Internet of vehicles communication mode selection system and method

Abstract

The invention relates to the technical field of Internet of Vehicles, in particular to an Internet of Vehicles communication mode selection system and method, and the system comprises a vehicle data collection module, a vehicle communication management module, a vehicle-mounted decision support module, an environment perception module, a driver health monitoring module, an advanced driving assistance module, a vehicle-mounted entertainment information module, and a self-adaptive communication mode selection module. The vehicle data acquisition module is used for sensor data collection, data preprocessing and data storage; the vehicle communication management module is used for communication protocol selection, data encryption and data transmission; according to the Internet of Vehicles communication mode selection system provided by the invention, the advanced machine learning algorithm and the adaptive optimization technology are introduced, so that the switching problem of the communication mode can be processed more intelligently and more efficiently, and the overall performance and the user experience of the Internet of Vehicles system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle networking, and in particular to a vehicle networking communication mode selection system and method. Background Art

[0002] The Internet of Vehicles refers to the use of wireless network technology to connect vehicles with the surrounding environment, other vehicles, infrastructure, and the Internet to achieve information interaction and sharing. Internet of Vehicles technology can significantly improve driving safety, improve traffic efficiency, and provide drivers and passengers with a more intelligent and convenient travel experience. The communication mode refers to the way and method of transmitting data and information between different devices or systems. In the Internet of Vehicles, the communication mode specifically refers to the standards and protocols for data exchange between vehicles and other entities. However, the existing Internet of Vehicles communication mode switching involves complex signaling and protocol conversion, resulting in large delays and affecting high-real-time applications. Frequent switching consumes a lot of network resources (such as bandwidth and signaling overhead), reduces network efficiency, and may cause short service interruptions or data loss during switching, affecting user experience and system reliability. The traditional switching mechanism is based on preset rules or threshold decisions, and lacks the ability to intelligently adjust to real-time network status and user needs.

[0003] In summary, the Internet of Vehicles communication mode selection system of the present invention introduces advanced machine learning algorithms and adaptive optimization technologies to handle the problem of switching communication modes more intelligently and efficiently, thereby improving the overall performance and user experience of the Internet of Vehicles system to solve the above-mentioned problems.

[0004] In summary, it is necessary to propose a vehicle network communication mode selection system and method to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle network communication mode selection system and method to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The vehicle networking communication mode selection system includes a vehicle data acquisition module, a vehicle communication management module, an in-vehicle decision support module, an environmental perception module, a driver health monitoring module, an advanced driving assistance module, an in-vehicle entertainment information module, and an adaptive communication mode selection module;

[0008] The vehicle data acquisition module is used for sensor data collection, data preprocessing and data storage;

[0009] The vehicle communication management module is used for communication protocol selection, data encryption and data transmission;

[0010] The vehicle-mounted decision support module is used for real-time traffic condition analysis, route planning and driving behavior analysis;

[0011] The environmental perception module is used for surrounding vehicle detection, pedestrian and obstacle detection and weather condition monitoring;

[0012] The driver health monitoring module is used to monitor the driver's physiological parameters, fatigue detection and health data analysis;

[0013] The advanced driver assistance module is used for automatic emergency braking, lane keeping and blind spot monitoring;

[0014] The in-vehicle entertainment information module is used for media playback control, information display and voice assistant;

[0015] The adaptive communication mode selection module is used for communication mode detection, mode switching decision and communication mode optimization.

[0016] Preferably, the vehicle data acquisition module further includes a sensor data collection unit, a data preprocessing unit and a data storage unit;

[0017] The sensor data collection unit is used to collect data on the vehicle status and surrounding environment through sensors during vehicle driving, and realizes real-time data collection function through sensor interface driver software;

[0018] The data preprocessing unit is used to filter and remove noise from the collected data, and improve the accuracy and reliability of the data through digital filtering algorithms and noise elimination software;

[0019] The data storage unit is used to store the processed data in a local storage device for subsequent analysis and use through a database management system and a data compression algorithm.

[0020] Preferably, the vehicle communication management module further includes a communication protocol selection unit, a data encryption unit and a data transmission unit;

[0021] The communication protocol selection unit is used to dynamically select V2V, V2I or V2C communication protocols in different scenarios, and realize communication adaptability through protocol selection algorithm and communication protocol stack;

[0022] The data encryption unit is used to ensure data security during data transmission, and to ensure data confidentiality and integrity through AES and RSA encryption algorithms;

[0023] The data transmission unit is used to transmit the encrypted data to the target device via a wireless network, and ensures efficient data transmission through a transmission control protocol and a network stack software.

[0024] Preferably, the vehicle-mounted decision support module further includes a real-time traffic condition analysis unit, a path planning unit and a driving behavior analysis unit;

[0025] The real-time traffic condition analysis unit is used to analyze the current road conditions according to the real-time traffic data and provide the optimal driving strategy through the traffic flow analysis algorithm and the machine learning model;

[0026] The path planning unit is used to plan the optimal driving route according to the real-time road conditions, and reduce driving time and fuel consumption through the A* algorithm and the Dijkstra algorithm;

[0027] The driving behavior analysis unit is used to analyze the driver's behavior pattern and provide driving suggestions, thereby improving driving safety through behavior analysis algorithms and driving behavior models.

