Vehicle control method, device and storage medium

Abstract

The application discloses a vehicle control method and device and a storage medium, and belongs to the intelligent driving field.The vehicle control method comprises the following steps: acquiring emotion data of a driver when a target vehicle is in a driving state; identifying the emotion data to determine an emotion state of the driver; and controlling a vehicle speed to be a target speed and controlling a driving mode to be an active safety mode when the emotion state of the driver is in an unstable state, wherein the unstable state comprises a fatigue state, an angry state and a sad state.The method can ensure that the vehicle can safely drive when the emotion of the driver is unstable, thereby ensuring the life safety of the driver and passengers.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a vehicle control method and device and a storage medium. BACKGROUND

[0002] With the increasing popularity of intelligent driving functions, on a highway, a driver can start a navigation-based automatic driving function, so that the vehicle cruises at a specified speed and changes lanes and overtakes other vehicles when road conditions permit.

[0003] Current intelligent driving functions do not take the emotional state of the driver as a reference factor. However, in daily driving, due to various reasons such as long driving time, road congestion, and disputes among passengers in the vehicle, the driver inevitably has emotional instability problems, especially when using the intelligent driving function on a highway. If the driver automatically exits the automatic driving function after stepping on the accelerator due to emotional problems, accidents are likely to occur, affecting the safety of the driver and passengers. SUMMARY

[0004] In view of this, the present application provides a vehicle control method, device and storage medium, which can ensure that the vehicle can safely drive when the driver's emotional state is unstable.

[0005] Specifically, the technical solutions include the following:

[0006] In a first aspect, the embodiments of the present application provide a vehicle control method, which comprises:

[0007] obtaining emotional data of the driver when the target vehicle is in a driving state;

[0008] identifying the emotional data to determine the emotional state of the driver;

[0009] controlling the vehicle speed to be a target vehicle speed and controlling the driving mode to be an active safety mode when the emotional state of the driver is in an unstable state, and the unstable state includes a fatigue state, an angry state and a sad state.

[0010] In some embodiments, the emotional data includes image data, sound data and biological information data, and the obtaining of the emotional data of the driver comprises:

[0011] obtaining the image data by using a camera, and the image data includes facial expressions and body postures of the driver;

[0012] obtaining the sound data by using a sound sensor, and the sound data includes the tone and speed of the driver;

[0013] obtaining the biological information data by using a biological sensor, and the biological information data includes the heart rate of the driver.

[0014] In some embodiments, the identifying the emotional data to determine the emotional state of the driver comprises:

[0015] substituting the emotional data into an emotional recognition model to obtain the emotional state of the driver.

[0016] In some embodiments, before the obtaining the emotional data of the driver when the target vehicle is in the driving state, the method further comprises:

[0017] obtaining a set of emotional data of the driver and a corresponding set of emotional state labels within a preset time period when the target vehicle is in the driving state;

[0018] substituting the set of emotional data of the driver and the corresponding set of emotional state labels into an initial model for training to obtain the emotional recognition model.

[0019] In some embodiments, the substituting the set of emotional data of the driver and the corresponding set of emotional state labels into an initial model for training to obtain the emotional recognition model comprises:

[0020] substituting the set of emotional data of the driver and the corresponding set of emotional state labels into an initial model for training to obtain a transition model;

[0021] performing precision detection on the transition model, and determining that the transition model is the emotional recognition model when the precision of the transition model is greater than or equal to a precision threshold.

[0022] In some embodiments, the method further comprises:

[0023] locking the driving mode to the active safety mode when the emotional state of the driver is in an unstable state;

[0024] unlocking the driving mode when the emotional state of the driver is in a stable state, the stable state including a calm state and a happy state.

[0025] In some embodiments, the method further comprises:

[0026] controlling the vehicle-mounted device to perform a soothing action when the emotional state of the driver is in an unstable state.

[0027] In some embodiments, the controlling the vehicle-mounted device to perform a soothing action comprises at least one of:

[0028] controlling a multimedia system to play music;

[0029] adjusting the position of a seat;

[0030] Change the color of the in-vehicle light to a warm color;

[0031] Control the turning on of the air conditioner.

