Vehicle navigation path processing method and system based on online information

Abstract

The invention provides a vehicle navigation path processing method and system based on online information, and is applied to the technical field of data processing. The method comprises the following steps: processing meteorological data of target road environment information and target road map information in a preset time period to generate an environment influence factor; processing the real-time traffic information and the target road map information to generate a road influence factor; processing the vehicle state information, the target vehicle attribute information and the driving information of the target driver to generate a vehicle driving influence factor; processing the environment influence factor and the road influence factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; and processing the initial vehicle navigation path information based on the vehicle driving influence factor to generate target vehicle navigation path information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vehicle navigation path processing method and system based on online information. Background Art

[0002] Current vehicle navigation systems mainly rely on map data and real-time traffic information to plan routes for users. Map data provides basic road topology, geographic location and other information, while real-time traffic information helps avoid congested sections. However, this approach has many shortcomings. For example, the consideration of road environment information is not comprehensive enough, and the road conditions are judged only based on traffic flow, without fully considering factors such as road type (such as highways, urban roads, rural roads, etc.), road infrastructure (such as street lighting, road sign clarity) and road surrounding environment (such as topography, distribution of surrounding traffic facilities) on vehicle driving. When driving at night, if the road lighting conditions are poor, there may be safety hazards even if the traffic flow is not large, but it is difficult for existing navigation systems to effectively evaluate and prompt this.

[0003] Most existing navigation systems do not deeply combine the vehicle's own status information and the driver's driving characteristics when planning routes. Different vehicles have different types and attributes (such as power performance, size, load, etc.), and their adaptability to different road conditions is also different. For example, large trucks require more space and power when climbing and turning, while small cars are more flexible on narrow roads. At the same time, the driver's driving habits (such as acceleration and braking habits, whether the driving style is aggressive or conservative), driving ability (such as the ability to deal with emergencies, vehicle control proficiency) and emotional state will also significantly affect the safety and efficiency of vehicle driving, but these factors have not been fully taken into account in traditional navigation route planning, resulting in the planned route may not be suitable for the current vehicle and driver, and cannot provide personalized navigation services.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a vehicle navigation path processing method and system based on online information, which at least overcomes the problems existing in the prior art to a certain extent, generates initial path information based on the target vehicle navigation path generation model, combined with environmental and road influencing factors, including generating a set of candidate paths, analyzing path relevance and attributes (such as length, time, environmental friendliness, safety) and comprehensively evaluating to determine the initial path, while considering special circumstances and user preference optimization. The candidate path weights are then determined based on the vehicle driving influencing factors, and the path with the highest weight is selected as the target navigation path, and can be dynamically adjusted according to vehicle status, driver needs, road condition changes, etc. It provides vehicles with accurate navigation paths through complex calculations and analysis, and can also adapt to rules and environmental changes in different regions. It is highly practical and adaptable, and is expected to improve the accuracy, safety and efficiency of vehicle navigation.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a vehicle navigation path processing method based on online information is provided, including: obtaining vehicle status information, target vehicle attribute information, target driver's driving information, target road environment information, real-time traffic information, target road map information and meteorological data of the target road map information within a preset time period; processing the target road environment information and the meteorological data of the target road map information within the preset time period to generate an environmental impact factor; processing the real-time traffic information and the target road map information to generate a road impact factor; processing the vehicle status information, the target vehicle attribute information and the target driver's driving information to generate a vehicle driving impact factor; processing the environmental impact factor and the road impact factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; processing the initial vehicle navigation path information based on the vehicle driving impact factor to generate target vehicle navigation path information.

[0008] Another aspect of the present application is a vehicle navigation path processing device based on online information, characterized in that it includes: an acquisition module for acquiring vehicle status information, target vehicle attribute information, target driver's driving information, target road environment information, real-time traffic information, target road map information and meteorological data of the target road map information within a preset time period; a processing module for processing the target road environment information and the meteorological data of the target road map information within a preset time period to generate an environmental impact factor; processing the real-time traffic information and the target road map information to generate a road impact factor; processing the vehicle status information, the target vehicle attribute information and the target driver's driving information to generate a vehicle driving impact factor; processing the environmental impact factor and the road impact factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; processing the initial vehicle navigation path information based on the vehicle driving impact factor to generate target vehicle navigation path information.

[0009] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the vehicle navigation path processing method based on online information is implemented.

[0010] The present application provides a vehicle navigation path processing method and system based on online information, which generates initial path information based on the target vehicle navigation path generation model and environmental and road influencing factors, including generating a set of candidate paths, analyzing path relevance and attributes (such as length, time, environmental friendliness, safety), and comprehensively evaluating to determine the initial path, while considering special circumstances and user preference optimization. The candidate path weights are then determined based on the vehicle driving influencing factors, and the path with the highest weight is selected as the target navigation path, and can be dynamically adjusted according to vehicle status, driver needs, road condition changes, etc. It provides vehicles with accurate navigation paths through complex calculations and analysis, and can also adapt to rules and environmental changes in different regions. It is highly practical and adaptable, and is expected to improve the accuracy, safety and efficiency of vehicle navigation.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart showing a vehicle navigation path processing method based on online information provided by an embodiment of the present application; Figure 2 A schematic structural diagram of a vehicle navigation path processing device based on online information provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0013] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0014] Combine the following Figure 1 The following describes a vehicle navigation path processing method based on online information according to an exemplary embodiment of the present application. In one embodiment, the present application also proposes a vehicle navigation path processing method and system based on online information. Figure 1 The flowchart of a vehicle navigation path processing method based on online information according to an embodiment of the present application is schematically shown. Figure 1 As shown, the method is applied to a server, comprising: S101, obtaining vehicle status information, target vehicle attribute information, target driver driving information, target road environment information, real-time traffic information, target road map information and meteorological data of the target road map information within a preset time period.

[0015] In one embodiment, the real-time speed and acceleration data of the vehicle are obtained by an on-board speed sensor and an acceleration sensor. For example, when driving on urban roads, the vehicle may start and stop frequently, the speed varies between 0-60 km / h, and the acceleration fluctuates between -2 and 2 m / s²; when driving on highways, the vehicle speed is stable at 80-120 km / h, and the acceleration is relatively small, within the range of -1 to 1 m / s². These data can reflect the driving dynamics of the vehicle, such as acceleration, deceleration and constant speed driving. The steering angle sensor records the steering wheel rotation angle, and the steering wheel rotation frequency can be calculated in combination with the time data. The steering angle will change significantly during turning or lane changing operations. For example, when turning on an ordinary curve, the steering angle may be between 10-30 degrees; at a sharp bend, the steering angle may reach 60-90 degrees. The frequency of steering wheel rotation can reflect the frequency of driving operations. For example, under complex road conditions, the steering wheel rotation frequency may be higher, with an obvious rotation every few minutes. When the road conditions are good for straight driving, the rotation frequency is lower, and there may be slight adjustments every few minutes or even more than ten minutes.

[0016] Use the Global Positioning System (GPS) or Beidou Navigation System to obtain the latitude and longitude position information of the vehicle, and use an electronic compass or gyroscope to obtain the vehicle's heading angle. For example, when the vehicle is driving, the GPS updates the position information once a second, accurate to several decimal places, and can accurately display the vehicle's position on the map; the heading angle can indicate the vehicle's driving direction, such as 0 degrees to the north and 90 degrees to the east. The vehicle's actual driving direction changes continuously during driving, and this information is crucial to determining the vehicle's position and driving direction in the road network. Obtain the vehicle type from the vehicle license or vehicle configuration database, such as sedans, SUVs, MPVs, trucks, buses, etc., and obtain detailed vehicle size information, including body length, width, height, wheelbase, track, etc. For example, the length of an ordinary car may be between 4-5 meters, the width is about 1.7-1.9 meters, the height is 1.4-1.6 meters, and the wheelbase is 2.5-2.8 meters; while the length of a large truck may reach 10-20 meters, the width is 2.5-3 meters, the height is 3-4 meters, and the wheelbase is 4-6 meters. Vehicle type and size information is important for determining the vehicle's driving space requirements, turning radius, and passability on the road.

[0017] The power and torque data of a vehicle engine can reflect its power performance. For example, a high-performance sports car engine may have a power of 300-500 kilowatts and a torque of 400-600 Nm, which can provide strong power output and achieve rapid acceleration and high-speed driving; while an ordinary family car engine usually has a power of 80-150 kilowatts and a torque of about 150-250 Nm, and its power performance is relatively stable. In addition, information such as the vehicle's transmission type (manual, automatic, CVT, etc.) and drive mode (front drive, rear drive, four-wheel drive) can also be obtained. These factors will affect the vehicle's driving performance under different road conditions. For vehicles with load requirements such as trucks or buses, obtain their approved load and actual load. For example, the approved load of a light truck may be 1-2 tons, and the actual load depends on the transportation task; the approved load of a heavy truck can reach tens of tons. The vehicle's suspension system type (such as independent suspension, non-independent suspension) and parameters (spring stiffness, shock absorber damping, etc.) will also affect the vehicle's riding comfort and handling stability, especially under different load conditions, the performance of the suspension system will be different.

[0018] The on-board driving behavior monitoring system records the driver's accelerator pedal stroke, brake pedal stroke and steering wheel operation data. For example, by analyzing the accelerator pedal stroke change curve, the driver's acceleration habits can be judged, whether it is steady acceleration or frequent sudden acceleration; the brake pedal stroke data can reflect the driver's braking force and frequency. If the brake pedal stroke is frequent and deep, it may mean that the driver often brakes suddenly; the steering wheel operation data can reflect whether the driver's steering operation is smooth and accurate, such as whether the steering wheel turns smoothly and the angle is appropriate when changing lanes or turning. The driver's driving data is collected for a long time to analyze their average driving speed preference, overtaking frequency, following distance habits and other driving habits. For example, some drivers like to drive at high speeds, and the average driving speed is often maintained at a high level (such as an average speed of more than 100 kilometers per hour on highways); while some drivers prefer to drive at a stable medium speed. The frequency of overtaking also varies from person to person. Some drivers overtake more frequently and choose to overtake when they have the opportunity, while some drivers are relatively conservative and rarely overtake. In terms of following distance habits, some drivers maintain a larger safe following distance, while some drivers may follow the car closer. In addition, the driver's preference for specific road types can be understood, such as whether they like to take highways, urban expressways, or prefer scenic country roads.

