Passenger protection method and device, vehicle and storage medium

Abstract

The invention provides a passenger protection method and device, a vehicle and a storage medium, and relates to the technical field of vehicles, and the method comprises the steps: judging whether a target vehicle has a potential collision risk or not according to obtained road traffic environment information; when the target vehicle has the potential collision danger, performing damage probability analysis on a passenger on a target seat in the target vehicle according to the obtained road traffic environment information, the vehicle exterior information and the vehicle interior information of the target vehicle to obtain a damage probability result; when the damage probability result is larger than a first preset probability, seat position parameters of the target seat are adjusted until the damage probability result is smaller than a second preset probability, and the first preset probability is larger than or equal to the second preset probability and used for protecting the passenger in combination with the sitting posture of the passenger.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a passenger protection method and device, a vehicle and a storage medium. BACKGROUND

[0002] With the continuous development of intelligent and networked technologies of vehicles, the cockpit presents various use scenarios such as office, entertainment, rest, etc. In these use scenarios, the passenger sitting posture presents diversity, and the seatback angle is mostly in a large angle form. The sitting posture has a certain correlation with the injury of the passenger in a traffic accident. Under a large angle sitting posture, the passenger is more likely to be injured.

[0003] In the related art, the passenger protection method has technical limitations in passenger protection. It mainly considers the passenger protection method and vehicle protection after an accident occurs, such as passive safety measures such as airbag deployment and seat belt pretensioning to reduce the injury caused by the collision. This kind of method is usually designed and optimized based on the standard sitting posture, or the passive protection is performed after the non-standard sitting posture is instantaneously returned to the standard sitting posture. However, the instantaneous return when a collision occurs is easy to cause the passenger to be injured, and the passive protection when a collision occurs has a lag. Therefore, the related art is difficult to adapt to the diversified passenger sitting posture scenarios in the current intelligent cockpit, and the protection method has limitations. SUMMARY

[0004] The problem solved by the present application is how to protect the passenger in combination with the passenger sitting posture.

[0005] To solve the above problems, the present application provides a passenger protection method, device, vehicle and storage medium.

[0006] In a first aspect, the present application provides a passenger protection method, comprising: determining whether a target vehicle has a potential collision danger according to acquired road traffic environment information; when the target vehicle has a potential collision danger, performing injury probability analysis on a passenger located on a target seat in the target vehicle according to the acquired road traffic environment information, off-vehicle information and in-vehicle information of the target vehicle, and obtaining an injury probability result; when the injury probability result is greater than a first preset probability, adjusting a seat position parameter of the target seat until the injury probability result is less than a second preset probability, wherein the first preset probability is greater than or equal to the second preset probability.

[0007] Optionally, the passenger protection method further comprises: obtaining a seat target parameter when the seat position parameter of the target seat is adjusted to the injury probability result being less than the second preset probability; determining a target restraint parameter of an occupant restraint system matched with the target seat according to the in-vehicle information, the seat target parameter, the road traffic environment information and the out-of-vehicle information.

[0008] Optionally, after the determining the target restraint parameter of the occupant restraint system matched with the target seat according to the in-vehicle information, the seat target parameter, the road traffic environment information and the out-of-vehicle information, the method further comprises: controlling the occupant restraint system to perform occupant restraint according to the target restraint parameter in response to a collision signal, performing occupant injury probability prediction based on the collision signal to obtain a prediction probability result; triggering an alarm and rescue when the prediction probability result meets a preset condition.

[0009] Optionally, the road traffic environment information comprises at least one of road information, road condition information or weather information; and the determining whether the target vehicle exists a potential collision risk according to the acquired road traffic environment information comprises: determining whether at least one of the road information, the road condition information or the weather information is abnormal; if yes, determining that the target vehicle exists a potential collision risk; and if no, determining that the target vehicle does not exist a potential collision risk.

[0010] Optionally, the method further comprises: triggering a driving warning when the target vehicle exists a potential collision risk; and / or, determining occupant sitting posture information of an occupant located on the target seat according to the in-vehicle information, determining whether the occupant sitting posture information meets a safe sitting posture condition, and triggering a safety warning when the occupant sitting posture information does not meet the safe sitting posture condition.

[0011] Optionally, the out-of-vehicle information is acquired based on an out-of-vehicle sensing device. the injury probability analysis of the occupant located on the target seat in the target vehicle according to the acquired road traffic environment information, out-of-vehicle information and in-vehicle information of the target vehicle to obtain an injury probability result comprises: inputting the road traffic environment information, the out-of-vehicle information and the in-vehicle information into a pre-trained occupant injury prediction model to determine injury probabilities of each part of the occupant located on the target seat as the injury probability result.

[0012] Optionally, the seat position parameter comprises a seat backrest angle, a seat cushion angle and a foot support angle. The adjusting the seat position parameter of the target seat until the injury probability result is less than a second preset probability comprises: When the injury probability of at least one part is greater than the first preset probability, stepwise adjusting at least one of the seatback angle, the cushion angle and the footrest angle of the target seat; After each adjustment, the injury probability of each part of the occupant located on the target seat is re-determined by the occupant injury prediction model, and the seat position parameter is iteratively adjusted based on the re-determined injury probability until the injury probability of each part is less than the second preset probability, and the seat target parameter is obtained.

