Highway intelligent transportation service platform and method based on big data fusion

Abstract

The application provides a highway intelligent traffic service platform based on big data fusion and a method thereof, and relates to the technical field of big data, wherein the platform comprises: a traffic big data fusion module, which performs dynamic traffic big data fusion on a future travel section of a target vehicle to obtain fused traffic big data; and a traffic service module, which is used for performing traffic service on the target vehicle based on the fused traffic big data. The application performs dynamic traffic big data fusion on a future travel section of a target vehicle, performs traffic service on the target vehicle based on the fused traffic big data, can meet the interactive demand of vehicles and the surrounding environment which is increasingly diversified and dynamic, and improves the safety and smoothness of the travel of the target vehicle, and is very intelligent.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a highway intelligent transportation service platform and method based on big data fusion. Background Technology

[0002] Currently, with the rapid development of intelligent connected vehicles (V2X technology) and autonomous driving technology, the interaction needs between vehicles and their surroundings have become more diverse and dynamic. This is not limited to traditional road traffic and traffic signal control, but also includes real-time traffic information acquisition, intelligent navigation, environmental perception, autonomous driving decision support, vehicle-to-vehicle collaborative operations, and vehicle-to-infrastructure interaction. For example, intelligent vehicles not only need to rely on traditional traffic lights and road signs for guidance, but also need to exchange information with road infrastructure, traffic management centers, other vehicles, and pedestrians to achieve a safer and smoother travel experience. In addition, intelligent vehicles also need to dynamically adjust their routes and speeds based on real-time traffic flow, weather conditions, traffic accidents, and other information.

[0003] Therefore, traditional traffic service methods, such as manual traffic control, setting up single road traffic facilities, and static map navigation, can no longer meet these growing demands. Summary of the Invention

[0004] One of the objectives of this invention is to provide a highway intelligent transportation service platform based on big data fusion. This platform dynamically integrates traffic big data for the future travel routes of target vehicles. Based on the integrated traffic big data, it provides traffic services to target vehicles, which can meet the increasingly diverse and dynamic interaction needs between vehicles and their surrounding environment, improve the safety and smoothness of target vehicle travel, and is highly intelligent.

[0005] The intelligent transportation service platform for highways based on big data fusion provided in this embodiment of the invention includes:

[0006] The traffic big data fusion module is used to dynamically fuse traffic big data for the future travel routes of target vehicles to obtain fused traffic big data.

[0007] The traffic service module is used to provide traffic services to target vehicles based on integrated traffic big data.

[0008] Optionally, the traffic big data fusion module performs dynamic traffic big data fusion on the future travel routes of the target vehicle to obtain fused traffic big data, including:

[0009] Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms.

[0010] The big data to be integrated is processed to obtain integrated transportation big data.

[0011] Optionally, the traffic service module provides traffic services to the target vehicle based on integrated traffic big data, including:

[0012] Based on the digital twin engine, a digital twin model is constructed using integrated transportation big data;

[0013] Obtain the traffic status of the target vehicle;

[0014] Based on the traffic service AI model, traffic service strategies are determined according to traffic conditions and digital twin models;

[0015] Based on traffic service strategies, traffic services are provided to target vehicles.

[0016] Optionally, the traffic service module provides traffic services to the target vehicle based on integrated traffic big data, including:

[0017] The candidate areas of interest are determined from multiple scenic spots that the target vehicle will pass through within a preset time period in the future; wherein, the candidate areas of interest first enter the field of vision of at least one seated passenger seat in the target vehicle and then enter the field of vision of at least another seated passenger seat in the target vehicle, or simultaneously enter the field of vision of at least two seated passenger seats in the target vehicle within the preset time period in the future; and, there is at least one standard association relationship between the candidate areas of interest and the current destination of the target vehicle.

[0018] Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively.

[0019] Identify target data related to potential areas of interest from integrated transportation big data;

[0020] Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future;

[0021] When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers already seated at the target location are given joint guidance to select areas of interest.

[0022] Optionally, the traffic service module generates a joint guidance map based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, including:

[0023] Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located;

[0024] Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold;

[0025] The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set.

[0026] Each target dataset is assigned to the guide path points in the target path point set in descending order of importance;

[0027] The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map;

[0028] Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

[0029] The intelligent transportation service method for highways based on big data fusion provided in this embodiment of the invention includes:

[0030] Dynamic traffic big data is integrated to obtain integrated traffic big data for the future travel routes of target vehicles.