[0028] Preferably, the environment perception module further includes a surrounding vehicle detection unit, a pedestrian and obstacle detection unit and a weather condition monitoring unit;

[0029] The surrounding vehicle detection unit is used to monitor the position and speed of surrounding vehicles in real time, and ensure driving safety through target detection algorithms and computer vision models;

[0030] The pedestrian and obstacle detection unit is used to identify pedestrians and obstacles on the road and prevent collision accidents through deep learning models and image recognition algorithms;

[0031] The weather condition monitoring unit is used to monitor and predict the impact of weather conditions on driving, and ensure driving safety through meteorological data processing algorithms and weather forecast models.

[0032] Preferably, the driver health monitoring module further includes a physiological parameter monitoring unit, a fatigue detection unit and a health data analysis unit;

[0033] The physiological parameter monitoring unit is used to monitor the driver's heart rate and blood pressure physiological parameters in real time, and prevent sudden health problems through physiological signal processing algorithms and sensor interfaces;

[0034] The fatigue detection unit is used to detect the driver's fatigue state and provide warnings, and prevent fatigue driving through fatigue detection algorithms and eye tracking technology;

[0035] The health data analysis unit is used to analyze the driver's health data and provide health advice, and improve the driver's health management through health data analysis models and machine learning algorithms.

[0036] Preferably, the advanced driver assistance module further includes an automatic emergency braking unit, a lane keeping assistance unit and a blind spot monitoring unit;

[0037] The automatic emergency braking unit is used to automatically brake in an emergency situation and avoid collision through emergency braking algorithm and radar data processing;

[0038] The lane keeping assist unit is used to assist the vehicle to stay in the lane and prevent the vehicle from deviating from the lane through lane detection algorithms and direction control software;

[0039] The blind spot monitoring unit is used to monitor the blind spot area of ​​the vehicle and provide warnings, and avoid collisions when changing lanes through blind spot monitoring algorithms and ultrasonic sensor data processing.

[0040] Preferably, the in-vehicle entertainment information module further includes a media playback control unit, an information display unit and a voice assistant unit;

[0041] The media player control unit is used to control the in-vehicle entertainment system to play music and videos, and improve the driving experience through the media player software and user interface control;

[0042] The information display unit is used to display navigation information and real-time road conditions on the vehicle screen, and to assist driving decisions through information display software and a graphical interface library;

[0043] The voice assistant unit is used to control the vehicle system through voice, and improve the operational convenience through voice recognition algorithm and natural language processing model.

[0044] Preferably, the adaptive communication mode selection module further includes a communication mode detection unit, a mode switching decision unit and a communication mode optimization unit;

[0045] The communication mode detection unit is used to detect the status and performance of the current communication network, and monitor the network status in real time through a network performance monitoring algorithm and data analysis software;

[0046] The mode switching decision unit is used to decide whether to switch the communication mode according to the detection result, and ensure communication stability through a decision tree algorithm and a dynamic switching strategy;

[0047] The communication mode optimization unit is used to optimize the parameter settings of the communication mode and improve the transmission efficiency and communication performance by optimizing the algorithm and the parameter tuning model.

[0048] The present invention also provides a working method of a vehicle networking communication mode selection system, comprising the following steps:

[0049] S1. Data collection: The vehicle collects data on the vehicle status and surrounding environment in real time through sensors. The collected data is pre-processed, including filtering and denoising, to ensure the accuracy and reliability of the data. The processed data is stored in the local storage device for subsequent analysis and use;

[0050] S2. Communication protocol selection: According to different driving scenarios of vehicles, dynamically select communication protocols including V2V, V2I or V2C, calculate network performance parameters through multiple protocol selection algorithms, obtain selection tendencies of different communication protocols, and obtain a set of selection tendencies of different communication protocols through information entropy algorithm, and use weighted summation to combine the two selection tendencies to select the appropriate communication protocol;

[0051] S3. Data encryption and transmission: During the data transmission process, the AES and RSA encryption algorithms are used to encrypt the data to ensure the confidentiality and integrity of the data. The encrypted data is transmitted to the target device via the wireless network to ensure efficient data transmission;

[0052] S4. Traffic condition analysis: Based on real-time collected traffic data, analyze the current road conditions and use traffic flow analysis algorithms and machine learning models to provide the best driving strategy;

[0053] S5. Path planning: Plan the optimal driving route based on real-time traffic conditions, and reduce driving time and fuel consumption through A* algorithm and Dijkstra algorithm;

[0054] S6. Driving behavior analysis: Analyze the driver's behavior patterns, provide driving suggestions, and improve driving safety through behavior analysis algorithms and driving behavior models;

[0055] S7. Environmental perception: Real-time monitoring of the position and speed of surrounding vehicles, identification of pedestrians and obstacles on the road, monitoring and predicting the impact of weather conditions on driving, and ensuring driving safety through target detection algorithms, deep learning models, and meteorological data processing algorithms;

