Airbag preparation method, system and terminal combining feature fusion and relative weight

Abstract

The invention relates to the technical field of vehicle safety, and provides a feature fusion and relative weight combined airbag preparation method and system and a terminal. The risk occurrence probability of each risk assessment factor is obtained by assessing the probability that the vehicle terminal has the risk event, feature fusion is performed according to the relative risk probability between the risk occurrence probabilities to obtain the first risk probability, and the risk relative weight is determined according to the relative importance between the risk assessment factors. The risk occurrence probability is subjected to weighted calculation according to the risk relative weight to obtain the second risk probability, so that whether the airbag controller enters the preparation state or not is judged in combination with the first risk probability and the second risk probability, the risk assessment robustness is improved, the weight is determined through the relative importance among the risk assessment factors, and the risk assessment accuracy is improved. Therefore, the relative weight can truly and accurately reflect the actual influence of each factor in a specific scene, so that the reliability of decision making when the airbag controller enters the pre-preparation state is improved.

Description

Airbag pre-preparation method, system and terminal combining feature fusion and relative weighting Technical Field

[0001] This application relates to the field of vehicle safety technology, specifically to an airbag pre-preparation method, system, and terminal that combines feature fusion and relative weighting. Background Technology

[0002] Currently, as automotive electronic and electrical architectures gradually evolve towards a combination of central computing and regional control, the functions of traditionally distributed ECUs (Electronic Control Units) have been significantly simplified and integrated. The computing power requirements, functional integration, and software complexity of regional controllers have increased significantly. The automotive industry has placed higher demands on the response speed and reliability of vehicle safety functions, especially safety measures such as door lock unlocking and airbag deployment. The airbag deployment process involves a dynamic judgment chain, including collision occurrence, sensor signal acquisition, ABM (Airbag Module) threshold calculation, determination of whether to deploy, and execution of deployment. To shorten the deployment time, existing technologies use the collected vehicle signals as risk assessment factors to assess the driving scenario. By predicting the potential collision probability, the airbag controller is activated in advance and pre-preparation actions are performed, thereby transforming the traditional dynamic judgment into a static preparation process before a collision and shortening the airbag deployment time.

[0003] However, due to the simplistic risk assessment strategy, it is difficult to accurately quantify the probability of collision risks. When faced with complex and ever-changing real-world driving environments, the robustness and accuracy of its assessment results are insufficient, resulting in low reliability of the entire airbag pre-preparation process and failing to meet the stringent safety performance standards of the automotive industry. Summary of the Invention

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0005] In view of the shortcomings of the prior art described above, this application provides an airbag pre-preparation method, system and terminal that combines feature fusion and relative weighting to improve the accuracy of risk assessment results.

[0006] This application provides an airbag pre-preparation method combining feature fusion and relative weighting, comprising: acquiring multiple risk assessment factors; assessing the probability of a risk event occurring in a vehicle terminal according to each of the risk assessment factors to obtain the risk occurrence probability corresponding to each of the risk assessment factors, and performing feature fusion based on the relative risk probabilities between the risk occurrence probabilities to obtain a first risk probability; assessing the importance of each of the risk assessment factors, and determining the relative risk weight corresponding to each of the risk assessment factors based on the relative importance between the importance levels, and performing a weighted calculation on each of the risk occurrence probabilities based on the relative risk weights to obtain a second risk probability; combining the first risk probability and the second risk probability to calculate a comprehensive risk probability, and if the comprehensive risk probability is greater than a preset risk probability threshold, controlling the airbag controller of the vehicle terminal to enter a pre-preparation state.

[0007] In one embodiment of this application, risk assessment is performed according to each of the risk assessment factors to obtain the probability of risk occurrence corresponding to each of the risk assessment factors, including: collecting data from the vehicle terminal to obtain risk-related signals corresponding to each of the risk assessment factors; assessing the probability of a risk event occurring at the vehicle terminal according to each of the risk-related signals to obtain a risk assessment vector, wherein the risk assessment vector includes the risk assessment value corresponding to each of the risk assessment factors.

[0008] In one embodiment of this application, feature fusion is performed based on the relative risk probabilities between the risk occurrence probabilities to obtain a first risk probability, including: using each of the risk assessment factors as the row index and column index of a first judgment matrix, and filling the first judgment matrix with the ratio between the risk occurrence probabilities as the relative risk probability; performing feature fusion on the first judgment matrix at least once based on a preset feature fusion step to obtain a fusion matrix, wherein the feature fusion step includes downsampling and convolution operations; calculating the fusion matrix using the geometric mean method to obtain a matrix quantization value, and mapping the matrix quantization value to a preset quantization value range to obtain the first risk probability.

