Internet of vehicles intelligent navigation system based on Internet of Things

Abstract

The invention relates to the technical field of Internet of Vehicles, and particularly discloses an Internet of Vehicles intelligent navigation system based on Internet of Things, comprising: a multi-source information acquisition module; a communication module; an intelligent safety protection module; an intelligent decision and optimization module; a user interaction and display module; a data storage and sharing module; a multi-source information acquisition module, a communication module, an intelligent security protection module, an intelligent decision and optimization module, a user interaction and display module and a data storage and sharing module cooperate with one another. The multi-source information acquisition module fuses multi-type sensor data of a laser radar, a millimeter wave radar and a camera and access road infrastructure sensor information to realize comprehensive and accurate perception of a vehicle surrounding environment and a road condition, and the communication module guarantees stable transmission of various sensor data. Therefore, the system can accurately judge the real-time traffic flow, the congestion condition, the obstacle position and other information of the road, and the accuracy and reliability of road condition judgment are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle networking, and in particular relates to a vehicle networking intelligent navigation system based on the Internet of Things. Background Art

[0002] The Internet of Vehicles Intelligent Navigation System is an automatic navigation tool that integrates the Global Positioning System (GPS), map data, sensor information and real-time traffic information. The system mainly relies on GPS satellite signals to obtain the real-time location of the vehicle, and collects data such as speed, direction, acceleration, etc. through sensors. These data are crucial to determine the current location and direction of travel of the vehicle; For example, the patent document application number is CN201810277680.X, which discloses an intelligent navigation system based on the Internet of Vehicles, including a communication module, an image acquisition module, a display screen, a navigation and positioning module, a host and a cloud server. The host includes an ARM processor, a DSP processor and a control circuit. The control circuit is connected to the DSP processor and the ARM processor respectively. The navigation and positioning module, the display screen and the communication module are connected to the ARM processor respectively. The ARM processor is communicated with the cloud server through the communication module. The invention obtains real-time traffic information through the Internet of Vehicles system, and cooperates with the camera of the vehicle to judge the current road conditions and their changes. The navigation module optimizes the navigation route in real time according to the information sent by the processor, which effectively improves the accuracy of navigation and reduces the probability of user congestion.

[0003] However, the above-mentioned intelligent navigation system only relies on the Internet of Vehicles system to obtain real-time traffic information, and the information source is relatively single. In complex traffic scenarios, such as some remote areas or newly opened roads, insufficient Internet of Vehicles coverage may lead to the inability to accurately obtain real-time traffic data, affecting the accuracy of navigation route optimization. Therefore, we need to propose an Internet of Vehicles-based intelligent navigation system to solve the above problems, so that it can comprehensively and accurately obtain vehicle surrounding environment information, make up for the shortcomings of a single camera's field of view and perception capabilities, and improve the accuracy of navigation route optimization. Summary of the invention

[0004] The purpose of the present invention is to provide an Internet of Vehicles intelligent navigation system based on the Internet of Things, which can comprehensively and accurately obtain the vehicle's surrounding environment information, make up for the shortcomings of the field of view and perception ability of a single camera, improve the accuracy of navigation route optimization, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An Internet of Things-based vehicle networking intelligent navigation system includes: a multi-source information acquisition module, which integrates multiple sensors with road infrastructure sensors to collect vehicle surrounding environment information; A communication module, which automatically switches the communication protocol according to different driving areas to ensure the stability of communication; An intelligent security protection module, which monitors network traffic in real time, identifies abnormal traffic and attack behaviors, takes defensive measures when there is an intrusion or attack, and encrypts the data to be transmitted when there is no intrusion or attack. The communication module is electrically connected to the multi-source information acquisition module and the intelligent security protection module respectively; Intelligent decision-making and optimization module, which uses big data analysis and artificial intelligence algorithms to collect and analyze massive amounts of traffic data securely transmitted from multi-source information acquisition modules, and formulates the optimal navigation route based on multiple factors such as real-time traffic flow, road conditions, weather and emergencies; A user interaction and display module, which combines navigation information with actual road scenes by combining AR navigation display and voice interaction, so that the driver can complete interactive operations through voice commands, and the intelligent decision-making and optimization module is electrically connected to the intelligent safety protection module and the user interaction and display module respectively; A data storage and sharing module stores massive real-time and historical data of vehicles and road infrastructure through a cloud server, and then shares and collaborates data between the cloud server and a third-party service platform. The data storage and sharing module is electrically connected to a multi-source information acquisition module, a communication module, an intelligent safety protection module, an intelligent decision-making and optimization module, and a user interaction and display module.

