Commercial vehicle intelligent connection system based on Beidou positioning

Abstract

The present invention belongs to the technical field of commercial vehicles, and discloses a commercial vehicle intelligent connection system based on Beidou positioning; it realizes sub-meter high-precision positioning of electric vehicles; the system conducts multi-dimensional status monitoring on the vehicle power system, battery system and in-vehicle equipment, constructs a vehicle health index model, and forms a spatio-temporal trajectory knowledge graph based on big data mining technology. Based on a dynamic energy management strategy network, it optimizes the energy efficiency and charging plan of electric vehicles, and constructs a collaborative perception and distributed decision-making mechanism between vehicles. By deeply integrating a multi-level vehicle connection cooperation framework with an urban intelligent transportation system, it realizes three-layer collaboration among vehicle individuals, vehicle groups and urban transportation systems, forms an integrated intelligent travel platform, effectively reduces energy consumption and improves traffic efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of commercial vehicles, and more specifically, to a commercial vehicle intelligent connection system based on Beidou positioning. Background Art

[0002] With the rapid development of intelligent transportation and vehicle networking technologies, the intelligence and networking of commercial vehicles have become an important trend in the industry. However, existing commercial vehicle intelligent systems still have many limitations: insufficient positioning accuracy, making it difficult to cope with complex environments such as high-rise buildings and numerous tunnels in cities; incomplete vehicle status monitoring, unable to detect potential fault risks in a timely manner; low energy management efficiency, making it difficult to optimize the cruising range and charging strategy of electric commercial vehicles; lack of group collaboration ability, failing to give full play to the overall advantages of vehicle networking; low integration with the urban traffic system, making it difficult to achieve seamless docking between commercial vehicles and urban infrastructure; limited data mining and knowledge extraction capabilities, failing to make full use of massive vehicle data to support high-level decision-making; insufficient system adaptability and robustness, performing poorly in complex and changeable actual operating environments. These problems seriously restrict the operation efficiency and safety of commercial vehicle fleets and also hinder the coordinated development of intelligent logistics and smart cities.

[0003] In view of this, the present invention proposes a commercial vehicle intelligent connection system based on Beidou positioning to solve the above problems. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solution: A commercial vehicle intelligent connection system based on Beidou positioning, comprising:

[0005] A data acquisition module, configured to perform fusion processing and accuracy enhancement on the Beidou multimodal positioning signals obtained by a commercial vehicle to obtain high-precision spatio-temporal positioning data;

[0006] An intelligent analysis module, configured to perform multi-dimensional acquisition and intelligent analysis on the state parameters of the power system, battery system, and in-vehicle equipment of a commercial vehicle to obtain a vehicle health index model;

[0007] An intelligent mining module, based on the high-precision spatio-temporal positioning data and the vehicle health index model, performs mining on the group behavior patterns of commercial vehicles to obtain a spatio-temporal trajectory knowledge graph;

[0008] An energy optimization module, configured to use the spatio-temporal trajectory knowledge graph to perform energy efficiency optimization and charging planning for commercial vehicles to obtain a dynamic energy management strategy network;

[0009] The multi-level vehicle connection module constructs a collaborative perception and distributed decision-making mechanism among vehicles based on high-precision spatio-temporal positioning data and a dynamic energy management strategy network, obtaining a multi-level vehicle connection cooperation framework; integrating the multi-level vehicle connection cooperation framework with the urban intelligent transportation system to obtain an integrated solution for the intelligent travel of commercial vehicles.

[0010] Further, the Beidou multi-modal positioning signals obtained by the commercial vehicle are fused and processed and the accuracy is enhanced to obtain high-precision spatio-temporal positioning data, including:

[0011] Collect multi-frequency signals of the Beidou navigation system and differential signals of the ground augmentation station to obtain an original positioning data set, and perform signal quality evaluation on the original positioning data set to obtain a signal reliability vector;

[0012] Based on the signal reliability vector, perform weighted fusion on multi-source positioning information to obtain a preliminary fusion positioning result, and use the Kalman filtering algorithm to suppress positioning noise to obtain filtered positioning data;

[0013] Combine the data of the inertial navigation unit to perform adaptive compensation on the filtered positioning data to obtain a continuous positioning trajectory, and apply a trajectory prediction algorithm in the signal occlusion area to obtain a complete positioning sequence;

[0014] Perform map matching and constraint optimization on the complete positioning sequence to obtain road-level precise positioning data, and perform adaptive correction on the positioning accuracy in complex scenarios based on a deep learning model to obtain a sub-meter-level positioning result;

[0015] Construct a spatio-temporal index and synchronize timestamps for the sub-meter-level positioning result to obtain high-precision spatio-temporal positioning data.

[0016] Further, the state parameters of the power system, battery system and in-vehicle equipment of the commercial vehicle are collected and intelligently analyzed in multiple dimensions to obtain a vehicle health index model, including:

[0017] Collect power system parameters through a multi-source sensor network to obtain a power system state matrix, and perform anomaly detection and fault diagnosis on the power system state matrix to obtain a power system health vector;

[0018] Monitor the key parameters of the battery pack to obtain a battery state data set, and evaluate the battery health state based on electrochemical impedance spectroscopy analysis technology to obtain a battery capacity attenuation model;

[0019] Collect the operating state data of the in-vehicle control unit, communication module and auxiliary equipment to obtain a set of equipment performance indicators, and construct an equipment reliability evaluation network based on the set of equipment performance indicators to obtain an equipment health score;

[0020] Perform multi-level fusion on the power system health vector, the battery capacity attenuation model, and the device health score to obtain a vehicle comprehensive state feature space, and apply clustering and classification algorithms in the vehicle comprehensive state feature space to obtain a vehicle state evaluation result;

[0021] Based on the vehicle state evaluation result, construct a deep neural network prediction model to dynamically predict the remaining service life of key vehicle components, and combine historical operation data to generate a vehicle health index model.

[0022] Furthermore, based on the high-precision spatio-temporal positioning data and the vehicle health index model, conduct mining on the group behavior patterns of commercial vehicles to obtain a spatio-temporal trajectory knowledge graph, including:

[0023] Perform trajectory segmentation and feature extraction on the high-precision spatio-temporal positioning data to obtain a vehicle movement pattern feature set, and conduct trajectory clustering based on the vehicle movement pattern feature set to obtain a typical driving path library;

[0024] Combine the vehicle health index model and driving behavior data to establish an association analysis model between driving habits and vehicle states to obtain a driving-vehicle state mapping matrix;

[0025] Perform frequent pattern mining on the spatio-temporal trajectory data of a large number of vehicles to identify high-frequency travel paths and time windows to obtain a spatio-temporal activity pattern set, and construct an urban traffic flow prediction model based on the spatio-temporal activity pattern set to obtain a dynamic traffic flow distribution map;

[0026] Use a graph neural network to model the interaction behavior between vehicles to obtain a vehicle social network structure, and identify key nodes and community structures in the vehicle social network structure to obtain a vehicle group influence distribution;

[0027] Integrate the typical driving path library, the driving-vehicle state mapping matrix, the dynamic traffic flow distribution map, and the vehicle group influence distribution to construct a multi-level knowledge representation model to obtain a spatio-temporal trajectory knowledge graph.

[0028] Furthermore, use the spatio-temporal trajectory knowledge graph to optimize the energy efficiency of commercial vehicles and plan charging to obtain a dynamic energy management strategy network, including:

[0029] Based on the spatio-temporal trajectory knowledge graph, conduct energy consumption analysis on the driving routes of commercial vehicles to obtain a road section energy consumption feature library, and combine terrain, weather, and traffic condition data to establish a multi-factor energy consumption prediction model to obtain an accurate energy consumption estimation result;

[0030] Based on the accurate energy consumption estimation results and battery status information, calculate the vehicle's cruising range, obtain the driving range prediction curve, and based on the driving range prediction curve, provide personalized energy-saving driving suggestions to the driver to obtain a real-time driving optimization strategy;

[0031] Utilize urban charging facility distribution data and real-time charging station status information, combine with the spatio-temporal trajectory knowledge graph, construct an intelligent charging recommendation model, obtain the optimal charging station selection plan, and based on grid load and electricity price fluctuation data, generate suggestions for the best charging time period to obtain an economic charging strategy;

[0032] Perform collaborative scheduling on the charging demands of multiple vehicles to obtain a balanced charging resource allocation plan, and optimize the charging resource sharing mechanism between vehicles based on the game theory model to obtain a collaborative charging network;

[0033] Integrate the real-time driving optimization strategy, the economic charging strategy, and the collaborative charging network to construct a hierarchical decision support system to obtain a dynamic energy management strategy network.