[0009] In one embodiment of this application, the first judgment matrix is ​​subjected to feature fusion at least once based on a preset feature fusion step to obtain a fusion matrix, including: using the first judgment matrix as the matrix to be fused; responding to the current matrix, downsampling the current matrix through a preset pooling layer to obtain an intermediate matrix; performing a convolution operation on the current matrix and the intermediate matrix to obtain a target matrix; if the matrix dimension of the target matrix meets a preset matrix dimension threshold, then the target matrix is ​​used as the fusion matrix; if the matrix dimension of the target matrix does not meet the matrix dimension threshold, then the target matrix is ​​used as a new current matrix.

[0010] In one embodiment of this application, assessing the importance of each risk assessment factor includes: acquiring a vehicle event set, wherein the vehicle event set includes multiple vehicle historical events, and the vehicle historical events include historical vehicle signals of each risk assessment factor; extracting multiple time-series data segments from the vehicle historical events and labeling each vehicle historical event with a risk tag, wherein the risk tag is used to characterize whether the vehicle historical event belongs to a preset risk event type; inputting each of the time-series data segments into a time-series model with an attention mechanism, and determining the attention score corresponding to each risk assessment factor based on the attention weight distribution output by the time-series model, wherein the time-series model is obtained by training a preset artificial intelligence model; and determining the factor importance corresponding to each of the risk assessment factors based on each attention score.

[0011] In one embodiment of this application, determining the relative risk weights corresponding to each of the risk assessment factors based on the relative importance among the importance levels includes: using each risk assessment factor as the row index and column index of a second judgment matrix, and filling the second judgment matrix with the ratio between the importance levels of the factors as the relative importance; calculating the largest eigenvalue corresponding to the second judgment matrix to obtain a second eigenvalue, and calculating the eigenvector corresponding to the second eigenvalue to obtain a second eigenvector; normalizing the second eigenvector to obtain a relative weight vector, wherein the relative weight vector includes the relative risk weights corresponding to each risk assessment factor.

[0012] In one embodiment of this application, a comprehensive risk probability is obtained by combining the first risk probability and the second risk probability, including: obtaining the probability weights corresponding to the first risk probability and the second risk probability respectively; and performing a weighted calculation on the first risk probability and the second risk probability according to the probability weights to obtain the comprehensive risk probability.

[0013] In one embodiment of this application, controlling the airbag controller of the vehicle terminal to enter a pre-ready state includes at least one of the following: controlling the airbag controller to switch from a dormant state to an active state; controlling the power supply voltage of the airbag power supply circuit according to a preset airbag deployment voltage through the airbag controller, wherein the airbag power supply circuit is used to supply power to the airbag of the vehicle terminal; charging the capacitor of the airbag igniter through the airbag controller, wherein the airbag igniter is used to trigger the gas generator to inflate the airbag; and reallocating the computing resources of the airbag controller.

[0014] This application also provides an airbag pre-preparation system combining feature fusion and relative weighting, comprising: an acquisition module for acquiring multiple risk assessment factors; a fusion module for assessing the probability of a risk event occurring in a vehicle terminal based on each of the risk assessment factors, obtaining the risk occurrence probability corresponding to each of the risk assessment factors, and performing feature fusion based on the relative risk probabilities between the risk occurrence probabilities to obtain a first risk probability; a calculation module for assessing the importance of each of the risk assessment factors, determining the relative risk weight corresponding to each of the risk assessment factors based on the relative importance between the importance levels, and performing a weighted calculation on each of the risk occurrence probabilities based on the relative risk weights to obtain a second risk probability; and a control module for calculating a comprehensive risk probability by combining the first risk probability and the second risk probability, and, if the comprehensive risk probability is greater than a preset risk probability threshold, controlling the airbag controller of the vehicle terminal to enter a pre-preparation state.

[0015] This application also provides a vehicle terminal, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the vehicle terminal to perform the method described above.

