Child seat selection and evaluation method, device, electronic device, and storage medium

Abstract

The present disclosure relates to a child seat selection and evaluation method, apparatus, electronic device, and storage medium. The method comprises: obtaining a child seat selection dataset, the dataset comprising at least collision pulse data from multiple vehicles, seat measurement data from multiple seats, and multiple injury outcome data; performing data correction on the child seat selection dataset; parameterizing key features of the standardized dataset using the Pearson correlation coefficient; training a child seat selection model pre-built using a random forest regression algorithm using the key feature data; inputting the collision pulse data of a target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle; and, in response to an update to the child seat selection dataset, updating the child seat selection model using the updated child seat selection dataset.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a child seat selection and evaluation method, device, electronic device, and storage medium. Background Art

[0002] Child safety in vehicles is a global concern, with child injuries resulting from traffic accidents occurring frequently each year. Many of these injuries and deaths could be prevented with appropriate child restraint systems, such as child safety seats. However, traditional child seat design and selection relies primarily on simulation development, crash testing, and expert experience. This approach is time-consuming, labor-intensive, and costly, and it is difficult to fully assess safety under various collision scenarios. Summary of the Invention

[0003] In order to solve the above technical problems, the present disclosure provides a child seat selection and evaluation method, device, electronic device and storage medium.

[0004] The present disclosure provides a child seat selection and evaluation method, comprising: obtaining a child seat selection data set, the child seat selection data set comprising at least collision pulse data of multiple vehicles, seat measurement data of multiple seats, and multiple injury result data, wherein the injury result data is calculated based on the collision pulse data, a standard operating condition simulation model of the vehicle, and a seat simulation model of the child seat; performing data correction on the child seat selection data set to obtain a standardized data set; performing key feature parameterization on the standardized data set, screening out waveform features that are significantly correlated with target variables in the standardized data set through the Pearson correlation coefficient, and obtaining key feature data; using the key feature data to train a child seat selection model pre-constructed using a random forest regression algorithm, comprising: performing integrated learning on the input key feature data through multiple decision trees; inputting the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat adapted to the target vehicle; and in response to an update of the child seat selection data set, updating the child seat selection model using the updated child seat selection data set.

[0005] Optionally, the standard operating condition simulation model is calculated based on rear seat data, front seat data, cabin data and safety configuration data of multiple vehicles.

[0006] Optionally, the seat measurement data includes the size data of the child seat and the installation data of the child seat, and the injury result data includes the 3ms synthetic acceleration data of the child seat's head, the child seat's head injury data, the child seat's neck force data, and the child seat's chest pressure displacement data.

[0007] Optionally, data correction is performed on the child seat selection data set to obtain a standardized data set, including: using an interpolation method to repair incomplete data in the collision pulse data.

[0008] Optionally, abnormal values, outliers and missing values ​​in the seat measurement data and injury result data are processed, denoising and data correction are performed on the seat measurement data and injury result data, and the data units of the seat measurement data and the injury result data are unified.

[0009] Optionally, the waveform features include waveform activation duration, signal strength integral, root mean square power, dominant harmonic amplitude, spectrum extreme points, frequency band energy integral, power spectrum centroid and spectrum randomness measure.

[0010] Optionally, the collision pulse data of the target vehicle is input into a trained child seat selection model to obtain a child seat suitable for the target vehicle, including: inputting the collision pulse data of the target vehicle into the child seat selection model to obtain injury result data of multiple child seats to be selected on the target vehicle; calculating the selection scores of multiple child seats to be selected on the target vehicle based on the injury result data and target regulations; sorting the multiple selection scores, and selecting the child seat with the highest selection score as the child seat suitable for the target vehicle.

