A method, medium, and device for determining dynamic risks during vehicle driving based on big data

Abstract

The present invention discloses a method, medium and device for determining dynamic risks during vehicle driving based on big data, including the following steps: obtaining historical data during a vehicle trip, performing edge computing and data preprocessing on the historical data to obtain target data; extracting features based on the target data to obtain input features of the target data, and the feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction; constructing a dynamic risk assessment model, and training the dynamic risk assessment model according to the input features of the target data, and the dynamic risk assessment model uses an ARIMA model and an LSTM network model to predict dynamic risks; The present invention proposes real-time data processing and edge computing: performing data processing on in-vehicle devices to reduce latency and bandwidth requirements and improve the system response speed. Dynamically adjusting the risk model: using machine learning and deep learning technologies to automatically adjust the risk assessment model and improve prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle driving risk determination, and specifically relates to a method, medium and device for determining dynamic risks during vehicle driving based on big data. Background Art

[0002] During the in-transit driving of a vehicle, safety issues are undoubtedly of utmost importance. The influencing factors of safety issues are complex and diverse, covering multiple aspects such as drivers, vehicles, road conditions, and weather. It is worth noting that most of these influencing factors are difficult to quantify. They are like hidden time bombs, adding many uncertain risks to the in-transit driving process and thus having a non-negligible impact on in-transit safety. In view of this, in order to improve the safety of vehicles during in-transit driving, we need to pay attention to and analyze these factors.

[0003] There are still many technical problems in the prior art:

[0004] 1. Data quality and integrity issues:

[0005] Incomplete data: The data of vehicle and environmental sensors may be lost, incorrect or inconsistent. The lack of key data or poor data quality may lead to inaccurate risk assessment results.

[0006] Data latency: There may be latency in the data collection and transmission processes, affecting real-time performance and accuracy.

[0007] 2. Data fusion and processing difficulties:

[0008] Data heterogeneity: The data from different sources may have inconsistent formats, scales and qualities, making it difficult to effectively fuse.

[0009] Computational complexity: Big data analysis requires high-performance computing resources, especially in a real-time environment, with high demands for computing and storage resources.

[0010] 3. Model generalization ability:

[0011] Overfitting problem: Machine learning models may overfit the training data, resulting in poor performance in actual applications.

[0012] 4. Dynamic changes: The dynamic changes of vehicles and road environments pose challenges to the adaptability of models, and the models need to be continuously updated and adjusted. Summary of the Invention

[0013] To solve one of the above technical problems, a method, medium and device for determining dynamic risks during vehicle driving based on big data are provided, which are used to monitor and predict potential risks during vehicle driving in real time. To improve the accuracy, real-time performance and user experience of the existing technical solutions.

[0014] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0015] First aspect: A method for determining dynamic risks during vehicle driving based on big data, comprising the following steps:

[0016] Obtain historical data during the vehicle's journey, perform edge computing and data preprocessing on the historical data to obtain target data;

[0017] Based on the target data, perform feature extraction to obtain the input features of the target data. The feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction;

[0018] Construct a dynamic risk assessment model, and train the dynamic risk assessment model according to the input features of the target data. The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks;

[0019] Generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state;

[0020] Adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driver's behavior pattern through the Q-learning algorithm.

[0021] Preferably: Performing edge computing and data preprocessing on the historical data to obtain target data specifically includes:

[0022] Perform preliminary data processing on the in-vehicle computing platform, and use edge computing nodes to perform preliminary analysis and processing on the data;

[0023] Data preprocessing: Clean and normalize the data, process missing values and outliers, and perform feature extraction of acceleration and speed. The expression is:

[0024] ;

[0025] ;

[0026] Wherein, is the acceleration value of the i-th measurement; is the speed value of the i-th measurement.

[0027] Preferably: The input features of the target data include speed, acceleration, vehicle distance, road conditions, and weather; The high-dimensional feature space is reduced in dimension through the PCA (Principal Component Analysis) feature extraction algorithm. The expression is:

[0028] ;

[0029] Among them, is the data matrix, is the principal component matrix.