[0019] Obtain the driver's historical driving records from the traffic management department, including traffic violation records (such as speeding, running red lights, illegal lane changes, drunk driving, etc.) and accident records (accident time, location, cause, responsibility determination, etc.). For example, if the driver has multiple speeding violation records, it may mean that his driving style is more aggressive and he does not pay enough attention to speed limits; if there are many accident records, especially accidents caused by improper operation, it may reflect that his driving skills or safety awareness need to be improved. These historical records can provide important reference for evaluating the driver's driving risks and behavioral characteristics.

[0020] Road infrastructure information includes the following: Street lighting conditions: Obtain information such as the distribution density and brightness of street lights through field surveys or data from relevant management departments. For example, street lights on urban main roads are usually densely distributed, with a spacing of about 30-50 meters and high brightness, which can provide good nighttime lighting conditions; while some remote rural roads may have few or even no street lights, and poor lighting conditions, which will affect the safety and visibility of nighttime driving. Clarity of road signs: Observe whether the traffic signs on the road (such as direction signs, prohibition signs, warning signs, etc.) are complete and clearly identifiable. On well-maintained roads, the signs are clear, the colors are bright, and the text and patterns are clear, so drivers can easily obtain road information; but on some old roads or sections that have long lacked maintenance, the signs may have problems such as fading, wear, and obstruction, making it difficult for drivers to accurately identify them, increasing the difficulty and potential risks of driving.

[0021] Road geometry information includes the following: Road slope information: Use professional measuring equipment or reference geographic information system (GIS) data to obtain the slope of the road. For example, mountain roads may have a large slope, and some steep slopes may have a slope of 10%-20% or even greater. Vehicles need more power when climbing and better braking control when going downhill; while urban roads have relatively small slopes, generally within 5%. Curve curvature information: Also use measuring equipment or GIS data to determine the curvature radius of road curves. The curvature radius of highway curves is large, usually hundreds of meters or even thousands of meters, and vehicles can pass at a higher speed; the curvature radius of curves on urban roads varies greatly, and the curvature radius of small curves may be tens of meters. Vehicles need to slow down when passing, otherwise they are prone to skidding or loss of control.

[0022] The road surrounding environment information includes the following: Topography on both sides of the road: satellite images or field surveys are used to understand whether the two sides of the road are plains, mountains, rivers, or densely built areas. For example, roads near mountainous areas may be at risk of natural disasters such as falling rocks and landslides; roads near rivers may face the risk of being submerged during flood seasons; and roads located in densely built urban areas may have more pedestrians and non-motor vehicles interfering with traffic, and there may also be problems such as buildings blocking the line of sight. Distribution of surrounding transportation facilities: obtain the location information of transportation facilities such as parking lots, gas stations, and bus stops around the road. For example, in the central area of ​​the city, there are many parking lots and bus stops, but parking resources may be tight; on highways, gas stations and service areas are distributed at large intervals, and drivers need to plan refueling and resting places in advance. The distribution of these surrounding transportation facilities will affect the driver's itinerary and driving decisions.

[0023] Real-time traffic flow data of different sections of roads can be obtained through geomagnetic sensors, cameras or traffic flow monitoring systems installed on the road. For example, during peak hours of urban traffic, the traffic volume on the main roads may reach thousands or even tens of thousands of vehicles per hour, and vehicles are slow and congested; while during non-peak hours or on suburban roads, the traffic volume is relatively small, and there may be only a few hundred vehicles per hour or even less, and vehicles can travel smoothly. Traffic flow data can intuitively reflect the busyness of the road and provide an important basis for route planning. Real-time networking with the traffic management department to obtain traffic control information, including road construction control, temporary traffic control (such as during large-scale events), and restrictions (such as odd-even number restrictions, truck restrictions, etc.). For example, a road is semi-closed due to road construction, and vehicles can only travel in one direction or need to detour; when holding large-scale sports events or concerts, temporary traffic control may be implemented on roads around the venue to restrict the passage of some vehicles; some cities restrict certain types of vehicles during specific periods, such as restricting non-local licensed vehicles during peak hours in the morning and evening on weekdays. These traffic control information directly affects the vehicle's route selection and must be obtained in a timely manner and taken into account in path planning.

[0024] The topological structure of the road network is obtained from the electronic map database, including information such as the connection relationship of the roads, the types of intersections (such as crossroads, T-junctions, roundabouts, etc.) and the number of intersections. For example, in the central area of ​​the city, the road network is dense and there are many intersections, forming a complex topological structure; while in the suburbs or newly developed areas, the road network is relatively simple and there are fewer intersections. Understanding the topological structure of the road network helps to plan a reasonable driving route and avoid frequent turns or getting lost at complex intersections. The map information contains road level information, such as expressways, national roads, provincial roads, urban trunk roads, secondary trunk roads, branch roads, etc., as well as road attribute information, such as road width, number of lanes, whether it is one-way driving, etc. Expressways usually have higher design standards, wide roads, many lanes (four lanes in both directions or more), and high speed limits (generally 60-120 kilometers per hour); urban trunk roads are wider, have more lanes, and have large traffic volume, and the speed limit is generally 40-60 kilometers per hour; while branch roads are relatively narrow, have fewer lanes, and have lower speed limits (generally below 30 kilometers per hour). These road grade and attribute information play an important role in evaluating road capacity and selecting appropriate driving routes.

[0025] Obtain precipitation forecast data for the target road area within a preset time period (such as the next few hours or days) from the meteorological department, including precipitation amount, precipitation intensity and precipitation type (such as rain, snow, hail, etc.). For example, the forecast shows that there will be moderate rain on a certain road section in the next 2 hours, with precipitation between 10-25 mm and medium precipitation intensity. The vehicle may encounter problems such as slippery road surface and obstructed vision during driving, and needs to be prepared in advance, such as slowing down, turning on wipers and fog lights, etc. Obtain the temperature and humidity information of the road area. The temperature data can affect the performance and driving environment of the vehicle. In hot weather (such as the temperature exceeds 35°C), the heat dissipation burden of the vehicle engine increases, and overheating may occur. At the same time, the tire temperature increases, increasing the risk of tire blowout; in cold weather (such as the temperature below 0°C), the road may be frozen, especially on bridges, viaducts and other sections, posing a serious threat to vehicle driving safety. Humidity data will affect the friction of the road surface. In a high humidity environment, the road surface may be more slippery, reducing the braking performance of the vehicle.

[0026] The wind speed and direction information in the meteorological data also has an important impact on vehicle driving, especially for high-body vehicles (such as trucks, buses, SUVs, etc.). For example, in strong wind weather (wind speed exceeding level 8), the vehicle will be subjected to a large lateral force during driving, and it is easy to skid or deviate from the driving trajectory. The driver needs to control the vehicle more carefully and maintain a stable driving direction. Wind direction information can help the driver predict the direction of the wind's impact on the vehicle in advance and take corresponding measures, such as appropriately adjusting the vehicle speed and steering wheel angle on roads with strong crosswinds.

[0027] S102, processing the target road environment information and the meteorological data of the target road map information within a preset time period to generate an environmental impact factor.

[0028] In one implementation, feature extraction is performed on the target road environment information to generate road type features, road infrastructure features, and road surrounding environment features. Road types can be divided into expressways, national highways, provincial highways, urban trunk roads, urban secondary roads, urban branch roads, rural roads, etc. For example, a highway connecting two major cities has obvious road type characteristics, with features such as full closure, multiple lanes (four lanes in both directions or more), and high design speed (generally 80-120 kilometers per hour); while urban branch roads are usually narrower, with fewer lanes (possibly single lanes or two lanes in both directions), and relatively small traffic flow, but complex traffic participants, and many and irregular intersections. By analyzing the road network topology and road attribute information (such as road width, number of lanes, etc.), the road type characteristics can be accurately identified, providing a basis for subsequent evaluation of road capacity and its impact on vehicle driving.

[0029] The characteristics of road infrastructure include the following: Street lighting conditions: Taking a certain city's main road as an example, street lights are evenly distributed along both sides of the road, with a spacing of about 35 meters. High-pressure sodium lamps are used as light sources, which have high brightness and can provide good lighting conditions for vehicles at night to ensure driving safety. However, on some old urban secondary roads, street lights may be aging or damaged, and the lighting effect is poor. Some sections of the road may even have dim or no street lights, which will increase the difficulty and risk of driving at night. Drivers need to pay more attention and reduce their speed to cope with poor visibility. Road sign clarity: On well-maintained highways, traffic signs are complete and clear, and various signs (such as exit signs, lane division signs, etc.), prohibition signs (such as speed limit signs, no overtaking signs, etc.) and warning signs (such as curve warnings, steep slope warnings, etc.) are brightly colored, with clear text and patterns, which can provide drivers with road information and driving rules prompts in a timely and accurate manner. However, on rural roads in some remote areas, due to long-term lack of maintenance or low construction standards, road signs may be unclear, obscured (such as by tree branches) or even missing. Drivers find it difficult to obtain accurate road information while driving, and are prone to taking the wrong road or violating traffic rules, increasing driving uncertainty and potential dangers.

[0030] The characteristics of the road surrounding environment include the following: Topography on both sides of the road: There are high mountains and steep ridges on both sides of a mountain road, with large undulating terrain and many steep slopes and sharp turns. This kind of topography makes the vehicle face great challenges during driving, such as requiring greater power output when climbing, and strictly controlling the speed when going downhill to prevent the brakes from overheating and failing; at the same time, there may be natural disaster risks such as falling rocks and landslides around mountain roads, especially in the rainy season or when geological disasters such as earthquakes occur frequently, which poses a serious threat to vehicle driving safety. On the other hand, roads in plain areas have relatively flat and open terrain, good vision, and smoother vehicle driving, but may be affected by factors such as farmland irrigation and wind and sand. For example, during the crop harvest season, crops may be scattered on the road, affecting vehicle driving safety. Distribution of surrounding transportation facilities: In the central commercial area of ​​the city, there are dense transportation facilities such as parking lots, bus stops, and subway stations around the road. For example, there may be multiple parking lots near a large shopping mall, but during the peak shopping season, parking spaces are still tight, and vehicles may spend a lot of time looking for parking spaces. At the same time, vehicles entering and leaving the parking lot will also increase the traffic flow and congestion of surrounding roads. Frequent stops at bus stops and subway stations and passengers boarding and alighting will also cause certain interference to road traffic. In contrast, in urban suburbs or newly developed areas, there are relatively few transportation facilities and a limited number of parking lots. Drivers need to consider parking issues in advance when planning their trips to avoid affecting their travel plans due to the inability to find parking spaces. The distance between bus stops and subway stations is large, which is not very convenient for people who rely on public transportation, and may also cause some people to choose to travel by car, thereby increasing traffic pressure in the area.