[0013] Optionally, before the road traffic environment information, the out-of-vehicle information and the in-vehicle information are input into the pre-trained occupant injury prediction model to determine the injury probability of each part of the occupant located on the target seat as the injury probability result, it further comprises: The acquired first input data set and the true injury probability of each part of the occupant corresponding to the first input data set are used as first training samples, and each first input data set comprises a set of out-of-vehicle information samples, in-vehicle information samples and road traffic environment samples; The first machine learning model is trained by the first training sample until the first machine learning model meets a first preset convergence condition, and the occupant injury prediction model is obtained.

[0014] Optionally, the target restraint parameter of the occupant restraint system matched with the target seat according to the in-vehicle information, the seat target parameter, the road traffic environment information and the out-of-vehicle information comprises: Obtaining the occupant physical sign of the occupant located on the target seat according to the in-vehicle information; Determining the crash condition information according to the road traffic environment information and the out-of-vehicle information; Inputting the occupant physical sign, the seat target parameter and the crash condition information into a pre-trained occupant restraint parameter optimization model to determine the target restraint parameter.

[0015] Optionally, the crash condition information comprises at least one of the crash type, the speed, the relative lateral displacement and the angle; And / or, the target restraint parameter comprises at least one of the airbag ignition time, the seat belt pretensioning time, the seat belt limiting force value, and the seat belt waistband pretensioning time.

[0016] Optionally, before inputting the occupant vital signs, the target seat parameters, and the collision condition information into a pre-trained occupant constraint parameter optimization model to determine the target constraint parameters, the method further includes: The acquired second input data set and the actual constraint parameters of the occupant restraint system corresponding to the second input data set are used as the second training samples. Each second input data set includes a set of occupant vital signs training data, seat parameter training data, and collision condition training data. Based on the second training sample, the second machine learning model is optimized and trained using a preset optimization algorithm until the second machine learning model meets the second preset convergence condition, thereby obtaining the occupant constraint parameter optimization model.

[0017] Optionally, the step of controlling the occupant restraint system to perform occupant restraint based on the target constraint parameters, and predicting the occupant injury probability based on the collision signal to obtain the predicted probability result includes: The occupant injury prediction model is used to predict the probability of occupant injury based on the collision signal and the collision condition information, and the predicted probability result is obtained. The occupant injury prediction model is trained from traffic accident data samples including data of the target vehicle.

[0018] Secondly, the present invention also provides an occupant protection device, comprising: The driving safety warning control module is used to determine whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information; The seating posture adjustment control module is used to perform injury probability analysis on the occupant in the target seat inside the target vehicle based on the acquired road traffic environment information, external information and internal information of the target vehicle when there is a potential collision hazard in the target vehicle, and obtain an injury probability result; it is also used to adjust the seat position parameters of the target seat when the injury probability result is greater than a first preset probability, until the injury probability result is less than a second preset probability, wherein the first preset probability is greater than or equal to the second preset probability.

[0019] Thirdly, the present invention also provides a vehicle, including a memory and a processor; The memory is used to store computer programs; The processor is configured to implement the occupant protection method as described above when executing the computer program.

[0020] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the occupant protection method as described above.

[0021] The beneficial effects of the occupant protection method of the present invention are: By acquiring road traffic environment information during vehicle movement, potential collision hazards can be identified in advance. When a potential collision hazard exists, road traffic environment information, external vehicle information, and internal vehicle information are further integrated to analyze the probability of injury to occupants in the target seats. Based on this, when the probability of injury is greater than a first preset probability, the seat position parameters are proactively adjusted until the probability of injury drops below a second preset probability. Proactive seat adjustment only occurs when there is a potential collision hazard and the probability of occupant injury is high. This reduces false triggering, improves the accuracy of occupant protection, and balances occupant comfort and reliability. Adjusting the seat in advance based on pre-collision predictions improves the effectiveness of occupant protection. Furthermore, adjusting the seat at normal speed before a collision avoids secondary injuries that might result from forcibly straightening the seat at the moment of impact. This achieves proactive optimization of seat position based on the occupant's actual sitting posture during the collision avoidance phase, enhancing the effectiveness and safety of occupant protection in non-standard sitting positions. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the occupant protection method according to an embodiment of the present invention; Figure 2 This is another schematic flowchart of the occupant protection method according to an embodiment of the present invention; Figure 3 This is a flowchart of the occupant protection method during the driving phase according to an embodiment of the present invention; Figure 4 This is a flowchart illustrating the seat position step adjustment in the occupant protection method according to an embodiment of the present invention. Figure 5 This is a flowchart of the collision avoidance stage of the occupant protection method according to an embodiment of the present invention; Figure 6 This is a system block diagram of the occupant protection system according to an embodiment of the present invention; Figure 7 This is an example diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0023] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0024] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0025] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0026] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0027] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0028] like Figure 1 As shown, an embodiment of the present invention provides an occupant protection method, comprising: Step S100: Determine whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information.