[0016] The beneficial effects of this application are as follows: By assessing the probability of a risk event occurring at the vehicle terminal, the probability of risk occurrence corresponding to each risk assessment factor is obtained. Feature fusion is performed based on the relative risk probabilities among the risk occurrence probabilities to obtain a first risk probability. Then, relative risk weights are determined based on the relative importance among the risk assessment factors. A second risk probability is obtained by weighting the risk occurrence probabilities according to the relative risk weights. The first and second risk probabilities are then combined to determine whether the airbag controller enters a pre-preparation state. This not only significantly improves the robustness of risk assessment by combining different risk assessment algorithms to determine risk probabilities, but also effectively establishes the correlation between risk factors by analyzing their relative importance, compared to independently assigning weights to each risk factor. This allows the assigned weights to more realistically and accurately reflect the actual influence of each factor in a specific scenario, thereby more accurately determining the vehicle's collision probability and improving the reliability of the airbag controller's decision to enter a pre-preparation state. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] In the accompanying drawings: Figure 1 is a flowchart illustrating an airbag pre-preparation method combining feature fusion and relative weighting according to an embodiment of this application; Figure 2 is a structural diagram illustrating a hierarchical model based on risk assessment factors according to an embodiment of this application; Figure 3 is a schematic diagram illustrating the installation location of an airbag controller in a vehicle terminal according to an embodiment of this application; Figure 4 is a structural diagram illustrating a control system for an airbag controller according to an embodiment of this application; Figure 5 is a flowchart illustrating another airbag pre-preparation method combining feature fusion and relative weighting according to an embodiment of this application; Figure 6 is a structural diagram illustrating an airbag pre-preparation system combining feature fusion and relative weighting according to an embodiment of this application; Figure 7 is a structural diagram illustrating a vehicle terminal according to an embodiment of this application. Detailed Implementation

[0019] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0022] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0023] Unless otherwise stated, the term "multiple" means two or more.

[0024] In this application, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0025] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0026] Referring to Figure 1, this application provides an airbag pre-preparation method combining feature fusion and relative weighting, including: step S101, obtaining multiple risk assessment factors; step S102, assessing the probability of a risk event occurring in the vehicle terminal according to each risk assessment factor, obtaining the risk occurrence probability corresponding to each risk assessment factor, and performing feature fusion based on the relative risk probabilities between the risk occurrence probabilities to obtain a first risk probability; step S103, assessing the importance of each risk assessment factor, and determining the relative risk weight corresponding to each risk assessment factor based on the relative importance between the importance levels, and performing a weighted calculation on each risk occurrence probability based on the relative risk weights to obtain a second risk probability; step S104, calculating a comprehensive risk probability by combining the first risk probability and the second risk probability, and if the comprehensive risk probability is greater than a preset risk probability threshold, controlling the airbag controller of the vehicle terminal to enter a pre-preparation state.

[0027] The airbag pre-preparation method combined with feature fusion and relative weighting provided in this application assesses the probability of a risk event occurring in the vehicle terminal, obtaining the risk occurrence probability corresponding to each risk assessment factor. Feature fusion is performed based on the relative risk probabilities to obtain a first risk probability. Relative risk weights are determined based on the relative importance of the risk assessment factors. A second risk probability is obtained by weighting the risk occurrence probabilities according to these relative risk weights. The first and second risk probabilities are then combined to determine whether the airbag controller enters a pre-preparation state. This approach not only significantly improves the robustness of risk assessment by combining different risk assessment algorithms to determine risk probabilities, but also effectively establishes the correlation between risk factors by analyzing their relative importance, compared to independently assigning weights to each risk factor. This allows the assigned weights to more realistically and accurately reflect the actual influence of each factor in a specific scenario, thereby more accurately determining the vehicle's collision probability and improving the reliability of the airbag controller's decision to enter the pre-preparation state.

[0028] Optionally, risk assessment is performed separately for each risk assessment factor to obtain the probability of risk occurrence corresponding to each risk assessment factor, including: obtaining risk-related signals corresponding to each risk assessment factor by collecting data from the vehicle terminal; assessing the probability of risk events occurring at the vehicle terminal based on each risk-related signal to obtain a risk assessment vector, wherein the risk assessment vector includes the risk assessment value corresponding to each risk assessment factor.

[0029] Referring to Figure 2, an embodiment of this application presents a hierarchical model based on risk assessment factors. The risk dimensions include one or more of the following: user state dimension, vehicle state dimension, and environmental perception dimension. The risk assessment factors corresponding to the user state dimension include one or more of the following: in-vehicle environment perception, driving behavior perception, and user fatigue detection. The risk assessment factors corresponding to the vehicle state dimension include one or more of the following: driving speed, accelerator pedal travel, brake pedal travel, time-to-collision (TTC), and expected collision angle. The risk assessment factors corresponding to the environmental perception dimension include one or more of the following: road surface perception, weather perception, user blind spot perception, and driving direction perception.