[0031] Based on the integration of traffic big data, traffic services are provided to target vehicles.

[0032] Optionally, the dynamic traffic big data fusion for the future travel routes of the target vehicle to obtain fused traffic big data includes:

[0033] Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms.

[0034] The big data to be integrated is processed to obtain integrated transportation big data.

[0035] Optionally, the provision of traffic services to target vehicles based on integrated traffic big data includes:

[0036] Based on the digital twin engine, a digital twin model is constructed using integrated transportation big data;

[0037] Obtain the traffic status of the target vehicle;

[0038] Based on the traffic service AI model, traffic service strategies are determined according to traffic conditions and digital twin models;

[0039] Based on traffic service strategies, traffic services are provided to target vehicles.

[0040] Optionally, the provision of traffic services to target vehicles based on integrated traffic big data includes:

[0041] The candidate areas of interest are determined from multiple scenic spots that the target vehicle will pass through within a preset time period in the future; wherein, the candidate areas of interest first enter the field of vision of at least one seated passenger seat in the target vehicle and then enter the field of vision of at least another seated passenger seat in the target vehicle, or simultaneously enter the field of vision of at least two seated passenger seats in the target vehicle within the preset time period in the future; and, there is at least one standard association relationship between the candidate areas of interest and the current destination of the target vehicle.

[0042] Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively.

[0043] Identify target data related to potential areas of interest from integrated transportation big data;

[0044] Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future;

[0045] When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers already seated at the target location are given joint guidance to select areas of interest.

[0046] Optionally, the step of generating a joint guidance map based on the first relative positional relationship between each pair of target occupied passenger locations, target data, and target local road segments includes:

[0047] Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located;

[0048] Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold;

[0049] The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set.

[0050] Each target dataset is assigned to the guide path points in the target path point set in descending order of importance;

[0051] The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map;

[0052] Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

[0053] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0055] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0056] Figure 1 This is a schematic diagram of a highway intelligent transportation service platform based on big data fusion in an embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram showing the field of vision of a seated passenger in an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram illustrating the process of determining the target local road segment in an embodiment of the present invention;

[0059] Figure 4 This is a schematic diagram of a highway intelligent transportation service method based on big data fusion in an embodiment of the present invention. Detailed Implementation

[0060] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0061] This invention provides a highway intelligent transportation service platform based on big data fusion, such as... Figure 1 As shown, it includes:

[0062] Traffic Big Data Fusion Module 1 dynamically fuses traffic big data for the future travel routes of target vehicles to obtain fused traffic big data.

[0063] Traffic service module 2 is used to provide traffic services to target vehicles based on integrated traffic big data.

[0064] Future travel routes can be obtained from the current navigation route on the target vehicle's navigation software. The integrated traffic big data includes at least: real-time traffic flow data, traffic incident and accident data, meteorological and environmental data, road infrastructure information, historical traffic data, public transportation data, and vehicle-to-everything (V2X) data. Based on this integrated traffic big data, traffic services can be provided to the target vehicle, such as: providing alerts about upcoming traffic conditions, accidents, and weather; providing more comprehensive route navigation, environmental perception, and autonomous driving decision support; and matching the target vehicle with accident vehicles that it can assist along its route.

[0065] This application integrates dynamic traffic big data on the future travel routes of the target vehicle. Based on the integrated traffic big data, traffic services are provided to the target vehicle, which can meet the increasingly diverse and dynamic interaction needs between the vehicle and the surrounding environment, improve the safety and smoothness of the target vehicle's travel, and is highly intelligent.

[0066] In one embodiment, the traffic big data fusion module performs dynamic traffic big data fusion on the future travel routes of the target vehicle to obtain fused traffic big data, including:

[0067] Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms.

[0068] The big data to be integrated is processed to obtain integrated transportation big data.

[0069] When performing dynamic traffic big data fusion, the first step is to acquire real-time big data related to the future travel routes of target vehicles from traffic big data platforms and traffic IoT platforms. This data is then processed to obtain fused traffic big data. The traffic big data platform integrates various traffic data sources, performs data storage, analysis, and decision support. The traffic IoT platform primarily relies on various intelligent devices distributed throughout roads (such as smart streetlights, traffic cameras, and vehicle-to-everything (V2X) devices) for physical layer data collection and transmits and processes data via the internet. Therefore, the required fused big data can be obtained from the traffic big data platform and the traffic IoT platform.