[0030] Preferably: The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks, specifically including:

[0031] The ARIMA model is a random forest, and the expression is:

[0032] ;

[0033] Where is the prediction result of the i-th decision tree for the input x, is the number of decision trees;

[0034] The LSTM network model, the expression is:

[0035] ;

[0036] Where is the hidden state at the current time step, is the input data at the current time step.

[0037] Preferably: Generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state, specifically including:

[0038] The risk score uses the risk score formula to calculate the current risk, and the expression is:

[0039] ;

[0040] Among them, is the comprehensive risk score, is the weight of the feature, is the impact of feature i on the risk;

[0041] The real-time warning, the threshold judgment formula is:

[0042] ;

[0043] The evaluation of the safety level of the current driving state, the expression is:

[0044] ;

[0045] Among them, is the weight coefficient, obtained through model training.

[0046] Preferably, the driving behavior pattern of the driver is optimized through the Q-learning algorithm, and the expression is:

[0047] ;

[0048] where is the action-value function of taking action a in state s, is the immediate reward, is the discount factor, is the learning rate.

[0049] Preferably, the historical data includes vehicle internal data, external environment data, big data platform data, and driving behavior data. The temporal feature extraction is to extract the dynamic features of the vehicle; the environmental feature extraction is to extract the features of environmental changes, and the behavior pattern extraction is to extract the patterns of the driver's behavior.

[0050] Second aspect: A device for determining dynamic risks during vehicle driving based on big data, including:

[0051] A task acquisition module, configured to acquire historical data during the vehicle journey, perform edge computing and data preprocessing on the historical data to obtain target data;

[0052] A feature extraction module, configured to extract features from the target data to obtain the input features of the target data. The feature extraction includes temporal feature extraction, environmental feature extraction, and behavior pattern extraction;

[0053] A dynamic risk assessment module, configured to build a dynamic risk assessment model, train the dynamic risk assessment model according to the input features of the target data, and the dynamic risk assessment model uses an ARIMA model and an LSTM network model to predict dynamic risks;

[0054] A risk scoring module, configured to generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger real-time warnings when the threshold is exceeded, and evaluate the safety level of the current driving state;

[0055] An optimized driving strategy module, configured to adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driving behavior pattern of the driver through the Q-learning algorithm.

[0056] Third aspect: A computer device, including:

[0057] A processor;

[0058] A memory, configured to store executable instructions;

[0059] Among them, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the method for determining dynamic risks during vehicle driving based on big data.

[0060] Fourth aspect: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method for determining dynamic risks during vehicle driving based on big data.

[0061] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0062] The present invention proposes real-time data processing and edge computing: data processing is performed on in-vehicle devices, reducing latency and bandwidth requirements and improving the system response speed.

[0063] Dynamically adjust the risk model: utilize machine learning and deep learning technologies to automatically adjust the risk assessment model and improve prediction accuracy.

[0064] Intelligent warning system: optimize the warning strategy through real-time data and user feedback to achieve personalized driving suggestions.

[0065] Reinforcement learning to optimize decisions: utilize reinforcement learning algorithms to optimize driving decisions and improve the adaptability and intelligence level of the system.

[0066] Through these optimizations, the solution not only improves the accuracy and real-time performance of risk assessment, but also greatly enhances the intelligence and user experience of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 is a flowchart of the method for determining dynamic risks during vehicle driving based on big data according to the present invention;

[0068] Figure 2 is a schematic structural diagram of a computer device according to Embodiment 3 of the present invention.

[0069] Figure 3 is a module diagram of the device for determining dynamic risks during vehicle driving based on big data according to the present invention;

[0070] In the figure, 10 is a computer device; 1002 is a processor; 1004 is a memory; 1006 is a transmission device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0071] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0072] Embodiment 1:

[0073] Refer to Figure 1 As shown, a method for determining dynamic risks during vehicle driving based on big data includes the following steps:

[0074] Obtain historical data during the vehicle's journey, perform edge computing and data preprocessing on the historical data to obtain target data;

[0075] Data collection: Collect data from various sources, including vehicle sensors (such as speed, acceleration, brake status, etc.), environmental sensors (such as weather, road conditions, etc.), driving behavior data (such as hard acceleration, hard braking, etc.), and other traffic-related data (such as traffic signals, road conditions, etc.);

[0076] Multi-source data fusion: Use data fusion algorithms to integrate data from different sources into a unified data model. Data fusion algorithms (such as Kalman filtering, particle filtering) can be used to improve the integrity and accuracy of the data;

[0077] Based on the target data, perform feature extraction to obtain the input features of the target data. The feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction;

[0078] Time series feature extraction: Extract dynamic features of the vehicle, such as speed change rate, acceleration change rate, etc.