[0030] In some embodiments, a safe threshold range and a dangerous threshold range are determined based on a preset vehicle signal threshold. If a risk-related signal is located in the safe threshold range, the risk assessment value corresponding to the risk-related signal is 0. If a risk-related signal is located in the dangerous threshold range, the signal deviation value of the risk-related signal relative to the vehicle signal threshold is calculated, and the risk assessment value of the risk assessment factor corresponding to the risk-related signal is obtained by matching the signal deviation value.

[0031] In some embodiments, a training sample set is constructed based on a vehicle event set; a preset neural network model is trained using the training sample set to obtain a risk assessment model; and the risk assessment model is used to assess the risk-related signals corresponding to each risk assessment factor to obtain the risk assessment value corresponding to each risk assessment factor.

[0032] Optionally, feature fusion is performed based on the relative risk probabilities between the probabilities of risk occurrence to obtain a first risk probability, including: using each risk assessment factor as the row index and column index of the first judgment matrix, and using the ratio between the probabilities of risk occurrence as the relative risk probability, and filling it into the first judgment matrix; performing feature fusion on the first judgment matrix at least once based on a preset feature fusion step to obtain a fusion matrix, wherein the feature fusion step includes downsampling and convolution operations; calculating the fusion matrix using the geometric mean method to obtain a matrix quantization value, and mapping the matrix quantization value to a preset quantization value range to obtain the first risk probability.

[0033] In some embodiments, the first The risk assessment factor is relative to the first one. The relative risk probability of each risk assessment factor is expressed as: ,in, For the first The probability of occurrence of each risk assessment factor For the first The probability of occurrence of each risk assessment factor.

[0034] In some embodiments, at least a portion of the first judgment matrix corresponding to the relative risk probability is shown in Table 1.

[0035] Table 1

[0036] Optionally, the first judgment matrix is ​​subjected to feature fusion at least once based on a preset feature fusion step to obtain a fusion matrix, including: using the first judgment matrix as the matrix to be fused; responding to the current matrix, downsampling the current matrix through a preset pooling layer to obtain an intermediate matrix; performing convolution operation on the current matrix and the intermediate matrix to obtain a target matrix; if the matrix dimension of the target matrix meets a preset matrix dimension threshold, then the target matrix is ​​used as the fusion matrix; if the matrix dimension of the target matrix does not meet the matrix dimension threshold, then the target matrix is ​​used as the new current matrix.

[0037] In some embodiments, the matrix dimension threshold is 2×2.

[0038] In some embodiments, a first judgment matrix with a matrix dimension of 8×8 is used as the current matrix T1. The current matrix T1 is downsampled through a pooling layer to obtain an intermediate matrix T2 with a matrix dimension of 4×4. A convolution is then performed between the current matrix T1 and the intermediate matrix T2 to obtain a target matrix T3 with a matrix dimension of 4×4. The target matrix T3 is then used as the new current matrix. The current matrix T3 is downsampled through a pooling layer to obtain an intermediate matrix T4 with a matrix dimension of 2×2. A convolution is then performed between the current matrix T3 and the intermediate matrix T4 to obtain a target matrix T5 with a matrix dimension of 2×2. The target matrix T5 is then used as the fusion matrix, and the geometric mean method is used to calculate the matrix quantization value corresponding to the fusion matrix T5. Quantize the matrix values Mapped to and The first risk probability is obtained by quantifying the range between these values.

[0039] In some embodiments, average pooling is used to downsample the current matrix to achieve matrix dimensionality reduction and feature selection, retaining the correlation features between relative probabilities and avoiding the loss of key features due to max pooling.

[0040] In some embodiments, a valid convolution operation is performed on the current matrix and the intermediate matrix to capture the deep correlation between matrix elements and achieve feature correlation extraction.

[0041] In some embodiments, if the fusion matrix T5=[[ , ],[ , Then, the geometric mean method is used to calculate the fusion matrix T5, ​​and the matrix quantization value corresponding to the fusion matrix T5 is obtained. , where matrix quantization value This represents the intensity value of the relative risk probability; through vehicle collision experiments, the minimum value of the matrix quantization value in a no-collision-risk scenario is set. And the maximum value of the matrix quantization value in a collision-free risk scenario. A linear normalization algorithm is used to quantize the matrix values. Mapped to and The first risk probability is obtained by quantifying the range between these values, where the first risk probability = .

