Route planning device and method based on intelligent navigation

Abstract

The invention belongs to the technical field of artificial intelligence, and discloses a route planning device and method based on intelligent navigation, and the device comprises a data collection and fusion module which is used for obtaining traffic data, vehicle data, user preference data and third-party service data, and transmitting the data to an intelligent route planning module; the intelligent route planning module is used for performing calculation according to the traffic data, the vehicle data, the user preference data, the third-party service data, the user travel mode and the travel characteristics to obtain a planning route and a planning scheme and sending the planning route and the planning scheme to the route presentation interaction module; the route presentation interaction module is used for receiving and displaying the planning route and the planning scheme; and obtaining and executing interaction adjustment information based on the planning route and the planning scheme. The travel efficiency of the user can be improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a route planning device and method based on intelligent navigation. Background Technology

[0002] With the widespread adoption of GPS and mobile internet technologies, in-car navigation and mobile map applications have become indispensable tools for people's daily travel. Traditional navigation systems, such as early GPS navigators and basic map applications, primarily provide users with the shortest or fastest route planning from their origin to their destination based on static electronic map data. To a large extent, they have solved the fundamental problem of how to reach a destination through navigation.

[0003] However, traditional navigation systems primarily rely on static road classifications and historical average vehicle speeds for planning, neglecting real-time road dynamics and user preferences. Inferences based solely on historical data cannot continuously optimize the overall user travel experience. In real-world travel scenarios, users not only focus on the navigation route itself but also seek to balance multiple objectives to meet their travel needs. Therefore, how to simultaneously meet users' travel planning needs while providing navigation, thereby improving travel efficiency, has become a problem to be solved. Summary of the Invention

[0004] This application provides a route planning device and method based on intelligent navigation. It can input traffic data, vehicle data, user preference data, third-party service data, user travel patterns, and travel characteristics into an intelligent route planning module for calculation and processing to obtain the currently preferred planned route and planning scheme. This application can process and analyze data such as current user preference data, thereby further refining the user's travel route planning needs while completing route navigation. This makes the user's travel route more personalized, eliminates the need to search for other destinations during the journey, and improves user travel efficiency.

[0005] In a first aspect, embodiments of this application provide a route planning device based on intelligent navigation, the device comprising:

[0006] The data acquisition and fusion module is used to acquire traffic data, vehicle data, user preference data, and third-party service data and send them to the intelligent route planning module;

[0007] The intelligent route planning module is used to calculate based on traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics, obtain the planned route and plan scheme, and send them to the route presentation and interaction module;

[0008] The route presentation and interaction module is used to receive and display the planned route and planning scheme; and to obtain and execute interactive adjustment information based on the planned route and planning scheme.

[0009] Furthermore, the device also includes:

[0010] The execution feedback module is used to obtain real-time vehicle location, real-time vehicle status, and real-time environmental conditions; compare the real-time vehicle location with the planned route to obtain the deviation value; and send the deviation value, real-time vehicle status, and real-time environmental conditions to the intelligent route planning module.

[0011] The intelligent route planning module is specifically used to receive deviation values, real-time vehicle status, and real-time environmental conditions, process them according to the path cost calculation model, obtain updated planned routes and updated planning schemes, and send them to the route presentation and interaction module.

[0012] The route presentation interaction module is specifically used to receive and display updated planned routes and updated planning schemes.

[0013] Furthermore, the intelligent route planning module includes a time cost calculation unit, an economic cost calculation unit, a comfort cost quantification unit, an energy consumption cost calculation unit, a weight determination unit, and a comprehensive calculation unit;

[0014] The time cost calculation unit is used to obtain the time cost based on the historical average travel time database and real-time traffic data;

[0015] The economic cost calculation unit is used to obtain the economic cost based on the road segment toll database and road segment distance;

[0016] The comfort cost quantification unit is used to obtain the comfort cost based on high-precision map data and road geometry data;

[0017] The energy cost calculation unit is used to calculate energy costs based on vehicle model and historical energy consumption data.

[0018] The weighting determination unit is used to obtain time weight, economic weight, comfort weight, and range and safety weight based on the user's travel pattern;

[0019] The comprehensive calculation unit is used to calculate the comprehensive cost of a road segment by weighting time cost and time weight, economic cost and economic weight, comfort cost and comfort weight, energy consumption cost and range safety weight; and to obtain the planned route and planning scheme based on the comprehensive cost of the road segment.

[0020] Furthermore, user travel modes include time-priority mode, economy-priority mode, comfort-priority mode, and range-priority mode.

[0021] In the time-priority mode, the time weight is 0.7, the economy weight is 0.1, the comfort weight is 0.1, and the range and safety weight is 0.1.

