89 results about "Feature synthesis" patented technology

The invention provides a fine-grained cultivated land protection potential optimization method, medium and system, and belongs to the technical field of cultivated land data processing.The method comprises the steps that firstly, multi-source remote sensing, soil and climate data are obtained, and a basic feature matrix is extracted through multi-dimensional decomposition; then, multi-scale analysis of soil quality features is realized by utilizing a pyramid neural network model, and adaptive fusion is carried out through a feature integration module; and then constructing a contribution degree optimization equation set, comprehensively considering four aspects of benchmark evaluation, space correlation, time sequence evolution and weight balance, realizing accurate evaluation of the cultivated land protection potential, and generating an optimized protection partition scheme. On one hand, the pyramid neural network model overcomes the problem of insufficient feature extraction of a traditional method through multi-scale feature extraction and adaptive fusion; and on the other hand, through multi-dimensional information fusion and dynamic optimization, the contribution degree optimization equation set solves the problem that accurate evaluation of the cultivated land protection potential is difficult to realize in the prior art.

The invention relates to the technical field of defect detection, and particularly discloses an electronic component defect detection method, system and device, and the method comprises the steps: collecting a multiband original image set based on multispectral imaging, inhibiting batch material difference and surface reflection through orthogonal complementary space projection, and obtaining a de-noised image set; performing feature extraction on the de-noised image set, and identifying and marking all fragmented defect areas; based on a graph neural network space attention mechanism, establishing an association relationship between fragmented defect areas to form a complete defect feature chain; gray frequency value sequences of the to-be-detected image and the standard sample image are constructed respectively, and a first fitting curve and a second fitting curve are obtained through fitting of a skewed distribution function; and finally, comprehensively judging whether the electronic component has defects or not by combining the defect characteristic chain and the difference characteristics of the two fitting curves. According to the method, interference can be effectively suppressed, fragmented defects can be accurately identified, and the detection accuracy and reliability are remarkably improved through multi-dimensional feature fusion.

The invention discloses a travel emergency state judgment method and device based on semantic analysis and a storage medium, and relates to the technical field of classification models. Comprising the following steps: extracting speech characteristic parameters such as speech speed, volume, speech signal spectrum entropy and the like by collecting speech data of an independent user with known emotion and target intention, and calculating a speech judgment coefficient; and based on the voice text data, performing voice recognition by using a knowledge perception network model, and generating a danger feature comprehensive vector. And using the vector to train a neural network model, taking the danger feature comprehensive vector as input, and predicting a corresponding emotion and a target intention. And monitoring voice data of the independent user in real time, obtaining a corresponding danger feature comprehensive vector, calculating a comprehensive emergency state judgment index by combining the voice judgment coefficient and the environment data, comparing the index with a risk threshold value, and outputting an emergency state instruction. The method can effectively predict the emergency situation of the user in travel, and provides support for safety emergency.

The invention provides a talent resource information management platform and method oriented to a multi-dimensional standard, and relates to the technical field of resource information management, and the method comprises the steps: receiving multi-source talent data through multiple data sources; performing talent resource evaluation on the multi-source talent data according to the evaluation dimension of the talent, and constructing a talent stereo map; performing intelligent feature analysis based on the talent stereo map to generate a comprehensive evaluation score; performing personalized talent recommendation according to the comprehensive evaluation score to obtain a comprehensive recommendation result; and carrying out dynamic visualization on the comprehensive recommendation result, and carrying out interactive management. According to the method and the device, the technical problem that effective integration of talents and team cooperation efficiency are further influenced due to lack of comprehensive consideration of multi-dimensional features in candidate evaluation in the prior art can be solved, and the technical goal of performing multi-dimensional feature comprehensive evaluation on candidates is achieved; the technical effect of improving the talent matching degree and the team cooperation efficiency is achieved.

The invention belongs to the technical field of power equipment state monitoring, and discloses a transformer fault detection method based on feature fusion. The method comprises the following steps: acquiring and preprocessing a transformer sound signal; feature extraction of a Mel frequency cepstrum coefficient (MFCC) and a power regularization cepstrum coefficient (PNCC) is carried out on the preprocessed sound signals; using a Fisher criterion-based feature fusion algorithm to perform weighted fusion on the MFCC feature parameters and the PNCC feature parameters to generate fused feature parameters; inputting the fusion feature parameters into a deep neural network model for training; inputting the obtained fusion feature parameters of the sound signals of the transformer to be detected into the trained deep neural network model to obtain a detection result of the fault category of the transformer; according to the method, MFCC and PNCC feature parameters are fused, MPFC features are obtained through dynamic weighting, frequency domain information, anti-noise information and sensitive frequency band information are integrated, and the detection accuracy and the anti-interference capacity are improved.

