Information acquisition methods, devices, computer equipment and storage media

Abstract

This invention relates to an information acquisition method, apparatus, computer equipment, and storage medium. The method includes: acquiring the duration of attention a driver of a vehicle pays attention to a target surrounding vehicle, and determining the collision time of the target surrounding vehicle, wherein the target surrounding vehicle is any one of the surrounding vehicles, the duration of attention paid by the driver to the target surrounding vehicle indicates the duration of the driver's attention to the target surrounding vehicle, and the duration of attention is determined based on the driver's gaze point; and determining the collision risk level of the target surrounding vehicle based on the duration of attention paid by the driver to the target surrounding vehicle and the collision time of the target surrounding vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically to information acquisition methods, devices, computer equipment, and storage media. Background Technology

[0002] Obtaining the collision risk level of nearby vehicles is crucial for autonomous driving systems to make driving decisions, such as lateral and longitudinal control strategies. Current technologies that rely on a single factor—vehicle parameters—to determine the collision risk level of nearby vehicles suffer from low accuracy. Therefore, improving the accuracy of the obtained collision risk results is a problem that needs to be addressed. Summary of the Invention

[0003] One of the objectives of this invention is to provide an information acquisition method, apparatus, computer device, and storage medium to solve the problem.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] An information acquisition method, comprising:

[0006] The driver of the vehicle pays attention to a target surrounding vehicle for the vehicle for a period of time, and the collision time of the target surrounding vehicle is determined. The target surrounding vehicle is any one of the surrounding vehicles of the vehicle. The driver's attention to the target surrounding vehicle indicates the duration of the driver's attention to the target surrounding vehicle. The attention duration is determined based on the driver's gaze point.

[0007] The collision risk level of the vehicles surrounding the target is determined based on the driver's attention duration to the vehicles surrounding the target and the collision time of the vehicles surrounding the target.

[0008] Based on the aforementioned technical means, the collision risk level of the surrounding vehicles is obtained by utilizing multiple factors, namely, the driver's attention duration towards the target surrounding vehicles and the collision time of the target surrounding vehicles. Considering the driver-related characteristics of the collision risk level—that is, the actions of the surrounding vehicles that the driver is paying attention to usually have a significant impact on the vehicle's actions—the driver's attention duration towards the target surrounding vehicles in the information acquisition method provided by this invention can quantify the degree of driver attention to the surrounding vehicles more accurately. The driver's attention duration towards surrounding vehicles has a high correlation with the collision risk level. Simultaneously, by utilizing the collision time and the driver's attention duration towards the surrounding vehicles, which are both highly correlated with the collision risk level, the accuracy of the obtained collision risk level is improved.

[0009] Furthermore, based on the driver's attention duration to the vehicles surrounding the target and the collision time of the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined, including:

[0010] Based on the comparison result between the driver's attention duration to the vehicles surrounding the target and the first attention duration threshold, a attention target judgment result for the vehicles surrounding the target is generated, wherein the attention target judgment result for the vehicles surrounding the target indicates whether the vehicles surrounding the target are the driver's attention targets;

[0011] Based on the collision time of the vehicles surrounding the target and the target attention determination results of the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined.

[0012] Furthermore, based on the collision time of the vehicles surrounding the target and the target of interest assessment results of the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined, including:

[0013] When the target attention determination result of the vehicles surrounding the target indicates that the vehicles surrounding the target are not the driver's target of attention, and the vehicles surrounding the target were previously the driver's target of attention within the target's previous time period, the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined based on the collision time of the vehicles surrounding the target. The target's previous time period is a time period whose end time is the current time and whose duration is a preset observation duration. The collision risk level of the vehicles surrounding the target is determined based on the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

[0014] Furthermore, based on the collision risk level of the autonomous driving systems corresponding to the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined, including:

[0015] The difference between the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles and a preset value is determined as the collision risk level of the target surrounding vehicles.

[0016] Furthermore, based on the collision time of the vehicles surrounding the target and the target of interest assessment results of the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined, including:

[0017] When the target attention determination result of the vehicles surrounding the target indicates that the vehicles surrounding the target are the driver's target attention, the driver correction level corresponding to the vehicles surrounding the target is determined according to the driver's attention duration to the vehicles surrounding the target, and the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined according to the collision time of the vehicles surrounding the target.

[0018] The sum of the driver correction level corresponding to the vehicle surrounding the target and the collision risk level of the autonomous driving system corresponding to the vehicle surrounding the target is determined as the collision risk level of the vehicle surrounding the target.

[0019] Furthermore, based on the driver's attention duration to vehicles surrounding the target, the driver correction level corresponding to the vehicles surrounding the target is determined, including:

[0020] When the driver's attention duration to the vehicles surrounding the target is not less than a first attention duration threshold and the driver's attention duration to the vehicles surrounding the target is not greater than a second attention duration threshold, the first correction level is determined as the driver correction level corresponding to the vehicles surrounding the target, wherein the second attention duration threshold is greater than the first attention duration threshold.

[0021] When the driver's attention duration to the vehicles surrounding the target exceeds the second attention duration threshold, the second correction level is determined as the driver correction level corresponding to the vehicles surrounding the target, and the second correction level is higher than the first correction level.

[0022] Furthermore, based on the collision time of the vehicles surrounding the target, the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined, including:

[0023] Based on the collision time and collision time threshold of the vehicles surrounding the target, determine the type of vehicles surrounding the target that are related to collision risk;

[0024] Based on the types of collision risk associated with the vehicles surrounding the target, determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

[0025] Furthermore, based on the collision time and collision time threshold of the vehicles surrounding the target, the types of vehicles surrounding the target that are related to collision risk are determined, including:

[0026] When the collision time of the vehicles surrounding the target is greater than the target collision time threshold, the no-collision-risk type is determined as the collision-risk-related type of the vehicles surrounding the target.

[0027] When the collision time of the vehicles surrounding the target is not greater than the target collision time threshold, the collision risk type will be determined as the collision risk-related type of the vehicles surrounding the target.

[0028] And based on the types of collision risk associated with the target surrounding vehicles, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles is determined, including:

[0029] When the collision risk-related type of the vehicles surrounding the target is no collision risk, the preset minimum risk level used to determine the collision risk level of the autonomous driving system will be determined as the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

[0030] When the collision risk associated with the target surrounding vehicles is a collision risk type, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles is determined based on the collision time of the target surrounding vehicles, the correlation between the collision time of the surrounding vehicles and the collision risk level of the autonomous driving system corresponding to the surrounding vehicles, wherein the preset minimum risk level used to determine the collision risk level of the autonomous driving system is lower than the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles determined when the collision risk associated with the target surrounding vehicles is a collision risk type.

