Processing method, device and equipment based on user takeover capability evaluation

Abstract

The embodiment of the invention provides a processing method, device and equipment based on user takeover capability evaluation, and the method comprises the steps: obtaining a user takeover capability parameter of a user taking over a vehicle control right under the prompt of an auxiliary driving system, and obtaining a user takeover capability evaluation result according to the user takeover capability parameter; and determining a take-over time threshold value for prompting the user by the auxiliary driving system, and controlling the auxiliary driving system to prompt the user to take over the vehicle control right according to the take-over time threshold value, so that the user can be differentially prompted to take over the vehicle control right based on the take-over capability of the user, and the user experience is improved. And the user can take over the vehicle in time at a critical moment, so that accidents are saved and the driving safety is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of assisted driving, in particular to a processing method based on user takeover ability evaluation, a processing device based on user takeover ability evaluation and an electronic device. BACKGROUND

[0002] For different drivers, the current user training of assisted driving is relatively unified, that is, after watching a video test, completing a mileage or activating for a period of time, the user can be unlocked for use. The assisted driving system does not provide differentiated services for different user groups, and assisted driving is not equal to automatic driving. Many assisted driving users excessively rely on the assisted driving system and believe that they can use the assisted driving system well, thus being careless and ignoring manual takeover when necessary, resulting in some traffic accidents caused by carelessness or excessive reliance on the assisted driving system. SUMMARY

[0003] The embodiments of the present application provide a processing method, device and electronic device based on user takeover ability evaluation, and further include a computer readable storage medium to overcome the above problems or at least partially solve the problem that many assisted driving users excessively rely on the assisted driving system and believe that they can use the assisted driving system well, thus being careless and ignoring manual takeover when necessary, resulting in some traffic accidents caused by carelessness or excessive reliance on the assisted driving system.

[0004] The embodiments of the present application disclose a processing method based on user takeover ability evaluation, characterized in that the method comprises: obtaining a user takeover ability parameter of a user taking over control of a vehicle under prompting of an assisted driving system; determining a takeover time threshold for prompting the user by the assisted driving system according to the user takeover ability parameter; controlling the assisted driving system to prompt the user to take over control of the vehicle according to the takeover time threshold.

[0005] Optionally, the method further comprises: generating a first personalized training strategy for the user according to the user takeover ability parameter of the user, and controlling the vehicle to respond according to the first personalized training strategy Optionally, obtaining the user takeover ability parameter of the user taking over control of the vehicle under prompting of the assisted driving system comprises: obtaining historical driving behavior data of the user; determining a plurality of behavior reward values corresponding to the historical driving behavior data; performing weighted calculation on the plurality of behavior reward values to obtain a driving ability value of the user; According to the driving ability value, a user takeover ability parameter of the user taking over the control of the vehicle under the prompting of the assisted driving system is determined.

[0006] Optionally, according to the driving ability value, the user takeover ability parameter of the user taking over the control of the vehicle under the prompting of the assisted driving system comprises: According to the historical driving behavior data, a user takeover accuracy rate and a user takeover timeliness rate are determined. According to the driving ability value, the user takeover accuracy rate and the user takeover timeliness rate, the user takeover ability parameter of the user taking over the control of the vehicle under the prompting of the assisted driving system is determined.

[0007] Optionally, the behavior reward value comprises a negative reward value, and according to the driving ability value, the user takeover ability parameter of the user taking over the control of the vehicle under the prompting of the assisted driving system comprises: According to the negative reward value, a target driving item is determined. According to the driving ability value and the target driving item, the user takeover ability parameter of the user taking over the control of the vehicle under the prompting of the assisted driving system is determined.

[0008] Optionally, the method further comprises: According to the target driving item, a second personalized training strategy for the user is generated, and the vehicle is controlled to respond according to the second personalized training strategy.

[0009] Optionally, the historical driving behavior data comprises a plurality of target data, and according to the negative reward value, the target driving item is determined, comprising: A number of negative reward values corresponding to the plurality of target data respectively is determined. According to the number of negative reward values corresponding to the plurality of target data respectively, a negative reward proportion corresponding to the plurality of target data respectively is determined. According to the negative reward proportion corresponding to the plurality of target data respectively, the target driving item is determined.

[0010] Optionally, the historical driving behavior data is driving behavior data of a preset historical mileage, and the historical driving behavior data comprises one or more of the following: Lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, user takeover data.

[0011] Embodiments of the present application also disclose a processing device based on user takeover ability evaluation, characterized in that the device comprises: a data acquisition module configured to acquire a user takeover capability parameter of the user taking over the control of the vehicle under the prompting of the advanced driving system; a time threshold determination module configured to determine a takeover time threshold of the user being prompted by the advanced driving system according to the user takeover capability parameter; a control prompting module configured to control the advanced driving system to prompt the user to take over the control of the vehicle according to the takeover time threshold.

[0012] Optionally, the method further comprises: a first personalized learning module configured to generate a first personalized training strategy for the user according to the user takeover capability parameter of the user, and control the vehicle to respond according to the first personalized training strategy.