[0056] S8. Driver health monitoring: Real-time monitoring of the driver's heart rate and blood pressure physiological parameters, detection of the driver's fatigue state and provision of warnings, and improvement of the driver's health management through physiological signal processing algorithms, fatigue detection algorithms and health data analysis models, to prevent sudden health problems and fatigue driving;

[0057] S9. Advanced driving assistance: Automatically brakes in emergency situations, assists the vehicle to stay in the lane, monitors the vehicle's blind spots and provides warnings, and avoids collisions and prevents the vehicle from leaving the lane through emergency braking algorithms, lane detection algorithms, and blind spot monitoring algorithms;

[0058] S10. In-car entertainment and information display: Control the in-car entertainment system to play music and videos, display navigation information and real-time traffic conditions on the in-car screen, and improve driving experience and operating convenience through media player software, information display software and voice recognition algorithms;

[0059] S11. Adaptive optimization of communication modes: Detect the status and performance of the current communication network, decide whether to switch the communication mode based on the detection results, monitor the network status in real time through network performance monitoring algorithms, decision tree algorithms and optimization algorithms, ensure the stability of communication and improve transmission efficiency.

[0060] Compared with the prior art, the present invention can dynamically select a suitable communication mode according to the specific scenario of vehicle driving to ensure the best data transmission efficiency and stability. By optimizing the communication protocol and network stack configuration, the system can maximize network performance indicators, reduce delays and packet loss rates, and improve data transmission efficiency. AES and RSA encryption technologies are used to ensure the confidentiality and integrity of data during transmission to prevent information leakage or tampering. Machine learning models are used to analyze traffic conditions and driving behavior to provide drivers with personalized driving strategies and driving suggestions to improve driving safety. The adaptability of the selected communication protocol can be regularly evaluated, and adaptive optimization can be performed according to the network status to ensure good communication performance in various network environments. Therefore, the vehicle network communication mode selection system of the present invention can handle the switching problem of communication modes more intelligently and efficiently by introducing advanced machine learning algorithms and adaptive optimization technologies, thereby improving the overall performance and user experience of the vehicle network system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 Selecting a system topology diagram for the vehicle networking communication mode of the present invention;

[0062] Figure 2 This is a flow chart of the vehicle networking communication mode selection method of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Example 1

[0065] See also Figure 1 , the present invention proposes a vehicle networking communication mode selection system, the system is composed of a vehicle data acquisition module, a vehicle communication management module, a vehicle decision support module, an environment perception module, a driver health monitoring module, an advanced driving assistance module, an in-vehicle entertainment information module, and an adaptive communication mode selection module;

[0066] Among them, it should be noted that this system collects sensor data, preprocesses data and stores data through the vehicle data acquisition module, selects communication protocols, encrypts data and transmits data through the vehicle communication management module, performs real-time traffic condition analysis, path planning and driving behavior analysis through the on-board decision support module, detects surrounding vehicles, pedestrians and obstacles and monitors weather conditions through the environmental perception module, monitors the driver's physiological parameters, performs fatigue detection and analyzes health data through the driver health monitoring module, performs automatic emergency braking, lane keeping and blind spot monitoring through the advanced driving assistance module, controls media playback, displays information and uses voice assistants through the on-board entertainment information module, and performs communication mode detection, mode switching decisions and communication mode optimization through the adaptive communication mode selection module.

[0067] In this embodiment, it should also be noted that the vehicle data acquisition module of the system also includes a sensor data collection unit, a data preprocessing unit and a data storage unit. The sensor data collection unit is used to collect data on the vehicle status and the surrounding environment through sensors during vehicle driving, and realizes the real-time data acquisition function through the sensor interface driver software. The data preprocessing unit is used to filter and denoise the collected data, and improve the accuracy and reliability of the data through digital filtering algorithms and noise elimination software. The data storage unit is used to store the processed data in a local storage device, and perform subsequent analysis and use through a database management system and a data compression algorithm.

[0068] In this embodiment, it should also be noted that the vehicle communication management module of the system also includes a communication protocol selection unit, a data encryption unit and a data transmission unit. The communication protocol selection unit is used to dynamically select V2V, V2I or V2C communication protocols in different scenarios, and achieve communication adaptability through protocol selection algorithms and communication protocol stacks. The data encryption unit is used to ensure data security during data transmission, and to ensure data confidentiality and integrity through AES and RSA encryption algorithms. The data transmission unit is used to transmit encrypted data to the target device via a wireless network, and to ensure efficient data transmission through transmission control protocols and network stack software.

[0069] In this embodiment, it should also be noted that the on-board decision support module of the system also includes a real-time traffic condition analysis unit, a path planning unit and a driving behavior analysis unit. The real-time traffic condition analysis unit is used to analyze the current road conditions based on real-time traffic data, and provide the optimal driving strategy through traffic flow analysis algorithms and machine learning models. The path planning unit is used to plan the optimal driving route according to the real-time road conditions, and reduce driving time and fuel consumption through the A* algorithm and the Dijkstra algorithm. The driving behavior analysis unit is used to analyze the driver's behavior patterns and provide driving suggestions, and improve driving safety through behavior analysis algorithms and driving behavior models.