[0029] The occupant protection method in this invention aims to provide end-to-end protection for occupants by determining whether there is a potential collision hazard in the road traffic environment before a collision. For example, road traffic environment information includes information generated by the road traffic environment obtained through the Internet, such as speed limits, congestion near the vehicle, accident situations, or weather information received through the network. When at least one of the above information is abnormal, it indicates that the probability of an accident is higher than in normal traffic conditions, triggering a pre-collision driving safety warning to remind the driver to pay attention and remind the occupants to maintain proper seating posture.

[0030] Step S200: When the target vehicle has a potential collision hazard, the occupant in the target seat inside the target vehicle is subjected to damage probability analysis based on the obtained road traffic environment information, external information and internal information of the target vehicle, and damage probability results are obtained.

[0031] Occupant injury probability analysis is a process of quantitatively assessing the degree of injury that occupants may suffer under specific collision conditions by integrating data on the vehicle's external environment and the occupants' internal state.

[0032] When a vehicle presents a potential hazard, proactive predictions are made based on both external and internal vehicle information. By identifying potential risks in advance and making corresponding adjustments, the actual severity of occupant injury in a collision can be effectively reduced. External information includes data acquired by onboard sensors, such as images and point clouds obtained through radar and cameras. Internal information includes data acquired by onboard sensors, such as two-dimensional and three-dimensional images or point clouds of the vehicle interior obtained through cameras, 3D cameras, and radar. Damage probability analysis is performed using both external and internal information, incorporating occupants into the assessment system. This ensures that safety protection measures are more closely aligned with actual occupant characteristics and provides an objective basis for the dynamic adjustment of safety system parameters.

[0033] Step S300: When the damage probability result is greater than the first preset probability, the seat position parameters of the target seat are adjusted until the damage probability result is less than the second preset probability, wherein the first preset probability is greater than or equal to the second preset probability.

[0034] The first preset probability and the second preset probability represent pre-set damage risk thresholds, where the first preset probability represents the threshold for higher risk and the second preset probability represents the threshold for lower risk. When the target vehicle has a potential collision hazard, damage probability analysis is performed on the occupants in the target seats based on acquired road traffic environment information, external vehicle information, and internal vehicle information. If the damage probability result is greater than the first preset probability, the seat position parameters are adjusted until the obtained damage probability result is less than the second preset probability, and the corresponding seat position parameters are determined as the target seat parameters.

[0035] After triggering the pre-collision safety warning, the system enters the collision avoidance phase. During this phase, given the probability of a collision, the system assesses the occupant's risk of injury based on their current seating position and environmental information. When the probability of injury is higher than a first preset probability, it indicates a high safety risk in the current seat position parameters, requiring pre-emptive optimization of the seat position to reduce potential collision-related injuries. By directly adjusting the seat position to a state where the probability of injury is lower than a second preset probability, it effectively prevents restraint system failure or abnormal occupant force during a collision due to the seat being in an unsafe posture.

[0036] By directly linking seat position adjustments to occupant injury risk, protection strategies are based on objective injury probability assessments rather than fixed rules or experience-based settings, thereby achieving more precise and effective occupant protection in diverse seating scenarios.

[0037] In embodiments of the present invention, by acquiring road traffic environment information during vehicle operation, it is possible to identify in advance whether a target vehicle poses a potential collision hazard. When a potential collision hazard exists, road traffic environment information, external vehicle information, and internal vehicle information are further integrated to perform an injury probability analysis on the occupant in the target seat. Based on this, when the injury probability result is greater than a first preset probability, the seat position parameters are actively adjusted until the injury probability drops below a second preset probability, thereby obtaining target seat parameters adapted to the current occupant's sitting posture and the risk scenario. This avoids secondary injuries that may be caused by forcibly straightening the seat at the moment of collision, and achieves proactive optimization of the seat position based on the occupant's actual sitting posture during the collision avoidance phase, improving the effectiveness and safety of occupant protection in non-standard sitting postures.

[0038] Optionally, such as Figure 2 As shown, occupant protection methods also include: Step S400: Obtain the seat position parameters of the target seat so that the damage probability result is less than the second preset probability; Step S500: Determine the target constraint parameters of the occupant restraint system that matches the target seat based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information.

[0039] Target constraint parameters represent occupant restraint system parameters determined to meet occupant safety requirements, including active protection parameters for airbags and seat belts.

[0040] By combining in-vehicle information, taking into account the occupants' posture and state, and sensing the external driving environment through road traffic environmental information obtained from the network, and by sensing the real-time external state through external information, the restraint system parameters are determined based on comprehensive environmental and occupant state data, making the restraint system parameters more scientific and reasonable. By integrating multi-source information, the pertinence and effectiveness of safety protection measures are improved; human judgment errors are reduced, and the level of occupant safety protection is enhanced. By combining in-vehicle information, the problem of the restraint system's inability to adaptively adjust due to changes in occupant posture is solved. Based on target restraint parameters, the occupant restraint system can be controlled to restrain occupants in advance before a collision, or to restrain occupants during a collision.

[0041] Optionally, such as Figure 2 As shown, occupant protection methods also include: Step S600: In response to the collision signal, control the occupant restraint system to perform occupant restraint according to the target constraint parameters, and predict the occupant injury probability based on the collision signal to obtain the prediction probability result.