[0022] In the economy-first mode, the economic weight is 0.6, the time weight is 0.2, the comfort weight is 0.1, and the range and safety weight is 0.1.

[0023] In Comfort Priority Mode, the comfort weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the range and safety weight is 0.1.

[0024] In the range priority mode, the range safety weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the comfort weight is 0.1.

[0025] Furthermore, the time cost calculation unit is specifically used to obtain the basic travel time based on the historical average travel time database, and to obtain the real-time congestion coefficient based on real-time traffic data; it uses a machine learning network to process historical travel time data, real-time traffic flow data, weather data, and holiday data to obtain the prediction adjustment coefficient; and it multiplies the basic travel time, the real-time congestion coefficient, and the prediction adjustment coefficient to obtain the time cost.

[0026] Furthermore, the economic cost calculation unit is specifically used to obtain road and bridge tolls based on the road segment toll database; to obtain fuel costs based on road segment distance, vehicle fuel consumption per 100 kilometers, and fuel unit price; to obtain electricity costs based on road segment distance, vehicle electricity consumption per 100 kilometers, and electricity price; to obtain additional costs based on third-party service data interfaces; and to obtain the economic cost by adding the road and bridge tolls, fuel costs, and additional costs; or, to obtain the economic cost by adding the road and bridge tolls, electricity costs, and additional costs.

[0027] Furthermore, the comfort cost quantification unit is specifically used to obtain road geometry data based on high-precision map data, calculate the curvature coefficient based on the road geometry data; obtain the traffic light coefficient based on the traffic light density; obtain the congestion coefficient based on historical data and real-time road conditions; add the curvature coefficient, traffic light coefficient and congestion coefficient together, and then multiply by the basic comfort level to obtain the comfort cost.

[0028] Furthermore, the energy consumption cost calculation unit is specifically used to calculate the basic energy consumption based on the vehicle model and historical energy consumption data; calculate the elevation data using a digital elevation model to obtain the slope coefficient; calculate the wind speed coefficient based on real-time wind speed and direction; calculate the temperature coefficient based on real-time ambient temperature and a preset temperature-efficiency relationship table; and multiply the basic energy consumption, slope coefficient, wind speed coefficient, and temperature coefficient to obtain the energy consumption cost.

[0029] Furthermore, the intelligent route planning module is specifically used to acquire origin, destination, traffic data, and vehicle data; it uses a multi-objective A* algorithm to process traffic data and obtain K alternative routes; and it calculates the planned route and planning scheme based on the K alternative routes, user preference data, and third-party service data by the comprehensive calculation unit.

[0030] Secondly, embodiments of this application provide a route planning method based on intelligent navigation, the method comprising:

[0031] The data acquisition and fusion module obtains traffic data, vehicle data, user preference data, and third-party service data and sends them to the intelligent route planning module;

[0032] The intelligent route planning module calculates based on traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics to obtain the planned route and plan scheme, and sends it to the route presentation and interaction module;

[0033] The route presentation and interaction module receives and displays the planned route and planning scheme; it also obtains and executes interactive adjustment information based on the planned route and planning scheme.

[0034] In summary, compared with the prior art, the beneficial effects of the technical solution provided in this application include at least the following:

[0035] This application provides a route planning device based on intelligent navigation. This device can input traffic data, vehicle data, user preference data, third-party service data, user travel patterns, and travel characteristics into an intelligent route planning module for calculation and processing to obtain the currently preferred planned route and planning scheme. This application can process and analyze data such as current user preference data, thereby further refining the user's travel route planning needs while completing route navigation, making the user's travel route more personalized, eliminating the need to search for other destinations during the journey, and improving user travel efficiency. Attached Figure Description

[0036] Figure 1 This is a structural diagram of a route planning device based on intelligent navigation, provided as an exemplary embodiment of this application.

[0037] Figure 2 A flowchart illustrating an exemplary embodiment of this application provides a route planning method based on intelligent navigation. Detailed Implementation

[0038] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0039] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] Please see Figure 1 This application provides a route planning device based on intelligent navigation, which specifically includes:

[0041] The data acquisition and fusion module 101 is used to acquire traffic data, vehicle data, user preference data and third-party service data and send them to the intelligent route planning module.

[0042] The data acquisition and fusion module can collect data from various internal and external data sources. All the data described below can be directly acquired through this module, improving data acquisition efficiency. For example, the module acquires real-time traffic conditions, accidents, and traffic control information from traffic management departments and map service providers as vehicle data; it acquires remaining battery power, remaining fuel, average energy consumption, driving range, and vehicle model through the vehicle's CAN bus or mobile phone interconnection technology as vehicle data; it acquires user preference data through the human-machine interface set in the vehicle, allowing users to set preferences, such as avoiding highways or reducing tolls; it can also implicitly learn users' historical route selections through machine learning algorithms, thereby continuously optimizing; the module can also access charging pile operator data through third-party service data interfaces to obtain charging pile location, type, availability status, and price; access parking lot data to obtain available parking spaces and prices; and access catering and accommodation service data, etc., as third-party service data to further integrate multi-source data and improve users' travel efficiency.