[0079] Environmental feature extraction: Extract features of environmental changes, such as weather change trends, road condition changes, etc.

[0080] Behavior pattern analysis: Extract patterns of driver behavior, such as hard braking frequency, speeding behavior, etc.

[0081] Construct a dynamic risk assessment model, and train the dynamic risk assessment model according to the input features of the target data. The dynamic risk assessment model uses an ARIMA model and an LSTM network model to predict dynamic risks;

[0082] Generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state;

[0083] Adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driver's behavior pattern through the Q-learning algorithm.

[0084] Specifically: Perform edge computing and data preprocessing on the historical data to obtain target data, specifically including:

[0085] Perform preliminary data processing on the in-vehicle computing platform, and use edge computing nodes to perform preliminary analysis and processing on the data;

[0086] Data preprocessing: Clean and normalize the data, handle missing values and outliers, and perform feature extraction of acceleration and speed. The expression is:

[0087] ;

[0088] ;

[0089] Among them, is the acceleration value of the i-th measurement; is the speed value of the i-th measurement.

[0090] Edge computing: Perform preliminary data processing on the in-vehicle computing platform to reduce latency and bandwidth consumption. Use edge computing nodes to perform preliminary analysis and processing on the data.

[0091] Data preprocessing: Clean, normalize, and perform feature extraction on the data.

[0092] Specifically: The input features of the target data include speed, acceleration, vehicle distance, road conditions, and weather; the high-dimensional feature space is reduced by the PCA (Principal Component Analysis) feature extraction algorithm. The expression is:

[0093] ;

[0094] Among them, is the data matrix, is the principal component matrix.

[0095] Specifically: The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks, specifically including:

[0096] The ARIMA model is a random forest. The expression is:

[0097] ;

[0098] Among them is the prediction result of the i-th decision tree for the input x, is the number of decision trees;

[0099] The LSTM network model, the expression is:

[0100] ;

[0101] Among them is the hidden state of the current time step, is the input data of the current time step.

[0102] Specifically: generate a risk score based on the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state, specifically including:

[0103] The risk score calculates the current risk using a risk score formula, and the expression is:

[0104] ;

[0105] Where, is the comprehensive risk score, is the weight of the feature, is the impact of feature i on the risk;

[0106] For the real-time warning, the threshold judgment formula is:

[0107] ;

[0108] The expression for evaluating the safety level of the current driving state is:

[0109] ;

[0110] Where, is the weight coefficient, obtained through model training.

[0111] Specifically: optimize the driver's behavior pattern through the Q-learning algorithm, and the expression is:

[0112] ;

[0113] Where, is the action-value function of taking action a in state s, is the immediate reward, is the discount factor, is the learning rate.

[0114] Real-time warning: Based on the calculated risk score, send a real-time warning to the driver through the in-vehicle system. For example,

[0115] Adopt forms such as voice prompts and visual warnings (such as HUD display).

[0116] Adaptive adjustment: Adjust the warning strategy through a feedback mechanism, such as adjusting the warning intensity under different road conditions.

[0117] Optimize driving decisions using reinforcement learning algorithms and provide personalized driving suggestions. For example, use the Q-learning algorithm to optimize driving strategies.

[0118] Specifically, the historical data includes vehicle internal data, external environment data, big data platform data, and driving behavior data. The temporal feature extraction is to extract the dynamic features of the vehicle; the environmental feature extraction is to extract the features of environmental changes, and the behavior pattern extraction is to extract the patterns of driver behavior.

[0119] 1. Real-time data processing and edge computing:

[0120] Edge computing: Move data processing to the in-vehicle computing platform, reduce data transmission latency, and reduce dependence on cloud computing resources. This method effectively shortens the response time, enables real-time dynamic risk assessment, and improves the reaction speed and efficiency of the system.