[0042] Optionally, assessing the importance of each risk assessment factor includes: acquiring a vehicle event set, wherein the vehicle event set includes multiple historical vehicle events, and the historical vehicle events include historical vehicle signals for each risk assessment factor; extracting multiple time-series data segments from the historical vehicle events and labeling each historical vehicle event with a risk tag, wherein the risk tag is used to characterize whether the historical vehicle event belongs to a preset risk event type; inputting each time-series data segment into a time-series model with an attention mechanism, and determining the attention score corresponding to each risk assessment factor based on the attention weight distribution output by the time-series model, wherein the time-series model is obtained by training a preset artificial intelligence model; and determining the factor importance corresponding to each risk assessment factor based on each attention score.

[0043] In some embodiments, vehicle history events record historical vehicle signals for multiple risk assessment factors, including collision time, vehicle speed, fatigue monitoring, road friction, etc. Each vehicle history event is risk-labeled: if the event ultimately leads to a collision, or triggers the vehicle's emergency braking mechanism, the risk label is set to 1, indicating that the event is a risk event; otherwise, the risk label is set to 0. An AI model based on the Transformer architecture is used for training. The time-series data segments obtained in the previous step are used as input, and their corresponding risk level labels are used as the model's prediction targets, resulting in a time-series model with an attention mechanism. This model can output corresponding risk labels based on new time-series data segments. Furthermore, the attention mechanism of the time-series model reveals which risk assessment factors the model "pays more attention to" when making classification decisions. The attention score for each risk assessment factor is determined, and the attention scores are normalized to obtain the factor importance corresponding to each risk assessment factor.

[0044] Optionally, based on the relative importance among the factors of importance, the relative risk weights corresponding to each risk assessment factor are determined, including: using each risk assessment factor as the row index and column index of the second judgment matrix, and using the ratio between the factors of importance as the relative importance, and filling it into the second judgment matrix; calculating the largest eigenvalue corresponding to the second judgment matrix to obtain the second eigenvalue, and calculating the eigenvector corresponding to the second eigenvalue to obtain the second eigenvector; normalizing the second eigenvector to obtain the relative weight vector, wherein the relative weight vector includes the relative risk weights corresponding to each risk assessment factor.

[0045] In some embodiments, the first The risk assessment factor is relative to the first one. The relative importance of each risk assessment factor is expressed as follows: ,in, For the first Factor importance of each risk assessment factor. For the first The factor importance of each risk assessment factor is calculated based on the relative importance between each risk factor, and a portion of the judgment matrix is ​​shown in Table 2.

[0046] Table 2

[0047] In some embodiments, the first verification rule is expressed as .

[0048] In some embodiments, the second verification rule is expressed as

[0049] In some embodiments, the third verification rule is expressed as [ , , , , , , , ]= [ , , , , , , , ].

[0050] In some embodiments, the relative weight vector corresponding to the second judgment matrix is ​​calculated using the AHP (Analytic Hierarchy Process) algorithm, wherein the AHP algorithm includes the eigenvalue method and the approximation algorithm.

[0051] In some embodiments, the eigenvalue method includes calculating a second judgment matrix. The largest eigenvalue According to the second judgment matrix and the largest eigenvalue Solve the second judgment matrix The eigenvectors are then normalized so that the sum of all elements is 1. The resulting column vector is the relative weight vector. .

[0052] In some embodiments, the relative weight vector is normalized. The sum of the vector elements in the vector is set to 100%, where the relative weight vector... It reflects the relative importance of each risk assessment factor and is a micro-representation of weights based on the AHP algorithm.

[0053] In some embodiments, the approximation algorithm includes: normalizing each column of the second judgment matrix, summing the normalized matrix by row, and normalizing the vector obtained after summing again to obtain an approximate value of the relative weight vector.

[0054] Optionally, the comprehensive risk probability is calculated by combining the first risk probability and the second risk probability, including: obtaining the probability weights corresponding to the first risk probability and the second risk probability respectively; and performing a weighted calculation on the first risk probability and the second risk probability according to the probability weights to obtain the comprehensive risk probability.

[0055] In some embodiments, the overall risk probability ,in, The probability weight for the first risk probability. The first risk probability, The probability weight for the second risk probability. This represents the second risk probability.

[0056] Optionally, controlling the airbag controller of the vehicle terminal to enter a pre-ready state includes at least one of the following: controlling the airbag controller to switch from a dormant state to an active state; controlling the power supply voltage of the airbag power supply circuit according to a preset airbag detonation voltage via the airbag controller, wherein the airbag power supply circuit is used to supply power to the airbag of the vehicle terminal; charging the capacitor of the airbag igniter via the airbag controller, wherein the airbag igniter is used to trigger the gas generator to inflate the airbag; and reallocating the computing resources of the airbag controller.