[0070] In this embodiment, it should also be noted that the environmental perception module of the system also includes a surrounding vehicle detection unit, a pedestrian and obstacle detection unit and a weather condition monitoring unit. The surrounding vehicle detection unit is used to monitor the position and speed of surrounding vehicles in real time, and ensure driving safety through target detection algorithms and computer vision models. The pedestrian and obstacle detection unit is used to identify pedestrians and obstacles on the road, and prevent collision accidents through deep learning models and image recognition algorithms. The weather condition monitoring unit is used to monitor and predict the impact of weather conditions on driving, and ensure driving safety through meteorological data processing algorithms and weather forecast models.

[0071] In this embodiment, it should also be noted that the driver health monitoring module of the system also includes a physiological parameter monitoring unit, a fatigue detection unit and a health data analysis unit. The physiological parameter monitoring unit is used to monitor the driver's heart rate and blood pressure physiological parameters in real time, and prevent sudden health problems through physiological signal processing algorithms and sensor interfaces. The fatigue detection unit is used to detect the driver's fatigue state and provide warnings, and prevent fatigue driving through fatigue detection algorithms and eye tracking technology. The health data analysis unit is used to analyze the driver's health data and provide health advice, and improve the driver's health management through health data analysis models and machine learning algorithms.

[0072] In this embodiment, it should also be noted that the advanced driving assistance module of the system also includes an automatic emergency braking unit, a lane keeping assist unit and a blind spot monitoring unit. The automatic emergency braking unit is used to automatically brake in an emergency situation and avoid collisions through emergency braking algorithms and radar data processing. The lane keeping assist unit is used to assist the vehicle to stay in the lane and prevent the vehicle from deviating from the lane through lane detection algorithms and direction control software. The blind spot monitoring unit is used to monitor the blind spot area of ​​the vehicle and provide warnings, and avoid collisions when changing lanes through blind spot monitoring algorithms and ultrasonic sensor data processing.

[0073] In this embodiment, it should also be noted that the in-vehicle entertainment information module of the system also includes a media playback control unit, an information display unit and a voice assistant unit. The media playback control unit is used to control the in-vehicle entertainment system to play music and videos, and to improve the driving experience through media player software and user interface control. The information display unit is used to display navigation information and real-time road conditions on the in-vehicle screen, and to assist driving decisions through information display software and a graphical interface library. The voice assistant unit is used to control the in-vehicle system through voice, and to improve operational convenience through voice recognition algorithms and natural language processing models.

[0074] In this embodiment, it should also be noted that the adaptive communication mode selection module of the system also includes a communication mode detection unit, a mode switching decision unit and a communication mode optimization unit. The communication mode detection unit is used to detect the status and performance of the current communication network, and monitor the network status in real time through a network performance monitoring algorithm and data analysis software. The mode switching decision unit is used to decide whether to switch the communication mode based on the detection results, and ensure communication stability through a decision tree algorithm and a dynamic switching strategy. The communication mode optimization unit is used to optimize the parameter settings of the communication mode, and improve transmission efficiency and communication performance through optimization algorithms and parameter tuning models.

[0075] Example 2

[0076] See also Figure 2 The present invention also proposes a working method of a vehicle networking communication mode selection system, which, in practical application, specifically includes the following steps:

[0077] Step S1: Data collection:

[0078] Sensor data collection: Real-time data collection of vehicle status and surrounding environment through sensors on the vehicle, including cameras, radars, and GPS;

[0079] Data preprocessing: Filter and denoise the collected data, and use digital filtering algorithms to improve the accuracy and reliability of the data;

[0080] Data storage: Store the processed data in local storage devices and use database management systems for data storage and management;

[0081] Data compression: Apply data compression algorithms to reduce storage space usage and facilitate subsequent data analysis and use;

[0082] Data access: Provide data access interface so that other modules can access and use the data;

[0083] Step S2: Communication protocol selection:

[0084] The protocol selection algorithm dynamically selects communication protocols including V2V, V2I or V2C according to different vehicle driving scenarios. The network performance parameters are calculated through multiple protocol selection algorithms to obtain different selection tendencies of communication protocols, set as A1, A2, A3, and a set of different selection tendencies of communication protocols are obtained through the information entropy algorithm, set as B1, B2, B3, and the weighted sum method is used to combine the two selection tendencies to select the appropriate communication protocol. First, based on the network performance parameters collected during vehicle driving, such as delay, packet loss rate, throughput, etc., the selection tendency is calculated using the network performance parameters. For each communication protocol (V2V, V2I, V2C), the network performance parameters are used to calculate its applicability score:

[0085]

[0086] In the formula, A i is the suitability score of the i-th communication protocol (i=1, 2, 3 respectively indicate the selection of V2V, V2I, and V2C protocols), wj is the weight of the j-th network performance parameter, and p ij It is the performance of the i-th communication protocol on the j-th network performance parameter. The score calculation is based on the weighted sum of the delay, packet loss rate and throughput parameters. The specific weight is determined according to the actual application scenario.