[0006] Preferably, the multi-source information acquisition module includes a laser radar and a millimeter-wave radar, and the laser radar and the millimeter-wave radar are integrated with a camera located on the vehicle to perceive the road conditions from different dimensions and complement each other.

[0007] Preferably, the process of fusing the laser radar and millimeter wave radar with the camera located on the vehicle is as follows: A1. Collect information about the vehicle's surrounding environment from different dimensions through cameras, lidar and millimeter-wave radar; A2. Use the clock synchronization circuit to synchronize the camera, LiDAR, and millimeter-wave radar to ensure that the camera, LiDAR, and millimeter-wave radar are aligned in time. A3. Preprocess the collected vehicle surrounding environment information by category and extract features of the preprocessed data; A4. Build a neural network model, use the features extracted by lidar, millimeter-wave radar and camera as the input of the model, learn the intrinsic relationship between different features through training model, and output the fused feature representation.

[0008] Preferably, the road infrastructure sensors include geomagnetic sensors and traffic flow monitoring sensors. When integrated with lidar and millimeter-wave radar, the Internet of Things technology is used to enable the geomagnetic sensors and traffic flow monitoring sensors to communicate with the lidar and millimeter-wave radar to obtain traffic flow, road congestion conditions and road construction information in a wider area.

[0009] Preferably, the communication module includes a multi-communication protocol fusion unit and a low-power wide area network technology auxiliary unit, the multi-communication protocol fusion unit is electrically connected to the low-power wide area network technology auxiliary unit, the communication protocol fusion unit monitors the signal strength and quality parameters of different communication links of 4G, 5G and satellite communications in real time, and selects the optimal communication protocol according to the signal strength and quality monitoring results combined with a preset switching strategy, the low-power wide area network technology auxiliary unit integrates the auxiliary module supporting low-power wide area network technology into the vehicle intelligent navigation system, and configures and initializes it.

[0010] Preferably, the intelligent security protection module includes an intrusion detection and defense unit and an encryption communication and authentication unit electrically connected to the intrusion detection and defense unit, the intrusion detection and defense unit is electrically connected to the multi-source information acquisition unit, and the encryption communication and authentication unit is electrically connected to the intelligent decision-making and optimization module.

[0011] Preferably, the process of intrusion detection and defense performed by the intrusion detection and defense unit is as follows: B1. Collect network traffic data in the Internet of Vehicles system through the network interface. The network traffic data includes the source address, destination address, port number and protocol type of the data packet; B2. Perform feature extraction on the collected traffic data through statistical analysis methods to extract features related to normal and abnormal behaviors; B3. Establish an intrusion detection model and use the characteristic data of historical normal traffic to train the intrusion detection model. At the same time, the intrusion detection model needs to be updated every day to adapt to new network attacks and changes in the Internet of Vehicles system. The formula of the intrusion detection model is: ,in, Output results for intrusion detection. is the ReLU or Sigmoid activation function, is the input feature, is the weight value of the input feature, is the bias term of the input feature, is the total number of input features; B4. Input the collected traffic data into the trained intrusion detection model in real time for detection. When abnormal traffic is detected, take corresponding defense measures according to the defense strategy to prevent hacker intrusion and malware attacks. When no abnormal traffic is detected, the data is transmitted to the encryption communication and authentication unit for encrypted transmission and authentication.

[0012] Preferably, the process of processing massive traffic data by big data analysis and artificial intelligence algorithms is as follows: C1. Receive traffic data collected by the multi-source information collection module, clean, denoise and normalize the data, and divide the processed data into training set, validation set and test set; C2. Build an LSTM network model and determine the structural parameters of the number of network layers and hidden units; C3, initialize the weight matrix and bias term in the network, input the training set data into the LSTM network model according to the time step, and calculate the predicted value through forward propagation; C4. Use the loss function to calculate the error between the predicted value and the true value, adjust the weight matrix and bias term through the back propagation algorithm, and continuously iterate the training model until the LSTM network model achieves the optimal performance on the validation set; C5. Use the test set data to evaluate the trained LSTM network model; C6. Pre-process the real-time collected traffic data and input it into the trained LSTM network model to predict the traffic conditions at different time periods and different road sections in the future.