[0034] Furthermore, based on the high-precision spatio-temporal positioning data and the dynamic energy management strategy network, construct a collaborative perception and distributed decision-making mechanism between vehicles to obtain a multi-level vehicle connection and collaboration framework, including:

[0035] Based on vehicle-to-vehicle wireless communication technology, establish a direct communication link between vehicles to obtain a vehicle communication topology network, and according to the vehicle communication topology network, define a data exchange protocol to obtain an efficient information sharing mechanism;

[0036] Integrate the vehicle's own sensor data and the perception information shared by surrounding vehicles to obtain an enhanced perception result, and based on the enhanced perception result, construct a local environment dynamic map to obtain a shared situation model;

[0037] According to the high-precision spatio-temporal positioning data, calculate the relative position relationship between vehicles to obtain a set of convoy formation conditions, and based on the set of convoy formation conditions, define an adaptive convoy organization algorithm to obtain an intelligent convoy formation strategy;

[0038] Combine the shared situation model and the dynamic energy management strategy network to define a distributed decision-making mechanism, enabling each vehicle to make a globally optimal decision based on local information to obtain a collaborative decision-making framework;

[0039] Define a fault tolerance mechanism and a backup decision-making strategy to obtain a robustness guarantee plan, and integrate the efficient information sharing mechanism, the intelligent convoy formation strategy, the collaborative decision-making framework, and the robustness guarantee plan to obtain a multi-level vehicle connection and collaboration framework.

[0040] A commercial vehicle intelligent connection device based on Beidou positioning, the commercial vehicle intelligent connection device based on Beidou positioning includes: a memory and at least one processor, and instructions are stored in the memory;

[0041] The at least one processor calls the instructions in the memory to enable the commercial vehicle intelligent connection device based on Beidou positioning to execute the commercial vehicle intelligent connection system as described.

[0042] A computer-readable storage medium, on which instructions are stored, and when the instructions are executed by a processor, the commercial vehicle intelligent connection system as described is implemented.

[0043] The technical effects and advantages of the commercial vehicle intelligent connection system based on Beidou positioning of the present invention:

[0044] The present invention constructs a complete commercial vehicle intelligent networking solution by performing fusion processing and accuracy enhancement on the Beidou multi-modal positioning signals obtained by commercial vehicles, combined with comprehensive monitoring and analysis of vehicle states. This solution realizes the leap from single-vehicle intelligence to group collaboration, organically combines vehicle positioning, state monitoring, behavior analysis, energy management and collaborative control, and forms a closed-loop intelligent travel ecosystem. The system greatly improves the positioning accuracy, energy efficiency and travel experience of commercial vehicles through advanced technologies such as multi-source data fusion, machine learning, and distributed decision-making. At the same time, through deep integration with the urban intelligent transportation system, it promotes the coordinated development of commercial vehicles and urban traffic infrastructure. Description of the Drawings

[0045] Figure 1 It is a schematic diagram of the commercial vehicle intelligent connection system based on Beidou positioning of the present invention. Detailed Embodiments

[0046] The embodiments of the present application provide a commercial vehicle intelligent connection system based on Beidou positioning. Terms such as "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0047] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer toFigure 1 In the embodiments of the present application, an embodiment of a commercial vehicle intelligent connection system based on Beidou positioning includes:

[0048] The data acquisition module is used to perform fusion processing and precision enhancement on the Beidou multi-modal positioning signals acquired by commercial vehicles to obtain high-precision spatiotemporal positioning data;

[0049] It is understandable that the execution subject of this application can be a commercial vehicle intelligent connection system based on Beidou positioning, or an intelligent control unit or cloud service platform on a commercial vehicle, which is not limited here. The embodiment of this application is explained by taking the intelligent control unit on a commercial vehicle as the execution subject.

[0050] Specifically, the multi-frequency satellite signals provided by the Beidou navigation system, including navigation information of different frequencies such as B1, B2, and B3, are collected, and the differential signals provided by the ground enhancement station are received at the same time. These signals together constitute the original positioning data set. The quality of each signal in the original positioning data set is evaluated, including factors such as signal-to-noise ratio, multipath effect, and satellite geometric distribution, to obtain the signal reliability vector. Based on the signal reliability vector, the multi-source positioning information is weighted and fused, and the weight distribution is proportional to the signal reliability, so as to improve the positioning accuracy and obtain the preliminary fusion positioning result. The Kalman filter algorithm is used to suppress the noise in the preliminary fusion positioning result. The Kalman filter effectively removes the influence of random noise through two steps of prediction and update to obtain the filtered positioning data. Combined with the acceleration, angular velocity and other data of the vehicle-mounted inertial navigation unit (IMU), the filtered positioning data is adaptively compensated to compensate for the temporary loss of satellite signals or the decrease in accuracy, and a continuous positioning trajectory is obtained. In signal-blocked areas such as tunnels and high-rise buildings, a prediction algorithm based on historical trajectories is applied, combined with road network constraints, to infer the possible position of the vehicle and obtain a complete positioning sequence. The complete positioning sequence is matched with the high-precision electronic map, and the vehicle position is accurately matched to the actual road through the road constraint optimization algorithm to obtain road-level precise positioning data. For complex scenes such as urban canyons and multi-story elevated roads, a deep learning model is used to adaptively correct the positioning results. The model learns the historical positioning error pattern and performs real-time correction to obtain sub-meter positioning results. Finally, a spatiotemporal index structure is established for the sub-meter positioning results and synchronized with the Universal Time (UTC) to ensure that the spatiotemporal reference system of all vehicles is consistent and obtain high-precision spatiotemporal positioning data.

[0051] Intelligent analysis module, used to collect and intelligently analyze the state parameters of the power system, battery system and on-board equipment of commercial vehicles in multiple dimensions to obtain the vehicle health index model;

[0052] Specifically, various sensors installed on key components such as motors and electronic control units are used to collect power system parameters in real time, including motor temperature, speed, torque, output power, efficiency, etc., to form a power system state matrix. An anomaly detection algorithm based on machine learning is applied to the power system state matrix to identify potential fault patterns and signs of performance degradation, and combined with an expert knowledge base for fault diagnosis to obtain a power system health vector, which quantifies the health status of each component of the power system. The battery management system (BMS) monitors key parameters such as the single-cell voltage, current, temperature distribution, internal resistance change, and charge-discharge cycle times of the battery pack to form a battery state data set. Based on the electrochemical impedance spectroscopy (EIS) analysis technique, by applying a small-signal alternating current and measuring the corresponding voltage response, the internal electrochemical state of the battery is evaluated, and a battery capacity degradation model is established in combination with historical data. This model can accurately predict the remaining battery capacity and aging rate. Through the on-board diagnostic system (OBD) and communication network, the operating status data of auxiliary devices such as the on-board control unit, communication module, air conditioning system, and lighting system are collected, including indicators such as processor load, memory usage, communication quality, and power consumption, to form a set of device performance indicators. According to the set of device performance indicators, a Bayesian network is used to construct a device reliability evaluation network, which considers the interdependencies and failure modes between devices to obtain a device health score. Through a deep fusion algorithm, the power system health vector, battery capacity degradation model, and device health score are integrated at multiple levels to construct a vehicle comprehensive state feature space. In this feature space, the K-means clustering and random forest classification algorithms are applied to finely divide and evaluate the vehicle health status to obtain a vehicle state evaluation result. Based on the evaluation result, a deep neural network prediction model containing LSTM (long short-term memory network) and attention mechanism is constructed. This model can learn the changing trends of the health status of each component of the vehicle and dynamically predict the remaining service life of key components. Combining the vehicle's historical operation data, maintenance records, and data of the same model vehicle group, a comprehensive vehicle health index model is generated. This model intuitively represents the overall health status of the vehicle with a score of 0-100, and provides the health scores of subsystems and the expected maintenance time points.

