Driver attention management system and method

Abstract

A driver attention management system and method are provided. The driver attention management system may include a driver monitoring module, a human-machine interface, and an attention management module. The driver monitoring module may be configured to obtain facial feature information of the driver. The human-machine interface may be operable to provide a system interaction stimulus. The attention management module may be configured to determine the driver's attention level based on the facial feature information, the system interaction stimulus, and the driver's response to the system interaction stimulus.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving, and in particular to a driver attention management system and method. Background Art

[0002] Current advanced driver assistance systems (ADAS) have increasingly powerful capabilities. ADAS is designed to completely take over driving control, but it is still unable to fully assume the responsibility of driving control, and the driver is still required to take over in extreme cases. Depending on different driving scenarios, such systems will switch between full control of the vehicle and full handover of control. This is difficult to accept for the driver's experience and safety in an emergency, because the driver's attention may have been completely diverted from vehicle control. Therefore, from the perspective of attention management, it is necessary to maintain a considerable level of driver attention when ADAS is in control. Reduce the requirements for driver attention through auxiliary information or prompts when the driver needs to take over. Summary of the invention

[0003] The present disclosure provides a driver attention management system and method, which can keep the driver's attention at a reasonable level even when the vehicle is in an autonomous driving mode.

[0004] According to one aspect of the present disclosure, a driver attention management system may include a driver monitoring module, a human-computer interaction interface, and an attention management module. The driver monitoring module may be configured to obtain facial feature information of the driver. The human-computer interaction interface may be operable to provide a system interaction incentive. The attention management module may be configured to determine the driver's attention level based on the facial feature information, the system interaction incentive, and the driver's response to the system interaction incentive.

[0005] In an optional embodiment, the attention management module may include a discrete time series generation unit, a correlation determination unit and a response speed determination unit. The discrete time series generation unit may be configured to generate discrete time series of facial feature information, system interaction stimuli and responses, respectively. The correlation determination unit may be configured to determine the correlation between the driver's response and the system interaction stimuli based on the discrete time series of facial feature information, the discrete time series of system interaction stimuli and the discrete time series of responses. The response speed determination unit may be configured to determine the response speed of the driver's response relative to the system interaction stimuli based on the discrete time series of facial feature information, the discrete time series of system interaction stimuli and the discrete time series of responses. The attention level determination unit may be configured to determine the driver's attention level based on the correlation and the response speed.

[0006] In an optional embodiment, the attention management module may further include an attention maintaining unit configured to perform a corresponding wake-up action based on the attention level determined by the attention level determining unit.

[0007] In an optional embodiment, the attention level may include a first level, a second level, and a third level with increasing attention levels. The first level may correspond to a first awakening action, the second level may correspond to a second awakening action, and the third level may correspond to a third awakening action.

[0008] In an optional embodiment, the first awakening action may include controlling the vehicle to sound a first alarm.

[0009] In an optional embodiment, the second wake-up action may include: causing the human-computer interaction interface to issue a visual prompt, the visual prompt being used to prompt the driver to perform a corresponding operation in response to the visual prompt; and in response to determining that the driver has not performed a corresponding operation in response to the visual prompt, controlling the vehicle to issue a second alarm.

[0010] In an optional embodiment, the third wake-up action may include causing the human-computer interaction interface to display push information.

[0011] In an optional embodiment, the attention management module may be further configured to determine the driver's attention level when the host vehicle is in an autonomous driving state.

[0012] According to another aspect of the present disclosure, the driver attention management method may include: obtaining facial feature information of the driver; and determining the driver's attention level based on the facial feature information, system interaction stimuli provided by the human-computer interaction interface, and the driver's response to the system interaction stimuli.

[0013] In an optional embodiment, determining the driver's attention level may include: generating discrete time series of facial feature information, system interaction stimuli, and responses, respectively; determining the correlation between the driver's response and the system interaction stimuli based on the discrete time series of facial feature information, the discrete time series of system interaction stimuli, and the discrete time series of responses; determining the response speed of the driver's response relative to the system interaction stimuli based on the discrete time series of facial feature information, the discrete time series of system interaction stimuli, and the discrete time series of responses; and determining the driver's attention level based on the correlation and the response speed.

[0014] In an optional embodiment, the method may further include executing a corresponding wake-up action based on the attention level determined by the attention level determination unit.