[0121] Example: In traditional systems, data processing may be centralized in the cloud, which leads to transmission latency, especially in the case of high-speed movement. Through edge computing, the vehicle can immediately process data from the CAN bus and in-vehicle sensors, quickly identify potential risks, and make real-time responses, such as immediately warning the driver or adjusting the driving strategy.

[0122] 2. Dynamic risk model and machine learning application:

[0123] Deep learning model: Use LSTM (Long Short-Term Memory Network) to process time series data to more accurately predict dynamic risks. The LSTM model can effectively capture long-term time dependencies during vehicle driving, improving the accuracy of risk prediction.

[0124] PCA dimensionality reduction: Through principal component analysis (PCA) dimensionality reduction processing, improve the efficiency of model training and reduce the computational burden brought by high-dimensional data.

[0125] Example: For example, LSTM can process the speed and acceleration time series data of the vehicle to identify patterns that may trigger risks. PCA can reduce the dimensionality of high-dimensional sensor data, thereby accelerating the model training speed and prediction efficiency, which is particularly important for real-time risk assessment.

[0126] 3. Intelligent warning system and personalized configuration:

[0127] Adaptive warning mechanism: Through real-time data and driver feedback, the system can dynamically adjust the warning strategy, such as automatically adjusting the warning intensity under different road conditions or weather.

[0128] Personalized configuration: Provide personalized risk management suggestions based on the driver's historical data and driving habits. This method improves the user experience and makes the warning system more in line with individual needs.

[0129] For example: If the system detects that the driver is slow to react under adverse weather conditions, it may increase the frequency and intensity of warnings. In addition, the system can adjust the warning method according to the driver's habits, such as issuing earlier warnings to drivers who often drive at high speeds.

[0130] 4. Optimization of Decision-making by Reinforcement Learning

[0131] Q-learning algorithm: Use reinforcement learning algorithms (such as Q-learning) to optimize driving decisions. Q-learning can continuously adjust and optimize decision-making strategies based on real-time feedback, provide personalized driving suggestions, and improve the adaptability of the system.

[0132] For example: For instance, Q-learning can optimize how to adjust the vehicle speed or acceleration strategy when encountering complex road conditions. Through continuous training and feedback, the system can provide more intelligent driving suggestions to help drivers make optimal decisions in different driving environments.

[0133] Improved real-time performance and response speed: Through edge computing and real-time data processing, the system can respond to potential risks faster and reduce latency.

[0134] Enhanced accuracy of risk prediction: Using deep learning and dimensionality reduction techniques improves the prediction accuracy of the model, making dynamic risk assessment more precise.

[0135] Optimized user experience: The intelligent warning system and personalized configuration enhance the adaptability and user satisfaction of the system, making the warnings more in line with actual needs.

[0136] Enhanced the intelligence level of the system: By optimizing driving decisions through reinforcement learning, the intelligent decision-making ability and adaptive ability of the system are improved.

[0137] These breakthroughs enable the solution to provide more efficient and accurate risk assessment and warning in practical applications, greatly enhancing driving safety and user experience.

[0138] In other embodiments, the following steps are included:

[0139] Data fusion algorithm:

[0140] Multi-sensor data fusion: Use a Kalman filter to fuse data from different sensors to improve the accuracy and reliability of the data.

[0141] ;

[0142] where is the estimated state, is the Kalman gain, is the measurement value, is the measurement matrix.

[0143] Real-time big data analysis:

[0144] Streaming data processing: Use tools such as Apache Kafka and Apache Flink to process real-time data streams, ensuring the efficiency and accuracy of data processing.

[0145] Vehicle-to-Everything (V2X) integration:

[0146] V2X communication:

[0147] Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I): Integrate V2X technology to obtain real-time information about surrounding vehicles and infrastructure for optimizing dynamic risk assessment.

[0148] ;

[0149] Among them, is vehicle-to-vehicle data, is vehicle-to-infrastructure data, is vehicle's own data.

[0150] User experience optimization:

[0151] Adaptive user interface:

[0152] Dynamic adjustment: Dynamically adjust the display and warning mechanisms of the user interface according to the driver's feedback and driving habits. For example, use user behavior analysis to optimize the presentation of warning messages.

