A method and system for encrypting and protecting automobile EDR data

Abstract

The present invention discloses an automobile EDR data encryption protection method and system, which specifically relate to the field of automobile electronic technology. By real-time capture, preprocessing and feature extraction of electromagnetic signals in various driving scenarios, a signal feature library is constructed, and risk assessment and scene division are performed based on the library. Corresponding protection measures can be taken for driving scenarios with different risk levels, especially in high-risk scenarios. Through risk analysis and prediction within a fixed time period, high-intensity protection strategies can be formulated and implemented. This method can not only effectively prevent electromagnetic signal leakage and ensure the data security of the EDR system, but also improve the overall safety and reliability of the system and enhance the integrity and accuracy of accident data.

Description

Technical Field

[0001] The present invention relates to the field of automotive electronic technology, and in particular to an automotive EDR data encryption protection method and system. Background Art

[0002] Automobile EDR data encryption protection refers to the encryption of vehicle status data collected by the automobile event data recorder (EDR) to ensure the security of these data during transmission and storage. Through encryption protection, unauthorized access and tampering can be prevented, thereby protecting the integrity and confidentiality of the data and ensuring the authenticity and reliability of the data during accident analysis and responsibility determination.

[0003] Specifically, the data encryption protection method uses a combination of symmetric encryption and asymmetric encryption technology to encrypt the key data collected by EDR. Symmetric encryption algorithms (such as AES) are used to encrypt actual data, while asymmetric encryption algorithms (such as RSA) are used to encrypt symmetric encryption keys. This dual encryption mechanism ensures that even if the data is intercepted during transmission or storage, unauthorized users cannot decrypt and read the data, thereby effectively improving data security.

[0004] The shortcomings of the prior art:

[0005] In the prior art, the key data collected by EDR is encrypted by combining symmetric encryption and asymmetric encryption technologies. However, attackers may use highly sensitive equipment to capture the electromagnetic signals generated by the EDR system during the encryption and decryption process. By analyzing the captured electromagnetic signals, attackers can recover the encryption keys of users in different driving scenarios and then decrypt the data. Once the electromagnetic signal leak occurs, the data security in the EDR system will be seriously threatened. Summary of the invention

[0006] The purpose of the present invention is to provide an automobile EDR data encryption protection method and system to address the deficiencies in the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for encrypting and protecting automobile EDR data, comprising the following steps:

[0008] S1: Divide several driving scenarios according to the driving conditions and operating status of the vehicle, and use high-sensitivity electromagnetic signal receiving equipment to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time;

[0009] S2: pre-process the captured electromagnetic signal data, extract characteristic parameters related to the encryption process, and build a signal feature library;

[0010] S3: Based on the signal feature library, the signal features and strength of the captured electromagnetic signal data are identified and analyzed to assess the risk level of electromagnetic signal leakage in various driving scenarios;

[0011] S4: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios;

[0012] S5: Based on the classification results, take corresponding protective measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system;

[0013] S6: For high-risk driving scenarios, analyze the risk of electromagnetic signal leakage within a fixed time period, and make advance predictions of electromagnetic signal leakage risk events that may occur in subsequent fixed time periods. Based on the prediction results, formulate and implement high-intensity protective measures.

[0014] In a preferred embodiment, the signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed, the risk level of electromagnetic signal leakage in each driving scenario is evaluated, and the signal characteristic prominence is generated according to the signal characteristics of the captured electromagnetic signal data. The method for obtaining the signal characteristic prominence is:

[0015] The captured electromagnetic signal data matrix is ​​represented as X, where each row represents a sample and each column represents a feature. The electromagnetic signal data in the matrix is ​​standardized, and the mean vector and standard deviation vector of the electromagnetic signal data features in the matrix are calculated respectively; the standardized data matrix is ​​calculated The covariance matrix C of , where the calculation expression of the covariance matrix is: In the formula, n is the number of samples, The transpose of the standardized data matrix is ​​used to perform eigenvalue decomposition on the covariance matrix C to obtain the eigenvalue λ and eigenvector v, where the eigenvalue decomposition formula is: C*vi=λi*vi; where λi is the ith eigenvalue and vi is the ith eigenvector; the principal component is selected according to the size of the eigenvalue. The larger the eigenvalue, the more significant the feature represented by the corresponding eigenvector. The eigenvectors corresponding to the first k largest eigenvalues ​​of the eigenvalue λ are summed, and the summation result is used as the eigenvalue of the principal component, that is, the signal feature prominence, where k is a positive integer greater than 0.

[0016] In a preferred embodiment, the signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed, the risk level of electromagnetic signal leakage in various driving scenarios is evaluated, and the electromagnetic wave power fluctuation index is generated according to the captured signal strength. The method for obtaining the electromagnetic wave power fluctuation index is:

[0017] Extract the electromagnetic wave power time series data P(t) from the captured electromagnetic signal, where t represents time and P(t) represents the power value at time t. Preprocess the signal. For discrete time signals, use discrete Fourier transform to convert them into frequency domain. The calculation formula is: P(f) is the amplitude of the frequency domain signal at frequency f, N is the number of sampling points of the signal, e -j2πft / N is a complex exponential function;

[0018] Calculate the energy density of the electromagnetic wave power spectrum at each frequency in the time series. The calculation formula is: PSD(f) is the power spectral density at frequency f, (P(f)) 2 It is the square of the frequency domain signal amplitude; by analyzing the power spectrum density diagram, the root mean square value of the power spectrum density is calculated, that is, the electromagnetic wave power fluctuation index is calculated.