[0031] An information acquisition device, comprising:

[0032] The acquisition unit is used to acquire the duration of the driver's attention to the target surrounding vehicle of the vehicle and to determine the collision time of the target surrounding vehicle of the vehicle. The target surrounding vehicle is any one of the surrounding vehicles of the vehicle. The duration of the driver's attention to the target surrounding vehicle of the vehicle indicates the duration of the driver's attention to the target surrounding vehicle. The duration of attention is determined based on the driver's gaze point.

[0033] The determining unit is used to determine the collision risk level of the vehicles surrounding the target based on the driver's attention duration to the vehicles surrounding the target and the collision time of the vehicles surrounding the target.

[0034] Furthermore, the determining unit is also configured to generate a target attention judgment result for the target surrounding vehicles based on the comparison result of the driver's attention duration for the target surrounding vehicles and a first attention duration threshold, wherein the target attention judgment result for the target surrounding vehicles indicates whether the target surrounding vehicles are the driver's target attention; and determine the collision risk level of the target surrounding vehicles based on the collision time of the target surrounding vehicles and the target attention judgment result for the target surrounding vehicles.

[0035] Furthermore, the determining unit is also configured to, when the target attention determination result of the target surrounding vehicles indicates that the target surrounding vehicles are not the driver's target of attention and the target surrounding vehicles were previously the driver's target of attention during the target's previous time period, determine the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles based on the collision time of the target surrounding vehicles, wherein the target's previous time period is a time period with an end time of the current time and a duration of a preset observation duration; and determine the collision risk level of the target surrounding vehicles based on the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles.

[0036] Furthermore, the determining unit is also used to determine the difference between the collision risk level of the autonomous driving system corresponding to the target surrounding vehicle and a preset value as the collision risk level of the target surrounding vehicle when the target surrounding vehicle's target attention determination result indicates that the target surrounding vehicle is not the driver's target of attention and the target surrounding vehicle was used as the driver's target of attention in the previous time period of the target.

[0037] Furthermore, the determining unit is also configured to, when the target attention determination result of the target surrounding vehicles indicates that the target surrounding vehicles are the driver's target attention, determine the driver correction level corresponding to the target surrounding vehicles based on the driver's attention duration to the target surrounding vehicles, and determine the autonomous driving system collision risk level corresponding to the target surrounding vehicles based on the collision time of the target surrounding vehicles; and determine the collision risk level of the target surrounding vehicles as the sum of the driver correction level corresponding to the target surrounding vehicles and the autonomous driving system collision risk level corresponding to the target surrounding vehicles.

[0038] Furthermore, the determining unit is also configured to determine the first correction level as the driver correction level corresponding to the target surrounding vehicle when the driver's attention duration to the target surrounding vehicle is not less than a first attention duration threshold and the driver's attention duration to the target surrounding vehicle is not greater than a second attention duration threshold, wherein the second attention duration threshold is greater than the first attention duration threshold; and to determine the second correction level as the driver correction level corresponding to the target surrounding vehicle when the driver's attention duration to the target surrounding vehicle is greater than the second attention duration threshold, wherein the second correction level is higher than the first correction level.

[0039] Furthermore, the determining unit is also used to determine the collision risk-related type of the vehicles surrounding the target based on the collision time and collision time threshold of the vehicles surrounding the target; and to determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target based on the collision risk-related type of the vehicles surrounding the target.

[0040] Furthermore, the determining unit is also configured to: when the collision time of the vehicles surrounding the target is greater than a target collision time threshold, determine the no-collision-risk type as the collision-risk-related type of the vehicles surrounding the target; when the collision time of the vehicles surrounding the target is not greater than the target collision time threshold, determine the collision-risk-related type of the vehicles surrounding the target; the determining unit is also configured to: when the collision-risk-related type of the vehicles surrounding the target is a no-collision-risk type, determine the preset minimum risk level used to determine the collision risk level of the autonomous driving system as the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target; when the collision-risk-related type of the vehicles surrounding the target is a collision-risk-related type, determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target based on the correlation between the collision time of the vehicles surrounding the target, the collision time of the surrounding vehicles, and the collision risk level of the autonomous driving system corresponding to the surrounding vehicles, wherein the preset minimum risk level used to determine the collision risk level of the autonomous driving system is less than the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target determined when the collision-risk-related type of the vehicles surrounding the target is a collision-risk-related type.

[0041] The beneficial effects of this invention are:

[0042] This invention utilizes multiple factors, namely the driver's attention duration to surrounding vehicles and the collision time of those vehicles, to obtain the collision risk level of the vehicle's surrounding vehicles. Considering the driver-centric nature of collision risk level—that is, the actions of surrounding vehicles observed by the driver typically have a significant impact on the vehicle's actions—the information acquisition method provided by this invention allows for a relatively precise quantification of the driver's attention duration to surrounding vehicles. The driver's attention duration to surrounding vehicles has a high correlation with the collision risk level. Furthermore, by utilizing both the collision time and the driver's attention duration, which are highly correlated with the collision risk level, to obtain the collision risk level of the vehicle's surrounding vehicles, the accuracy of the obtained collision risk level is improved. Attached Figure Description

[0043] Figure 1 A flowchart illustrating the information acquisition method provided in an embodiment of the present invention;

[0044] Figure 2 A flowchart illustrating another information acquisition method provided in an embodiment of the present invention;

[0045] Figure 3 A flowchart illustrating an example of obtaining the collision risk level of surrounding vehicles for a vehicle;

[0046] Figure 4 This is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0047] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0048] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0049] refer to Figure 1 This diagram illustrates a flowchart of the information acquisition method provided by an embodiment of the present invention. It should be noted that the "self-driving vehicle" can be any vehicle to which the information acquisition method provided by the embodiment of the present invention can be applied. During the driving of the self-driving vehicle, the information acquisition method provided by the embodiment of the present invention can be executed periodically according to a preset cycle duration. Steps S101-S102 can be periodically executed for each surrounding vehicle of the self-driving vehicle. Thus, the collision risk level of each surrounding vehicle of the self-driving vehicle is obtained. The information acquisition method provided by the embodiment of the present invention can be executed with the authorization of the self-driving vehicle's driver. The driver's perspective image captured by the camera of the device worn by the driver provided by the embodiment of the present invention can be used with the driver's authorization.

[0050] In step S101, the duration of the driver's attention to the target surrounding vehicles of the vehicle is obtained, and the collision time of the target surrounding vehicles of the vehicle is determined.