[0015] In an optional embodiment, the attention level may include a first level, a second level, and a third level with increasing attention levels. The first level may correspond to a first awakening action, the second level may correspond to a second awakening action, and the third level may correspond to a third awakening action.

[0016] In an optional embodiment, the first awakening action may include controlling the vehicle to sound a first alarm.

[0017] In an optional embodiment, the second wake-up action may include: causing the human-computer interaction interface to issue a visual prompt, the visual prompt being used to prompt the driver to perform a corresponding operation in response to the visual prompt; and in response to determining that the driver has not performed a corresponding operation in response to the visual prompt, controlling the vehicle to issue a second alarm.

[0018] In an optional embodiment, the third wake-up action may include causing the human-computer interaction interface to display push information.

[0019] In an optional embodiment, the driver's attention level may be determined while the host vehicle is in an autonomous driving state.

[0020] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium may include instructions stored thereon, which, when executed by a processor, cause the processor to perform the driver attention management method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Attached Figure 1 The various embodiments discussed in this document are illustrated generally by way of example and not by way of limitation.

[0022] Figure 1 A block diagram of an example driver attention management system 100 is shown, according to an embodiment.

[0023] Figure 2 A block diagram of an example attention management module 14 is shown, according to an embodiment.

[0024] Figure 3 is a schematic diagram of a driver attention transition process implemented by an example driver attention management system 100 according to the present embodiment.

[0025] Figure 4 is a schematic diagram of an example driver attention management method 400 according to an embodiment.

[0026] Figure 5 is a schematic diagram of a driver attention model according to an embodiment. DETAILED DESCRIPTION

[0027] In the following description, numerous specific details are set forth. However, it should be understood that embodiments of the present invention may be practiced without these specific details. In other instances, well-known circuits, structures, and techniques are not shown in detail to avoid obscuring the understanding of this description.

[0028] References in the specification to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment may include the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.

[0029] As used herein, the term module may include a packaged functional hardware unit designed to be used with other components, a set of instructions executable by a controller (e.g., a processor executing software or firmware), a processing circuit configured to perform a specific function, and a self-contained hardware or software component that interfaces with a larger system. For example, a module may include an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a circuit, a digital logic circuit, an analog circuit, a discrete circuit, a gate, and a combination or combination of other types of hardware. In other embodiments, a module may include a memory that stores instructions that can be executed by a controller to implement the features of the module.

[0030] At present, the ADAS (Advanced Driver Assistance System) installed in the vehicle can already realize autonomous driving in some scenarios. ADAS includes functions such as automatic cruise, automatic braking, lane departure warning, blind spot monitoring and automatic parking assistance, which can provide many auxiliary functions for the driver. In many driving scenarios (such as automatic cruise on highways and automatic following), the driving control of the vehicle can be taken over. However, the current ADAS or similar driving assistance systems can only take over the control of the vehicle in limited circumstances. In other cases, it is still necessary to switch to a driving mode dominated by manual driving. However, there is a concern that the driver will be completely distracted by the vehicle driving being taken over. If the vehicle control is returned to the driver in this state, the driver may not have time to deal with the driving scene in front of him, resulting in an increase in the accident rate. To this end, the present disclosure aims to alleviate the attention gap caused by the transfer of driving control, so that the driver can maintain the required level of attention in the state of autonomous driving, so that the control of the vehicle can be smoothly taken over when needed.

[0031] Figure 1The figure shows a block diagram of an example driver attention management system 100 according to an embodiment. The driver attention management system 100 is disposed in the vehicle 1 , and includes a driver monitoring module 12 , an attention management module 14 and a human-machine interface 16 .

[0032] The driver monitoring module 12 obtains the driver's facial feature information. An example of the driver monitoring module 12 is a DMS (driver monitoring system) camera, which is usually installed on the front side of the driver's face, such as on the center console or dashboard. The DMS camera obtains the driver's facial feature information by detecting changes in the eyes and face. Facial feature information includes but is not limited to eyelid status, nodding movements, eye movements, and mouth movements. Based on these facial feature information, gesture recognition results can be preliminarily generated, such as fatigue (yawning, closing eyes), making phone calls, distracted driving (looking around, looking down), smoking, and leaving the driving sight.