[0019] In a preferred embodiment, the signal feature prominence and the electromagnetic wave power fluctuation index are converted into a first eigenvector, and the first eigenvector is used as the input of a machine learning model. The machine learning model uses each group of first eigenvectors to predict the risk value label of electromagnetic signal leakage in each driving scenario as a prediction target, and uses minimizing the sum of prediction errors of the risk value labels of electromagnetic signal leakage in all driving scenarios as a training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The risk value of electromagnetic signal leakage in each driving scenario is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0020] In a preferred embodiment, the acquired risk value of electromagnetic signal leakage in each driving scenario is compared with a gradient risk threshold, the gradient risk threshold includes a first risk threshold and a second risk threshold, and the first risk threshold is less than the second risk threshold, and the risk value of electromagnetic signal leakage in each driving scenario is compared with the first risk threshold and the second risk threshold respectively;

[0021] If the risk value of electromagnetic signal leakage in each driving scenario is greater than a second risk threshold, the driving scenario is classified as a high-risk driving scenario;

[0022] If the risk value of electromagnetic signal leakage in each driving scenario is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, the driving scenario is classified as a medium-risk driving scenario;

[0023] If the risk value of electromagnetic signal leakage in each driving scenario is less than the first risk threshold, the driving scenario is classified as a low-risk driving scenario.

[0024] In a preferred embodiment, corresponding protective measures are taken for medium-risk driving scenarios and low-risk driving scenarios, specifically: the protective measures taken for medium-risk driving scenarios include: increasing electromagnetic shielding, Shielding Factori = α * Shielding Materialmid; wherein: Shielding Factori is a shielding factor used to describe the shielding effect, α is an adjustment coefficient, and ShieldingMaterialmid is a shielding material of medium strength; using an optimized encryption algorithm, Encryption Strengthi = β·Algorithmenhanced; wherein: Encryption Strengthi is encryption strength, β is an adjustment coefficient, and Algorithmenhanced is an enhanced encryption algorithm; introducing random noise interference, NoiseLeveli = γ·Random Noisemid; wherein: Noise Leveli is the noise level, γ is an adjustment coefficient, which is set according to actual needs, and Random Noisemid is a medium level of random noise;

[0025] Protection measures for low-risk driving scenarios include: basic electromagnetic shielding, Shielding Factori = δ·Shielding Materialbasic; Shielding Factori is the shielding factor used to describe the shielding effect, δ is the adjustment coefficient, and Shielding Materialbasic is the basic shielding material; use of standard encryption algorithm, EncryptionStrengthi = ∈·Algorithmstandard; Encryption Strengthi is the encryption strength, ∈ is the adjustment coefficient, set according to actual needs, and Algorithmstandard is the standard encryption algorithm.

[0026] In a preferred embodiment, for high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed. When the driving scenario is classified as a high-risk driving scenario, that is, the risk value of electromagnetic signal leakage in the driving scenario within the fixed time period is greater than a second risk threshold, and the risk values ​​of electromagnetic signal leakage in driving scenarios greater than the second risk threshold generated in a subsequent fixed time period are collected, and a corresponding data set is established, the mean and standard deviation of the data set are calculated and analyzed, and based on the analysis results, the electromagnetic signal leakage risk event occurring in the subsequent fixed time period is predicted in advance, and based on the prediction results, high-intensity protective measures are formulated and implemented.

[0027] In a preferred embodiment, if the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and the fluctuation is small, and the risk of electromagnetic signal leakage is stable and concentrated in the high-risk area. At this time, electromagnetic shielding is strengthened, and the highest level of encryption algorithm is adopted, and a high level of random noise is introduced;

[0028] If the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and fluctuates greatly, and the risk of electromagnetic signal leakage has high uncertainty. The shielding and encryption strength are dynamically adjusted according to the real-time monitoring data, and a more complex encryption algorithm is used at the same time, and a real-time noise interference strategy is implemented to enhance the protection effect;

[0029] If the mean value of the risk value of electromagnetic signal leakage is less than the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is low but the fluctuation is large; use medium-strength shielding materials, adopt enhanced encryption algorithms, and introduce medium-level random noise;

[0030] If the mean risk value of electromagnetic signal leakage is less than the reference threshold of the mean risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is low and the fluctuation is small, and the risk of signal leakage remains stable at a low level; basic shielding materials are used, standard encryption algorithms are adopted, and basic random noise is introduced.