[0051] In the disclosed embodiment, the surrounding vehicles of the vehicle are the vehicles near the vehicle. The target surrounding vehicles of the vehicle can be any one of the surrounding vehicles of the vehicle.

[0052] In one possible implementation, the surrounding vehicles of the vehicle are: vehicles within a preset shape centered on the vehicle's current position.

[0053] In another possible implementation, the surrounding vehicles of the vehicle are those whose location is less than a distance threshold from the vehicle's current location.

[0054] In this embodiment of the invention, a gaze point determination method based on images can be used, determining the gaze point based on environmental images captured by the vehicle's camera or driver-view images captured by the camera of a device worn by the driver. For each captured environmental image, the driver's gaze point is determined based on the captured environmental image.

[0055] The environmental images captured by the vehicle's camera describe objects such as vehicles, pedestrians, and obstacles in the environment in which the vehicle is located.

[0056] In one possible implementation, the driver wears an eye tracker. The data obtained from the eye tracker includes eye movement data and images from the driver's perspective. The eye movement data includes fixation points and saccades. Saccades record the driver's viewpoint switching process. Driver saccades are often caused by eye movement, therefore, it is necessary to extract fixation points from the eye movement data and filter saccades. The driver's fixation points can be extracted using a speed thresholding method. The principle of the speed thresholding method is to use the speed of the driver's viewpoint movement to distinguish between fixation and saccades. Typically, the speed of fixation point movement is less than 100° / second; the speed of saccade movement is greater than 300° / second. The speed threshold can be set to 100° / second. If the speed of the viewpoint movement is less than the speed threshold, the viewpoint can be identified as a fixation point; if the speed of the viewpoint movement is greater than the speed threshold, the viewpoint can be identified as a saccade.

[0057] It's important to note that when the algorithm used to detect gaze points outputs coordinates of the gaze point in the driver's view image's coordinate system, these coordinates need to be converted to the coordinate system of the corresponding environmental image captured by cameras of surrounding vehicles. This allows us to determine the gaze point's position within the environmental image and, based on its position and the bounding box surrounding the surrounding vehicles, whether the gaze point is fixed on a vehicle. The transformation relationship between the gaze point's coordinates in the driver's view image, the coordinates of pixels in the driver's view image, and the coordinates of pixels in the environmental image can be used to convert the coordinates in the driver's view image to those in the environmental image's coordinate system. To obtain this transformation relationship, the environmental image whose acquisition time is closest to that of the driver's view image can be identified as the corresponding environmental image. The SURF feature matching method can be applied to a driver's view image and the corresponding environmental image to obtain the transformation relationship between the coordinates of pixels in the driver's view image in the image coordinate system and the coordinates of pixels in the environmental image in the image coordinate system.

[0058] In this embodiment of the invention, for vehicles surrounding the target vehicle, the driver of the vehicle indicates the duration of attention the driver pays to the vehicles surrounding the target vehicle.

[0059] In step S101, for the target surrounding vehicles of the vehicle, the parameter value of the attention duration parameter of the target surrounding vehicles of the vehicle can be read, thereby obtaining the attention duration of the driver of the vehicle for the target surrounding vehicles of the vehicle.

[0060] Attention duration to vehicles surrounding the target is determined based on the driver's gaze point. The driver's gaze point is determined based on the image used to determine the driver's gaze point.

[0061] It should be noted that the parameter value of the attention duration parameter for vehicles around the target vehicle is a variable.

[0062] For vehicles in the vicinity of the vehicle, before the vehicle is first detected and the attention duration parameter of the vehicle is updated, the driver's attention duration parameter for the vehicle is set to an initial value of 0.

[0063] In this embodiment of the invention, the parameter value of the attention duration parameter of the target surrounding vehicles of the vehicle is updated based on whether the driver's gaze point, determined by the image used to determine the driver's gaze point of the vehicle, is fixed on the target surrounding vehicles.

[0064] Whether the driver's gaze, determined from the image used to determine the driver's gaze, is fixed on surrounding vehicles can be determined based on the following: the image used to determine the driver's gaze, and the environmental image corresponding to the image used to determine the driver's gaze.

[0065] The environmental image corresponding to the image used to determine the driver's gaze point of the vehicle can be one of the following: a first environmental image, a second environmental image, or a third environmental image.

[0066] The first environmental image is the environmental image whose acquisition time is closest to the acquisition time of the image used to determine the driver's gaze point of the vehicle.

[0067] The second environmental image is: an environmental image whose acquisition time is earlier than that of the image used to determine the driver's gaze point of the vehicle, and an environmental image whose acquisition time is closest to that of the image used to determine the driver's gaze point of the vehicle.

[0068] The third environmental image is: an environmental image whose acquisition time is later than that of the image used to determine the driver's gaze point of the vehicle, and an environmental image whose acquisition time is closest to that of the image used to determine the driver's gaze point of the vehicle.

[0069] Given an image j used to determine the driver's gaze point and an environmental image k corresponding to the image j, if the coordinates of the driver's gaze point determined by image j in the environmental image k are within the detection box of vehicles surrounding the target in the environmental image k, then it can be determined that the driver's gaze point determined by image j is located on a vehicle surrounding the target.

[0070] Here, the image j used to determine the driver's gaze point of the vehicle can be any image used to determine the driver's gaze point of the vehicle.

[0071] Updating the parameter value of the driver's attention duration to surrounding vehicles may include steps S1011 and S1012. Step S1011 is used to increase the parameter value of the driver's attention duration to surrounding vehicles, and step S1012 is used to reset the parameter value of the driver's attention duration to surrounding vehicles.

[0072] In step S1011, for the target surrounding vehicles of the vehicle, if it is determined that the driver's gaze point, determined by the (t-1)th image used to determine the driver's gaze point, is fixed on the target surrounding vehicles, and it is also determined that the driver's gaze point, determined by the tth image used to determine the driver's gaze point, is fixed on the target surrounding vehicles, then the parameter value of the driver's attention duration parameter for the target surrounding vehicles can be updated. The parameter value of the driver's attention duration parameter for the target surrounding vehicles can be updated to: the sum of the current parameter value of the attention duration parameter for the target surrounding vehicles and the target time difference.

[0073] The current parameter value of the attention duration parameter for vehicles surrounding the target can refer to the parameter value of the driver's attention duration parameter for vehicles surrounding the target at the moment when the update begins.

[0074] The target time difference can be one of the following: the first time interval, the second time interval, or the third time interval.

[0075] The first time interval can be: the time interval between determining when the driver's gaze point, determined by the (t-1)th image used to determine the driver's gaze point, rests on a vehicle surrounding the target and determining when the driver's gaze point, determined by the tth image used to determine the driver's gaze point, rests on a vehicle surrounding the target.