[0153] ;

[0154] Among them, is the adjustment of the user interface, is the user feedback, is the driving mode.

[0155] Data encryption and privacy protection: Encryption technology: Use end-to-end encryption to protect the security of data transmission and prevent data from being accessed or tampered with without authorization;

[0156] ;

[0157] Among them, is the encrypted data, is the encryption function, is the encryption key, is the original data.

[0158] Further improve the overall performance, user experience and security of the system.

[0159] Embodiment 2

[0160] Figure 3 as shown in:

[0161] A device for determining dynamic risks during vehicle driving based on big data, comprising:

[0162] A task acquisition module, configured to acquire historical data during a vehicle trip, perform edge computing and data preprocessing on the historical data to obtain target data;

[0163] A feature extraction module, configured to extract features from the target data to obtain input features of the target data, where the feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction;

[0164] A dynamic risk assessment module, configured to construct a dynamic risk assessment model, train the dynamic risk assessment model according to the input features of the target data, and the dynamic risk assessment model uses an ARIMA model and an LSTM network model to predict dynamic risks;

[0165] A risk scoring module, configured to generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state;

[0166] An optimized driving strategy module, configured to adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driver's behavior pattern through a Q-learning algorithm.

[0167] The foregoing Figure 1 All the various change modes and specific examples of a method for determining dynamic risks during vehicle driving based on big data in Embodiment 1 are equally applicable to the device for determining dynamic risks during vehicle driving based on big data in this embodiment. Through the foregoing detailed description of a method for determining dynamic risks during vehicle driving based on big data, those skilled in the art can clearly know the implementation method of the device for determining dynamic risks during vehicle driving based on big data in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here.

[0168] Embodiment 3

[0169] The embodiment of the present application provides a computer device, which includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to implement a method for determining dynamic risks during vehicle driving based on big data as provided in the foregoing method embodiment.

[0170] Figure 2The figure shows a schematic hardware structure of a device for implementing a method for determining dynamic risks during vehicle driving provided in an embodiment of the present application. The device may participate in forming or include the device or system provided in the embodiment of the present application. As Figure 2 shown, the computer device 10 may include one or more processors 1002 (the processor may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may further include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those of ordinary skill in the art can understand that Figure 2 the structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the computer device 10 may further include more or fewer components than Figure 2 shown, or have a different configuration from Figure 2 shown.

[0171] It should be noted that the above one or more processors and / or other data processing circuits are generally referred to as "data processing circuits" in this article. The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuit may be a single independent processing module, or be incorporated in whole or in part into any one of other elements in the computer device 10 (or mobile device). As involved in the embodiments of the present application, the data processing circuit is a kind of processor control (such as the selection of a variable resistor terminal path connected to an interface).

[0172] The memory 1004 may be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to a method for determining dynamic risks during vehicle driving based on big data in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implements the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may further include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 1004 may further include a memory remotely set relative to the processor, and these remote memories may be connected to the computer device 10 through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] The transmission device 1006 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0174] The display can be, for example, a touch-screen liquid crystal display (LCD), which enables the user to interact with the user interface of the computer device 10 (or mobile device).

[0175] Embodiment 4

[0176] The embodiment of the present application also provides a computer-readable storage medium, which can be arranged in a server to store at least one instruction or at least one segment of program related to a method for determining dynamic risks during vehicle driving based on big data in the method embodiment. The at least one instruction or the at least one segment of program is loaded and executed by the processor to implement the method for determining dynamic risks during vehicle driving based on big data provided by the above method embodiment.

[0177] Optionally, in this embodiment, the above storage medium can be located in at least one of multiple network servers in a computer network. Optionally, in this embodiment, the above storage medium can include, but is not limited to: various media that can store program codes such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0178] Embodiment 5

[0179] The embodiment of the present invention also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method for determining dynamic risks during vehicle driving based on big data provided in the above various optional implementation manners.

[0180] It should be noted that: The above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of the present application have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0181] Each embodiment in the present application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and storage medium, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description of the method embodiments.

[0182] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disk, etc.