[0043] The intelligent route planning module 102 is used to calculate based on traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics, obtain the planned route and planning scheme, and send them to the route presentation and interaction module.

[0044] In some embodiments, the intelligent route planning module includes a time cost calculation unit, an economic cost calculation unit, a comfort cost quantification unit, an energy consumption cost calculation unit, a weight determination unit, and a comprehensive calculation unit.

[0045] The time cost calculation unit is used to obtain the time cost based on the historical average travel time database and real-time traffic data.

[0046] The economic cost calculation unit is used to obtain the economic cost based on the road segment toll database and road segment distance.

[0047] The comfort cost quantification unit is used to obtain the comfort cost based on high-precision map data and road geometry data.

[0048] The energy cost calculation unit is used to obtain energy costs based on vehicle model and historical energy consumption data.

[0049] The weight determination unit is used to obtain time weight, economic weight, comfort weight, and range and safety weight based on the user's travel pattern.

[0050] The comprehensive calculation unit is used to calculate the comprehensive cost of a road segment by weighting time cost and time weight, economic cost and economic weight, comfort cost and comfort weight, energy consumption cost and range safety weight; and to obtain the planned route and planning scheme based on the comprehensive cost of the road segment.

[0051] In some embodiments, the user travel mode includes a time-priority mode, an economy-priority mode, a comfort-priority mode, and a range-priority mode; in the time-priority mode, the time weight is 0.7, the economy weight is 0.1, the comfort weight is 0.1, and the range safety weight is 0.1; in the economy-priority mode, the economy weight is 0.6, the time weight is 0.2, the comfort weight is 0.1, and the range safety weight is 0.1; in the comfort-priority mode, the comfort weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the range safety weight is 0.1; in the range-priority mode, the range safety weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the comfort weight is 0.1.

[0052] In some embodiments, the time cost calculation unit is specifically used to obtain the basic travel time based on the historical average travel time database, obtain the real-time congestion coefficient based on real-time traffic data, process the historical travel time data, real-time traffic flow data, weather data and holiday data using a machine learning network to obtain the prediction adjustment coefficient, and multiply the basic travel time, the real-time congestion coefficient and the prediction adjustment coefficient to obtain the time cost.

[0053] The time cost calculation unit calculates basic travel times based on a historical average travel time database, categorized by road segment and time period. It then dynamically calculates real-time congestion coefficients using real-time traffic data, such as congestion indices and accident impacts. Preferably, congestion levels are divided into four categories based on real-time traffic data: smooth traffic, light congestion, moderate congestion, and severe congestion. The classification uses a threshold method: if the average vehicle speed is greater than 80% of the road speed limit, it is considered smooth traffic with a real-time congestion coefficient of 1.0; if the average vehicle speed is between 50% and 80% of the speed limit, it is considered light congestion with a real-time congestion coefficient of 1.2; if the average vehicle speed is between 30% and 50% of the speed limit, it is considered moderate congestion with a real-time congestion coefficient of 1.5; and if the average vehicle speed is less than 30% of the speed limit, it is considered severe congestion with a real-time congestion coefficient of 2.0. The time cost calculation unit can also dynamically update the congestion level of each road segment based on the real-time data stream.

[0054] In some embodiments, time series analysis or machine learning methods are used, combined with factors such as weather and holidays, to predict future travel times and obtain prediction adjustment coefficients. Specifically, firstly, historical travel time data, real-time traffic flow data, weather data, and holiday indicators are collected; after processing the above data, time characteristics are obtained: hour, day of the week, and whether it is a holiday; weather characteristics: rainfall level (can be no rain, light rain, heavy rain), temperature segment (can be <0℃, 0-25°C, >25℃); traffic characteristics: real-time congestion index, number of accidents; then, an LSTM neural network can be used, with the input being the travel time series and feature data of the past N hours, to output the predicted travel time value for the next M hours; finally, the predicted travel time of each road segment in the future period is output as a prediction adjustment coefficient for time cost calculation.

[0055] In some embodiments, the economic cost calculation unit is specifically used to obtain road and bridge tolls based on the road segment toll database; obtain fuel costs based on road segment distance, vehicle fuel consumption per 100 kilometers and fuel unit price; obtain electricity costs based on road segment distance, vehicle electricity consumption per 100 kilometers and electricity price; obtain additional costs based on third-party service data interfaces; add road and bridge tolls, fuel costs and additional costs to obtain economic costs; or add road and bridge tolls, electricity costs and additional costs to obtain economic costs.