[0070] In one embodiment, the traffic service module provides traffic services to target vehicles based on integrated traffic big data, including:

[0071] Based on the digital twin engine, a digital twin model is constructed using integrated transportation big data;

[0072] Obtain the traffic status of the target vehicle;

[0073] Based on the traffic service AI model, traffic service strategies are determined according to traffic conditions and digital twin models;

[0074] Based on traffic service strategies, traffic services are provided to target vehicles.

[0075] A digital twin engine can be a platform providing digital twin technology services. Based on the integration of big data on transportation, it can build a digital twin model, which includes different traffic conditions for future travel routes. The target vehicle's traffic driving status includes at least: driving position, driver blind spots, etc. The traffic service AI model is an artificial intelligence model trained using a large amount of traffic service experience as training samples. It can decide how to provide traffic services to the target vehicle based on traffic conditions and the digital twin model, i.e., it determines the traffic service strategy. Finally, based on the traffic service strategy, traffic services are provided to the target vehicle.

[0076] This invention introduces a traffic service AI model, which is used to automatically provide traffic services to target vehicles, thereby improving the response speed of traffic services.

[0077] Narratives of attractions along the route are an indispensable function of modern transportation services, but current technology suffers from several significant drawbacks. Current systems typically play audio narration automatically as the vehicle approaches an attraction; however, this approach fails to effectively consider passengers' actual needs and interests. Most passengers are often unprepared or uninterested in certain attractions when they hear the narration. Therefore, many choose to turn off the audio narration, resulting in the system's underutilization. To improve passenger engagement and satisfaction, the system should more accurately determine the timing of narrations, pushing relevant content at the most appropriate moment based on passenger needs and driving conditions, thus ensuring passengers receive valuable information at the optimal time.

[0078] Furthermore, existing systems typically push voice prompts to both the driver and passengers simultaneously, neglecting the driver's specific needs while driving. Drivers require a high level of concentration to ensure safety, and any distraction can lead to inattention and increase driving risks. Therefore, the system should avoid pushing unnecessary voice content to the driver, ensuring that the driver can maintain optimal focus at all times and guaranteeing driving safety.

[0079] Therefore, to address the aforementioned issues, in one embodiment, the traffic service module provides traffic services to the target vehicle based on integrated traffic big data, including:

[0080] The candidate areas of interest are determined from multiple scenic spots that the target vehicle will pass through within a preset time period in the future; wherein, the candidate areas of interest first enter the field of vision of at least one seated passenger seat in the target vehicle and then enter the field of vision of at least another seated passenger seat in the target vehicle, or simultaneously enter the field of vision of at least two seated passenger seats in the target vehicle within the preset time period in the future; and, there is at least one standard association relationship between the candidate areas of interest and the current destination of the target vehicle.

[0081] Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively.

[0082] Identify target data related to potential areas of interest from integrated transportation big data;

[0083] Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future;

[0084] When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers already seated at the target location are given joint guidance to select areas of interest.

[0085] The preset time can be 200 seconds. When determining the multiple scenic areas the target vehicle will pass through within the preset time, this can be based on the future route and the current average speed. "Seated seats" refers to the seats in the target vehicle where passengers are currently seated. The field of vision of a passenger seat is the range of vision when a passenger is sitting in a normal riding posture. Figure 2 As shown, taking a four-seater car as an example, the field of vision of the passenger seat A1 in the first row is the range of A2 (including the area outside the windshield and the area outside the right-hand window), the field of vision of the passenger seat B1 on the left side of the second row is the range of B2 (including the area outside the left-hand window), and the field of vision of the passenger seat C1 on the right side of the second row is the range of C2 (including the area outside the right-hand window).

[0086] The constraint that a candidate area of ​​interest must first enter the field of view of at least one occupied seat in the target vehicle within a preset future time, and then enter the field of view of at least one other occupied seat in the target vehicle, or simultaneously enter the field of view of at least two occupied seats in the target vehicle, ensures that multiple passengers in the target vehicle can view the candidate area of ​​interest sequentially or simultaneously within a preset future time. In this case, the candidate area of ​​interest has the value of introducing and prompting passengers.