[0042] In one embodiment, the collision signal is triggered by vehicle acceleration or pressure on the vehicle body, or by sensors such as radar or cameras installed in the vehicle, or by network signals.

[0043] During the collision phase, the occupant restraint system is triggered based on pre-determined target constraint parameters, ensuring that the constraint parameters are optimal for the current situation. Simultaneously with triggering the restraint system, the probability of occupant injury is predicted based on the collision signal, ensuring that an alarm and rescue response are triggered immediately.

[0044] Step S700: When the predicted probability result meets the preset conditions, an alarm rescue is triggered.

[0045] When it is determined that the occupant may be injured, that is, when the predicted probability meets the preset conditions, an alarm and rescue are triggered.

[0046] For example, the predicted probability results include the predicted probability of injury to various parts of the occupant's body. When any occupant has a part of their body that exceeds the probability of injury, an accident alarm and rescue are triggered.

[0047] In embodiments of the present invention, during the driving phase, potential hazards are identified before a collision using road traffic environment information, and a collision avoidance phase is initiated after the potential hazard is identified. Occupant injury probability analysis is performed by combining external and internal vehicle information. Seat position parameters are adjusted incrementally based on the occupant injury probability until the occupant injury probability is less than a second preset probability, avoiding additional damage caused by the seat instantly returning to its original position during a collision. Before a collision, seat target parameters and appropriate target constraint parameters for the current vehicle driving state are predicted based on the target parameters of the seat inside the vehicle, internal vehicle information, and external vehicle information. Occupant constraints are applied based on these target constraint parameters during a collision, resolving the adaptive adjustment problem between occupant posture and the constraint system. After a collision, occupant injury probability is predicted, and when the prediction result meets a preset condition (i.e., a certain probability of occupant injury is predicted), an alarm is triggered, achieving end-to-end protection from the driving phase, collision avoidance phase, collision phase, and accident rescue.

[0048] Optionally, the road traffic environment information includes at least one of road information, road condition information, or weather information; the step of determining whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information includes: Determine whether at least one of the road information, traffic condition information, or weather information is abnormal; If yes, then the target vehicle is determined to have a potential collision risk; if no, then the target vehicle is determined not to have a potential collision risk.

[0049] In one embodiment, road traffic environment information refers to external environmental data such as road infrastructure conditions, traffic flow status, and weather conditions obtained through the Internet, including basic road information such as road type and speed limit requirements, real-time road condition information such as traffic congestion and road construction, and meteorological elements such as visibility and road surface slipperiness.

[0050] A potential collision hazard indicates that at least one of the above information items is in an abnormal state, such as a sudden change in the road speed limit from high to low, traffic congestion in road traffic environment information, or weather conditions such as rain, snow, or fog. By determining whether potential collision hazards exist in the road traffic environment information, an initial benchmark for environmental risk assessment is established. Using external environmental anomalies as trigger conditions for safety warnings allows for timely responses based on changes in environmental risks, enabling early identification of potential risk environments and avoiding the limitations of relying solely on the vehicle's own condition for judgment.

[0051] Optionally, such as Figure 3 As shown, the occupant protection method further includes: When the target vehicle presents a potential collision hazard, a driving warning is triggered; and / or, Based on the in-vehicle information, determine the occupant's sitting posture information in the target seat, and determine whether the occupant's sitting posture information meets the safe sitting posture conditions; when the occupant's sitting posture information does not meet the safe sitting posture conditions, trigger a safety warning.

[0052] In one embodiment, when a potential hazard is determined to exist in the road traffic environment, a driving warning is triggered, such as a text warning on the in-vehicle screen or a speed reminder warning, to remind the driver to slow down.

[0053] The in-vehicle information refers to data related to the occupant's posture obtained through in-vehicle sensing devices such as 3D cameras and radar, including parameters such as body posture angle, limb position, and contact status with the seat.

[0054] Occupant injury probability analysis is an assessment based on in-vehicle and out-of-vehicle information used to determine the level of injury risk to occupants in a potential collision. Safe seating posture conditions indicate the baseline for occupant posture that does not meet safety requirements, including feet off the footrests, upper body not remaining upright, and shoulders not naturally relaxed. Safety warnings include textual warnings on in-vehicle screens or seatbelt vibration reminders.

[0055] In one embodiment, a 3D camera is used to detect whether body parts meet the conditions for a safe sitting posture, such as whether the feet are placed on the footrest, whether the upper body is upright, whether the shoulders are naturally relaxed, whether the arms are naturally bent, and whether the headrest is level with the head; or an image recognition model such as YOLO or OpenPose is used to detect whether body parts meet the conditions for a safe sitting posture.

[0056] In one embodiment, the injury probability result represents the injury probability result of different parts of the occupant in the current sitting posture, such as the injury probability of the occupant's head, chest, abdomen, lumbar spine, pelvis, lower limbs, etc. as the injury probability result.

[0057] In one embodiment, occupant posture information is acquired through in-vehicle sensing devices. A machine learning model is then used to convert the acquired occupant posture images or point cloud data into occupant posture information. For example, machine learning models include YOLO, OpenPose, and others. The posture information includes image information, point cloud information, or information acquired by other in-vehicle sensing devices.