[0076] The second time interval can be the time interval between the acquisition times of two adjacent images used to determine the driver's gaze point of the vehicle.

[0077] The third time interval can be the time interval between the acquisition times of two adjacent environmental images.

[0078] In one possible implementation of step S1012, for the target surrounding vehicles of the vehicle, if it is determined that the driver's gaze point, determined by the (t-1)th image used to determine the driver's gaze point, is fixed on the target surrounding vehicles, and it is determined that the driver's gaze point, determined by the tth image used to determine the driver's gaze point, is not fixed on the target surrounding vehicles, then the parameter value of the driver's attention duration parameter for the target surrounding vehicles can be updated to 0.

[0079] In another possible implementation of step S1012, for the target surrounding vehicles of the vehicle, if it is determined that the driver's gaze point, determined through the (t-1)th image used to determine the driver's gaze point, is fixed on the target surrounding vehicle, and it is determined that the driver's gaze point, determined through each of the t-th image used to determine the driver's gaze point...t+k-th image used to determine the driver's gaze point, is not fixed on the target surrounding vehicle, then the parameter value of the driver's attention duration parameter for the target surrounding vehicle can be updated to 0. Here, k is a preset value.

[0080] It should be noted that the order of the images used to determine the driver's gaze point refers to the order obtained by sorting the images used to determine the driver's gaze point from earliest to latest. The earlier the image used to determine the driver's gaze point was acquired, the earlier the image used to determine the driver's gaze point will appear in that order.

[0081] In one possible implementation, for the target surrounding vehicles, the collision time indicator for the target surrounding vehicles is: how long after the current moment will a collision with the vehicle occur. Any existing method for predicting vehicle collision times can be used to predict how long after the current moment a collision will occur.

[0082] In another possible implementation, for the target surrounding vehicles, the collision time indication of the target surrounding vehicles is: how long after the current moment will the target surrounding vehicles enter the safe zone of the vehicle. The module for predicting the vehicle's trajectory predicts the trajectory of the vehicle and the trajectories of the target surrounding vehicles. For example, assuming the vehicle is traveling at its current speed along its planned trajectory, and the target surrounding vehicles are accelerating at their current acceleration and speed along their predicted trajectories, the trajectory of the vehicle and the trajectory of the target surrounding vehicles within a certain time period (e.g., 20 seconds) from the current moment are predicted. Based on the vehicle's trajectory, the position of the vehicle after a certain time period (e.g., 20 seconds) from the current moment is determined. A rectangular area with its center point representing the position of the vehicle after a certain time period from the current moment is designated as the vehicle's safe zone. The length of the vehicle's safe zone can be the sum of the vehicle's length and a preset length; for example, the preset length is 2 meters. The width of the vehicle's safe zone can be called the safe driving pipe width. The width of the vehicle's safe zone can be preset, or determined based on the vehicle's speed and acceleration after a certain time elapsed from the current moment. Based on the trajectories of surrounding vehicles, it predicts whether those vehicles will enter the vehicle's safe zone within a certain timeframe from the current moment. If the vehicle predicts that a surrounding vehicle will enter its safe zone within a certain timeframe from the current moment, it predicts the collision time of that vehicle, indicating how long after the current moment it will enter the vehicle's safe zone.

[0083] In step S102, the collision risk level of the target surrounding vehicles is determined based on the driver's attention duration to the target surrounding vehicles and the collision time of the target surrounding vehicles.

[0084] In step S102, the driver's attention duration for each surrounding vehicle can be normalized to obtain a normalized value. The collision time for each surrounding vehicle can also be normalized to obtain a normalized value. The average of the normalized values ​​of the driver's attention duration for the target surrounding vehicle and the normalized values ​​of the collision time for the target surrounding vehicle is determined; that is, the sum of the normalized values ​​of the driver's attention duration for the target surrounding vehicle and the normalized values ​​of the collision time for the target surrounding vehicle divided by 2. This average value is used as the collision risk level of the target surrounding vehicle.

[0085] In this embodiment of the invention, multiple collision risk level ranges can be preset. Each collision risk level range corresponds to a control strategy. After determining the collision risk level of the target surrounding vehicles of the vehicle, the collision risk level range in which the collision risk of the target surrounding vehicles of the vehicle belongs can be determined, and the control strategy corresponding to the collision risk level range in which the collision risk of the target surrounding vehicles belongs can be determined as the control strategy for the target surrounding vehicles of the vehicle. The higher the collision risk level of the target surrounding vehicles of the vehicle, the higher the priority of the driving decision for the target surrounding vehicles of the vehicle.

[0086] As an example, three pre-defined collision risk level intervals are set: a first interval, a second interval, and a third interval. The left endpoint of the first interval is 6, and the right endpoint is a value much greater than 6, such as positive infinity. The left endpoint of the second interval is 3, and the right endpoint is 5. The left endpoint of the third interval is a value much less than 2, such as negative infinity, and the right endpoint is 2. If the collision risk level of surrounding vehicles is greater than 6, the strategy for dealing with these vehicles is to slow down or swerve laterally to reduce or avoid the collision risk. If the collision risk level of surrounding vehicles is less than 2, the collision risk can be considered very low, and the driving decision can be to temporarily refrain from taking any action against them. If the collision risk level of surrounding vehicles is greater than 3 and less than 5, the collision risk can be considered low, and the strategy can be to reduce speed by releasing the accelerator.

[0087] refer to Figure 2 The diagram illustrates a flowchart of another information acquisition method provided by an embodiment of the present invention.

[0088] In step S201, the duration of the driver's attention to the target surrounding vehicles of the vehicle is obtained, and the collision time of the target surrounding vehicles of the vehicle is determined.

[0089] Step S202 includes: S2021-S2022. Step S202 considers whether the vehicles surrounding the target are the focus of the driver of the vehicle. Considering whether the vehicles surrounding the target are the focus of the driver of the vehicle, the collision risk level of the vehicles surrounding the target is obtained, thereby improving the accuracy of the obtained collision risk level of the vehicles surrounding the target.

[0090] In S021, based on the comparison between the driver's attention duration for the target surrounding vehicles and the first attention duration threshold, a target attention judgment result for the target surrounding vehicles is generated. The target attention judgment result for the target surrounding vehicles indicates whether the target surrounding vehicles of the vehicle are the driver's attention targets.

[0091] As an example, the first attention duration threshold is 0.5 seconds.

