Vehicle control method and vehicle

Abstract

The invention relates to a vehicle control method and a vehicle, and is applied to the field of vehicle driving technology application. The vehicle control method comprises the steps of obtaining multi-dimensional perception data and time sequence change data, conducting prediction based on the multi-dimensional perception data and the time sequence change data to obtain a current risk index of a vehicle, and triggering early warning operation corresponding to the risk level based on the risk level to which the current risk index belongs. And meanwhile, the vehicle is controlled to execute emergency operation corresponding to the risk level. Therefore, risk prediction is carried out by integrating the multi-dimensional data of the environment, the vehicle and the driver and the time sequence change data, risk perception can be carried out in a cross-dimension manner, the false alarm rate is reduced, risk pre-identification is realized by predicting the current risk index, and cooperation of early warning and execution is realized by triggering early warning operation and controlling the vehicle to execute emergency operation. And the overall response efficiency of the system is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle driving technology applications, and in particular to a vehicle control method and a vehicle. Background Technology

[0002] Currently, in the field of vehicle active safety technology, vehicle active safety warning systems mainly rely on real-time data monitoring of the vehicle itself and its surrounding environment to identify immediate risks. Their warning time is usually only 0.5 to 1 second, which is insufficient to provide drivers with enough reaction time.

[0003] While existing early warning systems employ multiple sensors, insufficient data fusion from these sensors hinders cross-dimensional risk perception, resulting in a high false alarm rate. Furthermore, current solutions primarily focus on presenting warning information, lacking proactive protection mechanisms. They fail to adjust vehicle status proactively to enhance safety redundancy before danger occurs, leading to delayed emergency response and failing to meet the growing demands for advanced active safety. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a vehicle control method and a vehicle.

[0005] A first aspect of this disclosure provides a vehicle control method, including: Acquire multidimensional sensing data and time-series change data, wherein the multidimensional sensing data includes environmental data, vehicle operation data, and driver status data; Based on the multi-dimensional perception data and the time-series change data, a prediction is made to obtain the vehicle's current risk index. Based on the risk level of the current risk index, a warning operation corresponding to the risk level is triggered, and the vehicle is controlled to perform an emergency operation corresponding to the risk level.

[0006] In some embodiments of this disclosure, acquiring multidimensional sensing data includes: The environmental data is obtained by acquiring surrounding vehicle data, road information, and meteorological parameters through vehicle-road cooperative components; The vehicle's operating data is obtained by collecting operating parameters of the engine, braking, steering, and suspension systems via the controller area network bus. The driver's state data is obtained by collecting data on the driver's facial expression, steering wheel grip strength, and heart rate through in-vehicle sensors. The multidimensional perception data is constructed based on the environmental data, the vehicle operation data, and the driver status data.

[0007] In some embodiments of this disclosure, obtaining the vehicle's current risk index based on the multidimensional sensing data and the time-series change data includes: The multidimensional sensing data and the time-series change data are input into the time-series prediction model to obtain the risk factors for the future time period. The current risk index of the vehicle is calculated based on the multidimensional perception data and the risk factors.

[0008] In some embodiments of this disclosure, the calculation of the vehicle's current risk index based on the multidimensional perception data and the risk factors includes: The preset weight configuration is adjusted based on the multidimensional sensing data to obtain the target weight configuration; Based on the target weight configuration, the multidimensional perception data and the risk factors are weighted and fused to calculate the current risk index.

[0009] In some embodiments of this disclosure, adjusting the preset weight configuration based on the multidimensional sensing data to obtain the target weight configuration includes: Construct an initial weight model that includes environmental, vehicle, and driver dimensions; Based on the multi-dimensional perception data, the similarity between the current driving scenario and the preset driving scenario is calculated; If the similarity between the current driving scenario and the target driving scenario in the preset driving scenario is greater than a preset threshold, then the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration.

[0010] In some embodiments of this disclosure, triggering a warning operation corresponding to the risk level based on the current risk index, and simultaneously controlling the vehicle to perform an emergency operation corresponding to the risk level, includes: When the risk level is the first risk level, a text message and a vibration alert of the first intensity are triggered. When the risk level is the second risk level, a voice prompt, an airflow reminder, and a vibration reminder of the second intensity are triggered, and the vehicle's target execution system is controlled to initiate basic emergency operations; When the risk level is the third risk level, a vibration alert of the third intensity, a hazard warning signal, and a seat compression are triggered, and multiple actuators of the vehicle are controlled to perform coordinated emergency operations.

[0011] In some embodiments of this disclosure, the coordinated emergency operations performed by the multiple execution systems controlling the vehicle include: Control the vehicle's braking system to pre-fill the braking pressure; Control the vehicle's steering system to adjust steering assist parameters; Control the vehicle's suspension system to adjust damping or stiffness; Control the vehicle's powertrain to limit output torque.

[0012] In some embodiments of this disclosure, the method further includes: During vehicle operation, multi-dimensional perception data and corresponding actual risk index are acquired in high-risk scenarios, where the high-risk scenario is a driving scenario where the risk index is greater than a preset risk index threshold. The parameters of the time series prediction model are optimized and updated based on the multidimensional sensing data and the corresponding actual risk index.

[0013] In some embodiments of this disclosure, after triggering the warning operation corresponding to the risk level, the method further includes: Monitor the driver's operational response within a preset time period; If an operation response is detected and the current risk index is less than the preset cancellation threshold, then the warning operation and the emergency operation are cancelled.

[0014] A second aspect of this disclosure provides a vehicle control device, including: The acquisition module is used to acquire multidimensional sensing data and time-series change data, wherein the multidimensional sensing data includes environmental data, vehicle operation data, and driver status data; The module is used to make predictions based on the multidimensional perception data and the time-series change data to obtain the current risk index of the vehicle. The processing module is used to trigger an early warning operation corresponding to the current risk level based on the risk level to which the current risk index belongs, and at the same time control the vehicle to perform an emergency operation corresponding to the risk level.

[0015] In some embodiments of this disclosure, when the acquisition module acquires multidimensional sensing data, it is specifically used for: The environmental data is obtained by acquiring surrounding vehicle data, road information, and meteorological parameters through vehicle-road cooperative components; The vehicle's operating data is obtained by collecting operating parameters of the engine, braking, steering, and suspension systems via the controller area network bus. The driver's state data is obtained by collecting data on the driver's facial expression, steering wheel grip strength, and heart rate through in-vehicle sensors. The multidimensional perception data is constructed based on the environmental data, the vehicle operation data, and the driver status data.

[0016] In some embodiments of this disclosure, when the obtaining module obtains the current risk index of the vehicle based on the multidimensional sensing data and the time-series change data, it is specifically used for: The multidimensional sensing data and the time-series change data are input into the time-series prediction model to obtain the risk factors for the future time period. The current risk index of the vehicle is calculated based on the multidimensional perception data and the risk factors.