[0053] An intelligent mining module, based on the high-precision spatio-temporal positioning data and the vehicle health index model, conducts mining on the group behavior patterns of commercial vehicles to obtain a spatio-temporal trajectory knowledge graph;

[0054] Specifically, perform segmented processing on high-precision spatio-temporal positioning data in terms of time and space dimensions, extract features such as vehicle acceleration, deceleration, turning angle, and residence time to form a vehicle movement pattern feature set. Based on this feature set, apply the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm for trajectory clustering to identify typical driving patterns in different driving scenarios, such as urban commuting, highway cruising, congested travel, etc., and form a typical driving path library. Combine the vehicle health index model and driving behavior data from in-vehicle sensors, including throttle pedal position, braking force, steering angular velocity, etc., to establish an association analysis model between driving habits and vehicle states. Through multiple regression analysis, this model quantifies the impact of different driving habits on the vehicle health status and generates a driving-vehicle state mapping matrix. Apply the Apriori algorithm and sequence pattern mining technology to the historical trajectory data of a large-scale vehicle group to identify high-frequency travel paths and time windows within the city, such as commuting routes during morning and evening rush hours, access patterns to weekend leisure areas, etc., to obtain a spatio-temporal activity pattern set. Based on this pattern set, combine time series analysis methods to construct a hybrid urban traffic flow prediction model based on ARIMA (Autoregressive Integrated Moving Average) and neural networks, and generate a dynamic traffic flow distribution map reflecting traffic flows in different time periods and regions. Use graph neural network (GNN) technology to model the interaction behaviors between vehicles (such as appearing at the same location simultaneously, similar driving paths, etc.) as a graph structure, where nodes represent vehicles and edges represent the interaction relationships between vehicles, to obtain a vehicle social network structure. In this network structure, apply centrality analysis and community detection algorithms to identify key vehicle nodes with high influence and closely connected vehicle communities to obtain the vehicle group influence distribution. Integrate the typical driving path library, driving-vehicle state mapping matrix, dynamic traffic flow distribution map, and vehicle group influence distribution, and use knowledge graph technology to construct a multi-level knowledge representation model. This model is stored in the form of a graph database, including entities (vehicles, drivers, road segments, time windows, etc.), attributes, and relationships, and supports complex queries and inferences to form a spatio-temporal trajectory knowledge graph.

[0055] An energy optimization module for using the spatio-temporal trajectory knowledge graph to optimize the energy efficiency of commercial vehicles and plan charging, and obtaining a dynamic energy management strategy network;

[0056] Specifically, based on the spatio-temporal trajectory knowledge graph, statistical analysis is carried out on the commercial vehicle energy consumption data of different road sections in the city at different times. Considering factors such as road conditions, gradients, and speed limits, a road section energy consumption feature library is established. Combining meteorological data (temperature, humidity, wind speed), real-time traffic conditions, and vehicle load information, machine learning methods such as Gradient Boosting Decision Tree (GBDT) are applied to construct a multi-factor energy consumption prediction model. By inputting the current road conditions and environmental conditions, this model can accurately estimate the energy consumption of future trips and obtain accurate energy consumption estimation results. According to the accurate energy consumption estimation results and the battery status information (SOC, SOH, etc.) provided by the battery management system, a method combining physical models and data-driven approaches is used to calculate the cruising range of the vehicle under different driving modes and environmental conditions, and a driving range prediction curve is generated. Based on this prediction curve and combined with the driver's historical driving habit data, a personalized energy-saving driving recommendation system is developed. This system can provide the best speed suggestions, acceleration timing tips, and energy recovery strategies during driving, forming a real-time driving optimization strategy. Using the geographical distribution data of urban charging infrastructure and the real-time operation status information of charging stations (number of idle charging piles, queuing situation, charging rate, etc.), combined with the vehicle positions and trip plans in the spatio-temporal trajectory knowledge graph, an intelligent charging recommendation system is constructed. This system uses a multi-objective optimization algorithm to comprehensively consider factors such as distance, charging time, and waiting time, recommends the most suitable charging station, and obtains the optimal charging station selection plan. Combining grid load data and time-of-use electricity price policies, the charging cost differences at different times are analyzed, and the most economical charging time suggestions are generated to form an economic charging strategy. By constructing a regional charging demand prediction model, spatio-temporal distribution analysis of the charging demands of multiple vehicles is carried out to achieve coordinated scheduling of charging resources. This scheduling system can avoid congestion of charging resources at specific times and regions through a reservation mechanism and real-time guidance, and obtain a balanced charging resource allocation plan. Based on the game theory model, a charging resource sharing mechanism among vehicles is defined, including a sharing pricing model for private charging piles, charging right trading rules, and a reciprocal credit system, forming a collaborative charging network. Integrating the real-time driving optimization strategy, economic charging strategy, and collaborative charging network, a hierarchical decision support system including a perception layer, a decision-making layer, and an execution layer is constructed. This system can adaptively adjust the energy management strategy according to dynamic factors such as vehicle status, driving habits, energy prices, and the distribution of charging infrastructure, forming a dynamic energy management strategy network.

[0057] The multi-level vehicle connection module, based on high-precision spatio-temporal positioning data and the dynamic energy management strategy network, constructs a collaborative perception and distributed decision-making mechanism among vehicles to obtain a multi-level vehicle connection cooperation framework; integrates the multi-level vehicle connection cooperation framework with the urban intelligent transportation system to obtain an integrated solution for the intelligent travel of commercial vehicles;

[0058] Specifically, based on wireless communication technologies such as vehicle DSRC (Dedicated Short Range Communication) and C-V2X (Cellular Vehicle-to-Everything), direct information exchange between vehicles is realized, and a dynamic vehicle communication topology network is established. This network can adapt to changes in vehicle density and communication environment and maintain stable connectivity. According to the characteristics of the vehicle communication topology network, a lightweight and low-latency data exchange protocol is defined, including message format definition, transmission priority strategy, and congestion control mechanism, to form an efficient information sharing mechanism. By integrating the sensor data of the vehicle's own radar, camera, lidar, etc., and the perception information shared by surrounding vehicles through V2V (Vehicle-to-Vehicle) communication, the perception range of a single vehicle is extended, the perception blind area is eliminated, and environmental collaborative perception is achieved. Sensor data fusion algorithms, including Kalman filtering, particle filtering, and deep learning methods, are applied to suppress noise and process the consistency of multi-source perception data to obtain enhanced perception results. Based on the enhanced perception results, a local environment dynamic map containing elements such as roads, vehicles, pedestrians, and obstacles is constructed. This map represents the environmental state in a unified coordinate system and can be updated in real time to support the sharing of situations between vehicles and form a shared situation model. According to the high-precision spatio-temporal positioning data, the relative position, relative speed, and driving direction between adjacent vehicles are calculated, and combined with the vehicle intention inference results, the feasibility of forming a platoon is evaluated to obtain a set of platoon formation conditions. Based on the set of platoon formation conditions, an adaptive platoon organization algorithm considering road conditions, vehicle performance, and traffic rules is defined. This algorithm can dynamically determine the platoon size, vehicle spacing, and formation shape, support the split and merge operations of the platoon, and form an intelligent platoon formation strategy. Combining the shared situation model and the dynamic energy management strategy network, a distributed decision-making mechanism based on a consensus algorithm is defined. This mechanism enables each vehicle to reach a consistent decision based on local information and information shared by neighboring vehicles according to common decision rules without relying on central control, forming a collaborative decision-making framework. For abnormal situations such as communication interruption, node failure, and malicious attacks, a fault tolerance mechanism including redundant communication paths, decision degradation strategies, and security authentication mechanisms is defined. At the same time, a backup decision-making strategy based on local information is pre-configured to ensure that the basic functions can still be maintained when part of the collaborative system fails, forming a robustness guarantee scheme. Integrating the efficient information sharing mechanism, intelligent platoon formation strategy, collaborative decision-making framework, and robustness guarantee scheme, a multi-level vehicle connection and collaboration framework including a communication layer, a perception layer, a decision-making layer, and a security layer is constructed. This framework supports different levels of vehicle connection and collaboration, from simple information sharing to complex collaborative decision-making, and adapts to application scenarios under different penetration rates and technical conditions.

[0059] In a specific embodiment, the execution process of the data acquisition module specifically includes the following steps:

[0060] (1)Collect multi-frequency signals of the Beidou Navigation System and differential signals of ground augmentation stations to obtain an original positioning data set, and perform signal quality assessment on the original positioning data set to obtain a signal reliability vector;

[0061] (2)Based on the signal reliability vector, perform weighted fusion on multi-source positioning information to obtain a preliminary fusion positioning result, and use the Kalman filtering algorithm to suppress positioning noise to obtain filtered positioning data;

[0062] (3)Combine inertial navigation unit data to perform adaptive compensation on the filtered positioning data to obtain a continuous positioning trajectory, and apply a trajectory prediction algorithm in a signal occlusion area to obtain a complete positioning sequence;

[0063] (4)Perform map matching and constraint optimization on the complete positioning sequence to obtain road-level precise positioning data, and perform adaptive correction on the positioning accuracy in complex scenarios based on a deep learning model to obtain a sub-meter-level positioning result;

[0064] (5)Construct a spatio-temporal index and synchronize timestamps for the sub-meter-level positioning result to obtain high-precision spatio-temporal positioning data.