[0058] By monitoring occupants' sitting posture in real time and incorporating it into the safety early warning system, the system makes safety warnings more relevant to the actual situation of occupants. After an environmental risk is triggered, the system further assesses the occupants' own condition, improving the accuracy and necessity of the warning. Through the dual judgment of sitting posture and environmental risk, the system reduces the false alarm rate and enhances the effectiveness of occupant safety protection.

[0059] Optionally, the external information is acquired based on external vehicle sensing devices; The step of performing injury probability analysis on the occupant in the target seat inside the target vehicle based on the acquired road traffic environment information, exterior information, and interior information of the target vehicle, and obtaining the injury probability results includes: The road traffic environment information, the vehicle exterior information, and the vehicle interior information are input into a pre-trained occupant injury prediction model to determine the injury probability of each part of the occupant located on the target seat, which is then used as the injury probability result.

[0060] External information refers to real-time environmental data acquired by external sensors, including speed, acceleration, and the positions of other vehicles. Internal information refers to parameters related to occupant status acquired by internal sensors, including seat position parameters and occupant posture data. Occupant injury probability analysis represents the process of calculating the risk of injury to various parts of the occupant's body based on external and internal information using a seat parameter optimization model.

[0061] By dynamically linking seat position parameters with the collision environment, and assessing and predicting occupant injury in their current sitting posture based on real-world scenario data, this provides a quantitative basis for seat parameter optimization. Quantitative analysis enables scientific optimization of seat parameters; avoids the uncertainty caused by relying solely on experience-based adjustments; and makes damage assessments more closely aligned with actual collision scenarios, thereby improving the effectiveness of safety protection measures.

[0062] Optionally, such as Figure 4 As shown, the seat position parameters include the seat back angle, seat cushion angle, and footrest angle; When the damage probability result is greater than a first preset probability, adjusting the seat position parameters of the target seat until the damage probability result is less than a second preset probability includes: When the probability of damage to at least one part is greater than the first preset probability, at least one of the angles of the target seat back, the seat cushion, and the footrest is adjusted in a stepwise manner. After each adjustment, the probability of injury to each part of the occupant located on the target seat is re-determined by the occupant injury prediction model. The seat position parameters are iteratively adjusted based on the re-determined injury probabilities until the probability of injury to each part is less than the second preset probability, thereby obtaining the target parameters of the seat.

[0063] Step adjustment refers to making small, continuous adjustments to the seat position parameters according to a preset step size. These parameters include the seat back angle, seat cushion angle, and footrest angle, and directly affect the force distribution on the occupant during a collision. Step adjustment involves making small, continuous adjustments to the seat position parameters according to a preset step size, and recalculating the probability of injury after each adjustment.

[0064] In one embodiment, the seat back angle, seat cushion angle, and footrest angle have different iteration step sizes and iteration ranges. For example, the iteration step size for the seat back angle of a certain model is 10°, the iteration step size for the seat cushion angle is ±5°, and the iteration step size for the footrest angle is ±15°; the iteration range for the seat back angle is 20-70°, the iteration range for the seat cushion angle is 0-30°, and the iteration range for the footrest angle is 0-90°.

[0065] By continuously iterating and evaluating the probability of damage, the seat parameters are gradually optimized to a safe range, ensuring that the final seat position meets safety requirements. This avoids the discomfort caused by making large, one-time adjustments to the seat, making the adjustment process smoother and more natural; iterative evaluation ensures that the final seat parameters meet safety requirements; and adjustments are made based on quantitative indicators of the probability of damage, making seat optimization more reasonable.

[0066] Optionally, before inputting the road traffic environment information, the vehicle exterior information, and the vehicle interior information into a pre-trained occupant injury prediction model to determine the injury probability of each part of the occupant located on the target seat, and using this as the injury probability result, the method further includes: The first input data set that has been acquired and the actual damage probability of each part of the occupant corresponding to the first input data set are used as the first training samples. Each first input data set includes a set of external information samples, internal information samples and road traffic environment samples. The first machine learning model is trained using the first training sample until the first machine learning model meets the first preset convergence condition, thereby obtaining the occupant injury prediction model.

[0067] External information samples include environmental parameters such as collision type, collision speed, relative lateral displacement and angle; internal information samples include seat structure parameters such as backrest angle, seat cushion angle, and footrest angle; true damage probability represents the damage probability data of various parts of the occupant obtained from actual collision experiments or actual accident records, which serves as a reference standard for model training.

[0068] The first training sample consists of external information samples, internal information samples, and the true damage probability, forming the dataset required for model training. The first machine learning model refers to the initial prediction model, used to learn the relationship between external information, internal information, and damage probability. The first preset convergence criterion represents the evaluation standard for model training completion; for example, the first preset convergence criterion can be set as: the model prediction error is below a specific threshold or the accuracy reaches a specific requirement. The occupant damage prediction model represents the final model obtained through training, used to predict damage probability based on external and internal information. Building the prediction model using historical data improves the objectivity and reliability of damage probability prediction; avoids the limitations of relying solely on subjective experience for seat adjustments; and ensures the model meets requirements through preset training completion conditions.

[0069] In one embodiment, a backpropagation artificial neural network (BP-ANN) model is used as the first machine learning model to effectively process the nonlinear relationship between external information, internal information and damage probability. By learning patterns in historical data, accurate prediction of damage probability is achieved.

