1824 results about "Feature selection" patented technology

A method for structuring the latent space of an autoencoder is provided. The method includes analyzing natural language descriptions related to input data; creating language-guided libraries that categorize and abstract data features based on the analyzed descriptions; mapping input data into the categorized and abstracted features within the latent space of the autoencoder; and training the autoencoder to minimize reconstruction loss while adhering to the structure imposed by the language-guided libraries.

The invention discloses a network security analysis early warning system based on artificial intelligence, and the system comprises a data collection layer which captures full flow based on DPI, aggregates firewall logs, terminal behaviors and threat intelligence, and constructs a structured data pool; through TLS fingerprint identification of AI driving, the encrypted traffic is penetrated, and a sampling strategy is dynamically adjusted in combination with reinforcement learning. The intelligent analysis layer is used for carrying out cross validation on known threats and abnormal behaviors; the time sequence CNN extracts encrypted traffic features, and a novel threat detector is rapidly generated by using historical attack fragments in combination with a meta-learning framework; sHAP value driving dynamic feature selection and optimization feature vector input; the decision-making early warning layer is used for fusing multi-source features through a Bayesian network and generating 0-100 score risk scores; a self-adaptive threshold module is combined to adjust a score threshold in real time, and a high-risk event is pushed; the collaborative response layer is used for triggering a preset decision tree, deploying a GAN dynamic honeypot to trap an attacker and reversely tracing; the Neo4j visually restores the attack path, and blocking is executed after the threat is confirmed by a progressive response mechanism.

The invention relates to the technical field of wind power equipment monitoring, and discloses a wind power gear box intelligent fault early warning method and system based on machine learning. The method comprises the steps that multi-source monitoring data such as vibration signals, temperature data and oil analysis data of the wind power gear box are acquired, and multi-scale operation characteristics are extracted through time-frequency conjoint analysis; key fault sensitive features are determined through an adaptive feature selection algorithm, and a dynamic fault feature weight matrix is constructed in combination with a historical fault case library; multi-modal data fusion is adopted to generate an enhanced fault feature set, and modal decomposition is carried out on the enhanced fault feature set to obtain a trend component and a fluctuation component; a fault evolution feature space is constructed by using a deep neural network based on two components, then a fault development mode is identified by using a time sequence mode matching algorithm, and finally a graded early warning signal is generated according to a matching degree with a preset mode, so that fault features can be comprehensively captured, and safe operation of a wind power gear box is ensured.

The invention discloses a method and a system for monitoring the reliability of a photovoltaic converter in a special plateau environment. The method comprises the following steps: firstly, acquiring electrical quantity, temperature quantity, environment quantity and operation quantity, filtering abnormal data, and realizing accurate alignment of multi-frequency signals in combination with a dynamic time warping algorithm; secondly, constructing a plateau sensitive feature set, and optimizing feature quality through physical consistency check and three-stage feature selection; then, an IGBT thermal fatigue equation and a capacitance aging equation are fused to establish a health index evolution model, a Bayesian physical information neural network is used for prediction, and a high-reliability confidence interval is output through Monte Carlo sampling. And finally, dynamically correcting the residual life based on the comprehensive environment factor, and triggering a hierarchical maintenance decision according to the health index state, the residual life and the confidence interval width. The service life prediction precision of the photovoltaic converter in the plateau environment is remarkably improved, the operation and maintenance cost is effectively reduced, and the equipment operation reliability is enhanced.

The invention relates to the crossing field of hydraulic engineering hydrological monitoring technology and machine learning prediction technology, discloses a sediment concentration prediction method based on deep learning, and aims to solve the problems that in existing sediment concentration prediction, hyper-parameter manual tuning is low in efficiency, key feature attention is insufficient, local and time sequence information is difficult to consider by a single model and the like. Accurate prediction is realized through five core modules: a data preprocessing module performs missing value filling, abnormal value processing and derivative feature generation on hydrological data; the feature selection module screens key features based on mutual information; the time sequence construction module generates time sequence data through a sliding window; the hyper-parameter automatic optimization module adopts Bayesian optimization iteration to obtain an optimal hyper-parameter; the CNN-LSTM-attention prediction module fuses CNN local feature extraction, bidirectional LSTM time sequence dependence capture and multi-head self-attention mechanism key feature focusing capability, is suitable for scenes such as river channels and channels, and provides efficient decision support for hydrological regulation and control.