[0057] In some embodiments, the airbag controller is positioned at the vehicle terminal as shown in Figure 3. As the core of the airbag control system, the airbag controller is in a low-power standby mode under normal conditions to reduce the energy consumption of the entire vehicle. When a collision signal is received, the airbag power supply circuit is activated, and the capacitor of the airbag igniter is charged through high voltage triggering, so that the airbag igniter triggers the gas generator to inflate the airbag. Based on this, this application adds a risk assessment strategy, so that the airbag controller is prepared in advance when a collision risk may occur, thereby reducing the time required to trigger the airbag.

[0058] Referring to Figure 4, this application provides a control system for an airbag controller, including an airbag controller, an airbag, a vehicle power supply, a risk assessment module, a collision sensor, and an electronic control unit (ECU).

[0059] The airbag controller includes a microcontroller unit (MCU) and a backup power supply.

[0060] The microcontroller unit is used to receive the pre-preparation signal sent by the risk assessment module, perform pre-preparation actions related to the airbag, and receive the vehicle collision signal sent by the collision sensor to issue the deployment command to the airbag.

[0061] Backup power supply, used to supply power to the airbag controller when the vehicle's power supply fails.

[0062] Airbags, including front airbags and side airbags, are used to rapidly inflate via a gas generator to protect passengers inside the vehicle.

[0063] Vehicle power supply, used to power the airbag controller.

[0064] The risk assessment module is used to wake up the airbag controller and send a pre-preparation command to the airbag controller if the overall risk probability is greater than the preset risk probability threshold.

[0065] Collision sensors are used to send vehicle collision signals to the airbag controller.

[0066] The electronic control unit (ECU) is connected to the airbag controller via a CAN bus. The ECU is used to send vehicle status information (such as vehicle speed, steering wheel angle, braking status, etc.) as an auxiliary basis for the airbag controller to make collision judgments.

[0067] Referring to Figure 5, this application provides an airbag pre-preparation method combining feature fusion and relative weighting, including: step S501, obtaining multiple risk assessment factors; step S502, assessing the probability of a risk event occurring in the vehicle terminal according to each risk assessment factor, obtaining the risk occurrence probability corresponding to each risk assessment factor, and proceeding to steps S503 and S504; step S503, performing feature fusion based on the relative risk probabilities between risk occurrence probabilities to obtain a first risk probability, and proceeding to step S507; step S504, assessing the importance of each risk assessment factor; step... Step S505: Determine the relative risk weights for each risk assessment factor based on their relative importance. Step S506: Calculate the probability of occurrence of each risk based on its relative risk weight to obtain the second risk probability, then proceed to step S507. Step S507: Calculate the comprehensive risk probability by combining the first and second risk probabilities. Step S508: Determine whether the comprehensive risk probability is greater than the risk probability threshold. If yes, proceed to step S509; otherwise, proceed to step S502. Step S509: Control the airbag controller of the vehicle terminal to enter the pre-ready state.

[0068] The airbag pre-preparation method combined with feature fusion and relative weighting provided in this application assesses the probability of a risk event occurring in the vehicle terminal, obtaining the risk occurrence probability corresponding to each risk assessment factor. Feature fusion is performed based on the relative risk probabilities to obtain a first risk probability. Relative risk weights are determined based on the relative importance of the risk assessment factors. A second risk probability is obtained by weighting the risk occurrence probabilities according to these relative risk weights. The first and second risk probabilities are then combined to determine whether the airbag controller enters a pre-preparation state. This approach not only significantly improves the robustness of risk assessment by combining different risk assessment algorithms to determine risk probabilities, but also effectively establishes the correlation between risk factors by analyzing their relative importance, compared to independently assigning weights to each risk factor. This allows the assigned weights to more realistically and accurately reflect the actual influence of each factor in a specific scenario, thereby more accurately determining the vehicle's collision probability and improving the reliability of the airbag controller's decision to enter the pre-preparation state.

[0069] Referring to Figure 6, this application provides an airbag pre-preparation system that combines feature fusion and relative weighting, including an acquisition module 601, a fusion module 602, a calculation module 603, and a control module 604.

[0070] The acquisition module 601 is used to acquire multiple risk assessment factors.