[0033] The human-machine interaction interface 16 is used to display information and can be controlled to provide system interaction incentives. The human-machine interaction interface 16 can be a center console, an instrument panel, or a separately arranged display, etc. The system interaction incentive instructs the driver to perform a corresponding operation as a response. Examples of system interaction incentives include, but are not limited to: display push information (such as messages, services, prompt boxes, button dialog boxes, etc.), voice messages (such as alarms, voice prompt lights requiring the driver to perform specific operations). The system interaction incentives and the driver's response to the system interaction incentives can be collected separately.

[0034] The attention management module 14 determines the driver's attention level based on the facial feature information from the driver monitoring module 12 , the system interaction stimuli provided by the human-machine interface 16 , and the driver's response to the system interaction stimuli.

[0035] Figure 2 The figure shows a block diagram of an example attention management module 14 according to an embodiment. In this embodiment, the attention management module 14 includes a discrete time series generation unit 141, a relevance determination unit 142, a response speed determination unit 143, an attention level determination unit 144 and an attention maintenance unit 145.

[0036] The discrete time series generation unit 141 generates discrete time series of facial feature information, system interaction stimulus, and driver's response to the system interaction stimulus, respectively.

[0037] The correlation determination unit 142 determines the correlation between the driver response and the system interaction stimulus based on the discrete time sequence of the facial feature information generated by the discrete time sequence generation unit 141, the discrete time sequence of the system interaction stimulus and the discrete time sequence of the response. The system interaction stimulus can be assigned corresponding calculation values ​​according to the different degrees of involvement of various interactive functions to form the discrete sequence of the above-mentioned system interaction stimulus. The driver response is also assigned calculation values ​​according to the form and significance of the driver's reaction action to form a discrete time sequence of the driver's response. The calculated and assigned driver response includes, for example: driving operation feedback, human-machine interface operation feedback, posture movement changes, line of sight changes, etc. A part of the driver response can be obtained from the discrete time sequence of the response, such as posture movement changes and line of sight changes. After obtaining the discrete sequence of the system interaction stimulus and the discrete sequence of the driver's response, the correlation can be calculated by the following formula (1).

[0038]

[0039] Among them, y(n) is a truncated excitation sequence with a length of N, and x(t) is a continuous response sequence.

[0040] The response speed determination unit 143 determines the response speed of the driver's response relative to the system interaction stimulus based on the discrete time sequence of the facial feature information, the discrete time sequence of the system interaction stimulus, and the discrete time sequence of the response generated by the discrete time sequence generation unit 141. As an example, the time difference between the peak of the correlation and the system interaction stimulus sequence can be calculated. The smaller the time difference, the faster the response speed.

[0041] The attention level determination unit 144 determines the driver's attention level based on the relevance determined by the relevance determination unit 142 and the response speed determined by the response speed determination unit 143. In this embodiment, the attention level determination unit 144 may calculate an attention score by weighted summing the relevance and the response speed, and determine the driver's attention level based on the attention score.

[0042] The attention maintaining unit 145 performs corresponding wake-up actions based on the attention level determined by the attention level determining unit 144, so as to provide the driver's attention level and maintain it at a certain level. The attention level can be distinguished according to the attention level. According to different levels of attention levels, wake-up actions of corresponding intensity can be selected. The wake-up action includes various means that can attract the driver's attention, such as voice, vibration, visual reminders, etc. For the lowest attention level, the strongest wake-up action can be used. On the contrary, when the attention level is higher, a milder wake-up action can be used. When the attention level rises to the designed highest level, the purpose of performing the wake-up action is to maintain the driver at this attention level.

[0043] In an example embodiment, the attention level can be divided into three levels, for example. The first level of attention is the weakest. At this time, the driver may be in a drowsy state, unable to respond to the system interaction stimulus provided by the human-machine interaction interface 16, or responding very slowly, resulting in a low correlation between the driver's response and the system interaction stimulus and a low response speed of the driver's response relative to the system interaction stimulus. At this time, the driver's attention may have been completely diverted from vehicle driving, and it is necessary to attract part of the driver's attention to vehicle driving as soon as possible.

[0044] Since the driver at the first attention level may no longer pay attention to the human-machine interface 16, the attention maintenance unit 145 may perform the first wake-up action with the highest intensity. As an example of the first wake-up action, for example, the vehicle 1 may be caused to directly issue a strong alarm (also referred to as the first alarm herein). The strong alarm may be issued, for example, via an onboard speaker, or may be achieved by vibration of the driver's seat or other means, in order to bring the driver's attention back to the human-machine interface 16. In some embodiments, the alarm issued by the speaker may contain a voice instruction to prompt the driver to observe the human-machine interface 16.