[0017] In some embodiments of this disclosure, when the obtaining module calculates the current risk index of the vehicle based on the multi-dimensional perception data and the risk factors, it is specifically used for: The preset weight configuration is adjusted based on the multidimensional sensing data to obtain the target weight configuration; Based on the target weight configuration, the multidimensional perception data and the risk factors are weighted and fused to calculate the current risk index.

[0018] In some embodiments of this disclosure, when the obtaining module adjusts the preset weight configuration based on the multidimensional sensing data to obtain the target weight configuration, it is specifically used for: Construct an initial weight model that includes environmental, vehicle, and driver dimensions; Based on the multi-dimensional perception data, the similarity between the current driving scenario and the preset driving scenario is calculated; If the similarity between the current driving scenario and the target driving scenario in the preset driving scenario is greater than a preset threshold, then the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration.

[0019] In some embodiments of this disclosure, when the processing module triggers a warning operation corresponding to the risk level based on the risk level to which the current risk index belongs, and simultaneously controls the vehicle to perform an emergency operation corresponding to the risk level, it is specifically used for: When the risk level is the first risk level, a text message and a vibration alert of the first intensity are triggered. When the risk level is the second risk level, a voice prompt, an airflow reminder, and a vibration reminder of the second intensity are triggered, and the vehicle's target execution system is controlled to initiate basic emergency operations; When the risk level is the third risk level, a vibration alert of the third intensity, a hazard warning signal, and a seat compression are triggered, and multiple actuators of the vehicle are controlled to perform coordinated emergency operations.

[0020] In some embodiments of this disclosure, when the processing module controls multiple execution systems of the vehicle to perform coordinated emergency operations, it is specifically used for: Control the vehicle's braking system to pre-fill the braking pressure; Control the vehicle's steering system to adjust steering assist parameters; Control the vehicle's suspension system to adjust damping or stiffness; Control the vehicle's powertrain to limit output torque.

[0021] In some embodiments of this disclosure, the apparatus further includes: The update module is used to acquire multi-dimensional perception data and corresponding actual risk index in high-risk scenarios during vehicle operation. The high-risk scenario is a driving scenario where the risk index is greater than a preset risk index threshold. The parameters of the time series prediction model are optimized and updated based on the multidimensional sensing data and the corresponding actual risk index.

[0022] In some embodiments of this disclosure, after triggering the warning operation corresponding to the risk level, the device further includes: The monitoring module is used to monitor the driver's operational response within a preset time period; If an operation response is detected and the current risk index is less than the preset cancellation threshold, then the warning operation and the emergency operation are cancelled.

[0023] A third aspect of this disclosure provides an electronic device, including: processor; Memory, used to store executable instructions; The processor is used to read executable instructions from memory and execute the executable instructions to implement the vehicle control method provided in the first aspect above.

[0024] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the vehicle control method provided in the first aspect.

[0025] A fifth aspect of this disclosure provides a computer program product comprising a computer program or instructions that, when executed by a processor, implement the vehicle control method of the first aspect described above.

[0026] A sixth aspect of this disclosure provides a vehicle that includes electronic equipment provided in the third aspect.

[0027] The technical solution provided in this disclosure has the following advantages: The vehicle control method and vehicle provided in this disclosure can acquire multi-dimensional perception data and time-series change data. The multi-dimensional perception data includes environmental data, vehicle operation data, and driver status data. Furthermore, based on the multi-dimensional perception data and the time-series change data, a prediction is made to obtain the vehicle's current risk index. Then, based on the risk level to which the current risk index belongs, a warning operation corresponding to the risk level is triggered, and the vehicle is simultaneously controlled to perform an emergency operation corresponding to the risk level. Thus, by comprehensively considering multi-dimensional data and time-series change data of the environment, vehicle, and driver for risk prediction, cross-dimensional risk perception can be achieved, reducing the false alarm rate. By predicting the current risk index, proactive risk identification is realized. By triggering warning operations and controlling the vehicle to perform emergency operations, coordination between warning and execution is achieved, improving the overall system response efficiency. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0029] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of this disclosure; Figure 2 This is a flowchart of another vehicle control method provided in this disclosure embodiment; Figure 3 This is a flowchart of yet another vehicle control method provided in this disclosure embodiment; Figure 4 This is a schematic diagram of the overall architecture of a vehicle control system provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the architecture of the time series prediction model provided in the embodiments of this disclosure; Figure 6 This is a schematic diagram of the collaborative emergency response process provided in the embodiments of this disclosure; Figure 7 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this disclosure; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0031] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0032] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0033] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0034] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0035] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0036] Currently, in the field of vehicle active safety technology, vehicle active safety warning systems mainly rely on real-time data monitoring of the vehicle itself and its surrounding environment to identify immediate risks. Their warning time is usually only 0.5 to 1 second, which is insufficient to provide drivers with enough reaction time.

[0037] While existing early warning systems employ multiple sensors, insufficient data fusion from these sensors hinders cross-dimensional risk perception, resulting in a high false alarm rate. Furthermore, current solutions primarily focus on presenting warning information, lacking proactive protection mechanisms. They cannot proactively adjust vehicle status to enhance safety redundancy before a hazard occurs, failing to meet the growing demands for advanced active safety. Therefore, this disclosure provides a vehicle control method, which will be described below with reference to specific embodiments.

[0038] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of the present disclosure. The method can be executed by a vehicle control device, which can be implemented in software and / or hardware. The vehicle control device can be configured in an electronic device, such as a server or terminal, wherein the terminal specifically includes an in-vehicle terminal, a computer, or a tablet computer, etc.

[0039] like Figure 1 As shown, the vehicle control method provided in this disclosure can be applied to the field of vehicle driving technology applications. For example, it can be used to provide early warning of driving risks. Figure 4 This is a schematic diagram of the overall architecture of a vehicle control system provided in this disclosure embodiment. The following is in conjunction with... Figure 4 The vehicle control method provided in this disclosure includes the following steps: S110. Acquire multi-dimensional sensing data and time-series change data. Multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data.

[0040] In this embodiment of the disclosure, the electronic device acquires multi-dimensional sensing data and time-series change data. Optionally, the multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data. Figure 4 As shown, multidimensional sensing data and time-series change data can be acquired through a multidimensional data acquisition module. Specifically, data can be collected in real time from multiple dimensions using various sensors and communication units. Time-series change data is obtained by caching historical sequences of multidimensional sensing data within a recent period (e.g., 3 seconds) and calculating the change trends and rates of change for each data dimension (e.g., the rate of change of the deceleration of the vehicle in front, the upward trend of the driver's heart rate over the past 10 seconds). This time-series data is a key input for predicting future risks.