The invention discloses a refractive index structure constant adaptive forecasting method and system based on atmospheric turbulence multi-scale characteristics. The method comprises the following steps: 1, measuring and preprocessing an atmospheric refractive index structure constant; 2, constructing a spatial-temporal feature extraction module of an atmospheric turbulence refractive index structure constant; 3, learning a dependency relationship representing a long-time sequence by using a gating mechanism, and constructing a long-time correlation feature extraction module; 4, capturing dependency relationships of different times through convolution kernels of different time steps, and constructing a short-time correlation feature extraction module; 5, designing a self-adaptive turbulence multi-scale feature fusion module which comprises three groups of bidirectional cross attention modules to realize alignment and fusion among different turbulence feature extraction modules; and introducing a gating mechanism, performing dynamic control and feature selection on output information streams of the three groups of bidirectional cross attention modules, and simulating the change of importance of different scale features of turbulence along with conditions to obtain a predicted value.

The invention discloses a camouflage target detection method based on feature selection attention and frequency domain edge guidance. According to the method, four-level features of a camouflage target image are extracted through a backbone network SMT and are respectively screened; the high-level features are input into a semantic information supplement module, and after semantic features are enhanced, the high-level features and the trunk features are sent into a spatial feature enhancement module together. And inputting the obtained fine-grained features into an edge feature sensing module, and finally fusing multi-scale features through a multi-scale jump connection technology to generate a mask pattern with higher discrimination. The method has the advantages that the network parameter quantity is reduced and key information is reserved through a feature selection mechanism; a spatial feature enhancement module is used for enhancing multi-scale feature representation and remote dependence modeling; the dilution of the semantic context is relieved by means of a semantic supplement module so as to improve the positioning precision; and an edge feature enhancement module is adopted to enhance edge semantic perception and improve boundary integrity. According to the method, the camouflage target detection performance is remarkably improved with relatively low calculation cost.

Some embodiments improve the security of service principals, service accounts, and other application identity accounts by detecting compromise of account credentials. Application identity accounts provide computational services with access to resources, as opposed to human identity accounts which operate on behalf of a particular person. Authentication attempt access data is submitted to a machine learning model which is trained specifically to detect application identity account anomalies. Heuristic rules are applied to the anomaly detection result to reduce false positives, yielding a compromise assessment suitable for access control mechanism usage. Embodiments reflect differences between application identity accounts and human identity accounts, in order to avoid inadvertent service interruptions, improve compromise detection for application identity accounts, and facilitate compromise containment and recovery efforts by focusing on credentials individually. Aspects of familiarity measurement, model feature selection, and a model feature engineering pipeline are also described.

The invention relates to the technical field of industrial data, discloses a mining equipment state monitoring method and system based on the Internet of Things, and effectively solves the problem of insufficient model generalization ability caused by scarcity of fault samples of mining equipment. The virtual sample generation technology expands the available training data volume by 3-5 times, so that the early fault detection rate is improved to 85% or above. The self-adaptive feature selection mechanism reduces the consumption of computing resources by more than 30%, and maintains the integrity of key fault features at the same time. The multi-stage early warning system realizes accurate grading of fault severity, so that the maintenance resource distribution efficiency is improved by about 40%. The closed-loop optimization mechanism enables the model to continuously evolve in the operation process, and the annual false alarm rate is reduced by about 15%. The explainable diagnosis report provides a clear technical basis for field maintenance, and the average troubleshooting time is shortened by about 50%.