[0013] Preferably, the process of the intelligent decision-making and optimization module formulating the optimal navigation route is as follows: D1. According to the influence of different factors on navigation route planning, the weights of real-time traffic flow, road conditions, weather and emergency factors are determined by using the analytic hierarchy process; D2. Quantitatively evaluate real-time traffic flow and road condition factors; D3. Based on the quantified factors and weights, the Dijkstra algorithm is used in combination with traffic condition prediction results to search for the optimal navigation route in the map data. When encountering road construction or emergencies, the traffic information is updated in a timely manner and the weights are recalculated to quickly adjust the navigation route.

[0014] Preferably, the AR navigation display superimposes navigation information such as turning arrows and distance prompts on the real-time image captured by the camera, so that the driver can obtain navigation guidance more intuitively.

[0015] The vehicle networking intelligent navigation system based on the Internet of Things proposed by the present invention has the following advantages compared with the prior art: 1. The present invention realizes comprehensive and accurate perception of the vehicle's surrounding environment and road conditions through the coordinated cooperation of a multi-source information acquisition module, a communication module, an intelligent safety protection module, an intelligent decision-making and optimization module, a user interaction and display module, and a data storage and sharing module. The multi-source information acquisition module integrates laser radar, millimeter-wave radar, camera multi-type sensor data and access road infrastructure sensor information to achieve comprehensive and accurate perception of the vehicle's surrounding environment and road conditions. The communication module ensures the stable transmission of various sensor data and provides a basis for subsequent processing, so that the system can accurately judge the real-time traffic flow, congestion conditions, obstacle locations and other information of the road, overcomes the limitations of a single sensor or information source, and improves the accuracy and reliability of road condition judgment.

[0016] 2. The intelligent decision-making and optimization module of the present invention uses big data analysis and artificial intelligence algorithms to collect and analyze massive amounts of traffic data safely transmitted from the multi-source information acquisition module, and formulates the optimal navigation route based on multiple factors such as real-time traffic flow, road conditions, weather and emergencies, so that the system can quickly respond to changes in road conditions and update navigation information in a timely manner. This effectively reduces the probability of users encountering congestion and improves travel efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A system block diagram according to an embodiment of the present invention is shown; Figure 2 A flowchart of fusing a laser radar and a millimeter-wave radar with a camera located on a vehicle according to an embodiment of the present invention is shown; Figure 3 A flowchart of intrusion detection and defense performed by an intrusion detection and defense unit according to an embodiment of the present invention is shown; Figure 4 A flowchart of processing massive traffic data using big data analysis and artificial intelligence algorithms according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the accompanying 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, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] The present invention provides Figure 1-4The shown is an Internet of Things-based vehicle networking intelligent navigation system, comprising a multi-source information acquisition module, a communication module, an intelligent safety protection module, an intelligent decision-making and optimization module, a user interaction and display module, and a data storage and sharing module. The communication module is electrically connected to the multi-source information acquisition module and the intelligent safety protection module, respectively, the intelligent decision-making and optimization module is electrically connected to the intelligent safety protection module and the user interaction and display module, respectively, and the data storage and sharing module is electrically connected to the multi-source information acquisition module, the communication module, the intelligent safety protection module, the intelligent decision-making and optimization module, and the user interaction and display module, respectively.

[0020] The multi-source information acquisition module integrates multiple sensors with road infrastructure sensors to collect vehicle surrounding environment information, including the speed, distance change and outline of objects. It can not only obtain detailed environmental information around the vehicle at a close distance, but also obtain information on traffic flow and road conditions in a wider area, providing a more comprehensive and accurate data basis for navigation; The multi-source information acquisition module includes laser radar and millimeter-wave radar, which are integrated with the camera located on the vehicle to perceive the road conditions from different dimensions and complement each other. The laser radar and millimeter-wave radar can obtain long-distance and high-precision object information, and combined with the visual information of the camera, they can judge the road conditions and their changes more comprehensively and accurately, avoiding the problem of limited field of view and inaccurate judgment relying solely on the vehicle's camera.