[0065] Specifically, the Beidou receiver on a commercial vehicle simultaneously collects signals of multiple frequency points such as B1 (1561.098 MHz), B2 (1207.14 MHz), and B3 (1268.52 MHz) from the Beidou Satellite Navigation System, and receives differential correction signals from the ground augmentation station network. The differential signals contain correction parameters such as satellite orbit error, clock error, and atmospheric delay, which can significantly improve positioning accuracy. These signals together constitute an original positioning data set D containing information such as satellite pseudorange, carrier phase, and Doppler frequency shift. Perform quality assessment on each signal in the original positioning data set D, calculate quality indicators such as signal-to-noise ratio (SNR), multipath effect index, and geometric dilution of precision (GDOP), and form a signal quality assessment matrix Q. Based on matrix Q, apply the fuzzy comprehensive evaluation method to calculate the reliability weight of each signal source to obtain a signal reliability vector ; where W is the evaluation index weight vector determined by expert experience. Based on the signal reliability vector R, perform weighted fusion on multi-source positioning information, and the weight is proportional to the signal reliability. The fusion formula is as follows:

[0066] ; where P_i represents the position information provided by the i-th signal source, is the signal reliability vector of the i-th signal source, and a preliminary fusion positioning result P_fusion is obtained. Use the Kalman filtering algorithm to suppress the random noise in the preliminary fusion positioning result. The Kalman filtering includes two steps: prediction and update:

[0067] Prediction step: ;

[0068] Update step: ;

[0069] where \(X_k\) represents the state vector at time \(k\) (including information such as position and velocity), \(A\) is the state transition matrix, \(B\) is the control matrix, \(u_k\) is the control vector, \(Z_k\) is the observation vector, \(H\) is the observation matrix, is the intermediate value of the state vector at time \(k\); \(K_k\) is the Kalman gain. By repeatedly iterating the prediction and update steps, the filtered positioning data is obtained. Combining the acceleration and angular velocity data provided by the vehicle-mounted inertial navigation unit (IMU), adaptive compensation is performed on the filtered positioning data. According to the IMU data, attitude calculation and motion integration are carried out to obtain the displacement estimation from the previous valid positioning point to the current time, compensating for possible short-term loss or accuracy degradation of satellite signals. The calculation formula is:

[0070] ;

[0071] where \(P_{last}\) represents the previous valid positioning point, \(a(t)\) represents the acceleration function, is the compensation for the valid positioning point. The displacement estimation is obtained by double integration of the acceleration to form a continuous positioning trajectory \(T_{con}\). In signal occlusion areas such as tunnels and high-rise dense areas, a prediction algorithm based on historical trajectory features and road network constraints is applied. Using the kinematic characteristics of the vehicle's historical trajectory and the road topology structure, the possible positions of the vehicle in the signal missing area are predicted. The prediction algorithms include:

[0072] A trajectory prediction model trained based on historical data and the application of road constraint conditions; Through the above prediction algorithms, the position calculation in the signal occlusion area is realized, and a complete positioning sequence \(T_{comp}\) is obtained. The complete positioning sequence is matched with a high-precision electronic map, and map matching algorithms such as the hidden Markov model (HMM) are applied to accurately correspond the vehicle position to the actual road. The map matching process takes into account the position measurement error, road network topology and vehicle motion constraints, and through maximizing the likelihood probability, the road-level accurate positioning data \(P_{road}\) is obtained:

[0073] For complex scenarios such as urban canyons and multi-layer viaducts, a deep learning model including a convolutional neural network (CNN) and a recurrent neural network (RNN) is adopted to adaptively correct the positioning results. The model learns the relationship between the error patterns and environmental features in a large amount of historical positioning data to establish an error compensation model to achieve real-time correction:

[0074] \(P_{corrected}=P_{road}-CNN - RNN(Env)\);

[0075] Among them, P_corrected is the corrected data of the road-level precise positioning data; Env includes environmental features such as the number of visible satellites, building height, road type, etc. Through calibration, a sub-meter-level positioning result is obtained. Finally, a quadtree or grid-based spatio-temporal index structure is established for the sub-meter-level positioning result and is highly synchronized with Coordinated Universal Time (UTC) to ensure that the spatio-temporal reference systems of all vehicles are consistent, obtaining high-precision spatio-temporal positioning data, which includes accurate position coordinates, timestamps, accuracy evaluations, and credibility indicators.

[0076] In a specific embodiment, the execution process of the intelligent analysis module specifically includes the following steps:

[0077] (1) Collect power system parameters such as motor temperature, speed, output power, etc. through a multi-source sensor network to obtain a power system state matrix, and perform anomaly detection and fault diagnosis on the power system state matrix to obtain a power system health vector;

[0078] (2) Monitor key parameters such as the voltage, current, temperature, number of cycles, etc. of the battery pack to obtain a battery state data set, and evaluate the battery health state based on electrochemical impedance spectroscopy analysis technology to obtain a battery capacity attenuation model;

[0079] (3) Collect the operating state data of the vehicle control unit, communication module, and auxiliary equipment to obtain a set of equipment performance indicators, and construct an equipment reliability evaluation network based on the set of equipment performance indicators to obtain an equipment health score;

[0080] (4) Perform multi-level fusion on the power system health vector, the battery capacity attenuation model, and the equipment health score to obtain a vehicle comprehensive state feature space, and apply clustering and classification algorithms in the feature space to obtain a vehicle state evaluation result;

[0081] (5) Based on the vehicle state evaluation result, construct a deep neural network prediction model to dynamically predict the remaining service life of key vehicle components, and combine historical operation data to generate a vehicle health index model.

[0082] Specifically, by installing various sensors such as temperature sensors, Hall effect sensors, current sensors, and vibration sensors on key components of the power system such as motors, motor controllers, and reducers, power system parameters such as motor temperature, stator current, speed, torque, output power, efficiency, noise, and vibration spectrum are collected in real time. These parameters are organized into a power system state matrix M according to a time series. Each row of the matrix represents a time point, and each column represents a parameter. Apply principal component analysis (PCA) to the power system state matrix M for dimensionality reduction, extract key features, and then use an anomaly detection method based on the isolation forest algorithm to identify potential anomaly points. The mathematical expression for identifying potential anomaly points is:

[0083] ; where is the anomaly score of sample x in the total number of samples, h(x) is the path length of sample x, c(n) is the normalization factor, is the total number of samples, is the abbreviation of the expected path length. It represents the average path length of sample x from the root node to the leaf node during multiple constructions of the isolation tree. For the detected anomaly points (anomaly scores greater than the threshold), a fault diagnosis is carried out by combining a knowledge-based reasoning system and case-based reasoning (CBR) to identify the specific fault type and severity. According to the diagnosis results, a power system health vector H_power is constructed, which includes the health scores, expected service lives, and maintenance suggestions of each key component. The key parameters such as the individual cell voltage, charge and discharge current, temperature distribution, internal resistance change, charge and discharge cycle times, and deep charge and discharge times of the battery pack are monitored in real time through the battery management system (BMS), and these parameters together constitute the battery state dataset B. Using electrochemical impedance spectroscopy (EIS) analysis technology, a small-signal alternating current (usually in the frequency range of mHz to kHz) is applied to the battery under different states of charge (SOC), the corresponding voltage response is measured, and the impedance spectrum Z ;

[0084] where |Z| is the impedance amplitude and φ is the phase angle, is the frequency, is the control parameter. The impedance spectrum is fitted through an equivalent circuit model (such as the Randles model) to extract the internal parameters of the battery, including the ohmic impedance, charge transfer impedance, diffusion impedance, etc., which are closely related to the aging state and health state of the battery. Combining the historical charge and discharge data and the change trend of the impedance parameters, a battery capacity attenuation model :

[0085] ;

[0086] where \(C_0\) is the initial capacity, \(k\) is the attenuation coefficient, \(f\) is the attenuation function (such as exponential function), \(N\) is the number of cycles, DOD is the depth of discharge, \(T\) is the temperature, and \(I\) is the charge and discharge current. This model can accurately predict the remaining capacity and aging rate of the battery under different usage conditions. Through the on-board diagnostic system (OBD) and in-vehicle Ethernet, collect the operating status data of auxiliary devices such as the on-board control unit (ECU), communication modules (4G / 5G, DSRC), air conditioning system, lighting system, and infotainment system, including indicators such as processor load, memory usage, communication quality, response time, power consumption, and error logs, to form the device performance index set \(P\). According to the device performance index set \(P\), apply the Bayesian network to construct the device reliability evaluation network. The Bayesian network is a probabilistic graphical model, represented by a directed acyclic graph (DAG) to show the dependence relationship between variables, and each node is associated with a conditional probability table (CPT):

[0087] \(P(X_i|\text{Parents}(X_i))\);