[0031] The present invention also provides an automobile EDR data encryption protection system, including an electromagnetic signal acquisition module, a feature extraction module, a risk assessment module, a driving scene division module, a protection module and a risk event prediction module;

[0032] Electromagnetic signal acquisition module: It divides several driving scenarios according to the driving conditions and operating status of the vehicle, and uses a highly sensitive electromagnetic signal receiving device to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time;

[0033] Feature extraction module: pre-processes the captured electromagnetic signal data, extracts characteristic parameters related to the encryption process, and builds a signal feature library;

[0034] Risk assessment module: Based on the signal feature library, it identifies and analyzes the signal features and strength of the captured electromagnetic signal data, and evaluates the risk level of electromagnetic signal leakage in various driving scenarios;

[0035] Driving scenario classification module: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios;

[0036] Protection module: Based on the classification results, take corresponding protection measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system;

[0037] Risk event prediction module: For high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed, and the electromagnetic signal leakage risk events that occur in the subsequent fixed time period are predicted in advance. Based on the prediction results, high-intensity protection measures are formulated and implemented.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] 1. The present invention captures the electromagnetic signal data generated by the EDR system in various driving scenarios in real time, performs preprocessing and feature extraction, and constructs a signal feature library, which can effectively identify and analyze the characteristics and strength of electromagnetic signals and evaluate the risk level of electromagnetic signal leakage in different driving scenarios. Based on the evaluation results, for medium-risk and low-risk driving scenarios, corresponding protective measures such as increasing electromagnetic shielding, using optimized encryption algorithms, and introducing random noise interference are taken to prevent electromagnetic signal leakage and ensure data security in the EDR system.

[0040] 2. For high-risk driving scenarios, the present invention further analyzes the risk of electromagnetic signal leakage within a fixed time period in detail, and uses the mean and standard deviation of the data set for prediction, thereby identifying potential risk events in advance. According to the prediction results, high-intensity protection measures are formulated and implemented, such as efficient shielding, the use of the highest level of encryption algorithms and strong random noise interference, to enhance the protection effect. Overall, it not only improves the EDR system's ability to resist electromagnetic signal leakage, but also improves the safety and reliability of the system, and ensures the integrity and accuracy of vehicle accident data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 The figure is a flow chart of the method of the present invention.

[0043] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0045] Example 1

[0046] See also Figure 1 As shown, the automobile EDR data encryption protection method described in this embodiment includes the following steps:

[0047] S1: Divide several driving scenarios according to the driving conditions and operating status of the vehicle, and use high-sensitivity electromagnetic signal receiving equipment to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time;

[0048] S2: pre-process the captured electromagnetic signal data, extract characteristic parameters related to the encryption process, and build a signal feature library;

[0049] S3: Based on the signal feature library, the signal features and strength of the captured electromagnetic signal data are identified and analyzed to assess the risk level of electromagnetic signal leakage in various driving scenarios;

[0050] S4: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios;

[0051] S5: Based on the classification results, take corresponding protective measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system;

[0052] S6: For high-risk driving scenarios, analyze the risk of electromagnetic signal leakage within a fixed time period, and make advance predictions of electromagnetic signal leakage risk events that may occur in subsequent fixed time periods. Based on the prediction results, formulate and implement high-intensity protective measures.

[0053] Among them, in S1, several driving scenarios are divided according to the driving conditions and vehicle operating status of the vehicle, and the electromagnetic signal data generated by the EDR system in the encryption and decryption process in each driving scenario is captured in real time through a high-sensitivity electromagnetic signal receiving device, specifically:

[0054] The purpose of dividing driving scenarios is to fully understand and analyze the electromagnetic signal characteristics generated by the automotive EDR system under different conditions, so as to identify and prevent potential electromagnetic side channel attacks. The specific division method is as follows:

[0055] Classification based on driving conditions:

[0056] Urban roads: Vehicles travel in cities at relatively low speeds and start and stop frequently. There may be many sources of electromagnetic interference, such as other vehicles, buildings, traffic lights, etc.

[0057] Expressway: Vehicles travel on the expressway at a relatively high and stable speed, and the electromagnetic environment is relatively open.

[0058] Rural roads: Vehicles travel on rural roads with speeds and EMI levels between those on urban roads and highways.

[0059] Classification based on vehicle operating status:

[0060] Acceleration: When a vehicle accelerates from a stationary or slow speed to a higher speed, the load on the engine and electronic systems increases.

[0061] Braking: When the vehicle is decelerated or braked suddenly, the braking system and ABS work.

[0062] Stationary: The vehicle is stopped and the engine is idling or completely turned off.

[0063] Turning: When the vehicle turns, the steering wheel and steering system work, which may generate specific electromagnetic signal characteristics.

[0064] Through the high-sensitivity electromagnetic signal receiving device, the electromagnetic signals generated by the car EDR system during the encryption and decryption process in various driving scenarios are captured and recorded in real time. The specific steps are as follows:

[0065] Install a highly sensitive antenna outside or inside the vehicle to capture electromagnetic signals generated by various vehicle components. Connect a signal receiver to the antenna to receive and record electromagnetic signal data in real time. Store the captured electromagnetic signal data in a data recorder to ensure data integrity and accuracy.

[0066] The receiving device runs continuously while the vehicle is driving, monitoring and recording electromagnetic signals under different driving conditions and vehicle operating states in real time. The captured electromagnetic signals are sampled at high frequencies to obtain detailed signal characteristic data.