[0011] Based on the same inventive concept, the present disclosure also provides a child seat selection and evaluation device, comprising: a data and model acquisition module, configured to acquire a child seat selection dataset, the child seat selection dataset comprising at least collision pulse data of multiple vehicles, seat measurement data of multiple seats, and multiple injury result data, wherein the injury result data is calculated based on the collision pulse data, a standard operating condition simulation model of the vehicle, and a seat simulation model of the child seat; a data correction module, configured to perform data correction on the child seat selection dataset to obtain a standardized dataset; a feature extraction module, configured to parameterize key features of the standardized dataset, and to screen waveform features significantly correlated with target variables in the standardized dataset using the Pearson correlation coefficient to obtain key feature data; a model training module, configured to use the key feature data to train a child seat selection model pre-constructed using a random forest regression algorithm, including: performing ensemble learning of the input key feature data through multiple decision trees; an evaluation module, configured to input the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle; and an update module, configured to update the child seat selection model using the updated child seat selection dataset in response to an update of the child seat selection dataset.

[0012] Based on the same inventive concept, the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions; wherein the processor is used to read the executable instructions from the memory and execute the executable instructions to implement any one of the methods.

[0013] Based on the same inventive concept, the present disclosure also provides a computer-readable storage medium on which a computer program is stored. The storage medium stores the computer program, and when the computer program is executed by a processor, the processor implements any one of the methods.

[0014] The technical solution provided by this disclosure offers the following advantages over existing technologies: The method provided by this disclosure, through a training model, eliminates the need for individual simulation and testing of child seats for product verification and evaluation. Simply inputting vehicle collision pulse data allows for rapid child seat selection during the early stages of new vehicle development, significantly saving manpower, time, and costs, and accelerating vehicle development. Furthermore, the method provided by this disclosure can dynamically adapt to regulatory updates. As regulatory child seat data becomes available, only the child seat selection dataset needs to be updated, allowing for rapid development of child seat selection and evaluation solutions for all vehicles under development. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0016] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A flowchart of a child seat selection and evaluation method provided by an embodiment of the present disclosure;

[0018] Figure 2 A flowchart of another child seat selection and evaluation method provided by an embodiment of the present disclosure;

[0019] Figure 3 A schematic structural diagram of a child seat selection and evaluation device provided by an embodiment of the present disclosure;

[0020] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned purposes, features and advantages of the embodiments of the present disclosure, the scheme of the embodiments of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the embodiments of the present disclosure, but the embodiments of the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, not all of the embodiments.

[0023] In related technologies, the design and selection of child seats typically requires extensive simulation research and development and crash testing. These tests not only require significant investment in equipment and facilities, but also require specialized technicians for operation and data analysis. Furthermore, these tests have long development cycles, making them difficult to meet the rapid iteration requirements of modern automotive products. Therefore, traditional methods have limitations in improving child safety in vehicles, and a more scientific, efficient, and economical approach is urgently needed to optimize child seat selection.

[0024] In view of this, an embodiment of the present disclosure provides a method for selecting and evaluating a child seat. Figure 1 Shown, including:

[0025] S1. Obtain a child seat selection dataset, where the child seat selection dataset includes at least collision pulse data of multiple vehicles, seat measurement data of multiple seats, and multiple injury result data, wherein the injury result data is calculated based on the collision pulse data, a standard operating condition simulation model of the vehicle, and a seat simulation model of the child seat.

[0026] Specifically, before S1, the method provided in the embodiment of the present disclosure also includes constructing a vehicle seat coupling simulation model based on the vehicle's standard operating condition simulation model and the child seat's seat simulation model, wherein the seat simulation model mainly includes a variety of child seat models recommended by C-NCAP, covering child seats of different brands, installation methods, and material properties. The standard operating condition simulation model is a simulation model of a conventional vehicle, which will be further described in the following embodiments. The collision pulse data of the layout position obtained by the structural simulation standard collision is used as the input condition of the vehicle seat coupling simulation model, and dynamic collision simulation is performed using finite element analysis software to calculate the dynamic response of the child seat during the collision, that is, the above-mentioned injury score, so as to obtain a complete child seat selection data set.

[0027] S2. Perform data correction on the child seat selection dataset to obtain a standardized dataset.

[0028] The method provided in the embodiments of the present disclosure ensures the consistency and availability of data by integrating and correcting the data set, providing a solid data foundation for model training and prediction.