[0087] Standard association refers to the association between the current destination and the candidate area of ​​interest, which gives the destination value in introducing and prompting passengers. Examples of standard association include: the current destination and the candidate area of ​​interest being similar types of attractions; the current destination and the candidate area of ​​interest being close in distance; and historically, other vehicles traveling to the current destination often first visit the candidate area of ​​interest. Setting the constraint that there must be at least one standard association between the candidate area of ​​interest and the target vehicle's current destination further enhances the candidate area of ​​interest's value in introducing and prompting passengers.

[0088] When determining the target local road segment, such as Figure 3 As shown, region D is the candidate region of interest, waypoint E is the starting point of the future travel segment, waypoint F is the earliest waypoint from which the candidate region of interest enters the field of vision of already seated passengers (the earliest waypoint the target vehicle will travel to when the candidate region of interest is visible from the field of vision of already seated passengers), and waypoint G is the latest waypoint from which the candidate region of interest enters the field of vision of already seated passengers (the latest waypoint the target vehicle will travel to when the candidate region of interest is visible from the field of vision of already seated passengers). The local path segment between waypoint E and waypoint G is then designated as the target local road segment. This determined target local road segment is most suitable for joint guidance to passengers when selecting candidate regions of interest.

[0089] The target data for identifying candidate regions of interest in the integrated traffic big data should include at least the following: the number of vehicles currently heading to the candidate regions of interest, the number of vehicles that have historically arrived at but not left the candidate regions of interest, the routes taken by vehicles from their current location to the candidate regions of interest, introductory information about the candidate regions of interest, and the relative positional relationship between the candidate regions of interest and the current location of the vehicles.

[0090] The joint guidance map can silently adapt to the first relative positional relationship between each pair of seats already occupied by the target passengers, and provide joint guidance to passengers in the target seats to select areas of interest.

[0091] Finally, as the target vehicle travels along the target section of road, based on the joint guidance map, passengers already seated are given joint guidance to select potential areas of interest. Passengers can then discuss and make their final selection under this guidance. After selection, the vehicle's system will automatically plan and change its route to the selected area of ​​interest.

[0092] This invention sets constraints for determining the candidate area of ​​interest based on the field of vision between the candidate area of ​​interest and the already occupied seats in the target vehicle, and the existence of at least one standard correlation between the candidate area of ​​interest and the current destination of the target vehicle. Based on this, it accurately selects candidate areas of interest with value for introducing and prompting passengers from multiple scenic areas that the target vehicle will pass through within a preset future timeframe. It uses the starting point of the future travel segment and the latest path point within the future travel segment from which the candidate area of ​​interest enters the field of vision of the already occupied seats as the beginning and end of the target local road segment to accurately determine the most suitable target local road segment for joint guidance to passengers in selecting candidate areas of interest. Then, a joint guidance map is generated. When the target vehicle… When a vehicle is traveling along a target section of road, based on a joint guidance map, passengers already seated in the target area are given joint guidance to select potential areas of interest. This joint guidance to passengers in the target vehicle at the most appropriate time avoids direct rejection due to unpreparedness, thus improving passenger participation and satisfaction. It ensures that passengers receive valuable information at the best time. The joint guidance map can silently adapt to the first relative positional relationship between each pair of passengers already seated in the target area, providing joint guidance to passengers already seated in the target area to select potential areas of interest. This fully ensures that the driver of the target vehicle is not affected, improves their concentration, and ensures driving safety.

[0093] Even after ensuring that joint guidance is provided only to passengers in the target vehicle and at appropriate times, a drawback remains: during vehicle operation, passengers' field of vision is significantly constrained by their seating position. For example, a passenger sitting in the second row on the left can only see the view outside their left-hand window most of the time. Consequently, passengers in different seats may look at different views before passing the desired area of ​​interest. Providing joint guidance to all passengers directly could disrupt their current travel experience and cause discomfort. Furthermore, when more than two passengers are traveling together, the relative seating arrangements become more complex, making it even more difficult to provide the most appropriate joint guidance.

[0094] Therefore, to address the aforementioned issues, in one embodiment, the traffic service module generates a joint guidance map based on the first relative positional relationship between each pair of target occupied passenger locations, target data, and target local road segments, including:

[0095] Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located;

[0096] Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold;

[0097] The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set.

[0098] Each target dataset is assigned to the guide path points in the target path point set in descending order of importance;

[0099] The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map;

[0100] Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

[0101] The first similarity threshold can be 80%; the second similarity threshold can be 85%. The first relative positional relationship and the second relative positional relationship refer to the relative orientation relationship between the two.