[0067] S2: Preprocess the captured electromagnetic signal data, extract characteristic parameters related to the encryption process, and build a signal feature library.

[0068] The purpose of preprocessing the captured electromagnetic signal data, extracting characteristic parameters related to the encryption process, and building a signal feature library is to systematically analyze electromagnetic signals and identify potential security threats.

[0069] Data preprocessing is the process of converting raw electromagnetic signal data into a format more suitable for analysis. This step includes denoising, smoothing, and normalization to ensure data quality and consistency.

[0070] Use filters (such as low-pass filtering, high-pass filtering, band-pass filtering, etc.) to remove high-frequency or low-frequency noise. Eliminate noise in the signal and retain useful signal information.

[0071] Use moving average, weighted moving average or other smoothing techniques to process signal data, reduce random fluctuations in the signal and make the signal characteristics more obvious.

[0072] Normalize the signal amplitude to facilitate subsequent analysis and comparison. Adjust the signal amplitude to a standard range (such as 0 to 1) to eliminate amplitude differences between different signals.

[0073] Feature parameter extraction is to extract information that can represent the characteristics of the encryption process from the preprocessed electromagnetic signal data. These feature parameters include frequency domain features, time domain features, statistical features, and short-term features. Frequency domain features such as spectral density, main frequency components, and harmonic components can be used to analyze the frequency distribution of signals through Fourier transform to reflect the energy distribution of signals during the encryption process. Time domain features such as mean, variance, peak, and zero crossing rate reveal the characteristics of signal changes over time by directly analyzing time series data.

[0074] Statistical features such as mean, standard deviation, skewness and kurtosis reflect the overall distribution characteristics of the signal by statistically analyzing the signal data. Short-term features include short-time Fourier transform (STFT) and wavelet transform, which extract the local change characteristics of the signal by dividing the signal into short time periods or multi-scale analysis. These characteristic parameters jointly construct a signal feature library for subsequent signal analysis and pattern recognition, helping to identify and prevent electromagnetic side channel attacks.

[0075] Building a signal feature library is to systematize and standardize the extracted feature parameters for subsequent analysis and comparison. According to different driving conditions and vehicle status, signal features are divided into multiple categories for easy management and retrieval. Determine the storage format of feature parameters, such as matrix, vector or other data structure, to ensure the consistency and availability of feature data.

[0076] Select a suitable database system (such as a relational database, NoSQL database, etc.) to store signal feature data. Create indexes for feature parameters in the feature library to facilitate quick retrieval and query. Regularly update the feature library and add new signal feature data to keep the feature library up to date and comprehensive. Regularly clean up redundant and invalid data in the feature library to ensure the quality of the feature library.

[0077] S3: Based on the signal feature library, the signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed to evaluate the risk level of electromagnetic signal leakage in various driving scenarios.

[0078] The signal feature library contains the electromagnetic signal feature parameters after preprocessing and extraction, which represent the frequency domain, time domain, statistical features and short-term features in the encryption process. The data in the feature library is classified and stored according to different driving conditions and vehicle operating states to ensure accurate analysis for specific scenarios.

[0079] During the driving process of the vehicle, the electromagnetic signal is captured in real time through a high-sensitivity electromagnetic signal receiving device. The captured real-time electromagnetic signal is preprocessed (denoising, smoothing, normalization, etc.) to extract feature parameters consistent with the signal feature library.

[0080] The signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed, and the risk level of electromagnetic signal leakage in various driving scenarios is evaluated. The signal characteristic prominence is generated according to the signal characteristics of the captured electromagnetic signal data. The method for obtaining the signal characteristic prominence is as follows:

[0081] The captured electromagnetic signal data matrix is ​​represented as X, where each row represents a sample and each column represents a feature. The electromagnetic signal data in the matrix is ​​standardized, and the mean vector and standard deviation vector of the electromagnetic signal data features in the matrix are calculated respectively; the standardized data matrix is ​​calculated The covariance matrix C of , where the calculation expression of the covariance matrix is: In the formula, n is the number of samples, The transpose of the standardized data matrix is ​​used to perform eigenvalue decomposition on the covariance matrix C to obtain the eigenvalue λ and eigenvector v, where the eigenvalue decomposition formula is: C*vi=λi*vi; where λi is the ith eigenvalue and vi is the ith eigenvector; the principal component is selected according to the size of the eigenvalue. The larger the eigenvalue, the more significant the feature represented by the corresponding eigenvector. The eigenvectors corresponding to the first k largest eigenvalues ​​of the eigenvalue λ are summed, and the summation result is used as the eigenvalue of the principal component, that is, the signal feature prominence, where k is a positive integer greater than 0.

[0082] The greater the signal feature prominence, the more obvious and significant the electromagnetic signal features are in a specific driving scenario. This means that these electromagnetic signals are more easily captured and analyzed by attackers through electromagnetic side channel attacks, thereby recovering encryption keys or other sensitive information. Therefore, in driving scenarios with greater feature prominence, the risk of electromagnetic signal leakage increases significantly.