[0056] Among them, road and bridge tolls are obtained directly from the road segment toll database; additional costs are obtained directly from third-party service data interfaces, and additional costs may include factors that can affect user choices, such as charging service fees and parking fees.

[0057] In some embodiments, for gasoline vehicles, fuel cost = distance × fuel consumption per 100 kilometers × fuel price per unit / 100; for electric vehicles, electricity cost = distance × electricity consumption per 100 kilometers × electricity price / 100.

[0058] In some embodiments, the comfort cost quantification unit is specifically used to obtain road geometry data based on high-precision map data, calculate the curvature coefficient based on the road geometry data, obtain the traffic light coefficient based on the traffic light density, obtain the congestion coefficient based on historical data and real-time road conditions, and then multiply the curvature coefficient, traffic light coefficient and congestion coefficient by the basic comfort level to obtain the comfort cost.

[0059] The calculation process for the curvature coefficient is as follows: obtain road geometry data from a high-precision map data provider, which may include a sequence of node coordinates; take three consecutive nodes (P1, P2, P3) for the road segment, and calculate the angle θ between vectors P1P2 and P2P3; calculate the radius of curvature R = (segment length) / θ (radians); curvature coefficient = 1.0 + (1.0 / R) * scaling factor, where the scaling factor is calibrated based on experiments using historical data to ensure that the curvature coefficient is within the range of 1.0 to 2.0.

[0060] The traffic light coefficient is calculated based on the number of traffic lights per unit distance; higher density results in higher costs, with a coefficient ranging from 1.0 to 1.5, and the specific value can be flexibly set. The congestion coefficient is calculated based on historical data and real-time traffic conditions; higher congestion probability results in higher costs, with a coefficient ranging from 1.0 to 2.0, and the specific value can also be flexibly set. Other factors, such as road surface smoothness and the number of lanes, can also be considered, and these can be pre-input into the comfort cost quantification model according to the developer's needs for processing.

[0061] In some embodiments, the energy consumption cost calculation unit is specifically used to calculate the basic energy consumption based on the vehicle model and historical energy consumption data; calculate the elevation data using a digital elevation model to obtain the slope coefficient; calculate the wind speed coefficient based on real-time wind speed and direction; calculate the temperature coefficient based on real-time ambient temperature and a preset temperature-efficiency relationship table; and multiply the basic energy consumption, slope coefficient, wind speed coefficient, and temperature coefficient to obtain the energy consumption cost.

[0062] The basic energy consumption is calculated based on the vehicle model and historical energy consumption data. Preferably, the basic energy consumption = road distance × energy consumption per unit distance. The vehicle model directly affects the energy consumption per unit distance. The energy cost calculation model has a built-in vehicle energy consumption database, which queries the typical energy consumption value for different models. For example, for the electric vehicle model "Tesla Model 3", the energy consumption per unit distance is 15kWh / 100km, so the basic energy consumption = road distance (km) × 15 / 100. If specific model data is unavailable, the average energy consumption value of the vehicle category (such as SUV, sedan) is used as the default energy consumption per unit distance.

[0063] In some embodiments, energy consumption increases on uphill sections and decreases on downhill sections; therefore, elevation data used in the Digital Elevation Model (DEM) is obtained from a Geographic Information System, or elevation data is integrated through a real-time traffic data interface; for each road segment, the elevation values ​​H1 and H2 of the starting and ending points are obtained; the slope angle α = arctan((H2-H1) / segment distance); the slope coefficient = 1.0 + k*α, where k is a calibration parameter (e.g., k = 0.1), α > 0 for uphill sections and α < 0 for downhill sections.

[0064] In some embodiments, headwinds increase energy consumption, while tailwinds decrease energy consumption. Therefore, wind speed and direction are obtained through a real-time meteorological data interface. If the vehicle's driving direction is at an angle of 180° to the wind direction (complete headwind) and the wind speed is 10 m / s, then the wind speed coefficient = 1.0 + 0.05 * (10 / 5) = 1.1, meaning energy consumption increases by 10%. If the wind is completely tailwind, the wind speed coefficient = 1.0 - 0.03 * (10 / 5) = 0.94, meaning energy consumption decreases by 6%.