[0041] S120: Based on multi-dimensional perception data and time-series change data, a prediction is made to obtain the current risk index of the vehicle.

[0042] In this embodiment of the disclosure, after acquiring multidimensional sensing data and time-series change data, the electronic device can make predictions based on the multidimensional sensing data and time-series change data to obtain the vehicle's current risk index. In some embodiments, a multidimensional feature vector can be constructed based on the multidimensional sensing data and time-series change data, and the multidimensional feature vector can be input into a pre-trained risk index prediction model to obtain the vehicle's current risk index. Optionally, the current risk index is a percentage, with a value range of 0 to 100%.

[0043] S130. Based on the risk level of the current risk index, trigger the warning operation corresponding to the risk level, and at the same time control the vehicle to perform the emergency operation corresponding to the risk level.

[0044] In this embodiment of the disclosure, multiple risk levels are preset. The electronic device can trigger the warning operation corresponding to the risk level based on the current risk index, output the warning information matching the level to the driver, and at the same time control the vehicle to perform the emergency operation corresponding to the risk level. It sends control commands to one or more underlying execution systems of the vehicle (such as braking, steering, suspension, power system) to make it enter the preparation state matching the risk level or perform restrictive operations, so as to prepare for possible emergency intervention without interfering with the driver's current normal operation.

[0045] Therefore, in this embodiment, multi-dimensional sensing data and time-series change data can be acquired. The multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data. Furthermore, based on the multi-dimensional sensing data and time-series change data, a prediction is made to obtain the vehicle's current risk index. Then, based on the risk level of the current risk index, a warning operation corresponding to the risk level is triggered, and the vehicle is simultaneously controlled to perform an emergency operation corresponding to the risk level. Thus, by comprehensively considering multi-dimensional data and time-series change data from the environment, vehicle, and driver for risk prediction, cross-dimensional risk perception can be achieved, reducing the false alarm rate. By predicting the current risk index, proactive risk identification is realized. By triggering warning operations and controlling the vehicle to perform emergency operations, coordination between warning and execution is achieved, improving the overall system response efficiency.

[0046] Optionally, S110 may specifically include S1101, S1102, S1103, and S1104: S1101. Obtain surrounding vehicle data, road information, and meteorological parameters through the vehicle-road cooperative component to obtain the environmental data; In this step, road information up to 3 kilometers ahead can be obtained through vehicle-to-infrastructure (V2V) components such as roadside units. Data exchange can be performed via vehicle-to-vehicle (V2V) communication to acquire surrounding vehicle data. Meteorological parameters are collected using micro-weather sensors, and real-time traffic events are obtained through a traffic cloud platform, thus yielding environmental data. Figure 4 As shown, the environment submodule is used to acquire road, traffic, and weather data through V2X (vehicle-to-everything) and meteorological sensors; the vehicle submodule is used to acquire the status of braking, steering, suspension, and power systems through the CAN bus and dedicated sensors; the driver submodule is used to monitor the driver's fatigue, distraction, and tension through cameras and biosensors; the time-series auxiliary submodule does not directly collect new data, but is used to process the historical sequences of the first three types of data, calculate the changing trends (such as acceleration, heart rate change rate, etc.), and provide time-series features for prediction.

[0047] S1102. The operating parameters of the engine, braking, steering and suspension systems are collected through the controller local area network bus to obtain the vehicle operating data; In this step, operating parameters of the engine, braking, steering, and suspension systems are collected via the CAN bus to obtain vehicle operating data. For example, engine speed and torque are read from the engine control unit (sampling frequency 10Hz), brake pressure and brake pedal travel are read from the braking system (using Omron sensors, accuracy ±0.1mm), vehicle height, damping status, and suspension stiffness are read from the suspension system (electromagnetic suspension with built-in pressure sensors, measurement range 0-5MPa), and steering angle and steering torque are read from the steering system.

[0048] S1103. Collect driver's facial state, steering wheel grip force and heart rate data through in-vehicle sensors to obtain the driver state data.

[0049] In this step, facial features are captured by a camera, steering wheel grip force is collected by a grip force sensor (sampling frequency 10Hz), and heart rate data is collected by a heart rate sensor to obtain driver status data. Specifically, the driver-facing built-in camera uses image recognition algorithms to detect the driver's facial features and determine whether the driver is fatigued (e.g., abnormal duration of eye closure or blinking frequency) or distracted (e.g., gaze deviating from the road ahead); the grip force sensor on the steering wheel detects the magnitude and stability of the driver's hand grip; and biosensors integrated into the seat or steering wheel monitor the driver's heart rate, skin conductance, and other physiological signals.

[0050] S1104. Based on the environmental data, the vehicle operation data, and the driver status data, construct the multi-dimensional perception data.

[0051] In this step, after obtaining the environmental data, the vehicle operation data, and the driver status data, the multidimensional perception data can be constructed based on the environmental data, the vehicle operation data, and the driver status data, providing a high-quality data foundation for risk prediction.

[0052] Therefore, in this embodiment of the disclosure, by collecting environmental data through the vehicle-road cooperative component, vehicle operation data through the CAN bus, and driver status data through in-vehicle sensors, the comprehensiveness, real-time nature, and accuracy of the collected data are ensured, laying a reliable data foundation for subsequent accurate risk calculation.

[0053] Figure 2 This is a flowchart of another vehicle control method provided in this embodiment.

[0054] like Figure 2 As shown, the vehicle control method may include the following steps: S310. Acquire multi-dimensional sensing data and time-series change data. Multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data.

[0055] Specifically, the implementation process and principle of S310 and S110 are the same, and will not be repeated here.

[0056] S320. Input multidimensional sensing data and time-series change data into the time-series prediction model to obtain risk factors for future time periods.

[0057] Specifically, electronic devices are pre-trained with time-series prediction models, which can input multi-dimensional sensing data and time-series change data into the prediction models to obtain risk factors for future time periods. For example... Figure 4 As shown, the time-series risk prediction module can receive a data stream with time-series information from the multi-dimensional data acquisition module. Using a time-series prediction model, the changing patterns of the data are analyzed to predict risk factors within a future time period. For example, feature vectors are constructed from multi-dimensional sensing data and time-series change data. The time-series prediction model analyzes the input feature vectors and outputs predicted values ​​for key risk factors within a future time period (e.g., 3-5 seconds). Examples include predicting "the probability of a target vehicle ahead braking suddenly within the next 3 seconds," "the boundary margin for the vehicle to maintain stable driving under current road conditions," and "the likelihood of driver fatigue worsening within the next 5 seconds." Optionally, the time-series prediction model can be an LSTM model, without specific limitations. Figure 5 As shown, the input layer of the time-series prediction model is a 3-second × 12-dimensional feature vector (4-dimensional environment + 4-dimensional vehicle + 3-dimensional driver + 1-dimensional time series), the hidden layer has 64 neurons, the attention mechanism layer has 32 weighted neurons, and the output layer is the predicted value of risk factors for the next 3-5 seconds, with a prediction error ≤ 5%.