[0083] Specifically, signals with greater feature prominence have higher energy concentration and frequency stability, which makes them more obvious in noise and easier to distinguish and extract. Attackers can use these significant features to more accurately parse the original information of electromagnetic signals through advanced signal processing technology and machine learning algorithms. In this case, even in a more complex electromagnetic environment, the high feature prominence of the signal still leads to a higher risk of leakage.

[0084] Therefore, for driving scenarios with high feature prominence, more stringent protection measures must be taken, such as enhancing electromagnetic shielding, introducing random noise, and using encryption algorithms that resist side channel attacks, to reduce the risk of electromagnetic signal leakage. Through effective protection, the prominence of signal features can be reduced, thereby improving the overall security of the system and preventing sensitive data from being illegally acquired and used.

[0085] The signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed, the risk level of electromagnetic signal leakage in various driving scenarios is evaluated, and the electromagnetic wave power fluctuation index is generated according to the captured signal strength. The method for obtaining the electromagnetic wave power fluctuation index is as follows:

[0086] Extract the electromagnetic wave power time series data P(t) from the captured electromagnetic signal, where t represents time and P(t) represents the power value at time t. Preprocess the signal. For discrete time signals, use discrete Fourier transform to convert them into frequency domain. The calculation formula is: P(f) is the amplitude of the frequency domain signal at frequency f, N is the number of sampling points of the signal, e -j2πft / N is a complex exponential function;

[0087] Calculate the energy density of the electromagnetic wave power spectrum at each frequency in the time series. The calculation formula is: PSD(f) is the power spectral density at frequency f, (P(f)) 2 It is the square of the frequency domain signal amplitude; by analyzing the power spectrum density diagram, the root mean square value of the power spectrum density is calculated, that is, the electromagnetic wave power fluctuation index is calculated.

[0088] When the electromagnetic wave power fluctuation index is large, it means that the signal fluctuates significantly in the frequency domain and the frequency components are more prominent. Attackers can more easily capture these significant frequency characteristics through high-sensitivity receiving equipment, thereby conducting further signal analysis and decryption.

[0089] A high fluctuation index indicates that the signal energy is highly concentrated at certain frequencies, which makes these frequency components easier to distinguish and extract from noise. Attackers can use these concentrated energy frequency components to reconstruct the information in the encryption process, thereby increasing the success rate of decryption.

[0090] A high volatility index also indicates that the signal strength fluctuates greatly in time and frequency. Frequent strength changes can cause the signal strength to be abnormally high at certain points in time, allowing attackers to obtain a clearer signal at these points in time.

[0091] The signal feature prominence and the electromagnetic wave power fluctuation index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the risk value label of electromagnetic signal leakage in each driving scenario with each group of first eigenvectors as the prediction target, and takes minimizing the sum of prediction errors of the risk value labels of electromagnetic signal leakage in all driving scenarios as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The risk value of electromagnetic signal leakage in each driving scenario is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0092] The method for obtaining the risk value of electromagnetic signal leakage in each driving scenario is as follows: from the first eigenvector training data of the trained machine learning model, obtain the corresponding function expression: NX=f1(KP, SD); where f1 is the output function of the model, KP is the signal feature prominence, SD is the electromagnetic wave power fluctuation index, and NX is the risk value of electromagnetic signal leakage in each driving scenario.

[0093] S4: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios.

[0094] Compare the acquired risk value of electromagnetic signal leakage in each driving scenario with the gradient risk threshold, where the gradient risk threshold in the present application includes a first risk threshold and a second risk threshold, and the first risk threshold is less than the second risk threshold, and compare the risk value of electromagnetic signal leakage in each driving scenario with the first risk threshold and the second risk threshold respectively;

[0095] If the risk value of electromagnetic signal leakage in each driving scenario is greater than a second risk threshold, the driving scenario is classified as a high-risk driving scenario;

[0096] If the risk value of electromagnetic signal leakage in each driving scenario is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, the driving scenario is classified as a medium-risk driving scenario;

[0097] If the risk value of electromagnetic signal leakage in each driving scenario is less than the first risk threshold, the driving scenario is classified as a low-risk driving scenario.

[0098] S5: Based on the classification results, take corresponding protective measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system.

[0099] The protective measures taken for medium-risk driving scenarios are:

[0100] Increase electromagnetic shielding:

[0101] Shielding Factori = α*Shielding Materialmid; where: Shielding Factori is the shielding factor, which is used to describe the shielding effect, α is the adjustment coefficient, which is set according to actual needs, and Shielding Materialmid is a medium-strength shielding material.

[0102] Using optimized encryption algorithm:

[0103] Encryption Strengthi=β·Algorithmenhanced; where:

[0104] Encryption Strengthi is the encryption strength, β is the adjustment coefficient, which is set according to actual needs, and Algorithmenhanced is the enhanced encryption algorithm.

[0105] Introduce random noise interference:

[0106] Noise Leveli = γ Random Noisemid; where:

[0107] Noise Leveli is the noise level, γ is the adjustment coefficient, which is set according to actual needs, and Random Noisemid is the medium level of random noise.