[0032] In a second aspect, the embodiments of the present application further provide a vehicle control device, the device comprising:

[0033] The first acquisition module is configured to acquire emotional data of the driver when the target vehicle is in a driving state.

[0034] The recognition module is configured to recognize the emotional data to determine the emotional state of the driver.

[0035] The control module is configured to control the vehicle speed to be a target speed and control the driving mode to be an active safety mode when the emotional state of the driver is in an unstable state, and the unstable state includes a fatigue state, an angry state, and a sad state.

[0036] In a third aspect, the embodiments of the present application further provide a non-volatile readable storage medium, the non-volatile readable storage medium stores at least one program, and the at least one program is loaded and executed by a processor to implement the vehicle control method according to the first aspect.

[0037] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0038] The vehicle control method provided by the embodiments of the present application, when the vehicle is in a driving state, acquires and recognizes the emotional data of the driver to determine the emotional state of the driver, and when the emotional state of the driver is in an unstable state, controls the vehicle speed to change to a target speed and controls the driving mode to change to an active safety mode, so that the vehicle considers the emotional state of the driver in the intelligent driving function, ensures that the vehicle can safely drive in the case that the emotional state of the driver is unstable, and further ensures the safety of the passengers. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 A system architecture diagram of a vehicle control provided by the embodiments of the present application;

[0041] Figure 2 A flowchart of a vehicle control method provided by the embodiments of the present application;

[0042] Figure 3A flowchart of another vehicle control method provided by the embodiments of the present application;

[0043] Figure 4 A structural schematic diagram of a vehicle control device provided by the embodiments of the present application.

[0044] The specific embodiments of the present application have been shown in the above-described drawings, and will be described in more detail hereinafter. These drawings and the written description are not intended to restrict the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative work are within the scope of protection of the present application.

[0046] Unless otherwise defined, all the technical terms used in the embodiments of the present application have the same meanings as commonly understood by those skilled in the art.

[0047] In order to make the technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail in combination with the drawings.

[0048] The traditional intelligent driving system mainly relies on sensors, computer vision technology, control algorithms, so that the car can autonomously perceive the surrounding environment, make decisions and control driving, which can help the driver to assist driving or realize partial autonomous driving function. In the traditional intelligent driving system, the camera is used to obtain the image information of the road, traffic signs, pedestrians, vehicles and the like around the vehicle, the laser beam is used to measure the distance and position of the object, the high-precision three-dimensional point cloud map is provided, the millimeter wave is used to detect the surrounding obstacles and measure their distance and speed, the ultrasonic wave radar is used to detect the near-distance obstacles; the data obtained by the sensors are analyzed, the road, lane line, traffic sign, pedestrian and vehicle are identified and understood, and the data of multiple sensors are fused together to improve the perception accuracy and robustness of the environment; based on the perception result, the intelligent driving system will make decisions and planning, determine the appropriate driving path and speed, ensure the safe driving of the vehicle according to the traffic rules, safety and efficiency; the control algorithm converts the decision result into actual vehicle control instructions, such as acceleration, braking and steering, to realize the autonomous driving of the vehicle.

[0049] However, current intelligent driving systems do not take the driver's emotional state into account, especially when the driver is in an emotionally unstable state, such as an agitated state. If the driver suddenly accelerates due to emotional problems and the system automatically disengages from the autonomous driving function, it can easily lead to accidents and endanger the lives of the passengers.

[0050] In order to solve the technical problems existing in the related technologies, this application provides a vehicle control method that can ensure the safe driving of a vehicle when the driver is emotionally unstable.

[0051] Before providing a detailed explanation of the embodiments of this application, a brief introduction will be given to the system architecture of vehicle control involved in the embodiments of this application.

[0052] Figure 1 A schematic diagram of a vehicle control system architecture provided in this application embodiment is shown below. Figure 1 The system architecture includes an on-board controller 101, an actuator 102, a sensor assembly 103, and an on-board device 104. The actuator 102, sensor assembly 103, and on-board device 104 are all connected to the on-board controller 101. The actuator 102 is used to perform operations such as acceleration, deceleration, braking, and steering. The sensor assembly 103 is used to acquire information such as facial expressions, body posture, voice, and bioelectrical signals of the driver and passengers. The on-board device 104 is used to meet the driving and riding needs of the driver or passengers and provide a more comfortable driving and riding experience.