The invention provides a multi-scale exercise rehabilitation assessment method and system, computer equipment and a storage medium. The method comprises the following steps: acquiring a limb rehabilitation exercise video of a to-be-assessed object in a rehabilitation training process; for each frame of image in the limb rehabilitation exercise video, feature information, including equivalent shape information, vector information and joint point information, of a limb part is extracted; performing feature coding on each limb part to generate a weight and an action sequence code corresponding to each limb part; based on the feature coding result, an evaluation model is constructed, the model is a time sequence model for establishing the internal relation of actions, and an evaluation result of rehabilitation training of the to-be-evaluated object is output. According to the method, the body part information, the limb vector features and the joint point features in the actions can be synthesized to comprehensively evaluate the training actions, so that the training actions are evaluated more accurately.

The invention provides an acupoint compatibility prediction method and device, equipment and a medium, and relates to the technical field of traditional Chinese medicine acupoint compatibility prediction.The method comprises the steps that acupoint compatibility information and acupoint attribute information of to-be-predicted acupoint compatibility are obtained, and an acupoint feature composite graph is constructed based on the acupoint compatibility information and the acupoint attribute information; constructing a de-noised acupoint feature matrix on the basis of a deep non-negative matrix factorization method according to the acupoint feature composite graph, training the de-noised acupoint feature matrix through a residual image attention network model to obtain a target acupoint feature matrix, and obtaining an association relationship of compatibility of the to-be-predicted acupoints according to the target acupoint feature matrix so as to predict the compatibility of the to-be-predicted acupoints. A deep non-negative matrix factorization method is used for carrying out layer-by-layer factorization and fine adjustment on an adjacent matrix of the acupoint feature composite graph to construct a de-noised acupoint feature matrix, random noise in the network can be relieved, comprehensive and effective acupoint feature representation is obtained through a residual image attention network model, and the prediction accuracy is effectively improved.

The invention discloses a rice disease and insect pest image real-time identification and decision-making system based on deep learning, and particularly relates to the technical field of agriculture. A multi-modal fusion identification module; a resistance decision engine module; a dynamic prevention and control execution module; and a feedback optimization module. According to the invention, through a new intelligent plant protection normal form of intelligent perception-collaborative decision-precise execution-closed loop evolution, a multi-spectral imaging and microscopic feature synthesis technology is utilized, the bottleneck of traditional diagnosis is broken through, early-stage precise recognition of diseases and insect pests is realized, a medicament-pathogenic bacteria-natural enemy tripartite game model and a multi-objective optimization mechanism are innovatively constructed, and the method has a wide application prospect. The ecological regulation and control capability of the rice field is activated while the risk of drug resistance is avoided, it is ensured that prevention and control measures accurately reach a target by means of the three-dimensional profiling spraying and natural enemy synergistic release technology, residual feedback and model self-iteration are fused in the whole process, a prevention and control closed loop which is more intelligent is formed, and an evolvable digital solution is provided for rice green production.

The invention relates to the technical field of data analysis, and discloses a multi-dimensional classification method and device for computing power resources, and the method comprises the steps: obtaining the distribution information of all computing power resources within a target range; analyzing multi-dimensional information of each computing power resource according to the distribution information; according to all the multi-dimensional information, a multi-dimensional feature value of each computing power resource is calculated, and the multi-dimensional feature value is used for representing the comprehensive performance condition of the multi-dimensional feature of the computing power resource; and allocating each computing power resource to at least one classification set according to all the multi-dimensional feature values. Therefore, by implementing the method, the classification accuracy of the computing power resources can be improved from the perspective of multi-dimensional feature comprehensive analysis of the computing power resources in the level of a computing power resource management platform and before the computing power resources are applied, the coordination matching accuracy of the computing power tasks and the computing power resources can be improved, and the computing power resources can be more accurately classified. The application scientificity and application sustainability of the computing power resources are improved, and the application efficiency of the regional computing power resources is improved.