[0108] The protective measures for low-risk driving scenarios are:

[0109] Basic electromagnetic shielding:

[0110] Shielding Factori = δ · Shielding Materialbasic; Shielding Factori is the shielding factor used to describe the shielding effect, δ is the adjustment coefficient, which is set according to actual needs, and Shielding Materialbasic is the basic shielding material.

[0111] Use standard encryption algorithms:

[0112] Encryption Strengthi=∈·Algorithmstandard;

[0113] Encryption Strengthi is the encryption strength, ∈ is the adjustment coefficient, which is set according to actual needs, and Algorithmstandard is the standard encryption algorithm.

[0114] In the present invention, by setting appropriate shielding factors, encryption strengths and noise levels and adjusting them according to the risk level of the driving scenario, electromagnetic signal leakage can be effectively prevented and data security in the EDR system can be ensured. The formulaic expression provides a systematic method to quantify and implement these protective measures, thereby improving the controllability and operability of the protective effect.

[0115] S6: For high-risk driving scenarios, analyze the risk of electromagnetic signal leakage within a fixed time period, and make advance predictions of electromagnetic signal leakage risk events that may occur in subsequent fixed time periods. Based on the prediction results, formulate and implement high-intensity protective measures.

[0116] For high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed. When the driving scenario is classified as a high-risk driving scenario, that is, the risk value of electromagnetic signal leakage in the driving scenario within a fixed time period is greater than the second risk threshold, the risk values ​​of electromagnetic signal leakage in driving scenarios generated in subsequent fixed time periods that are greater than the second risk threshold are collected, and a corresponding data set is established. The mean and standard deviation of the data set are calculated and analyzed. According to the analysis results, the electromagnetic signal leakage risk events that occur in the subsequent fixed time period are predicted in advance, and according to the prediction results, high-intensity protective measures are formulated and implemented.

[0117] If the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and the fluctuation is small. This means that the risk of electromagnetic signal leakage is stable and concentrated in high-risk areas, and attackers can easily use this stable feature to capture and analyze signals;

[0118] At this time, electromagnetic shielding should be strengthened, high-efficiency shielding materials should be used, signal leakage should be reduced, and the highest level of encryption algorithm should be adopted to increase the difficulty of data decryption, and high levels of random noise should be introduced to interfere with signal capture and analysis.

[0119] If the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and fluctuates greatly. This means that the risk of electromagnetic signal leakage has high uncertainty, and it is difficult for attackers to predict and capture high-risk signals at specific times;

[0120] Dynamically adjust shielding and encryption strength based on real-time monitoring data to adapt to changes in risks. At the same time, use more complex encryption algorithms to increase the difficulty of data decryption, and implement real-time noise interference strategies to enhance protection effects.

[0121] If the mean value of the risk value of electromagnetic signal leakage is less than the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is low but fluctuates greatly. This means that although the overall risk is low, there are some high-risk moments, and high-risk events may suddenly occur;

[0122] Use medium-strength shielding materials to balance cost and effectiveness, adopt enhanced encryption algorithms to improve data security, and introduce medium levels of random noise to interfere with signal analysis.

[0123] If the mean value of the risk value of electromagnetic signal leakage is less than the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that the risk of electromagnetic signal leakage is low and fluctuates little in the subsequent fixed time period. This means that the risk of signal leakage remains stable at a low level and it is not easy to have sudden high-risk events.

[0124] Use basic shielding materials to ensure basic protection, adopt standard encryption algorithms to ensure data security, and introduce basic random noise to prevent signal leakage.

[0125] In the present invention, by analyzing the mean and standard deviation of the electromagnetic signal leakage risk value, the risk situation in a fixed time period in the future can be predicted and corresponding protective measures can be formulated. According to different risk situations, high-intensity shielding, dynamic adjustment of protection strategies or basic protection measures are adopted to ensure the data security of the EDR system and prevent electromagnetic signal leakage.

[0126] In this embodiment, several driving scenarios are divided according to the driving conditions and vehicle operation status of the vehicle, and the electromagnetic signal data generated by the EDR system in the encryption and decryption process in each driving scenario is captured in real time through a high-sensitivity electromagnetic signal receiving device; the captured electromagnetic signal data is preprocessed, the characteristic parameters related to the encryption process are extracted, and a signal feature library is constructed; based on the signal feature library, the signal characteristics and strength of the captured electromagnetic signal data are identified and analyzed, and the risk level of electromagnetic signal leakage in each driving scenario is evaluated; according to the risk of electromagnetic signal leakage in each driving scenario, the driving scenario is divided into high-risk driving scenario, medium-risk driving scenario and low-risk driving scenario; according to the division results, corresponding protective measures are taken for medium-risk driving scenario and low-risk driving scenario to prevent the occurrence of electromagnetic signal leakage and ensure the data security in the EDR system; for high-risk driving scenarios, the risk of electromagnetic signal leakage in a fixed time period is analyzed, and the electromagnetic signal leakage risk event that occurs in the subsequent fixed time period is predicted in advance, and high-intensity protective measures are formulated and implemented according to the prediction results. It can not only effectively prevent electromagnetic signal leakage and ensure the data security of the EDR system, but also improve the overall safety and reliability of the system and improve the integrity and accuracy of accident data.