[0021] The process of fusing LiDAR and mmWave radar with the camera on the vehicle is as follows: A1. Collect information about the vehicle's surrounding environment from different dimensions through cameras, lidar and millimeter-wave radar. Specifically, cameras collect visual image data around the vehicle; lidar emits laser beams and receives reflected light, obtains the distance and contour information of the target object by measuring the flight time of light, and generates point cloud data; millimeter-wave radar emits millimeter-wave signals, uses the Doppler effect to measure the speed and distance changes of the target object, and generates radar echo data; A2. The camera, lidar and millimeter-wave radar are synchronized through the clock synchronization circuit to ensure that the camera, lidar and millimeter-wave radar are aligned in time. The hardware clock synchronization circuit uses a high-precision clock source, such as a crystal oscillator or an atomic clock, to generate a stable clock signal. The camera, lidar and millimeter-wave radar obtain a unified time reference by connecting to the clock source, and use a phase-locked loop (PLL) circuit to lock the clock signal, compensate for signal transmission delay, and ensure that the data of each sensor is aligned in time for subsequent fusion processing. A3. Preprocess the collected vehicle surrounding environment information by category and extract the features of the preprocessed data. Specifically, perform denoising and enhancement preprocessing operations on the camera image to improve the image quality, and then use the scale-invariant feature transformation algorithm to extract image features; filter the laser radar point cloud data to remove noise points, and then extract geometric features from the point cloud data. The geometric features include the shape, size and surface normal vector of the target object; demodulate and detect the millimeter wave radar echo data to extract the characteristic information of the target object, such as speed, acceleration and angle change rate; A4. Build a neural network model, use the features extracted by lidar, millimeter-wave radar and camera as the input of the model, learn the intrinsic relationship between different features through training model, and output the fused feature representation. During the training process, use a large amount of labeled sample data and adjust the model parameters through the back propagation algorithm so that the model can accurately fuse the features of different sensors.

[0022] Road infrastructure sensors include geomagnetic sensors and traffic flow monitoring sensors. When integrated with lidar and millimeter-wave radar, the Internet of Things technology is used to enable geomagnetic sensors and traffic flow monitoring sensors to communicate with lidar and millimeter-wave radar to obtain traffic flow, road congestion and road construction information in a wider area, provide more comprehensive real-time road condition data for navigation, and solve the problem of limitations in information acquisition.

[0023] The communication module automatically switches the communication protocol according to different driving areas to ensure the stability of communication. For example, 5G communication is used in areas with good signals to ensure adjusted and stable data transmission. In remote areas or underground parking lots with weak signals, satellite communication is automatically switched to ensure uninterrupted communication with the cloud server. The communication module includes a multi-communication protocol fusion unit and a low-power wide area network technology auxiliary unit. The multi-communication protocol fusion unit is electrically connected to the low-power wide area network technology auxiliary unit. The communication protocol fusion unit monitors the signal strength and quality parameters of different communication links of 4G, 5G and satellite communications in real time, and selects the optimal communication protocol based on the signal strength and quality monitoring results combined with a preset switching strategy. When switching the communication protocol, a new communication link connection is first established to ensure the continuity of data transmission, and then the data being transmitted is seamlessly switched to the new communication link, while releasing the original communication link resources.

[0024] The signal strength evaluation method of the communication link is to use the signal strength calculation formula to calculate the signal strength, and select the communication link with the largest strength. The signal strength calculation formula is: , , in, is the signal strength of the communication link, is the transmission power, is the receiving sensitivity, L is the path loss, is the propagation distance in km, is the propagation frequency, in MHz; The preset switching strategy is to decide whether to switch by comparing the utility values ​​of different communication protocols. The effect value calculation formula is: ,in, is the utility value of the communication protocol, is the signal strength of the communication protocol, is the signal-to-noise ratio of the communication protocol, is the bandwidth of the communication protocol, , and are the weight coefficients of signal strength, signal-to-noise ratio and bandwidth respectively; The low-power wide area network technology auxiliary unit integrates an auxiliary module supporting low-power wide area network technology (i.e., LPWAN) into the vehicle intelligent navigation system, and performs configuration and initialization, sets parameters of communication frequency, power, and encoding method, and then encapsulates non-real-time data transmitted through the low-power wide area network technology, and then packages it according to the format specified by the LPWAN protocol, and then transmits the packaged data to the data storage and sharing module through the LPWAN network. After receiving the LPWAN data, the data storage and sharing module decapsulates it, extracts the original data, and forwards it to the vehicle intelligent system for processing and storage.