[0092] In one possible implementation, in step S2021, based on the comparison between the driver's attention duration for the target surrounding vehicles and a first attention duration threshold, generating a target surrounding vehicle attention determination result includes: if the driver's attention duration for the target surrounding vehicles is less than the first attention duration threshold, a target surrounding vehicle attention determination result indicating that the target surrounding vehicles are not the driver's attention targets can be generated. If the driver's attention duration for the target surrounding vehicles is not less than the first attention duration threshold, a target surrounding vehicle attention determination result indicating that the target surrounding vehicles are the driver's attention targets can be generated.

[0093] In S2022, the collision risk level of the vehicle's surrounding vehicles is determined based on the collision time of the vehicle's surrounding vehicles and the target of the vehicle's attention judgment results.

[0094] In one possible implementation of step S2022, the driver's attention duration for each surrounding vehicle can be normalized to obtain a normalized value. The collision time for each surrounding vehicle can also be normalized to obtain a normalized value. The average of the driver's attention duration for the target surrounding vehicle and the collision time of the target surrounding vehicle is determined, and this average is used as the base value for calculating the collision risk level of the target surrounding vehicle. If the target surrounding vehicle is not the driver's focus, a preset reduction value can be subtracted from the base value used to calculate the collision risk level of the target surrounding vehicle to obtain a difference, which is used as the collision risk level of the target surrounding vehicle. If the target surrounding vehicles of the vehicle are the focus of the driver's attention, the base value used to calculate the collision risk level of the target surrounding vehicles can be added to the preset increment value to obtain the sum of the base value and the preset increment value used to calculate the collision risk level of the target surrounding vehicles of the vehicle. This sum is used as the collision risk level of the target surrounding vehicles of the vehicle.

[0095] In another possible implementation of step S3022, when the target attention determination result of the vehicle's target surrounding vehicles indicates that the vehicle's target surrounding vehicles are the target attention of the vehicle's driver, the driver correction level corresponding to the target surrounding vehicles is determined based on the driver's attention duration to the target surrounding vehicles, and the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles is determined based on the collision time of the target surrounding vehicles; the collision risk level of the target surrounding vehicles is determined by summing the driver correction level corresponding to the target surrounding vehicles and the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles.

[0096] In one possible implementation, when determining the driver correction level for a target surrounding vehicle based on the driver's attention duration to that vehicle, the driver correction level can be determined by considering the relationship between the driver's attention duration and the corresponding driver correction level. This relationship is pre-set and can be represented by a function. Alternatively, the collision risk level of the target surrounding vehicle can be determined by considering the collision time of that vehicle, the collision time of that vehicle, and the corresponding autonomous driving system collision risk level. Again, this relationship is pre-set and can be represented by a function.

[0097] In this embodiment, the driver correction level and the autonomous driving system collision risk level corresponding to the target surrounding vehicles of the vehicle are determined. The collision risk level of the target surrounding vehicles is determined by summing the driver correction level and the autonomous driving system collision risk level of the target surrounding vehicles. This is because directly calculating the collision risk level of the target surrounding vehicles based on the driver's attention duration and collision time may reduce the accuracy of the collision risk level in some cases. For example, in some cases, the driver's attention duration and collision time are both long. The driver's attention duration is positively correlated with the collision risk level, while the collision time is negatively correlated. The actual collision risk level of the target surrounding vehicles should be low, but the calculated collision risk level is high due to the long driver attention duration. For example, because the distance between the target vehicles and the vehicle is far, the collision time with the target vehicles is long. At the same time, the driver pays more attention to the target vehicles. Because the distance between the target vehicles and the vehicle is far, the actual collision risk level of the target vehicles should be relatively small, but the calculated collision risk level of the target vehicles is relatively large.

[0098] Therefore, based on the driver's attention duration and collision time regarding surrounding vehicles, the driver's attention duration is quantified into a corresponding driver correction level for each surrounding vehicle, while the collision time is also considered. This ensures that even if the driver's attention duration is high, it will be limited to the highest pre-set collision risk level set by the autonomous driving system. This avoids situations where the driver's attention duration and collision risk level are positively correlated, while the collision time is negatively correlated, meaning the actual collision risk of the surrounding vehicles should be low, but the calculated collision risk level is high due to the driver's long attention duration. This improves the accuracy of the collision risk level calculation for surrounding vehicles.

[0099] In one possible implementation, when determining the driver correction level for the target surrounding vehicles based on the driver's attention duration, the collision risk level of the autonomous driving system for the target surrounding vehicles is calculated based on the collision time of the target surrounding vehicles. Following the principle that the shorter the collision time of the target surrounding vehicles, the higher the collision risk level of the autonomous driving system, a collision risk coefficient for the autonomous driving system of the target surrounding vehicles is determined using an inverse proportional function. The collision risk level of the autonomous driving system corresponding to the target surrounding vehicles is then determined based on a comparison between the autonomous driving system collision risk coefficient and the autonomous driving system collision risk coefficient threshold.

[0100] The collision risk coefficient of the autonomous driving system for vehicles surrounding the target vehicle, determined by the inverse proportional function, can be expressed as:

[0101]

[0102] Among them, E S t represents the collision risk coefficient of the autonomous driving system for the target surrounding vehicles of the vehicle, and t represents the collision time of the target surrounding vehicles of the vehicle.

[0103] In this embodiment of the invention, if the collision risk coefficient of the autonomous driving system of the vehicle's surrounding vehicles is greater than the highest autonomous driving system collision risk coefficient threshold, then the collision risk level of the autonomous driving system corresponding to the vehicle's surrounding vehicles is the highest autonomous driving system collision risk level, such as Level 8 autonomous driving system collision risk level. If the collision risk coefficient of the autonomous driving system of the vehicle's surrounding vehicles is less than the lowest autonomous driving system collision risk coefficient threshold, then the collision risk level of the autonomous driving system corresponding to the vehicle's surrounding vehicles is the lowest autonomous driving system collision risk level, such as Level 1 autonomous driving system collision risk level.

[0104] Table 1 shows the collision risk coefficient E of the autonomous driving system for vehicles surrounding the target vehicle. S The collision risk level P of the autonomous driving system corresponding to the target vehicles around the vehicle. S An example of the value relationship of E S The unit is seconds. 0.5, 1, 1.5, 2, 3, 5, and 10 are all collision risk coefficient thresholds for autonomous driving systems.