[0102] The constraint is set such that the second relative positional relationship between each guide waypoint and the candidate area of ​​interest is similar to the first relative positional relationship between at least one pair of target already occupied passenger positions, which exceeds a first similarity threshold, and the two pairs of target already occupied passenger positions have a joint field of vision in their respective fields of vision when the guide waypoint is reached. This makes it appropriate to provide joint guidance to the two passengers in the pair of target already occupied passenger positions when the target vehicle travels to the guide waypoint.

[0103] The distance threshold can be 15 meters. A constraint is set that the distance between any two guide path points in the target waypoint set does not exceed the distance threshold, ensuring that the guide path points in the target waypoint set are not too far apart. This allows for optimal joint guidance to multiple passengers as the target vehicles arrive at the guide path points in the target waypoint set sequentially.

[0104] The target data is divided into multiple target datasets according to their importance from highest to lowest. The total number of target datasets is the same as the number of guide waypoints in the target waypoint set, ensuring that each guide waypoint is assigned a corresponding target dataset. The importance of a target dataset refers to its value in helping passengers understand the candidate area of ​​interest. For example, if the target datasets consist of a dataset containing introductions to the candidate area of ​​interest and a dataset containing the number of vehicles that have historically arrived at but not left the candidate area of ​​interest, the former can help passengers understand the basic attractions, while the latter can help passengers understand the approximate number of people staying at the attractions. Therefore, the former is more important than the latter. Each target dataset is assigned to the guide waypoints in the target waypoint set in descending order of importance. The guide waypoints in the target waypoint set and their assigned target datasets are then mapped onto a virtual map to obtain a joint guidance map.

[0105] The virtual map is a traffic road map. After mapping each guide waypoint in the target waypoint set with its assigned target dataset, the virtual map displays the assigned target dataset next to each guide waypoint. First, the virtual map, showing the mapped guide waypoints and their assigned target datasets, is pushed to all passengers' smart terminals and on-vehicle screens. When the vehicle reaches a guide waypoint, the target dataset next to that guide waypoint flashes dynamically, prompting the two passengers already seated at that guide waypoint to view the flashing dataset. This allows different passengers on the vehicle to be guided to view the corresponding target dataset at appropriate times, avoiding the potential disruption to their journey by providing joint guidance to all passengers, thus improving the passenger experience and enhancing the applicability of joint guidance for more than two passengers.

[0106] This invention provides a method for intelligent transportation services for highways based on big data fusion, such as... Figure 4 As shown, it includes:

[0107] S1. Dynamically integrate traffic big data for the future travel routes of the target vehicle to obtain integrated traffic big data;

[0108] S2. Based on the integration of traffic big data, provide traffic services to target vehicles.

[0109] The dynamic traffic big data fusion for the future travel routes of the target vehicle yields fused traffic big data, including:

[0110] Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms.

[0111] The big data to be integrated is processed to obtain integrated transportation big data.

[0112] The provision of traffic services for target vehicles based on integrated traffic big data includes:

[0113] Based on the digital twin engine, a digital twin model is constructed using integrated transportation big data;

[0114] Obtain the traffic status of the target vehicle;

[0115] Based on the traffic service AI model, traffic service strategies are determined according to traffic conditions and digital twin models;

[0116] Based on traffic service strategies, traffic services are provided to target vehicles.

[0117] The provision of traffic services for target vehicles based on integrated traffic big data includes:

[0118] The candidate areas of interest are determined from multiple scenic spots that the target vehicle will pass through within a preset time period in the future; wherein, the candidate areas of interest first enter the field of vision of at least one seated passenger seat in the target vehicle and then enter the field of vision of at least another seated passenger seat in the target vehicle, or simultaneously enter the field of vision of at least two seated passenger seats in the target vehicle within the preset time period in the future; and, there is at least one standard association relationship between the candidate areas of interest and the current destination of the target vehicle.

[0119] Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively.

[0120] Identify target data related to potential areas of interest from integrated transportation big data;

[0121] Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future;

[0122] When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers already seated at the target location are given joint guidance to select areas of interest.

[0123] The process of generating a joint guidance map based on the first relative positional relationship between each pair of already occupied passenger locations, target data, and target local road segments includes:

[0124] Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located;

[0125] Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold;

[0126] The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set.