[0013] Optionally, the data acquisition module comprises: a data acquisition sub-module configured to acquire historical driving behavior data of the user; a reward value determination sub-module configured to determine a plurality of behavior reward values corresponding to the historical driving behavior data; a driving capability value determination sub-module configured to perform weighted calculation on the plurality of behavior reward values to obtain a driving capability value of the user; a takeover capability determination sub-module configured to determine the user takeover capability parameter of the user taking over the control of the vehicle under the prompting of the advanced driving system according to the driving capability value.

[0014] Optionally, the takeover capability determination sub-module comprises: a takeover data determination unit configured to determine a user takeover accuracy rate and a user takeover timeliness rate according to the historical driving behavior data; a first takeover capability determination unit configured to determine the user takeover capability parameter of the user taking over the control of the vehicle under the prompting of the advanced driving system according to the driving capability value, the user takeover accuracy rate and the user takeover timeliness rate.

[0015] Optionally, the behavior reward value comprises a negative reward value, and the takeover capability determination sub-module comprises: a target item determination unit configured to determine a target driving item according to the negative reward value; a first takeover capability determination unit configured to determine the user takeover capability parameter of the user taking over the control of the vehicle under the prompting of the advanced driving system according to the driving capability value and the target driving item.

[0016] Optionally, the method further comprises: The second personalized learning module is configured to generate a second personalized training strategy for the user according to the target driving item, and control the vehicle to respond according to the second personalized training strategy.

[0017] Optionally, the historical driving behavior data includes a plurality of target data, and the target item determination unit includes: A negative reward value quantity determination subunit is configured to determine a quantity of negative reward values corresponding to the plurality of target data respectively. A negative reward proportion determination subunit is configured to determine a proportion of negative reward corresponding to the plurality of target data respectively according to the quantity of negative reward values corresponding to the plurality of target data respectively. A target item determination subunit is configured to determine a target driving item according to the proportion of negative reward corresponding to the plurality of target data respectively.

[0018] Optionally, the historical driving behavior data is driving behavior data of a preset historical mileage, and the historical driving behavior data includes one or more of the following: Lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, and user takeover data.

[0019] Embodiments of the present application also disclose an electronic device including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus. The memory is configured to store a computer program. The processor is configured to execute the program stored on the memory to implement the method described in the embodiments of the present application.

[0020] Embodiments of the present application also disclose one or more computer readable media having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method described in the embodiments of the present application.

[0021] Embodiments of the present application have the following advantages: In the embodiments of the present application, the historical driving behavior data of the user is acquired, the user takeover ability parameter of the user in the case of taking over the control right of the vehicle under the prompt of the auxiliary driving system is determined according to the historical driving behavior data, the personalized training strategy for the user is generated according to the user takeover ability parameter, and the vehicle is controlled to respond according to the personalized training strategy, so that the vehicle takeover ability of the user is determined according to the historical driving behavior data of the user, the training strategy can be determined based on the user takeover ability of the user, the vehicle takeover ability of the user is improved, and then it is ensured that the user can take over the vehicle in time in a critical moment to rescue an accident and improve driving safety. Attached Figure Description

[0022] Figure 1 This is a flowchart of the steps of a processing method based on user takeover capability assessment provided in the embodiments of this application; Figure 2 This is a structural block diagram of a processing device based on user takeover capability assessment provided in the embodiments of this application; Figure 3 This is a block diagram of an electronic device provided in an embodiment of this application; Figure 4 This is a schematic diagram of a computer-readable medium provided in an embodiment of this application. Detailed Implementation

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] To facilitate understanding of the technical solutions and effects of the embodiments of this application, the relevant technologies of this application will be briefly described below.

[0025] Currently, there is no industry-consensus assessment model for human-machine takeover capability regarding the evaluation of user takeover capabilities.

[0026] This application designs a system based on the DRL algorithm (Deep Reinforcement Learning) to determine the user's takeover ability level and provide personalized learning and training, starting from the user's driving behavior. At the same time, the system can monitor the driver's driving behavior and takeover ability during the driving process.

[0027] In addition, it can provide differentiated training strategies for different driving user groups and dynamically adjust the training content based on these behaviors, so that users can effectively improve their driving skills in specific scenarios when using assisted driving, thereby improving driving safety and user experience.

[0028] Reference Figure 1 The diagram illustrates a flowchart of a processing method based on user takeover capability assessment provided in an embodiment of this application, which may specifically include the following steps: Step 101: Obtain the user takeover capability parameters when the user takes over vehicle control under the prompts of the driver assistance system.

[0029] In the scenario that the vehicle perception system fails or is out of the ODD (Operational Design Domain), the assisted driving system detects that it cannot continue to operate safely, and actively sends a request to the driver to take over. The process in which the driver takes over the control of the vehicle according to the prompt of the assisted driving system can be called passive takeover. The ability of the user to passively take over is the user takeover ability.

[0030] When the user is driving the vehicle, if the user is using the assisted driving system for assisted driving, the user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system can be obtained.