The invention discloses an important node screening method for an active telemetering scene, and provides a comprehensive evaluation and optimization framework aiming at the problems of probe resource waste and overhigh system load caused by improper node selection in the existing telemetering technology. According to the method, network static topology features and dynamic state features are combined, a node importance scoring model is constructed through feature extraction, dimension reduction fusion and multi-task feature comprehensive analysis, and accurate selection of important network nodes is achieved. According to the method, topological information is analyzed through a weighted TOPSIS method to obtain spatial features, key dimensions of state features in stage historical telemetry data are extracted through principal component analysis (PCA), redundant data are remarkably reduced, and efficient state feature representation is generated. On the basis, a screening method combining spatial features and node state features is designed, and a screening strategy is dynamically adjusted through feature analysis of staged telemetering so as to optimize node priority ranking. The method is suitable for an active telemetering scene in a complex network environment, the capturing capacity of important events can be remarkably improved, system resource consumption is reduced, and the overall performance of an active telemetering system is comprehensively optimized.

The invention relates to the technical field of information retrieval, in particular to an image retrieval method and device based on depth difficulty perceptual hash and a storage medium. In the method, in order to comprehensively model a global geometric structure of an embedded space, self-adaptive difficulty perception enhancement is carried out on an original data sample, and the difficulty level is dynamically adjusted by utilizing linear interpolation for embedding; difficulty perception feature synthesis is carried out to generate enhanced data samples which are consistent in semantics and reserved in labels, and loop training is carried out on the enhanced data samples; the strategy not only makes full use of potential information in all training samples, but also systematically challenges learned metrics with the difficulty of adaptive calibration, ensures continuous optimization on the whole feature manifold, and promotes generation of similarity-preserving hash codes.

The invention relates to the technical field of artificial intelligence, and discloses an artificial intelligence-driven multi-modal data analysis method and system, and the system comprises a data collection module which is used for setting collection nodes and terminals, collecting multi-modal data and equipment operation parameters in real time, and carrying out the format conversion; the multi-modal fusion module is used for constructing a cross-modal semantic association model, processing space-time characteristics, fusing characterization characteristics and performing association simulation; the feature extraction module is used for constructing image, text and voice related extraction algorithms to obtain corresponding features; the comprehensive analysis module is used for carrying out correlation calculation on the features after standardization processing, and comparing and analyzing semantic consistency with a preset threshold value; and the grading processing module is used for combining context calculation analysis when semantics are inconsistent, and analyzing target scene performance after secondary comparison. The system and the method can effectively process multi-modal data, improve semantic analysis accuracy and efficiency, and are suitable for various scenes.

The invention discloses a bearing fault diagnosis method based on feature mode decomposition and heterogeneous model fusion, and belongs to the technical field of mechanical fault diagnosis. An original vibration signal of the rolling bearing is collected; independent of any bearing geometric parameter or fault characteristic frequency information, a finite impulse response (FIR) filter is iteratively optimized to maximize a correlation kurtosis (CK) value, and a plurality of intrinsic mode functions (IMF) are adaptively decomposed; selecting first M IMFs with the highest CK value, extracting time domain, frequency domain and nonlinear complexity features of the IMFs, generating high-order derivative features by adopting depth feature synthesis DFS, and constructing an enhanced fusion feature vector; and finally, inputting a stacked integrated classifier consisting of six types of heterogeneous basic learners and an XGBoost element learner, and outputting a fault diagnosis result. According to the method, high-precision and high-robustness diagnosis can still be realized under the working conditions of speed change, strong noise and weak faults.

The invention discloses a focus auxiliary recognition method and device based on deep learning, and relates to the technical field of image recognition. The method comprises the following steps: acquiring a CT image of a target area, taking the CT image as a target image, and executing an image enhancement operation according to the target image to obtain a first feature map; performing image reconstruction operation according to the first feature map to obtain a first reconstructed image, and inputting the first feature map into a decoder to obtain a first continuous vector; the first continuous vector is a continuous vector obtained by decoding a first feature map; performing an abnormal feature synthesis operation according to the first continuous vector to obtain a discrete feature vector; inputting the discrete feature vector into an encoder to obtain a second reconstructed image; fusing the first reconstructed image and the second reconstructed image to obtain a final reconstructed image; performing feature classification network operation on the discrete feature vector to obtain an abnormal feature vector; and integrating the abnormal feature vector and the final reconstructed image to obtain a second abnormal feature graph. The method improves the definition of the image and the accuracy of diagnosis.