The invention discloses a wind power multi-scale decomposition prediction method. At present, single-point prediction is not comprehensive and accurate enough, and cannot adapt to quantitative accurate requirements of a wind power plant and a power grid dispatching mechanism in risk management. The method comprises the following steps of: forming an original wind power sequence from actually acquired wind power data, sequentially performing feature selection and data decomposition processing to form multi-scale modal data, and constructing a depth prediction model according to the multi-scale modal data; a probability prediction interval determination process is completed in the residual error distribution mode depth prediction model through adaptive bandwidth kernel density estimation; after actually obtained wind power data form an original wind power sequence, an initial model is established, feature selection processing is performed on the initial model, that is, weighted marginal contribution is calculated for each feature of the initial model according to all involved feature subsets by using an SHAP algorithm based on a Shapley value in a game theory, and the weighted marginal contribution of each feature of the initial model is calculated; and completing a feature data acquisition process of accurately quantifying interdependence and interaction effect between features.

The invention provides a construction method of a predictive cell senescence model, a method for predicting the senescence state of a tissue sample based on the senescence model, a method for screening potential therapeutic drugs, equipment, a medium and a program product, and relates to the field of intelligent medical treatment. The model construction method comprises the following steps: acquiring a training set sample expression profile data set; identifying a key senescence gene set from the data set by using a feature selection algorithm; inputting the key senescence gene set into a machine learning model to fit a prediction model, and determining an optimal hyper-parameter to obtain a cell senescence model containing the weight of a single gene in the key senescence gene set; the cell senescence model is a senescence score obtained by calculating the sum of the product of the expression quantity of a single gene and the regression coefficient thereof. The cell senescence model, namely PreCSenM, is constructed by integrating a plurality of senescence characteristic gene sets and a gene scoring algorithm, the accuracy in CS evaluation is superior to that of 10 existing methods, and the application of CS from biological research to clinical scenes is also realized.

The invention provides a cognitive ability decline detection method and system based on physiological indexes of wearable equipment, and relates to the technical field of feature selection and machine learning. Comprising the following steps of multi-dimensional physiological data acquisition, data preprocessing and time alignment, cognitive ability state label definition, feature engineering and data balance, cognitive ability decline detection model training and optimization, and output of cognitive ability state prediction. Multi-dimensional physiological indexes and time information of a user are collected in real time through a wearable device, and the physiological indexes comprise heart rate fluctuation features, heart rate statistical features, body temperature features, blood oxygen saturation features, motion data, electroencephalogram state features, skin electrical features, near infrared spectrum features and the like. The wearable device is used for integrating multiple types of physiological signal sensors, and continuous and non-inductive collection of multi-dimensional physiological data such as heart rate variability, electrodermal response and oxyhemoglobin saturation is achieved.

A set of features of a training document are identified in a training document for training a machine learning model. A subset of the features is selected to be omitted from a training forward propagation. As a result of omitting the subset of the set of features, a different subset of the set of features is used to train the machine learning model to classify documents and distinguish between an out-of-domain document and in-domain document.

The invention relates to the technical field of load prediction, and provides a charging load prediction method and system based on comprehensive similarity similar day screening, and the method comprises the steps: carrying out the similarity calculation and normalization of obtained historical load features, meteorological features and context features; by taking a mean value and a standard deviation of minimum fusion similarity scores as a target, solving to obtain a fusion weight of each similarity and then constructing a standard similar day set; calculating day pair features of similarity between meteorological features and context features of a to-be-predicted target day and a candidate day as input, and screening out a most matched similar day identification set through the trained model; and obtaining a load prediction result based on the meteorological features and context features of the target day to be predicted and the screened similar day identification set. Through multi-feature comprehensive similarity calculation and optimized similar day screening, similar day set construction based on multi-dimensional features is realized, and a high-precision input feature selection framework is provided for charging load prediction.

The invention discloses an on-orbit spacecraft attitude estimation method and system based on ISAR image feature selection, and belongs to the field of aerospace control systems. The method comprises the following steps: acquiring an ISAR image of a spacecraft, and acquiring a complex linear structure set and three-dimensional feature points of an on-orbit spacecraft; then, according to the obtained three-dimensional-two-dimensional projection model, the CRLB of each reference structure in the complex linear structure set is deduced to carry out attitude estimation error analysis; calculating the trace of the CRLB covariance matrix of each reference structure to select an optimal feature structure, correcting the scattering point trace of the optimal feature structure by using polynomial fitting, and switching the reference structures as a new optimal feature structure according to the scattering point loss rate and a preset sequence; and optimizing the spacecraft attitude angle solving function by using a particle swarm and LM hybrid algorithm to obtain attitude angle parameters. The target with high-precision target attitude real-time estimation can be completed aiming at the problems that high-order frequency change in a dynamic environment is difficult to capture and resolution and noise suppression are contradictory due to a fixed window time-frequency analysis method.