[0031] The user takeover ability parameter is the user takeover ability level of the user after the user takeover ability of the user is graded.

[0032] In some embodiments of the present application, the user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system comprises: Sub-step 11, obtaining the historical driving behavior data of the user.

[0033] In order to determine the user takeover ability level of the user, the historical driving behavior data of the user can be obtained.

[0034] In some embodiments of the present application, the historical driving behavior data is the driving behavior data of a preset historical mileage, and the historical driving behavior data comprises one or more of the following: Lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, and user takeover data.

[0035] In actual application, the driving behavior data of the user in the preset historical mileage, that is, the historical driving behavior data, can be obtained. For example, the preset historical mileage can be 300 kilometers in the past, that is, the historical driving behavior data of the user can be obtained after the user drives 300 kilometers, so as to determine the user takeover ability level.

[0036] In order to update and accurately locate the user takeover ability level of the user in time, the preset historical mileage is preferably not more than 500 kilometers, and of course it cannot be too low, such as 50 kilometers, so as to prevent the user takeover ability level of the user from being updated frequently, thereby causing a bad user experience.

[0037] Specifically, when the user is driving the vehicle, the behavior data (such as eye gaze direction, hand movement, and facial expression) of the user and the vehicle state data (such as speed and position) in the driving process can be obtained and processed to obtain the driving behavior data of the user and save it.

[0038] For example, behavior data of the user during driving can be collected by a multi-modal monitoring device (such as a high-precision camera, an infrared sensor), and then key features such as the user's eye gaze deviation, hand movements, etc. are extracted using a deep learning algorithm (such as a convolutional neural network), so as to obtain attention determination data of the user, such as whether the user is attentive, whether there is fatigue driving, etc.

[0039] The vehicle state data can also be used to determine whether the vehicle is driving in the correct lane, to obtain lane keeping data; to determine whether the vehicle complies with traffic signals, to obtain traffic signal compliance data; to determine whether the vehicle maintains a safe distance from the vehicle in front, to obtain safe distance keeping data; and to determine whether the vehicle speed is within the speed limit, to obtain safe speed control data.

[0040] The user takeover data can be related data of the user taking over the control of the vehicle under the prompt of the assisted driving system, and can also be obtained in combination with the vehicle state data. The related data can include the total number of times the user takes over the control of the vehicle, the number of times the user takes over the control of the vehicle in time, and the number of times the user takes over the control of the vehicle accurately.

[0041] The determination basis for the user taking over the control of the vehicle in time is that the actual time T of the user taking over the control of the vehicle does not exceed the threshold value TOT_max of the maximum allowed takeover time (TOT_max) of the takeover request according to relevant safety standards and experimental data, and otherwise the user taking over the control of the vehicle is not in time.

[0042] The accuracy of the user taking over the control of the vehicle is determined according to some specific index items and their scoring standards, and the accurate standard is to meet all the following standards at the same time: (a) The vehicle control stability meets "vehicle control is smooth, without obvious shaking or sudden turning" or "vehicle control is basically smooth, with occasional slight shaking", that is, the absolute value of the yaw rate change rate <= ±0.5 rad / s² and the longitudinal acceleration change rate <= ±1 m / s². The vehicle control stability includes lateral stability and longitudinal stability. The lateral stability judgment index is that the absolute value of the yaw rate change rate does not exceed a certain threshold (such as ±0.5 rad / s²), which can be considered as that the vehicle is basically stable in lateral control. The longitudinal stability judgment index is that the longitudinal acceleration change rate is too large (such as exceeding ±1 m / s²), which indicates that the user's control of the longitudinal dynamics of the vehicle is not smooth, which may cause passenger discomfort or vehicle longitudinal stability problems, such as easy to slip on wet road surface, etc. (b) The lane deviation is <= 30 cm; (c) The vehicle speed is controlled within ±5% of the target speed; (d) The distance between the vehicle and the front vehicle is greater than 1.5 seconds; (e) The average value of the brake pedal force is less than 200 N; (f) The steering operation meets the "smooth steering operation without excessive adjustment" or "basically smooth steering operation with occasional slight adjustment", that is, the steering wheel angle change rate is <= ± 50° / s and the steering frequency per unit time is < 3 times per minute. The specific index item can be extended according to the specific situation, which is not mandatory.

[0043] Sub-step 12, according to the historical driving behavior data, a plurality of behavior reward values corresponding to the historical driving behavior data are determined.

[0044] After obtaining the lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, and user takeover data, corresponding behavior reward values can be set for these data.

[0045] The behavior reward value can include positive reward value and negative reward value, for example, positive reward value is given for behaviors such as obeying traffic rules and keeping safe distance, and negative reward value is given for dangerous behaviors.

[0046] As an example, for lane keeping data, the behavior reward value can be set as R lane If the vehicle keeps in the center of the lane, a positive reward value +1 is given, and if the vehicle deviates from the lane, a negative reward value -1 is given. For traffic signal following data, the behavior reward value can be set as R signa If the vehicle follows the traffic signal (such as stopping at a red light and going at a green light), a positive reward value +2 is given, and if the vehicle violates the traffic signal, a negative reward -2 is given.