[0053] See Figure 1 The sensor assembly 103 includes a camera 1031, a sound sensor 1032, and a biosensor 1033, wherein the camera 1031, the sound sensor 1032, and the biosensor 1033 are all connected to the vehicle controller 101.

[0054] Camera 1031 is used to acquire image data containing the facial expressions and body postures of the driver and passengers in real time. In some embodiments, there may be multiple cameras 1031, which are mounted on the top of the vehicle to acquire images containing the faces and bodies of the driver and passengers. In some embodiments, camera 1031 is a high-precision camera.

[0055] The sound sensor 1032 is used to acquire voice data of the driver and passengers, including tone of voice and speech rate. In some embodiments, the sound sensor 1032 is mounted in the front of the vehicle interior, adjacent to the steering wheel. In some embodiments, the sound sensor 1032 is a microphone.

[0056] The biosensor 1033 is used to obtain the biological information data of the driver, and the biological information data includes the heart rate of the driver. In some embodiments, the biosensor 1033 is installed on the steering wheel.

[0057] Referring to Figure 1 The vehicle-mounted device 104 includes a multimedia component 1041, a seat 1042, an in-vehicle light 1043, and an air conditioner 1044, wherein the multimedia component 1041, the seat 1042, the in-vehicle light 1043, and the air conditioner 1044 are connected with the vehicle-mounted controller 101.

[0058] The multimedia component 1041 is used to provide voice, text, image, video, and other interactive functions for the driver and the passenger. In some embodiments, the multimedia component 1041 includes a display screen, which can display text, images, and videos for the user. In some embodiments, the multimedia component 1041 can also have an intelligent conversation with the driver or the passenger, and provide emotional support for the driver or the passenger.

[0059] The seat 1042 is used to meet the comfortable seating needs of the driver and the passenger. In some embodiments, the seat 1042 can move in multiple directions to meet the needs of different sitting postures of the passenger. In some embodiments, the seat 1042 has a heating function, which can meet the heating needs of the driver or the passenger.

[0060] The in-vehicle light 1043 is used to illuminate the in-vehicle space in dark conditions. In some embodiments, the number of in-vehicle lights 1043 is multiple, and the multiple in-vehicle lights 1043 are installed on the top of the vehicle.

[0061] The air conditioner 1044 is used to provide heating or cooling services for the driver and the passenger in the vehicle, so that the comfort of the in-vehicle environment is better.

[0062] After introducing the system architecture of the vehicle control involved in the application examples, in order to make the technical solutions and advantages of the present application more clear, the application embodiments will be further described in detail below with reference to the accompanying drawings.

[0063] Based on the above-mentioned system architecture of vehicle control, the application embodiment provides a vehicle control method. Referring to Figure 2 , wherein Figure 2 A flowchart of a vehicle control method provided by the application embodiment, the method is applied to the vehicle-mounted controller in the above-mentioned system architecture, and includes:

[0064] Step 201, obtaining the emotional data of the driver when the target vehicle is in a driving state;

[0065] Step 202, identifying the emotional data to determine the emotional state of the driver;

[0066] In step 203, when the emotional state of the driver is in an unstable state, the vehicle speed is controlled to be the target vehicle speed, and the driving mode is controlled to be the active safety mode. The unstable state includes a fatigue state, an angry state, and a sad state.

[0067] The vehicle control method provided by the embodiments of the present application determines the emotional state of the driver by acquiring and identifying the emotional data of the driver when the vehicle is in a driving state, and controls the vehicle speed to change to the target vehicle speed and controls the driving mode to change to the active safety mode when the emotional state of the driver is in an unstable state, so that the vehicle considers the emotional state of the driver in the intelligent driving function, ensures that the vehicle can safely drive in the case that the emotional state of the driver is unstable, and further ensures the safety of the passengers.

[0068] In some embodiments, the emotional data includes image data, sound data, and biological information data, and acquiring the emotional data of the driver includes:

[0069] The image data is acquired by using a camera, and the image data includes facial expressions and body postures of the driver;

[0070] The sound data is acquired by using a sound sensor, and the sound data includes the tone and speed of the driver;

[0071] The biological information data is acquired by using a biological sensor, and the biological information data includes the heart rate of the driver.