[0029] S3. Parameterize the key features of the standardized data set, and use the Pearson correlation coefficient to screen out waveform features that are significantly correlated with the target variable in the standardized data set to obtain key feature data.

[0030] The method provided in the embodiment of the present disclosure extracts key feature parameters from a standardized data set through feature extraction, thereby achieving accurate input processing of data.

[0031] S4. Using the key feature data, train a child seat selection model pre-built using a random forest regression algorithm. Specifically, this includes: performing ensemble learning on the input key feature data through multiple decision trees.

[0032] The method provided in the embodiment of the present disclosure obtains a high-precision child seat selection model based on the extracted key feature parameters. The model is trained with a large amount of data, which significantly improves its predictive evaluation capabilities, making the child seat selection process more efficient and accurate, and providing guarantees for the selection and safety evaluation of child seats.

[0033] S5. Input the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle.

[0034] Since the seat measurement data and seat simulation model in S1 include information about the child seat to be selected, for the trained child seat selection model, only the vehicle's collision pulse data needs to be input to obtain a child seat suitable for the vehicle.

[0035] S6. In response to the updating of the child seat selection dataset, the child seat selection model is updated using the updated child seat selection dataset.

[0036] The method provided by the disclosed embodiments utilizes a training model to eliminate the need for individual simulation and testing of child seats for product verification and evaluation. Simply inputting vehicle collision pulse data allows for rapid child seat selection during the early stages of new vehicle development, significantly saving manpower, time, and costs while accelerating vehicle development. Furthermore, the method provided by the disclosed embodiments can dynamically adapt to regulatory updates. As regulatory child seat data becomes available, only the child seat selection dataset needs to be updated, allowing for rapid development of child seat selection and evaluation solutions for all vehicles under development.

[0037] In some embodiments, the above-mentioned standard operating condition simulation model is calculated and constructed based on rear seat data, front seat data, cabin data and safety configuration data of multiple vehicles.

[0038] Specifically, the above-mentioned standard working condition simulation model is calculated and constructed based on the statistical mean of rear seat data, front seat data, cabin data and safety configuration data of multiple vehicles.

[0039] The front seat data and rear seat data include data related to backrest angle, seat material, anti-submarine bracket, etc.; the cockpit data includes data related to the body of the vehicle, B-pillar, etc.; the safety configuration data includes data related to seat belt pre-tensioning and buckle arrangement.

[0040] Seat material-related data (such as elastic modulus and yield strength) and safety configuration data (such as seat belt ignition time, force limit, and layout space) are determined based on the statistical mean of simulation data from historical R&D vehicles to ensure that the standard operating condition simulation model meets industry standards.

[0041] In some embodiments, the seat measurement data includes the size data of the child seat and the installation data of the child seat, and the injury result data includes the 3ms synthetic acceleration data of the child seat's head, the child seat's head injury data, the child seat's neck force data, and the child seat's chest pressure displacement data.

[0042] Specifically, the size data of the child seat includes data such as the length, width, height, and thickness of each component of the seat; the installation data of the child seat includes the corresponding installation method and installation direction of the seat.

[0043] In specific implementation, the method for obtaining the above-mentioned child seat size data and child seat installation data includes: using a three-dimensional laser scanner to perform an all-round scan of the child seat to obtain accurate geometric size data, measuring the sizes of key components, including the length, width, height and thickness of the seat base, the backrest height and inclination, the headrest adjustment range, and the side protection device size, establishing a size parameter database, and recording the size characteristics of each model of seat; the installation method and installation direction are obtained through the seat usage method.

[0044] Specifically, the 3ms composite acceleration of the head refers to the composite value of the acceleration experienced by the head within 3 milliseconds, and is one of the key factors in measuring the risk of head injury; the neck force data reflects the tensile, compressive, or shear force experienced by the neck under impact, and the chest pressure injury data records the composite acceleration of the chest when subjected to force, and is an important basis for assessing the risk of chest injury. The calculation formulas for the head injury HIC value are shown in Equations (1) and (2):

[0045]

[0046]

[0047] in, 、 、 is the acceleration value of the head in three directions, in g, .