[0058] Specifically, the 12-dimensional feature vector can be: 1) Environment: road friction coefficient, visibility, V2V interaction vehicle speed, traffic event level; 2) Vehicle: brake fade coefficient, suspension stiffness, steering clearance, power response delay; 3) Driver: heart rate, grip strength, fatigue level, operation deviation; 4) Time series: rate of change of multi-dimensional perception data.

[0059] S330 calculates the vehicle's current risk index based on multi-dimensional perception data and risk factors.

[0060] In this step, the electronic device calculates the vehicle's current risk index based on multi-dimensional perception data and risk factors. Specifically, based on current real-time multi-dimensional perception data (reflecting the current state) and model-predicted risk factors (reflecting future trends), a preset fusion algorithm (such as weighted summation or neural network fusion) is used to calculate and ultimately generate a comprehensive, quantitative current risk index. This index is used to characterize the overall risk level faced by the vehicle currently and in the near future.

[0061] This disclosure introduces a time-series prediction model, which takes multidimensional data and time-series change data as input. The model can capture dynamic trends and output risk factors, providing a basis for risk index calculation. This enables the vehicle system to not only focus on the current state, but also to infer short-term future trends, thereby extending the warning window from the immediate to the future time period, and giving the driver and vehicle system valuable additional reaction time.

[0062] In some embodiments, S330 specifically includes S3301 and S3302: S3301. Adjust the preset weight configuration based on multi-dimensional perception data to obtain the target weight configuration.

[0063] In this embodiment of the disclosure, the preset weight configuration can be: 30% for the environmental dimension, 30% for the vehicle dimension, and 40% for the driver dimension. The electronic device can adjust the preset weight configuration based on multi-dimensional perception data to obtain the target weight configuration. Figure 4 As shown, the self-learning weight modeling module can dynamically adjust the weights of the three dimensions of data—environment, vehicle, and driver—in risk assessment based on the current driving scenario (e.g., rainy nighttime highway). For example, the weight of "environment-road friction coefficient" will automatically increase in rainy weather.

[0064] S3302. Based on the target weight configuration, the multi-dimensional perception data and risk factors are weighted and fused to calculate the current risk index.

[0065] In this step, the electronic device performs weighted fusion of multi-dimensional perceived data and risk factors according to the target weight configuration to calculate the current risk index. Specifically, it calculates the risk values ​​of environmental data, vehicle operation data, and driver status data, and also calculates the risk values ​​of risk factors. Furthermore, it performs weighted fusion of the risk values ​​of environmental data, vehicle operation data, driver status data, and risk factors to calculate the current risk index. Optionally, the risk index = (weighted sum of multi-dimensional perceived data and the weights of each dimension) × first proportional coefficient + (risk factor × second proportional coefficient). The first proportional coefficient can be 60%, and the second proportional coefficient can be 40%, which is not limited here.

[0066] By using a weight adjustment mechanism, the weights of each dimension are dynamically adjusted according to different scenarios, which improves the accuracy and scenario adaptability of risk index calculation and reduces misjudgments or omissions caused by fixed weights.

[0067] S340: Based on the risk level of the current risk index, trigger the warning operation corresponding to the risk level, and at the same time control the vehicle to perform the emergency operation corresponding to the risk level.

[0068] Specifically, the implementation process and principle of S340 and S130 are the same, and will not be repeated here.

[0069] In some embodiments, after triggering the warning operation corresponding to the risk level, the method further includes: monitoring the driver's operation response within a preset time; if an operation response is detected and the current risk index is less than a preset cancellation threshold, then canceling the warning operation and the emergency operation.

[0070] In this embodiment, the electronic device monitors the driver's operational response within a preset time. If an operational response is detected and the current risk index is less than a preset cancellation threshold, the warning operation and the emergency operation are cancelled. For example, the driver's operational response (such as braking or steering correction) is monitored within 0.5 seconds after the warning is triggered. If no effective response is detected, the warning intensity is increased by one level and the emergency operation intervention depth is increased every 0.3 seconds; if a response is detected and the risk index drops below 30%, the warning and emergency operation are gradually cancelled. This embodiment achieves human-machine collaboration by monitoring the driver's response and dynamically adjusting the warning status, avoiding continuous system interference with normal driving.

[0071] S350: During vehicle operation, acquire multi-dimensional perception data and corresponding actual risk indices for high-risk scenarios. High-risk scenarios are driving scenarios where the risk index is greater than a preset risk index threshold.

[0072] In this step, the electronic device continuously collects multi-dimensional perception data and corresponding actual risk indices for high-risk scenarios. For example, on a mountain curve, an oncoming vehicle crosses the line, triggering an emergency warning and successfully assisting the driver in avoiding the collision. This event is marked as a high-risk scenario. The electronic device will fully record all multi-dimensional perception data and actual risk indices for a period of time before and after the event (e.g., from 5 seconds before the warning to 3 seconds after the warning).

[0073] S360 optimizes and updates the parameters of the time series prediction model based on multi-dimensional perception data and the corresponding actual risk index.

[0074] In this step, the electronic device does not update using a single set of data, but rather accumulates data. For example, after driving 100 kilometers or accumulating more than 50 sets of valid high-risk scenario data, a batch learning process is initiated. This collected high-risk scenario data (including perceived data and actual risk indices) is used as new training samples. Machine learning algorithms (such as gradient descent) are employed to fine-tune and optimize the internal parameters of the time-series prediction model using these new samples. The goal of optimization is to make the model's prediction output for these high-risk scenarios closer to the actual risk index, thereby reducing prediction errors.

[0075] This embodiment acquires multi-dimensional sensing data and time-series change data, including environmental data, vehicle operation data, and driver status data. This multi-dimensional sensing data and time-series change data are input into a time-series prediction model to obtain risk factors for future time periods. Furthermore, based on the multi-dimensional sensing data and risk factors, a current risk index for the vehicle is calculated. Based on the risk level of the current risk index, a warning operation corresponding to the risk level is triggered, and the vehicle is simultaneously controlled to perform emergency operations corresponding to the risk level. Moreover, during vehicle operation, multi-dimensional sensing data and corresponding actual risk indices for high-risk scenarios are acquired, and the parameters of the time-series prediction model are optimized and updated based on this data. Therefore, by continuously collecting data and optimizing the model during actual driving, the system's prediction accuracy and risk assessment capabilities can continuously improve with increased usage time and mileage, solving the problem of traditional system algorithms being fixed and unable to be continuously improved.

[0076] Figure 3 This is a flowchart of another vehicle control method provided in this disclosure.

