Fatigue relieving control method, vehicle and storage medium

Abstract

The invention discloses a fatigue relieving control method, a vehicle and a storage medium. The fatigue relieving control method comprises the steps that the current driving mode of the vehicle and driving state information of a driver are obtained; when the current driving mode is an automatic driving mode and it is determined that the driver is in a fatigue state according to the driving state information, the current fatigue level of the driver is determined; and executing fatigue relieving operation according to the current fatigue level. According to the invention, different fatigue relieving operations corresponding to the current fatigue level can be used for fatigue relieving, and the relieving effect is better. And the fatigue relieving operation is not carried out in a non-automatic driving mode, so that the driving safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control, and in particular, to a fatigue relief control method, a vehicle, and a storage medium. Background Art

[0002] At present, when a driver drives for a long time, mental and physical fatigue is likely to occur, which may endanger traffic safety. In the prior art, there are ways to refresh the driver through aromatherapy or massage to relieve fatigue. However, since the fatigue phenomenon of the driver is continuous and has a tendency to accumulate and intensify over time, the reminder methods in the prior art are single. As long as the user is fatigued, the same method is used to relieve it, and the relief effect is not good. Summary of the Invention

[0003] Embodiments of the present invention provide a fatigue relief control method, a vehicle, and a storage medium to solve the problem that the fatigue relief effect of the fatigue relief solution for the driver in the prior art is not good.

[0004] Embodiments of the present invention provide a fatigue relief control method, including: Obtaining the current driving mode of the vehicle and the driving state information of the driver; When the current driving mode is the autonomous driving mode and it is determined according to the driving state information that the driver is in a fatigued state, determining the current fatigue level of the driver; Performing a fatigue relief operation according to the current fatigue level.

[0005] Embodiments of the present invention further provide a vehicle, including a controller, where the controller includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned fatigue relief control method is implemented.

[0006] Embodiments of the present invention further provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned fatigue relief control method is implemented.

[0007] In the present invention, when it is determined that the current driving mode of the vehicle is the autonomous driving mode and it is determined that the driver is in a fatigued state according to the driving state information of the vehicle, the current fatigue level of the driver is first determined, and different fatigue relief operations are performed according to the current fatigue level. In this way, during a long-term continuous driving process, for the continuously accumulating and intensifying fatigue degree of the driver, different fatigue relief operations corresponding to the current fatigue level can be used to relieve fatigue, and the relief effect is better. At the same time, it also avoids the situation where the driver develops tolerance and the relief becomes ineffective when only the same fatigue relief operation is used to relieve fatigue during a long-term fatigued process. At the same time, the fatigue relief control method of the present application is only executed when the current driving mode of the vehicle is the autonomous driving mode. Therefore, the fatigue relief operation will not be performed in the non-autonomous driving mode, and it will not endanger the driving behavior of the driver, ensuring driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a flowchart of the fatigue relief control method in an embodiment of the present invention.

[0010] Figure 2 It is a flowchart of step S200 of the fatigue relief control method in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0012] As Figure 1 shown, the present invention provides a fatigue relief control method, including the following steps: S100. Obtain the current driving mode of the vehicle and the driving state information of the driver. Among them, the current driving mode of the vehicle includes an autonomous driving mode and a non-autonomous driving mode. The autonomous driving mode includes a full autonomous driving mode, that is, a driving state in which the vehicle autonomously travels through artificial intelligence, sensors, and other technologies without human intervention. In the present invention, the current driving mode of the vehicle can be directly obtained by the controller. Understandably, in the present invention, in the non-autonomous driving mode, since manual takeover of driving is required, for safe driving, fatigue relief operations cannot be used during driving to avoid distraction and cause safety accidents. Among them, the driving state information refers to the current physical state, behavior performance, etc. of the driver. For example, the driving state information can refer to the facial features of the driver or the body posture features, body pressure distribution information, etc. of the driver. The driving state information can be used to determine whether the driver is in a fatigued state.

[0013] S200. When the current driving mode is the autonomous driving mode and it is determined that the driver is in a fatigued state according to the driving state information, determine the current fatigue level of the driver. That is, in this embodiment, when it is detected that the current driving mode is the autonomous driving mode and at the same time it is determined that the driver is in a fatigued state according to the driving state information, it is first necessary to determine the current fatigue level of the driver. Furthermore, according to the current fatigue level, the specific severity of the driver's fatigued state is determined, and then targeted fatigue relief operations are performed according to the current fatigue level.