[0047] For safe distance keeping data, the behavior reward value can be set as R distance If the vehicle keeps a safe distance (such as a distance of more than 2 seconds) from the front vehicle, a positive reward value +1 is given, and if the vehicle is too close to the front vehicle, a negative reward -1 is given.

[0048] For safe speed control data, the behavior reward value can be set as R speed If the vehicle speed is within the speed limit, a positive reward value +1 is given, and if the vehicle speed is over the speed limit, a negative reward -2 is given.

[0049] For attention determination data, the behavior reward value can be set as R attention If the user's attention is focused (such as looking at the road), a positive reward value +1 is given, and if the user is distracted (such as looking away from the road, playing with the phone, and being tired), a negative reward -2 is given.

[0050] For the user to take over the data, the behavior reward value can be set as R takeover If the user takes over in time and accurately after the prompt of the intelligent driving system, a positive reward value +5 is given, if the user takes over not in time but accurately after the prompt of the intelligent driving system, a negative reward value -2.5 is given, if the user takes over in time but not accurately after the prompt of the intelligent driving system, a negative reward value -2.5 is given, and if the user takes over neither in time nor accurately after the prompt of the intelligent driving system, a negative reward value -5 is given.

[0051] Substep 13, the plurality of behavior reward values are weighted and calculated to obtain the driving ability value of the user.

[0052] Each data in the historical driving behavior data can correspond to a plurality of behavior reward values. After determining the plurality of behavior reward values corresponding to the plurality of data, a reasonable reward function can be designed, which can accurately reflect the safety and effectiveness of the driving behavior, and encourage the driver to take safe driving behavior.

[0053] The design of the reward function should consider multiple data to ensure the safety and efficiency of driving. For the reward function of the preset historical mileage, it can be expressed as: =

[0054] Wherein, is the weight of the behavior reward value corresponding to each data, The initial value is 0, that is, the driving ability value. As an example, The value of the weight can be adjusted by training the relationship between the driving behavior data and the weight using a large amount of data to achieve the best.

[0055] The reward function is used to weight and calculate the plurality of behavior reward values to obtain the driving ability value of the user .

[0056] Substep 14, according to the driving ability value, determining the user takeover ability parameter of the user taking over the vehicle control right under the prompt of the assisted driving system.

[0057] After obtaining the driving ability value of the user, the user takeover ability parameter of the user can be determined according to the driving ability value, that is, the user takeover ability of the user is classified by the driving ability value.

[0058] In some embodiments of the application, the determination of the user takeover ability parameter of the user taking over the vehicle control right under the prompt of the assisted driving system according to the driving ability value comprises: Substep 21, according to the historical driving behavior data, determining the user takeover accuracy rate and the user takeover timely rate.

[0059] Specifically, the historical driving behavior data includes user takeover data, including data related to the user taking over the control of the vehicle under the prompt of the assisted driving system, which can include the total number of times the user takes over the control of the vehicle, the number of times the user takes over the control of the vehicle in time, and the number of times the user takes over the control of the vehicle accurately.

[0060] The user takeover accuracy rate and the user takeover timely rate can be determined by the following formula: User takeover timely rate = (number of times the user takes over the control of the vehicle in time / total number of times the user takes over the control of the vehicle) * 100%; User takeover accuracy rate = (number of times the user takes over the control of the vehicle accurately / total number of times the user takes over the control of the vehicle) * 100%.

[0061] Sub-step 22, determining a user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system according to the driving ability value, the user takeover accuracy rate, and the user takeover timely rate.

[0062] After obtaining the driving ability value R, the user takeover accuracy rate, and the user takeover timely rate, the user takeover ability level of the user can be determined by combining the positive and negative of the R value, that is, the user takeover ability parameter of the user is determined.

[0063] Specifically, after weighting calculation, when the R value is positive and the user takeover accuracy rate and the user takeover timely rate reach 90% or more, it can be determined that the user takeover ability level of the user is level one; When the R value is positive and the user takeover accuracy rate and the user takeover timely rate reach 80% or more, it can be determined that the user takeover ability level of the user is level two; When the R value is negative or the passive takeover timely rate and the accuracy rate are between 60% and 80%, it can be determined that the user takeover ability level of the user is level three.

[0064] In some embodiments of the present application, the behavior reward value includes a negative reward value, and the user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system is determined according to the driving ability value, including: Sub-step 31, determining a target driving project according to the negative reward value.

[0065] The behavior reward value includes a positive reward value and a negative reward value, and multiple negative reward values corresponding to multiple data can be included in multiple behavior reward values, so that the data type corresponding to the negative reward value with the highest number and the highest frequency of occurrence, that is, the target driving project, can be determined according to multiple negative reward values corresponding to multiple data respectively.

[0066] Sub-step 32, determining a user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system according to the driving ability value and the target driving item.

[0067] After determining the target driving item, the user takeover ability parameter of the user taking over the control of the vehicle under the prompt of the assisted driving system can be determined in combination with the driving ability value.