[0077] like Figure 3 As shown, the vehicle control method may include the following steps: S410: Acquire multi-dimensional sensing data and time-series change data. Multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data.

[0078] Specifically, the implementation process and principle of S410 and S110 are the same, and will not be repeated here.

[0079] S420. Input multidimensional sensing data and time-series change data into the time-series prediction model to obtain risk factors for future time periods.

[0080] Specifically, the implementation process and principle of S420 and S320 are the same, and will not be repeated here.

[0081] S430. Construct an initial weight model that includes the dimensions of environment, vehicle, and driver.

[0082] In this step, an initial weight model will be constructed that includes the dimensions of environment, vehicle, and driver. For example, the initial weight model might have 30% for the environment dimension, 30% for the vehicle dimension, and 40% for the driver dimension; no specific limit is set here.

[0083] Optionally, the initial weight model can be trained using 1000 sets of sample data.

[0084] S440. Based on multi-dimensional perception data, calculate the similarity between the current driving scenario and the preset driving scenario.

[0085] Specifically, electronic devices can calculate the similarity between the current driving scenario and a preset driving scenario based on multi-dimensional perception data. For example, if the current scenario corresponding to the multi-dimensional perception data is "highway in rainy weather", the current multi-dimensional perception data (low visibility, low adhesion coefficient, high vehicle speed) is matched with the preset driving scenario to calculate the similarity between the current scenario and the preset driving scenario.

[0086] Optionally, preset driving scenarios may include urban traffic jams, fatigued driving on suburban roads, highway driving in rainy weather, asphalt road curves, sudden crossing at urban intersections, and vehicle breakdowns on mountain curves, without specific limitations.

[0087] Scenario 1: Urban traffic jam following scenario (warning level: risk index 30%-50%), environmental conditions: dry asphalt road, visibility ≥200 meters (sunny day), vehicle speed 10-30km / h (frequent starts and stops of the vehicle in front); vehicle conditions: brake fade coefficient ≤0.1 (normal braking system), suspension stiffness 28-32N / mm (normal setting), steering clearance ≤3° (normal steering system), power response delay ≤0.3 seconds (normal power system); driver conditions: heart rate 60-90 beats / minute (normal), grip strength 30-40N (stable), fatigue level 1 (no fatigue), operation deviation ≤5% (reasonable following distance control, no frequent acceleration and deceleration).

[0088] Scenario 2: Suburban road fatigue driving scenario (warning level: risk index 50%-80%), environmental conditions: light dust, visibility 150-200 meters (evening), V2V interactive vehicle speed 60-80km / h (sparse traffic), traffic incident level 1; vehicle conditions: brake fade coefficient 0.1-0.2 (slight fade), suspension stiffness 28-32N / mm, steering clearance ≤3°, power response delay ≤0.3 seconds; driver conditions: heart rate 55-70 beats / minute (slow, lack of concentration), grip strength 20-30N (relaxed), fatigue level 3 (continuous driving ≥4 hours), operation deviation 10%-15% (frequent line crossing, inconsistent following distance).

[0089] Scenario 3: Highway driving in rainy weather (Warning level: Risk index 50%-80%), slippery road surface, visibility 50-100 meters (moderate to heavy rain), vehicle speed 80-100km / h (highway traffic), traffic incident level 2 (local road section water accumulation, no accidents); vehicle status: brake fade coefficient ≤0.1, suspension stiffness 28-32N / mm, steering clearance ≤3°, power response delay ≤0.3 seconds; driver status: heart rate 80-100 beats / minute (slightly tense), grip strength 35-45N (firmly gripping the steering wheel), fatigue level 2 (continuous driving for 2-3 hours), operation deviation 8%-12% (occasionally correcting the direction, increased braking frequency).

[0090] Scenario 4: Sudden crossing of a curved asphalt road / urban intersection / vehicle malfunction on a mountain curve (emergency warning: risk index ≥ 80%), some fallen leaves, visibility 100-150 meters (cloudy), vehicle speed 40-60 km / h (oncoming traffic), traffic incident level 2 (no construction, limited visibility on the curve); vehicle status: brake fade coefficient ≥ 0.3 (brake system malfunction, reduced braking force), suspension stiffness ≥ 35 N / mm (abnormally stiff suspension), steering clearance ≥ 5° (loose steering system), power response delay ≥ 0.5 seconds (power output lag); driver status: heart rate 100-120 beats / minute (nervous), grip strength 40-50 N (gripping the steering wheel tightly), fatigue level 1, operation deviation 15%-20% (frequent sharp turns, emergency braking).

[0091] S450. If the similarity between the current driving scenario and the target driving scenario in the preset driving scenario is greater than the preset threshold, then the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration.

[0092] In this step, if the similarity between the current driving scenario and the target driving scenario in the preset driving scenarios is greater than a preset threshold, the weights of each dimension in the initial weight model will be fine-tuned based on the weight configuration data of the target driving scenario to obtain the target weight configuration. Optionally, the weight adjustment range in a single instance shall not exceed 10%. For example, if the similarity between the current driving scenario and the target driving scenario is calculated to be 85%, and the preset threshold is 70%, the environmental dimension weight in the target driving scenario is adjusted to 50%, the vehicle dimension to 35%, and the driver dimension to 15%. This is because external environmental risks dominate in this scenario, and the electronic device will fine-tune the initial weights, for example, slightly increasing the environmental weight from 30% to 35%, the vehicle weight from 30% to 33%, and the driver weight from 40% to 32%, thus obtaining the target weight configuration. Because the environmental risk weight is appropriately increased, the negative impacts of slippery roads and low visibility are more fully accounted for, allowing the calculated current risk index to more accurately reflect the special risks of highways in rainy weather.

[0093] By calculating the similarity between the current driving scenario and the preset driving scenario, the initial weights are further adjusted, so that the risk calculation model is no longer static and general, but can intelligently adjust the assessment focus according to different driving scenarios (such as sunny / rainy days, city / highway), which significantly improves the accuracy and scenario adaptability of risk index calculation and reduces misjudgment or omission caused by fixed weights.

[0094] S460. Based on the target weight configuration, multi-dimensional perception data and risk factors are weighted and fused to calculate the current risk index.

[0095] Specifically, the implementation process and principle of S460 and S3302 are the same, and will not be repeated here.

[0096] S470. When the risk level is the highest, trigger a text message and a vibration alert of the highest intensity.

[0097] Optionally, the first risk level can be designated as a warning level, corresponding to a risk index of 30%-50%. In this case, a text message will be displayed on the screen, and a vibration alert of the highest intensity will be triggered. For example... Figure 4 As shown, the risk level is divided into three levels—first risk level, second risk level, and third risk level—based on the current risk index by the graded early warning module, and a clear risk level signal (such as "third-level early warning signal") and specific early warning instructions are output.