[0105] Table 1

[0106]

[0107]

[0108] In one possible implementation, determining the driver correction level corresponding to the target surrounding vehicles based on the driver's attention duration includes: when the driver's attention duration to the target surrounding vehicles is not less than a first attention duration threshold and not greater than a second attention duration threshold, the first correction level is determined as the driver correction level corresponding to the target surrounding vehicles, wherein the second attention duration threshold is greater than the first attention duration threshold; when the driver's attention duration to the target surrounding vehicles is greater than the second attention duration threshold, the second correction level is determined as the driver correction level corresponding to the target surrounding vehicles, wherein the second correction level is higher than the first correction level.

[0109] As an example, the first attention duration threshold is 0.5 seconds, the second attention duration threshold is 1.5 seconds, the first correction level is driver correction level 1, and the second correction level is driver correction level 2. If the driver's attention duration to surrounding vehicles is between 0.5 seconds and 1.5 seconds, then the first correction level is determined to be the driver correction level corresponding to the surrounding vehicles, i.e., P. d =1, if the driver's attention duration to surrounding vehicles exceeds 1.5 seconds, then the second correction level is determined as the driver correction level corresponding to the surrounding vehicles, P. d =2. It should be noted that if the driver's attention duration to surrounding vehicles is less than 0.5 seconds, it can be considered as the driver correction level P corresponding to the surrounding vehicles. d =0.

[0110] In one possible implementation, determining the collision risk level of the vehicle's surrounding vehicles based on the collision time of the vehicle's surrounding vehicles and the target attention determination result of the vehicle's surrounding vehicles includes: when the target attention determination result of the vehicle's surrounding vehicles indicates that the vehicle's surrounding vehicles are not the target of the vehicle's driver's attention and the vehicle's surrounding vehicles were previously the target of the vehicle's driver's attention within the target's previous time period, determining the collision risk level of the vehicle's surrounding vehicles corresponding to the autonomous driving system based on the collision time of the vehicle's surrounding vehicles, wherein the target's previous time period is a time period with an end time of the current time and a duration of a preset observation duration; and determining the collision risk level of the vehicle's surrounding vehicles based on the collision risk level of the autonomous driving system corresponding to the vehicle's surrounding vehicles. When determining the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles based on the collision times of the vehicle's surrounding vehicles, the normalized value of the collision times of the target surrounding vehicles obtained by normalizing the collision times of each of the vehicle's surrounding vehicles can be used as the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles. Alternatively, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles can be determined based on the correlation between the collision times of the surrounding vehicles, the collision times of the surrounding vehicles, and the collision risk levels of the autonomous driving systems corresponding to the surrounding vehicles. When determining the collision risk level of the vehicle's target surrounding vehicles based on their respective collision risk levels, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles can be used as the final collision risk level of the vehicle's target surrounding vehicles.

[0111] As an example, the preset observation time can be 1.5 seconds.

[0112] It should be noted that the preset observation duration can be the second attention duration threshold mentioned above.

[0113] In this embodiment of the disclosure, when the target attention determination result of the vehicle's surrounding vehicles indicates that the vehicle's surrounding vehicles are not the driver's target of attention but were previously considered as targets of attention in the target's previous time period, the collision risk level of the vehicle's surrounding vehicles corresponding to the autonomous driving system is determined based on the collision time of the vehicle's surrounding vehicles. This is because it takes into account that: if the vehicle's surrounding vehicles are not currently the driver's target of attention, but were previously considered as targets of attention by the driver in the target's previous time period, it reflects that: the surrounding vehicles are not currently the driver's target of attention, but were previously considered as targets of attention by the driver in the target's previous time period, and the driver of the vehicle judges that in the short term...

[0114] The driver shifted their attention away from the target vehicle because there was no risk of collision. Therefore, the time the driver spent focusing on the target vehicle's surroundings is not included in the acquisition of the vehicle's collision risk level, thus improving the accuracy of the acquired collision risk level for the target vehicle's surroundings.

[0115] In one possible implementation, when the target attention determination result of the vehicle's surrounding vehicles indicates that the vehicle's surrounding vehicles are not the vehicle's driver's target of attention and the vehicle's surrounding vehicles were previously the vehicle's driver's target of attention in the target time period, determining the collision risk level of the vehicle's surrounding vehicles according to the collision risk level of the autonomous driving system corresponding to the vehicle's surrounding vehicles includes: determining the difference between the collision risk level of the autonomous driving system corresponding to the surrounding vehicles and a preset value as the collision risk level of the surrounding vehicles.

[0116] The difference between the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target and the preset value is: the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target minus the preset value.

[0117] The default value is a positive number.

[0118] As an example, when the target attention assessment result of the vehicle's surrounding vehicles indicates that the vehicle's surrounding vehicles are not the driver's target of attention, and the vehicle's surrounding vehicles were previously the driver's target of attention within a previous time period, the collision risk level of the vehicle's surrounding vehicles can be determined using the following formula:

[0119]

[0120] Where P represents the collision risk level of the target surrounding vehicles of the vehicle, and t represents the collision time of the target surrounding vehicles of the vehicle, with a preset value of 1.

[0121] The difference between the collision risk level of the autonomous driving system for the target surrounding vehicles and the preset value is determined as the collision risk level of the target surrounding vehicles. This ensures that the obtained collision risk level of the target surrounding vehicles is relatively low.

[0122] In one possible implementation, determining the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles based on the collision time of the vehicle includes: determining the collision risk-related type of the target surrounding vehicles based on the collision time and collision time threshold of the vehicle; and determining the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles based on the collision risk-related type of the vehicle.

[0123] As an example, collision risk is categorized into three types: collision risk present, potential collision risk, and no collision risk. Multiple collision risk level ranges can be preset.

[0124] Multiple collision risk level intervals can be pre-set. The left and right endpoints of each interval are collision time thresholds. Each interval corresponds to a different collision risk-related type. Each collision risk-related type corresponds to different parameters. The system can determine the collision risk level interval in which the vehicle's surrounding vehicles fall, and define the type corresponding to that interval as the collision risk-related type for those vehicles. The parameters corresponding to the collision risk-related type are then defined as the collision risk level of the autonomous driving system for those vehicles.

[0125] In one possible implementation, the collision risk-related types are divided into: collision risk type and no collision risk type. Determining the collision risk-related type of the vehicle's surrounding vehicles based on the collision time and collision time threshold includes: when the collision time of the vehicle's surrounding vehicles exceeds the target collision time threshold, the no-collision-risk type is determined as the collision risk-related type; when the collision time of the vehicle's surrounding vehicles does not exceed the target collision time threshold, the collision risk type is determined as the collision risk-related type. Furthermore, determining the collision risk level of the autonomous driving system corresponding to the vehicle's surrounding vehicles based on their collision risk-related type includes: when the collision risk-related type of the vehicle's surrounding vehicles is no-collision-risk... The preset minimum risk level used to determine the collision risk level of the autonomous driving system is set as the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles. When the collision risk-related type of the target surrounding vehicles of the self-vehicle is a collision risk type, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles of the self-vehicle is determined according to the collision time of the target surrounding vehicles of the self-vehicle, the collision time of the surrounding vehicles and the collision risk level of the autonomous driving system corresponding to the surrounding vehicles. Among them, the preset minimum risk level used to determine the collision risk level of the autonomous driving system is lower than the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles determined when the collision risk-related type of the target surrounding vehicles is a collision risk type.

