Vehicle control method and device, electronic device, vehicle and storage medium

Abstract

The invention discloses a vehicle control method. The vehicle control method comprises the steps that at least one of vehicle speed information, in-vehicle image information and vehicle control information is obtained to complete obtaining of vehicle information; and controlling the vehicle to run according to the driving emotion of the target user determined by the vehicle information. Therefore, the vehicle can be controlled to execute the corresponding operation according to one or more of the vehicle speed information, the in-vehicle image information and the vehicle control information and the determined driving emotion of the target user, so that the automatic driving behavior or the auxiliary driving behavior of the vehicle can be executed based on the driving emotion of the driver; the safety of users in the vehicle, the vehicle and other users on the vehicle driving road can be guaranteed to a certain extent.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a vehicle control method, a control device, an electronic device, a vehicle, and a computer-readable storage medium. Background Art

[0002] If the user has an aggressive personality, or suffers from road rage, the user is very likely to perform dangerous operations while driving the vehicle, such as controlling the vehicle to make a sharp turn or driving at high speed, which can easily cause traffic accidents. Therefore, the personal personality or mental state of the user in the vehicle is crucial to the safety of the vehicle, the user in the vehicle, and other users on the road where the vehicle is located. Summary of the invention

[0003] The present application provides a vehicle control method, a control device, an electronic device, a vehicle, and a computer-readable storage medium.

[0004] The present application provides a vehicle control method, including:

[0005] Acquiring vehicle information, wherein the vehicle information includes at least one of vehicle speed information, in-vehicle image information, and vehicle control information;

[0006] The vehicle is controlled to travel according to a driving emotion of a target user, wherein the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage.

[0007] In the vehicle control method provided in the embodiment of the present application, the vehicle acquires at least one of vehicle speed information, in-vehicle image information and vehicle control information to complete the acquisition of vehicle information, and controls the vehicle driving according to the driving emotion of the target user determined by the vehicle information.

[0008] In this way, the implementation mode of the present application enables the vehicle to control the vehicle to perform corresponding operations based on the driving emotion of the target user determined by one or more of the vehicle speed information, the in-vehicle image information and the vehicle control information, so that the vehicle's automatic driving behavior or assisted driving behavior can be executed based on the driver's driving emotion, and thus, can ensure the safety of the users in the vehicle, the vehicle and other users on the road where the vehicle is driving to a certain extent.

[0009] In certain embodiments, the method further comprises:

[0010] The driving emotion is determined according to the emotion recognition result, wherein the emotion recognition result is determined according to a preset recognition model and the vehicle information.

[0011] In this way, the implementation mode of the present application is based on the setting of a preset recognition model, so that the driving emotion of the target user can be determined according to the emotion recognition result output by the preset recognition model to identify the vehicle information, so that the efficiency of determining the driving emotion of the target user can be improved to a certain extent.

[0012] In some embodiments, determining the driving emotion according to the emotion recognition result includes:

[0013] The driving emotion is determined based on the first recognition result, the second recognition result and the third recognition result, wherein the preset recognition model includes a first preset recognition model, a second preset recognition model and a third preset recognition model, the first recognition result is determined based on the first preset recognition model and the vehicle speed information, the second recognition result is determined based on the second preset recognition model and the in-vehicle image information, the third recognition result is determined based on the third preset recognition model and the vehicle control information, and the first recognition result, the second recognition result and the third recognition result all include the road rage emotion.

[0014] In this way, the implementation of the present application is based on the acquisition of vehicle speed information, in-vehicle image information and vehicle control information, so that the target user's driving emotion recognition can be completed through three dimensions of information. In other words, the driver's road rage recognition can be detected based on multi-dimensional information, thereby obtaining strong data support and high credibility. At the same time, the implementation of the present application can control the vehicle's driving according to the driving emotion determination result with high credibility, thereby ensuring the reliability of vehicle control to a certain extent, or enabling the vehicle's automatic driving or assisted driving to be reliably executed.

[0015] In certain embodiments, the method further comprises:

[0016] Based on the first preset recognition model, the first recognition result is determined according to the vehicle speed information and the type of the current driving section of the vehicle.

[0017] In this way, the implementation mode of the present application is based on the current driving section type and vehicle speed information, so that the first recognition result will match the type of the vehicle's current driving section. Furthermore, the first recognition result can be consistent with the actual driving conditions of the vehicle, and the credibility of the first recognition result can be guaranteed.

[0018] In certain embodiments, when it is determined according to the first preset recognition model that the vehicle speed information satisfies the vehicle speed condition corresponding to the current driving section type, the first recognition result is not the road rage emotion; and / or, when it is determined according to the first preset recognition model that the vehicle speed information does not satisfy the vehicle speed condition, the first recognition result is the road rage emotion.

[0019] In this way, the implementation method of the present application enables efficient execution of the determination of the first recognition result through the vehicle speed condition corresponding to the current driving section type, and thus, the efficiency of detecting the driving emotion of the target user is guaranteed.

[0020] In certain embodiments, the method further comprises:

[0021] Acquire target vehicle speeds for multiple types of driving sections, wherein the target vehicle speeds for the driving sections are determined based on historical driving data corresponding to the driving sections by multiple users whose driving emotions are not road rage emotions;

[0022] The vehicle speed condition corresponding to each type of the traveling section is determined based on the target vehicle speed corresponding to each type of the traveling section.

[0023] In this way, the implementation mode of the present application is based on the vehicle speed conditions corresponding to multiple types of driving sections that are predetermined, so that after the vehicle obtains the vehicle speed information and the current driving section type, it can determine the vehicle speed condition corresponding to the current driving section type from the multiple predetermined vehicle speed conditions, and determine the first recognition result in combination with the vehicle speed information, thereby enabling the first recognition result to be determined efficiently.

[0024] In certain embodiments, the method further comprises:

[0025] Determining the facial image of the target user according to the in-vehicle image information;

[0026] The second recognition result is determined according to the expression recognition result, wherein the expression recognition result is determined by the second preset recognition model according to the facial image.

[0027] In this way, the implementation mode of the present application enables the target user's driving emotion to be obtained based on the user's expression recognition result, thereby ensuring the credibility of the driving emotion detection result to a certain extent.

[0028] In some embodiments, determining the facial image of the target user according to the in-vehicle image information includes:

[0029] Determining original facial image information of the target user according to the in-vehicle image information;

[0030] The original facial image information is subjected to a preset noise reduction process to obtain the facial image.

[0031] In this way, the implementation mode of the present application enables the second recognition result to be obtained based on the facial image after noise reduction processing, and thus, the credibility of the second recognition result is guaranteed, and the accuracy of the detection result of the target user's driving emotion is also improved to a certain extent.

[0032] In certain embodiments, the method further comprises:

[0033] Based on the third recognition model, the third recognition result is determined according to vehicle brake information, vehicle pedal information and vehicle crankshaft information, wherein the vehicle brake information, the vehicle pedal information and the vehicle crankshaft information are determined according to the vehicle control information.

[0034] In this way, the implementation mode of the present application enables the third recognition result to be determined by the vehicle braking information, vehicle pedal information and vehicle crankshaft information, and further, enables the third recognition result to be associated with the user's operating behavior, and the credibility of the third recognition result can be guaranteed to a certain extent.

[0035] In certain embodiments, the third recognition model is determined based on historical vehicle control information corresponding to a target driving section type and a target time period for users whose driving emotion is road rage, and historical vehicle control information corresponding to a target driving section type and a target time period for users whose driving emotion is not road rage. The target driving section type is determined based on the type of the vehicle's current driving section, and the target time period is determined based on the current time.

[0036] In this way, the implementation mode of the present application completes the training of the third preset recognition model through the historical vehicle control information of users whose driving emotion is road rage and the historical vehicle control information of users whose driving emotion is not road rage, so that the third preset recognition model can learn the difference in vehicle control information between users whose driving emotion is road rage and users who are not road rage during the training process, so as to effectively output the corresponding third recognition result according to the vehicle control information corresponding to the target user.