[0071] The fusion module 602 is used to assess the probability of a risk event occurring at the vehicle terminal according to each risk assessment factor, obtain the probability of risk occurrence corresponding to each risk assessment factor, and perform feature fusion based on the relative risk probabilities between the risk occurrence probabilities to obtain the first risk probability.

[0072] The calculation module 603 is used to assess the importance of each risk assessment factor and determine the relative risk weight of each risk assessment factor based on the relative importance between the factors. The probability of occurrence of each risk is then calculated by weighting the relative risk weights to obtain the second risk probability.

[0073] The control module 604 is used to calculate the comprehensive risk probability by combining the first risk probability and the second risk probability. If the comprehensive risk probability is greater than the preset risk probability threshold, the airbag controller of the vehicle terminal is controlled to enter the pre-ready state.

[0074] The airbag pre-preparation system provided in this application, which combines feature fusion and relative weighting, assesses the probability of a risk event occurring in the vehicle terminal to obtain the probability of risk occurrence corresponding to each risk assessment factor. Feature fusion is performed based on the relative risk probabilities to obtain a first risk probability. Relative risk weights are determined based on the relative importance of the risk assessment factors. A second risk probability is obtained by weighting the risk occurrence probabilities according to these relative risk weights. The first and second risk probabilities are then combined to determine whether the airbag controller enters a pre-preparation state. This approach not only significantly improves the robustness of risk assessment by combining different risk assessment algorithms to determine risk probabilities, but also effectively establishes the correlation between risk factors by analyzing their relative importance, compared to independently assigning weights to each risk factor. This allows the assigned weights to more realistically and accurately reflect the actual influence of each factor in a specific scenario, thereby more accurately determining the vehicle's collision probability and improving the reliability of the airbag controller's decision to enter the pre-preparation state.

[0075] This application also provides a vehicle terminal, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the vehicle terminal performs the above-described method.

[0076] Figure 7 shows a schematic diagram of a computer system suitable for implementing the embodiments of this application. It should be noted that the computer system 700 of the vehicle terminal shown in Figure 7 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0077] As shown in Figure 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 702 or programs loaded from storage portion 708 into Random Access Memory (RAM) 703. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0078] The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 710 as needed so that computer programs read from it can be installed into storage section 708 as needed.

[0079] The vehicle terminal disclosed in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and communication interface are connected to the processor and transceiver and complete communication between them. The memory is used to store computer programs, the communication interface is used for communication, and the processor and transceiver are used to run the computer programs, enabling the vehicle terminal to perform the various steps of the above method. The above description and drawings fully illustrate the embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Unless explicitly required, individual components and functions are optional, and the order of operation may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the terminology used in this application is only for describing embodiments and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated subsamples, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other subsamples, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes the element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0080] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0081] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some sub-samples may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and 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 implement this embodiment according to actual needs. Furthermore, the functional units in this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of the systems, methods, and computer program products according to this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than those disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for airbag pre-preparation combining feature fusion and relative weighting, characterized in that, include: Obtain multiple risk assessment factors; The probability of a risk event occurring at the vehicle terminal is assessed based on each of the aforementioned risk assessment factors to obtain the probability of risk occurrence corresponding to each of the aforementioned risk assessment factors. The first risk probability is obtained by feature fusion based on the relative risk probabilities among the risk occurrence probabilities. Assess the importance of each of the aforementioned risk assessment factors, and determine the relative risk weight of each of the aforementioned risk assessment factors based on the relative importance among the aforementioned factors. Then, calculate the probability of occurrence of each of the aforementioned risks by weighting the relative risk weights to obtain the second risk probability. The comprehensive risk probability is calculated by combining the first risk probability and the second risk probability. If the comprehensive risk probability is greater than a preset risk probability threshold, the airbag controller of the vehicle terminal is controlled to enter a pre-ready state.

2. The method according to claim 1, characterized in that, Risk assessment is performed based on each of the aforementioned risk assessment factors to obtain the probability of risk occurrence corresponding to each of the aforementioned risk assessment factors. This includes: collecting data from the vehicle terminal to obtain risk-related signals corresponding to each of the aforementioned risk assessment factors; assessing the probability of a risk event occurring at the vehicle terminal based on each of the aforementioned risk-related signals to obtain a risk assessment vector, wherein the risk assessment vector includes the risk assessment value corresponding to each of the aforementioned risk assessment factors.