[0072] In some embodiments, identifying the emotional data to determine the emotional state of the driver includes:

[0073] The emotional data is substituted into an emotional recognition model to obtain the emotional state of the driver.

[0074] In some embodiments, before acquiring the emotional data of the driver when the target vehicle is in a driving state, the method further includes:

[0075] When the target vehicle is in a driving state, a set of emotional data of the driver and a corresponding set of emotional state labels in a preset time period are acquired;

[0076] The set of emotional data of the driver and the corresponding set of emotional state labels are substituted into an initial model for training to obtain an emotional recognition model.

[0077] In some embodiments, substituting the set of emotional data of the driver and the corresponding set of emotional state labels into the initial model for training to obtain the emotional recognition model includes:

[0078] The set of emotional data of the driver and the corresponding set of emotional state labels are substituted into an initial model for training to obtain a transition model;

[0079] The transition model is subjected to precision detection, and in a case where the precision of the transition model is greater than or equal to a precision threshold, the transition model is determined as the emotion recognition model.

[0080] In some embodiments, the vehicle control method provided by the embodiments of the present application further includes:

[0081] When the emotional state of the driver is in an unstable state, the driving mode is locked as an active safety mode.

[0082] When the emotional state of the driver is in a stable state, the driving mode is unlocked, and the stable state includes a calm state and a happy state.

[0083] In some embodiments, the vehicle control method provided by the embodiments of the present application further includes:

[0084] When the emotional state of the driver is in an unstable state, the vehicle-mounted device is controlled to perform a soothing action.

[0085] In some embodiments, the control of the vehicle-mounted device to perform a soothing action includes at least one of the following: controlling a multimedia system to play music; adjusting the position of a seat; controlling the color of a car light to change to a warm color; and controlling the start of an air conditioner.

[0086] Based on the above-mentioned system architecture of vehicle control, another vehicle control method provided by the embodiments of the present application is provided. Referring to Figure 3 , wherein Figure 3 A flowchart of another vehicle control method provided by the embodiments of the present application is provided, and the method is applied to the vehicle-mounted controller in the above-mentioned system architecture and includes:

[0087] Step 301: When the target vehicle is in a driving state, the emotional data set of the driver and the corresponding emotional state label set in a preset time period are obtained.

[0088] The emotional data includes image data, sound data and biological information data; the emotional state includes a stable state and an unstable state, and the unstable state includes a fatigue state, an angry state and a sad state; and the stable state includes a calm state and a happy state.

[0089] In some embodiments, the preset time period can be one week or more.

[0090] In the embodiments of the present application, the image data in the emotional data set is the main processing data, and the sound data and the biological information data are auxiliary data of the image data, and the image data corresponds to the labeled emotional state.

[0091] Step 302: The emotional data set of the driver and the corresponding emotional state label set are substituted into an initial model for training to obtain an emotion recognition model.

[0092] The emotion data set of the driver is taken as an input of the initial model, and the corresponding emotion state label set is taken as an output of the initial model.

[0093] The emotion recognition model can be obtained by learning and training based on the emotion data set of the driver and the corresponding emotion state label set. The emotion of the driver can be recognized by using the emotion recognition model.

[0094] In some embodiments, the initial model is a convolutional neural network model.

[0095] In some embodiments, the step includes: training the initial model by substituting the emotion data set of the driver and the corresponding emotion state label set into the initial model to obtain a transition model; performing precision detection on the transition model, and determining the transition model as the emotion recognition model when the precision of the transition model is greater than or equal to the precision threshold.

[0096] When the data amount of the emotion data set of the driver and the corresponding emotion state label set is not large enough, the precision of the transition model obtained after training may be poor. If the transition model is used as the emotion recognition model at this time, there may be a problem of low recognition accuracy of the emotion recognition model. Therefore, by performing precision detection on the transition model after obtaining the transition model through training, and determining the transition model as the emotion recognition model when the precision is greater than or equal to the precision threshold, the emotion recognition model can more accurately recognize the emotion and improve the robustness.