[0045] When the driver's attention returns to the human-computer interaction interface 16, the attention level determined in real time by the attention level determination unit 144 can rise to a second level higher than the first level or a higher third level. When the driver's attention level is at the second level, the attention maintenance unit 145 can perform a second wake-up action. Since the driver's attention level is higher than the first level at this time, the intensity of the second wake-up action can be lower than the first wake-up action. As an example, the human-computer interaction interface 16 can issue a visual prompt as a system interaction stimulus at this time. Visual prompts include but are not limited to color changes, flashing, etc. In the case where the human-computer interaction interface 16 uses a multi-layer display, the visual prompt can be an image jumping back and forth between display layers at different depths. If the driver's response to the visual prompt (such as eye movement) is good, the calculated driver response has a high correlation with the system interaction stimulus, and the response speed is also fast, and the driver's attention level can be determined to be the third level with the highest attention.

[0046] At this time, the attention maintenance unit 145 can perform a third wake-up action to maintain the driver's attention level. For example, the attention maintenance unit 145 can cause the human-computer interaction interface 16 to push information to maintain the driver's attention. The pushed information may not be information related to driving or safety, for example, it may be entertainment information. The pushed information itself can also be used as a system interaction stimulus. The driver's eyelid state, eye movement, etc. can be used as a corresponding response. Therefore, the driver's attention level can continue to be monitored even in the state of pushing information.

[0047] However, after the driver's attention returns to the human-machine interaction interface 16, the driver may still not have reached a sufficient level of attention. For example, the driver may be in a distracted state, with only his face facing the human-machine interaction interface 16, and not paying substantial attention to the content of the human-machine interaction interface 16, and thus does not respond to the visual prompts provided by the human-machine interaction interface 16. At this time, as a continuation of the second wake-up action, the attention maintenance unit 145 can, for example, cause the vehicle 1 to issue an alarm (also referred to as the second alarm herein) until the driver responds accordingly to the visual prompt. Since the driver's attention level in this scenario is higher than the first level, the intensity of the second alarm can be weaker than the first alarm described above.

[0048] Figure 3 is a schematic diagram of a driver attention transition process implemented by an example driver attention management system 100 according to the present embodiment.

[0049] As described above, when the driver's attention is at the lowest first level, his attention has been separated from the human-computer interaction interface 16. Therefore, a first wake-up action with a higher intensity (such as a first alarm) is used to make the driver refocus on the human-computer interaction interface 16. After the driver's line of sight returns to the human-computer interaction interface 16, a second wake-up action (such as a visual prompt and a second alarm) can be used to further improve the driver's attention level. When the driver's attention level is improved to the third level, a third wake-up action (such as a push message) can be used to keep the driver's attention at the third level. As a result, when there is a need to switch to manual driving, it will not add too much attention burden to the driver, so that the driver can quickly adapt to the control of the vehicle.

[0050] Figure 4 is a schematic diagram of an example driver attention management method 400 according to an embodiment. The method 400 is performed when the vehicle is in an autonomous driving state.

[0051] like Figure 4 As shown, in step 401, the driver monitoring module 12 (eg, DMS) is used to obtain the driver's facial feature information in real time and send it to the attention management module 14. The facial feature information includes, for example, eyelid status, nodding movements, eye movements, mouth movements, etc.

[0052] In step 402 , the attention management module 14 determines the attention level of the driver based on the facial feature information from the driver monitoring module 12 , the system interaction stimulus provided by the human-machine interface 16 , and the driver's response to the system interaction stimulus.

[0053] According to the attention level determined by the attention management module 14, a corresponding wake-up action may be performed.

[0054] For example, if it is determined in step 402 that the driver's attention level is the lowest first level, then in step 403, the attention maintenance unit 145 may perform the first awakening action with the highest intensity. For example, the attention maintenance unit 145 may cause the vehicle 1 to directly issue a strong alarm. Then, the driver monitoring module 12 continues to monitor the driver's facial feature information, and the attention management module 14 continues to determine the driver's attention level.

