vehicle positioning data module, a vehicle detection data module, a trip data module, a road segment travel time analysis module, a lane travel time analysis module, and a trip route planning module; The high-precision map module is used to store high-precision maps; The traffic signal module is used to collect traffic light data; The vehicle positioning data module is used to collect real-time vehicle positioning data. The vehicle detection data module is used to collect vehicle detection data through radar or vision sensors on the vehicle; The trip data module is used to obtain vehicle origin and destination information and generate vehicle trip data; The road segment travel time analysis module is used to analyze and process the travel time of all road segments from the origin to the destination of the vehicle using the high-precision map, real-time vehicle positioning data and vehicle travel data, and generate a set of road segment travel time data within the vehicle's travel range. The lane travel time analysis module is used to analyze and process the travel time of each lane in all road segments within the set range of the current road segment of the vehicle, based on the high-precision map, real-time vehicle positioning data and vehicle detection data, and generate a set of lane travel time data for road segments near the vehicle. The route planning module is used to analyze a first number of road segment combinations with the shortest travel time from the origin to the destination based on the data set of travel time of road segments within the vehicle's travel range, and generate preliminary route planning data for the vehicle; it is also used to analyze a second number of road segments and lane combinations with the shortest travel time within the vehicle's set range based on the data set of travel time of lanes near the vehicle, and generate optimized route data near the vehicle.

2. The intelligent transportation system based on big data processing according to claim 1, characterized in that, The road segment travel time analysis module generates a data set of road segment travel time within the vehicle's travel range, including the following steps: The high-precision map is divided into road segments to generate several high-precision road segment maps; Based on the location corresponding to the real-time vehicle positioning data, virtual vehicle data points are constructed on the corresponding high-precision road segment map; Based on the position changes of the virtual vehicle data points on the high-precision road segment map, the average speed of the virtual vehicle data points with the most recent set duration on each high-precision road segment map is calculated and processed to generate the most recent average speed data of vehicles on the road segment. Based on high-precision road segment maps and the most recent average speed data of vehicles on the road segments, the time taken for vehicles to pass through the high-precision road segment maps is calculated and processed to generate the most recent passage time data of the road segments. The starting point and ending point in the vehicle trip data, as well as the two ends of all high-precision road segment maps, are used as nodes. The road segments corresponding to the high-precision road segment maps, and the lines connecting the starting point or ending point on the road segment to the two nodes of the road segment are used as edges to construct a trip route map set. Search the set of travel route maps for all paths whose length is less than a multiple of the set straight-line distance from the start point to the end point, and generate a set of travel route segments. Based on the most recent passage time data of road segments and the corresponding travel road segment paths in the travel road segment path set, the passage time of all travel road segment paths is calculated and processed to generate a data set of road segment passage time within the vehicle's travel range.

3. The intelligent transportation system based on big data processing according to claim 2, characterized in that, The process of generating the set of travel route segments includes the following steps: a. Initialize the number of ants used for pathfinding, pheromone factor, heuristic factor, pheromone evaporation coefficient, pheromone constant, and maximum number of iterations; b. Calculate and process the heuristic information of all edges in the trip route map set, and initialize the pheromone matrix; c. For each pathfinder ant, place the pathfinder ant at the starting node. The pathfinder ant selects the next node of the path based on the state transition probability rule until the pathfinder ant reaches the ending node, thus obtaining the travel route path. d. Calculate the length of the travel segments of all path-searching ants, obtain the travel segment length data, and calculate the set multiple of the straight-line distance from the starting point to the end point to obtain the maximum path value; e. Determine whether the path length data of the travel segment is less than or equal to the maximum path value. If so, add the path length data of the travel segment and the corresponding travel segment path to the constructed travel segment path set. f. Reduce the pheromone levels of all edges according to the set ratio; g. Add pheromone increment to the pheromone of all edges corresponding to the travel segments generated in this iteration in the travel segment path set; h. Determine if the maximum number of iterations has been reached. If yes, output the set of travel segments; otherwise, return to step c.

4. The intelligent transportation system based on big data processing according to claim 1, characterized in that, The lane passage time analysis module generates a set of lane passage time data for road sections near the vehicle, including the following steps: The high-precision map is divided into road segments to generate several high-precision road segment lane maps; Based on vehicle detection data, the vehicle's lane is located, and vehicle lane data is generated; Based on the real-time vehicle positioning data and the vehicle lane data, virtual vehicle data points are constructed on the corresponding lanes on the high-precision road segment lane map. Based on the position changes of the virtual vehicle data points on the high-precision road segment lane map, the average speed of the virtual vehicle data points of the most recently set time in each lane on each high-precision road segment lane map is calculated and processed to generate the most recent average speed data of vehicles in the road segment lane. Based on its own vehicle's real-time positioning data and vehicle detection data, the system performs positioning analysis on the current road segment and lane of the vehicle, and generates the current road segment and lane data of the vehicle. The system searches and collects the most recent average speed data of vehicles in the road segments and lanes within the set range of the current road segment lane data of the vehicle, and generates a set of road segment lane travel time data near the vehicle.

5. The intelligent transportation system based on big data processing according to claim 2, characterized in that, The route planning module generates preliminary route planning data for the vehicle, including the following steps: Based on traffic light data, travel route set, and vehicle travel range road segment passage time data set, the vehicle travel range road segment passage time data corresponding to all travel route paths in the travel route set are summed with the waiting time required to pass through traffic lights to generate a total travel route path time data set; Sort the total duration data of the trip segments and routes in the dataset in ascending order of duration; Extract the travel segment paths corresponding to the travel time data of the first number of vehicle travel range road segments from the set of travel segment paths and the total travel time data set of the arranged travel segment paths, and generate preliminary planning data for vehicle travel routes.

6. The intelligent transportation system based on big data processing according to claim 3, characterized in that, The route planning module generates optimized route data near the vehicle, including the following steps: Based on the path search ants, with the vehicle's current position as the new starting point, any point on all edges corresponding to the preliminary planning data of the current vehicle's route within the set range of the current road segment where the vehicle is currently located is the new ending point. Search for all paths whose path length is less than a set multiple of the straight-line distance from the new starting point to the new ending point, and generate an optimized path set near the vehicle. Based on the data set of traffic lights and lane passage time of road segments near vehicles, the passage time of each optimized path near vehicles and the sum of waiting time at traffic lights are calculated to generate a data set of passage time of optimized paths near vehicles. The optimized routes near the vehicle are arranged in ascending order of duration, and the optimized routes near the vehicle corresponding to the duration data of the optimized routes near the vehicle are selected first, and the optimized routes near the vehicle are generated.

7. The intelligent transportation system based on big data processing according to claim 6, characterized in that, The system also includes a route selection module, which is used by users to select preliminary planning data for vehicle travel routes and optimized route data near the vehicle, including the following steps; The user selects one of the generated preliminary vehicle route planning data as the current preliminary vehicle route planning data. Determine whether the absolute value of the difference between the shortest path in the optimized path passage time data set near the vehicle and the current path is greater than the set path optimization threshold; If so, notify the user to select one route optimization data point from all vehicle-side route optimization data to update the current preliminary route planning data.

Images