[0127] Example 2

[0128] See also Figure 2 As shown, the automobile EDR data encryption protection system described in this embodiment includes an electromagnetic signal acquisition module, a feature extraction module, a risk assessment module, a driving scene division module, a protection module and a risk event prediction module;

[0129] Electromagnetic signal acquisition module: It divides several driving scenarios according to the driving conditions and operating status of the vehicle, and uses a highly sensitive electromagnetic signal receiving device to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time;

[0130] Feature extraction module: pre-processes the captured electromagnetic signal data, extracts characteristic parameters related to the encryption process, and builds a signal feature library;

[0131] Risk assessment module: Based on the signal feature library, it identifies and analyzes the signal features and strength of the captured electromagnetic signal data, and evaluates the risk level of electromagnetic signal leakage in various driving scenarios;

[0132] Driving scenario classification module: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios;

[0133] Protection module: Based on the classification results, take corresponding protection measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system;

[0134] Risk event prediction module: For high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed, and the electromagnetic signal leakage risk events that occur in the subsequent fixed time period are predicted in advance. Based on the prediction results, high-intensity protection measures are formulated and implemented.

[0135] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0136] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0137] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0138] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0139] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for encrypting and protecting automobile EDR data, characterized in that: The following steps are involved: S1: Divide several driving scenarios according to the driving conditions and operating status of the vehicle, and use high-sensitivity electromagnetic signal receiving equipment to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time; S2: pre-process the captured electromagnetic signal data, extract characteristic parameters related to the encryption process, and build a signal feature library; S3: Based on the signal feature library, the signal features and strength of the captured electromagnetic signal data are identified and analyzed to assess the risk level of electromagnetic signal leakage in various driving scenarios; The step S3 specifically includes: identifying and analyzing the signal characteristics and strength of the captured electromagnetic signal data, evaluating the risk level of electromagnetic signal leakage in various driving scenarios, and generating a signal characteristic prominence degree according to the signal characteristics of the captured electromagnetic signal data. The method for obtaining the signal characteristic prominence degree is: The captured electromagnetic signal data matrix is ​​represented as X, where each row represents a sample and each column represents a feature. The electromagnetic signal data in the matrix is ​​standardized, and the mean vector and standard deviation vector of the electromagnetic signal data features in the matrix are calculated respectively; the standardized data matrix is ​​calculated The covariance matrix C of , where the calculation expression of the covariance matrix is: C = ; Where n is the number of samples, is the transpose of the standardized data matrix, and the covariance matrix C is decomposed by eigenvalue to obtain the eigenvalue λ and eigenvector v, where the eigenvalue decomposition formula is: ; In the formula, λi is the i-th eigenvalue, and vi is the i-th eigenvector; the principal component is selected according to the size of the eigenvalue. The larger the eigenvalue, the more significant the feature represented by the corresponding eigenvector. The eigenvectors corresponding to the first k largest eigenvalues ​​of the eigenvalue λ are summed, and the summation result is used as the eigenvalue of the principal component, that is, the signal feature prominence, where k is a positive integer greater than 0; The step S3 specifically includes: identifying and analyzing the signal characteristics and strength of the captured electromagnetic signal data, evaluating the risk level of electromagnetic signal leakage in various driving scenarios, and generating an electromagnetic wave power fluctuation index according to the captured signal strength. The method for obtaining the electromagnetic wave power fluctuation index is: Extract the electromagnetic wave power time series data P(t) from the captured electromagnetic signal, where t represents time and P(t) represents the power value at time t. Preprocess the signal. For discrete time signals, use discrete Fourier transform to convert them into frequency domain. The calculation formula is: P(f)= ; P(f) is the amplitude of the frequency domain signal at frequency f, N is the number of sampling points of the signal, is a complex exponential function; Calculate the energy density of the electromagnetic wave power spectrum at each frequency in the time series. The calculation formula is: (f)= ; (f) is the power spectral density at frequency f, It is the square of the amplitude of the frequency domain signal; by analyzing the power spectrum density diagram, the root mean square value of the power spectrum density is calculated, that is, the electromagnetic wave power fluctuation index is calculated; The signal feature prominence and the electromagnetic wave power fluctuation index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the risk value label of electromagnetic signal leakage in each driving scenario with each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the risk value labels of electromagnetic signal leakage in all driving scenarios as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The risk value of electromagnetic signal leakage in each driving scenario is determined according to the model output results, wherein the machine learning model is a polynomial regression model; S4: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios; S5: Based on the classification results, take corresponding protective measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system; S6: For high-risk driving scenarios, analyze the risk of electromagnetic signal leakage within a fixed time period, and make advance predictions of electromagnetic signal leakage risk events that may occur in subsequent fixed time periods. Based on the prediction results, formulate and implement high-intensity protective measures.