[0025] Through the fusion of multiple communication protocols in the communication module and the assistance of LPWAN technology, stable communication can be ensured in various complex environments. High-speed 5G communication is used in areas with good signals, and satellite communication or LPWAN technology is switched in areas with weak signals. This solves the problem of unstable communication in the original system and ensures that the data transmission between the host and the cloud server is real-time and reliable, providing a guarantee for the navigation system to obtain information and adjust the route in real time.

[0026] The intelligent security protection module monitors network traffic in real time, identifies abnormal traffic and attack behaviors, takes defensive measures when there is intrusion or attack behaviors, and encrypts the data to be transmitted when there is no intrusion or attack. The intelligent security protection module includes an intrusion detection and defense unit and an encryption communication and authentication unit electrically connected to the intrusion detection and defense unit. The intrusion detection and defense unit is electrically connected to the multi-source information acquisition unit, and the encryption communication and authentication unit is electrically connected to the intelligent decision-making and optimization module; The process of intrusion detection and defense by the intrusion detection and defense unit is as follows: B1. Collect network traffic data in the Internet of Vehicles system through the network interface. The network traffic data includes the source address, destination address, port number and protocol type of the data packet; B2. Perform feature extraction on the collected traffic data through statistical analysis methods to extract features related to normal and abnormal behaviors; B3. Establish an intrusion detection model and use the characteristic data of historical normal traffic to train the intrusion detection model. At the same time, the intrusion detection model needs to be updated every day to adapt to new network attacks and changes in the Internet of Vehicles system. The formula of the intrusion detection model is: ,in, Output results for intrusion detection. is the ReLU or Sigmoid activation function, is the input feature, is the weight value of the input feature, is the bias term of the input feature, is the total number of input features; B4. Input the collected traffic data into the trained intrusion detection model in real time for detection. When abnormal traffic is detected, take corresponding defense measures according to the defense strategy to prevent hacker intrusion and malware attacks. The defense measures include blocking connections, sending alarms, and isolating infected areas. When no abnormal traffic is detected, the data is transmitted to the encrypted communication and authentication unit for encrypted transmission and authentication.

[0027] The encryption communication and authentication unit uses a public key encryption algorithm to generate a public key and a private key pair for communication between the vehicle and the cloud server. Before data transmission, the sender uses the public key of the receiver to encrypt the data and sends the encrypted data over the communication network. When the device is connected to the Internet of Vehicles system, the digital certificate and username / password authentication method are used for identity authentication. After receiving the encrypted data, the receiver uses its own private key to decrypt it. At the same time, the integrity of the data is verified through a message authentication code or a hash algorithm to ensure that the data has not been tampered with during transmission. Through the intrusion detection and defense system of the intelligent security protection module and the encrypted communication and authentication mechanism, system security is guaranteed from multiple levels, network traffic is monitored in real time, hacker attacks are promptly discovered and blocked, encrypted communication prevents data from being stolen or tampered with, and the device authentication mechanism ensures that only legitimate devices are connected, effectively solving the security risks faced by the original system and ensuring the accuracy of navigation information and vehicle driving safety.