[0037] In some embodiments, determining the driving emotion according to the first recognition result, the second recognition result, and the third recognition result includes:

[0038] Based on a first confidence level corresponding to the first recognition result, a second confidence level corresponding to the second recognition result, and a third confidence level corresponding to the third recognition result, the driving emotion is determined according to the recognition result with the highest confidence level, wherein the first confidence level is generated according to the first preset recognition model and the vehicle speed information, the second confidence level is generated according to the second preset recognition model and the in-vehicle image information, and the third confidence level is generated according to the third preset recognition model and the vehicle control information.

[0039] In this way, the implementation method of the present application enables the target user's driving emotion to be determined based on the recognition result with the highest confidence, and thus the credibility of the driving emotion detection result can be guaranteed to a certain extent. At the same time, in the case where any one of the vehicle control information, the in-vehicle image information and the vehicle speed information is invalid, such as when the in-vehicle camera is damaged and the in-vehicle image information is not collected, the implementation method of the present application can also complete the determination of the driving emotion based on the remaining vehicle control information and vehicle speed information, thereby ensuring the robustness of the driving emotion detection.

[0040] In some embodiments, the in-vehicle image information is obtained based on a driver monitoring system of the vehicle.

[0041] In some embodiments, the vehicle speed information is determined based on wheel speed information collected by a wheel speed sensor of the vehicle and acceleration information collected by an inertial measurement unit of the vehicle.

[0042] In certain embodiments, the vehicle control information is determined based on vehicle brake information collected by a brake sensor of the vehicle, vehicle pedal information collected by a pedal sensor of the vehicle, and vehicle crankshaft information collected by a crankshaft sensor of the vehicle.

[0043] In some embodiments, controlling the vehicle to travel according to the driving emotion of the target user includes:

[0044] When the driving emotion is the road rage emotion, the vehicle is controlled to enter a preset working mode.

[0045] In this way, the implementation method of the present application enables the vehicle to automatically enter a preset working mode to assist the user in driving the vehicle when the target user's driving emotion is road rage, thereby achieving efficient control of the vehicle to a certain extent.

[0046] The present application provides a control device, including:

[0047] A transceiver unit, used to obtain vehicle information, wherein the vehicle information includes at least one of vehicle speed information, in-vehicle image information and vehicle control information;

[0048] A processing unit is used to control the driving of the vehicle according to the driving emotion of the target user, wherein the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage.

[0049] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned vehicle control method is implemented.

[0050] An embodiment of the present application provides a vehicle, including a vehicle body;

[0051] The vehicle body is installed with the above-mentioned control device or the above-mentioned electronic device.

[0052] An embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by one or more processors, the above-mentioned vehicle control method is implemented.

[0053] The control device, electronic device, vehicle and computer-readable storage medium provided in the embodiments of the present application enable the vehicle to control the vehicle to perform corresponding operations based on the driving emotion of the target user determined by one or more of the vehicle speed information, the in-vehicle image information and the vehicle control information, so that the vehicle's automatic driving behavior or assisted driving behavior can be executed based on the driver's driving emotion, thereby ensuring the safety of the in-vehicle users, the vehicle and other users on the road where the vehicle is driving to a certain extent.

[0054] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0056] Figure 1 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0057] Figure 2 A schematic diagram of a control device in some embodiments of the present application;

[0058] Figure 3 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0059] Figure 4 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0060] Figure 5 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0061] Figure 6 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0062] Figure 7 A schematic flow chart of a vehicle control method in certain embodiments of the present application;

[0063] Figure 8 A schematic diagram of a vehicle in some embodiments of the present application;

[0064] Fig. 9 A schematic diagram of a domain controller in certain embodiments of the present application;

[0065] Fig.10 A flow chart of a vehicle control method in certain embodiments of the present application;

[0066] Fig.11 A flowchart of a method for controlling a vehicle in certain embodiments of the present application. DETAILED DESCRIPTION

[0067] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and cannot be understood as limiting the embodiments of the present application.

[0068] During vehicle driving, the driver's driving behavior (such as braking and turning the steering wheel) is related to factors such as the user's emotions (or personality), driving experience, and the current driving environment. Among them, compared with calm drivers, angry drivers have higher safety risks in driving behaviors, such as stepping on the accelerator pedal with greater force, turning the steering wheel at a larger angle, and overtaking more frequently. Furthermore, in the case where the driver suffers from road rage, or in other words, the user is prone to anger when driving a vehicle, the user is more likely to cause a traffic accident. Therefore, the user's emotions when driving a vehicle are crucial to the safety of the user himself, the user's vehicle, and other users on the road.

[0069] For the above problems that may be encountered, please refer to Figure 1 The present application provides a vehicle control method, comprising:

[0070] 01: Obtain vehicle information, wherein the vehicle information includes at least one of vehicle speed information, in-vehicle image information and vehicle control information;

[0071] 02: Control the vehicle driving according to the driving emotion of the target user, wherein the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage emotion.

[0072] See also Figure 2, an embodiment of the present application provides a control device 100. The control method of the vehicle of the embodiment of the present application can be implemented by the control device 100. Specifically, the control device 100 includes a transceiver unit 110 and a processing unit 120. Among them, the transceiver unit 110 is used to obtain vehicle information, and the vehicle information includes at least one of vehicle speed information, in-vehicle image information and vehicle control information. The processing unit 120 controls the vehicle driving according to the driving emotion of the target user, and the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage emotion.

[0073] The embodiment of the present application also provides an electronic device, which includes a memory and a processor. The vehicle control method of the embodiment of the present application can be implemented by the electronic device of the embodiment of the present application. Specifically, a computer program is stored in the memory, and the processor is used to obtain vehicle information, and the vehicle information includes at least one of vehicle speed information, in-vehicle image information and vehicle control information; and is used to control the vehicle driving according to the driving emotion of the target user, and the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage emotion.

[0074] That is, the vehicle of the implementation mode of the present application can obtain one or more vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information according to various sensors in the vehicle, and then control the vehicle's driving according to the driving emotion of the target user determined by the vehicle information. In other words, the vehicle (or the controller in the vehicle) knows whether the driver suffers from road rage based on the road rage detection result (i.e., driving emotion) of the vehicle driver determined by at least one of the vehicle speed information, in-vehicle image information and vehicle control information, and controls the vehicle's driving according to the road rage detection result, or assists the driver in controlling the vehicle.

[0075] It is understandable that when a user suffers from road rage, the user is prone to adopt relatively dangerous driving operations due to the stimulation of the external environment, such as frequently controlling the vehicle to accelerate, frequently overtaking the vehicle in front, and frequently changing the driving road. Therefore, compared with users who do not suffer from road rage, when users with road rage control the vehicle, the speed is higher (corresponding to the vehicle speed information), the pedal is pressed more frequently (corresponding to the vehicle control information), and the expression may be more angry or irritable (corresponding to the in-vehicle image information).

[0076] For this reason, the implementation manner of the present application detects the emotions of the target user based on at least one of the collected vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information, that is, detects the emotions of the user in the cab, so as to determine whether the target user suffers from road rage, or in other words, determines whether the driving emotion of the target user is road rage (or anger).

[0077] Among them, it can be understood that the vehicle speed information in the implementation mode of the present application can be understood as the vehicle speed. The in-vehicle image information can be understood as a video or image obtained by shooting the vehicle cockpit (or the main driving cabin) through a camera pre-installed in the vehicle. The vehicle control information can be understood as a specific value corresponding to the driving operation performed by the user. In some embodiments, the vehicle control information includes but is not limited to the braking torque, the accelerator pedal opening, and the brake pedal opening.

[0078] It can also be understood that the specific process of detecting the target user's driving emotion based on at least one of the vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information is content that can be set according to actual conditions.