[0183] Taking the above ideal embodiments based on the present invention as inspiration, through the above description, relevant staff can, without departing from the technical idea of the present invention, make various changes and modifications. The technical scope of the present invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

[0184] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for determining dynamic risks during vehicle driving based on big data, characterized in that, It includes the following steps: Obtain historical data during the vehicle journey, perform edge computing and data preprocessing on the historical data to obtain target data, where the historical data includes vehicle internal data, external environment data, big data platform data, and driving behavior data; Based on the target data, perform feature extraction to obtain input features of the target data, and the feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction; Construct a dynamic risk assessment model, and train the dynamic risk assessment model according to the input features of the target data. The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks; Generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state, specifically including: The risk score calculates the current risk using the risk score formula, and the expression is: ； Among them, is the comprehensive risk score, is the weight of the feature, is the impact of feature i on the risk; For the real-time warning, the threshold judgment formula is: ； For evaluating the safety level of the current driving state, the expression is: ； Among them, is the safety level evaluation value at time ; is the driving speed at time ; is the acceleration at time ; is the driving distance at time ; is the driving state. is a weight coefficient obtained through model training; Adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driver's behavior pattern through the Q-learning algorithm; Data encryption and privacy protection: Encryption technology: Use end-to-end encryption to protect the security of data transmission and prevent data from being accessed or tampered with without authorization; ； Among them, is the encrypted data, is the encryption function, is the encryption key, is the original data.

2. The method according to claim 1, wherein: Perform edge computing and data preprocessing on the historical data to obtain target data, specifically including: Perform preliminary data processing on the in-vehicle computing platform, and use edge computing nodes to perform preliminary analysis and processing on the data; Data preprocessing: Clean and normalize the data, handle missing values and outliers, and perform feature extraction of acceleration and speed. The expression is: ； ； wherein, is the acceleration value of the i-th measurement; is the velocity value of the i-th measurement, is the average velocity, average acceleration.

3. The method according to claim 1, characterized in that: The input features of the target data include speed, acceleration, vehicle distance, road conditions, and weather; the high-dimensional feature space is reduced through the PCA (Principal Component Analysis) feature extraction algorithm. The expression is: ； Among them, is the data matrix, is the principal component matrix.

4. The method according to claim 1, characterized in that: The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks, specifically including: The ARIMA model is a random forest, and the expression is: ； where is the prediction result of the $i$-th decision tree for the input $x$, is the number of decision trees; The LSTM network model, the expression is: ； wherein is the hidden state at the current time step t, is the input data at the current time step t, is the hidden state at the previous time step t.

5. The method according to claim 1, wherein: Optimize the driver's behavior pattern through the Q-learning algorithm. The expression is: ； Among them, is the action-value function for taking action a in state s, is the immediate reward, is the discount factor, is the learning rate; is the next state the agent enters after taking action a; in the next state is the action taken; In the next state among all actions, the maximum action-value function value.

6. The method according to claim 1, characterized in that: The time series feature extraction is to extract the dynamic features of the vehicle; the environmental feature extraction is to extract the features of environmental changes, and the behavior pattern extraction is the pattern of the driver's behavior.

7. A device for determining dynamic risks during vehicle driving based on big data, characterized in that It includes: A task acquisition module, which is used to obtain historical data during the vehicle journey, perform edge computing and data preprocessing on the historical data to obtain target data; A feature extraction module, which is used to perform feature extraction on the target data to obtain input features of the target data, and the feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction; A dynamic risk assessment module, which is used to construct a dynamic risk assessment model and train the dynamic risk assessment model according to the input features of the target data. The dynamic risk assessment model uses the ARIMA model and the LSTM network model to predict dynamic risks; A risk scoring module, which is used to generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state; An optimized driving strategy module, which is used to adjust the model warning parameters according to the real-time data and the risk assessment results, and optimize the driver's behavior pattern through the Q-learning algorithm.

8. A computer device, characterized in that, Comprising: A processor; A memory for storing executable instructions; Wherein, the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for determining dynamic risks during vehicle driving based on big data as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the processor is caused to implement the method for determining dynamic risks during vehicle driving based on big data as described in any one of claims 1 to 6.

Images