[0014] In this step, there are various ways to determine the current fatigue level.

[0015] For example, in some embodiments, the current fatigue level can be determined with reference to steps S201-203 in the subsequent embodiments according to the real-time face image of the driver, or the current fatigue level can be judged by the change in body pressure distribution that occurs when the driver is fatigued, and then further fatigue relief operations are performed according to the current fatigue level.

[0016] In some other embodiments, before step S200, if the vehicle determines that the driver's real-time fatigue level exceeds the target level, the vehicle will automatically control itself to enter the autonomous driving mode. In this case, the determination of the driver's current fatigue level is as follows: the controller directly obtains the real-time fatigue level and then determines this real-time fatigue level as the current fatigue level. In the above embodiments, before the vehicle determines that the real-time fatigue level exceeds the target level, it first needs to determine the driver's real-time fatigue level. At this time, the process of determining the driver's real-time fatigue level can be based on the driver's real-time facial image or the change in body pressure distribution that occurs during fatigue; alternatively, to determine the driver's real-time fatigue level, it can also be the real-time fatigue level directly entered by the driver through the vehicle's preset display screen when the driver feels overly fatigued. At this time, after the vehicle receives the entered real-time fatigue level, it can directly determine that the entered real-time fatigue level exceeds the target level, determine to automatically control the vehicle to enter the autonomous driving mode, and at the same time, the real-time fatigue level entered by the driver can be determined as the current fatigue level.

[0017] In some other embodiments, the autonomous driving mode is not entered based on the real-time fatigue level, but is entered by the user's operation or switched through other means. At this time, the current fatigue level can be directly determined based on the driver's real-time facial image or the change in body pressure distribution, etc. It can also be detected whether the driver marks their fatigue level within a preset duration (such as within 3 minutes) at the current time point. If there is a mark, the marked fatigue level can also be directly determined as the current fatigue level.

[0018] S300, perform fatigue relief operations according to the current fatigue level. It can be understood that in this embodiment, after determining that the vehicle is in the autonomous driving mode, the driver is in a fatigued state, and the current fatigue level is determined, different fatigue relief operations will be performed according to different current fatigue levels.

[0019] In the above embodiments of the present invention, when it is determined that the current driving mode of the vehicle is the autonomous driving mode and it is determined that the driver is in a fatigued state based on the driving state information of the vehicle, first, the driver's current fatigue level is determined, and then different fatigue relief operations are performed according to the current fatigue level. In this way, during a long-term continuous driving process, for the continuously accumulating and intensifying fatigue degree of the driver, different fatigue relief operations corresponding to the current fatigue level can be used to relieve fatigue, and the relief effect is better. At the same time, it also avoids the situation where the driver develops tolerance and the relief becomes ineffective when only using the same fatigue relief operation to relieve fatigue during a long-term fatigued process. Therefore, the fatigue relief operations will not be performed in the non-autonomous driving mode, which will not endanger the driver's driving behavior and ensures driving safety.

[0020] In one embodiment, step S300, that is, performing a fatigue relief operation according to the current fatigue level, includes: When the current fatigue level is mild fatigue, perform a seat tilting operation, and the seat tilting operation includes: controlling the seat back to tilt backward by a preset relief angle.

[0021] Among them, the preset relief angle can be set according to actual needs. For example, the vehicle can default to set a preset relief angle within a preset angle adjustment range (such as 2° - 5°, but this preset angle adjustment range can also not be limited to 2° - 5°). In the default state, when the driver is in mild fatigue, the body feels slightly sore or uncomfortable, but the mental state is still okay. At this time, the seat tilting operation can be performed to control the seat back to tilt backward by this preset relief angle, thereby relieving the driver's fatigue by the vehicle tilting backward.