[0031] Although the vehicle's speed, acceleration, steering angle and other status information have been mentioned, the vehicle's fault code information is equally important for navigation route planning. For example, when the vehicle's engine control system detects a fault and generates a fault code, this may affect the vehicle's power performance, fuel consumption, etc., and thus affect the choice of navigation route. If the vehicle has an engine fault, the navigation system should give priority to routes that are closer to the vehicle maintenance point when planning the route, or avoid choosing roads with complex road conditions and frequent starts and stops to avoid aggravating the vehicle's fault. For heavy-duty vehicles such as trucks, real-time and accurate load information is crucial. In addition to obtaining the vehicle's approved load capacity, an on-board weighing sensor is added to monitor the vehicle's actual load in real time. Different loads will affect the vehicle's driving performance (such as acceleration, braking, climbing ability, etc.) and the degree of damage to the road. When planning the route, for vehicles with heavy loads, roads with low bridge weight limits and large slopes should be avoided to ensure driving safety and the integrity of road facilities.

[0032] The maintenance of a vehicle is directly related to its performance and reliability. Obtain the vehicle's maintenance records, including the last maintenance time, maintenance items, and replacement parts. If the vehicle is approaching the maintenance cycle or some key parts (such as brake pads, tires, etc.) are close to the wear limit, the navigation system can give priority to recommending routes that are closer to the car repair and maintenance shop when planning the route, so that the driver can perform vehicle maintenance in time and reduce the driving risk caused by vehicle failure. Clarify the vehicle's fuel type (gasoline, diesel, natural gas, electric, etc.) and the current remaining fuel or power information. For electric vehicles, the compatibility and distribution of charging piles must also be considered. When planning the route, according to the vehicle's fuel type and remaining amount, plan a route with more gas stations along the way for fuel vehicles, and plan a route with suitable charging piles and reasonable charging time for electric vehicles to avoid the vehicle breaking down on the way due to insufficient energy.

[0033] The driver's fatigue state is monitored in real time through in-car cameras, steering wheel sensors, driving behavior analysis and other methods. For example, the driver's eye closure time, head movement trajectory, and regularity of driving operations are analyzed. If driver fatigue is detected, the navigation system can issue a warning in time, and at the same time, the route planning gives priority to routes that are closer to service areas or safe parking areas to facilitate the driver's rest and reduce the safety risks caused by fatigue driving. If the vehicle configuration allows, the driver's emergency response ability is tested regularly or irregularly, such as simulating sudden emergencies (sudden obstacles appearing in front, sudden loss of control of the vehicle, etc.), and recording the driver's reaction time, operation accuracy and other data. These data can help the navigation system more accurately evaluate the driver's ability to respond to emergencies under different road conditions, so that when planning the route, drivers with weak emergency response capabilities can avoid choosing roads with complex traffic conditions and high accident risks.

[0034] For road sections under construction, it is necessary not only to obtain construction control information, but also to update the construction progress in real time. For example, whether the construction section is in the initial excavation stage (road capacity has dropped significantly and the road conditions are extremely poor), the mid-term paving stage (some lanes may be closed, but the road conditions are relatively stable) or the late finishing stage (normal traffic will be restored soon and traffic control will be gradually lifted). Based on the construction progress information, the navigation system can more accurately assess the impact of the construction section on vehicle driving and provide drivers with more reasonable route planning suggestions. In some areas with severe pollution or specific environments (such as industrial areas and areas with severe traffic congestion), road air quality may have an impact on vehicle driving and the health of drivers and passengers. Through air quality monitoring equipment or data sharing with environmental protection departments, obtain air quality data along the road (such as PM2.5, PM10, harmful gas concentration, etc.). For sections with poor air quality, the navigation system can consider avoiding them when planning the route, or remind the driver to close the windows, turn on the air purification equipment in the car, etc.

[0035] When road construction or traffic accidents are obtained in traffic control information, further detailed information is obtained, such as the type of accident (rear-end collision, collision, breakdown, etc.), the severity of the accident (whether there are casualties, the degree of damage to the vehicle), and the progress of the accident handling (estimated cleaning time, whether a rescue vehicle is needed, etc.). These detailed information helps the navigation system to more accurately assess the duration and scope of traffic congestion, so as to plan a more reasonable detour route for the vehicle. For example, if it is a minor rear-end collision and the handling is about to be completed, the navigation system may suggest that the driver wait for a while nearby before passing through, rather than choosing to detour immediately; if it is a serious accident and the cleaning time is long, the vehicle is guided to detour to other roads in a timely manner. In addition to the current real-time traffic flow data, historical traffic data, machine learning algorithms and other means are used to predict the traffic flow change trend of the road in the future (such as the next 15 minutes, 30 minutes, 1 hour, etc.). This helps the navigation system plan the optimal path in advance to avoid the vehicle from getting stuck in the congested section that is about to form during driving. For example, according to the prediction model, the traffic flow of a certain road will increase rapidly and form congestion in the next 30 minutes. The navigation system can guide the vehicle to choose other relatively unobstructed routes in advance to improve the foresight and accuracy of navigation.

[0036] Collect and analyze historical traffic data of the target road in different time periods (such as different seasons in the past year, weekdays and weekends, daytime and nighttime, etc.), including average speed, congestion index, accident rate, etc. These historical data can help the navigation system better understand the traffic characteristics and rules of the road, and more accurately evaluate the traffic capacity and potential risks of different roads at different times when planning the route. For example, a road is often congested during the morning and evening rush hours on weekdays, but the traffic is relatively smooth during the noon period. The navigation system can recommend the best driving time and route for the vehicle based on the current time and historical traffic data. For parking lots, restaurants, gas stations, shopping centers and other points of interest along the road, obtain their real-time dynamic information, such as the number of parking spaces, changes in charging standards, the business status of restaurants (whether they are open, whether there are seats, etc.), and the supply of oil products at gas stations. When planning the route, according to the needs of the driver (such as parking, dining, refueling, etc.), combined with these real-time dynamic information, provide the driver with a more intimate and practical navigation service. For example, when the vehicle is low on fuel and the driver wants to eat out, the navigation system can recommend a route that has both a gas station and an open restaurant that is close to each other, and display parking space information to help the driver choose a suitable parking spot.

[0037] The meteorological data of the target road map information within the preset time period is processed to generate meteorological element information. The target road area is monitored by weather radar, rain gauge and other equipment to obtain precipitation data. For example, the forecast shows that a certain city will have a rainfall process in the next 3 hours, with an estimated precipitation of 15-20 mm and a precipitation intensity of moderate rain. This means that the road surface will become slippery, the braking distance of the vehicle will increase, and the driver needs to maintain a larger safe distance and reduce the speed to prevent rear-end collisions. At the same time, rainfall may affect vision, especially at night or in low visibility. The driver needs to turn on the wipers and fog lights to ensure good vision. Assume that a certain area is in the high temperature period in summer, the temperature reaches 38°C and the humidity is high (relative humidity 70%-80%). High temperature weather will make it difficult for the vehicle engine to dissipate heat, and it is easy to overheat, affecting the engine performance and life. For tires, high temperature will cause the tire pressure to increase, increasing the risk of tire blowout. Drivers need to pay attention to checking the tire pressure and reduce the speed appropriately. A high humidity environment will make the road more slippery, especially when it has just rained or there is water on the road. The braking effect of the vehicle will be significantly reduced. It is necessary to predict the braking distance in advance and avoid sudden braking operations.

[0038] Strong winds are common in coastal areas. For example, weather forecasts show that a coastal highway will be affected by strong winds, with wind speeds of up to 10-15 m / s (about 6-7 winds) and northwest winds. For vehicles traveling on this highway, especially high-body trucks, buses and SUVs, strong winds will generate large lateral forces, making the vehicles prone to skidding or deviating from their driving trajectory. During driving, the driver needs to hold the steering wheel tightly and adjust the vehicle's driving direction according to the wind direction. For example, when driving against the wind, increase the throttle appropriately to maintain the vehicle speed, and slow down on sections with strong crosswinds to ensure stable driving of the vehicle.

[0039] Process the meteorological element information to generate meteorological trend information. Analyze meteorological trends using historical meteorological data and real-time monitoring data combined with meteorological forecast models (such as numerical weather forecast models). For example, according to the meteorological model forecast, the temperature in a certain city will continue to rise in the next 6 hours, with the highest temperature reaching 40°C, and the relative humidity will remain at a high level (75%-85%). This continuous high temperature and high humidity meteorological trend has a great impact on vehicle driving safety and performance. The navigation system can issue early warnings to drivers to remind them to pay attention to vehicle heat dissipation and tire conditions, avoid long-term driving during high temperature periods or long-term parking in high temperature environments, and prevent vehicle failures. For another example, the meteorological department has monitored that the precipitation in a local area of ​​a mountainous area will increase rapidly in the next 2 hours, and the precipitation intensity will change from light rain to heavy rain, which may be accompanied by lightning activities. Based on this weather trend information, the navigation system can promptly notify vehicles that are about to enter the area and suggest them to choose other safe routes to bypass, or remind drivers to prepare for heavy rain and thunderstorms before entering the area, such as checking whether wipers, lights and other equipment are working properly, closing windows, and avoiding parking near large trees, high-voltage lines and other objects that are easily struck by lightning.

[0040] Based on the information of meteorological change trend, the road type characteristics, road infrastructure characteristics and road surrounding environment characteristics are processed to generate environmental impact values. The quantification methods of road type characteristics, road infrastructure characteristics and road surrounding environment characteristics, as well as the quantitative relationship between the impact of meteorological change trend information on these characteristics (reflected by weights and time function adjustment factors, etc.) are determined. Taking a mountain road as an example, its road type is a secondary mountain highway (the quantification value is set to 2, according to the set road type quantification standard). In terms of road infrastructure characteristics, the street lighting is general (the quantification value is set to 1), and the road signs are clear (the quantification value is set to 1); in the characteristics of the road surrounding environment, the terrain on both sides is complex (the quantification value is set to 3), and the surrounding traffic facilities are sparsely distributed (the quantification value is set to 2).