The invention discloses a sewer pipe network defect detection method based on multi-label zero sample learning. The method comprises the following steps: generating defect description corresponding to each pipeline defect category through a large language model; performing feature extraction and domain adaptation on the pipeline inner wall image and the defect description by using a representation guide module to obtain global and local image features and defect detailed description text features; synthesizing global and local image features of the image, respectively calculating global and local matching scores of the global and local image features and detailed description text features, and fusing to obtain a defect initial prediction score; constructing a semantic relationship adjacency matrix for displaying the relationship between different defect categories; and correcting the initial prediction score by using the semantic relationship adjacency matrix between the categories to obtain a final prediction score of each defect category. According to the method provided by the invention, knowledge migration from known defects to unknown defects is realized by constructing a guidance-fusion-correction network, and the difficulty in identifying types of unseen defects is effectively solved.

This application relates to the field of computer technology, providing an intent prediction method, apparatus, electronic device, and storage medium. The intent prediction method includes: first, acquiring target user data, which includes data associated with a target product; then, determining comprehensive characteristics corresponding to the target user based on the target user data, including user profile features, sentiment features, and behavioral features; finally, obtaining a target probability based on the comprehensive characteristics of the target user and a target prediction strategy, whereby the target probability represents the probability that the target user will purchase the target product. The target prediction strategy is correlated with the amount of historical user data corresponding to the target product, and the amount of historical user data is positively correlated with the product's shelf life. This allows the target prediction strategy to evolve gradually over time, enabling it to match prediction needs at different stages and improving prediction accuracy.

The application discloses a kind of neurogenetic disease identification model construction method and system, it is related to neurogenetic disease identification technical field.The method includes: obtaining multiple identification results and multiple user feature sets of neurogenetic disease identification, and multiple inter-class difference degrees are obtained by analysis;Based on multiple identification results and multiple user feature sets, train first identification model;According to multiple inter-class difference degrees, configure user feature synthesis strategy, generate synthetic user feature set and synthetic identification result, carry out the reinforcement learning of first identification model, obtain second identification model;Test the combined identification error rate of second identification model, combined with multiple inter-class difference degrees again configure synthetic strategy, continue to generate synthetic user feature set and synthetic identification result, carry out reinforcement learning, obtain third identification model.The application solves the problem that neurogenetic disease identification model is poor in generalization performance, easily confused class and low in recognition accuracy under small sample condition.

The present invention discloses an action recognition method based on graph-guided selective scanning. By constructing a learnable adjacency matrix, dynamic topological relationships are effectively captured, overcoming the limitation that traditional static topology is difficult to reflect multiple joint relationships when processing complex actions. In the feature extraction process, a multi-branch structure is used to process joints, bones and motion features, and the convolution operation is extended to non-Euclidean space through graph convolution to capture the complex spatial relationships in skeleton data. 2D selective scanning makes full use of the graph-guided state space modeling features, comprehensively considers global and local features, so as to improve the performance and accuracy of feature extraction; the application of multi-scale time convolution enhances the understanding of complex motion patterns, making the analysis of dynamically changing time series data more effective.

The application discloses an automatic feature engineering method based on Monte Carlo tree search and a large language model, which comprises inputting feature data such as a table data set into a computer system; the computer system performs feature initialization, evaluates the score of each initial feature input, and constructs an initial feature tree structure; the steps of candidate feature selection, expansion based on a large language model, feature score evaluation and score parameter updating are iteratively performed until the termination condition is met; based on the selected features, the large language model is called in combination with the prompt word engineering to expand and generate new feature nodes; the new feature nodes are substituted into a predefined end-to-end machine learning pipeline for evaluation, and the feature score is comprehensively calculated; the related parameters of all ancestor nodes in the feature tree are updated from bottom to top along the feature synthesis path; and after the iteration is terminated, the optimal feature set capable of improving the prediction performance of a basic machine learning model is output. The application can significantly improve the accuracy of a machine learning model in a table data prediction task.