[0022] Further, before performing the fatigue relief operation according to the current fatigue level, it includes: receiving an angle setting instruction containing the driver's identity information, and setting the seat adjustment angle included in the angle setting instruction as the preset relief angle. The angle setting instruction is generated after the driver selects the seat adjustment angle from the preset angle adjustment range, and the preset angle adjustment range is 2° - 5°. That is, in this embodiment, if the driver is not applicable to the above default preset relief angle, the driver can select a seat adjustment angle within the allowed preset angle range according to his own physical condition as a new preset relief angle applicable to himself. At this time, the driver needs to send an angle setting instruction through the preset display screen on the vehicle or a smart device communicatively connected to the vehicle controller during non-driving hours. The vehicle will automatically set the seat adjustment angle in the angle setting instruction as the preset relief angle associated with this driver. It can be understood that this angle setting instruction needs to contain the driver's identity information. The same vehicle may be driven by different drivers, and the preset relief angles required for different drivers will also be different. Therefore, the driver's identity information needs to be associated with the preset relief angle selected by the driver, so that each driver corresponds to a preset relief angle applicable to himself, so that the seat tilting operation is applicable to different drivers and brings a better relief experience.

[0023] In a further embodiment, when the current fatigue state is mild fatigue, some relatively gentle massage methods can also be added. At this time, when the current fatigue level is mild fatigue, not only the seat tilting operation will be performed, but also at least one of the following mild massage operations can be performed in cooperation to massage the waist or / and the shoulder and neck to relieve waist fatigue or / and relax the shoulder and neck muscles: Massage in a soothing mode: The massage intensity is gentle and the rhythm is slow, suitable for relaxation after daily short-term driving.

[0024] Wave mode massage: The massage action is wavy, with a wide coverage area, suitable for full-body relaxation.

[0025] In one embodiment, the step S300, that is, performing the fatigue relief operation according to the current fatigue level, includes: When the current fatigue level is moderate fatigue, perform a massage operation, and the massage operation includes: controlling the massage device installed on the seat to start to massage the preset parts of the driver.

[0026] In this embodiment, when the driver is moderately fatigued, the body feels obvious soreness or stiffness, and the mental state is slightly tired. At this time, the moderate massage operation can be directly performed, and then the driver's fatigue can be relieved through the massage operation. The moderate massage operation can include at least one of the following massage modes: Kneading mode: Simulate the kneading action of human hands, with moderate strength, suitable for relaxing muscles.

[0027] Acupressure mode: Massage by acupressure method, suitable for relieving local muscle tension.

[0028] Pulse mode: Intermittent strong impact, suitable for relieving muscle tension in specific parts.

[0029] Hot stone massage: Through several massage air bags, inflate and lift, deflate and contract at different frequencies and in different orders, and simulate the massage operation to play a role in relieving fatigue.

[0030] The above-mentioned moderate massage operation can massage some or all of the waist, shoulders and neck, back, buttocks, legs, etc. to relieve fatigue. During this process, the intensity of the massage or the preset parts of the massage can also be automatically adjusted according to the user's sitting posture. For example, for the target part where the user is closer to the seat (the body pressure of this part measured by the body pressure sensor on the seat is greater), if the massage of this part has started, the massage intensity and duration of this target part can be increased. If the massage of this part has not started yet, the massage of this target part can be started, that is, this target part is added as one of the preset parts that need to be massaged.

[0031] In one embodiment, the step S300, that is, performing the fatigue relief operation according to the current fatigue level, includes: When the current fatigue level is severe fatigue, perform the seat tilting operation and the massage operation at the same time. The seat tilting operation includes: controlling the seat back to tilt backward by a preset relief angle; the massage operation includes: controlling the massage device installed on the seat to start to massage the preset parts of the driver.

[0032] In this embodiment, when the driver is severely fatigued, the body feels extremely sore or stiff, and the mental state is exhausted. At this time, the seat tilting operation and the deep massage operation are performed simultaneously. Thus, while controlling the seat back to tilt backward at a preset soothing angle to relieve the driver's fatigue, the driver's fatigue is also relieved through the deep massage operation. The deep massage operation may include at least one of the following massage modes: Deep massage mode: With a greater intensity, it can penetrate into muscle tissues and is suitable for long-term driving or when the body is relatively fatigued.

[0033] Hot compress massage mode: Combining the hot compress function, it first relaxes the muscles through hot compress and then performs massage, which is suitable for cold weather or when the body is stiff.

[0034] Twisting mode: Simulating twisting movements, it is suitable for relieving the stiffness of the body.