[0041] The weather trend information shows that in the next 2 hours, there will be heavy rain in the area (the precipitation quantization value is set to 3), the temperature will drop (the impact on the road is relatively small, the quantization value is set to 0.5), and the wind speed will increase (the quantization value is set to 2). According to the environmental impact value calculation formula ,in, represents the weight of the jth feature item under the i-th feature category, represents the quantitative value of the jth feature item under the i-th feature category, Represents the time function adjustment factor based on meteorological trend information. When i=1, the i-th feature category refers to the road type feature. Road types can be divided into expressways, national roads, provincial roads, urban trunk roads, urban secondary roads, urban branch roads, rural roads, etc. Different types of roads have different design standards and traffic characteristics. These differences will affect vehicle driving. For example, expressways are fully closed, multi-lane, and have high design speeds, while urban branch roads are narrow, have a small number of lanes, and have complex traffic participants. These characteristics need to be considered when calculating environmental impact values.

[0042] When i=2, the i-th feature category refers to the road infrastructure features, which include street lighting conditions, road sign clarity, etc. Good street lighting can ensure nighttime driving safety, and clear road signs can help drivers obtain road information. If street lights are aging or signs are blurred, it will increase driving difficulty and risk, affecting the environmental impact value.

[0043] When i=3, the i-th feature category refers to the environmental characteristics of the road surroundings, covering the topography on both sides of the road (such as plains, mountains, rivers, etc.) and the distribution of surrounding transportation facilities (parking lots, gas stations, bus stops, etc.). For example, there are risks of falling rocks and landslides on mountain roads, and there is a large traffic flow around parking lots in the city center. These factors have different degrees of impact on vehicle driving and are considered as a type of feature when calculating the environmental impact value.

[0044] Assumption Weight Determined based on data analysis (e.g. cross-weighting of road type and rainstorm precipitation is 0.3, the cross weight of street lighting and wind speed The time function adjustment factor is determined according to the duration and intensity of the rainstorm (assuming that within the first 30 minutes after the rainstorm begins, The value increases gradually over time, from 1 to 1.5).

[0045] When calculating the environmental impact value, first calculate the cross-impact value of each characteristic item and meteorological elements. For example, the cross-impact value of road type characteristics and rainstorm precipitation is (Assuming t = 30 minutes ), and then add up all the cross-impact values ​​to obtain the environmental impact value of the mountain road under the current meteorological change trend. This value reflects the comprehensive impact of meteorological changes on the overall road environment and provides a quantitative basis for the subsequent generation of environmental impact factors. When considering the impact of meteorological factors on the road environment, the impact model of different weather phenomena (such as rain, snow, fog, ice, frost, etc.) on road friction is further refined. Different precipitation types (such as light rain, heavy rain, rainstorm, freezing rain, etc.) and factors such as snow depth and ice degree will cause road friction to change to varying degrees, thereby affecting the braking distance and handling performance of the vehicle. By establishing a more accurate friction impact model and combining real-time meteorological data, the environmental impact factor can be calculated more accurately to provide a more scientific basis for path planning. For example, when calculating the environmental impact value, the degree of reduction in road friction can be determined more accurately based on the actual precipitation type and precipitation, and then the corresponding quantitative value and weight can be adjusted so that the environmental impact factor can more truly reflect the impact of weather on road driving conditions.

[0046] In addition to static environmental features such as the topography and distribution of traffic facilities on both sides of the road, the assessment of dynamic risks of the road surrounding environment is increased. For example, on some mountainous areas or roads in nature reserves, wild animals may appear at specific times (such as early morning and evening), posing a threat to vehicle driving safety; on urban roads, temporary construction areas (such as road repairs, pipeline laying, etc.) may appear. Although these areas are not included in the regular construction control information, they will have a certain impact on road traffic. Through data sharing with relevant departments (such as wildlife protection agencies and municipal management departments) or real-time monitoring methods (such as wildlife monitoring cameras and road inspections), these dynamic risk information can be obtained in a timely manner and included in the calculation of environmental impact factors. For example, when a road section is detected to have the risk of wild animals appearing, the environmental impact factor of the road section is increased accordingly, and drivers are reminded to observe and slow down; for temporary construction areas, the environmental impact factor is adjusted according to the scale of construction and the degree of impact on road traffic, and vehicles are guided to reasonably bypass or pass carefully.

[0047] The environmental impact value is processed to generate an environmental impact factor. After the environmental impact value is obtained, it is further processed to generate an environmental impact factor. For example, the environmental impact value is divided into different level ranges, corresponding to different environmental impact factor levels. Assume that the environmental impact value in the range of 0-10 is a low impact factor (indicated by 1), 10-20 is a medium impact factor (indicated by 2), and 20-30 is a high impact factor (indicated by 3). If the environmental impact value calculated for the above mountain road is 18, it is judged that the corresponding environmental impact factor is 2, indicating that under the current meteorological change trend, the environmental conditions of the road have a moderate impact on vehicle driving.

[0048] Environmental impact factors can serve as an important reference for subsequent route planning and vehicle driving decisions. When planning a navigation route, the navigation system can give priority to avoiding road sections with higher environmental impact factors, or remind the driver to pay special attention to safety during driving, adjust the speed according to actual conditions, maintain a safe distance, etc.; for sections with lower environmental impact factors, it can be based on a comprehensive consideration of other factors (such as road distance, traffic flow, etc.) and be more inclined to choose these sections to improve driving efficiency and safety. At the same time, as the meteorological conditions and road environment change in real time during vehicle driving, the environmental impact factors will also be dynamically updated. The navigation system will promptly adjust the route planning suggestions based on the new impact factors to ensure that the vehicle is always driving on a relatively safe and efficient route.

[0049] S103: Process the real-time traffic information and the target road map information to generate a road impact factor.

[0050] In one implementation, real-time traffic information is processed to generate real-time traffic flow information and real-time traffic control information. Real-time traffic flow data of different sections are obtained by geomagnetic sensors, cameras or traffic flow monitoring systems installed on the road. For example, in a busy commercial district in the city center, between 10-11 am on weekdays, the traffic flow sensor data shows that the average number of vehicles passing through a main road per minute reaches 80-100, and the traffic flow is large; while in the suburban roads of the same city, during the same time period, the number of vehicles passing through per minute may be only 10-20, and the traffic flow is relatively small. These data can intuitively reflect the busyness of the road and provide an important basis for subsequent path planning. For highways, the traffic flow monitoring system can accurately count the traffic flow of each lane. For example, during the peak travel period of a certain section of highway during holidays, the traffic flow of the three lanes is: 40-50 vehicles per minute in the inner fast lane, 30-40 vehicles per minute in the middle lane, and 20-30 vehicles per minute in the outer slow lane. At the same time, the vehicle's driving speed information can also be obtained to further analyze the state of the traffic flow. For example, if the vehicle speed in the inner fast lane is generally 80-100 km / h, the vehicle speed in the middle lane is 60-80 km / h, and the vehicle speed in the outer slow lane is 40-60 km / h, and the vehicles are driving in a relatively orderly manner, it means that the traffic is smooth; if there is a significant drop in speed and vehicles queue up, such as the speed in the inner fast lane drops to 20-30 km / h and the length of the vehicle queue reaches several kilometers, it indicates that there is congestion on the road section.

[0051] Real-time networking with traffic management departments to obtain traffic control information. For example, a city held a large international conference and implemented temporary traffic control in the area around the conference venue. The control time was from 8 am to 6 pm on the day of the conference. The control range included all roads within a radius of 2 kilometers around the venue. Except for vehicles with special conference passes, other vehicles were prohibited from passing. After the navigation system obtained the control information in time, it would avoid the area during route planning to prevent vehicles from being trapped in impassable sections of the road. Road construction control is also a common traffic control situation. For example, a city trunk road was semi-closed due to road widening construction. During the construction period (expected to last for 3 months), the road section was changed from a two-way six-lane to a two-way three-lane. Vehicles were required to slow down and pay attention to the safety warning signs in the construction area. After the navigation system obtained the construction control information, it would plan a reasonable detour route for the vehicle based on the construction progress (such as the initial excavation stage, the mid-term paving stage, and the later finishing stage) and the degree of impact on the road's traffic capacity, and remind the driver to pay attention to changes in road conditions.

[0052] Process the real-time traffic flow information to generate traffic flow quantitative indicators. Set traffic flow quantitative indicators for the acquired real-time traffic flow information. For example, divide the traffic flow into different levels: low flow (less than 20 vehicles per minute), medium flow (20-50 vehicles per minute), high flow (50-100 vehicles per minute) and congestion (more than 100 vehicles per minute and the vehicle speed is significantly reduced). When calculating the traffic flow quantitative indicators, the corresponding values ​​can be assigned according to the level to which the actual traffic flow data belongs. For example, if the real-time traffic flow of a certain section of road is 35 vehicles per minute, according to the quantitative standard, its traffic flow quantitative indicator is 2 (corresponding to the medium traffic level). Further considering the impact of vehicle speed on traffic flow, the speed factor is introduced to correct the traffic flow quantitative indicators. Assume that the vehicle speed is 60-80 km / h in the normal driving speed range, and the speed factor is 1; when the speed is 40-60 km / h, the speed factor is 0.8; when the speed is 20-40 km / h, the speed factor is 0.5; when the speed is less than 20 km / h (severe congestion), the speed factor is 0.2. If the traffic volume of a certain road section is 45 vehicles per minute (belonging to the medium traffic level, the quantitative index is 2), but the average vehicle speed is 30 km / h, after correction according to the speed factor, the traffic volume quantitative index becomes This can more accurately reflect the actual traffic conditions of the road and avoid evaluation bias caused by relying solely on traffic flow data.

[0053] Process the real-time traffic control information to generate quantitative indicators for vehicle traffic. Generate quantitative indicators for vehicle traffic based on real-time traffic control information. Set corresponding quantitative values ​​for different types of traffic control measures. For example, road construction control (semi-closure or partial lane closure) is quantified according to the scale of construction and the degree of impact on road capacity. Small-scale construction (such as local road repair, which has little impact on lanes) has a quantitative value of 1, medium-scale construction (such as partial lane closure for pipeline laying, which affects a certain amount of traffic flow) has a quantitative value of 2, and large-scale construction (such as road widening, bridge reconstruction, etc., which leads to a significant decrease in road capacity) has a quantitative value of 3. Temporary traffic control (such as control during large-scale events) is quantified according to the size of the control area, the length of control time, and the scope of impact on surrounding roads. If the control area is small (such as only one street or one intersection), the control time is short (1-2 hours), and the impact on surrounding roads is small, the quantitative value is 1; if the control area is large (covering multiple blocks), the control time is long (3-6 hours), and it causes traffic diversion on multiple surrounding roads, the quantitative value is 2; if the control scale is larger (such as large-scale event control in the city center, involving multiple main roads and large areas), the quantitative value is 3. Take a marathon held in a certain city as an example. The race route involves multiple main roads. The control time is from 7 am to 2 pm, which has a great impact on the traffic on surrounding roads. The vehicle traffic quantitative index of this temporary traffic control is 3. Traffic restriction measures (such as odd-even number restrictions, truck restrictions, etc.) are also quantified according to the degree of impact of the restricted area, time and restricted vehicle type. For example, during the morning and evening rush hours on weekdays, non-local licensed vehicles are restricted in specific areas (such as the city's core business district), and the quantitative value is 2; a certain type of truck (such as heavy trucks) is restricted in the main urban area of ​​the city all day, and the quantitative value is 3.