[0098] S480: When the risk level is the second risk level, trigger a voice prompt, airflow warning, and vibration warning of the second intensity, and control the vehicle's target execution system to initiate basic emergency operations.

[0099] Optional, such as Figure 6 As shown, the second risk level can be a warning level, corresponding to a risk index of 50%-80%. At this time, a voice prompt is triggered (e.g., "Slippery road ahead, please maintain a safe distance"), and simultaneously, an airflow is released through the air conditioning vents to remind the driver's face, and a second-intensity vibration alert (e.g., seat vibration, steering wheel vibration) is activated, with the second intensity being greater than the first. At the same time, the vehicle's target execution system initiates basic emergency operations. The target execution system includes the braking system and / or steering system.

[0100] S490: When the risk level is the third risk level, trigger the third intensity of vibration alert, hazard warning signal and seat compression, and control multiple actuators of the vehicle to perform coordinated emergency operations.

[0101] Optional, such as Figure 6 As shown, the third risk level can be classified as dangerous, with a risk index greater than 80%. At this level, a third-intensity vibration alert, hazard warning signal, and seat compression are triggered, with the second intensity being greater than the third intensity. This triggers multiple vehicle actuators to coordinate emergency operations. These actuators include the braking system, steering system, suspension system, and powertrain system. Figure 6 This is a schematic diagram of the collaborative emergency response process provided in the embodiments of this disclosure, such as... Figure 6 As shown, upon receiving a risk level signal, the central controller distributes specific control commands to each execution unit. The braking system execution unit performs corresponding brake pressure pre-filling based on the warning level signal; for example, at the second risk level (warning level), it performs a 1.5 times pre-fill pressure; at the third risk level (emergency level), it performs a 2 times pre-fill pressure. The steering system execution unit adjusts the steering assist based on the warning level, making steering more sensitive or stable in emergency situations; for example, at the second risk level (warning level), steering assist is increased by 20%; at the third risk level (emergency level), steering assist is increased by 40%. The suspension system execution unit increases suspension stiffness according to commands to suppress nose-diving during emergency braking or body roll during emergency steering; for example, at the second risk level (warning level) or the third risk level (emergency level), suspension stiffness is increased by 25%. The powertrain execution unit is mainly used to limit engine torque output and assist deceleration at the third risk level, for example, limiting torque to 70%. It should be noted that the specific values ​​mentioned above are for illustrative purposes only, and other values ​​may also be used, without any specific limitations here.

[0102] In some embodiments, multiple actuators controlling the vehicle in S490 perform coordinated emergency operations, including S4901, S4902, S4903, and S4904: S4901, Control the vehicle's braking system to pre-fill the braking pressure; In this step, such as Figure 6 As shown, the vehicle's braking system is pre-filled with brake pressure, increasing the master cylinder pressure to 1.5 times the normal value. This significantly reduces the braking response delay when the driver actually needs to brake urgently. The purpose of brake pressure pre-filling is to eliminate the "initial response delay" in traditional hydraulic braking systems, thereby achieving maximum braking force "instantaneously" when the driver actually presses the brake pedal or the automatic emergency braking system is triggered. Brake pressure pre-filling includes the following steps: 1) Active pressure build-up: The motor in the brake controller drives the hydraulic pump to actively inject a small amount of brake fluid into the wheel cylinder lines. 2) Eliminating gaps: This pressure is sufficient to push the brake caliper piston, causing the brake pads to slightly, just barely, contact the brake disc (but without generating significant frictional braking force to avoid interfering with normal driving). At this time, the brake pedal may have a very slight sinking sensation (which the driver usually cannot perceive). 3) Maintaining pressure: The system maintains a low "standby" pressure in the lines. When emergency braking is triggered, such as when the driver presses the brake pedal, the braking force can be established linearly and rapidly the instant the driver presses the pedal because the gap has been eliminated and there is already a base pressure in the lines, with almost zero response delay. For example, when automatic emergency braking is activated, the system directly uses the established pre-pressure as a starting point, quickly increasing the pressure to the high pressure required for full braking, achieving a much faster response speed than building pressure from zero. By pre-filling the brake pressure, braking response time can be shortened, response speed can be improved, thereby shortening braking distance and improving safety.

[0103] S4902, Control the vehicle's steering system and adjust the steering assist parameters; In this step, such as Figure 6 As shown, the steering system controls the vehicle's steering assist parameters to adjust the steering assist force appropriately (e.g., by 10%), making the steering wheel feel slightly heavier. This enhances the perception of directional stability on high-speed, slippery roads and prevents the driver from making unconscious, large steering maneuvers.

[0104] S4903, Control the vehicle's suspension system to adjust damping or stiffness; In this step, such as Figure 6 As shown, the vehicle's suspension system is controlled to adjust damping or stiffness, setting the suspension to a firmer sport mode to improve the vehicle's body posture control during emergency lane changes.

[0105] S4904, Controls the vehicle's power system to limit output torque.

[0106] In this step, such as Figure 6 As shown, the vehicle's power system limits the output torque, restricting the maximum available torque of the electric motor or engine to 90% of the normal value to prevent the drive wheels from slipping during rapid acceleration.

[0107] This disclosed embodiment shortens braking response time through brake pre-filling, enhances handling through improved steering assist, and improves vehicle stability in emergency situations through suspension and powertrain coordination. This multi-system coordinated contingency plan can optimize the vehicle's power, braking, and handling before a hazard occurs, adjusting the vehicle to its optimal readiness state. As a result, when the driver takes emergency actions, the vehicle can respond faster, more stably, and more controllably, greatly increasing the upper limit of its ability to actively avoid obstacles or stabilize the vehicle body.

[0108] In some embodiments, the method further includes the following steps after triggering the warning operation: monitoring the driver's operation response within a preset time; if no effective response is detected, gradually increasing the warning intensity and increasing the intervention depth of the emergency operation; if an effective response is detected and the risk index drops below the cancellation threshold, canceling the warning and emergency operation.

[0109] This embodiment of the disclosure acquires multi-dimensional perception data and time-series change data, inputs the multi-dimensional perception data and time-series change data into a time-series prediction model to obtain risk factors for a future time period. Then, an initial weight model including environmental, vehicle, and driver dimensions is constructed. Based on the multi-dimensional perception data, the similarity between the current driving scenario and a preset driving scenario is calculated. If the similarity between the current driving scenario and a target driving scenario in the preset driving scenario is greater than a preset threshold, the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration. Further, based on the target weight configuration, the multi-dimensional perception data and risk factors are weighted and fused to calculate the current risk index. Then, when the risk level is the first risk level, text information and a vibration alert of the first intensity are triggered; or, when the risk level is the second risk level, voice prompts, airflow reminders, and a vibration alert of the second intensity are triggered, and the vehicle's target execution system is controlled to initiate basic emergency operations; or, when the risk level is the third risk level, a vibration alert of the third intensity, a hazard warning signal, and seat compression are triggered, and multiple execution systems of the vehicle are controlled to perform coordinated emergency operations. Therefore, through a tiered early warning and coordinated response mechanism, multi-level warnings correspond to different risk levels, with response intensity gradually escalating. By coordinating the early warning and execution systems, driving safety and response timeliness are improved. Different risk levels correspond to different intensities of sensory warnings and varying degrees of vehicle system emergency operations. This tiered intervention approach provides gentle reminders when risks first emerge, as well as strong warnings and in-depth vehicle status preparation during high-risk situations, achieving a good balance between safety and driving comfort.