[0079] Exemplarily, in certain embodiments where the vehicle information only includes vehicle speed information, if it is determined based on the vehicle speed information that the vehicle speed has a large change amplitude (such as a minimum change amplitude of 20 km / h) within a certain period of time (such as within 10 minutes) and a high change frequency (such as a change every 10 seconds), then the target user's driving emotion can be determined to be road rage driving. Conversely, if it is determined based on the vehicle speed information that the vehicle speed has a small change amplitude (such as a minimum change amplitude of less than 20 km / h) within a certain period of time (such as within 10 minutes) or a low change frequency (such as a change every 30 seconds), then the target user's driving emotion can be determined not to be road rage driving.

[0080] In certain embodiments where the vehicle information only includes vehicle speed information and vehicle control information, if the vehicle speed information determines that the average vehicle speed within a certain period of time (e.g., 10 minutes) is higher than a preset vehicle speed, and the vehicle control information determines that the pedal usage frequency is high (e.g., the brake pedal or the accelerator pedal is pressed once every 10 seconds), then the target user's driving emotion can be determined to be road rage driving. On the contrary, if the vehicle speed average is not higher than the preset vehicle speed, or the pedal usage frequency is low (e.g., the brake pedal or the accelerator pedal is pressed once every 1 minute), then the target user's driving emotion is determined not to be road rage driving.

[0081] In certain embodiments where the vehicle information includes vehicle speed information, in-vehicle image information, and vehicle control information, if the average vehicle speed of the vehicle within a certain period of time (e.g., 10 minutes) is determined to be higher than a preset speed based on the vehicle speed information, the pedal usage frequency is determined to be high (e.g., the brake pedal or the accelerator pedal is pressed once every 10 seconds) based on the vehicle control information, and the target user's expression is determined to be angry or irritable based on the in-vehicle image information, then the target user's driving emotion can be determined to be road rage driving. On the contrary, if the average vehicle speed is not higher than the preset speed, or the pedal usage frequency is low (e.g., the brake pedal or the accelerator pedal is pressed once every 1 minute), or the target user's expression is not angry or irritable, then the target user's driving emotion can be determined not to be road rage driving.

[0082] It should be noted that the step of detecting the driving emotion of the target user based on at least one of the vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information in the implementation mode of the present application can be completed by the vehicle of the implementation mode of the present application (or the controller in the vehicle), or the vehicle can send at least one of the vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information to a remote electronic device (such as a server or an edge gateway) and complete it. That is, the remote electronic device detects the driving emotion of the target user based on at least one of the received vehicle information such as vehicle speed information, in-vehicle image information and vehicle control information, and sends the detection result to the vehicle.

[0083] It should also be noted that after obtaining the determination or recognition result of the driving emotion, the vehicle can control the vehicle's driving according to the driving emotion determination result to ensure the safety of the user in the car, the vehicle and other users on the road.

[0084] It is understandable that the specific method of controlling the operation of the vehicle according to the driving emotion of the target user is a content that can be set according to the actual situation. For example, in some embodiments, when the driving emotion of the target user is road rage, the maximum speed of the vehicle can be limited (such as limited to 60km / h), so that after the user steps on the accelerator pedal, the maximum speed of the vehicle can only reach the maximum speed after the limit (i.e. 60km / h). In this way, the risk of traffic accidents caused by users performing dangerous driving behaviors can be reduced to a certain extent.

[0085] In other embodiments, when the target user's driving emotion is road rage, the vehicle response efficiency can be limited. That is, under normal circumstances, after the user steps on the accelerator pedal, the time required for the vehicle speed to increase by 10 km / s is 3 seconds. However, when the target user's driving emotion is road rage, the vehicle response efficiency is limited. After the user steps on the accelerator pedal, the vehicle speed will increase by 10 km / s. It will change to 5 seconds. In this way, the risk of traffic accidents caused by users performing dangerous driving behaviors can be reduced to a certain extent.

[0086] In addition, it is conceivable that if the target user's driving emotion is not road rage, the vehicle can drive normally, or in other words, similar vehicle operations such as limiting the vehicle's maximum speed and limiting the vehicle's response efficiency as mentioned above will not be performed.

[0087] In summary, the implementation methods of the present application enable the vehicle to control the vehicle to perform corresponding operations based on the driving emotion of the target user determined by one or more of the vehicle speed information, the in-vehicle image information and the vehicle control information, so that the vehicle's automatic driving behavior or assisted driving behavior can be executed based on the driver's driving emotion, and thus, can ensure the safety of the in-vehicle users, the vehicle and other users on the road where the vehicle is driving to a certain extent.

[0088] In certain embodiments of this application, please refer to Figure 3 , the vehicle control method further includes:

[0089] 03: Determine the driving emotion based on the emotion recognition result, wherein the emotion recognition result is determined based on a preset recognition model and vehicle information.

[0090] The processing unit of the implementation mode of the present application is also used to determine the driving emotion according to the emotion recognition result, wherein the emotion recognition result is determined according to the preset recognition model and vehicle information.

[0091] The processor of the embodiment of the present application is also used to determine the driving emotion based on the emotion recognition result, wherein the emotion recognition result is determined based on a preset recognition model and vehicle information.

[0092] That is, the embodiment of the present application can identify the vehicle information according to the neural network model that has been trained and stored in advance, or according to the algorithm model that has been set and stored in advance, so as to obtain the emotion recognition result corresponding to the vehicle information, that is, the vehicle information is input into the preset recognition model to obtain the corresponding emotion recognition result. Furthermore, the vehicle of the embodiment of the present application can determine the driving emotion of the target user according to the emotion recognition result.

[0093] It can be understood that the preset recognition model of the implementation mode of the present application can be the above-mentioned preset trained and stored neural network model, or it can be the above-mentioned pre-set and stored algorithm model. The specific composition and specific operation of the preset recognition model can be set according to actual conditions.

[0094] It can also be understood that the preset recognition model can be implemented by a functional module of the vehicle or a functional module of the electronic device. Furthermore, in the implementation of the preset recognition model implemented by a functional module of the vehicle, or in other words, the preset recognition model is installed in a certain component of the vehicle (such as a controller), the vehicle can automatically call the preset recognition model to identify the emotion recognition result corresponding to the vehicle information after obtaining the vehicle information.

[0095] In the case where the preset recognition model is implemented by a functional module of an electronic device, the vehicle can send vehicle information to the electronic device after obtaining the vehicle information, so that the electronic device calls the preset recognition model to output the corresponding emotion recognition result and feeds the emotion recognition result back to the vehicle.

[0096] In addition, it should be noted that the emotion recognition results in the embodiments of the present application can, in certain embodiments, be data or values ​​that can represent the user's emotions determined based on one or more of the above-mentioned vehicle speed information, in-vehicle image information, and vehicle control information, or in other words, after one or more of the vehicle speed information, in-vehicle image information, and vehicle control information are input into a preset recognition model, so that the preset recognition model outputs a data or value that can represent the user's emotions, that is, the emotion recognition result.

[0097] In other embodiments, the embodiments of the present application may input one or more data or values ​​representing the user's emotions based on one or more of the vehicle speed information, the in-vehicle image information, and the vehicle control information. For example, when the vehicle information includes the vehicle speed information and the in-vehicle image information, the vehicle speed information is input into the preset recognition model so that the preset recognition model outputs a first emotion recognition result corresponding to the vehicle speed, and then the in-vehicle image information is input into the preset recognition model so that the preset recognition model outputs a second emotion recognition result corresponding to the in-vehicle image. Furthermore, the emotion recognition result output by the preset recognition model based on the vehicle information includes a first emotion recognition result and a second emotion recognition result.

[0098] It should also be noted that the specific form of the emotion recognition result can be set according to the actual situation. For example, in some embodiments, the emotion recognition result can be a probability value, which is used to characterize the probability that the target user's driving emotion is road rage emotion. Then, the vehicle of the embodiment of the present application can determine that the target user's emotion type is road rage type when the emotion recognition result is greater than a preset value, or when the probability that the driving emotion is road rage emotion is greater than a preset value (such as 0.8).

[0099] In other implementations, the emotion recognition results can be divided into two categories: "road rage emotion" or "non-road rage emotion". Furthermore, the implementation methods of the present application can determine the driving emotion of the target user based on the category of the emotion recognition results.