[0087] Specifically, the performance determination process of the i-th communication protocol on the j-th network performance parameter is as follows:

[0088] For each network performance parameter j, define one or more specific performance standards or indicators. These standards can be throughput, delay, packet loss rate, stability. For each communication protocol i, measure its performance on each performance parameter j in the actual network environment or simulate it in a simulation environment. Record the specific value of each communication protocol on each performance parameter. Convert the performance of each communication protocol on each performance parameter into a standardized score. The standardized score can be a relative score based on the maximum value, minimum value, average value or other statistics. Convert the original performance value into a standardized score:

[0089]

[0090] In the formula, x ij is the original value of communication protocol i on performance parameter j, min(x j ) and max(x j ) are the minimum and maximum values ​​of all communication protocols on performance parameter j respectively;

[0091] Apply weights:

[0092] According to the importance of each performance parameter, a weight w is assigned to it. j ;

[0093] Weights can be based on expert opinion, historical data, or other relevant information;

[0094] Calculate the suitability score for each communication protocol:

[0095]

[0096] Through the above steps, the performance of each communication protocol on each network performance parameter can be determined and its applicability score can be calculated;

[0097] Then, based on the collected interaction information between the vehicle and the surrounding environment (other vehicles, infrastructure, and the cloud), the information entropy algorithm is used to calculate the selection tendency, analyze the information entropy of the interaction between the vehicle and the surrounding environment, and calculate the applicability score of each communication protocol based on the size of the information entropy:

[0098]

[0099] In the formula, B i is the suitability score of the ith communication protocol, q ik is the probability distribution of the i-th communication protocol in the k-th information entropy category;

[0100] Specifically, the probability distribution calculation process of the i-th communication protocol in the k-th information entropy category is as follows:

[0101] First, the definition of information entropy categories is clear, which are different data features, message types or communication modes. The total number of information entropy categories to be analyzed is determined. For each communication protocol i, the number of occurrences or frequencies of the protocol in each information entropy category k is collected. The data can come from actual communication records, simulation data or expert evaluation. For each communication protocol i and each information entropy category k, the probability q of the protocol in the category is calculated. ik , with probability q ik It is calculated by dividing the number of occurrences of the protocol in category k by the total number of occurrences of the protocol in all categories, ensuring that all calculated probabilities q ik are all between 0 and 1, and for each communication protocol i, the sum of the probabilities of all categories k is equal to 1, and the suitability score of each communication protocol is calculated:

[0102]

[0103] Explain the results,The communication protocol with a higher suitability score Bi performs better in terms of information entropy, which means it is more efficient or reliable in processing or transmitting information;

[0104] The two algorithms are combined using a weighted summation method to obtain the comprehensive applicability score of each student's protocol:

[0105] C i =α·A i +(1-α)·B i

[0106] In the formula, C i is the comprehensive applicability score of the i-th communication protocol, α is the weight of the selection tendency calculated by the network performance parameter, and 1-α is the weight of the selection tendency calculated by the information entropy algorithm. Finally, according to the comprehensive applicability score, the communication protocol with the highest score is selected.

[0107] Among them, it should be noted that when using the information entropy algorithm to calculate the selection tendency, when the calculated entropy value is low, it means that the decision tree has a higher certainty in selecting the communication protocol, corresponding to a more stable and more suitable communication protocol selection. If the V2V communication protocol shows lower latency and packet loss rate in multiple driving scenarios, then the entropy value in the decision tree will be lower, indicating that it is a more reliable choice. At that time, the weight score is increased; when the calculated entropy value is a medium entropy value, it means that there is a certain uncertainty in the decision tree when selecting the communication protocol, indicating that there are multiple communication protocols that show similar performance in the current scenario. Therefore, the decision tree will further distinguish and select the most suitable communication protocol based on other factors such as network load and communication distance, and the weight score remains unchanged; if a high entropy value is calculated, it means that the decision tree faces greater uncertainty in selecting the communication protocol, indicating that there is no obvious optimal communication protocol in the current scenario, so the decision tree will tend to choose a more general communication protocol, or make decisions based on other more complex strategies to reduce the weight score.

[0108] Specifically, the entropy value range is defined as follows:

[0109] Lower entropy value: defined as the entropy value is less than or equal to a certain threshold T low In this embodiment, the entropy value ranges from 0 to 1, and T is set low =0.3, then entropy values ​​less than or equal to 0.3 are considered “low”;

[0110] Medium entropy: defined as entropy greater than T low and is less than or equal to another threshold T high In this embodiment, T high = 0.7, entropy values ​​between 0.3 and 0.7 are considered “medium”;

[0111] Higher entropy: defined as an entropy value greater than T high ,In this embodiment, an entropy value greater than 0.7 is considered “high”;

[0112] The adjustment strategy of weight α is:

[0113] When the entropy value is "low", increase the value of weight α to emphasize the importance of network performance parameters, and increase α by 0.1;

[0114] When the entropy value is "medium", keep the value of weight α unchanged;

[0115] When the entropy value is "high", reduce the value of weight α to emphasize the importance of the information entropy algorithm and reduce α by 0.1;