[0110] Figure 4 This is a schematic diagram of the overall architecture of a vehicle control system provided in an embodiment of this disclosure, such as... Figure 4As shown, the vehicle control system works in concert with a multi-dimensional data acquisition module, a time-series risk prediction module, a self-learning weight modeling module, a graded early warning module, and a multi-system collaborative preprocessing module to achieve accurate early warning 3-5 seconds before an emergency, and to link the underlying vehicle system to perform pre-protection preprocessing.

[0111] The multi-dimensional data acquisition module is used to collect four types of key data: Environmental data: surrounding vehicle dynamics (within 500 meters), road conditions, and weather; Vehicle operation data: working status of components such as brakes, suspension, and steering; Driver status data: fatigue, distraction, and driving habits; and Time-series change data: the changing trend of perceived data within the last 3 seconds.

[0112] The time-series risk prediction module is used to predict risk changes in future time periods, such as 3-5 seconds, through a time-series risk model. For example, it can predict whether the vehicle in front will brake suddenly or whether driver fatigue will worsen.

[0113] The self-learning weight modeling module is used to automatically adjust the weights of various data based on driver habits and historical road conditions. For example, it focuses on road conditions in rainy weather and driver status during long-distance driving.

[0114] The tiered warning module offers three warning levels to suit different user groups. The levels are: **Information Level:** Screen text + slight vibration; **Warning Level:** Voice prompt + airflow alert; **Emergency Level:** Strong vibration + seat compression + red warning. Optional features include an elderly mode (increased volume, simplified prompts) and a disabled person mode (enhanced vibration).

[0115] The multi-system collaborative preprocessing module is used to coordinate the braking, steering, suspension, and power systems in advance to prepare (such as pre-pressurizing the brakes and making the steering lighter) when a warning is issued. This does not affect normal driving but can improve the emergency response.

[0116] Figure 7 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this disclosure.

[0117] In this embodiment, the vehicle control device can be housed within an electronic device and is understood as a functional module within the aforementioned electronic device. Specifically, the electronic device can be a server or a terminal, wherein the terminal specifically includes an in-vehicle terminal, a computer, or a tablet computer, etc., without limitation.

[0118] like Figure 7 As shown, the vehicle control device 700 may include an acquisition module 710, a obtaining module 720, and a processing module 730.

[0119] The acquisition module 710 is used to acquire multidimensional sensing data and time-series change data, wherein the multidimensional sensing data includes environmental data, vehicle operation data, and driver status data; The module 720 is used to make predictions based on the multidimensional perception data and the time-series change data to obtain the current risk index of the vehicle. The processing module 730 is used to trigger a warning operation corresponding to the risk level based on the risk level to which the current risk index belongs, and at the same time control the vehicle to perform an emergency operation corresponding to the risk level.

[0120] In some embodiments of this disclosure, when the acquisition module 710 acquires multidimensional sensing data, it is specifically used for: The environmental data is obtained by acquiring surrounding vehicle data, road information, and meteorological parameters through vehicle-road cooperative components; The vehicle's operating data is obtained by collecting operating parameters of the engine, braking, steering, and suspension systems via the controller area network bus. The driver's state data is obtained by collecting data on the driver's facial expression, steering wheel grip strength, and heart rate through in-vehicle sensors. The multidimensional perception data is constructed based on the environmental data, the vehicle operation data, and the driver status data.

[0121] In some embodiments of this disclosure, when the obtaining module 720 obtains the current risk index of the vehicle based on the multi-dimensional perception data and the time-series change data, it is specifically used for: The multidimensional sensing data and the time-series change data are input into the time-series prediction model to obtain the risk factors for the future time period. The current risk index of the vehicle is calculated based on the multidimensional perception data and the risk factors.

[0122] In some embodiments of this disclosure, when the obtaining module 720 calculates the current risk index of the vehicle based on the multi-dimensional perception data and the risk factors, it is specifically used for: The preset weight configuration is adjusted based on the multidimensional sensing data to obtain the target weight configuration; Based on the target weight configuration, the multidimensional perception data and the risk factors are weighted and fused to calculate the current risk index.

[0123] In some embodiments of this disclosure, when the obtaining module 720 adjusts the preset weight configuration based on the multidimensional sensing data to obtain the target weight configuration, it is specifically used for: Construct an initial weight model that includes environmental, vehicle, and driver dimensions; Based on the multi-dimensional perception data, the similarity between the current driving scenario and the preset driving scenario is calculated; If the similarity between the current driving scenario and the target driving scenario in the preset driving scenario is greater than a preset threshold, then the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration.

[0124] In some embodiments of this disclosure, when the processing module 730 triggers a warning operation corresponding to the risk level based on the risk level to which the current risk index belongs, and simultaneously controls the vehicle to perform an emergency operation corresponding to the risk level, it is specifically used for: When the risk level is the first risk level, a text message and a vibration alert of the first intensity are triggered. When the risk level is the second risk level, a voice prompt, an airflow reminder, and a vibration reminder of the second intensity are triggered, and the vehicle's target execution system is controlled to initiate basic emergency operations; When the risk level is the third risk level, a vibration alert of the third intensity, a hazard warning signal, and a seat compression are triggered, and multiple actuators of the vehicle are controlled to perform coordinated emergency operations.

[0125] In some embodiments of this disclosure, when the processing module 730 controls multiple execution systems of the vehicle to perform coordinated emergency operations, it is specifically used for: Control the vehicle's braking system to pre-fill the braking pressure; Control the vehicle's steering system to adjust steering assist parameters; Control the vehicle's suspension system to adjust damping or stiffness; Control the vehicle's powertrain to limit output torque.

[0126] In some embodiments of this disclosure, the device 700 further includes: The update module 740 is used to acquire multi-dimensional perception data and corresponding actual risk index in high-risk scenarios during vehicle operation. The high-risk scenario is a driving scenario in which the risk index is greater than a preset risk index threshold. The parameters of the time series prediction model are optimized and updated based on the multidimensional sensing data and the corresponding actual risk index.