[0048] The calculation formula of chest injury value is shown in formula (1).

[0049] In some embodiments, the above S2 includes:

[0050] Interpolation method is used to repair incomplete data in collision pulse data.

[0051] In practice, collision pulse data, specifically pulse collision curves, require data correction to check for continuity and integrity, eliminating incomplete data. Interpolation methods are required for non-smooth curves with fewer nodes. Correction also requires converting collision pulse curve data in different unit systems to a unified unit system.

[0052] In some embodiments, the above S2 includes:

[0053] Process outliers, outliers, and missing values ​​in the seat measurement data and injury result data, perform denoising and data correction on the seat measurement data and injury result data, unify the data units of the seat measurement data, and unify the data units of the injury result data.

[0054] In practice, data correction for numerical data such as seat measurement data and injury outcome data requires detecting and processing outliers and outliers, filling missing values, and performing numerical smoothing. This includes data denoising and correction. Data correction for numerical data also requires converting data in different unit systems to a unified unit system.

[0055] In some embodiments, in the above S3, the waveform features include waveform activation duration, signal strength integral, root mean square power, dominant harmonic amplitude, spectrum extreme points, frequency band energy integral, power spectrum centroid and spectrum randomness measurement. These waveform features are multiple key feature pairs ranked at the top of the Pearson correlation with the target value.

[0056] In specific implementation, S3 includes: Using multi-dimensional features, Pearson correlation coefficient feature extraction. Pearson correlation coefficient feature extraction significantly improves the model's ability to understand complex crash dynamics and enhances the accuracy and robustness of model predictions, ensuring the model can capture complex crash dynamics and child seat performance.

[0057] In a specific embodiment, the above-mentioned S3 includes: establishing a correlation model between the pulse signal matrix and the injury result data (the above-mentioned 3ms synthetic acceleration data of the head, the head injury data HIC, the neck force data and the chest pressure injury data), and independently calculating the Pearson correlation coefficient for each injury indicator; using a multi-dimensional feature screening method, taking the average of the Pearson correlation coefficients of each indicator, and obtaining the sum of the Pearson correlation coefficient values ​​of each feature for the multi-dimensional target quantity, and then selecting key feature data, including waveform activation duration, signal strength integral, root mean square power, dominant harmonic amplitude, spectrum extreme point, frequency band energy integral, power spectrum centroid and spectrum randomness measurement.

[0058] The calculation method of Pearson correlation coefficient is shown in formula (3):

[0059]

[0060] In some embodiments, before the above S4, the method provided by the embodiment of the present disclosure further includes:

[0061] A child seat selection scoring model is constructed based on the random forest regression algorithm.

[0062] The method provided in the above-mentioned embodiment of the present disclosure uses a random forest regression algorithm to construct a child seat selection scoring model. This algorithm is highly robust when processing complex data sets and can effectively cope with the challenges of high-dimensional features, thereby ensuring the stability and accuracy of the model when faced with large amounts of diverse input data. In addition, the random forest regression algorithm reduces the variance of the model by integrating multiple decision trees for comprehensive judgment, significantly reduces the risk of overfitting, and improves the generalization ability of the model. By reasonably setting parameters such as the number of decision trees and the number of split features in the model, it can be ensured that the model is neither overly complex nor can it fully learn the characteristics of the data.

[0063] Random forest is a powerful machine learning algorithm widely used for classification and regression problems. Its core approach is to improve predictive performance and model robustness by integrating multiple decision tree models. Decision trees, the building blocks of random forests, recursively partition a dataset into smaller subsets to ultimately generate predictions. Each internal node represents a feature, branches represent possible values ​​for that feature, and leaf nodes represent the final prediction. Random forests build on traditional decision trees by incorporating bagging and feature randomization techniques to further optimize model performance.

[0064] Specifically, the random forest regression algorithm uses a bagging method during training. By randomly sampling the original dataset with replacement, it generates multiple training subsets, each used to train a decision tree. Furthermore, when splitting each node, the random forest does not consider all features, but instead randomly selects a subset of features for splitting. This feature randomization method effectively reduces correlation between models and increases model diversity, thereby further reducing model variance and enhancing generalization.