[0116] In the adaptive optimization of communication modes, the specific selection of optimization algorithms will vary depending on the selected optimization method and objective function. Assuming that the goal is to optimize the performance indicators of the communication mode such as throughput, delay or energy consumption, define an objective function f(x), where x is a vector containing communication mode parameters. The optimization problem can be expressed as finding a set of parameters x* that makes the objective function f(x) optimal (maximum or minimum). Here, the gradient descent method is used as the optimization algorithm, and its gradient parameter update formula is:

[0117]

[0118] In the formula, x k+1 is the parameter vector for the next iteration, x k is the parameter vector of the current iteration, α is the learning rate, a positive decimal used to control the step size of parameter update, is the objective function f(x) at x k The gradient descent method calculates the gradient of the objective function at the current parameter point and updates the parameters in the opposite direction of the gradient, thereby gradually approaching the optimal solution of the objective function.

[0119] Step S3: Data encryption and transmission:

[0120] Data encryption: Use AES and RSA to encrypt data to ensure data confidentiality and integrity;

[0121] Encryption key management: manage encryption keys to ensure key security and validity;

[0122] Data transfer: Transfer encrypted data to the target device via wireless network;

[0123] Transmission Control Protocol: Apply the transmission control protocol to ensure efficient data transmission;

[0124] Network stack configuration: configure the network stack to adapt to different network environments and transmission requirements;

[0125] Step S4: Traffic condition analysis:

[0126] Real-time traffic data collection: collect real-time traffic data, including traffic volume and speed;

[0127] Machine learning model training: Use machine learning models to train traffic data and provide optimal driving strategies;

[0128] Traffic condition prediction: predict future traffic changes based on real-time traffic data;

[0129] Strategy optimization: optimize driving strategies based on road condition prediction results;

[0130] Step S5: Path planning:

[0131] Real-time traffic information acquisition: Get real-time traffic information;

[0132] Route optimization: perform route planning and optimize driving routes based on real-time traffic conditions and driver preferences;

[0133] Route update: During driving, the driving route is updated according to real-time traffic conditions;

[0134] Route prompts: Provide drivers with prompts and navigation for the best driving route;

[0135] Step S6: Driving behavior analysis:

[0136] Driving behavior data collection: collecting the driver’s driving behavior data;

[0137] Behavioral analysis: Apply behavioral analysis techniques to analyze the driver’s behavior patterns;

[0138] Driving behavior model training: Use driving behavior models to train and evaluate driver behavior;

[0139] Driving advice generation: Based on the analysis results, driving advice is generated to improve driving safety;

[0140] Suggestion feedback: Provide driving suggestions to drivers and collect feedback to optimize the suggestions;

[0141] Step S7: Environmental perception:

[0142] Surrounding vehicle detection: Use sensors and target detection technology to monitor the location and speed of surrounding vehicles in real time;

[0143] Pedestrian and obstacle recognition: Use deep learning models and machine vision to identify pedestrians and obstacles on the road;

[0144] Weather condition monitoring: monitor and predict the impact of weather conditions on driving;

[0145] Environmental data fusion: Fusion of data on surrounding vehicles, pedestrians, obstacles, and weather conditions;

[0146] Environmental perception prompts: Provide environmental perception prompts and warning information to the driver;

[0147] Step S8: Driver health monitoring:

[0148] Physiological parameter collection: real-time monitoring of the driver's heart rate and blood pressure physiological parameters;

[0149] Fatigue status detection: Use fatigue detection and eye tracking technology to detect the driver's fatigue status;

[0150] Health data analysis: Use health data analysis models to analyze the driver’s health data;

[0151] Health advice generation: Based on the analysis results, health advice is generated to improve the driver's health management;

[0152] Health monitoring feedback: Provide health monitoring feedback and suggestions to drivers;

[0153] Step S9: Advanced Driving Assistance:

[0154] Emergency Braking: In an emergency, the emergency braking technology will automatically apply the brakes;

[0155] Lane Keeping Assist: Uses lane detection technology and steering software to help the vehicle stay within its lane.

[0156] Blind spot monitoring: Using blind spot monitoring and ultrasonic sensor data processing to monitor the vehicle's blind spot area and provide warnings;

[0157] Assisted driving decision: Comprehensive results of emergency braking, lane keeping and blind spot monitoring to make assisted driving decisions;

[0158] Assisted driving prompts: Provide the driver with assisted driving prompts and warning information;

[0159] Step S10: In-vehicle entertainment and information display:

[0160] Media playback control: Use the media player software to control the in-car entertainment system to play music and videos;

[0161] Information display: Display navigation information and real-time traffic conditions on the vehicle screen through information display software and graphical interface library;

[0162] Voice assistant: Use speech recognition technology and natural language processing models to realize voice control of vehicle systems;

[0163] User interface interaction: Provide user-friendly interface interaction design to enhance driving experience;

[0164] Entertainment information update: Regularly update the in-vehicle entertainment system and information display content;

[0165] Step S11: Communication mode adaptive optimization:

[0166] Network status monitoring: Apply network performance monitoring methods to monitor the status and performance of communication networks in real time;