3. The method according to claim 1, characterized in that, The first risk probability is obtained by feature fusion based on the relative risk probabilities between the risk occurrence probabilities, including: using each of the risk assessment factors as the row index and column index of the first judgment matrix, and filling the first judgment matrix with the ratio between the risk occurrence probabilities as the relative risk probability; performing feature fusion on the first judgment matrix at least once based on a preset feature fusion step to obtain a fusion matrix, wherein the feature fusion step includes downsampling and convolution operations; calculating the fusion matrix using the geometric mean method to obtain a matrix quantization value, and mapping the matrix quantization value to a preset quantization value range to obtain the first risk probability.

4. The method according to claim 3, characterized in that, The first judgment matrix is ​​fused at least once based on a preset feature fusion step to obtain a fused matrix, including: using the first judgment matrix as the matrix to be fused; responding to the current matrix, downsampling the current matrix through a preset pooling layer to obtain an intermediate matrix; performing a convolution operation on the current matrix and the intermediate matrix to obtain a target matrix; if the matrix dimension of the target matrix meets a preset matrix dimension threshold, then the target matrix is ​​used as the fused matrix; if the matrix dimension of the target matrix does not meet the matrix dimension threshold, then the target matrix is ​​used as the new current matrix.

5. The method according to claim 1, characterized in that, Assessing the importance of each risk assessment factor includes: acquiring a vehicle event set, wherein the vehicle event set includes multiple historical vehicle events, and the historical vehicle events include historical vehicle signals for each risk assessment factor; extracting multiple time-series data segments from the historical vehicle events and labeling each historical vehicle event with a risk tag, wherein the risk tag is used to characterize whether the historical vehicle event belongs to a preset risk event type; inputting each time-series data segment into a time-series model with an attention mechanism, and determining the attention score corresponding to each risk assessment factor based on the attention weight distribution output by the time-series model, wherein the time-series model is obtained by training a preset artificial intelligence model; and determining the factor importance corresponding to each risk assessment factor based on each attention score.

6. The method according to claim 5, characterized in that, Based on the relative importance among the aforementioned importance levels, the relative risk weights corresponding to each of the risk assessment factors are determined, including: using each risk assessment factor as the row index and column index of the second judgment matrix, and filling the second judgment matrix with the ratio between the importance levels of the factors as the relative importance; calculating the largest eigenvalue corresponding to the second judgment matrix to obtain the second eigenvalue, and calculating the eigenvector corresponding to the second eigenvalue to obtain the second eigenvector; normalizing the second eigenvector to obtain the relative weight vector, wherein the relative weight vector includes the relative risk weights corresponding to each risk assessment factor.

7. The method according to any one of claims 1 to 6, characterized in that, The comprehensive risk probability is calculated by combining the first risk probability and the second risk probability, including: obtaining the probability weights corresponding to the first risk probability and the second risk probability respectively; and performing a weighted calculation on the first risk probability and the second risk probability according to the probability weights to obtain the comprehensive risk probability.

8. The method according to any one of claims 1 to 6, characterized in that, Controlling the airbag controller of the vehicle terminal to enter a pre-ready state includes at least one of the following: controlling the airbag controller to switch from a dormant state to an active state; controlling the power supply voltage of the airbag power supply circuit according to a preset airbag deployment voltage through the airbag controller, wherein the airbag power supply circuit is used to supply power to the airbag of the vehicle terminal; charging the capacitor of the airbag igniter through the airbag controller, wherein the airbag igniter is used to trigger the gas generator to inflate the airbag; and reallocating the computing resources of the airbag controller.

9. An airbag pre-preparation system combining feature fusion and relative weighting, characterized in that, include: The acquisition module is used to acquire multiple risk assessment factors; The fusion module is used to assess the probability of a risk event occurring at the vehicle terminal according to each of the risk assessment factors, obtain the risk occurrence probability corresponding to each of the risk assessment factors, and perform feature fusion based on the relative risk probabilities between the risk occurrence probabilities to obtain a first risk probability. The calculation module is used to evaluate the importance of each of the risk assessment factors and determine the relative risk weight of each of the risk assessment factors based on the relative importance between the importance levels, so as to perform a weighted calculation on the probability of occurrence of each risk based on the relative risk weight to obtain a second risk probability. The control module is used to calculate a comprehensive risk probability by combining the first risk probability and the second risk probability, and if the comprehensive risk probability is greater than a preset risk probability threshold, it controls the airbag controller of the vehicle terminal to enter a pre-ready state.

10. A vehicle terminal, characterized in that, include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the vehicle terminal to perform the method as described in any one of claims 1-8.

Images