[0065] When building a model, it's important to properly set the key hyperparameters of the random forest regression algorithm. These hyperparameters include the number of decision trees, the number of features considered when splitting a single tree, the maximum depth of a single tree, the minimum number of samples required for a node split, and the minimum number of samples required for a leaf node. By properly setting these hyperparameters, you can ensure that the model fully learns the specific information in the feature dataset while avoiding issues like partial information mining and inaccurate weighting caused by a single decision tree. This reduces computational errors and improves the model's predictive accuracy.

[0066] During the model training process, it is necessary to select the appropriate model type based on the specific task objectives. For the embodiments of the present disclosure, a method combining a classification model and a regression model can be adopted. Specifically, when the target variable is N different child seats, the model outputs the category to which each sample belongs; and when the target variable is N different injury results, the model will output the predicted score for each sample. During the training process, it is necessary to adjust the hyperparameters of the algorithm so that the prediction results of the classification model and the regression model can be effectively integrated at the decision-making level.

[0067] In some embodiments, the above S5 includes:

[0068] S501: Inputting collision pulse data of a target vehicle into a child seat selection model to obtain injury result data of a plurality of child seats to be selected on the target vehicle.

[0069] S502: Calculate selection scores for multiple child seats to be selected for a target vehicle based on the injury result data and target regulations. Specifically, the selection score includes the total score of the injury results for each body part (head, neck, and chest) calculated based on the target regulations.

[0070] S503: Sort the multiple selection scores and use the child seat with the highest selection score as the child seat suitable for the target vehicle.

[0071] In the field of automobile safety, the NCAP (New Car Assessment Program) management rules (hereinafter referred to as the regulations) of various countries have set requirements for dynamic evaluation of child protection, including the frontal 100% overlap rigid barrier collision condition (FRB), the frontal 50% overlap moving progressively deforming barrier (MPDB) condition, and the side pole collision condition (pole collision).

[0072] In a specific embodiment, Figure 2 As shown, you first need to select a target regulation, such as China GB, China C-NCAP, or China C-IASI. Then, you need to select the vehicle's passive safety crash conditions, which in this example can be divided into head-on and pole-on conditions, and determine the target total scores for head-on and pole-on collisions. The input data is the collision pulse data, which is input into the child seat selection scoring model to obtain the selection scores of multiple child seats to be selected for the target vehicle.

[0073] The child seat selection model provided in the above-mentioned embodiments of the present disclosure provides important decision-making support for vehicle design and child seat selection. By inputting vehicle pulse data, it rapidly generates child seat selection recommendations and provides corresponding selection scores and ranking results. This not only provides a scientific basis for vehicle developers but also improves the efficiency and accuracy of child protection system design. Furthermore, the full automation of the entire process, from data collection to solution output, makes the optimization process of child seat selection more efficient and transparent, providing strong technical support for intelligent vehicle design.

[0074] In some embodiments, the above S6 includes:

[0075] In response to the target regulation update, a selection score is calculated based on the updated target regulation.

[0076] In a specific embodiment, after the child seat data in a target regulation (e.g., C-NCAP regulation) is updated, a new child seat needs to be selected as a reference in the child seat safety development. Therefore, the current child seat selection model needs to re-incorporate the feature-related information of the new seat specified in the regulation, and then repeat the above steps S1 to S5 to obtain a child seat that meets the requirements of the new regulation, dynamically adapting to the update of the regulation.

[0077] In a specific embodiment, the method provided by the embodiment of the present disclosure further includes testing, dynamically optimizing and updating the above-mentioned child seat selection model to ensure the adaptability and accuracy of the model.

[0078] To ensure the objectivity and reliability of test results, standardized key feature data must be partitioned into training, validation, and test sets. For the current model, the validation set is used for model selection and hyperparameter adjustment, while the test set is used for performance evaluation of the final model. Model testing is performed based on the partitioning ratio, ensuring the independence and representativeness of each part.