[0167] Mode switching decision: Use a decision tree to decide whether to switch the communication mode based on the network status;

[0168] Communication mode optimization: Apply optimization algorithms and parameter tuning models to optimize the parameter settings of the communication mode;

[0169] Specifically, in the optimization of communication mode, the specific formula of the optimization algorithm will vary according to the selected optimization method and objective function. Assume that the goal is to optimize the performance index of the communication mode as throughput, delay or energy consumption, define an objective function f(x), where x is a vector containing communication mode parameters, and the optimization problem can be expressed as finding a set of parameters x* so that the objective function f(x) reaches the optimal (maximum or minimum). The gradient descent method is used as the optimization algorithm to update the parameter formula, see formula (5);

[0170]

[0171] In the formula, x k+1 is the parameter vector for the next iteration, x k is the parameter vector of the current iteration, α is the learning rate, a positive decimal used to control the step size of parameter update, is the objective function f(x) at x k The gradient descent method calculates the gradient of the objective function at the current parameter point and updates the parameters in the opposite direction of the gradient, thereby gradually approaching the optimal solution of the objective function.

[0172] Communication stability assessment: Regularly assess the stability of communication modes and make adjustments;

[0173] Improved transmission efficiency: Improves data transmission efficiency based on communication mode optimization results.

[0174] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vehicle networking communication mode selection system, characterized in that: It includes vehicle data acquisition module, vehicle communication management module, vehicle decision support module, environmental perception module, driver health monitoring module, advanced driving assistance module, vehicle entertainment information module, and adaptive communication mode selection module; The vehicle data acquisition module is used for sensor data collection, data preprocessing and data storage; The vehicle communication management module is used for communication protocol selection, data encryption and data transmission; The vehicle-mounted decision support module is used for real-time traffic condition analysis, route planning and driving behavior analysis; The environmental perception module is used for surrounding vehicle detection, pedestrian and obstacle detection and weather condition monitoring; The driver health monitoring module is used to monitor the driver's physiological parameters, fatigue detection and health data analysis; The advanced driver assistance module is used for automatic emergency braking, lane keeping and blind spot monitoring; The in-vehicle entertainment information module is used for media playback control, information display and voice assistant; The adaptive communication mode selection module is used for communication mode detection, mode switching decision and communication mode optimization.

2. The vehicle networking communication mode selection system according to claim 1, characterized in that: The vehicle data acquisition module also includes a sensor data collection unit, a data preprocessing unit and a data storage unit; The sensor data collection unit is used to collect data on the vehicle status and surrounding environment through sensors during vehicle driving, and realizes real-time data collection function through sensor interface driver software; The data preprocessing unit is used to filter and remove noise from the collected data, and improve the accuracy and reliability of the data through digital filtering algorithms and noise elimination software; The data storage unit is used to store the processed data in a local storage device for subsequent analysis and use through a database management system and a data compression algorithm.

3. The vehicle networking communication mode selection system according to claim 2, characterized in that: The vehicle communication management module also includes a communication protocol selection unit, a data encryption unit and a data transmission unit; The communication protocol selection unit is used to dynamically select V2V, V2I or V2C communication protocols in different scenarios, and realize communication adaptability through protocol selection algorithm and communication protocol stack; The data encryption unit is used to ensure data security during data transmission, and to ensure data confidentiality and integrity through AES and RSA encryption algorithms; The data transmission unit is used to transmit the encrypted data to the target device via a wireless network, and ensures efficient data transmission through a transmission control protocol and a network stack software.

4. The vehicle networking communication mode selection system according to claim 3, characterized in that: The vehicle-mounted decision support module also includes a real-time traffic status analysis unit, a path planning unit and a driving behavior analysis unit; The real-time traffic condition analysis unit is used to analyze the current road conditions according to the real-time traffic data and provide the optimal driving strategy through the traffic flow analysis algorithm and the machine learning model; The path planning unit is used to plan the optimal driving route according to the real-time road conditions, and reduce driving time and fuel consumption through the A* algorithm and the Dijkstra algorithm; The driving behavior analysis unit is used to analyze the driver's behavior pattern and provide driving suggestions, thereby improving driving safety through behavior analysis algorithms and driving behavior models.

5. The vehicle networking communication mode selection system according to claim 4, characterized in that: The environment perception module also includes a surrounding vehicle detection unit, a pedestrian and obstacle detection unit and a weather condition monitoring unit; The surrounding vehicle detection unit is used to monitor the position and speed of surrounding vehicles in real time, and ensure driving safety through target detection algorithms and computer vision models; The pedestrian and obstacle detection unit is used to identify pedestrians and obstacles on the road and prevent collision accidents through deep learning models and image recognition algorithms; The weather condition monitoring unit is used to monitor and predict the impact of weather conditions on driving, and ensure driving safety through meteorological data processing algorithms and weather forecast models.