[0054] The target road map information is processed based on the traffic volume quantitative index and vehicle traffic quantitative index to generate the road impact value. Assume that we have a city trunk road A, whose traffic volume quantitative index is 2 according to real-time monitoring and calculation (taking into account the traffic volume and speed factors), and there is currently a medium-scale road construction control on this road section (the vehicle traffic quantitative index is 2). According to the road impact value calculation formula ;in, Represents the category of influencing factors, represents the weight of the zth influencing factor category, Represents the quantitative value of the zth influencing factor category. When the “influencing factor category” refers to the factors related to the quantitative indicators of traffic flow, When , “influencing factor category” refers to the factors related to the vehicle traffic quantitative index. When, "influencing factor category" refers to factors related to traffic volume quantitative index. Traffic volume quantitative index is obtained by processing real-time traffic flow information, taking into account the traffic volume and vehicle speed, dividing into different levels and assigning corresponding values, and introducing speed factor correction to reflect the actual traffic conditions of the road. For example, if the traffic volume on a certain road section is large and the speed is low, the traffic volume quantitative index is low, which has a corresponding impact on the road impact value. When the "influencing factor category" is used, it refers to the factors related to the vehicle traffic quantitative index. The vehicle traffic quantitative index is set based on real-time traffic control information. Different types of traffic control measures (road construction control, temporary traffic control, traffic restriction measures, etc.) are quantified according to scale, time, and scope of influence. For example, large-scale road construction control has a great impact on road traffic capacity and a high vehicle traffic quantitative index. When calculating the road impact value, it works together with the factors related to the traffic volume quantitative index to determine the comprehensive impact of the road on vehicle travel under the current traffic volume and control conditions.

[0055] Assuming the weight of traffic flow factors Set to 0.6, the weight of traffic control factors Set to 0.4. Calculate the road impact value of road A: This road impact value reflects the comprehensive impact of the road section on vehicle driving under the current traffic flow and control conditions. The larger the value, the greater the impact. When planning the route, more consideration should be given to the traffic conditions of the road section.

[0056] The road impact value is processed to generate a road impact factor. After the road impact value is obtained, it is further processed to generate a road impact factor. For example, the road impact value is divided into different level ranges, corresponding to different road impact factor levels. Assume that the road impact value in the range of 0-1 is a low impact factor (represented by 1), 1-2 is a medium impact factor (represented by 2), and 2-3 is a high impact factor (represented by 3). For the main road A with a road impact value of 2 calculated above, its corresponding road impact factor is 2, indicating that the road section has a moderate impact on vehicle driving under the current traffic conditions. The road impact factor can be used as an important reference for subsequent path planning. When planning the navigation path, the navigation system will try to avoid selecting sections with higher road impact factors, or remind the driver to pay attention to possible traffic congestion and control situations when selecting, and make preparations in advance; for sections with lower road impact factors, on the basis of comprehensive consideration of other factors (such as road distance, environmental impact, etc.), it will be more inclined to select these sections to improve driving efficiency and smoothness. At the same time, as traffic flow and control conditions change in real time, the road impact value and road impact factor will be dynamically updated, and the navigation system will adjust the path planning suggestions in a timely manner based on the new information to ensure that the vehicle is always traveling on the relatively optimal route. For example, if the construction control of the main road A ends, the traffic flow returns to normal, and the traffic flow quantitative index becomes 1, the road impact value is recalculated as (construction control ends, the vehicle traffic quantitative index becomes 0), and the road impact factor becomes 1, the navigation system may re-evaluate the priority of this section in the path planning and include it in the selection range of a better path.

[0057] When calculating the road impact factor, traffic flow and traffic control information are taken into account, but traffic signal control strategies (such as signal light cycle setting, green wave band design, etc.) also have an important impact on road capacity and traffic flow. Different signal light control strategies will lead to different waiting times and queue lengths for vehicles at intersections, which in turn affects the overall traffic efficiency of the road. By connecting to the signal control system of the traffic management department, real-time traffic signal control parameters are obtained, their impact on road capacity is analyzed, and they are included in the calculation of road impact factors. For example, when calculating the road impact value, for road sections that use intelligent traffic signal control and have reasonable green wave band settings, their traffic congestion quantitative indicators are reduced, so as to more accurately evaluate the actual traffic conditions of the road and provide a more comprehensive reference for path planning.

[0058] Roads that have been used for a long time will have different degrees of wear and tear, such as potholes and reduced flatness, which will not only affect the driving comfort of the vehicle, but may also increase the wear and tear of the vehicle and the risk of accidents. A road wear assessment model is established to quantify the degree of road wear through regular road inspection data (such as data obtained by equipment such as road surface flatness measuring instruments and ground penetrating radars) or sensor data during vehicle driving (such as vibration sensor data of the vehicle suspension system). The degree of road wear is included in the calculation of road impact factors. For road sections with severe wear, the quantitative value of their impact on vehicle driving is increased, so that the road impact factor can more comprehensively reflect the actual conditions of the road, guide vehicles to choose routes with better road conditions, and improve driving comfort and safety.

[0059] S104, processing the vehicle state information, the target vehicle attribute information and the target driver's driving information to generate a vehicle driving influencing factor.

[0060] In one implementation, the vehicle status information and the target vehicle attribute information are processed to generate the target vehicle's driving level information. The vehicle's driving data under different road conditions is obtained through the vehicle-mounted speed sensor and acceleration sensor. For example, in urban congested road conditions, the vehicle frequently starts and stops, the speed frequently changes between 0-30 km / h, and the acceleration fluctuates greatly between -2 and 2 m / s²; when driving on the highway, the vehicle speed is stable at 80-120 km / h, and the acceleration is relatively small, within the range of -1 to 1 m / s². The steering angle sensor data shows that when turning on urban roads, the steering angle changes frequently, and there is an average of 5-30 degrees of steering operation every few hundred meters; on highways, the steering angle changes less, and usually a smaller angle steering adjustment is made only after a longer distance. The vehicle's driving trajectory is obtained using the global positioning system (GPS) or the Beidou navigation system to analyze the vehicle's driving stability in complex road environments (such as mountain roads and narrow urban streets). For example, when driving on a mountain bend, whether the vehicle can stay in the lane, whether there are frequent lane deviation warning records, etc. These vehicle status information can reflect the vehicle's control difficulty and stability in different driving scenarios, and provide basic data for evaluating driving levels.

[0061] The type and size of the vehicle have a significant impact on the driving level. Taking small cars and large trucks as examples, small cars are compact and flexible, with a small turning radius, and have high maneuverability in narrow urban roads and parking lots, and are relatively easy to drive; while large trucks are longer, wider, and taller, with a large turning radius, requiring more space when driving on the road, especially when turning, turning around, and entering and exiting parking lots. The operation is more difficult, and the driving level is relatively high. The power performance of the vehicle is also an important factor. High-performance sports cars have high engine power and torque, and strong acceleration and high-speed driving capabilities, but for ordinary drivers, they are more difficult to control, and the driving level is correspondingly increased; ordinary family cars have moderate power and are relatively easy to drive.

[0062] For vehicles with load requirements such as trucks or buses, the load condition is directly related to the driving difficulty. For example, a truck with a rated load of 10 tons is relatively easy to drive when empty, but the acceleration, braking and handling performance of the vehicle will change when fully loaded, requiring the driver to have higher driving skills, and the driving level will also increase accordingly. The type and parameters of the vehicle's suspension system will also affect the driving experience and handling stability. The independent suspension system performs better in terms of comfort and handling. The non-independent suspension system may cause the vehicle to have poor stability on bumpy roads in some cases, affecting the driving difficulty assessment. Combining these vehicle status and attribute information, through certain algorithms and weight allocation (for example, determining the weights of different factors based on a large amount of actual driving data), the driving level information of the target vehicle can be generated. For example, the driving level is divided into 1-5 levels, with level 1 indicating the lowest driving difficulty and level 5 indicating the highest driving difficulty. A small family car driving on a normal urban road with good vehicle condition and moderate power performance may be assessed as a driving level of 2; while a fully loaded large truck driving on a mountain road may be assessed as a driving level of 4.

[0063] The target driver's driving information is processed to generate the target driver's driving behavior information. The on-board driving behavior monitoring system records the driver's accelerator pedal stroke, brake pedal stroke and steering wheel operation data in detail. During a city road driving process, by analyzing the accelerator pedal stroke change curve, it was found that the driver's accelerator pedal stroke was large and accelerated quickly when starting and overtaking, but the driver was able to release the pedal in time and decelerate smoothly when approaching the intersection and following the car; the brake pedal stroke data showed that the driver was able to quickly step on the brakes when encountering emergencies (such as the sudden braking of the vehicle in front), and the braking force was moderate, avoiding the risk of vehicle loss of control caused by sudden braking; the steering wheel operation data showed that the driver operated smoothly when turning and changing lanes, and the steering angle and speed were properly controlled, and the vehicle could be accurately driven into the target lane. When driving on the highway, the accelerator pedal stroke is relatively stable and maintained within a reasonable range, so that the vehicle can drive stably at the specified speed; the brake pedal is used less frequently, and is mostly lightly stepped on to maintain a safe distance; the steering wheel is less operated, but when overtaking and avoiding obstacles, the driver can make steering movements quickly and accurately to ensure driving safety. These driving operation data can accurately reflect the driver's driving habits and operating characteristics under different road conditions.