[0088] where \(X_i\) represents the device status variable, and \(\text{Parents}(X_i)\) represents the set of parent node variables that affect \(X_i\). Through Bayesian inference, calculate the probability distribution of the health status of the device under the given observed evidence to obtain the device health score. Through the deep fusion algorithm, multi-level integration of the power system health vector \(H_{\text{power}}\), the battery capacity attenuation model \(C(t)\), and the device health score is carried out. First, perform eigenvector splicing; then perform decision-level fusion, and through weighted voting or, integrate the decision results of each subsystem to construct the vehicle comprehensive status feature space. Apply the K-means++ clustering algorithm in the vehicle comprehensive status feature space to divide the vehicle status into multiple categories. Then use the random forest classification algorithm to accurately classify and evaluate the current vehicle status based on historical data and expert annotations to obtain the vehicle status evaluation result. Based on the vehicle status evaluation result, construct a deep neural network prediction model that includes the LSTM (long short-term memory network) and the Transformer attention mechanism. The core structure of the LSTM includes an input gate, a forget gate, and an output gate. This model dynamically predicts the remaining useful life \(RUL_i\) of key components (such as motors, batteries, transmissions, controllers, etc.) by learning the historical change trends of the health status of each vehicle component. Combining the vehicle's historical operation data, maintenance records, and data of the same model vehicle group, apply the transfer learning method to construct a comprehensive vehicle health index model ;

[0089] ;

[0090] Among them, w_i is the weight coefficient, f_i is the evaluation function (can be a product function), S_i is the component health status (quantitative value), RUL_i is the remaining service life, and Imp_i is the component importance. The health index model intuitively represents the overall health status of the vehicle with a score of 0-100, and provides the health score of the subsystem and the expected maintenance time point, providing a scientific basis for vehicle maintenance and use decisions.

[0091] In a specific embodiment, the execution process of the intelligent mining module 103 specifically includes the following steps:

[0092] (1) performing trajectory segmentation and feature extraction on the high-precision spatiotemporal positioning data to obtain a vehicle movement pattern feature set, and performing trajectory clustering based on the vehicle movement pattern feature set to obtain a typical driving path library;

[0093] (2) combining the vehicle health index model and driving behavior data, establishing a driving habit and vehicle state correlation analysis model to obtain a driving-vehicle state mapping matrix;

[0094] (3) Conduct frequent pattern mining on the spatiotemporal trajectory data of a large number of vehicles to identify high-frequency travel paths and time windows, obtain a spatiotemporal activity pattern set, and build an urban traffic flow prediction model based on the spatiotemporal activity pattern set to obtain a dynamic traffic flow distribution map;

[0095] (4) Using graph neural networks to model the interaction behaviors between vehicles, obtain the vehicle social network structure, identify key nodes and community structures in the vehicle social network structure, and obtain the vehicle group influence distribution;

[0096] (5) Integrate the typical driving path library, the driving-vehicle state mapping matrix, the dynamic traffic distribution map, and the vehicle group influence distribution to construct a multi-level knowledge representation model and obtain a spatiotemporal trajectory knowledge graph.

[0097] Specifically, the high-precision spatiotemporal positioning data T is segmented according to the time window and spatial features, and the piecewise linear approximation (PLA) or the segmentation method based on important inflection points is applied to divide the continuous trajectory into a series of driving segments. The feature vector is extracted for each driving segment, including:

[0098] Dynamic characteristics: average speed, maximum speed, acceleration distribution, deceleration distribution, driving stability;

[0099] Geometric features: trajectory curvature, turning angle, path complexity;

[0100] Spatiotemporal characteristics: travel time, travel distance, dwell time, temporal regularity;

[0101] These features together constitute the vehicle movement pattern feature set. Trajectory clustering is performed based on the vehicle movement pattern feature set. The parameters of trajectory clustering include radius ε and minimum number of points Pts. The process of trajectory clustering is as follows:

[0102] For any unvisited point p, mark it as visited;

[0103] Search for the ε-neighborhood N_ε(p) of p; if |N_ε(p)| < Pts, mark p as a noise point; otherwise create a new cluster C and add p to C; for each point q in C, repeat the above process to expand cluster C;

[0104] Through trajectory clustering, typical driving patterns in different driving scenarios are identified, such as urban commuting, highway cruising, congested travel, etc., to form a typical driving path library. Each path in the typical driving path library contains information such as path features, usage frequency, and applicable scenarios. Combining the vehicle health index model HI and driving behavior data from in-vehicle sensors, including throttle pedal position, braking force, steering angular velocity, shift frequency, etc., an association analysis model between driving habits and vehicle status is established. Apply multiple linear regression and regularization methods (such as Ridge regression or Lasso regression) to estimate the parameters of the association analysis model:

[0105] ;

[0106] where is the driving behavior feature, is the regression coefficient, is the error term. By calculating the influence coefficient of each driving behavior feature on the vehicle health index, the influence degree of different driving habits on the vehicle health status is quantified, and a driving-vehicle status mapping matrix M_map is generated. This matrix represents the influence weights of different driving behavior patterns on the health status of each vehicle system. Apply sequence pattern mining techniques, such as the PrefixSpan algorithm or the GSP (Generalized Sequence Pattern) algorithm, to the historical trajectory data of a large-scale vehicle population (thousands to tens of thousands of vehicles) to identify frequently occurring spatio-temporal sequence patterns. Frequently occurring spatio-temporal sequence patterns are defined as sequences with a support not less than the minimum support threshold sup:

[0107] Through mining, high-frequency travel paths within the city (such as commuting routes, business district access routes) and time windows (such as morning and evening rush hours, weekend leisure periods) are identified to obtain a spatio-temporal activity pattern set P. Based on the spatio-temporal activity pattern set P and combined with time series analysis methods, a hybrid prediction model is constructed. This model combines the ARIMA (Autoregressive Integrated Moving Average) model to capture linear time dependencies and neural networks to capture non-linear patterns:

[0108] Predict the traffic flow in different time periods and regions through a hybrid prediction model, generate a dynamic traffic flow distribution map, and the dynamic traffic flow distribution map visually displays the urban traffic flow distribution in the form of a heat map. Using a graph neural network (GNN), model the interaction behavior between vehicles as a graph structure G=(V, E, A), where V is the set of nodes (vehicles), E is the set of edges (interaction relationships between vehicles), and A is the adjacency matrix. The weight of the edge is obtained based on the weighted sum of the frequency, duration, and similarity of vehicle interactions;

[0109] The graph neural network updates the node representation through a message passing mechanism. By training the graph neural network, obtain the vehicle social network structure. In the vehicle social network structure, identify key nodes with high influence. Define centrality metrics including degree centrality, betweenness centrality, and eigenvector centrality;

[0110] Apply the Louvain algorithm or the InfoMap algorithm for community detection to identify closely connected vehicle groups:

[0111] Initialization: Each node is a community;

[0112] Local movement: Move the node to the adjacent community that maximizes the modularity gain;

[0113] Community aggregation: Merge nodes with the same community membership into a supernode;

[0114] Repeat the steps until the modularity no longer increases significantly; the modularity is the weighted sum of the centrality metrics;

[0115] Subsequently, obtain the vehicle group influence distribution, which reflects the status and influence of vehicles in the social network. Integrate the typical driving path library, the driving-vehicle state mapping matrix M_map, the dynamic traffic flow distribution map, and the vehicle group influence distribution, and adopt a knowledge graph to construct a multi-level knowledge representation model:

[0116] G_kn=(E, R, T) consists of an entity set E, a relationship set R, and a triple set T, where:

[0117] The entity set E includes vehicles, drivers, road segments, time windows, charging stations, etc.;

[0118] The relationship set R includes semantic relationships such as "travel on", "belong to", "influence", "be located at", etc.;

[0119] The triple set represents the relationships between entities;

[0120] The multi-level knowledge representation model is stored in a graph database (such as Neo4j), supports query languages such as SPARQL, and can perform complex semantic queries and inferences. Through knowledge representation learning, such as algorithms like TransE and ComplEx, entities and relationships are embedded into a low-dimensional vector space;

[0121] A spatio-temporal trajectory knowledge graph is formed, which integrates multi-source heterogeneous data, provides a unified knowledge representation of vehicle behavior patterns, and provides a data basis for subsequent energy optimization and collaborative decision-making.