[0035] Zero-gravity mode: Combining with the zero-gravity posture of the seat and the massage function, it allows users to enjoy a more comfortable experience when resting.

[0036] Music rhythm mode: The massage rhythm can be adjusted according to the music beat, enabling users to relax their bodies while enjoying music.

[0037] The above-mentioned deep massage operation can massage some or all of the waist, shoulders and neck, back, buttocks, legs, etc. to relieve fatigue. During this process, the massage intensity or the preset massage parts can also be automatically adjusted according to the user's sitting posture. For example, for the target part where the user is closer to the seat (the body pressure at this part measured by the body pressure sensor on the seat is greater), if massage has already started at this part, the massage intensity and duration for this target part can be increased. If massage has not started at this part currently, massage can be started for this target part (except for the prohibited massage parts set for this driver), that is, adding this target part as one of the preset parts that need to be massaged.

[0038] In one embodiment, before the step S300, that is, before performing the fatigue relief operation according to the current fatigue level, it includes: Receiving a part setting instruction containing the identity information of the driver, and setting the target massage part included in the part setting instruction as the preset part, where the target massage part includes at least one of the neck, shoulders and neck, waist, back, legs and buttocks.

[0039] That is, in this embodiment, the driver can set different preset parts for the moderate massage operation and the deep massage operation, for example, the preset parts to be massaged for the moderate massage operation can be set as the first part set, and the preset parts to be massaged for the deep massage operation can be set as the second part set. Similarly, when a mild massage operation is required in case of mild fatigue, a third part set can be associated with the mild massage operation. The body parts included in the first part set, the second part set, and the third part set can be the same or different. Moreover, the first part set associated with the identity information of different drivers can be different or the same, the second part set associated with the identity information of different drivers can also be different or the same, and the third part set associated with the identity information of different drivers can also be different or the same.

[0040] Among them, the preset parts (such as the first part set, the second part set, and the third part set) can be set according to actual needs. In the default state, the vehicle will massage the above preset parts in a targeted manner under different current fatigue levels. If the driver is not suitable for the above default preset parts, he can select a new preset part suitable for himself in the neck, shoulder neck, waist, back, legs and buttocks according to his actual physical conditions for different current fatigue levels. At this time, the driver needs to send a part setting instruction through the preset display screen on the vehicle or a smart device connected to the controller on the vehicle during non-driving hours. The vehicle will automatically set the target massage part in the part setting instruction as the target massage part associated with the driver. Understandably, for different current fatigue levels, the driver can set different target massage parts (that is, the first part set corresponding to mild fatigue, the second part set corresponding to moderate fatigue, and the third part set corresponding to severe fatigue). The part setting instruction needs to include the driver's identity information. The same vehicle may be driven by different drivers. For different drivers, the preset parts to be set will also be different. Therefore, it is necessary to associate the driver's identity information with the preset part selected by the driver, so that each driver corresponds to the preset part suitable for himself, so as to bring a better soothing experience.

[0041] Understandably, the driver's position setting instruction may also include the selected prohibited massage areas and the maximum massage duration corresponding to different preset areas. That is, due to the special requirements of some drivers, for example, in order to avoid aggravating muscle soreness caused by excessive massage, the maximum massage duration for all preset areas is set to 30 minutes, or the maximum massage duration corresponding to each area can be set differently. For another example, some drivers have serious physical diseases (such as heart disease, hypertension, etc.). At this time, the doctor recommends not to massage the back, shoulders, neck and other areas. Then, the back, shoulders, neck, etc. can be set as prohibited massage areas, and in any case, the driver will not be massaged on the back, shoulders, neck, etc.