2. The method for encrypting and protecting automobile EDR data according to claim 1 is characterized in that: The obtained risk value of electromagnetic signal leakage in each driving scenario is compared with a gradient risk threshold, where the gradient risk threshold includes a first risk threshold and a second risk threshold, and the first risk threshold is less than the second risk threshold, and the risk value of electromagnetic signal leakage in each driving scenario is compared with the first risk threshold and the second risk threshold respectively; If the risk value of electromagnetic signal leakage in each driving scenario is greater than a second risk threshold, the driving scenario is classified as a high-risk driving scenario; If the risk value of electromagnetic signal leakage in each driving scenario is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, the driving scenario is classified as a medium-risk driving scenario; If the risk value of electromagnetic signal leakage in each driving scenario is less than the first risk threshold, the driving scenario is classified as a low-risk driving scenario.

3. The method for encrypting and protecting automobile EDR data according to claim 2 is characterized in that: Take corresponding protective measures for medium-risk driving scenarios and low-risk driving scenarios. Specifically, the protective measures taken for medium-risk driving scenarios include: increasing electromagnetic shielding, ;in: is the shielding factor, used to describe the shielding effect, α is the adjustment coefficient, and ShieldingMaterialmid is a medium-strength shielding material; using an optimized encryption algorithm, ;in: is the encryption strength, β is the adjustment coefficient, It is an enhanced encryption algorithm; random noise interference is introduced. ;in: is the noise level, γ is the adjustment coefficient, which is set according to actual needs. is a medium level of random noise; Protection measures for low-risk driving scenarios include: basic electromagnetic shielding, ; is the shielding factor, used to describe the shielding effect, δ is the adjustment coefficient, As the basic shielding material; using standard encryption algorithms, ; is the encryption strength, To adjust the coefficient, set it according to actual needs. It is a standard encryption algorithm.

4. The method for encrypting and protecting automobile EDR data according to claim 3 is characterized in that: For high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed. When the driving scenario is classified as a high-risk driving scenario, that is, the risk value of electromagnetic signal leakage in the driving scenario within a fixed time period is greater than the second risk threshold, the risk values ​​of electromagnetic signal leakage in driving scenarios generated in subsequent fixed time periods that are greater than the second risk threshold are collected, and a corresponding data set is established. The mean and standard deviation of the data set are calculated and analyzed. According to the analysis results, the electromagnetic signal leakage risk events that occur in the subsequent fixed time period are predicted in advance, and according to the prediction results, high-intensity protective measures are formulated and implemented.

5. The method for encrypting and protecting automobile EDR data according to claim 4 is characterized in that: If the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and the fluctuation is small, and the risk of electromagnetic signal leakage is stable and concentrated in the high-risk area. At this time, electromagnetic shielding is strengthened, the highest level of encryption algorithm is adopted, and a high level of random noise is introduced; If the mean value of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is high and fluctuates greatly, and the risk of electromagnetic signal leakage has high uncertainty. The shielding and encryption strength are dynamically adjusted according to the real-time monitoring data, and a more complex encryption algorithm is used at the same time, and a real-time noise interference strategy is implemented to enhance the protection effect; If the mean value of the risk value of electromagnetic signal leakage is less than the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is greater than or equal to the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is low but has large fluctuations; Use medium-strength shielding materials, employ enhanced encryption algorithms, and introduce medium levels of random noise; If the mean value of the risk value of electromagnetic signal leakage is less than the reference threshold value of the mean value of the risk value of electromagnetic signal leakage, and the standard deviation of the risk value of electromagnetic signal leakage is less than the reference threshold value of the standard deviation of the risk value of electromagnetic signal leakage, it indicates that in the subsequent fixed time period, the risk of electromagnetic signal leakage is low and the fluctuation is small, and the risk of signal leakage remains stable at a low level; Use basic shielding materials, adopt standard encryption algorithms, and introduce basic random noise.

6. An automobile EDR data encryption protection system, used to implement an automobile EDR data encryption protection method according to any one of claims 1 to 5, characterized in that: It includes electromagnetic signal acquisition module, feature extraction module, risk assessment module, driving scene division module, protection module and risk event prediction module; Electromagnetic signal acquisition module: It divides several driving scenarios according to the driving conditions and operating status of the vehicle, and uses a highly sensitive electromagnetic signal receiving device to capture the electromagnetic signal data generated by the EDR system during the encryption and decryption process in each driving scenario in real time; Feature extraction module: pre-processes the captured electromagnetic signal data, extracts characteristic parameters related to the encryption process, and builds a signal feature library; Risk assessment module: Based on the signal feature library, it identifies and analyzes the signal features and strength of the captured electromagnetic signal data, and evaluates the risk level of electromagnetic signal leakage in various driving scenarios; Driving scenario classification module: According to the risk of electromagnetic signal leakage in each driving scenario, the driving scenarios are divided into high-risk driving scenarios, medium-risk driving scenarios and low-risk driving scenarios; Protection module: Based on the classification results, take corresponding protection measures for medium-risk driving scenarios and low-risk driving scenarios to prevent electromagnetic signal leakage and ensure data security in the EDR system; Risk event prediction module: For high-risk driving scenarios, the risk of electromagnetic signal leakage within a fixed time period is analyzed, and the electromagnetic signal leakage risk events that occur in the subsequent fixed time period are predicted in advance. Based on the prediction results, high-intensity protection measures are formulated and implemented.

Images