[0028] The intelligent decision-making and optimization module uses big data analysis and artificial intelligence algorithms to collect and analyze massive amounts of traffic data securely transmitted from the multi-source information acquisition module, and formulates the optimal navigation route based on multiple factors such as real-time traffic flow, road conditions, weather and emergencies, so that the system can quickly respond to changes in road conditions and update navigation information in a timely manner. This effectively reduces the probability of users encountering congestion and improves travel efficiency; The process of big data analysis and artificial intelligence algorithm processing massive traffic data is as follows: C1. Receive traffic data collected by the multi-source information collection module, clean, denoise and normalize the data, and divide the processed data into training set, validation set and test set; C2. Build an LSTM network model and determine the structural parameters of the number of network layers and hidden units; The LSTM network model includes input gate, forget gate, output gate and memory unit update, where the formula of input gate is: ,in, is the input gate value at time t, which controls the degree to which the current input information enters the memory unit. To map the input value to between 0 and 1, a Sigmoid function is used to control the degree of door opening. is the weight matrix input to the input gate, which is used to adjust the current input To weight, is the input data at time t, is the bias term of the input gate, Hide the state for the last moment to the weight matrix of the input gate, is the hidden state at time t-1, carrying the information of time step t, It is the bias term from the hidden state to the input gate at the previous moment; The formula of the forget gate is: ,in, is the forget gate value at time t, which controls the degree of information retained in the memory unit at the previous moment. is the weight matrix input to the forget gate, is the bias term of the forget gate, Hide the state for the last moment To the weight matrix of the forget gate, It is the bias term from the hidden state of the previous moment to the forget gate; The formula of the output gate is: ,in, is the output gate value at time t, which controls the degree to which the memory unit outputs to the hidden state. is the weight matrix input to the output gate, is the bias term of the output gate, is the hidden state at time t-1 The weight matrix to the output gate, is the bias term from the hidden state to the output gate at time t-1 The formula for updating the memory unit is: ,in, is the state of the memory unit after being updated at time t, which retains the long-term time series information. is an element-by-element multiplication operation, is the state of the memory unit at time t-1, is the weight matrix input to the memory unit, is the bias term input to the memory unit, is the weight matrix from the hidden state to the memory unit at time t-1, is the bias term from the hidden state to the memory unit at time t-1; C3, initialize the weight matrix and bias term in the network, input the training set data into the LSTM network model according to the time step, and calculate the predicted value through forward propagation; C4. Use the loss function to calculate the error between the predicted value and the true value, adjust the weight matrix and bias term through the back propagation algorithm, and continuously iterate the training model until the LSTM network model achieves the optimal performance on the validation set; C5. Use the test set data to evaluate the trained LSTM network model. The accuracy of the LSTM network model in predicting traffic conditions can be evaluated by calculating the accuracy and mean square error. C6. Pre-process the real-time collected traffic data and input it into the trained LSTM network model to predict the traffic conditions at different time periods and road sections in the future, confirm the probability of traffic congestion and vehicle speed changes, etc.

[0029] The process of the intelligent decision-making and optimization module to formulate the optimal navigation route is as follows: D1. According to the influence of different factors on navigation route planning, the weight of real-time traffic flow, road conditions, weather and emergency factors is determined by using the analytic hierarchy process. For example, when traffic congestion is serious, the weight of real-time traffic flow factor is high, and under bad weather conditions, the weight of weather factor is increased; D2. Quantitatively evaluate the real-time traffic flow and road condition factors. The real-time traffic flow is converted into a congestion index through traffic flow monitoring data. The road condition is classified and scored according to road construction and accident information. The weather condition is quantified according to the degree of impact on vehicles based on different weather types, including sunny, rainy and snowy days. D3. Based on the quantified factors and weights, the Dijkstra algorithm is used in combination with traffic condition prediction results to search for the optimal navigation route in the map data. When encountering road construction or emergencies, the traffic information is updated in a timely manner and the weights are recalculated to quickly adjust the navigation route.

[0030] The big data analysis and artificial intelligence algorithms of the intelligent decision-making and optimization module, as well as the multi-factor comprehensive decision-making method, have improved the accuracy and rationality of navigation route planning. By analyzing massive data to predict road conditions and formulating navigation routes based on comprehensive consideration of a variety of complex factors, the limitations of the original navigation optimization algorithm have been avoided, and it can provide users with better navigation routes and reduce the probability of users encountering congestion.

[0031] The user interaction and display module combines navigation information with actual road scenes by combining AR navigation display and voice interaction, so that the driver can complete interactive operations through voice commands; wherein, the AR navigation display superimposes navigation information such as turn arrows and distance prompts on the real-time picture taken by the camera, so that the driver can obtain navigation guidance more intuitively, reduce erroneous operations caused by the difficulty in understanding traditional two-dimensional navigation maps, and improve user experience; The AR navigation display and voice interaction of the user interaction and display module work together to improve the user's interactive experience with the navigation system. AR navigation makes navigation information more intuitive and voice interaction more natural and accurate, solving the problems of unclear voice prompts and complex operations in the original system, making it easier for drivers to operate and obtain navigation information, and improving driving safety and comfort.