[0042] In one embodiment, as Figure 2 shown, the driving state information includes the real-time face image of the driver captured by the camera device installed on the vehicle; In the step S200, determining that the driver is in a fatigued state according to the driving state information includes: S201. Input the real-time face image into a preset image recognition model. Identify the contours of both eyes in the real-time face image through the preset image recognition model, extract the eyelid distances between the upper and lower eyelids of each eye in the contours of both eyes, and output an eye closure result corresponding to the real-time face image based on the two eyelid distances. The eye closure result indicates that both eyes are closed or that at least one eye is not closed. Among them, the preset image recognition model can be a model obtained by training based on an initial neural network. It can be obtained by training multiple facial image samples in a preset image set. Specifically, each facial image sample is associated with a sample closure result, and the sample closure result is used to indicate that both eyes in the facial image are closed or that at least one eye is not closed. Input the facial image sample into an initial neural network with initial parameters. The initial neural network identifies the sample contours of both eyes in the facial image sample, extracts the sample eyelid distances between the upper and lower eyelids of each eye in the sample contours of both eyes (several key points can be selected from the upper and lower eyelids in the sample contours of both eyes, and then the sample eyelid distance can be determined according to the distance between the opposite two key points), and outputs a target closure result corresponding to the facial image sample based on the two sample eyelid distances (for example, when the sample eyelid distance of one eye is less than 0.2 cm, it is determined that the eye is closed, and when the sample eyelid distance corresponding to the other eye is greater than or equal to 0.2 cm, it is determined that the eye is not closed). The target closure result indicates that both eyes are closed or that at least one eye is not closed. When the target closure result does not match the sample closure result, adjust the initial parameters, and identify the next facial image sample according to the initial neural network model after adjusting the initial parameters. Among them, the target closure result and the sample closure result can be the probabilities representing that both eyes are closed (or the probability that at least one eye is not closed). When the difference between the probabilities corresponding to the target closure result and the sample closure result exceeds a preset difference threshold, it is considered that they do not match. Iterate continuously in this way until the target closure result matches the sample closure result, and determine the current initial neural network model as the preset image recognition model.

[0043] Understandably, before the step S201, it is also necessary to collect the real-time face image of the driver through a camera and preprocess the collected real-time face image to improve the signal quality, and then perform filtering to remove noise and interference.

[0044] S202. Obtain the eye closure results corresponding to all the real-time face images collected within a preset duration before the current time point, and determine the actual proportion of the eye closure results indicating that both eyes are closed among all the eye closure results. That is, the actual proportion refers to the percentage of the time when both eyes are closed within the preset duration.

[0045] S203. When the actual ratio exceeds the preset ratio threshold, it is confirmed that the driver is in a fatigued state. Understandably, in this embodiment, the preset ratio threshold can be set according to requirements. For example, it can be set to 10% - 20%, specifically, it can be set to 14%, 15%, 16% or 17%, etc. Understandably, when the actual ratio does not exceed the preset ratio threshold, it is confirmed that the driver is not in a fatigued state. At this time, the vehicle can continue to be controlled to drive in the current mode without performing other operations.

[0046] In one embodiment, the current fatigue level includes mild fatigue, moderate fatigue, and severe fatigue; in step S200, determining the current fatigue level of the driver includes: When the actual ratio belongs to the first ratio range, it is confirmed that the driver is in mild fatigue, and the minimum value of the first ratio range is greater than or equal to the preset ratio threshold; the first ratio range can be set according to requirements. For example, when the preset ratio threshold is 15%, the first ratio range can be 15% - 25%; When the actual ratio belongs to the second ratio range, it is confirmed that the driver is in moderate fatigue, and the minimum value of the second ratio range is greater than the maximum value of the first ratio range; the second ratio range can be set according to requirements. For example, 25% - 35%.

[0047] When the actual ratio is greater than the maximum value of the second ratio range, it is confirmed that the driver is in severe fatigue.

[0048] Understandably, after determining the current fatigue level, the current fatigue level can be encoded and converted, that is, the determined current fatigue level is encoded into digital codes, logic level signals, or specific communication protocol data. For example, mild fatigue is encoded as "01", moderate fatigue is encoded as "10", and severe fatigue is encoded as "11", and is transmitted through a serial port, CAN bus, or other communication interfaces.

[0049] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0050] In one embodiment, a vehicle is provided. The vehicle includes a controller, and the controller includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the fatigue relief control method in the above embodiment. To avoid repetition, it will not be elaborated here. Among them, the controller can be a vehicle controller, or other in-vehicle controller or control module on the vehicle, etc., which is not limited here.