[0079] Specifically, metrics such as classification accuracy, F1 score, mean squared error (MSE), and coefficient of determination (R²) can be used to comprehensively evaluate model performance and identify deficiencies. The regression task of the prediction model is evaluated, focusing on the model's prediction accuracy for the injury selection score. The injury selection score is an important indicator for measuring the safety performance of child seats, and its prediction accuracy directly affects the model's practical application value. In the test, mean squared error (MSE) and coefficient of determination (R²) were used as the primary evaluation metrics. MSE reflects the average error between the model's predicted value and the true value, while the coefficient of determination quantifies the model's ability to explain data variation. By analyzing these metrics, the model's performance in the regression task can be comprehensively evaluated. The classification task of the prediction model is evaluated. The goal of the classification task is to accurately predict the type of child seat, which is of great significance for vehicle selection decisions. Classification accuracy and F1 score are used as the primary evaluation metrics. Classification accuracy reflects the model's performance in the overall classification task, while the F1 score comprehensively considers the model's precision and recall, comprehensively evaluating the model's predictive ability across different categories. By analyzing these indicators, we can discover the advantages and disadvantages of the model in classification tasks and provide direction for subsequent optimization.

[0080] Specifically, prediction accuracy and efficiency can be improved by systematically adjusting model hyperparameters. These hyperparameters include the number of decision trees, the number of features considered when splitting a single tree, the maximum depth of a single tree, the minimum number of samples required for node splitting, and the minimum number of samples required for leaf nodes, etc., to accelerate convergence and improve model performance.

[0081] During model validation, the model's generalization ability needs to be evaluated to measure the model's performance on unseen data. To verify the model's generalization ability, cross-validation is used. By partitioning the standardized key feature data into training and validation sets multiple times, cross-validation effectively reduces the bias introduced by data partitioning and ensures high stability of the model's performance on different data subsets. The testing process and cross-validation results are recorded, and the mean and standard deviation are calculated to assess the model's generalization ability.

[0082] The model's continuous optimization mechanism not only improves the model's long-term performance, but also enhances the model's practicality and adaptability, ensuring its effectiveness in different design scenarios.

[0083] The interpretability of the child seat selection model, based on the random forest regression algorithm, was primarily evaluated. While the random forest regression algorithm offers high predictive performance, its complex model structure makes it difficult to directly interpret. Feature importance analysis was used to assess the influence of each feature on the model's predictions. This analysis of feature importance allows the testing department to provide valuable reference information to designers, helping them understand the model's predictive logic.

[0084] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario, where multiple devices cooperate with each other to complete the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the above method.

[0085] It should be noted that the above description is limited to some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] Based on the same inventive concept, corresponding to any of the above embodiments and methods, the present application also provides a child seat selection and evaluation device, such as Figure 3 Shown, including:

[0087] The data and model acquisition module 10 is used to obtain a child seat selection data set, which includes at least collision pulse data of multiple vehicles, seat measurement data of multiple seats, and multiple injury result data, wherein the injury results are calculated based on the collision pulse data, the vehicle's standard operating condition simulation model, and the child seat's seat simulation model.

[0088] The data correction module 20 is used to correct the child seat selection data set to obtain a standardized data set.

[0089] The feature extraction module 30 is used to parameterize key features of the standardized data set, and to screen out waveform features that are significantly correlated with the target variable in the standardized data set through the Pearson correlation coefficient to obtain key feature data.

[0090] The model training module 40 is used to train the child seat selection model pre-built using the random forest regression algorithm using key feature data, including: integrating the input key feature data through multiple decision trees.

[0091] The evaluation module 50 inputs the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle.

[0092] The updating module 60 is configured to update the child seat selection model using the updated child seat selection dataset in response to the updating of the child seat selection dataset.