The present invention discloses a method and system for hierarchical management of enterprise data assets, which relates to the field of hierarchical management of enterprise data assets. The key points of its technical solution include: collecting the comprehensive asset data and data classification criteria of an enterprise within a collection cycle time, and performing preliminary processing on the comprehensive asset data to obtain preliminary comprehensive data; using improved natural language processing technology to perform key feature analysis on each text in the preliminary comprehensive data, collecting the word conversion vectors corresponding to the feature words in all texts, and obtaining feature comprehensive data; using the K-means technology to perform clustering analysis on each text in the feature comprehensive data to obtain a similar hierarchical data set; using a hierarchical scheme design model to perform level matching on each group in the similar hierarchical data set to obtain the data classification level corresponding to each group; and according to the data classification level corresponding to each group, using the protection measures in the data classification criteria for management to achieve the hierarchical management of enterprise data assets.

The invention belongs to the field of target tracking, and particularly relates to an infrared weak and small target tracking method based on attention guidance proposal comparison, which comprises the following steps of: 1, preparing an infrared weak and small target tracking data set; 2, constructing a network model, wherein the model is composed of a feature extraction module, a hierarchical cross attention feature enhancement module, a global search proposal generation module, a comparison enhancement perception module and a dynamic template updating module; according to the method, cross-feature and cross-hierarchy information association is realized through a hierarchy cross attention module, and dependency between features is enhanced; a candidate proposal is generated by the global search module and then input into the contrast enhancement perception module, so that the gap between positive and negative samples is effectively enlarged, and the positive samples are closer to a real target; and finally, the output of the comparison module, the template features and the old dynamic template features are integrated through a dynamic template updating module to complete template updating, so that the robustness and the accuracy in the tracking process are improved, and the method is suitable for stable tracking of the infrared weak and small target under the complex background.

A key feature screening method includes a monitoring subsystem, a detection subsystem, and a feature screening module configured to execute the key feature screening method, in which a machine is monitored by the monitoring subsystem to generate a plurality of feature values corresponding to a plurality of features of the machine, autocorrelation of the plurality of feature values is calculated, and the autocorrelation of the plurality of feature values is calculated. And defining a moving average period number of each characteristic value according to the autocorrelation of each characteristic value, calculating a moving average according to the moving average period number of each characteristic value so as to judge whether each characteristic value has a gradual increase or gradual decrease trend, and then calculating the correlation between the characteristic value and the machine for each characteristic value with the consistent trend so as to judge whether the machine fails or not. And calculating a key feature comprehensive score of each feature, and screening out key features imported into the detection subsystem according to the key feature comprehensive scores.

A method includes obtaining a first dataset including a first feature set, generating a first set of feature values by providing the first dataset to a set of feature primitive stacks, and determining a reduced set of feature values based on the first set of feature values by dimensionally reducing features of the first set of feature values. The method further includes generating an intermediate set of feature values by providing a value of the first dataset and a value of the reduced set of feature values to at least one feature primitive of the set of feature primitive stacks. The method further includes updating the reduced set of feature values by dimensionally reducing features of the intermediate set of feature values and storing a second dataset including features of the intermediate set of feature values in association with the first feature set.

At least a method and an apparatus are presented for efficiently encoding or decoding video using neural networks wherein the bitstream is adapted to hybrid machine / human vision applications. For example, the scalable decoding comprises applying to a tensor of reconstructed data a neural network-based feature synthesis processing to generate a tensor of input feature representative of a feature of image data samples, resizing the tensor of input feature to generate a tensor of output feature intended to be fed a neural network-based vision inference processing to generate a collection of inference results. Advantageously, resizing the tensor of input feature adapt at least a dimension of the tensor of input feature to the neural network-based vision inference processing.

The invention relates to the technical field of brain-eye information sensing management systems, and discloses a chip-level encryption-based brain-eye information sensing management system, which comprises a data acquisition module, an encryption processing module, a feature extraction module, a comprehensive management module and a security verification module. The data acquisition module acquires electroencephalogram signals and eye movement characteristic data in real time through sensing nodes; the encryption processing module carries out chip-level encryption on data by adopting symmetric and asymmetric encryption technologies; the feature extraction module extracts electroencephalogram feature parameters and eye movement track features through a multi-modal fusion algorithm; the comprehensive management module carries out standardization processing and threshold comparison analysis; and the security verification module performs secondary dynamic verification in combination with the identity information. Through a hardware encryption engine and a multi-modal fusion technology, the data security and analysis precision are improved, and the method is suitable for the fields of identity authentication and the like.