[0065] In some embodiments, extreme temperatures can affect vehicle battery efficiency. The chemical activity and internal resistance of power batteries, especially lithium-ion batteries, are significantly affected by ambient temperature. At low temperatures, such as below 10°C, the viscosity of the battery electrolyte increases, the migration speed of lithium ions slows down, and the internal resistance increases, leading to a decrease in usable capacity and charge / discharge efficiency, manifested as increased energy consumption. At high temperatures, such as >30°C, although the internal resistance may decrease slightly in the short term, the vehicle system will activate the cooling system to protect the battery, resulting in a significant increase in air conditioning energy consumption. Sustained high temperatures may also accelerate battery aging and affect long-term efficiency. Therefore, the real-time ambient temperature of the area where the vehicle is located can be obtained through a real-time meteorological data interface. Then, through a built-in temperature-efficiency relationship lookup table, the temperature coefficient (Kt) can be calculated based on a piecewise function or lookup table method to ensure the highest efficiency within the typical operating temperature range, with corrections made at extreme temperatures.

[0066] Preferably, the formula for calculating the temperature coefficient (Kt) is: Kt=1.0+α*|T-T_optimal| (when T exceeds the comfort range); where T is the real-time ambient temperature; T_optimal is the range of optimal battery operating efficiency, within which Kt=1.0; α is the temperature sensitivity coefficient, which is a positive number calibrated through historical data and experiments, and can take different values ​​for low temperature and high temperature ranges.

[0067] Preferably, the temperature-efficiency relationship is shown in Table 1 below:

[0068] Table 1

[0069]

[0070]

[0071] In some embodiments, the time-priority mode prioritizes the shortest travel time and is suitable for time-sensitive users; the economy-priority mode prioritizes reducing travel costs and is suitable for cost-sensitive users; the comfort-priority mode prioritizes routes with smooth road conditions, few traffic lights, and low probability of congestion and is suitable for users sensitive to travel comfort; the range-priority mode can also be used for long-distance travel of electric vehicles, prioritizing the range safety of small vehicles and avoiding accidents caused by sudden power loss during driving.

[0072] The travel characteristics can be long-distance or short-distance travel; both the user's travel mode and travel characteristics are preset by the user, allowing the user to flexibly arrange travel plans. Correct input makes the subsequent calculations of the intelligent route planning module more accurate.

[0073] In some embodiments, users can also customize the weights of each factor, and the weight allocation can be dynamically optimized based on the user's historical choices and learning models. For example, if a user frequently chooses to rest during long-distance travel, the intelligent route planning module will automatically increase the comfort weight.

[0074] In some embodiments, the user rest judgment mechanism is as follows: Vehicle status is monitored in real time through vehicle data-related interfaces. When the vehicle speed is zero for more than a preset threshold time, and the vehicle is located within a rest area such as a service area or parking lot, it is determined as a rest event. Simultaneously, the intelligent route planning module can also record the duration, location, and frequency of each rest. Preferably, the preset threshold time can be 15 minutes, avoiding system misjudgments caused by a preset threshold time that is too short, such as during sudden traffic jams where stopping for more than 15 minutes is very easy; in actual travel environments, it is extremely rare for the vehicle speed to be zero for more than 15 minutes, thus avoiding user habit optimization failures caused by a preset threshold time that is too long.

[0075] In some embodiments, the intelligent route planning module can also count the number of times a user takes a break during several long-distance trips in the past, such as when the trip distance is greater than 200 kilometers. If the average number of breaks exceeds a preset threshold, such as once every 4 hours, it is identified as "frequent breaks" and the comfort weight is automatically increased, for example, the comfort weight is adjusted from 0.1 to 0.2.

[0076] In some embodiments, the intelligent route planning module is specifically used to acquire origin, destination, traffic data, and vehicle data; process the traffic data using a multi-objective A* algorithm to obtain K alternative routes; and calculate the planned route and planning scheme based on the K alternative routes, user preference data, and third-party service data by the comprehensive calculation unit.

[0077] The system can acquire origin, destination, real-time road network data, and real-time vehicle range. Using a multi-objective A* algorithm, it searches for K non-dominated paths in the road network graph to obtain K alternative paths (Path1, Path2, ..., PathK). Based on the K alternative paths, vehicle energy consumption model, user preferences, and third-party service data, it performs the following calculations on each path Path_i (i = 1 to K): Calculate the total time T_i = Σ(road segment time cost) + charging time + rest time; calculate the total cost C_i = Σ(road segment monetary cost) + charging cost + parking fee, etc.; determine whether mid-journey charging is needed; if the total energy consumption of the path is greater than the current range, it is marked as needing charging and the optimal charging station is inserted; calculate the number of rests: based on driving time and the user's historical rest frequency, the suggested number of rests is calculated; the output planning scheme can include path ID (as the planned route), total time, total cost, number of charging needs, number of rests, comfort score, and range safety score.

[0078] The route presentation interaction module 103 is used to receive and display the planned route and planning scheme; and to obtain and execute interactive adjustment information based on the planned route and planning scheme.