[0093] The device provided by the disclosed embodiments utilizes a training model to eliminate the need for individual simulation and testing of child seats for product verification and evaluation. Simply inputting vehicle collision pulse data allows for rapid selection of child seats during the early stages of new vehicle development, significantly saving manpower, time, and costs while accelerating vehicle development. Furthermore, the device provided by the disclosed embodiments can dynamically adapt to regulatory updates. As regulatory child seat data becomes available, only the child seat selection dataset needs to be updated, allowing for rapid development of child seat selection and evaluation solutions for all vehicles under development.

[0094] In some embodiments, the standard operating condition simulation model is calculated based on rear seat data, front seat data, cabin data, and safety configuration data of multiple vehicles.

[0095] In some embodiments, the seat measurement data includes the size data of the child seat and the installation data of the child seat, and the injury result data includes the 3ms synthetic acceleration data of the child seat's head, the child seat's head injury data, the child seat's neck force data, and the child seat's chest pressure displacement data.

[0096] In some embodiments, the data correction module is specifically used to:

[0097] Interpolation method is used to repair incomplete data in collision pulse data.

[0098] In some embodiments, the data correction module is specifically used to:

[0099] Process outliers, outliers and missing values ​​in seat measurement data and injury result data, perform denoising and data correction on the seat measurement data and injury result data, unify the data units of seat measurement data and injury result data.

[0100] In some embodiments, waveform features include waveform activation duration, signal strength integral, root mean square power, dominant harmonic amplitude, spectrum extreme points, frequency band energy integral, power spectrum centroid, and spectrum randomness measure.

[0101] In some embodiments, the evaluation module is specifically configured to:

[0102] The collision pulse data of the target vehicle is input into the child seat selection model to obtain injury result data of multiple child seats to be selected on the target vehicle; the selection scores of the multiple child seats to be selected on the target vehicle are calculated based on the injury result data and the target regulations; the multiple selection scores are ranked, and the child seat with the highest selection score is selected as the child seat suitable for the target vehicle.

[0103] For the convenience of description, the above devices are described as being divided into various modules according to their functions. Of course, when implementing this application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0104] The device of the above embodiment is used to implement the corresponding child seat selection and evaluation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0105] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown.

[0106] like Figure 4 As shown, the electronic device may include a processor 1101 and a memory 1102 storing computer program instructions.

[0107] Specifically, the processor 1101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0108] Memory 1102 may include a large-capacity memory for information or instructions. By way of example and not limitation, memory 1102 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1102 may include removable or non-removable (or fixed) media. Where appropriate, memory 1102 may be internal or external to the integrated gateway device. In a specific embodiment, memory 1102 is a non-volatile solid-state memory. In a specific embodiment, memory 1102 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0109] The processor 1101 reads and executes the computer program instructions stored in the memory 1102 to perform the steps of the child seat selection and evaluation method provided in the embodiment of the present disclosure.

[0110] In one example, the electronic device may further include a transceiver 1103 and a bus 1104. Figure 4 As shown, the processor 1101 , the memory 1102 and the transceiver 1103 are connected via a bus 1104 and communicate with each other.

[0111] The bus 1104 may include hardware, software, or both. By way of example, and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus 1104 may include one or more buses. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0112] The following is an embodiment of a computer-readable storage medium provided in an embodiment of the present disclosure. The computer-readable storage medium and the child seat selection and evaluation method of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the computer-readable storage medium, please refer to the embodiment of the above-mentioned child seat selection and evaluation method.

[0113] This embodiment provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a child seat selection and evaluation method.

[0114] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present disclosure is not limited to the above method operations, and its computer-executable instructions can also execute related operations in the child seat selection and evaluation method provided in any embodiment of the present disclosure.

[0115] Through the above description of the embodiments, those skilled in the art will clearly understand that the present disclosure can be implemented using software and necessary general-purpose hardware. Of course, it can also be implemented using hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present disclosure, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disk, and includes a number of instructions for enabling a computer cloud platform (which can be a personal computer, server, or network cloud platform, etc.) to execute the child seat selection and evaluation method provided by various embodiments of the present disclosure.

[0116] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a..." do not exclude the presence of other identical elements in the process, method, article or device that includes the above elements.