[0064] Long-term collection of drivers' driving data can analyze their driving habits and preferences. For example, by counting the average driving speed of drivers on different types of roads, it is found that a driver likes to drive at a speed close to the speed limit on the highway (for example, the speed limit is 120 kilometers per hour, and the average speed is between 110-120 kilometers per hour), while on urban roads, he prefers to maintain a stable medium speed (average speed is 40-60 kilometers per hour), which shows that he has a high speed preference and speed adaptability to different road conditions. Analysis of overtaking frequency data shows that the driver overtakes more frequently on highways, but is relatively cautious on urban roads, which reflects his judgment of overtaking risks and driving style under different road conditions. From the perspective of following distance habits, drivers can maintain a safe distance from the vehicle in front on highways (depending on the speed and road conditions, the distance is between 100-200 meters), and in congested urban road conditions, they can also try to maintain an appropriate distance to avoid collision risks caused by frequent starts and stops. In addition, we can understand the driver's preference for specific road types. For example, in daily travel, as long as time permits, the driver prefers to choose scenic rural roads rather than busy urban main roads. This reflects his preference for the driving environment and will also affect his driving behavior and decision-making. Through the comprehensive analysis of these driving habits and preferences, the driving behavior information of the target driver can be generated, providing a basis for subsequent feature extraction and driving matching.

[0065] The target driver's driving behavior information is processed by feature extraction to generate the target driver's driving habit features and the target driver's driving ability features. Driving habit features are extracted from driving operation data and driving habit analysis. For example, in terms of acceleration habits, if the driver often quickly presses the accelerator pedal during starting and acceleration, so that the vehicle quickly reaches a higher speed, and the acceleration changes greatly during acceleration, it can be judged that his acceleration style is more aggressive; on the contrary, if the acceleration process is smooth and the acceleration changes little, the acceleration habit is more stable. Braking habits can be judged by the brake pedal stroke and frequency. If the brake pedal stroke is frequent and the depth is large, it means that the driver often brakes suddenly; if the braking operation is smooth, mostly light and slow, then the braking habit is good. Steering habits are evaluated through steering wheel operation data, such as whether the steering wheel turning angle is too large or too small when turning, whether the turning speed is too fast or too slow, and whether the curve can be predicted in advance and turned smoothly. If the driver can accurately control the steering wheel at the curve, slow down in advance and turn at a suitable angle, then the steering habit is good.

[0066] Analyze the consistency of the driver's driving behavior under different road conditions. For example, in special road conditions such as rainy days or at night, whether the driver can maintain driving habits similar to those under normal road conditions, such as appropriately reducing the speed, increasing the distance between vehicles, and using lights reasonably. If the driver can quickly adjust his driving habits under special road conditions and adopt a more cautious driving style, it means that he has good road condition adaptability and safety awareness, which is also an important part of the driving habit characteristics. Driving ability characteristics include the ability to deal with emergencies, vehicle control proficiency, and spatial perception. By simulating emergencies (such as the sudden appearance of obstacles, the sudden braking of the vehicle in front, etc.), observe the driver's reaction time and operation accuracy. For example, in the simulation test, when an obstacle suddenly appears 50 meters ahead, the driver can react within 1.5 seconds, quickly step on the brakes and reasonably turn to avoid it, and the vehicle does not show signs of loss of control or collision during the operation, indicating that his ability to deal with emergencies is strong; on the contrary, if the reaction time exceeds 2.5 seconds and the operation is panic, resulting in an increased risk of the vehicle deviating from the lane or colliding with obstacles, the ability to deal with emergencies is weak.

[0067] Vehicle handling proficiency can be evaluated from the driver's driving performance in complex road environments (such as narrow streets, mountain curves, highway ramps, etc.). When driving on narrow streets, can the driver accurately control the distance between the vehicle and roadside obstacles and flexibly make turns and U-turns; when driving on mountain curves, can the driver reasonably control the speed, select the appropriate gear, and maintain the stability of the vehicle according to the curvature and slope of the curve; on the highway ramp, can the driver accurately control the speed and steering, and smoothly complete the operation of merging into and exiting the highway, etc. Spatial perception ability is reflected in the driver's ability to judge and utilize the space around the vehicle. For example, in operations such as parking, overtaking and changing lanes, can the driver accurately judge the distance and relative position relationship between the vehicle and surrounding vehicles and obstacles to avoid scratches and collision accidents. Through the comprehensive evaluation of these driving ability characteristics, a more comprehensive understanding of the driver's driving ability level can be obtained.

[0068] The target driver's driving habit characteristics and the target driver's driving ability characteristics are processed to generate driving matching information for the target driving vehicle. It is assumed that drivers are divided into different types according to their driving habit characteristics and driving ability characteristics, such as aggressive, stable, cautious, etc., and vehicles are divided into low difficulty, medium difficulty, high difficulty, etc. according to the vehicle's driving level information. For aggressive drivers, their driving style is bold and they pursue speed and control pleasure. They may have a higher matching degree with high-performance and difficult-to-drive vehicles (such as sports cars and sports cars); while stable drivers focus on driving safety and comfort and are more suitable for driving medium-difficulty family cars; cautious drivers have a conservative driving style and do not have high requirements for vehicle controllability. They may have a better matching degree with small vehicles (such as mini cars) with low driving difficulty. Consider the matching of driving ability characteristics with vehicle characteristics. For example, drivers with strong ability to cope with emergencies can better control vehicles with higher driving difficulty and better power performance, because they can quickly respond correctly when the vehicle is driving at high speed or encountering emergencies, giving full play to the performance advantages of the vehicle; and drivers with high vehicle control proficiency can better adapt to complex road conditions and special driving scenarios, and complement vehicles with good control performance. Drivers with good spatial perception ability have more advantages when driving large vehicles or driving in narrow spaces, and have a higher matching degree with the corresponding type of vehicles. By establishing such a matching relationship between driving habits, ability characteristics and vehicle type and driving difficulty, driving matching information of the target driving vehicle can be generated, providing a reference that is more in line with the actual situation of the driver for subsequent path planning.

[0069] The target vehicle's driving level information and the target driving vehicle's driving matching information are processed to generate several candidate driving routes. According to the target vehicle's driving level information, the road types and road conditions suitable for the vehicle are screened. For example, vehicles with lower driving levels (such as novice drivers of small cars) give priority to roads with wide roads, small traffic volume, good road conditions and relatively simple traffic rules, such as urban secondary roads and newly built urban expressways, and avoid narrow, congested, complex intersections or poor road conditions (such as narrow streets in old urban areas and roads under construction). Vehicles with higher driving levels (such as experienced drivers driving high-performance vehicles) can consider a variety of road types including expressways, mountainous tourist roads with many bends but beautiful scenery, but other factors still need to be considered when making choices, such as real-time traffic conditions and weather conditions.

[0070] Consider the driving matching information and further optimize the candidate driving routes. For drivers who like high-speed driving and have strong driving ability, if the traffic flow allows, they should give priority to expressways or urban expressways with higher speed limits, and try to choose sections with good road conditions and wide sight lines to meet their driving preferences; for drivers who focus on comfort and safety, they should choose routes with high road flatness, good traffic order, and complete facilities along the way (such as more service areas and gas stations), and avoid passing through construction sections, bumpy roads or areas with chaotic traffic. At the same time, according to the driver's preference for specific road types (such as scenic roads), roads that meet their preferences will be included in the candidate route range when possible. For example, when planning a route from city A to city B, if the driver likes the scenery of rural roads, and the current traffic conditions and vehicle driving level allow, the route passing through some scenic rural roads will be selected as one of the candidate routes and comprehensively evaluated together with other conventional routes.

[0071] Several candidate driving routes are processed to generate vehicle driving influencing factors. For each candidate driving route, its key features are quantified, such as route length, road slope change, number and curvature of bends, number of traffic control points, traffic flow changes, and complexity of the environment along the way. For example, a candidate route is 50 kilometers long, including 5 sections with large slopes (slopes between 5% and 10%), 10 bends (curvature radius of bends between 50 and 200 meters), and passes through 2 traffic control points along the way (such as intersections with many traffic lights or speed limit sections). The traffic flow varies in different sections (some sections have large traffic flow, with an average of 500-800 vehicles passing through per hour, and some sections have small traffic flow, with an average of 100-300 vehicles passing through per hour). The environment along the way includes urban areas, suburbs, and a section close to the mountains (with high environmental complexity).

[0072] These features are quantified. It is assumed that the route length is directly quantified in kilometers. The road slope change is weighted and quantified according to the slope size and the length of the road section (for example, for every 1% increase in slope, the quantified value increases by 0.1, and the longer the road section, the higher the weight). The number of curves and curvature are weighted and quantified according to the inverse of the curve curvature radius (for example, the smaller the curvature radius, the larger the quantified value, the more curves, and the higher the total quantified value). The number of traffic control points is directly used as the quantified value. The traffic flow change is weighted and quantified according to the traffic flow size and the change range (for example, the larger the traffic flow and the larger the change range, the higher the quantified value). Different quantified values ​​are set for the complexity of the environment along the way according to different regional types (for example, 1 for urban areas, 0.5 for suburbs, and 2 for complex areas such as mountainous areas). Through this quantification method, the characteristics of each candidate route are converted into computable values.

[0073] When calculating the vehicle driving impact factor, a weighted summation method is used to assign corresponding weights to each quantified route feature. The weight can be determined based on a large amount of actual driving data. For example, the change in road slope and the number of bends have a greater impact on the difficulty and safety of vehicle driving, and a higher weight (such as 0.3 and 0.25) can be assigned; the change in traffic flow and the number of traffic control points have an important impact on driving efficiency and comfort, and weights of 0.2 and 0.1 are assigned respectively; the complexity of the environment along the way has a relatively small impact, and a weight of 0.15 is assigned. Taking a candidate route as an example, the quantified value of its route length is 50, the quantified value of the road slope change is 8 (obtained according to the above calculation method), the quantified value of the number of bends and curvature is 6, the quantified value of the number of traffic control points is 2, the quantified value of the traffic flow change is 5, and the quantified value of the complexity of the environment along the way is 1.5. By performing such calculations on each candidate driving route, the respective vehicle driving impact factors are obtained. These impact factors can comprehensively reflect the degree of influence of different routes on vehicle driving, and provide an important basis for the final selection of the optimal driving route. In actual applications, vehicle driving influencing factors will be dynamically updated as vehicle status, driver behavior and road environment change, ensuring that the navigation path is always the most suitable option for the current situation.