[0122] In a specific embodiment, the execution process of the energy optimization module specifically includes the following steps:

[0123] (1) Based on the spatio-temporal trajectory knowledge graph, conduct an energy consumption analysis of the commercial vehicle driving route to obtain a road section energy consumption feature library, and combine terrain, weather, and traffic condition data to establish a multi-factor energy consumption prediction model to obtain an accurate energy consumption estimation result;

[0124] (2) According to the accurate energy consumption estimation result and battery state information, calculate the vehicle's endurance capacity to obtain a driving range prediction curve, and based on the driving range prediction curve, give personalized energy-saving driving suggestions to the driver to obtain a real-time driving optimization strategy;

[0125] (3) Utilize urban charging facility distribution data and real-time charging station status information, combine with the spatio-temporal trajectory knowledge graph, construct an intelligent charging recommendation system to obtain the optimal charging station selection plan, and based on grid load and electricity price fluctuation data, generate suggestions for the best charging time period to obtain an economic charging strategy;

[0126] (4) Coordinate the charging demands of multiple vehicles to avoid local charging resource competition, obtain a balanced charging resource allocation plan, and optimize the vehicle-to-vehicle charging resource sharing mechanism based on a game theory model to obtain a collaborative charging network;

[0127] (5) Integrate the real-time driving optimization strategy, the economic charging strategy, and the collaborative charging network to construct a hierarchical decision support system to obtain a dynamic energy management strategy network.

[0128] Specifically, based on the spatio-temporal trajectory knowledge graph, the commercial vehicle energy consumption data of each road segment s in the urban road network at different time periods t is extracted. Through statistical analysis, statistical features such as the mean, variance, and quantiles of the road segment energy consumption are calculated, and the physical attributes (length, slope, curvature, etc.) and traffic characteristics (speed limit, number of signal lights, etc.) of the road segment are associated to construct a road segment energy consumption feature library. Combining the terrain data provided by the digital elevation model (DEM), the weather data (temperature, humidity, wind speed, precipitation, etc.) provided by the meteorological department, and the real-time traffic condition data (average vehicle speed, congestion level, etc.), machine learning methods such as gradient boosting decision tree (GBDT) are applied to construct a multi-factor energy consumption prediction model. The multi-factor energy consumption prediction model gradually improves the prediction performance by integrating multiple weak learners (decision trees):

[0129] ;

[0130] where is the multi-factor energy consumption prediction model for the m-th iteration, is the multi-factor energy consumption prediction model for the (m - 1)-th iteration, is the m-th decision tree, is the step size for the m-th iteration, is the input of the model. The training objective of the multi-factor energy consumption prediction model is to minimize the loss function:

[0131] ;

[0132] where E_true is the actual energy consumption, E_pred is the predicted energy consumption, is the regularization parameter, is the regularization term. After training, the model can accurately estimate the energy consumption of the future journey according to the input route plan, current environmental conditions, and vehicle status, and obtain the accurate energy consumption estimation result E_es. According to the accurate energy consumption estimation result E_es and the battery state information (SOC, SOH, etc.) provided by the battery management system (BMS), a hybrid model combining the physical battery model and the data-driven method is used to calculate the vehicle's endurance. The physical battery model part considers the battery capacity, discharge efficiency, and temperature influence:

[0133] ;

[0134] where C_ava is the available power, C_total is the total capacity, f(T) is the temperature influence function (such as a Gaussian function of temperature T), and η_dis is the discharge efficiency. The data-driven method part learns the energy consumption characteristics under different working conditions through historical data:

[0135] ;

[0136] where is a correction function (which can be a weighted function) that takes into account driving mode , terrain and traffic conditions ; is the driving mileage. Through calculation, a driving mileage prediction curve is generated, which represents the expected cruising range under different speeds and road conditions. Based on the driving mileage prediction curve and combined with the driver's historical driving habit data, a personalized energy-saving driving recommendation model S_eco is obtained. This model analyzes the difference between the current driving behavior and the optimal energy-efficient driving mode in real time and uses reinforcement learning methods to optimize the driving strategy:

[0137] ;

[0138] where is the value of the updated state-action value function (value), is the value of the state-action value function before update, is the learning rate, r is the immediate reward (related to energy efficiency), γ is the discount factor, is the value generated by the action adopted in the new state. S_eco provides real-time advice to the driver, including the best vehicle speed, the best acceleration, the energy recovery strategy, etc., to form a real-time driving optimization strategy. Using the geographical distribution data of urban charging infrastructure and the real-time operation status information of charging stations (the number of idle charging piles, queuing situation, charging rate, etc.), combined with the vehicle location and itinerary plan in the spatio-temporal trajectory knowledge graph, an intelligent charging recommendation model is constructed. The intelligent charging recommendation model uses a multi-objective optimization algorithm and considers multiple factors:

[0139] Distance cost: d(v, c) is the distance from vehicle v to charging station c;

[0140] Time cost: t_wait(c) + t_charge(v, c) is the waiting time and charging time;

[0141] Price cost: p(c, t) is the electricity price of charging station c at time t;

[0142] Facility quality: q(c) is the facility quality score of the charging station;

[0143] The optimization objective function is to minimize the weighted sum of the above factors;

[0144] Dynamically adjusted according to user preferences. By solving the optimization problem, the optimal charging station selection scheme is obtained. Combining the grid load data and the time-of-use electricity price policy, the cost-benefit of different charging periods is analyzed. Applying the dynamic programming algorithm to solve the optimal charging time arrangement:

[0145] f[i] = min{f[i - 1] + cost(i), f[i - 2] + cost(i - 1, i),...};

[0146] where f[i] represents the minimum charging cost for the first i time periods, and cost(i) represents the cost of charging in the i-th time period. Through optimization, an economically optimal charging time recommendation is generated to form an economic charging strategy. By constructing a regional charging demand prediction model M_demand, the spatio-temporal distribution of the charging demands of multiple vehicles is analyzed. The prediction model is based on historical data and the current vehicle status, and uses time series prediction methods (such as ARIMA or Prophet) to predict the charging demand distribution in future time periods. Based on the prediction results, a charging demand balanced scheduling algorithm A_balance is defined. This algorithm guides vehicles to charge during off-peak hours through price incentives and time window allocation, avoiding congestion of charging resources at specific times and in specific areas. The constrained optimization problem solved by the algorithm is:

[0147] ;

[0148] ;

[0149] where D_t is the charging demand at time t, μ is the average demand level, and D_total is the total demand. Through algorithm optimization, a balanced charging resource allocation scheme is obtained. Based on the game theory model, a charging resource sharing mechanism among vehicles is defined. This mechanism regards private charging pile owners and charging demand parties as game participants, and through an incentive mechanism, realizes the efficient allocation of resources. The sharing pricing model is based on demand elasticity and cost structure:

[0150] ; where p is the sharing price, c is the basic cost, Δ is the price adjustment function, D is the demand quantity, and S is the supply quantity. At the same time, a credit evaluation system is defined to record the historical behaviors of participants, provide preferential treatment to high-credit users, and form a collaborative charging network. Integrating real-time driving optimization strategies, economic charging strategies, and collaborative charging networks, a hierarchical decision-making support model is constructed. This model includes three levels:

[0151] Perception layer: Collect vehicle status, environmental conditions, and user preferences;

[0152] Decision layer: Make decisions based on multi-objective optimization and reinforcement learning;

[0153] Execution layer: Translate decisions into specific control instructions and user suggestions;

[0154] The model adopts a hierarchical reinforcement learning framework. The upper-layer policy sets goals, and the lower-layer policy executes specific tasks. It can adaptively adjust the energy management strategy according to dynamic factors such as vehicle status, driving habits, energy prices, and the distribution of charging infrastructure, forming a dynamic energy management strategy network to provide a comprehensive energy optimization solution for commercial vehicle users.

[0155] In a specific embodiment, the execution process of the multi-level vehicle connection module 105 specifically includes the following steps:

[0156] (1) Based on vehicle wireless communication technology, establish a direct communication link between vehicles to obtain a vehicle communication topology network, and define a data exchange protocol according to the vehicle communication topology network to obtain an efficient information sharing mechanism;

[0157] (2) Integrate the sensor data of the vehicle itself and the perception information shared by surrounding vehicles to achieve collaborative environment perception, obtain an enhanced perception result, and construct a local environment dynamic map based on the enhanced perception result to obtain a shared situation model;

[0158] (3) Calculate the relative position relationship between vehicles according to the high-precision spatio-temporal positioning data to obtain a set of fleet formation conditions, and define an adaptive fleet organization algorithm based on the set of fleet formation conditions to obtain an intelligent fleet formation strategy;

[0159] (4) Combine the shared situation model and the dynamic energy management strategy network to define a distributed decision-making mechanism, enabling each vehicle to make a globally optimal decision based on local information to obtain a collaborative decision-making framework;

[0160] (5) Define a fault tolerance mechanism and a backup decision-making strategy for communication interruption and node failure situations to obtain a robustness guarantee scheme, and integrate the efficient information sharing mechanism, the intelligent fleet formation strategy, the collaborative decision-making framework, and the robustness guarantee scheme to obtain a multi-level vehicle connection cooperation framework.