[0100] And, it can be understood that, in the case where the emotion recognition results include multiple ones, such as the case similar to the above example where "the emotion recognition results include the first emotion recognition result and the second emotion recognition result", the implementation mode of the present application can determine the driving emotion corresponding to the emotion recognition result according to the actual situation. For example, when the emotion recognition result includes the first to third emotion recognition results, then: If the emotion recognition result is used to characterize the probability that the target user's driving emotion is road rage, and at least two of the first to third emotion recognition results are greater than a preset value (such as 0.8), then the target user's driving emotion is determined to be road rage. Similarly, if the emotion recognition results can be divided into two categories, "road rage emotion" or "non-road rage emotion", and at least two of the first to third emotion recognition results are "road rage emotion", then the target user's driving emotion is determined to be road rage.

[0101] In certain embodiments where the emotion recognition result only includes two emotion recognition results (such as the first and second emotion recognition results described above), if the emotion recognition result is used to characterize the probability that the target user's driving emotion is road rage, and both emotion recognition results are greater than a preset value (such as 0.8), then the driving emotion is determined to be road rage, and if at least one of the two emotion recognition results is not greater than the preset value, then the driving emotion is determined not to be road rage. Similarly, when the emotion recognition results can be divided into two categories, "road rage" or "non-road rage", and both emotion recognition results are "road rage", then the target user's driving emotion is determined to be road rage, and conversely, if there is at least one emotion recognition result of "non-road rage", then the driving emotion is determined not to be road rage.

[0102] In this way, the implementation mode of the present application is based on the setting of a preset recognition model, so that the driving emotion of the target user can be determined according to the emotion recognition result output by the preset recognition model to identify the vehicle information, so that the efficiency of determining the driving emotion of the target user can be improved to a certain extent.

[0103] In certain embodiments of this application, please refer to Figure 4 , the above step 03 includes:

[0104] 030: Determine driving emotion based on the first recognition result, the second recognition result and the third recognition result, wherein the preset recognition model includes a first preset recognition model, a second preset recognition model and a third preset recognition model, the first recognition result is determined based on the first preset recognition model and vehicle speed information, the second recognition result is determined based on the second preset recognition model and in-vehicle image information, the third recognition result is determined based on the third preset recognition model and vehicle control information, and the first recognition result, the second recognition result and the third recognition result all include road rage emotion.

[0105] The processing unit of the embodiment of the present application is also used to determine the driving emotion based on the first recognition result, the second recognition result and the third recognition result. The preset recognition model includes a first preset recognition model, a second preset recognition model and a third preset recognition model. The first recognition result is determined based on the first preset recognition model and the vehicle speed information, the second recognition result is determined based on the second preset recognition model and the in-vehicle image information, and the third recognition result is determined based on the third preset recognition model and the vehicle control information. The first recognition result, the second recognition result and the third recognition result all include road rage.

[0106] The processor of the embodiment of the present application is also used to determine the driving emotion based on the first recognition result, the second recognition result and the third recognition result. The preset recognition model includes a first preset recognition model, a second preset recognition model and a third preset recognition model. The first recognition result is determined based on the first preset recognition model and the vehicle speed information, the second recognition result is determined based on the second preset recognition model and the in-vehicle image information, and the third recognition result is determined based on the third preset recognition model and the vehicle control information. The first recognition result, the second recognition result and the third recognition result all include road rage.

[0107] That is, the preset recognition models of the implementation mode of the present application may include three, one of which is a first preset recognition model that can determine whether the driving emotion of the target user is road rage based on the vehicle speed information (corresponding to the first recognition result), the second is a second preset recognition model that can determine whether the driving emotion of the target user is road rage based on the in-vehicle image information (corresponding to the second recognition result), and the third is a third preset recognition model that can determine whether the driving emotion of the target user is road rage based on the vehicle control information (corresponding to the third recognition result). At the same time, the vehicle information of the implementation mode of the present application may include the above-mentioned vehicle speed information, in-vehicle image information and vehicle control information. The preset recognition results of the implementation mode of the present application may include the above-mentioned first to third recognition results. And, the implementation mode of the present application may determine whether the driving emotion of the target user is road rage based on the above-mentioned first to third recognition results.

[0108] It can be understood that the implementation mode of the present application enables the driving emotion of the target user to be completed according to the user dimension and the vehicle dimension, that is, based on the in-vehicle image data that can characterize the user's body movements and the user's facial expressions, and the vehicle control information that can characterize the user's driving behavior, and the vehicle speed information that can characterize the vehicle's driving speed, to identify or detect the driving emotion of the target user, thereby realizing multi-dimensional detection of driving emotions, and thereby, the credibility of the detection results of driving emotions is guaranteed.

[0109] It can also be understood that the specific process of determining the target user's driving emotion based on the first to third recognition results is a content that can be set according to actual conditions. Exemplarily, in some embodiments, if at least two of the first to third recognition results are "road rage emotion", the target user's driving emotion can also be determined as road rage emotion. As a result, the target user's driving emotion will be determined by the majority of the first to third recognition results, so the credibility of the target user's driving emotion can be guaranteed.

[0110] In this way, the implementation of the present application is based on the acquisition of vehicle speed information, in-vehicle image information and vehicle control information, so that the target user's driving emotion recognition can be completed through three dimensions of information. In other words, the driver's road rage recognition can be detected based on multi-dimensional information, thereby obtaining strong data support and high credibility. At the same time, the implementation of the present application can control the vehicle's driving according to the driving emotion determination result with high credibility, thereby ensuring the reliability of vehicle control to a certain extent, or enabling the vehicle's automatic driving or assisted driving to be reliably executed.

[0111] In certain embodiments of the present application, the method further comprises:

[0112] Based on the first preset recognition model, a first recognition result is determined according to the vehicle speed information and the type of the current driving section of the vehicle.

[0113] The processing unit of the implementation mode of the present application is also used to determine a first recognition result based on a first preset recognition model, according to the vehicle speed information and the type of the current driving section of the vehicle.

[0114] The processor of the implementation mode of the present application is also used to determine a first recognition result based on a first preset recognition model, according to the vehicle speed information and the type of the current driving section of the vehicle.

[0115] It is understandable that the maximum speed of motor vehicles on different road sections has corresponding restrictions. Therefore, when the user controls the vehicle to travel on different types of road sections, the driving speed also varies accordingly. For example, when the user drives the vehicle on a highway, the speed may be between 60km / h and 120km / s, while when driving on a school road section, the speed may be between 10km / h and 30km / h.

[0116] For this reason, the implementation method of the present application will define whether the target user's driving emotion is road rage based on the vehicle speed and the type of the current driving section, that is, determine the first recognition result, and then make the first recognition result match the current driving section type, thereby ensuring the credibility of the first recognition result.

[0117] It is understandable that the specific process of determining the first recognition result according to the current driving section type and the speed information is a content that can be set according to the actual situation. For example, in some embodiments, the maximum speed (or speed limit) corresponding to the current driving section type can be determined according to the current driving section type. Then, according to the real-time speed information of the vehicle and the previously determined maximum speed, the real-time difference between the real-time speed and the maximum speed is calculated. Finally, if the real-time difference is always maintained within a preset interval (such as [-5km / h, +5km / h]) for a certain period of time (such as 3 minutes), it is determined that the user's driving behavior is relatively stable and the driving emotion is not road rage. On the contrary, if the real-time difference does not always remain within the preset interval for a certain period of time, it is determined that the user's driving behavior is relatively excited or intense, resulting in obvious fluctuations in the speed, and then, the driving emotion is determined to be road rage.

[0118] In this way, the implementation mode of the present application is based on the current driving section type and vehicle speed information, so that the first recognition result will match the type of the vehicle's current driving section. Furthermore, the first recognition result can be consistent with the actual driving conditions of the vehicle, and the credibility of the first recognition result can be guaranteed.