[0126] It should be noted that the target collision time threshold is a threshold used to determine whether the target surrounding vehicles of the vehicle are of a collision time type related to collision risk.

[0127] In one possible implementation, the preset minimum risk level used to determine the collision risk level of the autonomous driving system is 0.

[0128] refer to Figure 3 The flowchart shows an example of obtaining the collision risk level of surrounding vehicles from a vehicle.

[0129] In this example, for the target surrounding vehicles of the vehicle, the parameter value of the attention duration parameter for the target surrounding vehicles can be read, thus determining the driver's attention duration for these vehicles. In this example, for the target surrounding vehicles, the collision time indicates how long after the current moment the target surrounding vehicles will enter the vehicle's safe zone. Predicting how long after the current moment the target surrounding vehicles will enter the vehicle's safe zone yields the collision time. Based on the driver's attention duration and the collision time, the collision risk level of the target surrounding vehicles is determined. Based on the collision risk level, a driving decision is made regarding the target surrounding vehicles.

[0130] This invention also provides an information acquisition device for implementing the above-described method embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "unit" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. The devices in this invention are presented in the form of functional units, where a functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-described functions.

[0131] The information acquisition device includes:

[0132] The acquisition unit is used to acquire the duration of the driver's attention to the target surrounding vehicle of the vehicle and to determine the collision time of the target surrounding vehicle of the vehicle. The target surrounding vehicle is any one of the surrounding vehicles of the vehicle. The duration of the driver's attention to the target surrounding vehicle of the vehicle indicates the duration of the driver's attention to the target surrounding vehicle. The duration of attention is determined based on the driver's gaze point.

[0133] The determining unit is used to determine the collision risk level of the vehicles surrounding the target based on the driver's attention duration to the vehicles surrounding the target and the collision time of the vehicles surrounding the target.

[0134] In one possible implementation, the determining unit is further configured to generate a target attention judgment result for the target surrounding vehicles based on a comparison result between the driver's attention duration and the attention duration threshold, wherein the target attention judgment result indicates whether the target surrounding vehicles are the driver's target attention; and determine the collision risk level of the target surrounding vehicles based on the collision time of the target surrounding vehicles and the target attention judgment result of the target surrounding vehicles.

[0135] In one possible implementation, the determining unit is further configured to, when the target attention determination result of the target surrounding vehicles indicates that the target surrounding vehicles are not the driver's target of attention and the target surrounding vehicles were previously the driver's target of attention during the target's previous time period, determine the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles based on the collision time of the target surrounding vehicles, wherein the target's previous time period is a time period with an end time of the current time and a duration of a preset observation duration; and determine the collision risk level of the target surrounding vehicles based on the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles.

[0136] In one possible implementation, the determining unit is further configured to determine the difference between the collision risk level of the autonomous driving system corresponding to the target surrounding vehicle and a preset value as the collision risk level of the target surrounding vehicle when the target surrounding vehicle's target attention determination result indicates that the target surrounding vehicle is not the driver's target of attention and the target surrounding vehicle was previously the driver's target of attention in the target's previous time period.

[0137] In one possible implementation, the determining unit is further configured to, when the target attention determination result of the target surrounding vehicles indicates that the target surrounding vehicles are the driver's target attention, determine the driver correction level corresponding to the target surrounding vehicles based on the driver's attention duration to the target surrounding vehicles, and determine the autonomous driving system collision risk level corresponding to the target surrounding vehicles based on the collision time of the target surrounding vehicles; and determine the collision risk level of the target surrounding vehicles as the sum of the driver correction level corresponding to the target surrounding vehicles and the autonomous driving system collision risk level corresponding to the target surrounding vehicles.

[0138] In one possible implementation, the determining unit is further configured to: determine a first correction level as the driver correction level corresponding to the target surrounding vehicle when the driver's attention duration to the target surrounding vehicle is not less than a first attention duration threshold and the driver's attention duration to the target surrounding vehicle is not greater than a second attention duration threshold, wherein the second attention duration threshold is greater than the first attention duration threshold; and determine a second correction level as the driver correction level corresponding to the target surrounding vehicle when the driver's attention duration to the target surrounding vehicle is greater than the second attention duration threshold, wherein the second correction level is higher than the first correction level.

[0139] In one possible implementation, the determining unit is further configured to determine the collision risk-related type of the vehicles surrounding the target based on the collision time and collision time threshold of the vehicles surrounding the target; and determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target based on the collision risk-related type of the vehicles surrounding the target.

[0140] In one possible implementation, the determining unit is further configured to: when the collision time of the vehicles surrounding the target is greater than a target collision time threshold, determine the no-collision-risk type as the collision-risk-related type of the vehicles surrounding the target; when the collision time of the vehicles surrounding the target is not greater than the target collision time threshold, determine the collision-risk-related type of the vehicles surrounding the target; the determining unit is further configured to: when the collision-risk-related type of the vehicles surrounding the target is a no-collision-risk type, determine the preset minimum risk level used to determine the collision risk level of the autonomous driving system as the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target; when the collision-risk-related type of the vehicles surrounding the target is a collision-risk-related type, determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target based on the correlation between the collision time of the vehicles surrounding the target, the collision time of the surrounding vehicles, and the collision risk level of the autonomous driving system corresponding to the surrounding vehicles, wherein the preset minimum risk level used to determine the collision risk level of the autonomous driving system is less than the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target determined when the collision-risk-related type of the vehicles surrounding the target is a collision-risk-related type.

[0141] refer to Figure 4 , Figure 4This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. The computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple devices can be connected, each providing some necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device can be a complex programmable logic device (CLP), a field-programmable gate array (FPGA), a general-purpose array logic (GPRS), or any combination thereof. The memory 20 stores instructions executable by at least one processor 10 to perform the methods shown in the above embodiments. The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on vehicle usage, etc. Furthermore, the memory 20 may include high-speed random access memory and non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid-state drive; the memory 20 may also include combinations of the above types of memory. The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 may be connected via a bus or other means. The input device 30 can receive input digital or character information, and generate key signal inputs related to user settings and function control of the computer device, such as touch screen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc.The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor). The display device includes, but is not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0142] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0143] A portion of the embodiments of this invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, these instructions, through the operation of the computer, can invoke or provide the methods and / or technical solutions according to the invention. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Accordingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0144] The above embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention.