[0161] Specifically, based on wireless communication technologies such as vehicle DSRC (Dedicated Short Range Communications, 5.9 GHz band) and C-V2X (Cellular Vehicle-to-Everything, based on 4G / 5G technology), a multi-mode communication system supporting vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-cloud (V2C) is established. The DSRC communication module uses the IEEE 802.11p protocol to provide low-latency communication with a 10 MHz bandwidth, a 6 Mbps data rate, and a communication range of about 300 m, which is suitable for safety-critical applications; the C-V2X communication module uses the 3GPP Release14 and above standards to provide a larger coverage area and higher reliability, which is suitable for non-safety-critical applications. The system dynamically selects the most suitable communication mode for the current scenario to form an adaptive hybrid communication architecture. Based on the vehicle position and communication connection status, a vehicle communication topology network G_co=(V, E, W) is constructed, where V is the set of vehicle nodes, E is the set of communication connections, and W is the set of connection quality weight sets. The connection quality weight w_ij is calculated based on signal strength (RSSI), signal-to-noise ratio (SNR), packet loss rate (PER), and latency, and can be a weighted sum; through periodic topology updates, the real-time and accurate communication network status is maintained. According to the characteristics of the vehicle communication topology network, a lightweight and low-latency data exchange protocol is defined. The protocol includes:

[0162] Message format definition: Based on ASN.1 (Abstract Syntax Notation), a standardized message structure is defined, including fields such as message type, timestamp, sender ID, priority, and payload;

[0163] Transmission priority strategy: Priorities are assigned according to the urgency and importance of the message content, such as collision warning > braking warning > road condition information > comfort application;

[0164] Congestion control mechanism: Based on the channel busy ratio (CBR), transmission parameters are adaptively adjusted, including transmission power, transmission rate, and message generation rate;

[0165] Security authentication mechanism: The elliptic curve digital signature algorithm (ECDSA) is used to ensure the authenticity and integrity of the message;

[0166] Through the protocol, an efficient and reliable information sharing mechanism M_sharing is implemented, which supports low-latency transmission of safety-critical information and high-throughput transmission of non-critical information. Integrate the sensor data of the vehicle itself (including radar, camera, lidar, etc.) and the perception information shared by surrounding vehicles through V2V communication to expand the perception range and eliminate blind spots. Apply the Bayesian sensor fusion framework for multi-source data integration:

[0167] ;

[0168] where X is the environmental state (quantized value), is the observation result from the 1st sensor to the nth sensor; is the observation result of the th sensor. The optimal state estimate is obtained through maximum a posteriori (MAP) estimation:

[0169] ;

[0170] In implementation, algorithms such as Kalman filtering and particle filtering are used to process continuous state variables, and the Dempster-Shafer theory (evidence theory) is used to process discrete state variables to achieve noise suppression and conflict resolution, obtaining enhanced perception results. Based on the enhanced perception results, a local environment dynamic map centered on the vehicle and covering a range of 300 - 500 meters around is constructed. This map includes the following layers:

[0171] Static layer: road geometry, lane lines, traffic signs, permanent obstacles, etc.;

[0172] Semi-static layer: temporary road works, traffic control, weather conditions, etc.;

[0173] Dynamic layer: dynamic targets such as surrounding vehicles, pedestrians, bicycles, animals, etc.;

[0174] The map is represented using a unified local coordinate system, supports an update frequency above 10Hz, and ensures the real-time nature of the environmental state. By structuring the local map information into a scene understanding model, including object recognition, behavior prediction, and risk assessment, a shared situation model is formed to support advanced decision-making functions. Based on high-precision spatio-temporal positioning data, the relative position, relative speed, and driving direction between adjacent vehicles are calculated. Define the necessary conditions for platoon formation:

[0175] Spatial proximity: the vehicle spacing is within a safe range;

[0176] Speed consistency: the speed difference is within a threshold range;

[0177] Direction consistency: the driving directions are basically the same;

[0178] Communication quality: the communication link quality is greater than a preset threshold;

[0179] These conditions constitute the platoon formation condition set. Based on the platoon formation condition set, an adaptive platoon organization algorithm is defined. This algorithm includes the following core components:

[0180] Platoon initialization: Select the platoon leader vehicle based on the leader election algorithm, usually choosing the vehicle with the best communication quality or the most forward position;

[0181] Platoon joining / leaving: Define smooth joining and leaving protocols to ensure the stability of the platoon structure;

[0182] Fleet splitting / merging: Support dynamic splitting and merging of fleets according to traffic conditions and destination information;

[0183] Spacing control: Adaptively adjust the vehicle spacing according to vehicle speed, road conditions, and communication quality. Common control strategies include Constant Time Headway (CTH) or Constant Safety Distance (CSD);

[0184] Distributed optimization methods are adopted in the algorithm implementation, such as Consensus-based Distributed Model Predictive Control (DMPC). Through algorithm optimization, an intelligent fleet formation strategy is formed to support dynamic, safe, and efficient fleet organization and control. Combining the shared context model and the dynamic energy management strategy network, a distributed decision-making mechanism is defined. This mechanism is based on consensus algorithms and game theory methods, enabling each vehicle to make globally optimized decisions based on local information and limited neighbor communication, including:

[0185] Distributed consensus algorithms are used for state synchronization and intention coordination, with the typical implementation being the average consensus algorithm; Distributed optimization algorithms are used to solve the global resource allocation problem, such as ADMM (Alternating Direction Method of Multipliers):

[0186] The distributed decision-making process considers multiple objectives, including safety, energy efficiency, travel efficiency, and ride comfort. These objectives are balanced through multi-objective optimization methods to form a collaborative decision-making framework, enabling each vehicle to make decisions close to the global optimum based on local information. For abnormal situations such as communication interruptions, node failures, and malicious attacks, a robustness guarantee scheme with multiple layers of protection is defined. This scheme includes:

[0187] Redundant communication paths: Utilize multi-hop communication and network coding technologies to ensure that information can still be transmitted when some links fail;

[0188] Decision degradation strategy: Define a hierarchical decision-making framework to smoothly degrade to a more conservative decision-making mode when the communication quality deteriorates;

[0189] Abnormal detection mechanism: Apply statistical methods and machine learning techniques to detect abnormal behaviors and malicious attacks;

[0190] Local backup strategy: Pre-configure a backup decision-making strategy based on local information to ensure basic safety when the collaborative system fails;

[0191] Security authentication mechanism: Use PKI (Public Key Infrastructure) and blockchain technologies to ensure communication security and data integrity;

[0192] Through these mechanisms, ensure that the system can still maintain its basic functions in the face of various abnormal situations, and guarantee the safety of vehicles and passengers. Integrate an efficient information sharing mechanism, an intelligent fleet formation strategy, a collaborative decision-making framework, and a robustness guarantee scheme to build a multi-level vehicle connection and collaboration framework. This framework consists of four levels:

[0193] Communication layer: Processes information exchange between vehicles to ensure the efficiency and reliability of data transmission;

[0194] Perception layer: Integrates multi-source perception data to build a shared environment model;

[0195] Decision-making layer: Based on the environment model and energy strategy, conducts collaborative decision-making optimization;

[0196] Security layer: Provides robustness guarantee to cope with abnormal situations;

[0197] The framework is defined modularly, supports independent upgrades and expansions of different functions, adapts to application scenarios under different penetration rates and technical conditions, from simple information sharing to complex collaborative control, and provides comprehensive collaborative support for the intelligent travel of commercial vehicles.

[0198] This application constructs a complete intelligent networking solution for commercial vehicles by performing fusion processing and accuracy enhancement on the Beidou multi-modal positioning signals obtained by commercial vehicles, combined with comprehensive monitoring and analysis of vehicle states. The solution realizes the leap from single-vehicle intelligence to group collaboration, organically combines vehicle positioning, state monitoring, behavior analysis, energy management, and collaborative control, forming a closed-loop intelligent travel ecosystem. The system significantly improves the positioning accuracy, energy efficiency, and travel experience of commercial vehicles through advanced technologies such as multi-source data fusion, machine learning, and distributed decision-making. At the same time, through deep integration with the urban intelligent transportation system, it promotes the collaborative development of commercial vehicles and urban traffic infrastructure.

[0199] This application also provides a commercial vehicle intelligent connection device based on Beidou positioning. The commercial vehicle intelligent connection device based on Beidou positioning includes a memory and a processor. When the computer-readable instructions stored in the memory are executed by the processor, the processor executes the steps of the Beidou positioning-based commercial vehicle intelligent connection system in the above-mentioned embodiments.