The invention discloses a method, a system and equipment for predicting the stability of integrated circuit test equipment and a medium, and belongs to the technical field of integrated circuit test. The method comprises the following steps: firstly, carrying out preprocessing and feature selection on historical data in an FT test stage, and adopting a Gaussian mixture model (GMM) to cluster and identify different operation condition clusters of a test machine; then, establishing a health state GMM reference for each working condition cluster, calculating a KL divergence value of a normal sample and the reference, and setting a dynamic anomaly detection threshold by 99.73% quantile of the KL divergence value; and finally, in real-time monitoring, calculating a KL divergence value of real-time data and a corresponding working condition cluster benchmark, and comparing the KL divergence value with a dynamic threshold value to realize accurate anomaly marking. The method effectively solves the problem of abnormal detection of the test data of the integrated circuit under complex and changeable working conditions, and improves the monitoring accuracy and working condition adaptability.

The invention discloses a high-dimensional data feature selection method and system based on a multi-strategy improved whale optimization algorithm, and the method guarantees the uniform distribution of populations through a good point set initialization strategy, and solves a search blind area problem caused by conventional random initialization. A whale optimization and particle swarm optimization double-population cooperation mechanism is adopted, and dynamic balance of global exploration and local development is achieved; and a tangential flight disturbance strategy is introduced, so that the capability of jumping out of local optimum of the algorithm is effectively enhanced. Finally, binary feature selection vectors are output and directly applied to machine learning model training, the classification precision is remarkably improved in the fields of medical diagnosis, image recognition and the like, the calculation complexity is reduced, and an efficient and reliable solution is provided for high-dimensional data feature selection.

The invention provides an unmanned aerial vehicle small target detection method based on an improved YOLOv8 network, and relates to the technical field of visual target detection. In order to solve the problems of insufficient multi-scale feature fusion and poor task collaboration in an existing detection method, the method utilizes a space-to-depth convolution module and a CSP-OKM module in a neck network to realize efficient transmission of multi-scale features and global context sensing, and significantly improves the feature extraction capability of a small target. Cross-task representation optimization is realized through a dynamic alignment detection head, multi-scale feature interactive learning and a dynamic feature selection mechanism, and the detection precision is maintained while the model complexity is reduced. And performing parameter optimization on the network model by using the obtained detection result, and detecting the small target aerial-photographed by the unmanned aerial vehicle.

The invention provides an integrated feature selection method and product based on quantum computing and Bayesian optimization, and relates to the technical field of data processing. According to the embodiment of the invention, an original mathematical integration model is converted into a QUBO model which can be solved by quantum calculation, and the QUBO model is decomposed into a joint optimization discretization step length optimization sub-problem and a parameterization QUBO sub-problem. In a mixed quantum classical optimization algorithm framework, a self-adaptive Q learning model is designed on the upper layer, and proper sub-problems can be dynamically selected in the search process. In the lower layer, a dropout Bayesian optimization algorithm is provided for effectively optimizing the high-dimensional discretization step length in each iteration. A CIM-based quantum computing method is adopted, and a parameterized QUBO sub-problem under the given discretization step length is efficiently solved. According to the method provided by the embodiment of the invention, the feature selection problem can be successfully and efficiently solved, and the selected features of the credit classification problem and the credit classification model for classification based on the selected features can be obtained.