[0068] Specifically, when the R value is negative, the data type corresponding to the largest number of negative reward values and the highest frequency is attention determination data, and the driver's takeover ability is determined to be level four at this time. When the R value is negative, the data type corresponding to the largest number of negative reward values and the highest frequency is user takeover data, and the driver's takeover ability is determined to be level five at this time.

[0069] Among them, the smaller the level value of the user's user takeover ability level represents the stronger the user's user takeover ability.

[0070] In some embodiments of the present application, the historical driving behavior data includes a plurality of target data, and the target driving item is determined according to the negative reward value, including: Sub-step 41, determining the number of negative reward values corresponding to the plurality of target data respectively.

[0071] The historical driving behavior data can include a plurality of target data, i.e. lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, and user takeover data.

[0072] The number of negative reward values corresponding to the plurality of target data respectively and the total number of negative reward values can be determined from a plurality of behavior reward values.

[0073] Sub-step 42, determining the negative reward proportion corresponding to the plurality of target data respectively according to the number of negative reward values corresponding to the plurality of target data respectively.

[0074] After obtaining the number of negative reward values corresponding to the plurality of target data respectively, the number of negative reward values corresponding to the plurality of target data respectively can be calculated to obtain the proportion of the number of negative reward values corresponding to the plurality of target data respectively in the total number of negative reward values, i.e. the negative reward proportion.

[0075] Sub-step 43, determining the target driving item according to the negative reward proportion corresponding to the plurality of target data respectively.

[0076] After obtaining the proportion of negative rewards corresponding to each target data, the data type corresponding to the highest negative reward proportion value, i.e., the data type corresponding to the highest number of negative reward values and the highest frequency, is obtained, which is the target driving project.

[0077] In step 102, the takeover time threshold of the auxiliary driving system prompting the user is determined according to the user takeover capability parameter.

[0078] In actual application, the maximum allowed takeover time (TOT_max) threshold of the takeover request can be set according to relevant safety standards and experimental data. In this application, after obtaining the user takeover capability level of the user, the takeover time threshold of the auxiliary driving system prompting the user can be determined differently according to the user takeover capability level of the user.

[0079] In actual application, for the user whose user takeover capability level (i.e., user takeover capability parameter) is greater than or equal to three, the auxiliary driving system can prompt the user earlier, for the user whose user takeover capability level is two, the auxiliary driving system can maintain the normal takeover access time node, and for the user whose user takeover capability level is one, the time of the auxiliary driving system prompting the user can be appropriately delayed.

[0080] Specifically, in some embodiments of the present application, when the user takeover capability of the user is greater than or equal to three, the user is prompted to take over the vehicle control right according to a preset first takeover time threshold; When the user takeover capability of the user is two, the user is prompted to take over the vehicle control right according to a preset second takeover time threshold; When the user takeover capability of the user is one, the user is prompted to take over the vehicle control right according to a preset third takeover time threshold; The first takeover time threshold is greater than the preset second takeover time threshold, and the second takeover time threshold is greater than the third takeover time threshold.

[0081] For example, the maximum allowed takeover time threshold is 15S, the first takeover time threshold can be 13S, the second takeover time threshold can be 11S, and the third takeover time threshold is 10S, which is not limited here.

[0082] In step 103, the auxiliary driving system prompts the user to take over the vehicle control right according to the takeover time threshold.

[0083] After determining the takeover time threshold of the auxiliary driving system prompting the user, the auxiliary driving system can prompt the user to take over the vehicle control right according to the takeover time threshold.

[0084] In some embodiments of the present application, further comprising: According to the user takeover ability parameter of the user, a first personalized training strategy for the user is generated, and the vehicle is controlled to respond according to the first personalized training strategy.

[0085] After determining the user takeover ability level of the user, a first personalized training strategy for the user can be generated according to the user takeover ability level, and the vehicle is controlled to respond according to the first personalized training strategy. Specifically, the first personalized training strategy for the user can be generated by the intelligent vehicle machine itself or the cloud, and then the vehicle prompts the user to perform the personalized training, thereby improving the user's takeover ability.

[0086] For example, in the case where the user takeover ability level of the user is determined to be level one or level two, it indicates that the user's takeover ability is strong, and no training is needed.

[0087] In the case where the user takeover ability level of the user is determined to be level three, which is relatively low, emergency takeover video training can be added for the user, such as prompting the user to watch emergency takeover videos for takeover ability training.

[0088] In the case where the user takeover ability level of the user is determined to be level four, which is relatively low, it can be seen that the user may always be inattentive during driving, and the specific possible performance is frequent hands-off the steering wheel. Therefore, emergency takeover driving training can be added for the user, such as prompting the user to perform targeted and personalized driving schemes for takeover ability training.

[0089] In the case where the user takeover ability level of the user is determined to be level five, which is relatively low, similar to the case of level four, emergency takeover driving training can be added for the user, such as prompting the user to perform targeted and personalized driving schemes for takeover ability training. However, the content and difficulty of the emergency takeover driving training corresponding to different user driving ability levels will be different.