[0200] This application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer executes the steps of the Beidou positioning-based commercial vehicle intelligent connection system.

[0201] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0202] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0203] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0204] The foregoing are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for ordinary users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A commercial vehicle intelligent connection system based on Beidou positioning, characterized in that, Including: A data acquisition module, which is used to obtain sub-meter-level high-precision spatio-temporal positioning data by fusing and enhancing the accuracy of Beidou multi-modal positioning signals obtained by commercial vehicles; wherein, the accuracy enhancement includes weighted fusion after signal quality evaluation of multi-source positioning information and suppression of positioning noise using the Kalman filter algorithm; An intelligent analysis module, which is used to perform multi-dimensional acquisition and intelligent analysis on the state parameters of the power system, battery system, and vehicle-mounted equipment of commercial vehicles, and dynamically predict the remaining service life of key components to obtain a vehicle health index model; wherein, the intelligent analysis includes evaluating the battery health state based on electrochemical impedance spectroscopy analysis technology and performing multi-level fusion with the health assessment results of the power system and vehicle-mounted equipment; An intelligent mining module, based on the sub-meter-level high-precision spatio-temporal positioning data and the vehicle health index model, conducts mining of the collective behavior patterns of commercial vehicles, and constructs a multi-level knowledge representation including vehicle movement patterns, driving-vehicle state mapping, and vehicle collective influence to obtain a spatio-temporal trajectory knowledge graph; wherein, the mining of the collective behavior patterns of commercial vehicles further includes using graph neural networks to model the interaction behaviors between vehicles to identify key nodes and community structures; An energy optimization module, which is used to utilize the spatio-temporal trajectory knowledge graph to optimize the comprehensive energy efficiency of commercial vehicles and conduct collaborative charging planning, and integrate real-time driving optimization, economic charging, and a collaborative charging network to obtain a dynamic energy management strategy network; wherein, the collaborative charging planning further includes optimizing the charging resource sharing mechanism between vehicles based on a game theory model to form a collaborative charging network; A multi-level vehicle connection module, based on the sub-meter-level high-precision spatio-temporal positioning data and the dynamic energy management strategy network, constructs a collaborative perception and distributed decision-making mechanism between vehicles, and integrates the multi-level vehicle connection collaboration framework with the urban intelligent transportation system to obtain a comprehensive solution for the intelligent travel of commercial vehicles; wherein, the collaborative perception and distributed decision-making mechanism between vehicles further includes integrating the sensor data of the vehicle itself and the perception information shared by surrounding vehicles to construct a shared situation model to support distributed collaborative decision-making.

2. The commercial vehicle intelligent connection system based on Beidou positioning according to claim 1, characterized in that, The data acquisition module, which is used to fuse and enhance the accuracy of the Beidou multi-modal positioning signals obtained by commercial vehicles to obtain high-precision spatio-temporal positioning data, further includes: Collecting multi-frequency signals of the Beidou navigation system and differential signals of ground augmentation stations to obtain an original positioning data set; Combining inertial navigation unit data, adaptively compensating the filtered positioning data to obtain a continuous positioning trajectory, and applying a trajectory prediction algorithm in a signal occlusion area to obtain a complete positioning sequence; Performing map matching and constraint optimization on the complete positioning sequence to obtain road-level precise positioning data, and adaptively correcting the positioning accuracy in complex scenarios based on a deep learning model to finally obtain the sub-meter-level positioning result; Constructing a spatio-temporal index and synchronizing timestamps for the sub-meter-level positioning result.

3. The commercial vehicle intelligent connection system based on Beidou positioning according to claim 1, characterized in that, The intelligent analysis module, which is used to perform multi-dimensional acquisition and intelligent analysis on the state parameters of the power system, battery system, and vehicle-mounted equipment of commercial vehicles to obtain a vehicle health index model, further includes: Collect power system parameters through a multi-source sensor network, obtain a power system state matrix, and perform anomaly detection and fault diagnosis on the power system state matrix to obtain a power system health vector; Collect the operating status data of in-vehicle control units, communication modules, and auxiliary devices, obtain a set of device performance indicators, and construct a device reliability evaluation network based on the set of device performance indicators to obtain a device health score; Perform multi-level fusion on the power system health vector, the battery capacity attenuation model, and the device health score to obtain a vehicle comprehensive state feature space, and apply clustering and classification algorithms in the feature space to obtain a vehicle state evaluation result; Based on the vehicle state evaluation result, construct a deep neural network prediction model to dynamically predict the remaining service life of the vehicle's key components, and combine historical operation data to generate the vehicle health index model.

4. The vehicle intelligent connection system based on Beidou positioning according to claim 1, characterized in that, The intelligent mining module, which performs mining on the group behavior patterns of commercial vehicles based on the high-precision spatio-temporal positioning data and the vehicle health index model to obtain a spatio-temporal trajectory knowledge graph, further includes: Perform trajectory segmentation and feature extraction on the high-precision spatio-temporal positioning data to obtain a set of vehicle movement pattern features, and perform trajectory clustering based on the set of vehicle movement pattern features to obtain a library of typical driving routes; Combine the vehicle health index model and driving behavior data to establish an association analysis model between driving habits and vehicle states to obtain a driving-vehicle state mapping matrix; Perform frequent pattern mining on the spatio-temporal trajectory data of a large number of vehicles to identify high-frequency travel routes and time windows to obtain a set of spatio-temporal activity patterns, and construct an urban traffic flow prediction model based on the set of spatio-temporal activity patterns to obtain a dynamic traffic flow distribution map; Integrate the library of typical driving routes, the driving-vehicle state mapping matrix, the dynamic traffic flow distribution map, and the vehicle group influence distribution to construct a multi-level knowledge representation model.

5. The commercial vehicle intelligent connection system based on Beidou positioning according to claim 1, wherein, The energy optimization module, which uses the spatio-temporal trajectory knowledge graph to perform energy efficiency optimization and charging planning for commercial vehicles to obtain a dynamic energy management strategy network, further includes: Based on the spatio-temporal trajectory knowledge graph, perform energy consumption analysis on the driving routes of commercial vehicles to obtain a library of road section energy consumption characteristics, and combine terrain, weather, and traffic condition data to establish a multi-factor energy consumption prediction model to obtain an accurate energy consumption estimation result; According to the accurate energy consumption estimation result and battery state information, calculate the vehicle's endurance capacity to obtain a driving range prediction curve, and based on the driving range prediction curve, give personalized energy-saving driving suggestions to the driver to obtain a real-time driving optimization strategy; Use urban charging facility distribution data and real-time charging station status information, combine with the spatio-temporal trajectory knowledge graph, construct an intelligent charging recommendation model to obtain an optimal charging station selection plan, and generate suggestions for the best charging time period based on grid load and electricity price fluctuation data to obtain an economic charging strategy; Perform collaborative scheduling on the charging requirements of multiple vehicles to obtain a balanced charging resource allocation plan; Integrate the real-time driving optimization strategy, the economic charging strategy, and the collaborative charging network to construct a hierarchical decision support system.

6. The commercial vehicle intelligent connection system based on Beidou positioning according to claim 1, characterized in that, The multi-level vehicle connection module constructs a collaborative perception and distributed decision-making mechanism between vehicles based on the high-precision spatio-temporal positioning data and the dynamic energy management strategy network to obtain a multi-level vehicle connection cooperation framework, and further includes: Based on vehicle wireless communication technology, establish a direct communication link between vehicles to obtain a vehicle communication topology network, and define a data exchange protocol according to the vehicle communication topology network to obtain an efficient information sharing mechanism; Calculate the relative position relationship between vehicles based on high-precision spatio-temporal positioning data to obtain a set of convoy formation conditions, and define an adaptive convoy organization algorithm based on the set of convoy formation conditions to obtain an intelligent convoy formation strategy; Define a fault tolerance mechanism and a backup decision-making strategy to obtain a robustness guarantee scheme, and integrate the efficient information sharing mechanism, the intelligent convoy formation strategy, the collaborative decision-making framework and the robustness guarantee scheme.

7. A commercial vehicle intelligent connection device based on Beidou positioning, characterized in that The commercial vehicle intelligent connection device based on Beidou positioning includes: a memory and at least one processor, and instructions are stored in the memory; the at least one processor calls the instructions in the memory so that the commercial vehicle intelligent connection device based on Beidou positioning executes the commercial vehicle intelligent connection system based on Beidou positioning according to any one of claims 1 to 6.

8. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instructions are executed by the processor, the commercial vehicle intelligent connection system based on Beidou positioning according to any one of claims 1 to 6 is implemented.

Images