[0079] Among them, the route presentation and interaction module can present the planned route and planning scheme in a graphical way through various terminal devices.

[0080] In some embodiments, the route presentation interaction module can use the in-vehicle central control screen to render the optimal route on a high-resolution map and mark key nodes; for example, charging points are represented by charging pile icons, and clicking on them can view the details of the charging point; rest stops are represented by coffee cup icons, and the suggested rest duration is displayed; the total remaining time and arrival time can also be displayed in real time at the top of the screen.

[0081] In some embodiments, the route presentation interaction module can also be a mobile app, where users can drag midpoints on the route using gestures, and the intelligent route planning module will then recalculate the path and update the visualization interface.

[0082] In some embodiments, voice prompts may also be included, incorporating TTS technology, to announce key turns, traffic congestion alerts, charging suggestions, etc.

[0083] In some embodiments, multiple alternative routes can be displayed in split-screen or pop-up format, and the total time, cost, and comfort rating of each route can be compared to facilitate user selection. For example, if a user long-presses a location on the map to set it as a stop, the intelligent route planning module will replan the route in real time, update the ETA and energy consumption prediction, and refresh the visualization interface.

[0084] In some embodiments, the device further includes:

[0085] The execution feedback module is used to obtain real-time vehicle location, real-time vehicle status, and real-time environmental conditions; compare the real-time vehicle location with the planned route to obtain the deviation value; and send the deviation value, real-time vehicle status, and real-time environmental conditions to the intelligent route planning module.

[0086] The intelligent route planning module is specifically used to receive deviation values, real-time vehicle status, and real-time environmental conditions, process them according to the path cost calculation model, obtain updated planned routes and updated planning schemes, and send them to the route presentation and interaction module.

[0087] The route presentation interaction module is specifically used to receive and display updated planned routes and updated planning schemes.

[0088] The execution feedback module obtains real-time vehicle coordinates and speed from the GPS module, acquires data such as remaining battery power, fuel consumption, vehicle speed, and mileage through the CAN bus / OBD-II interface, and obtains road conditions and weather data from the real-time traffic data interface; it compares the actual location with the planned route, and if the deviation exceeds a preset deviation value, it triggers replanning; it monitors sudden traffic events and assesses their impact on the current route; it sends real-time data to the intelligent route planning module, re-runs the multi-objective optimization algorithm, and generates a new route; and it informs the user of the route change through a visual interface and voice prompts, displaying the reason for the change.

[0089] The execution feedback module can also collect data such as the user's actual route selection, midway point adjustments, and preference deviations; and use machine learning algorithms to update the user preference model for subsequent planning.

[0090] Specifically, the machine learning model optimization process is as follows: acquire users' historical travel data and real-time feedback data; first, discover the preference patterns of similar user groups to fill in the missing preferences of the current user; then, use user feedback as a reward signal (e.g., a positive reward for accepting the recommended route and a negative reward for rejecting it), and adjust the weight allocation strategy through Q-learning or policy gradient methods; finally, obtain the updated user preference model for the next route planning.

[0091] The route planning device based on intelligent navigation provided in the above embodiments can input traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics into the intelligent route planning module for calculation and processing to obtain the current user's preferred planned route and planning scheme. This application can process and analyze data such as current user preference data, thereby further refining the user's travel route planning needs while completing route navigation, making the user's travel route more personalized, eliminating the need to search for other destinations during the journey, and improving the user's travel efficiency.

[0092] In some embodiments, this device can be deployed on the central control unit of a smart electric vehicle or on a user's high-performance smartphone, with the operating system being a customized Android Automotive OS or interconnected with a mobile app via CarPlay / Android Auto; real-time traffic data is sourced from a map API; charging pile data is accessed through mainstream operator platforms; and vehicle data is obtained via a standard CAN bus protocol or OBD-II interface.