[0117] The foregoing are merely specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not limited to the foregoing embodiments, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A child seat selection and evaluation method, characterized in that: include: Obtaining a child seat selection dataset, the child seat selection dataset comprising at least collision pulse data of a plurality of vehicles, seat measurement data of a plurality of seats, and a plurality of injury result data, wherein the injury result data is calculated based on the collision pulse data, a standard operating condition simulation model of the vehicle, and a seat simulation model of the child seat; performing data correction on the child seat selection data set to obtain a standardized data set; Parameterizing key features of the standardized data set, screening waveform features significantly correlated with target variables in the standardized data set using the Pearson correlation coefficient, and obtaining key feature data; Using the key feature data to train a child seat selection model pre-built using a random forest regression algorithm, including: performing integrated learning on the input key feature data through multiple decision trees; When the target variable is N different injury outcomes, the model will output the prediction score for each sample; Inputting collision pulse data of a target vehicle into a child seat selection model to obtain injury result data of a plurality of child seats to be selected on the target vehicle, and calculating selection scores of the plurality of child seats to be selected on the target vehicle based on the injury result data and target regulations to obtain a child seat suitable for the target vehicle; In response to the updating of the child seat selection dataset, the child seat selection model is updated using the updated child seat selection dataset.

2. The method according to claim 1, characterized in that The standard operating condition simulation model is calculated based on rear seat data, front seat data, cockpit data and safety configuration data of multiple vehicles.

3. The method according to claim 1, characterized in that The seat measurement data includes the size data of the child seat and the installation data of the child seat, and the injury result data includes the 3ms synthetic acceleration data of the child seat head, the head injury data of the child seat, the neck force data of the child seat and the chest pressure displacement data of the child seat.

4. The method according to claim 1, wherein The step of performing data correction on the child seat selection dataset to obtain a standardized dataset includes: An interpolation method is used to repair incomplete data in the collision pulse data.

5. The method according to claim 1, characterized in that The step of performing data correction on the child seat selection dataset to obtain a standardized dataset includes: Processing abnormal values, outliers and missing values ​​in the seat measurement data and the injury result data, performing denoising and data correction on the seat measurement data and the injury result data, unifying the data units of the seat measurement data and the injury result data.

6. The method according to claim 1, characterized in that The waveform features include waveform activation duration, signal strength integral, root mean square power, dominant harmonic amplitude, spectrum extreme point, frequency band energy integral, power spectrum centroid and spectrum randomness measurement.

7. The method according to claim 1, characterized in that Inputting the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle includes: Inputting the collision pulse data of the target vehicle into the child seat selection model to obtain injury result data of a plurality of child seats to be selected on the target vehicle; Calculating selection scores of multiple child seats to be selected on the target vehicle based on the injury result data and target regulations; The plurality of selection scores are sorted, and the child seat with the highest selection score is selected as the child seat adapted for the target vehicle.

8. A child seat selection and evaluation device, based on the method according to any one of claims 1 to 7, characterized in that: include: a data and model acquisition module, configured to acquire a child seat selection dataset, the child seat selection dataset comprising at least collision pulse data of a plurality of vehicles, seat measurement data of a plurality of seats, and a plurality of injury result data, wherein the injury result data is calculated based on the collision pulse data, a standard operating condition simulation model of the vehicle, and a seat simulation model of the child seat; a data correction module, configured to correct the child seat selection data set to obtain a standardized data set; A feature extraction module is used to parameterize key features of the standardized data set, and to screen out waveform features that are significantly correlated with the target variable in the standardized data set through the Pearson correlation coefficient to obtain key feature data; A model training module is used to train a child seat selection model pre-built using a random forest regression algorithm using the key feature data, including: integrating the input key feature data through multiple decision trees; an evaluation module, inputting the collision pulse data of the target vehicle into the trained child seat selection model to obtain a child seat suitable for the target vehicle; An updating module is configured to update the child seat selection model using the updated child seat selection dataset in response to an update of the child seat selection dataset.

9. An electronic device, characterized in that: include: processor; A memory for storing executable instructions; wherein the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method according to any one of claims 1 to 7.

Images