Claims

1. An information acquisition method, characterized in that: The method includes: The driver of the vehicle pays attention to a target surrounding vehicle for a given period of time, and the collision time of the target surrounding vehicle is determined. The target surrounding vehicle is any one of the surrounding vehicles of the vehicle. The driver's attention to the target surrounding vehicle indicates the duration of the driver's attention to the target surrounding vehicle. The attention duration is determined based on the driver's gaze point. The collision risk level of the vehicles surrounding the target is determined based on the driver's attention duration and the collision time of the vehicles surrounding the target. This determination includes: generating a target attention judgment result for the vehicles surrounding the target based on a comparison between the driver's attention duration and a first attention duration threshold, wherein the target attention judgment result indicates whether the vehicles surrounding the target are the driver's target of attention; and determining the collision risk level of the vehicles surrounding the target based on the collision time and the target attention judgment result. The collision risk level of the vehicles surrounding the target is determined based on the collision time of the vehicles surrounding the target and the target attention determination result of the vehicles surrounding the target. This includes: when the target attention determination result of the vehicles surrounding the target indicates that the vehicles surrounding the target are not the driver's target of attention and the vehicles surrounding the target were previously the driver's target of attention during a previous time period, the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined based on the collision time of the vehicles surrounding the target, wherein the previous time period is a time period with an end time of the current time and a duration of a preset observation duration; the collision risk level of the vehicles surrounding the target is determined based on the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

2. The method according to claim 1, characterized in that: The collision risk level of the vehicles surrounding the target is determined based on the collision risk level of their respective autonomous driving systems, including: The difference between the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles and a preset value is determined as the collision risk level of the target surrounding vehicles.

3. The method according to claim 1, characterized in that: Based on the collision time of the vehicles surrounding the target and the target of interest assessment results of the vehicles surrounding the target, the collision risk level of the vehicles surrounding the target is determined, including: When the target attention determination result of the vehicles surrounding the target indicates that the vehicles surrounding the target are the driver's target attention, the driver correction level corresponding to the vehicles surrounding the target is determined according to the driver's attention duration to the vehicles surrounding the target, and the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined according to the collision time of the vehicles surrounding the target. The sum of the driver correction level corresponding to the vehicle surrounding the target and the collision risk level of the autonomous driving system corresponding to the vehicle surrounding the target is determined as the collision risk level of the vehicle surrounding the target.

4. The method according to claim 3, characterized in that: Based on the driver's attention duration to vehicles surrounding the target, the driver correction level corresponding to the vehicles surrounding the target is determined as follows: When the driver's attention duration to the vehicles surrounding the target is not less than a first attention duration threshold and the driver's attention duration to the vehicles surrounding the target is not greater than a second attention duration threshold, the first correction level is determined as the driver correction level corresponding to the vehicles surrounding the target, wherein the second attention duration threshold is greater than the first attention duration threshold. When the driver's attention duration to the vehicles surrounding the target exceeds the second attention duration threshold, the second correction level is determined as the driver correction level corresponding to the vehicles surrounding the target, and the second correction level is higher than the first correction level.

5. The method according to any one of claims 2-4, characterized in that: Based on the collision time of the vehicles surrounding the target, the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined, including: Based on the collision time and collision time threshold of the vehicles surrounding the target, determine the type of vehicles surrounding the target that are related to collision risk; Based on the types of collision risk associated with the vehicles surrounding the target, determine the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

6. The method according to claim 5, characterized in that: Based on the collision time and collision time threshold of the vehicles surrounding the target, the types of vehicles associated with collision risk are determined, including: When the collision time of the vehicles surrounding the target is greater than the target collision time threshold, the no-collision-risk type is determined as the collision-risk-related type of the vehicles surrounding the target. When the collision time of the vehicles surrounding the target is not greater than the target collision time threshold, the collision risk type will be determined as the collision risk-related type of the vehicles surrounding the target. And based on the types of collision risk associated with the vehicles surrounding the target, determining the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target includes: When the collision risk-related type of the vehicles surrounding the target is no collision risk, the preset minimum risk level used to determine the collision risk level of the autonomous driving system will be determined as the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target. When the collision risk associated with the target surrounding vehicles is a collision risk type, the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles is determined based on the collision time of the target surrounding vehicles, the correlation between the collision time of the surrounding vehicles and the collision risk level of the autonomous driving system corresponding to the surrounding vehicles, wherein the preset minimum risk level used to determine the collision risk level of the autonomous driving system is lower than the collision risk level of the autonomous driving system corresponding to the target surrounding vehicles determined when the collision risk associated with the target surrounding vehicles is a collision risk type.

7. An information acquisition device, characterized in that: The device includes: The acquisition unit is used to acquire the duration of the driver's attention to the target surrounding vehicle of the vehicle and to determine the collision time of the target surrounding vehicle of the vehicle. The target surrounding vehicle is any one of the surrounding vehicles of the vehicle. The duration of the driver's attention to the target surrounding vehicle indicates the duration of the driver's attention to the target surrounding vehicle. The duration of attention is determined based on the driver's gaze point. The determining unit is configured to determine the collision risk level of the surrounding vehicles based on the driver's attention duration to the surrounding vehicles and the collision time of the surrounding vehicles; determining the collision risk level of the surrounding vehicles based on the driver's attention duration to the surrounding vehicles and the collision time of the surrounding vehicles includes: generating a target attention judgment result for the surrounding vehicles based on a comparison result between the driver's attention duration to the surrounding vehicles and a first attention duration threshold, wherein the target attention judgment result indicates whether the surrounding vehicles are the driver's target attention; and determining the surrounding vehicles based on the collision time of the surrounding vehicles and the target attention judgment result. The collision risk level is determined based on the collision time of the vehicles surrounding the target and the target attention determination result of the vehicles surrounding the target. This includes: when the target attention determination result of the vehicles surrounding the target indicates that the vehicles surrounding the target are not the driver's target of attention and the vehicles surrounding the target were previously the driver's target of attention during the target's previous time period, the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target is determined based on the collision time of the vehicles surrounding the target, wherein the target's previous time period is a time period with an end time of the current time and a duration of a preset observation duration; the collision risk level of the vehicles surrounding the target is determined based on the collision risk level of the autonomous driving system corresponding to the vehicles surrounding the target.

8. A computer device installed in a vehicle, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

Images