[0051] Each module in the above-mentioned controller can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0052] In the vehicle according to the above embodiment of the present invention, when the controller determines that the current driving mode of the vehicle is the autonomous driving mode and determines that the driver is in a fatigued state according to the driving state information of the vehicle, it first determines the current fatigue level of the driver, and then performs different fatigue relief operations according to the current fatigue level. In this way, during a long-term continuous driving process, for the continuously increasing fatigue degree of the driver, different fatigue relief operations corresponding to the current fatigue level can be used to relieve fatigue, and the relief effect is better. At the same time, it also avoids the situation where the driver develops tolerance and the relief becomes ineffective when only the same fatigue relief operation is used to relieve fatigue during a long-term fatigued process. Therefore, the fatigue relief operation will not be performed in the non-autonomous driving mode, which will not endanger the driving behavior of the driver and ensures driving safety.

[0053] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the fatigue relief control method in the above embodiment. To avoid repetition, it will not be elaborated here.

[0054] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A fatigue relief control method, characterized in that: include: Obtain the vehicle's current driving mode and the driver's driving status information; When the current driving mode is the automatic driving mode and it is determined according to the driving state information that the driver is in a fatigue state, determining a current fatigue level of the driver; A fatigue relief operation is performed according to the current fatigue level.

2. The fatigue relief control method according to claim 1, characterized in that: The performing the fatigue relief operation according to the current fatigue level includes: When the current fatigue level is mild fatigue, a seat tilting operation is performed, and the seat tilting operation includes: controlling the seat back to tilt backward to a preset relief angle.

3. The fatigue relief control method according to claim 1, characterized in that: The performing the fatigue relief operation according to the current fatigue level includes: When the current fatigue level is moderate fatigue, a massage operation is performed, and the massage operation includes: controlling a massage device installed on the seat to start, so as to massage a preset part of the driver.

4. The fatigue relief control method according to claim 1, characterized in that: The performing the fatigue relief operation according to the current fatigue level includes: When the current fatigue level is severe fatigue, the seat tilting operation and the massage operation are performed simultaneously, the seat tilting operation includes: controlling the seat back to tilt backward to a preset relief angle; the massage operation includes: controlling the massage device installed on the seat to start, so as to massage the preset part of the driver.

5. The fatigue relief control method according to claim 1, characterized in that: The driving status information includes a real-time facial image of the driver captured by a camera installed on the vehicle; The determining that the driver is in a fatigue state according to the driving state information includes: Input the real-time facial image into a preset image recognition model, recognize the eye contours in the real-time facial image through the preset image recognition model, extract the eyelid distance between the upper and lower eyelids of each eye in the eye contours, and output an eye closure result corresponding to the real-time facial image according to the two eyelid distances; the eye closure result indicates that both eyes are closed or that at least one eye is not closed; Obtaining eye closure results corresponding to all the real-time facial images collected within a preset time period before a current time point, and determining an actual proportion of the eye closure results representing the closure of both eyes in all the eye closure results; When the actual ratio exceeds a preset ratio threshold, it is confirmed that the driver is in a fatigue state.

6. The fatigue relief control method according to claim 5, characterized in that: The current fatigue level includes mild fatigue, moderate fatigue and severe fatigue; Determining the current fatigue level of the driver includes: When the actual ratio belongs to a first ratio range, it is confirmed that the driver is in a state of mild fatigue, and a minimum value of the first ratio range is greater than or equal to the preset ratio threshold; When the actual ratio belongs to a second ratio range, it is confirmed that the driver is in moderate fatigue, and the minimum value of the second ratio range is greater than the maximum value of the first ratio range; When the actual ratio is greater than the maximum value of the second ratio range, it is confirmed that the driver is in severe fatigue.

7. The fatigue relief control method according to claim 2 or 4, characterized in that: Before performing the fatigue relief operation according to the current fatigue level, the method includes: An angle setting instruction including the driver's identity information is received, and the seat adjustment angle included in the angle setting instruction is set to the preset relief angle, wherein the angle setting instruction is generated after the driver selects the seat adjustment angle from a preset angle adjustment range, and the preset angle adjustment range is 2°-5°.

8. The fatigue relief control method according to claim 3 or 4, characterized in that: Before performing the fatigue relief operation according to the current fatigue level, the method includes: A part setting instruction including the identity information of the driver is received, and a target massage part included in the part setting instruction is set as the preset part, wherein the target massage part includes at least one of the neck, shoulder neck, waist, back, legs and buttocks.

9. A vehicle, comprising a controller, the controller comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the fatigue relief control method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fatigue relief control method according to any one of claims 1 to 8 is implemented.

Images