[0093] In some embodiments, an electric vehicle owner plans a long-distance inter-provincial trip. The vehicle has a full-charge range of 500 kilometers, and the destination is 600 kilometers away. The user prefers to "save as much time as possible" and wants to avoid extreme congestion. The user enters the destination into the vehicle's navigation system, and the system automatically obtains the current battery level, remaining range, and average energy consumption through the vehicle's data interface. Immediately afterwards, the data acquisition module is invoked to obtain real-time traffic conditions from the origin to the destination, information on all charging stations along the route, and traffic flow predictions for the next period. The intelligent route planning module first determines that the current battery level is insufficient to reach the destination in one trip, requiring at least one charging. Under the "save time" preference, the time weight (Wt) is set to the highest. The intelligent route planning module evaluates multiple charging options; for example, should the user charge when the remaining range is 100 kilometers, or when it is 50 kilometers? Should the user choose a charging station with fast but slightly higher charging speed along the way, or a slightly detour but free charging station? The intelligent route planning module ultimately generates the optimal plan, recommending that the user charge at service area A within the first 300 kilometers. The rationale is as follows: Based on predictions, the service area has a high vacancy rate during the user's arrival time, eliminating the need for queuing; the charging station is a 150kW supercharger, adding approximately 300 kilometers of range in 30 minutes, with the shortest total time. Simultaneously, the system calculates that this charging coincides with the suggested driver rest time. Furthermore, based on parking data around the destination, it predicts potential parking spaces upon the user's arrival and recommends parking lot B. Finally, a complete route plan is presented to the user, clearly marked: Total travel time: 7 hours (including charging and rest); Total cost: Highway toll XX yuan + Electricity cost YY yuan; Key milestones: 30-minute charging / rest at service area A, expected arrival at parking lot B. Real-time monitoring is implemented after navigation begins. If an accident occurs 20 kilometers ahead causing severe congestion, dynamic replanning will immediately initiate, calculating a new route and assessing its impact on range and charging plans. If charging station adjustments are necessary, the user will be notified promptly.

[0094] The above embodiments follow users' preference for saving time and select the option with the shortest total time; they also accurately plan charging routes, selecting stations with high vacancy rates and fast charging speeds to avoid queuing; in addition, they intelligently combine charging and rest time to improve the travel experience; they provide destination parking prediction to solve the parking problem users face on the last leg of their journey; and they can respond quickly to unexpected road conditions to ensure that the planning is always optimal.

[0095] In some embodiments, this application unifies the modeling of real-time traffic data, real-time vehicle energy consumption data, user preference data, and third-party service data to construct a digital twin model that comprehensively describes the travel environment, providing a solid data foundation for intelligent planning. It also proposes a path cost calculation model that integrates time, cost, comfort, and range safety as unified optimization objectives, employing a dynamic weight allocation mechanism and an improved multi-objective graph search algorithm to generate a comprehensive optimal route for users. Furthermore, this application not only reflects the current state but also predicts future states based on historical data and machine learning models, proactively recommending intermediate stops accordingly, thus achieving a leap from simple path planning to complex trip management.

[0096] Please see Figure 2 Another embodiment of this application provides a route planning method based on intelligent navigation, the method comprising:

[0097] Step S1: The data acquisition and fusion module acquires traffic data, vehicle data, user preference data, and third-party service data and sends them to the intelligent route planning module.

[0098] In step S2, the intelligent route planning module calculates based on traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics to obtain the planned route and plan scheme, and sends it to the route presentation and interaction module.

[0099] Step S3: The route presentation interaction module receives and displays the planned route and planning scheme; it obtains and executes interactive adjustment information based on the planned route and planning scheme.

[0100] The specific limitations of the route planning method based on intelligent navigation provided in this embodiment can be found in the embodiment of the route planning device based on intelligent navigation described above, and will not be repeated here. Each module in the above-described route planning method based on intelligent navigation can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0101] This application provides a computer device that may include a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it causes the processor to perform the steps of a route planning method based on intelligent navigation as described in any of the above embodiments.

[0102] The working process, working details, and technical effects of the computer device provided in this embodiment can be found in the embodiment of a route planning method based on intelligent navigation described above, and will not be repeated here.

[0103] This application provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the steps of a route planning method based on intelligent navigation as described in any of the above embodiments. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0104] The working process, working details, and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment of a route planning method based on intelligent navigation, and will not be repeated here.

[0105] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A route planning device based on intelligent navigation, characterized in that, The device includes: The data acquisition and fusion module is used to acquire traffic data, vehicle data, user preference data, and third-party service data and send them to the intelligent route planning module; The intelligent route planning module is used to calculate the planned route and plan scheme based on the traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics, and send them to the route presentation and interaction module. The route presentation and interaction module is used to receive and display the planned route and the planning scheme; and to obtain and execute interactive adjustment information based on the planned route and the planning scheme.

2. The route planning device based on intelligent navigation according to claim 1, characterized in that, The device further includes: The execution feedback module is used to obtain real-time vehicle location, real-time vehicle status, and real-time environmental conditions; compare the real-time vehicle location with the planned route to obtain the deviation value; and send the deviation value, the real-time vehicle status, and the real-time environmental conditions to the intelligent route planning module. The intelligent route planning module is specifically used to receive the deviation value, the real-time vehicle status, and the real-time environmental conditions, process them according to the path cost calculation model, obtain an updated planned route and an updated planning scheme, and send them to the route presentation and interaction module. The route presentation interaction module is specifically used to receive and display the updated planned route and the updated planning scheme.