The invention discloses a power grid fault rapid diagnosis method and system based on artificial intelligence, relates to the technical field of power grid detection, and aims to analyze a power grid topological structure and historical fault data by using a convolutional neural network through a deep learning model and a positioning recovery prediction model so as to accurately position a fault source. Particularly, the performance is outstanding in a complex power grid environment, and the problem of low positioning precision of a traditional method is solved; according to the system, efficient processing of data such as voltage, current and frequency is achieved through an optimized data preprocessing module, the fault diagnosis response time is remarkably shortened by combining a fast training deep learning model, and the problem that the data processing speed is low is solved; besides, the system accurately identifies single, multiple and composite fault types through the fault feature comprehensive evaluation value Fce and a deep learning model, provides response measures for different fault types, and generates a real-time feedback report, thereby effectively solving the problems of misjudgment and missed judgment when an existing system processes complex faults.

The application relates to a driving risk identification method based on an automatic timing hyperparameter optimization model, aiming to construct an automatic timing hyperparameter optimization model based on space-time trajectory data to identify driving risk behaviors, reduce training costs and optimize model precision on the basis of an existing model. The method constructs an automatic timing hyperparameter optimization model, builds an automatic machine learning framework based on vehicle space-time trajectory data, realizes automatic optimization of sliding window parameters and model hyperparameters, first synchronizes the phase coupling relationship between multiple feature data based on a dynamic time warping algorithm; second, automatically generates and reduces the dimension of features based on a deep feature synthesis-sliding window algorithm and a t-distributed stochastic neighbor embedding algorithm; finally, automatic model selection and hyperparameter adjustment are realized through Bayesian optimization, and model integration is carried out; the method considers the time sequence characteristics of data in the automatic machine learning framework, realizes the reduction of training costs and the optimization of the precision of the driving risk identification model.

The invention discloses an action recognition method based on graphic guidance selective scanning, which effectively captures a dynamic topological relation by constructing a learnable adjacency matrix, overcomes the limitation that the traditional static topology is difficult to reflect various joint relations when processing complex actions, and improves the accuracy of action recognition in the feature extraction process. A multi-branch structure is adopted to process joint, skeleton and motion features, convolution operation is expanded to a non-Euclidean space through graph convolution to capture a complex spatial relationship in skeleton data, graph-guided state space modeling features are fully utilized by 2D selective scanning, global and local features are comprehensively considered, and the method is suitable for 3D scanning. The performance and the feature extraction accuracy are improved; the application of the multi-scale time convolution enhances the understanding of a complex motion mode, so that the analysis of dynamically changing time series data is more effective.

The invention relates to the technical field of signal detection, in particular to an abnormal radio signal monitoring method and system based on artificial intelligence and big data, and the method comprises the steps: obtaining radio signal data, collected by sensors and receivers in an Internet of Things environment, of each device in real time; the collected radio signal data is preprocessed; extracting abnormal signal features from the preprocessed radio signal data by using a feature engineering technology; training a convolutional neural network model based on the marked historical abnormal signal feature data; deploying the trained convolutional neural network model into a monitoring system, monitoring a radio signal of the Internet of Things equipment in real time, and automatically identifying an abnormal signal; and generating corresponding alarm information according to the severity of the abnormal signal, and sending an alarm notification through a corresponding channel. Therefore, the signal quality can be comprehensively judged according to the characteristics of various radio signals so as to monitor the fault condition, and the accuracy is high.

The application provides a digital prototype lightweight system based on feature extraction and adaptive grid optimization, and relates to the technical field of computers, comprising a model access and preprocessing module and a file analysis unit; the file analysis unit is used for receiving an original digital prototype model, and analyzing geometric topology data and design tree information of the model; a feature collaborative decision unit receives output results of the three units, realizes screening and classification of multi-dimensional features through feature influence weight calculation, and generates a feature mapping diagram containing key feature areas and non-key feature areas; through multi-dimensional collaborative extraction of geometric analysis, topology analysis and semantic analysis, and in combination with weight coefficient calculation of feature comprehensive influence degree determined according to downstream CAE analysis sensitivity, key areas having influences on product performance and assembly precision can be accurately identified, compared with an existing single-dimensional feature extraction scheme, loss of functional key features is avoided, and a basis guarantee for subsequent CAE analysis precision is provided.