[0055] If it is determined in step 402 that the driver's attention level is a second level higher than the first level, the attention maintenance unit 145 can perform a second wake-up action with a lower intensity than the first wake-up action. For example, the attention maintenance unit 145 can cause the human-machine interface 16 to issue a visual prompt in step 404. The visual prompt is, for example, a color change, a flash, etc. If the driver does not respond to the visual prompt, such as a responsive eye movement (no in step 406), the attention maintenance unit 145 can cause the vehicle 1 to issue a second alarm in step 407. Compared with the first alarm, the intensity of the second alarm can be slightly weaker because the driver's attention level is higher than the first level. If the driver responds well to the visual prompt issued by the human-machine interface 16 in step 404 (yes in step 406), return to step 401. At this time, it can be determined through steps 401 and 402 that the driver's attention level is at a higher third level, and then enter step 405.

[0056] In step 405, since the driver is at the highest third level and can take over the control of the vehicle 1 at any time, the attention maintaining unit 145 can maintain the driver's attention level by performing the third awakening action 405. For example, the attention maintaining unit 145 can cause the human-machine interface 16 to push information to maintain the driver's attention. The pushed information may not be information related to driving or safety, for example, it may be entertainment information. After that, the process returns to step 401.

[0057] It should be understood that the above-described embodiment divides the driver's attention level into three levels and adopts three wake-up actions, which is only an example. It can be further subdivided or divided into only two levels as needed. The wake-up action is not limited to the example described above, and other ways that can attract the driver's attention can be adopted. In addition, the attention level and the wake-up action may not be a one-to-one correspondence. For example, multiple attention levels can correspond to the same wake-up action. As long as the driver's attention level can be improved and maintained at a certain level through the wake-up action, the correspondence between the attention level and the wake-up action can be designed arbitrarily.

[0058] Figure 5 is a schematic diagram of a driver attention model according to an embodiment. Figure 5As shown in part (a) of the figure, for traditional ADAS, when autonomous driving is performed through ADAS, machine control assumes all control levels required to control the vehicle, including driving and safety. At this time, the driver's attention to vehicle driving is very limited, and even if the attention to entertainment information ("others" in the figure) is taken into account, the proportion is very small. Once it is necessary to switch to manual driving, as shown in (b), machine control will only assume the responsibility for vehicle safety, and the control of the vehicle will be returned to the driver. By comparing the rectangular segments on the left side of parts (a) and (b), it can be seen that at this time, the driver's attention requirements will be significantly increased. In some embodiments, when the vehicle is manually controlled, the machine control can provide certain control assistance (as shown in "driving" on the right side of part (d)) to reduce the driver's attention burden, as shown in part (d). At this time, the driver's attention for controlling the vehicle 1 (left side of part (d)) is not significantly increased compared with the autonomous mode (left side of part (c)), and it is only necessary to transfer the attention to entertainment information (as shown in "others" on the left side of part (c)) to driving the vehicle.

[0059] In contrast, if the control based on attention management of the present disclosure is adopted, the driver's attention can be maintained at a certain level even during autonomous driving through the method described above, as shown in the dotted box in part (c). Moreover, by using push information such as entertainment information to maintain the driver's attention, the driver will not feel too dull or tired. When it is necessary to switch to manual driving, the driver can quickly switch his attention to vehicle driving without increasing too much attention burden, as shown in part (d).

[0060] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium that represent various logic within a processor, which when read by a machine causes the machine to fabricate logic for performing the techniques described herein.

[0061] Such machine-readable storage media may include, but are not limited to, a non-transitory tangible arrangement of articles manufactured or formed by a machine or apparatus, including storage media such as: a hard disk; any other type of disk, including a floppy disk, an optical disk, a compact disk-read only memory (CD-ROM), a compact disk-read and writeable (CD-RW), and a magneto-optical disk; semiconductor devices such as read-only memory (ROM), random access memory (RAM) such as dynamic random access memory (DRAM) and static random access memory (SRAM), erasable programmable read-only memory (EPROM), flash memory, electrically erasable programmable read-only memory (EEPROM); phase change memory (PCM); a magnetic card or an optical card; or any other type of medium suitable for storing electronic instructions.

[0062] The preferred embodiments of the present invention are described in detail above. However, it should be understood that the present invention can be implemented in various ways and variations without departing from its broad spirit and scope. A person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should fall within the scope of protection determined by the claims of the present invention.

Claims

1. A driver attention management system, comprising: A driver monitoring module, configured to obtain facial feature information of the driver; A human-computer interaction interface operable to provide system interaction incentives; as well as an attention management module configured to determine the driver's attention level based on the facial feature information, the system interaction stimulus, and the relevance and response speed of the driver's response to the system interaction stimulus, wherein the relevance indicates the degree of relevance of the driver's response to the system interaction stimulus and is represented by the following formula: Wherein, y(n) is the discrete time series of the interactive excitation of the system, N is the length, and x(t) is the discrete time series of the response.