[0127] In some embodiments of this disclosure, after triggering the warning operation corresponding to the risk level, the device further includes: Monitoring module 750 is used to monitor the driver's operational response within a preset time period; If an operation response is detected and the current risk index is less than the preset cancellation threshold, then the warning operation and the emergency operation are cancelled.

[0128] It should be noted that, Figure 7The vehicle control device 700 shown can execute the various steps in the above method embodiments and realize the various processes and effects in the above method embodiments, which will not be elaborated here.

[0129] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0130] In this embodiment of the disclosure, Figure 8 The electronic device shown can be a server or a terminal. Specifically, the terminal includes in-vehicle terminals, computers, or tablets, etc., without limitation.

[0131] like Figure 8 As shown, the electronic device may include a processor 810 and a memory 820 storing computer program instructions.

[0132] Specifically, the processor 810 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this disclosure.

[0133] Memory 820 may include mass storage for information or instructions. For example, and not limitingly, memory 820 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 820 may include removable or non-removable (or fixed) media. Where appropriate, memory 820 may be internal or external to the integrated gateway device. In a particular embodiment, memory 820 is non-volatile solid-state memory. In a particular embodiment, memory 820 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0134] The processor 810 reads and executes computer program instructions stored in the memory 820 to perform the steps of the vehicle control method provided in the embodiments of this disclosure.

[0135] In one example, the electronic device may also include a transceiver 830 and a bus 840. Wherein, as... Figure 8 As shown, the processor 810, memory 820 and transceiver 830 are connected via bus 840 and communicate with each other.

[0136] Bus 840 may include hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 840 may include one or more buses.

[0137] This disclosure also provides a computer-readable storage medium that can store a computer program that, when executed by a processor, enables the processor to implement the vehicle control method provided in this disclosure.

[0138] When the computer program is executed by the processor, it can perform the following steps: acquire multi-dimensional sensing data and time-series change data, wherein the multi-dimensional sensing data includes environmental data, vehicle operation data, and driver status data; make predictions based on the multi-dimensional sensing data and the time-series change data to obtain the vehicle's current risk index; trigger a warning operation corresponding to the risk level based on the risk level to which the current risk index belongs, and simultaneously control the vehicle to perform an emergency operation corresponding to the risk level.

[0139] The aforementioned storage medium may, for example, include a memory 820 containing computer program instructions, which can be executed by a processor 810 of an electronic device to perform the vehicle control method provided in the embodiments of this disclosure. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), external cache memory, compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, flash memory, and optical data storage device. By way of illustration and not limitation, RAM is available in various forms, such as static random access memory (SRAM) and dynamic random access memory (DRAM).

[0140] This disclosure also provides a vehicle that includes electronic devices that can implement the various processes and effects described in the above embodiments of this disclosure, which will not be elaborated here.

[0141] This disclosure also provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, they implement the vehicle control method provided in this disclosure and can achieve the various processes and effects in the above embodiments of this disclosure, which will not be elaborated here.

[0142] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle control method, characterized in that, The method includes: Acquire multidimensional sensing data and time-series change data, wherein the multidimensional sensing data includes environmental data, vehicle operation data, and driver status data; Based on the multi-dimensional perception data and the time-series change data, a prediction is made to obtain the vehicle's current risk index. Based on the risk level of the current risk index, a warning operation corresponding to the risk level is triggered, and the vehicle is controlled to perform an emergency operation corresponding to the risk level.

2. The method according to claim 1, characterized in that, The acquisition of multidimensional sensing data includes: The environmental data is obtained by acquiring surrounding vehicle data, road information, and meteorological parameters through vehicle-road cooperative components; The vehicle's operating data is obtained by collecting operating parameters of the engine, braking, steering, and suspension systems via the controller area network bus. The driver's state data is obtained by collecting data on the driver's facial expression, steering wheel grip strength, and heart rate through in-vehicle sensors. The multidimensional perception data is constructed based on the environmental data, the vehicle operation data, and the driver status data.

3. The method according to claim 1, characterized in that, The process of obtaining the vehicle's current risk index based on the multi-dimensional perception data and the time-series change data includes: The multidimensional sensing data and the time-series change data are input into the time-series prediction model to obtain the risk factors for the future time period. The current risk index of the vehicle is calculated based on the multidimensional perception data and the risk factors.

4. The method according to claim 3, characterized in that, The calculation based on the multi-dimensional perception data and the risk factors to obtain the vehicle's current risk index includes: The preset weight configuration is adjusted based on the multidimensional sensing data to obtain the target weight configuration; Based on the target weight configuration, the multidimensional perception data and the risk factors are weighted and fused to calculate the current risk index.

5. The method according to claim 4, characterized in that, The step of adjusting the preset weight configuration based on the multidimensional sensing data to obtain the target weight configuration includes: Construct an initial weight model that includes environmental, vehicle, and driver dimensions; Based on the multi-dimensional perception data, the similarity between the current driving scenario and the preset driving scenario is calculated; If the similarity between the current driving scenario and the target driving scenario in the preset driving scenario is greater than a preset threshold, then the weights of each dimension in the initial weight model are fine-tuned according to the weight configuration data of the target driving scenario to obtain the target weight configuration.

6. The method according to claim 1, characterized in that, The process of triggering a warning operation corresponding to the current risk level based on the current risk index, and simultaneously controlling the vehicle to perform an emergency operation corresponding to the risk level, includes: When the risk level is the first risk level, a text message and a vibration alert of the first intensity are triggered. When the risk level is the second risk level, a voice prompt, an airflow reminder, and a vibration reminder of the second intensity are triggered, and the vehicle's target execution system is controlled to initiate basic emergency operations; When the risk level is the third risk level, a vibration alert of the third intensity, a hazard warning signal, and a seat compression are triggered, and multiple actuators of the vehicle are controlled to perform coordinated emergency operations.

7. The method according to claim 6, characterized in that, The coordinated emergency operation of the multiple execution systems controlling the vehicle includes: Control the vehicle's braking system to pre-fill the braking pressure; Control the vehicle's steering system to adjust steering assist parameters; Control the vehicle's suspension system to adjust damping or stiffness; Control the vehicle's powertrain to limit output torque.

8. The method according to claim 1, characterized in that, The method further includes: During vehicle operation, multi-dimensional perception data and corresponding actual risk index are acquired in high-risk scenarios, where the high-risk scenario is a driving scenario where the risk index is greater than a preset risk index threshold. The parameters of the time series prediction model are optimized and updated based on the multidimensional sensing data and the corresponding actual risk index.

9. The method according to claim 1, characterized in that, After triggering the warning operation corresponding to the risk level, the method further includes: Monitor the driver's operational response within a preset time period; If an operation response is detected and the current risk index is less than the preset cancellation threshold, then the warning operation and the emergency operation are cancelled.

10. A vehicle, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-9.

Images