[0032] The data storage and sharing module stores massive real-time and historical data of vehicles and road infrastructure through cloud servers, and then shares and collaborates data between the cloud servers and third-party service platforms, so as to obtain more surrounding service information. The data sharing and collaboration functions of the cloud servers are utilized to enrich the functions and service contents of the navigation system. By cooperating with other traffic management systems and third-party service platforms, more surrounding service information is provided to users, thereby improving the practicality and value of the navigation system and enabling the navigation system to be better integrated into the entire intelligent transportation ecosystem.

[0033] Through the coordinated cooperation of multi-source information acquisition module, communication module, intelligent safety protection module, intelligent decision-making and optimization module, user interaction and display module, and data storage and sharing module, the multi-source information acquisition module integrates multi-type sensor data such as lidar, millimeter-wave radar, and camera, as well as sensor information accessed from road infrastructure, to achieve comprehensive and accurate perception of the vehicle's surrounding environment and road conditions. The communication module ensures the stable transmission of various sensor data, providing a basis for subsequent processing, enabling the system to accurately judge the road's real-time traffic flow, congestion conditions, obstacle locations and other information, overcoming the limitations of a single sensor or information source and improving the accuracy and reliability of road condition judgment.

[0034] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An Internet of Things-based vehicle networking intelligent navigation system, characterized by: include: A multi-source information acquisition module, which integrates multiple sensors with road infrastructure sensors to collect vehicle surrounding environment information; A communication module, which automatically switches the communication protocol according to different driving areas to ensure the stability of communication; An intelligent security protection module, which monitors network traffic in real time, identifies abnormal traffic and attack behaviors, takes defensive measures when there is an intrusion or attack, and encrypts the data to be transmitted when there is no intrusion or attack. The communication module is electrically connected to the multi-source information acquisition module and the intelligent security protection module respectively; Intelligent decision-making and optimization module, which uses big data analysis and artificial intelligence algorithms to collect and analyze massive amounts of traffic data securely transmitted from multi-source information acquisition modules, and formulates the optimal navigation route based on multiple factors such as real-time traffic flow, road conditions, weather and emergencies; A user interaction and display module, which combines navigation information with actual road scenes by combining AR navigation display and voice interaction, so that the driver can complete interactive operations through voice commands, and the intelligent decision-making and optimization module is electrically connected to the intelligent safety protection module and the user interaction and display module respectively; A data storage and sharing module stores massive real-time and historical data of vehicles and road infrastructure through a cloud server, and then shares and collaborates data between the cloud server and a third-party service platform. The data storage and sharing module is electrically connected to a multi-source information acquisition module, a communication module, an intelligent safety protection module, an intelligent decision-making and optimization module, and a user interaction and display module.

2. The vehicle network intelligent navigation system based on the Internet of Things according to claim 1, characterized in that: The multi-source information acquisition module includes a laser radar and a millimeter-wave radar, which are integrated with a camera located on the vehicle to perceive road conditions from different dimensions and complement each other.

3. The vehicle network intelligent navigation system based on the Internet of Things according to claim 2, characterized in that: The process of fusing LiDAR and mmWave radar with the camera on the vehicle is as follows: A1. Collect information about the vehicle's surrounding environment from different dimensions through cameras, lidar and millimeter-wave radar; A2. Use the clock synchronization circuit to synchronize the camera, LiDAR, and millimeter-wave radar to ensure that the camera, LiDAR, and millimeter-wave radar are aligned in time. A3. Preprocess the collected vehicle surrounding environment information by category and extract features of the preprocessed data; A4. Build a neural network model, use the features extracted by lidar, millimeter-wave radar and camera as the input of the model, learn the intrinsic relationship between different features through training model, and output the fused feature representation.

4. The vehicle network intelligent navigation system based on the Internet of Things according to claim 3 is characterized by: The road infrastructure sensors include geomagnetic sensors and traffic flow monitoring sensors. When integrated with lidar and millimeter-wave radar, the Internet of Things technology is used to enable the geomagnetic sensors and traffic flow monitoring sensors to communicate with the lidar and millimeter-wave radar to obtain traffic flow, road congestion conditions and road construction information in a wider area.