[0097] It should be noted that when the precision of the transition model is less than the precision threshold, step 301 is repeated, that is, the emotion data set of the driver and the corresponding emotion state label set in a preset time period are obtained when the target vehicle is in a driving state, and the obtained data is substituted into the transition model which has been trained once for training and precision detection, until the precision of the transition model is greater than or equal to the precision threshold, and the learning and training is stopped, and the trained transition model is used as the emotion recognition model.

[0098] In some embodiments, the precision threshold is 98%.

[0099] Step 303, obtaining the emotion data of the driver when the target vehicle is in a driving state.

[0100] In some embodiments, the step specifically includes: obtaining image data by using a camera, the image data including facial expressions and body postures of the driver; obtaining sound data by using a sound sensor, the sound data including tone and speed of the driver; and obtaining biological information data by using a biological sensor, the biological information data including heart rate of the driver.

[0101] It can be understood that the emotion data of the driver obtained here is the emotion data to be measured.

[0102] Step 304, the emotional data is identified to determine the emotional state of the driver.

[0103] Based on the obtained emotional data, the emotional state of the driver is identified to obtain the emotional state of the driver, so as to determine whether the emotional state of the driver is in an unstable state.

[0104] In some embodiments, the step specifically comprises: substituting the emotional data into an emotional recognition model to obtain the emotional state of the driver.

[0105] By substituting the emotional data to be tested into the emotional recognition model, the emotional state can be output.

[0106] Step 305, when the emotional state of the driver is in an unstable state, the vehicle speed is controlled to be a target vehicle speed, and the driving mode is controlled to be an active safety mode.

[0107] When the target vehicle travels at a speed of 120km / h, the braking distance is at least 55m. If the driver's emotion is unstable during driving, especially in the case of high-speed driving, the driver may not be able to concentrate on judging the behavior trend of the vehicle and the traffic participants, and may not be able to hold the steering wheel, which may lead to an accident. When the vehicle-mounted controller determines that the emotional state of the driver is in an unstable state, especially when in a high-speed driving state, the vehicle speed is controlled to decelerate to a target vehicle speed, and the driving mode is controlled to be an active safety mode, so that the vehicle is in a safe and controllable range, and enough time is provided for the driver to calm down.

[0108] In the embodiments of the present application, the active safety mode refers to an automatic driving mode with the highest safety level, which can ensure the stable and safe operation of the vehicle. Controlling the vehicle speed to be the target vehicle speed refers to decelerating the target vehicle to the target vehicle speed at a certain acceleration, rather than directly reducing the vehicle speed to the target vehicle speed, to ensure the comfort of the driver and passenger in this processing manner. In addition, if the target vehicle is traveling on a highway and it is detected that the emotional state of the driver is in an unstable state, the target vehicle speed should not be set too low. In the embodiments of the present application, the target vehicle speed is in the range of 80km / h to 100km / h. Controlling the driving mode to be the active safety mode refers to changing the target vehicle from the active driving mode to the active safety mode, and switching from the human driving mode to the automatic driving of the target vehicle. The change of this mode is instantaneous.

[0109] In some embodiments, when the emotional state of the driver is in the unstable state, the vehicle controller not only controls the vehicle speed and driving mode, but also locks the driving mode to the active safety mode, that is, the driver cannot actively change the driving mode, and the driving mode at this time cannot be forcibly changed to prevent the driver from performing extreme operations (such as stepping on the accelerator to accelerate) when the emotional state is in the unstable state, and to ensure the safety of the driver and passengers. Only when the emotional state of the driver is in the stable state, the driver can unlock the driving mode by operating the touch control in the vehicle, and at this time the driving mode can be changed to exit the active safety mode.

[0110] In some embodiments, when the emotional state of the driver is in the unstable state, the vehicle controller controls the vehicle-mounted device to perform a soothing action to soothe the driver and provide emotional support to the driver so as to improve the emotional state of the driver.

[0111] In some embodiments, controlling the vehicle-mounted device to perform a soothing action includes at least one of the following: controlling a multimedia system to play music; adjusting the position of a seat; controlling the color of a light in the vehicle to change to a warm color; and controlling the start of an air conditioner.

[0112] For example, when the unstable state is a fatigue state, the multimedia system is controlled to play music with strong rhythm.