[0119] In certain embodiments of the present application, when it is determined according to the first preset recognition model that the vehicle speed information meets the speed condition corresponding to the current driving section type, the first recognition result is not road rage; and / or, when it is determined according to the first preset recognition model that the vehicle speed information does not meet the speed condition, the first recognition result is road rage.

[0120] That is, the vehicle of the implementation mode of the present application can define whether the driving emotion of the target user is road rage based on the pre-set vehicle speed conditions corresponding to each type of road section, thereby completing the determination of the first recognition result.

[0121] It should be understood that the vehicle speed condition in the implementation mode of the present application can be understood as "the speed of a user suffering from road rage when controlling the vehicle to travel on 'the road currently traveled by the vehicle'" and can also be understood as "the speed of a user who does not suffer from road rage when controlling the vehicle to travel on 'the road currently traveled by the vehicle'".

[0122] It should also be understood that the method for determining the vehicle speed condition in the embodiments of the present application can be set according to actual conditions. For example, in some embodiments, the embodiments of the present application collect the historical vehicle driving data of multiple users with road rage on different types of road sections in advance, and then perform a preset data analysis (such as cluster analysis) on the historical vehicle driving data of each type of road section to obtain the average vehicle speed of users with road rage on different types of road sections, and use the average vehicle speed as the above-mentioned vehicle speed condition.

[0123] Furthermore, after obtaining the vehicle speed information and the current type of road being traveled, the vehicle of the implementation mode of the present application can determine the average vehicle speed of users suffering from road rage on the road section of the current type of road being traveled based on the current type of road being traveled, and then, based on the vehicle speed information, determine whether the difference between the vehicle speed and the average vehicle speed is within a preset range. If so, it is determined that the driving emotion of the user of the vehicle (or the target user) is road rage, otherwise it is not road rage.

[0124] In this way, the implementation method of the present application enables efficient execution of the determination of the first recognition result through the vehicle speed condition corresponding to the current driving section type, and thus, the efficiency of detecting the driving emotion of the target user is guaranteed.

[0125] In addition, it should be noted that the first preset recognition model in the implementation mode of the present application is used to detect whether the vehicle speed information can meet the vehicle speed condition corresponding to the type of the current driving section. The specific setting method of the first preset recognition model can be set according to the actual situation.

[0126] In certain embodiments of this application, please refer to Figure 5 , the control method of the embodiment of the present application also includes:

[0127] 04: obtaining target vehicle speeds for multiple types of driving sections, wherein the target vehicle speeds for the driving sections are determined based on historical driving data corresponding to the driving sections by multiple users whose driving emotions are not road rage emotions;

[0128] 05: According to the target vehicle speed corresponding to each type of driving section, the vehicle speed condition corresponding to each type of driving section is determined.

[0129] The processing unit of the implementation mode of the present application is also used to obtain target vehicle speeds for multiple types of driving sections, wherein the target vehicle speeds for the driving sections are determined based on historical driving data corresponding to the driving sections for multiple users whose driving emotions are not road rage; and based on the target vehicle speeds corresponding to each type of driving section, the speed conditions corresponding to each type of driving section are determined.

[0130] The processor of the implementation mode of the present application is also used to obtain target vehicle speeds for multiple types of driving sections, wherein the target vehicle speeds for the driving sections are determined based on historical driving data corresponding to the driving sections for multiple users whose driving emotions are not road rage; and based on the target vehicle speeds corresponding to each type of driving section, the speed conditions corresponding to each type of driving section are determined.

[0131] It should be noted that when a "user with road rage" and a "user without road rage" control their vehicles to travel on the same road section, the speed of the vehicle of the "user with road rage" is usually higher, or in other words, there is a difference between the speed of the vehicle of the "user without road rage" and the speed of the vehicle of the "user with road rage".

[0132] Therefore, the implementation mode of the present application obtains historical vehicle data of multiple "users without road rage" controlling vehicles to travel on different types of road sections, and determines the usual vehicle speed (or average speed) of the "users without road rage" when controlling vehicles to travel on different types of road sections, that is, the target speed, and then sets the speed conditions for each type of road section according to the target speed for each type of road section.

[0133] Therefore, after the vehicle of the implementation mode of the present application obtains the vehicle speed information and the type of the current driving section, it determines whether the vehicle speed meets the vehicle speed condition based on the vehicle speed condition corresponding to the current driving section type. If so, it is determined that the driving habits of the target user are similar or match those of the "user who does not suffer from road rage", and then it is determined that the driving emotion of the target user is not road rage.

[0134] In this way, the implementation mode of the present application is based on the vehicle speed conditions corresponding to multiple types of driving sections that are predetermined, so that after the vehicle obtains the vehicle speed information and the current driving section type, it can determine the vehicle speed condition corresponding to the current driving section type from the multiple predetermined vehicle speed conditions, and determine the first recognition result in combination with the vehicle speed information, thereby enabling the first recognition result to be determined efficiently.

[0135] In addition, it should be noted that in some cases, when a "user with road rage" and a "user without road rage" control their vehicles to travel on the same road section, the speed of the "user with road rage" is 5 km / s higher than that of the "user without road rage". Therefore, in some embodiments, the speed condition in the embodiments of the present application is the sum of the target speed and 5 km / s, and the speed condition is used to characterize the driving habits of "users with road rage" on different types of roads. Therefore, the embodiments of the present application can also determine that the target user's driving emotion is road rage when "the difference between the vehicle speed and the 'sum of the target speed and 5 km / s' is within a preset error range".

[0136] In certain embodiments of this application, please refer to Figure 6 , the detection method also includes:

[0137] 06: Determine the target user’s facial image based on the in-car image information;

[0138] 07: Determine a second recognition result based on the expression recognition result, wherein the expression recognition result is determined by a second preset recognition model based on the facial image.

[0139] The processing unit of the implementation mode of the present application is also used to determine the facial image of the target user based on the in-vehicle image information; and determine the second recognition result based on the expression recognition result, wherein the expression recognition result is determined by the second preset recognition model based on the facial image.

[0140] The processor of the embodiment of the present application is also used to determine the facial image of the target user based on the in-vehicle image information; and determine the second recognition result based on the expression recognition result, wherein the expression recognition result is determined by the second preset recognition model based on the facial image.

[0141] That is, the vehicle of the implementation mode of the present application will determine the driving emotion of the target user based on the expression of the target user, that is, after extracting the facial image of the target user from the in-vehicle image information, the facial image of the target user is subjected to expression recognition based on a preset second preset recognition model, thereby obtaining the expression recognition result of the target user, and then obtaining the second recognition result based on the expression recognition result.

[0142] It is understandable that the expression recognition result of the embodiment of the present application can be completed by the vehicle itself or the remote electronic device, that is, when the second preset recognition model is mounted on the vehicle itself, the vehicle will automatically call the corresponding second preset recognition model to perform expression recognition on the facial image of the target user. When the second preset recognition model is mounted on the remote electronic device, the vehicle can send the facial image to the remote electronic device, so that the remote electronic device can recognize the expression recognition result corresponding to the facial image through the second preset recognition model, and then send the expression recognition result to the vehicle.

[0143] It is also understandable that the specific method of determining the second recognition result according to the expression recognition result is a content that can be set according to the actual situation. For example, in some embodiments, the types of expression recognition results that can be output by the second preset recognition model include "road rage emotion" and "non-road rage emotion", and then the expression recognition result can be directly used as the second recognition result.

[0144] In other embodiments, the types of expression recognition results that can be output by the second preset recognition model include happiness, anger, sadness, irritability and other emotions. Furthermore, when the expression recognition result is a preset category (such as anger, irritability), the second preset recognition model is "road rage emotion". Conversely, when the expression recognition result is not a preset category, the second preset recognition model is not "road rage emotion".

[0145] Furthermore, it should be noted that the method of determining the facial image of the target user according to the in-car image information in the embodiments of the present application can be set according to the actual situation. For example, in some embodiments, because the shooting position of the in-car camera and the position of the main driving cabin are fixed, after the in-car image information is acquired, the facial image of the person at the position of the main driving cabin in the in-car image information (or the facial image of the person in the main driving cabin) is used as the above facial image.