[0070] Optionally, such as Figure 5 As shown, determining the target constraint parameters of the occupant restraint system matching the target seat based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information includes: The occupant's vital signs in the target seat are obtained based on the in-vehicle information. The collision condition information is determined based on the road traffic environment information and the vehicle exterior information; The occupant vital signs, the target seat parameters, and the collision condition information are input into a pre-trained occupant constraint parameter optimization model to determine the target constraint parameters.

[0071] Occupant vital signs data obtained from inside the vehicle are acquired through in-vehicle information systems. This includes occupant vital signs percentiles, such as 5th percentile, 50th percentile, and 95th percentile. For example, based on millimeter-wave radar or 3D cameras installed inside the vehicle, a 3D model of the occupant is generated using millimeter-wave or 3D structured light technology. This 3D model is then compared with models stored in a database to determine the occupant's vital signs percentile.

[0072] In one embodiment, the target seat parameters represent the optimal seat position parameters obtained through seat parameter optimization, including one or more of the seat back angle, seat cushion tilt angle, and footrest angle. Collision condition information includes collision type, collision speed, relative lateral displacement, and angle, among other collision condition parameters. For example, by using an external sensor network and collecting data such as vehicle speed, steering angle, and braking status via the CAN bus, combined with GPS positioning information, the collision condition can be determined. When the vehicle suddenly brakes and steers, the CAN bus records data such as braking force, vehicle speed change, and steering angle; combined with GPS data, the collision type and collision speed can be determined. The vehicle's position and speed information can also be provided through the onboard GPS system; and the onboard DAQ system simultaneously collects data from multiple sensors such as radar, lidar, and cameras.

[0073] The target constraint parameters represent the occupant restraint system parameters determined to meet occupant safety requirements, including airbag ignition timing, seat belt pretensioning timing, seat belt force limiting value, and seat belt lap belt pretensioning timing.

[0074] The occupant constraint parameter optimization model represents a predictive model used to determine target constraint parameters. By learning patterns from historical data, it achieves accurate prediction of constraint parameters. It dynamically correlates individual occupant characteristics, seat status, and the collision environment, determining appropriate target constraint parameters based on comprehensive scenario data. This enables the constraint system parameters to adapt to different occupant characteristics and environmental conditions, avoiding inadequate protection due to changes in occupant posture.

[0075] Optionally, the collision condition information includes at least one of collision type, velocity, relative lateral displacement, and angle; And / or, the target constraint parameters include at least one of the following: airbag ignition time, seat belt pretensioning time, seat belt force limiting value, and seat belt lap belt pretensioning time.

[0076] Optionally, before inputting the occupant vital signs, the target seat parameters, and the collision condition information into a pre-trained occupant constraint parameter optimization model to determine the target constraint parameters, the method further includes: The acquired second input data set and the actual constraint parameters of the occupant restraint system corresponding to the second input data set are used as the second training samples. Each second input data set includes a set of occupant vital signs training data, seat parameter training data, and collision condition training data. Based on the second training sample, the second machine learning model is optimized and trained using a preset optimization algorithm until the second machine learning model meets the second preset convergence condition, thereby obtaining the occupant constraint parameter optimization model.

[0077] Occupant vital signs training data represents occupant vital signs parameter data used for model training; seat parameter training data represents seat parameter data used for model training; collision condition training data represents collision environment data used for model training.

[0078] The real constraint parameters represent the occupant restraint system parameters and seat parameters obtained from actual collision experiments or actual collision accidents; the real collision results refer to the occupant injury results obtained from actual collision experiments; the second training sample consists of occupant vital signs training data, seat parameter training data, collision condition training data, real constraint parameters, and real collision results, forming the dataset required for model training.

[0079] The second machine learning model represents the initial predictive model used to learn the relationship between occupant vital signs, seat parameters, collision conditions, and constraint parameters. The second preset convergence criterion represents the evaluation standard for the completion of model training, such as the model prediction error being lower than a specific threshold or the accuracy meeting a specific requirement.

[0080] The occupant constraint parameter optimization model represents the final model obtained through training, which is used to determine the appropriate target constraint parameters based on occupant vital signs, seat parameters, and collision conditions.

[0081] By building predictive models using historical data, the objectivity and reliability of constraint parameter determination are improved, avoiding the limitations of relying solely on subjective experience to set constraint parameters.

[0082] In one embodiment, the model is trained using a model adapted to complex data, such as a radial basis function model, a Kriging model, or a support vector machine model; and optimized using algorithms suitable for multi-parameter, global optimization, such as a multi-island genetic algorithm or a particle swarm optimization algorithm.

[0083] Optionally, such as Figure 5 As shown, the step of controlling the occupant restraint system to perform occupant restraint based on the target constraint parameters, and predicting the occupant injury probability based on the collision signal to obtain the predicted probability result includes: The occupant injury prediction model is used to predict the probability of occupant injury based on the collision signal and the collision condition information, and the predicted probability result is obtained. The occupant injury prediction model is trained from traffic accident data samples including data of the target vehicle.