[0113] In some embodiments, after the driving mode is locked to the active safety mode, the vehicle controller starts a timing function to obtain a locking time. When the locking time is less than a first time threshold, it indicates that the emotional state of the driver only has a small fluctuation, and at this time the driver can be prompted to lock the prompt by voice prompt; when the locking time is greater than the first time threshold and less than a second time threshold, it indicates that the emotional state of the driver has a relatively obvious fluctuation, and at this time the multimedia system can be controlled to play music according to the specific unstable state, and the driver can be prompted to lock the prompt by voice prompt; when the locking time is greater than the first time threshold, it indicates that the emotional state of the driver has a strong and persistent fluctuation, and at this time the multimedia system can be controlled to play music according to the specific unstable state, and the phone of an emergency contact person can be intelligently dialed to facilitate the emergency contact person to calm the driver.

[0114] Optionally, the first time threshold can be 5 minutes, and the second time threshold can be 10 minutes.

[0115] In some embodiments, the vehicle control method provided by the embodiments of the present application further includes: storing control records to provide historical data of the emotional state of the user, and generating an analysis report based on the historical data. In this way, historical data can be provided for the improvement and optimization of the vehicle control method.

[0116] In some embodiments, the vehicle control method provided by the embodiments of the present application further includes: performing privacy protection on the control record to ensure safety.

[0117] Therefore, the vehicle control method provided by the embodiments of the present application ensures that the vehicle can safely drive in the case that the driver's emotion is unstable by considering the emotional state of the driver into the intelligent driving function, thereby ensuring the safety of the passengers.

[0118] Figure 4 A structural schematic diagram of a vehicle control device provided by the embodiments of the present application is shown in FIG. 4. Figure 4 The device 400 includes a first obtaining module 401, an identifying module 402, and a control module 403.

[0119] The first obtaining module 401 is configured to obtain emotional data of a driver when a target vehicle is in a driving state; the identifying module 402 is configured to identify the emotional data to determine an emotional state of the driver; and the control module 403 is configured to control a vehicle speed to be a target speed and control a driving mode to be an active safety mode when the emotional state of the driver is in an unstable state, and the unstable state includes a fatigue state, an angry state, and a sad state.

[0120] In some embodiments, the emotional data includes image data, sound data, and biological information data, and the first obtaining module 401 specifically includes:

[0121] A first obtaining sub-module configured to obtain image data by using a camera, and the image data includes facial expressions and body postures of the driver;

[0122] A second obtaining sub-module configured to obtain sound data by using a sound sensor, and the sound data includes a tone and a speed of the driver;

[0123] A third obtaining sub-module configured to obtain biological information data by using a biological sensor, and the biological information data includes a heart rate of the driver.

[0124] In some embodiments, the identifying module 402 includes:

[0125] An identifying sub-module configured to substitute the emotional data into an emotional recognition model to obtain the emotional state of the driver.

[0126] In some embodiments, the vehicle control device provided by the embodiments of the present application further includes:

[0127] A second obtaining module configured to obtain a set of emotional data of the driver and a corresponding set of emotional state labels in a preset time period when the target vehicle is in the driving state;

[0128] The training module is configured to input the driver's emotion data set and the corresponding emotion state label set into the initial model for training to obtain the emotion recognition model.

[0129] In some embodiments, the training module specifically comprises:

[0130] The training submodule is configured to input the driver's emotion data set and the corresponding emotion state label set into the initial model for training to obtain the transition model.

[0131] The detection submodule is configured to detect the accuracy of the transition model, and determine that the transition model is the emotion recognition model when the accuracy of the transition model is greater than or equal to the accuracy threshold.

[0132] In some embodiments, the vehicle control device provided by the embodiments of the present application further comprises:

[0133] The locking module is configured to lock the driving mode as the active safety mode when the emotion state of the driver is in the unstable state.

[0134] The unlocking module is configured to unlock the driving mode when the emotion state of the driver is in the stable state, and the stable state includes the calm state and the happy state.

[0135] In some embodiments, the vehicle control device provided by the embodiments of the present application further comprises:

[0136] The control module is configured to control the vehicle-mounted device to perform the soothing action when the emotion state of the driver is in the unstable state.

[0137] The embodiments of the present application also provide a non-volatile readable storage medium, the non-volatile readable storage medium stores at least one program, the at least one program is loaded and executed by a processor to realize the vehicle control method in any one of the above embodiments.