[0146] In this way, the implementation mode of the present application enables the target user's driving emotion to be obtained based on the user's expression recognition result, thereby ensuring the credibility of the driving emotion detection result to a certain extent.

[0147] In certain embodiments of this application, please refer to Figure 7 , step 06 includes:

[0148] 060: Determine the original facial image information of the target user based on the in-car image information;

[0149] 061: Perform preset noise reduction processing on the original facial image information to obtain a facial image.

[0150] The processing unit of the implementation mode of the present application is also used to determine the original facial image information of the target user based on the in-vehicle image information; and perform a preset noise reduction process on the original facial image information to obtain a facial image.

[0151] The processor of the implementation mode of the present application is also used to determine the original facial image information of the target user based on the in-vehicle image information; and perform preset noise reduction processing on the original facial image information to obtain a facial image.

[0152] That is, after the vehicle implementing the method of the present application performs image extraction processing or target detection processing on the in-vehicle image information to obtain the facial image of the target user in the in-vehicle image information, it also performs a preset image noise reduction processing on the facial image of the target user, that is, the original facial image information of the target user is subjected to a preset noise reduction processing, thereby obtaining a facial image with higher image quality after noise reduction processing.

[0153] It is understood that the specific setting method of the preset noise reduction processing in the implementation mode of the present application can be set according to actual conditions. For example, in some embodiments, the preset noise reduction processing includes but is not limited to image scaling, pixel value normalization, image enhancement and Gaussian denoising.

[0154] In this way, the implementation mode of the present application enables the second recognition result to be obtained based on the facial image after noise reduction processing, and thus, the credibility of the second recognition result is guaranteed, and the accuracy of the detection result of the target user's driving emotion is also improved to a certain extent.

[0155] In addition, it should be noted that in certain embodiments where the second preset recognition model is implemented based on a neural network, the preset noise reduction processing in the embodiments of the present application can also be understood as an image preprocessing operation in the model training process (or reasoning process).

[0156] In certain embodiments of the present application, the detection method further comprises:

[0157] Based on the third recognition model, a third recognition result is determined according to the vehicle brake information, the vehicle pedal information and the vehicle crankshaft information, wherein the vehicle brake information, the vehicle pedal information and the vehicle crankshaft information are determined according to the vehicle control information.

[0158] The processing unit of the implementation mode of the present application is also used to determine a third recognition result based on the third recognition model according to the vehicle braking information, the vehicle pedal information and the vehicle crankshaft information.

[0159] The processor of the embodiment of the present application is also used to determine a third recognition result based on the third recognition model according to the vehicle braking information, the vehicle pedal information and the vehicle crankshaft information.

[0160] That is, the implementation mode of the present application will complete the determination of the third recognition result based on the vehicle braking information, the vehicle pedal information and the vehicle crankshaft information.

[0161] It should be understood that the vehicle brake information in the embodiments of the present application can be understood as information related to vehicle braking, including but not limited to brake torque, hydraulic pressure, hydraulic valve opening, etc. Also, the vehicle pedal information can be understood as brake pedal opening and accelerator pedal opening, etc. The vehicle crankshaft information can be understood as data related to the crankshaft in the engine, including but not limited to crankshaft position and crankshaft reverse rotation, etc.

[0162] It should also be understood that the vehicle braking information, vehicle pedal information and vehicle crankshaft information all change when the driver performs operations such as starting the vehicle, releasing the accelerator pedal and releasing the brake pedal. Therefore, the vehicle braking information, vehicle pedal information and vehicle crankshaft information can be used to characterize the driver's driving operation, and the vehicle braking information, vehicle pedal information and vehicle crankshaft information over a period of time can be used to characterize the driver's driving operation habits for the vehicle.

[0163] In this way, the implementation mode of the present application enables the third recognition result to be determined by the vehicle braking information, vehicle pedal information and vehicle crankshaft information, and further, enables the third recognition result to be associated with the user's operating behavior, and the credibility of the third recognition result can be guaranteed to a certain extent.

[0164] In certain embodiments of the present application, the third recognition model is determined based on historical vehicle control information corresponding to a target driving section type and a target time period for users whose driving emotion is road rage, and historical vehicle control information corresponding to a target driving section type and a target time period for users whose driving emotion is not road rage. The target driving section type is determined based on the type of the vehicle's current driving section, and the target time period is determined based on the current time.

[0165] That is, the implementation mode of the present application can determine users who suffer from road rage and users who do not suffer from road rage based on the time or time period when the user controls the vehicle (corresponding to the target time period) and the type of road the vehicle is currently traveling on (corresponding to the type of target driving section), and determine or train the above-mentioned third preset recognition model based on the vehicle control information when the vehicle is controlled to travel on a section of the target driving section type during the target time period.

[0166] For example, if the target user controls the vehicle to travel on the school road at 17:30 noon, the embodiment of the present application can extract or obtain the first historical vehicle control information of multiple users with road rage controlling the vehicle to travel on the school road section between 17:00 and 18:00. At the same time, the second historical vehicle control information of users with road rage controlling the vehicle to travel on the school road section between 17:00 and 18:00 is obtained.

[0167] Then, a preset initial model is trained according to the first historical vehicle control information and the second historical vehicle control information, thereby obtaining the third preset recognition model.

[0168] It can be understood that the specific type (or specific composition method) of the initial model or the third preset recognition model can be set according to actual conditions. For example, in some embodiments, the third preset recognition model is obtained by training any one of the support vector machine, K nearest neighbor model, and ADABOOST model using the first and second historical vehicle control information.

[0169] It can also be understood that the specific training process of the third preset recognition model is content that can be set according to actual conditions, and the evaluation indicators involved in the training process are also content that can be set according to actual conditions. For example, in some embodiments, the evaluation indicators involved in the training process of the third preset recognition model include accuracy, error rate, confidence, F1 parameter, etc.

[0170] In addition, it should be noted that after the third preset recognition model completes training, the third preset recognition model of the implementation mode of the present application can learn the differences in driving habits (or called vehicle control information differences) between users with road rage and users without road rage corresponding to the target driving section type and target time period based on the above-mentioned first historical vehicle control information and the second historical vehicle control information. Furthermore, the third preset recognition model can identify whether the target user is similar to a user without road rage or a user with road rage based on the learned knowledge and the currently input vehicle control information, thereby obtaining the above-mentioned third recognition result.

[0171] In this way, the implementation mode of the present application completes the training of the third preset recognition model through the historical vehicle control information of users whose driving emotion is road rage and the historical vehicle control information of users whose driving emotion is not road rage, so that the third preset recognition model can learn the difference in vehicle control information between users whose driving emotion is road rage and users who are not road rage during the training process, so as to effectively output the corresponding third recognition result according to the vehicle control information corresponding to the target user.

[0172] In some embodiments of the present application, step 030 includes:

[0173] Based on a first confidence level corresponding to the first recognition result, a second confidence level corresponding to the second recognition result, and a third confidence level corresponding to the third recognition result, the driving emotion is determined according to the recognition result with the highest confidence level, wherein the first confidence level is generated according to a first preset recognition model and vehicle speed information, the second confidence level is generated according to a second preset recognition model and in-vehicle image information, and the third confidence level is generated according to a third preset recognition model and vehicle control information.

[0174] The processing unit of the embodiment of the present application is also used to determine the driving emotion according to the recognition result with the highest confidence based on a first confidence corresponding to the first recognition result, a second confidence corresponding to the second recognition result, and a third confidence corresponding to the third recognition result, wherein the first confidence is generated based on a first preset recognition model and vehicle speed information, the second confidence is generated based on a second preset recognition model and in-vehicle image information, and the third confidence is generated based on a third preset recognition model and vehicle control information.