[0084] A collision signal represents a signal generated by a vehicle during a collision, including signals such as changes in vehicle acceleration and pressure fluctuations. For example, the vehicle may generate acceleration in a direction other than the driving direction that exceeds a threshold and / or experience pressure that exceeds a threshold. In some embodiments, the collision signal may also be triggered by sensors such as radar or cameras installed in the vehicle, or by network signals.

[0085] Collision condition information indicates the environmental parameters at the time of the collision, including collision type, collision speed, relative lateral displacement and angle.

[0086] Occupant injury prediction models are predictive tools trained on traffic accident data, used to calculate the probability of occupant injury.

[0087] Traffic accident data samples represent collision scenarios and occupant injury records collected experimentally or in actual traffic accidents. Incorporating real-world accident data into the injury prediction process makes the prediction results more consistent with actual collision situations.

[0088] Improve prediction reliability by using experimental or accident data; avoid biases that may arise from relying solely on simulation data; make damage prediction results closer to the actual collision environment, and improve the targeting and timeliness of rescue response.

[0089] like Figure 6 As shown, an embodiment of the present invention provides an occupant protection system, including a signal layer, a model layer, a control layer, and an execution layer.

[0090] The signal layer is used to provide at least one of the following at different stages based on vehicle-road-cloud cooperation: road traffic environment information, external vehicle information, and internal vehicle information. These stages include the driving stage, collision avoidance stage, collision stage, and rescue stage.

[0091] The model layer is used to construct, based on artificial intelligence methods, a cloud-based driving monitoring model, a seat parameter optimization model, an occupant constraint parameter optimization model, and an occupant injury prediction model, according to the needs of different stages. The driving monitoring model is used to determine the existence of potential collision hazards based on acquired road traffic environment information; it is also used to perform occupant injury probability analysis based on acquired external and internal vehicle information when such potential collision hazards exist, obtaining injury probability results. The seat parameter optimization model is used to progressively adjust seat position parameters when the injury probability of at least one part is greater than a first preset probability, until the injury probability of each part is less than a second preset probability, obtaining target seat parameters, wherein the first preset probability is greater than or equal to the second preset probability. The occupant constraint parameter optimization model is used to determine target constraint parameters based on the internal vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information. The occupant injury prediction model is used to predict occupant injury probabilities based on the collision signal, obtaining prediction probability results.

[0092] The control layer is used to issue driving safety warning control, step-by-step seating position adjustment control, dynamic control of occupant restraint system parameters, and collaborative control commands for accident rescue based on model analysis results.

[0093] The execution layer is used to perform corresponding actions based on control instructions.

[0094] An embodiment of the present invention provides an occupant protection device, comprising: The driving safety warning control module is used to determine whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information; The seating posture adjustment control module is used to perform injury probability analysis on the occupant in the target seat of the target vehicle based on the acquired road traffic environment information, external information and internal information of the target vehicle when there is a potential collision hazard in the target vehicle, and obtain an injury probability result; it is also used to adjust the seat position parameters of the target seat when the injury probability result is greater than a first preset probability, until the injury probability result is less than a second preset probability, wherein the first preset probability is greater than or equal to the second preset probability; The occupant restraint system parameter dynamic control module is used to determine the target restraint parameters of the occupant restraint system that match the target seat based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external information; it is also used to control the occupant restraint system to perform occupant restraint based on the target restraint parameters in response to a collision signal, and to perform occupant injury probability prediction based on the collision signal to obtain the prediction probability result; The accident rescue collaborative control module is used to trigger an alarm rescue when the predicted probability result meets preset conditions.

[0095] like Figure 7 As shown, an embodiment of the present invention provides a vehicle 700, including the occupant protection method and occupant protection system described above.

[0096] Vehicle 700, which can serve as a server or client of the present invention, is described below as an example of a hardware device applicable to various aspects of the present invention. Vehicle 700 includes various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Vehicle 700 may also include various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0097] Vehicle 700 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM can also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0098] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the occupant protection method described above.

[0099] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units.

[0100] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for occupant protection, characterized in that, include: Based on the obtained road traffic environment information, determine whether the target vehicle poses a potential collision hazard; When the target vehicle has a potential collision hazard, the occupant in the target seat inside the target vehicle is subjected to injury probability analysis based on the obtained road traffic environment information, external information and internal information of the target vehicle, and the injury probability result is obtained. When the damage probability result is greater than the first preset probability, the seat position parameters of the target seat are adjusted until the damage probability result is less than the second preset probability, wherein the first preset probability is greater than or equal to the second preset probability.

2. The occupant protection method according to claim 1, characterized in that, The occupant protection method also includes: Obtain the seat position parameters of the target seat so that the damage probability result is less than the second preset probability; The target constraint parameters of the occupant restraint system that matches the target seat are determined based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information.

3. The occupant protection method according to claim 2, characterized in that, After determining the target constraint parameters of the occupant restraint system matching the target seat based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information, the method further includes: In response to a collision signal, the occupant restraint system is controlled to perform occupant restraint according to the target constraint parameters, and occupant injury probability is predicted based on the collision signal to obtain the prediction probability result; When the predicted probability result meets the preset conditions, an alarm and rescue are triggered.