[0127] Each target dataset is assigned to the guide path points in the target path point set in descending order of importance;

[0128] The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map;

[0129] Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

[0130] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A highway intelligent transportation service platform based on big data fusion, characterized in that: include: The traffic big data fusion module is used to dynamically fuse traffic big data for the future travel routes of target vehicles to obtain fused traffic big data. The traffic service module is used to provide traffic services to target vehicles based on integrated traffic big data. The provision of traffic services to the target vehicle includes: The candidate areas of interest are determined from multiple scenic areas that the target vehicle will pass through within a predetermined timeframe. These candidate areas of interest must first be visible from at least one occupied seat in the target vehicle and then from at least another occupied seat, or simultaneously from at least two occupied seats. Furthermore, there must be at least one standard association between the candidate areas of interest and the target vehicle's current destination. This standard association refers to the association that demonstrates the value of the candidate areas of interest in providing information and guidance to passengers. Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively. Identify target data related to potential areas of interest from integrated transportation big data; Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future; When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers who are already seated in the target area are given joint guidance to select areas of interest. The generation of the joint guidance graph includes: Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located; Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold; The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set. Each target dataset is assigned to the guide path points in the target path point set in descending order of importance; The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map; Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

2. The intelligent transportation service platform for highways based on big data fusion as described in claim 1, characterized in that, The traffic big data fusion module dynamically fuses traffic big data for the future travel routes of the target vehicle to obtain fused traffic big data, including: Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms. The big data to be integrated is processed to obtain integrated transportation big data.

3. A highway intelligent transportation service method based on big data fusion, characterized in that: include: Dynamic traffic big data is integrated to obtain integrated traffic big data for the future travel routes of target vehicles. Based on the integration of big data on transportation, traffic services are provided to target vehicles. The provision of traffic services to the target vehicle includes: The candidate areas of interest are determined from multiple scenic areas that the target vehicle will pass through within a predetermined timeframe. These candidate areas of interest must first be visible from at least one occupied seat in the target vehicle and then from at least another occupied seat, or simultaneously from at least two occupied seats. Furthermore, there must be at least one standard association between the candidate areas of interest and the target vehicle's current destination. This standard association refers to the association that demonstrates the value of the candidate areas of interest in providing information and guidance to passengers. Target local road segments are determined from the future travel routes; the beginning and end of the target local road segment are the starting point of the future travel route and the latest path point from the selected area of ​​interest in the future travel route to the view of the seated passenger, respectively. Identify target data related to potential areas of interest from integrated transportation big data; Based on the first relative positional relationship between each pair of target passenger locations, target data, and target local road segments, a joint guidance map is generated; among them, the area of ​​interest will enter the field of view of the target passenger locations within a preset time period in the future; When the target vehicle travels along the target local road segment, based on the joint guidance map, passengers who are already seated in the target area are given joint guidance to select areas of interest. The generation of the joint guidance graph includes: Multiple guide path points are determined from the target local road segment; wherein, the second relative positional relationship between each guide path point and the candidate region of interest is similar to the first relative positional relationship between at least one pair of target already occupied locations exceeding a first similarity threshold, and the pair of target already occupied locations have a joint field of view in their respective fields of view when the guide path point is located; Determine the target path point set from each guide path point; wherein the driving distance between any two guide path points in the target path point set does not exceed a distance threshold; The target data is divided into multiple target datasets according to their importance from high to low; the total number of target datasets is the same as the number of guide path points in the target path point set. Each target dataset is assigned to the guide path points in the target path point set in descending order of importance; The guide path points in the target path point set and their respective assigned target datasets are mapped into a virtual map to obtain a joint guide map; Among them, the joint field of view is the part in the overlapping field of view of the two targets where the passengers are already seated that does not overlap with the field of view of the driver's position and other passengers already seated, and the third relative positional relationship between the local field of view corresponding to the two targets where the passengers are already seated is more similar to the second relative positional relationship than the second similarity threshold.

4. The intelligent transportation service method for highways based on big data fusion as described in claim 3, characterized in that, The dynamic traffic big data fusion for the future travel routes of the target vehicle yields fused traffic big data, including: Real-time big data related to the future travel routes of target vehicles is obtained from traffic big data platforms and traffic IoT platforms. The big data to be integrated is processed to obtain integrated transportation big data.

Images