[0138] In the present application, the terms "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance. The term "a plurality of" refers to two or more, unless otherwise explicitly limited.

[0139] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the application following the general principles thereof and including such departures from the present disclosure as come within known or customary practice in the art. The specification and examples are to be regarded as exemplary only.

[0140] It is to be understood that the application is not limited to the precise construction already described above and shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should only be limited by the claims appended hereto.

Claims

1. A vehicle control method, characterized in that, The method includes: While the target vehicle is in motion, acquire the driver's emotion dataset and corresponding emotion state annotation set within a preset time period; The driver's emotion dataset and the corresponding emotion state annotation set are substituted into the initial model for training to obtain the emotion recognition model; While the target vehicle is in motion, acquire the driver's emotional data; The emotional data is identified to determine the driver's emotional state; When the driver's emotional state is unstable, the vehicle speed is controlled to the target speed, and the driving mode is controlled to active safety mode. The unstable state includes fatigue, anger, and sadness. The emotional data includes image data, sound data, and biometric data. Acquiring the driver's emotional data includes: acquiring the image data using a camera, the image data including the driver's facial expressions and body posture; acquiring the sound data using a sound sensor, the sound data including the driver's tone and speech rate; and acquiring the biometric data using a biometric sensor, the biometric data including the driver's heart rate. The step of identifying the emotion data and determining the driver's emotional state includes: substituting the emotion data into the emotion recognition model to obtain the driver's emotional state; The step of substituting the driver's emotion dataset and the corresponding emotion state annotation set into the initial model for training to obtain the emotion recognition model includes: substituting the driver's emotion dataset and the corresponding emotion state annotation set into the initial model for training to obtain a transition model; performing accuracy detection on the transition model, and determining the transition model as the emotion recognition model if the accuracy of the transition model is greater than or equal to an accuracy threshold.

2. The vehicle control method according to claim 1, characterized in that, The method further includes: When the driver's emotional state is unstable, the driving mode is locked to the active safety mode; The driving mode is unlocked when the driver's emotional state is stable, including calm and pleasant states.

3. The vehicle control method according to claim 1, characterized in that, The method further includes: When the driver's emotional state is unstable, the on-board equipment is controlled to perform a soothing action.

4. The vehicle control method according to claim 3, characterized in that, The control of the on-board equipment to perform soothing actions includes at least one of the following: Control the multimedia system to play music; Adjust the seat position; Change the color of the interior lights to a warmer color; Control the air conditioner to turn on.

5. A vehicle control device, characterized in that, The device includes: The second acquisition module is used to acquire the driver's emotion dataset and corresponding emotion state annotation set within a preset time period when the target vehicle is in motion. The training module is used to input the driver's emotion dataset and the corresponding emotion state annotation set into the initial model for training, so as to obtain the emotion recognition model. The first acquisition module is used to acquire the driver's emotional data when the target vehicle is in motion; The recognition module is used to identify the emotion data and determine the driver's emotional state; The control module is used to control the vehicle speed to a target speed and control the driving mode to active safety mode when the driver's emotional state is unstable. The unstable state includes fatigue, anger, and sadness. The emotion data includes image data, sound data, and biometric data. The first acquisition module specifically includes: The first acquisition submodule is used to acquire the image data using a camera, the image data including the driver's facial expressions and body posture; The second acquisition submodule is used to acquire the sound data using a sound sensor, the sound data including the driver's tone and speech rate; The third acquisition submodule is used to acquire the biological information data using a biosensor, the biological information data including the driver's heart rate; The identification module includes: The recognition submodule is used to input the emotion data into the emotion recognition model to obtain the driver's emotional state; The training module specifically includes: The training submodule is used to input the driver's emotion dataset and the corresponding emotion state annotation set into the initial model for training, so as to obtain an intermediate model; The detection submodule is used to perform accuracy detection on the transition model, and determine the transition model as the emotion recognition model if the accuracy of the transition model is greater than or equal to the accuracy threshold.

6. A non-volatile readable storage medium, characterized in that, The non-volatile readable storage medium stores at least one program segment, which is loaded and executed by a processor to implement the vehicle control method as described in any one of claims 1 to 4.

Images