[0090] In some embodiments of the present application, further comprising: According to the target driving project, a second personalized training strategy for the user is generated, and the vehicle is controlled to respond according to the second personalized training strategy.

[0091] After determining the target driving project, i.e., the data type corresponding to the largest number of negative reward values and the highest frequency, in the case where the driving ability value of the user, i.e., the R value, is negative, if the target driving project is irrelevant to the user takeover ability level determination, a second personalized training strategy for the user can be generated for the target driving project, and the vehicle is controlled to respond according to the second personalized training strategy.

[0092] Specifically, it can be understood that the scheme in the application can identify the weak points in the driving behavior of the user and the strength of the user takeover ability of the user, thereby providing targeted and personalized training strategies.

[0093] For example, for the user whose corresponding data category with the most negative reward value and the highest frequency of occurrence is "lane keeping data", there may be "vehicle lane deviation" improper behavior, and the targeted and personalized training strategy can be to increase long-distance highway driving (long-time boring driving environment, let the user learn to overcome fatigue and attention dispersion, etc., focus on keeping the vehicle driving within the lane line), highway driving with traffic congestion and frequent traffic flow changes (the user needs to accurately grasp the position relationship between the vehicle and the lane line in the process of frequent lane changing and speed adjustment, and improve the control ability of the lane in complex traffic conditions), driving on curved roads and uphill and downhill sections (the inertia and center of gravity of the vehicle driving on these sections change greatly, which is easy to make the user deviate from the lane when operating, and the user needs to master the skill of keeping the vehicle stable driving on the curved road and the slope without deviating from the lane).

[0094] At the same time, after the personalized training strategy is achieved, it can also be changed from a highway section to an urban road and a rural road, and a driving scene of special weather and road, gradually increasing the difficulty.

[0095] In some embodiments of the application, after the second personalized training strategy is completed, a second target driving project is determined, and a third personalized training strategy for the user is generated according to the second target driving project, and the vehicle is controlled to respond according to the third personalized training strategy.

[0096] After the second personalized training strategy is completed, the data category corresponding to the most negative reward value and the highest frequency of occurrence is no longer the current target driving project, and if the driving ability value of the user, i.e., R value, is still negative, the data category corresponding to the most negative reward value and the highest frequency of occurrence can be determined as the second target driving project.

[0097] Or, after the second personalized training strategy is completed, the data category corresponding to the most negative reward value and the highest frequency of occurrence is still the current target driving project, and if the driving ability value of the user, i.e., R value, is still negative, the data category corresponding to the second most negative reward value and the second highest frequency of occurrence can be determined as the second target driving project.

[0098] For example, when the data type corresponding to the largest number of negative reward values and the highest frequency is no longer lane keeping data, the training content of lane deviation from the lane is reduced, and a third personalized training strategy for the user is generated according to the data type corresponding to the second largest number of negative reward values and the second highest frequency (i.e., the second target driving project), and the vehicle is controlled to respond according to the third personalized training strategy.

[0099] Alternatively, when the data type corresponding to the largest number of negative reward values and the highest frequency is still lane keeping data, the training content of lane deviation from the lane can also be reduced, and a third personalized training strategy for the user is generated according to the data type corresponding to the second largest number of negative reward values and the second highest frequency, and the vehicle is controlled to respond according to the third personalized training strategy.

[0100] In the above manner, the dynamic adjustment of the targeted and personalized user training strategy is realized, which can effectively improve the driving skills of the driver and thus improve the driving safety and user experience.

[0101] In an example, the method of the present application can also monitor the user in real time, provide instant feedback through an intelligent voice assistant, including conversational reminders and solutions, thereby improving the safety of driving while increasing the user's driving experience.

[0102] Conversational reminders: the intelligent voice assistant can communicate with the user through dialogue and remind the user of bad behavior. For example, "Hello, I noticed that you have been looking away from the road for a long time and are in a distracted driving state, which is an unsafe driving behavior. Please pay attention to traffic rules." Providing solutions: In addition to reminding the problem, the intelligent voice assistant can also provide solutions according to the behavior monitored in real time. For example, when the user is in a distracted driving state (e.g., fatigue), the voice assistant can provide information about nearby rest areas and help the user plan a route to the rest area.

[0103] In an embodiment of the present application, by acquiring a user takeover ability parameter of a user taking over control of a vehicle under a prompt of an assisted driving system, determining a takeover time threshold of the assisted driving system prompting the user to take over control of the vehicle according to the user takeover ability parameter, and controlling the assisted driving system to prompt the user to take over control of the vehicle according to the takeover time threshold, the user can be prompted to take over control of the vehicle differently based on the user's user takeover ability, ensuring that the user can take over the vehicle in critical situations to save accidents and improve driving safety.

[0104] It should be noted that, for the method embodiments, for the sake of simple description, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present application are not limited to the action sequence described, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily the necessary actions of the embodiments of the present application.