5. The vehicle network intelligent navigation system based on the Internet of Things according to claim 1, characterized in that: The communication module includes a multi-communication protocol fusion unit and a low-power wide area network technology auxiliary unit. The multi-communication protocol fusion unit is electrically connected to the low-power wide area network technology auxiliary unit. The communication protocol fusion unit monitors the signal strength and quality parameters of different communication links of 4G, 5G and satellite communications in real time, and selects the optimal communication protocol based on the signal strength and quality monitoring results combined with a preset switching strategy. The low-power wide area network technology auxiliary unit integrates the auxiliary module supporting low-power wide area network technology into the vehicle intelligent navigation system, and configures and initializes it.

6. The vehicle network intelligent navigation system based on the Internet of Things according to claim 5, characterized in that: The intelligent security protection module includes an intrusion detection and defense unit and an encryption communication and authentication unit electrically connected to the intrusion detection and defense unit, the intrusion detection and defense unit is electrically connected to a multi-source information acquisition unit, and the encryption communication and authentication unit is electrically connected to an intelligent decision-making and optimization module.

7. The vehicle network intelligent navigation system based on the Internet of Things according to claim 6 is characterized by: The process of intrusion detection and defense by the intrusion detection and defense unit is as follows: B1. Collect network traffic data in the Internet of Vehicles system through the network interface. The network traffic data includes the source address, destination address, port number and protocol type of the data packet; B2. Perform feature extraction on the collected traffic data through statistical analysis methods to extract features related to normal and abnormal behaviors; B3. Establish an intrusion detection model and use the characteristic data of historical normal traffic to train the intrusion detection model. At the same time, the intrusion detection model needs to be updated every day to adapt to new network attacks and changes in the Internet of Vehicles system. The formula of the intrusion detection model is: ,in, Output results for intrusion detection. is the ReLU or Sigmoid activation function, is the input feature, is the weight value of the input feature, is the bias term of the input feature, is the total number of input features; B4. Input the collected traffic data into the trained intrusion detection model in real time for detection. When abnormal traffic is detected, take corresponding defense measures according to the defense strategy to prevent hacker intrusion and malware attacks. When no abnormal traffic is detected, the data is transmitted to the encryption communication and authentication unit for encrypted transmission and authentication.

8. The vehicle network intelligent navigation system based on the Internet of Things according to claim 7, characterized in that: The process of big data analysis and artificial intelligence algorithm processing massive traffic data is as follows: C1. Receive traffic data collected by the multi-source information collection module, clean, denoise and normalize the data, and divide the processed data into training set, validation set and test set; C2. Build an LSTM network model and determine the structural parameters of the number of network layers and hidden units; C3, initialize the weight matrix and bias term in the network, input the training set data into the LSTM network model according to the time step, and calculate the predicted value through forward propagation; C4. Use the loss function to calculate the error between the predicted value and the true value, adjust the weight matrix and bias term through the back propagation algorithm, and continuously iterate the training model until the LSTM network model achieves the optimal performance on the validation set; C5. Use the test set data to evaluate the trained LSTM network model; C6. Pre-process the real-time collected traffic data and input it into the trained LSTM network model to predict the traffic conditions at different time periods and different road sections in the future.

9. The vehicle network intelligent navigation system based on the Internet of Things according to claim 8, characterized in that: The process of the intelligent decision-making and optimization module to formulate the optimal navigation route is as follows: D1. According to the influence of different factors on navigation route planning, the weights of real-time traffic flow, road conditions, weather and emergency factors are determined by using the analytic hierarchy process; D2. Quantitatively evaluate real-time traffic flow and road condition factors; D3. Based on the quantified factors and weights, the Dijkstra algorithm is used in combination with traffic condition prediction results to search for the optimal navigation route in the map data. When encountering road construction or emergencies, the traffic information is updated in a timely manner and the weights are recalculated to quickly adjust the navigation route.

10. The vehicle network intelligent navigation system based on the Internet of Things according to claim 9, characterized in that: The AR navigation display superimposes navigation information such as turn arrows and distance prompts on the real-time image captured by the camera, allowing the driver to obtain navigation guidance more intuitively.

Images