[0074] As the age of a vehicle increases, its performance and reliability will gradually decline, which will affect its performance during driving and its ability to adapt to different road conditions. Obtain information such as the vehicle's production date and mileage, establish a vehicle aging assessment model, and analyze the impact of vehicle aging on key components such as engine performance, suspension system, and braking system. When calculating the impact factor of vehicle driving, the degree of vehicle aging is taken into account as an important factor. For severely aged vehicles, the driving difficulty level and driving impact weight under different road conditions are appropriately adjusted. For example, old vehicles may have reduced performance when climbing, accelerating, and other operations. When planning a route, the navigation system should avoid choosing routes with large slopes and frequent acceleration to ensure the safety and reliability of vehicle driving. The driver's emotional state (such as tension, anxiety, fatigue, anger, etc.) will significantly affect his driving behavior, and thus affect the safety and efficiency of vehicle driving. The driver's emotional state is evaluated in real time through multiple methods such as monitoring the driver's facial expressions through in-car cameras, voice analysis of the driver's tone of voice, and driving behavior analysis (such as the frequency and amplitude changes of acceleration, braking, and steering operations). When calculating the factors affecting vehicle driving, the driver's emotional state is taken into account as a dynamic factor. When it is detected that the driver is emotionally unstable, the quantitative value and weight of the driving behavior characteristics are adjusted accordingly. For example, an emotionally excited driver may exhibit dangerous driving behaviors such as sudden acceleration, sudden braking, and frequent lane changes. The navigation system should adjust the route planning in time according to this situation to avoid choosing routes with complex road conditions and heavy traffic flow, and at the same time remind the driver to stay calm and drive safely.

[0075] S105, processing the environmental influencing factors and the road influencing factors based on a target vehicle navigation path generation model to generate initial vehicle navigation path information.

[0076] In one implementation, environmental impact factors and road impact factors are processed based on the target vehicle navigation path generation model to generate a set of candidate driving paths within a preset time period. The target vehicle navigation path generation model receives environmental impact factors and road impact factors as input data. For example, environmental impact factors include information such as the degree of slipperiness of the road due to heavy rain (calculated based on precipitation data and road friction model), the risk of rockfall around the road (based on the terrain and meteorological trends on both sides of the road); road impact factors include data such as the real-time traffic flow of the current road (obtained through equipment such as geomagnetic sensors), traffic control conditions (such as partial lane closures due to road construction), etc.

[0077] Based on these influencing factors and combined with map information, the model searches for possible driving routes within a preset time period (such as the next hour) and generates a set of candidate driving routes. Assuming that the vehicle is currently located in the city center of city A and the destination is a commercial district in city B, the model will consider multiple main roads starting from city A and the highways and provincial roads connected to it, and screen and combine these roads according to environmental and road influencing factors. For example, when the weather conditions are good and the traffic volume is small, the highway directly connecting city A and city B may be preferred as the main driving route, and multiple optional urban roads from the city center to the entrance of the highway will be considered; if there is heavy rain and part of a highway section has safety hazards due to water accumulation (high environmental impact factor), the model will avoid this section when searching for the route and choose other relatively safe and traffic-friendly road combinations, such as bypassing another highway leading to city B through the city's ring road or other secondary roads.

[0078] The candidate driving path set within a preset time period is processed to generate the correlation between different candidate driving paths and the attribute information of each candidate driving path, wherein the attribute information of the candidate driving path includes the path length, estimated driving time, environmental friendliness of the path and road safety. For the generated candidate driving path set, the correlation between different paths is analyzed. For example, two candidate paths may intersect at a certain intersection, or a certain section of one path may be a branch of another path. Taking the urban road network as an example, path A and path B may both pass through a large transportation hub in the city center, where the two paths can be converted to each other; path C may be part of path A, but it forks at a certain node and leads to different areas. This correlation information is very important for path planning, because in actual driving, the driver may switch between different paths according to the real-time road conditions.

[0079] Calculate the conversion cost between paths. For example, switching from path A to path B may require a certain amount of time and operation costs at the traffic hub, including waiting for traffic lights, changing lanes, turning, etc. If the traffic volume at the traffic hub is large, the conversion cost will increase accordingly; on the contrary, if the traffic organization is reasonable, such as setting up dedicated turning lanes and signal light phases, the conversion cost will be reduced. By analyzing the path relevance and conversion cost, more flexible navigation suggestions can be provided to drivers, so that they can quickly choose a suitable alternative path when encountering unexpected road conditions (such as sudden accidents or congestion on the road ahead). Use the road mileage information in the map data to accurately calculate the length of each candidate driving path. For example, candidate path D goes from the starting point of city A to the end point of city B, passing through multiple urban roads and a section of highway. By accumulating the length of each section, the total length of path D is 150 kilometers. Path length is one of the important factors affecting driving time and energy consumption. When other conditions are the same, shorter paths are usually more popular, but other attribute information needs to be considered comprehensively.

[0080] Combine real-time traffic flow data, road speed limit information, and environmental factors (such as the impact of weather on vehicle speed) to estimate the travel time of each path. When traffic flow is normal and weather is good, the travel time can be preliminarily estimated based on the road speed limit and path length. For example, a 60-kilometer section of a highway with a speed limit of 80 kilometers per hour is theoretically 45 minutes long; but if the real-time traffic flow is large and the average vehicle speed can only reach 60 kilometers per hour, the actual travel time will increase to 1 hour. At the same time, considering that heavy rain may cause vehicles to slow down, according to historical data and model predictions, the speed may decrease by 20%-30% in heavy rain, thereby further adjusting the estimated travel time. Consider environmental factors along the path, such as whether it passes through ecologically sensitive areas such as nature reserves and parks, as well as the air quality around the road (obtained through data sharing with environmental protection departments or on-board air quality monitoring equipment). For example, most of the sections of Path E pass through areas with good greening in the city and are far away from industrial pollution areas, so it is more environmentally friendly; while Path F needs to pass through an industrial park, the surrounding air quality is poor, and it is less environmentally friendly. In environmentally friendly driving scenarios (such as driving new energy vehicles or drivers with higher requirements for environmental quality), paths with higher environmental friendliness will have more advantages.

[0081] Road safety is assessed by comprehensively considering the road infrastructure conditions (such as road smoothness, street lighting conditions, road sign clarity, etc.), traffic control conditions (such as the setting of safety warning signs on construction sections, whether traffic lights are working properly, etc.), and environmental factors (such as road safety hazards under severe weather conditions). For example, a road has just completed road repairs, has good smoothness, sufficient street lighting, and no sections under construction, so its safety is relatively high; while another road has been in disrepair for many years, has many potholes, and some street lights are damaged, which poses a greater safety risk when driving at night. At the same time, in severe weather such as heavy rain and fog, the road is slippery and the line of sight is obstructed, which will significantly reduce safety. The model will quantitatively evaluate the safety of each candidate path based on these factors.

[0082] The correlation between different candidate driving paths and the attribute information of each candidate driving path are processed to generate the initial vehicle navigation path information. Based on the correlation and attribute information of different candidate driving paths, the paths are comprehensively evaluated. For example, for path G and path H, path G is shorter (120 kilometers), but the estimated driving time is longer (1.5 hours), because some sections of it have heavy traffic and pass through a road under construction (low road safety), but the environmental friendliness is better; path H is longer (135 kilometers), with an estimated driving time of 1.2 hours, good road conditions and high safety, but average environmental friendliness. The model calculates the comprehensive scores of the two paths based on preset weights (such as a path length weight of 0.3, an estimated driving time weight of 0.4, a road safety weight of 0.2, and an environmental friendliness weight of 0.1). The comprehensive score of path G is calculated as follows: (Assuming that the full score for environmental friendliness is 100, Path G scores 80 points; the full score for road safety is 100, Path G scores 60 points. The scores here are determined according to specific evaluation criteria and quantitative methods.) The comprehensive score of Path H is calculated as: By comparing the comprehensive scores, path G is relatively better after considering various factors and is preliminarily selected as one of the candidate paths in the initial vehicle navigation path information.

[0083] After a comprehensive evaluation of all candidate driving paths, one or more paths with the highest scores are selected as the initial vehicle navigation path information. For example, in the above example, if path G has the highest comprehensive score among all candidate paths, it will become the initial navigation path recommended to the driver. However, some special circumstances and user preferences need to be considered when determining the initial path. If the driver explicitly indicates in the navigation settings that he or she prefers paths with higher safety, even if path G has a slightly higher comprehensive score than other paths, if its safety score is relatively low, the system may adjust the selection based on user preferences, give priority to recommending paths with higher safety, or prompt the driver on the navigation interface about the safety differences between different paths, which is up to the driver to decide.

[0084] The initial path is optimized to check whether there are unreasonable sections or nodes in the path. For example, the initial path may contain some continuous sharp turns. If the vehicle type is a large truck, there may be great risks in driving on these sections. The model will try to find alternative sections to make the path smoother and safer. At the same time, combined with real-time traffic information updates (such as receiving information about sudden traffic accidents on a certain section of road that cause congestion during the path planning process), the initial path is adjusted in a timely manner to ensure that it is always the best choice under the current circumstances. The optimized initial vehicle navigation path information will include the detailed route of the path (such as the intersections and section names passed by, etc.), the estimated driving time, important tips along the way (such as construction sections, sections prone to congestion, etc.) and the comprehensive attribute evaluation results of the path (such as safety, environmental friendliness, etc.) to provide a basis for further optimizing the path according to vehicle driving influencing factors.

[0085] S106: Process the initial vehicle navigation path information based on the vehicle travel influencing factor to generate target vehicle navigation path information.

[0086] In one embodiment, the initial vehicle navigation path information is processed based on the vehicle driving influencing factor to generate weight information for each candidate driving path. Assume that there are three candidate driving paths: path A, path B, and path C. The vehicle driving influencing factor includes the comprehensive impact of multiple factors on driving, such as vehicle status, driver behavior, and the degree of matching between the vehicle and the driver. For example, the aging of the vehicle is taken into account in the vehicle driving influencing factor. If the vehicle is used for a long time, the engine performance is reduced, the suspension system is aged, and it is more difficult to climb and accelerate, then the weight of the path containing more steep slopes and sections requiring frequent acceleration will be reduced accordingly. Assuming that path A contains a long steep slope section and the vehicle is highly aged, the weight of path A may be reduced according to the calculation of the vehicle driving influencing factor.