6. The vehicle networking communication mode selection system according to claim 5, characterized in that: The driver health monitoring module also includes a physiological parameter monitoring unit, a fatigue detection unit and a health data analysis unit; The physiological parameter monitoring unit is used to monitor the driver's heart rate and blood pressure physiological parameters in real time, and prevent sudden health problems through physiological signal processing algorithms and sensor interfaces; The fatigue detection unit is used to detect the driver's fatigue state and provide warnings, and prevent fatigue driving through fatigue detection algorithms and eye tracking technology; The health data analysis unit is used to analyze the driver's health data and provide health advice, and improve the driver's health management through health data analysis models and machine learning algorithms.

7. The vehicle networking communication mode selection system according to claim 6, characterized in that: The advanced driver assistance module also includes an automatic emergency braking unit, a lane keeping assist unit, and a blind spot monitoring unit; The automatic emergency braking unit is used to automatically brake in an emergency situation and avoid collision through emergency braking algorithm and radar data processing; The lane keeping assist unit is used to assist the vehicle to stay in the lane and prevent the vehicle from deviating from the lane through lane detection algorithms and direction control software; The blind spot monitoring unit is used to monitor the blind spot area of ​​the vehicle and provide warnings, and avoid collisions when changing lanes through blind spot monitoring algorithms and ultrasonic sensor data processing.

8. The vehicle networking communication mode selection system according to claim 7, characterized in that: The in-vehicle entertainment information module also includes a media playback control unit, an information display unit and a voice assistant unit; The media player control unit is used to control the in-vehicle entertainment system to play music and videos, and improve the driving experience through the media player software and user interface control; The information display unit is used to display navigation information and real-time road conditions on the vehicle screen, and to assist driving decisions through information display software and a graphical interface library; The voice assistant unit is used to control the vehicle system through voice, and improve the operational convenience through voice recognition algorithm and natural language processing model.

9. The vehicle networking communication mode selection system according to claim 8, characterized in that: The adaptive communication mode selection module also includes a communication mode detection unit, a mode switching decision unit and a communication mode optimization unit; The communication mode detection unit is used to detect the status and performance of the current communication network, and monitor the network status in real time through a network performance monitoring algorithm and data analysis software; The mode switching decision unit is used to decide whether to switch the communication mode according to the detection result, and ensure communication stability through a decision tree algorithm and a dynamic switching strategy; The communication mode optimization unit is used to optimize the parameter settings of the communication mode and improve the transmission efficiency and communication performance by optimizing the algorithm and the parameter tuning model.

10. A working method of a vehicle networking communication mode selection system, according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Data collection: The vehicle collects data on the vehicle status and surrounding environment in real time through sensors. The collected data is pre-processed, including filtering and denoising, to ensure the accuracy and reliability of the data. The processed data is stored in the local storage device for subsequent analysis and use; S2. Communication protocol selection: According to different driving scenarios of vehicles, dynamically select communication protocols including V2V, V2I or V2C, calculate network performance parameters through multiple protocol selection algorithms, obtain selection tendencies of different communication protocols, and obtain a set of selection tendencies of different communication protocols through information entropy algorithm, and use weighted summation to combine the two selection tendencies to select the appropriate communication protocol; S3. Data encryption and transmission: During the data transmission process, the AES and RSA encryption algorithms are used to encrypt the data to ensure the confidentiality and integrity of the data. The encrypted data is transmitted to the target device via the wireless network to ensure efficient data transmission; S4. Traffic condition analysis: Based on real-time collected traffic data, analyze the current road conditions and use traffic flow analysis algorithms and machine learning models to provide the best driving strategy; S5. Path planning: Plan the optimal driving route based on real-time traffic conditions, and reduce driving time and fuel consumption through A* algorithm and Dijkstra algorithm; S6. Driving behavior analysis: Analyze the driver's behavior patterns, provide driving suggestions, and improve driving safety through behavior analysis algorithms and driving behavior models; S7. Environmental perception: Real-time monitoring of the position and speed of surrounding vehicles, identification of pedestrians and obstacles on the road, monitoring and predicting the impact of weather conditions on driving, and ensuring driving safety through target detection algorithms, deep learning models, and meteorological data processing algorithms; S8. Driver health monitoring: Real-time monitoring of the driver's heart rate and blood pressure physiological parameters, detection of the driver's fatigue state and provision of warnings, and improvement of the driver's health management through physiological signal processing algorithms, fatigue detection algorithms and health data analysis models, to prevent sudden health problems and fatigue driving; S9. Advanced driving assistance: Automatically brakes in emergency situations, assists the vehicle to stay in the lane, monitors the vehicle's blind spots and provides warnings, and avoids collisions and prevents the vehicle from leaving the lane through emergency braking algorithms, lane detection algorithms, and blind spot monitoring algorithms; S10. In-car entertainment and information display: Control the in-car entertainment system to play music and videos, display navigation information and real-time traffic conditions on the in-car screen, and improve driving experience and operating convenience through media player software, information display software and voice recognition algorithms; S11. Adaptive optimization of communication modes: Detect the status and performance of the current communication network, decide whether to switch the communication mode based on the detection results, monitor the network status in real time through network performance monitoring algorithms, decision tree algorithms and optimization algorithms, ensure the stability of communication and improve transmission efficiency.

Images