[0175] The processor of the embodiment of the present application is also used to determine the driving emotion according to the recognition result with the highest confidence based on a first confidence corresponding to the first recognition result, a second confidence corresponding to the second recognition result, and a third confidence corresponding to the third recognition result, wherein the first confidence is generated based on a first preset recognition model and vehicle speed information, the second confidence is generated based on a second preset recognition model and in-vehicle image information, and the third confidence is generated based on a third preset recognition model and vehicle control information.

[0176] That is, the three preset recognition models of the implementation mode of the present application will output the confidence levels corresponding to the recognition results when outputting the corresponding recognition results, namely, the first confidence level corresponding to the first recognition result, the second confidence level corresponding to the second recognition result, and the third confidence level corresponding to the third recognition result.

[0177] Therefore, after obtaining the three confidence levels corresponding to the three recognition results, the embodiment of the present application will determine the target user's driving emotion based on the recognition result corresponding to the highest confidence level among the three recognition results. Thus, the target user's driving emotion can be determined based on the recognition result with the highest confidence level, and thus, the credibility of the driving emotion detection result can be guaranteed to a certain extent.

[0178] It can be understood that, since the implementation method of the present application determines the driving emotion based on three recognition results, or in other words, the driving emotion is determined based on three recognition results corresponding to three types of information (i.e., vehicle control information, in-vehicle image information, and vehicle speed information), and further, when any one type of information is invalid, such as when the in-vehicle camera is damaged and the in-vehicle image information cannot be collected, and the confidence of the first recognition result is low (or, the first recognition result is not output), the implementation method of the present application can also determine the driving emotion of the target user based on the second recognition result and the third recognition result corresponding to the other two types of information (i.e., vehicle control information and vehicle speed information). As a result, when the vehicle or in-vehicle parts are partially damaged, the driving emotion of the target user can still be determined. In other words, the robustness of driving emotion detection is guaranteed.

[0179] In this way, the implementation method of the present application enables the target user's driving emotion to be determined based on the recognition result with the highest confidence, and thus the credibility of the driving emotion detection result can be guaranteed to a certain extent. At the same time, in the case where any one of the vehicle control information, the in-vehicle image information and the vehicle speed information is invalid, such as when the in-vehicle camera is damaged and the in-vehicle image information is not collected, the implementation method of the present application can also complete the determination of the driving emotion based on the remaining vehicle control information and vehicle speed information, thereby ensuring the robustness of the driving emotion detection.

[0180] In certain embodiments of the present application, the in-vehicle image information is acquired based on the vehicle's driver monitoring system.

[0181] That is, the vehicle in the implementation mode of the present application is installed with a driver monitoring system (Driver Monitoring System, DMS). Therefore, while the implementation mode of the present application monitors the driver based on the driver monitoring system, it can also be used to complete the collection of in-vehicle image information, thereby providing information support for the subsequent determination of the first recognition result.

[0182] In certain embodiments of the present application, the vehicle speed information is determined based on the wheel speed information collected by the wheel speed sensor of the vehicle and the acceleration information collected by the inertial measurement unit of the vehicle.

[0183] That is, the vehicle in the embodiment of the present application is equipped with a wheel speed sensor and an inertial measurement unit. Furthermore, the vehicle in the embodiment of the present application can determine the vehicle speed, that is, the vehicle speed information, based on the wheel speed information collected by the wheel speed sensor and the acceleration information collected by the inertial measurement unit.

[0184] In certain embodiments of the present application, the vehicle control information is determined based on the vehicle braking information collected by the vehicle's brake sensor, the vehicle pedal information collected by the vehicle's pedal sensor, and the vehicle crankshaft information collected by the vehicle's crankshaft sensor.

[0185] That is, the vehicle of the embodiment of the present application is equipped with a brake sensor for collecting vehicle braking information, a pedal sensor for collecting vehicle pedal information, and a crankshaft sensor for collecting vehicle crankshaft information.

[0186] The brake sensor may be understood as one or more sensors capable of collecting brake-related information. For example, in some embodiments, the brake sensor includes a brake vacuum pressure sensor and a hydraulic pressure sensor.

[0187] Similarly, the crankshaft sensor may be understood as one or more sensors capable of collecting information related to the crankshaft. For example, in some embodiments, the crankshaft sensor includes a crankshaft position sensor for collecting the position of the crankshaft.

[0188] Similarly, the pedal sensor can be understood as one or more sensors that can collect information related to the brake pedal and the accelerator pedal. For example, in some embodiments, the pedal sensor includes an accelerator pedal position sensor and a brake pedal depth position sensor.

[0189] In certain embodiments of this application, please refer to Figure 8 , Figure 8Schematic diagram of a vehicle in some embodiments of the present application. That is, in some embodiments of the present application, an ultrasonic radar 101, a first camera 102, a second camera 103, a millimeter-wave radar 104, a wheel speed sensor 105, an inertial measurement unit 106, an accelerator pedal sensor 107, a radar system controller 108, a positioning module 109, a domain controller 110 and a vehicle networking module 111 are provided in the vehicle. Among them, the first camera 102 is used to photograph the front, rear, left and right sides of the vehicle. The second camera 103 is used to cooperate with the millimeter-wave radar 104 to realize automatic driving.

[0190] Further, to clearly explain the domain controller 110 in the embodiment of the present application, please refer to Fig. 9 , Fig. 9 It is a schematic diagram of the domain controller 110 in some embodiments of the present application. That is, the vehicle of the embodiment of the present application is equipped with 5 domain controllers 110, which are used for the front domain controller 112, the left domain controller 113, the right domain controller 114, the rear domain controller 115 and the cockpit and intelligent driving domain controller 116. Among them, the front domain controller 112 is responsible for the control of electrical equipment in the front area of ​​the vehicle, the left domain controller 113 is responsible for the control of electrical equipment in the left area of ​​the vehicle, the right domain controller 114 is responsible for the control of electrical equipment in the right area of ​​the vehicle, the rear domain controller 115 is responsible for the control of electrical equipment in the rear area of ​​the vehicle, and the cockpit and intelligent driving domain controller 116 is responsible for the control of electrical equipment related to the cockpit and automatic driving in the vehicle. It should be noted that the electrical equipment to be controlled by each domain controller can be set according to actual conditions.

[0191] At the same time, it should be noted that the vehicle control method in the embodiment of the present application can be executed by operating one or more domain controllers in the vehicle according to actual conditions. Fig.10 and Fig.11 , Fig.10 and Fig.11 All of them are flowchart diagrams of vehicle control methods in certain embodiments of the present application.

[0192] That is, the vehicle control method of the embodiment of the present application depends on the left domain controller 113. Specifically, the acceleration information collected by the inertial measurement unit and the wheel speed information collected by the wheel speed sensor are converted into vehicle speed information based on the left domain controller 113. And, the left domain controller 113 outputs a first recognition result based on the vehicle speed condition corresponding to the type of the current driving section and the vehicle speed information.

[0193] At the same time, after the driver monitoring system collects the in-vehicle image information, it sends it to the left domain controller 113. The left domain controller 113 calls the second preset recognition model to perform emotion recognition on the facial image of the target user in the in-vehicle image information, and then outputs a second recognition result.

[0194] Furthermore, the crankshaft sensor transmits the collected vehicle crankshaft information to the left domain controller 113, the brake sensor transmits the collected vehicle brake information to the left domain controller 113, and the pedal sensor transmits the collected vehicle pedal information to the left domain controller 113. The left domain controller 113 calls the third preset recognition model to recognize the vehicle crankshaft information, the vehicle pedal information and the vehicle brake information, thereby obtaining a third recognition result.

[0195] Finally, the crankshaft sensor integrates the first to third recognition results to obtain the driving emotion of the target user and controls the vehicle driving according to the driving emotion.

[0196] In addition, it can be understood that the number of domain controllers in the implementation of the present application can also be one, or in other words, the vehicle of the implementation of the present application can be set based on the cross-domain integrated electronic and electrical architecture, and then, the number of domain controllers in the vehicle is one, and the domain controller will be responsible for the control of all electrical equipment in the vehicle. It can be understood that in this implementation, all control logic and data logic in the vehicle will be completed by this domain controller (or central computing unit), and then, relative to the situation where multiple domain controllers are responsible for vehicle control, when the vehicle is controlled based on one domain controller, data does not need to flow or transmit in multiple domain controllers, and then, the data processing efficiency and control efficiency of the vehicle can be improved to a certain extent.