[0087] The driver's driving habits and ability characteristics also play an important role in driving influencing factors. For example, if the driver has a high frequency of overtaking and likes to drive at high speed, he will be more adapted to the path with a wide road view, high speed limit and relatively small traffic volume, and its weight may increase; on the contrary, if the driver's driving style is more conservative, the weight of the path with complex road conditions, many bends or heavy traffic will be reduced. Assuming that the driver's driving behavior information shows that his overtaking frequency is low and he is not proficient in operating under complex road conditions, and path B passes through multiple complex intersections and sections with many bends, the weight of path B will be adjusted accordingly according to the driving influencing factors. In addition, the matching degree between the vehicle and the driver also affects the path weight. For example, a driver with insufficient driving experience matches a vehicle with lower driving difficulty, and the weight of the path with simple road conditions and clear traffic rules will be higher; while a driver with skilled driving skills may be more suitable for a path that is challenging but can bring out the performance of the vehicle when driving a high-performance vehicle. Assume that path C is a newly built urban expressway with a wide road, good road conditions and relatively simple traffic rules. For drivers with less driving experience, the weight of path C may be higher based on the vehicle driving influencing factors.

[0088] Based on the weight information of each candidate driving path, the candidate driving path set within the preset time period is processed to generate the navigation path information of the target vehicle. The weight information of each candidate driving path is calculated. Assume that the weight of path A is 0.3, the weight of path B is 0.25, and the weight of path C is 0.45 (the sum of the weights is 1) calculated by the vehicle driving influence factor. These weights reflect the relative advantages and disadvantages of each path under the current vehicle and driver conditions. For example, the higher weight of path C may be because its road conditions are more in line with the driver's driving habits and vehicle performance, and the difficulties faced by the vehicle when driving on this path (such as the complexity of the road conditions, the requirements for vehicle performance, etc.) are relatively small. The candidate driving path set within the preset time period is processed according to the weight information, and the path with the highest weight is selected as the navigation path information of the target vehicle. In the above example, path C has the highest weight and is therefore determined as the navigation path of the target vehicle. The navigation system will guide the vehicle to travel along path C, while continuously monitoring the changes in vehicle status, driver behavior, and road environment during the navigation process, and dynamically adjusting the path weight. For example, if a vehicle malfunctions during driving (such as the engine fault light comes on), the vehicle status changes, causing some sections of path C to pose a greater risk to vehicle driving (such as climbing sections that may increase the burden on the engine), the system will re-evaluate the weights of each path, which may reduce the weight of path C, and consider other paths with higher weights (such as path A or path B) as new target navigation paths to ensure that the vehicle always travels on the relatively optimal route.

[0089] In some special cases, although the target navigation path is selected based on the weight calculation, other factors still need to be considered. For example, although path C has the highest overall weight, if it encounters sudden road construction (real-time traffic information update) during driving, resulting in traffic obstruction on some sections of the path, even if its weight is high, the navigation system will re-evaluate the path based on the real-time situation. At this time, the system will quickly calculate the weights of other candidate paths (path A and path B) after considering the current real-time road conditions. If the comprehensive weight of path A becomes the highest after avoiding the construction section, the navigation system will adjust the navigation route in time and guide the vehicle to turn to path A. At the same time, the driver's real-time needs and preferences will also affect the path selection. If the driver expresses through the interactive interface of the navigation system during driving that he wants to give priority to a route with beautiful scenery (assuming that the scenery along the way of path B is good), the navigation system will adjust the path weight to a certain extent, increase the weight consideration of path B (such as incorporating the scenery factor into the weight calculation and giving a certain additional weight), and then re-evaluate each path, and determine whether to switch to path B or continue to maintain the original path selection based on the new weight information, so as to provide navigation services that better meet the needs of the driver and realize dynamic optimization and personalization of path planning.

[0090] The server generates initial path information based on the target vehicle navigation path generation model and environmental and road influencing factors, including generating a set of candidate paths, analyzing path relevance and attributes (such as length, time, environmental friendliness, and safety), and comprehensively evaluating and determining the initial path, while taking special circumstances and user preference optimization into consideration. The candidate path weights are then determined based on the vehicle driving influencing factors, and the path with the highest weight is selected as the target navigation path, which can be dynamically adjusted based on vehicle status, driver needs, and changes in road conditions. It provides vehicles with accurate navigation paths through complex calculations and analysis, and can also adapt to rules and environmental changes in different regions. It is highly practical and adaptable, and is expected to improve the accuracy, safety, and efficiency of vehicle navigation.

[0091] In one embodiment, if Figure 2 As shown, the present application also provides a vehicle navigation path processing device based on online information, comprising: An acquisition module 201 is used to acquire vehicle status information, target vehicle attribute information, target driver driving information, target road environment information, real-time traffic information, target road map information, and meteorological data of the target road map information within a preset time period; The processing module 202 is used to process the meteorological data of the target road environment information and the target road map information within a preset time period to generate an environmental impact factor; process the real-time traffic information and the target road map information to generate a road impact factor; process the vehicle status information, the target vehicle attribute information and the driving information of the target driver to generate a vehicle driving impact factor; process the environmental impact factor and the road impact factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; process the initial vehicle navigation path information based on the vehicle driving impact factor to generate target vehicle navigation path information.

[0092] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for evaluating the vehicle navigation path processing method based on online information, electronic device, electronic device, and readable storage medium embodiment, since it is basically similar to the above-mentioned vehicle navigation path processing method based on online information embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned vehicle navigation path processing method based on online information embodiment.

Claims

1. A vehicle navigation path processing method based on online information, characterized in that: include: Obtain vehicle status information, target vehicle attribute information, target driver driving information, target road environment information, real-time traffic information, target road map information, and weather data of the target road map information within a preset time period; Processing the target road environment information and the meteorological data of the target road map information within a preset time period to generate an environmental impact factor; Processing the real-time traffic information and the target road map information to generate a road impact factor; Processing the vehicle state information, the target vehicle attribute information and the target driver's driving information to generate a vehicle driving influencing factor; Processing the environmental influencing factors and the road influencing factors based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; The initial vehicle navigation path information is processed based on the vehicle travel influencing factor to generate target vehicle navigation path information.

2. The method according to claim 1, characterized in that Processing the target road environment information and the meteorological data of the target road map information within a preset time period to generate an environmental impact factor includes: Performing feature extraction processing on the target road environment information to generate road type features, road infrastructure features and road surrounding environment features; Processing the meteorological data of the target road map information within a preset time period to generate meteorological element information; Processing the meteorological element information to generate meteorological change trend information; Processing the road type characteristics, the road infrastructure characteristics and the road surrounding environment characteristics based on the meteorological change trend information to generate an environmental impact value; The environmental impact value is processed to generate an environmental impact factor.

3. The method according to claim 2, characterized in that Processing the real-time traffic information and the target road map information to generate a road impact factor includes: Processing the real-time traffic information to generate real-time traffic flow information and real-time traffic control information; Processing the real-time traffic flow information to generate a quantitative indicator of traffic flow; Processing the real-time traffic control information to generate vehicle traffic quantitative indicators; Processing the target road map information based on the vehicle flow quantitative index and the vehicle traffic quantitative index to generate a road impact value; The road impact value is processed to generate a road impact factor.

4. The method according to claim 3, characterized in that The method further comprises: The method includes a calculation formula for obtaining an environmental impact value, and the calculation formula is: ； in, represents the weight of the jth feature item under the i-th feature category, represents the quantitative value of the jth feature item under the i-th feature category, Represents the time function adjustment factor based on meteorological change trend information. When i=1, the i-th feature category refers to the road type feature. When i=2, the i-th feature category refers to the road infrastructure feature. When i=3, the i-th feature category refers to the road surrounding environment feature. Represents the number of feature items under each feature category; The method includes a calculation formula for obtaining a road impact value, and the calculation formula is: ； in, Represents the category of influencing factors, represents the weight of the zth influencing factor category, Represents the quantitative value of the zth influencing factor category. When the "influencing factor category" refers to the factors related to the quantitative indicators of traffic flow, When using the term "influencing factor category", it refers to the factors related to the quantitative indicators of vehicle traffic.

5. The method according to claim 1, characterized in that The vehicle state information, the target vehicle attribute information and the target driver's driving information are processed to generate a vehicle driving influencing factor, including: Processing the vehicle state information and the target vehicle attribute information to generate driving grade information of the target vehicle; Processing the driving information of the target driver to generate driving behavior information of the target driver; Performing feature extraction processing on the driving behavior information of the target driver to generate driving habit features and driving ability features of the target driver; Processing the driving habit characteristics of the target driver and the driving ability characteristics of the target driver to generate driving matching information of the target driving vehicle; Processing the driving grade information of the target vehicle and the driving matching information of the target driving vehicle to generate a plurality of candidate driving routes; Several candidate driving routes are processed to generate vehicle driving influencing factors.

6. The method according to claim 1, characterized in that The environmental influencing factors and the road influencing factors are processed based on the target vehicle navigation path generation model to generate initial vehicle navigation path information, including: Processing the environmental influencing factors and the road influencing factors based on the target vehicle navigation path generation model to generate a set of candidate driving paths within a preset time period; Processing a set of candidate driving paths within a preset time period to generate correlations between different candidate driving paths and attribute information of each candidate driving path, wherein the attribute information of the candidate driving paths includes path length, estimated driving time, environmental friendliness of the path, and road safety; The relevance of different candidate driving paths and the attribute information of each candidate driving path are processed to generate initial vehicle navigation path information.

7. The method according to claim 6, characterized in that The initial vehicle navigation path information is processed based on the vehicle travel influencing factor to generate target vehicle navigation path information, including: Processing the initial vehicle navigation path information based on the vehicle driving influencing factor to generate weight information of each candidate driving path; The candidate driving path set within a preset time period is processed based on the weight information of each candidate driving path to generate the navigation path information of the target vehicle.

8. A vehicle navigation path processing device based on online information, characterized in that: The device comprises: An acquisition module, used to acquire vehicle status information, target vehicle attribute information, target driver driving information, target road environment information, real-time traffic information, target road map information, and meteorological data of the target road map information within a preset time period; The processing module is used to process the meteorological data of the target road environment information and the target road map information within a preset time period to generate an environmental impact factor; process the real-time traffic information and the target road map information to generate a road impact factor; process the vehicle status information, the target vehicle attribute information and the driving information of the target driver to generate a vehicle driving impact factor; process the environmental impact factor and the road impact factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; process the initial vehicle navigation path information based on the vehicle driving impact factor to generate target vehicle navigation path information.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the vehicle navigation path processing method based on online information as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the vehicle navigation path processing method based on online information as claimed in any one of claims 1 to 7 is implemented.

Images