2. The driver attention management system according to claim 1, characterized in that: The attention management module comprises: A discrete time series generating unit, configured to respectively generate the facial feature information, the discrete time series of the system interaction stimulus, and the discrete time series of the response; A relevance determination unit configured to determine the relevance based on a discrete time sequence of the facial feature information, a discrete time sequence of the system interaction stimulus, and a discrete time sequence of the response; a response speed determination unit configured to determine the response speed of the driver's response relative to the system interaction stimulus based on the discrete time series of the facial feature information, the discrete time series of the system interaction stimulus, and the discrete time series of the response; and The attention level determination unit is configured to determine the driver's attention level based on the correlation and the response speed.

3. The driver attention management system according to claim 1, characterized in that: The attention management module also includes: The attention maintaining unit is configured to perform a corresponding wake-up action based on the attention level determined by the attention level determining unit.

4. The driver attention management system according to claim 3, characterized in that: The attention levels include a first level, a second level and a third level with increasing attention levels. The first level corresponds to a first wake-up action, The second level corresponds to a second wake-up action, and The third level corresponds to a third wake-up action.

5. The driver attention management system according to claim 4, characterized in that: The first awakening action includes controlling the vehicle to issue a first alarm.

6. The driver attention management system according to claim 4, characterized in that: The second wake-up action includes: causing the human-machine interaction interface to issue a visual prompt, wherein the visual prompt is used to prompt the driver to perform a corresponding operation according to the visual prompt; and In response to determining that the driver does not perform the corresponding operation in response to the visual prompt, controlling the vehicle to issue a second alarm.

7. The driver attention management system according to claim 4, characterized in that: The third awakening action includes causing the human-computer interaction interface to display push information.

8. The driver attention management system according to any one of claims 1 to 7, characterized in that: The attention management module is further configured to determine the driver's attention level when the host vehicle is in an autonomous driving state.

9. A driver attention management method, comprising: Obtaining the driver's facial feature information; as well as The driver's attention level is determined based on the facial feature information, the system interaction stimulus provided by the human-machine interaction interface, and the relevance and response speed of the driver's response to the system interaction stimulus, wherein the relevance indicates the degree of relevance of the driver's response to the system interaction stimulus and is represented by the following formula: Wherein, y(n) is the discrete time series of the interactive excitation of the system, N is the length, and x(t) is the discrete time series of the response.

10. The driver attention management method according to claim 9, characterized in that: Determining the driver's attention level includes: Generating the facial feature information, the discrete time series of the system interaction excitation, and the discrete time series of the response respectively; Determining the relevance based on the discrete time sequence of the facial feature information, the discrete time sequence of the system interaction stimulus, and the discrete time sequence of the response; Determining the response speed of the driver's response relative to the system interaction stimulus based on the discrete time sequence of the facial feature information, the discrete time sequence of the system interaction stimulus, and the discrete time sequence of the response; and The driver's attention level is determined based on the relevance and the response speed.

11. The driver attention management method according to claim 9, further comprising: A corresponding awakening action is performed based on the attention level determined by the attention level determination unit.

12. The driver attention management method according to claim 11, characterized in that: The attention levels include a first level, a second level and a third level with increasing attention levels. The first level corresponds to a first wake-up action, The second level corresponds to a second wake-up action, and The third level corresponds to a third wake-up action.

13. The driver attention management method according to claim 12, characterized in that: The first awakening action includes controlling the vehicle to issue a first alarm.

14. The driver attention management method according to claim 12, characterized in that: The second wake-up action includes: causing the human-machine interaction interface to issue a visual prompt, wherein the visual prompt is used to prompt the driver to perform a corresponding operation according to the visual prompt; and In response to determining that the driver does not perform the corresponding operation in response to the visual prompt, controlling the vehicle to issue a second alarm.

15. The driver attention management method according to claim 12, characterized in that: The third awakening action includes causing the human-computer interaction interface to display push information.

16. The driver attention management method according to any one of claims 9 to 15, characterized in that: When the host vehicle is in an autonomous driving state, the driver's attention level is determined. 17 . A non-transitory computer-readable storage medium, comprising instructions stored thereon, which, when executed by a processor, cause the processor to perform the driver attention management method according to any one of claims 9 to 16.

Images