[0197] In addition, it should be noted that when the domain controller of the embodiment of the present application outputs the first recognition result, it can also be determined according to the oxygen concentration in the cabin space collected by the oxygen sensor. Fig.10 As shown, the left domain controller of the implementation mode of the present application can determine whether the first recognition result is road rage based on the oxygen concentration in the cabin space collected by the oxygen sensor.

[0198] It is understandable that when the user in the cabin is more excited or angry, the user's breathing rate increases, causing the oxygen concentration in the cabin to decrease and the carbon dioxide concentration to increase. For this reason, the embodiment of the present application can also input the facial image of the target user and the oxygen concentration of the cabin space into the left domain controller, so that the left domain controller calls the second preset model to identify the oxygen concentration and the facial image, thereby completing the determination of the second recognition result. For example, when the oxygen concentration is lower than the preset value and the user's expression is determined to be angry or irritable based on the facial image, the user's driving emotion is determined to be road rage.

[0199] In certain embodiments of the present application, step 02 includes:

[0200] When the driving emotion is road rage, the vehicle is controlled to enter a preset working mode.

[0201] The processing unit of the implementation mode of the present application is also used to control the vehicle to enter a preset working mode when the driving emotion is road rage.

[0202] The processor of the implementation manner of the present application is also used to control the vehicle to enter a preset working mode when the driving emotion is road rage.

[0203] That is, when the implementation method of the present application determines that the user's driving emotion is road rage, the operating parameters or operating model of the vehicle will be restricted, that is, the vehicle will be controlled to enter a preset working mode.

[0204] In certain embodiments of the present application, after the vehicle enters the preset working mode, the maximum speed and maximum turning angle of the vehicle will be subject to corresponding restrictions. For example, when it is determined that the user's driving emotion is road rage and the current driving section is a school section, the maximum speed of the vehicle will be limited to 20km / h. Then, when the user presses the accelerator pedal hard, the maximum speed of the vehicle is 20km / h before leaving the school section.

[0205] It can also be understood that the preset working mode of the implementation mode of the present application is content that can be set according to actual conditions.

[0206] In this way, the implementation method of the present application enables the vehicle to automatically enter a preset working mode to assist the user in driving the vehicle when the target user's driving emotion is road rage, thereby achieving efficient control of the vehicle to a certain extent.

[0207] The embodiment of the present application further provides a vehicle, including a vehicle body, on which the control device or the electronic device is installed.

[0208] The present application also provides a computer-readable storage medium containing a computer program. When the computer program is executed by one or more processors, the one or more processors execute the vehicle control method of the present application.

[0209] In the description of this specification, the descriptions with reference to the terms "certain embodiments", "in an example", "exemplarily", etc., mean that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0210] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0211] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A vehicle control method, characterized in that: include: Acquiring vehicle information, wherein the vehicle information includes at least one of vehicle speed information, in-vehicle image information, and vehicle control information; The vehicle is controlled to travel according to a driving emotion of a target user, wherein the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage.

2. The method according to claim 1, characterized in that: The method further comprises: The driving emotion is determined according to the emotion recognition result, wherein the emotion recognition result is determined according to a preset recognition model and the vehicle information.

3. The method according to claim 2, characterized in that The determining the driving emotion according to the emotion recognition result includes: The driving emotion is determined based on the first recognition result, the second recognition result and the third recognition result, wherein the preset recognition model includes a first preset recognition model, a second preset recognition model and a third preset recognition model, the first recognition result is determined based on the first preset recognition model and the vehicle speed information, the second recognition result is determined based on the second preset recognition model and the in-vehicle image information, the third recognition result is determined based on the third preset recognition model and the vehicle control information, and the first recognition result, the second recognition result and the third recognition result all include the road rage emotion.

4. The method according to claim 3, characterized in that The method further comprises: Based on the first preset recognition model, the first recognition result is determined according to the vehicle speed information and the type of the current driving section of the vehicle.

5. The method according to claim 4, characterized in that When it is determined according to the first preset recognition model that the vehicle speed information satisfies the vehicle speed condition corresponding to the type of the current driving section, the first recognition result is not the road rage emotion; And / or, when it is determined according to the first preset recognition model that the vehicle speed information does not satisfy the vehicle speed condition, the first recognition result is the road rage emotion.

6. The method according to claim 5, characterized in that The method further comprises: Acquire target vehicle speeds for multiple types of driving sections, wherein the target vehicle speeds for the driving sections are determined based on historical driving data corresponding to the driving sections by multiple users whose driving emotions are not road rage emotions; The vehicle speed condition corresponding to each type of the traveling section is determined based on the target vehicle speed corresponding to each type of the traveling section.

7. The method according to claim 3, characterized in that The method further comprises: Determining the facial image of the target user according to the in-vehicle image information; The second recognition result is determined according to the expression recognition result, wherein the expression recognition result is determined by the second preset recognition model according to the facial image.

8. The method according to claim 7, characterized in that The step of determining the facial image of the target user according to the in-vehicle image information includes: Determining original facial image information of the target user according to the in-vehicle image information; The original facial image information is subjected to a preset noise reduction process to obtain the facial image.

9. The method according to claim 3, characterized in that: The method further comprises: Based on the third recognition model, the third recognition result is determined according to vehicle brake information, vehicle pedal information and vehicle crankshaft information, wherein the vehicle brake information, the vehicle pedal information and the vehicle crankshaft information are determined according to the vehicle control information.

10. The method according to claim 3, characterized in that: The third recognition model is determined based on the historical vehicle control information corresponding to the target driving section type and the target time period for users whose driving emotion is the road rage emotion, and the historical vehicle control information corresponding to the target driving section type and the target time period for users whose driving emotion is not the road rage emotion. The target driving section type is determined based on the type of the current driving section of the vehicle, and the target time period is determined based on the current time.

11. The method according to claim 3, characterized in that The determining the driving emotion according to the first recognition result, the second recognition result and the third recognition result includes: Based on a first confidence level corresponding to the first recognition result, a second confidence level corresponding to the second recognition result, and a third confidence level corresponding to the third recognition result, the driving emotion is determined according to the recognition result with the highest confidence level, wherein the first confidence level is generated according to the first preset recognition model and the vehicle speed information, the second confidence level is generated according to the second preset recognition model and the in-vehicle image information, and the third confidence level is generated according to the third preset recognition model and the vehicle control information.

12. The method according to claim 1, characterized in that The in-vehicle image information is obtained based on the driver monitoring system of the vehicle.

13. The method according to claim 1, characterized in that The vehicle speed information is determined based on the wheel speed information collected by the wheel speed sensor of the vehicle and the acceleration information collected by the inertial measurement unit of the vehicle.

14. The method according to claim 1, characterized in that The vehicle control information is determined based on vehicle brake information collected by a brake sensor of the vehicle, vehicle pedal information collected by a pedal sensor of the vehicle, and vehicle crankshaft information collected by a crankshaft sensor of the vehicle.

15. The method according to claim 1, characterized in that The controlling the vehicle to travel according to the driving emotion of the target user includes: When the driving emotion is the road rage emotion, the vehicle is controlled to enter a preset working mode.

16. A control device, characterized in that: include: A transceiver unit, used to obtain vehicle information, wherein the vehicle information includes at least one of vehicle speed information, in-vehicle image information and vehicle control information; A processing unit is used to control the driving of the vehicle according to the driving emotion of the target user, wherein the driving emotion is determined according to the vehicle information, and the driving emotion includes road rage.

17. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 15 is implemented.

18. A vehicle, characterized in that: Including the body; The vehicle body is mounted with the control device according to claim 16 or the electronic device according to claim 17.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method according to any one of claims 1 to 15 is implemented.

Images