[0105] Referring to Figure 2 , a structure block diagram of a processing device based on user takeover ability evaluation provided in the embodiments of the present application is shown, which can specifically include the following modules: The data acquisition module 201 is configured to acquire a user takeover ability parameter of the user taking over the control right of the vehicle under the prompting of the auxiliary driving system; The time threshold determination module 202 is configured to determine a takeover time threshold of the user prompted by the auxiliary driving system according to the user takeover ability parameter; The control prompting module 203 is configured to control the auxiliary driving system to prompt the user to take over the control right of the vehicle according to the takeover time threshold.

[0106] In an optional embodiment of the present application, it further includes: The first personalized learning module is configured to generate a first personalized training strategy for the user according to the user takeover ability parameter of the user, and control the vehicle to respond according to the first personalized training strategy.

[0107] In an optional embodiment of the present application, the data acquisition module 201 includes: The data acquisition submodule is configured to acquire historical driving behavior data of the user; The reward value determination submodule is configured to determine a plurality of behavior reward values corresponding to the historical driving behavior data; The driving ability value determination submodule is configured to perform weighted calculation on the plurality of behavior reward values to obtain a driving ability value of the user; The takeover ability determination submodule is configured to determine a user takeover ability parameter of the user taking over the control right of the vehicle under the prompting of the auxiliary driving system according to the driving ability value.

[0108] In an optional embodiment of the present application, the takeover ability determination submodule includes: The takeover data determination unit is configured to determine a user takeover accuracy rate and a user takeover timeliness rate according to the historical driving behavior data; The first takeover ability determining unit is configured to determine a user takeover ability parameter of the user taking over the control right of the vehicle under the prompting of the assisted driving system according to the driving ability value, the user takeover accuracy rate and the user takeover timeliness rate.

[0109] In an optional embodiment of the present application, the behavior reward value includes a negative reward value, and the takeover ability determining sub-module includes: The target project determining unit is configured to determine a target driving project according to the negative reward value. The first takeover ability determining unit is configured to determine a user takeover ability parameter of the user taking over the control right of the vehicle under the prompting of the assisted driving system according to the driving ability value and the target driving project.

[0110] In an optional embodiment of the present application, the present application further includes: The second personalized learning module is configured to generate a second personalized training strategy for the user according to the target driving project, and control the vehicle to respond according to the second personalized training strategy.

[0111] In an optional embodiment of the present application, the historical driving behavior data includes a plurality of target data, and the target project determining unit includes: The negative reward value quantity determining sub-unit is configured to determine a quantity of negative reward values corresponding to the plurality of target data respectively. The negative reward proportion determining sub-unit is configured to determine a negative reward proportion corresponding to the plurality of target data respectively according to the quantity of negative reward values corresponding to the plurality of target data respectively. The target project determining sub-unit is configured to determine a target driving project according to the negative reward proportion corresponding to the plurality of target data respectively.

[0112] In an optional embodiment of the present application, the historical driving behavior data is driving behavior data of a preset historical mileage, and the historical driving behavior data includes one or more of the following: Lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data and user takeover data.

[0113] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts refer to the part of the method embodiment.

[0114] In addition, the present application further provides an electronic device, such as Figure 3As shown, the device includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304, The memory 303 is configured to store a computer program. The processor 301 is configured to execute the program stored in the memory 303 to implement the following steps: obtain a user takeover ability parameter of a user taking over control of a vehicle under prompting of an advanced driving system; determine a takeover time threshold for the advanced driving system to prompt the user according to the user takeover ability parameter; control the advanced driving system to prompt the user to take over control of the vehicle according to the takeover time threshold.

[0115] In an optional embodiment of the present application, the device further includes: generate a first personalized training strategy for the user according to the user takeover ability parameter of the user, and control the vehicle to respond according to the first personalized training strategy.

[0116] In an optional embodiment of the present application, the obtaining of the user takeover ability parameter of the user taking over control of the vehicle under prompting of the advanced driving system includes: obtain historical driving behavior data of the user; determine a plurality of behavior reward values corresponding to the historical driving behavior data; perform weighted calculation on the plurality of behavior reward values to obtain a driving ability value of the user; determine the user takeover ability parameter of the user taking over control of the vehicle under prompting of the advanced driving system according to the driving ability value.

[0117] In an optional embodiment of the present application, the determining of the user takeover ability parameter of the user taking over control of the vehicle under prompting of the advanced driving system according to the driving ability value includes: determine a user takeover accuracy rate and a user takeover timeliness rate according to the historical driving behavior data; determine the user takeover ability parameter of the user taking over control of the vehicle under prompting of the advanced driving system according to the driving ability value, the user takeover accuracy rate, and the user takeover timeliness rate.

[0118] In an optional embodiment of the present application, the behavior reward value includes a negative reward value, and the determining of the user takeover ability parameter of the user taking over control of the vehicle under prompting of the advanced driving system according to the driving ability value includes: determine a target driving item according to the negative reward value; determine a user takeover ability parameter of the user taking over control of the vehicle under a prompt of an assisted driving system according to the driving ability value and the target driving item.

[0119] In an optional embodiment of the present application, the method further comprises: generate a second personalized training strategy for the user according to the target driving item, and control the vehicle to respond according to the second personalized training strategy.