4. The occupant protection method according to claim 1, characterized in that, The road traffic environment information includes at least one of road information, road condition information, or weather information; the step of determining whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information includes: Determine whether at least one of the road information, traffic condition information, or weather information is abnormal; If yes, then the target vehicle is determined to have a potential collision risk; if no, then the target vehicle is determined not to have a potential collision risk.

5. The occupant protection method according to any one of claims 1-4, characterized in that, The occupant protection method also includes: When the target vehicle presents a potential collision hazard, a driving warning is triggered; and / or, Based on the in-vehicle information, determine the occupant's sitting posture information in the target seat, and determine whether the occupant's sitting posture information meets the safe sitting posture conditions; when the occupant's sitting posture information does not meet the safe sitting posture conditions, trigger a safety warning.

6. The occupant protection method according to any one of claims 1-4, characterized in that, The external information is acquired based on external vehicle sensing devices; The step of performing injury probability analysis on the occupant in the target seat inside the target vehicle based on the acquired road traffic environment information, exterior information, and interior information of the target vehicle, and obtaining the injury probability results includes: The road traffic environment information, the vehicle exterior information, and the vehicle interior information are input into a pre-trained occupant injury prediction model to determine the injury probability of each part of the occupant located on the target seat, which is then used as the injury probability result.

7. The occupant protection method according to claim 6, characterized in that, The seat position parameters include the seat back angle, seat cushion angle, and footrest angle; When the damage probability result is greater than a first preset probability, adjusting the seat position parameters of the target seat until the damage probability result is less than a second preset probability includes: When the probability of damage to at least one part is greater than the first preset probability, at least one of the angles of the target seat back, the seat cushion, and the footrest is adjusted in a stepwise manner. After each adjustment, the probability of injury to each part of the occupant located on the target seat is re-determined by the occupant injury prediction model. The seat position parameters are iteratively adjusted based on the re-determined injury probabilities until the probability of injury to each part is less than the second preset probability, thereby obtaining the target parameters of the seat.

8. The occupant protection method according to claim 6, characterized in that, Before inputting the road traffic environment information, the vehicle exterior information, and the vehicle interior information into a pre-trained occupant injury prediction model to determine the injury probability of various parts of the occupant located on the target seat, and using this as the injury probability result, the method further includes: The first input data set that has been acquired and the actual damage probability of each part of the occupant corresponding to the first input data set are used as the first training samples. Each first input data set includes a set of external information samples, internal information samples and road traffic environment samples. The first machine learning model is trained using the first training sample until the first machine learning model meets the first preset convergence condition, thereby obtaining the occupant injury prediction model.

9. The occupant protection method according to claim 3, characterized in that, The step of determining the target constraint parameters of the occupant restraint system that matches the target seat based on the in-vehicle information, the target seat parameters, the road traffic environment information, and the external vehicle information includes: The occupant's vital signs in the target seat are obtained based on the in-vehicle information. The collision condition information is determined based on the road traffic environment information and the vehicle exterior information; The occupant vital signs, the target seat parameters, and the collision condition information are input into a pre-trained occupant constraint parameter optimization model to determine the target constraint parameters.

10. The occupant protection method according to claim 9, characterized in that, The collision condition information includes at least one of the following: collision type, velocity, relative lateral displacement, and angle. And / or, the target constraint parameters include at least one of the following: airbag ignition time, seat belt pretensioning time, seat belt force limiting value, and seat belt lap belt pretensioning time.

11. The occupant protection method according to claim 9, characterized in that, Before inputting the occupant vital signs, the target seat parameters, and the collision condition information into a pre-trained occupant constraint parameter optimization model to determine the target constraint parameters, the process further includes: The acquired second input data set and the actual constraint parameters of the occupant restraint system corresponding to the second input data set are used as the second training samples. Each second input data set includes a set of occupant vital signs training data, seat parameter training data, and collision condition training data. Based on the second training sample, the second machine learning model is optimized and trained using a preset optimization algorithm until the second machine learning model meets the second preset convergence condition, thereby obtaining the occupant constraint parameter optimization model.

12. The occupant protection method according to claim 9, characterized in that, The step of controlling the occupant restraint system to perform occupant restraint based on the target constraint parameters, and predicting the occupant injury probability based on the collision signal to obtain the prediction probability result includes: The occupant injury prediction model is used to predict the probability of occupant injury based on the collision signal and the collision condition information, and the predicted probability result is obtained. The occupant injury prediction model is trained from traffic accident data samples including data of the target vehicle.

13. An occupant protection device, characterized in that, include: The driving safety warning control module is used to determine whether the target vehicle has a potential collision hazard based on the acquired road traffic environment information; The seating posture adjustment control module is used to perform injury probability analysis on the occupant in the target seat inside the target vehicle based on the acquired road traffic environment information, external information and internal information of the target vehicle when there is a potential collision hazard in the target vehicle, and obtain an injury probability result; it is also used to adjust the seat position parameters of the target seat when the injury probability result is greater than a first preset probability, until the injury probability result is less than a second preset probability, wherein the first preset probability is greater than or equal to the second preset probability.

14. A vehicle, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to implement the occupant protection method as described in any one of claims 1-12 when executing the computer program.

15. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the occupant protection method as described in any one of claims 1-12.

Images