3. The route planning device based on intelligent navigation according to claim 2, characterized in that, The intelligent route planning module includes a time cost calculation unit, an economic cost calculation unit, a comfort cost quantification unit, an energy consumption cost calculation unit, a weight determination unit, and a comprehensive calculation unit; The time cost calculation unit is used to obtain the time cost based on the historical average travel time database and real-time traffic data; The economic cost calculation unit is used to obtain the economic cost based on the road segment toll database and the road segment distance; The comfort cost quantification unit is used to obtain the comfort cost based on high-precision map data and road geometry data; The energy consumption cost calculation unit is used to obtain the energy consumption cost based on the vehicle model and historical energy consumption data. The weight determination unit is used to obtain time weight, economic weight, comfort weight and range safety weight based on the user's travel pattern. The comprehensive calculation unit is used to calculate the comprehensive road segment cost by weighting the time cost and time weight, the economic cost and economic weight, the comfort cost and comfort weight, and the energy consumption cost and range safety weight; and to obtain the planned route and planning scheme based on the comprehensive road segment cost.

4. The route planning device based on intelligent navigation according to claim 3, characterized in that, The user travel modes include time-priority mode, economy-priority mode, comfort-priority mode, and range-priority mode. In the time-priority mode, the time weight is 0.7, the economy weight is 0.1, the comfort weight is 0.1, and the range and safety weight is 0.

1. In the aforementioned economy-first mode, the economic weight is 0.6, the time weight is 0.2, the comfort weight is 0.1, and the range and safety weight is 0.

1. In the comfort-first mode, the comfort weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the range safety weight is 0.

1. In the range priority mode, the range safety weight is 0.6, the time weight is 0.2, the economy weight is 0.1, and the comfort weight is 0.

1.

5. The route planning device based on intelligent navigation according to claim 4, characterized in that, The time cost calculation unit is specifically used to obtain a basic travel time based on the historical average travel time database, and to obtain a real-time congestion coefficient based on real-time traffic data; to process historical travel time data, real-time traffic flow data, weather data, and holiday data using a machine learning network to obtain a prediction adjustment coefficient; and to multiply the basic travel time, the real-time congestion coefficient, and the prediction adjustment coefficient to obtain the time cost.

6. The route planning device based on intelligent navigation according to claim 5, characterized in that, The economic cost calculation unit is specifically used to obtain road and bridge tolls based on the road segment toll database; to obtain fuel costs based on road segment distance, vehicle fuel consumption per 100 kilometers and fuel unit price; and to obtain electricity costs based on road segment distance, vehicle electricity consumption per 100 kilometers and electricity price. Additional costs are obtained based on third-party service data interfaces; the economic cost is obtained by adding the road and bridge tolls, the fuel cost, and the additional costs; or, the economic cost is obtained by adding the road and bridge tolls, the electricity cost, and the additional costs.

7. The route planning device based on intelligent navigation according to claim 6, characterized in that, The comfort cost quantification unit is specifically used to obtain road geometry data based on high-precision map data, calculate the curvature coefficient based on the road geometry data, obtain the traffic light coefficient based on the traffic light density, obtain the congestion coefficient based on historical data and real-time traffic conditions, and then multiply the curvature coefficient, the traffic light coefficient and the congestion coefficient by the basic comfort level to obtain the comfort cost.

8. The route planning device based on intelligent navigation according to claim 7, characterized in that, The energy consumption cost calculation unit is specifically used to calculate the basic energy consumption based on the vehicle model and historical energy consumption data; calculate the elevation data using a digital elevation model to obtain the slope coefficient; calculate the wind speed coefficient based on real-time wind speed and direction; calculate the temperature coefficient based on real-time ambient temperature and a preset temperature-efficiency relationship table; and multiply the basic energy consumption, the slope coefficient, the wind speed coefficient, and the temperature coefficient to obtain the energy consumption cost.

9. The route planning device based on intelligent navigation according to claim 8, characterized in that, The intelligent route planning module is specifically used to acquire the starting point, the destination, the traffic data, and the vehicle data; process the traffic data using a multi-objective A* algorithm to obtain K alternative routes; and calculate the planned route and the planning scheme based on the K alternative routes, the user preference data, and the third-party service data by the comprehensive calculation unit.

10. A route planning method based on intelligent navigation, characterized in that, The method includes: The data acquisition and fusion module obtains traffic data, vehicle data, user preference data, and third-party service data and sends them to the intelligent route planning module; The intelligent route planning module calculates the planned route and plan based on the traffic data, vehicle data, user preference data, third-party service data, user travel patterns and travel characteristics, and sends them to the route presentation and interaction module. The route presentation and interaction module receives and displays the planned route and the planning scheme; it also obtains and executes interactive adjustment information based on the planned route and the planning scheme.

Images