[0120] In an optional embodiment of the present application, the historical driving behavior data comprises a plurality of target data, and the determining of the target driving item according to the negative reward value comprises: determining a number of negative reward values corresponding to the plurality of target data respectively; determining a negative reward proportion corresponding to the plurality of target data respectively according to the number of negative reward values corresponding to the plurality of target data respectively; determining the target driving item according to the negative reward proportion corresponding to the plurality of target data respectively.

[0121] In an optional embodiment of the present application, the historical driving behavior data is driving behavior data of a preset historical mileage, and the historical driving behavior data comprises one or more of the following: lane keeping data, traffic signal following data, safe distance keeping data, safe speed control data, attention determination data, and user takeover data.

[0122] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0123] The communication interface is used for communication between the terminal and other devices.

[0124] The memory can include a Random Access Memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0125] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0126] As shown in the method for managing a home device provided in the embodiments of the present application, Figure 4 In another embodiment provided in the present application, a computer readable storage medium 401 is provided, and the computer readable storage medium 401 stores instructions, and when the instructions are executed on a computer, the computer executes the method for managing a home device provided in the embodiments of the present application.

[0127] In another embodiment provided in the present application, a computer program product is provided, and the computer program product includes instructions, and when the instructions are executed on a computer, the computer executes the method for evaluating a user takeover ability provided in the embodiments of the present application.

[0128] In the embodiments described above, the implementation can be achieved entirely or partially by software, hardware, firmware or any combination thereof. When implemented by software, the implementation can be achieved entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the entire or partial process or function described in the embodiments of the present application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0129] It is to be noted that, in the present document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0130] Each of the embodiments described in the present document is described in a related manner, and the same or similar parts among the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0131] The preferred embodiments of the present application have been described above with the aid of drawing figures, and are not limited to those embodiments; instead, they will include any modifications and alternatives obvious to those skilled in the art.

Claims

1. A processing method based on user takeover capability assessment, characterized in that, The method includes: Acquire user takeover capability parameters when prompted by the driver assistance system to take over vehicle control; Based on the user takeover capability parameters, determine the takeover time threshold for the driver assistance system to prompt the user. According to the stated takeover time threshold, the driver assistance system prompts the user to take over control of the vehicle.

2. The method according to claim 1, characterized in that, Also includes: Based on the user's user takeover capability parameters, a first personalized training strategy is generated for the user, and the vehicle is controlled to respond in accordance with the first personalized training strategy.

3. The method according to any one of claims 1-2, characterized in that, Acquire user takeover capability parameters when prompted by the driver assistance system, including: Obtain the user's historical driving behavior data; Based on the historical driving behavior data, determine the corresponding multiple behavior reward values; The driving ability value of the user is obtained by weighting the multiple behavior reward values; Based on the driving ability value, determine the user takeover capability parameter for taking over vehicle control with the prompts of the driver assistance system.

4. The method according to claim 3, characterized in that, Based on the driving ability value, determine the user takeover capability parameters for taking over vehicle control under the prompting of the driver assistance system, including: Based on the historical driving behavior data, determine the user takeover accuracy rate and the user takeover time rate; Based on the driving ability value, the user takeover accuracy rate, and the user takeover time rate, the user takeover capability parameters for taking over vehicle control with the prompts of the driver assistance system are determined.

5. The method according to claim 3, characterized in that, The behavioral reward value includes a negative reward value. Based on the driving ability value, the user takeover capability parameters for taking over vehicle control under the prompts of the driver assistance system are determined, including: The target driving activity is determined based on the negative reward value; Based on the driving ability value and the target driving item, determine the user takeover capability parameters for taking over vehicle control with the prompts of the driver assistance system.

6. The method according to claim 5, characterized in that, Also includes: Based on the target driving project, a second personalized training strategy is generated for the user, and the vehicle is controlled to respond in accordance with the second personalized training strategy.

7. The method according to claim 5, characterized in that, The historical driving behavior data includes multiple target data. Based on the negative reward value, target driving items are determined, including: Determine the number of negative reward values ​​corresponding to each of the various target data; Based on the number of negative reward values ​​corresponding to the various target data, the proportion of negative rewards corresponding to the various target data is determined. The target driving project is determined based on the proportion of negative rewards corresponding to the various target data.

8. The method according to claim 3, characterized in that, The historical driving behavior data is driving behavior data based on a preset historical mileage, and the historical driving behavior data includes one or more of the following: Lane keeping data, traffic signal compliance data, safe distance maintenance data, safe speed control data, attention assessment data, and user takeover data.

9. A processing device based on user takeover capability assessment, characterized in that, The device includes: The data acquisition module is used to acquire user takeover capability parameters when the user takes over vehicle control under the prompt of the driver assistance system; The time threshold determination module is used to determine the takeover time threshold for the assisted driving system to prompt the user based on the user takeover capability parameter. The control prompt module is used to control the driver assistance system to prompt the user to take over vehicle control according to the takeover time threshold.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements the method as described in any one of claims 1-8.

Images