The invention relates to the technical field of user behavior data processing, and discloses a user behavior analysis and personalized recommendation method and system, and the method comprises the steps: collecting multi-dimensional behavior data of a user, and carrying out the feature extraction of the multi-dimensional behavior data; key features are defined based on behavior data, redundant features are reduced through a feature selection algorithm, the dimension of numerical features is unified through normalization processing, and an input feature vector used for a deep learning model is generated; processing the input feature vector by adopting a hybrid deep learning architecture, and generating a user-commodity interaction model in combination with the user behavior sequence and the commodity features; performing real-time prediction on the new user behavior data based on a deep learning model, and dynamically adjusting a recommendation strategy according to a prediction result; and displaying a user behavior analysis result through a visual interface, and continuously optimizing a recommendation strategy in combination with an A / B test framework. According to the method, the defects of a traditional recommendation system in the aspects of multi-source data processing, recommendation individuation and the like are effectively overcome.

The invention provides an intelligent battery sorting method integrating impedance characteristics and deep learning. The method comprises the following steps: acquiring battery impedance data through an electrochemical workstation, drawing an electrochemical impedance spectroscopy (EIS), and extracting impedance characteristics of a medium-frequency region; a 25-dimensional impedance coupling feature space is innovatively constructed, a dual-network differentiated feature selection strategy (IC-GRU) is adopted, a main network selects 12 features with the highest correlation, a boundary expert network selects 10 features with the highest correlation and additionally constructs 5 boundary sensitive features, and finally, the main network selects 12 features with the highest correlation. And establishing an impedance coupling sensing gating circulation unit network to realize accurate prediction of the state of health (SOH). And performing four-stage sorting on the SOH result predicted by the IC-GRU through a random forest algorithm (RF). According to the method, more accurate SOH prediction is realized through deep learning guided by a physical mechanism, the battery pack health state sorting precision and consistency are improved, and an intelligent solution is provided for new energy automobile battery life management.

The invention discloses a multi-channel coal quality online detection system and method based on signal enhancement, belongs to the technical field of coal quality detection, and solves the problem that the accuracy and stability of a detection result are affected as a fixed threshold rule adopted by wavelet threshold denoising in the existing method cannot adapt to noise characteristic changes in different temperature intervals. The method comprises the steps of performing signal enhancement preprocessing on a real-time information set, performing initial feature selection on a signal enhancement set based on an index identification model, and performing index collaborative correction based on a drift risk amount of an initial index set and the initial index set; according to the method, signal enhancement preprocessing is carried out on coal quality multi-channel spectral information and associated environment information which are acquired in real time, interference of environmental factors on spectral signals is considered during signal enhancement preprocessing, and interference of the environmental factors on the signals can be effectively compensated through coupling of a field three-dimensional temperature field and a self-adaptive time period; therefore, the stability and the accuracy of the signal are improved.

The invention discloses a cerebral hemorrhage postoperative gastrointestinal hemorrhage prediction method based on an LGBM model. The method comprises the steps of obtaining a multi-dimensional clinical feature sequence of a target patient, screening out a stable feature subset by adopting a Boruta feature selection algorithm, performing nonlinear relation fitting and integrated decision by utilizing a pre-trained LightGBM machine learning model, and generating an individualized ATH risk probability value; and when the risk probability value exceeds a dynamic risk threshold value, triggering a high-risk early warning signal, and based on a Kaplan-Meier survival analysis model, carrying out association mapping on a prognosis track of poor long-term neural function recovery, and finally generating a comprehensive prediction report. According to the invention, accurate quantitative evaluation of ATH risk is realized, clinical intervention timeliness is improved through a dynamic threshold early warning mechanism, short-term complication risk and long-term function prognosis are organically combined, and a comprehensive and reliable prognosis basis is provided for individualized treatment decision.

The invention relates to the technical field of tunnel construction, and discloses a shield tunneling attitude prediction method and system based on data fusion and deep learning, and the method comprises the following steps: S1, cross-data-source time alignment; s2, missing value processing and anomaly detection; s3, input and output feature selection; s4, feature standardization and sliding window design; s5, establishing and predicting a shield attitude prediction model; according to the method, the average absolute error is reduced by 20%, and the overall prediction accuracy reaches 95%; key parameters such as rolling angle prediction goodness of fit is close to 0.99, the shield head horizontal deviation prediction precision is improved by about 28% compared with LSTM / GRU, high-precision prediction can be kept for parameters with small fluctuation or large change through the synergistic effect of time alignment, feature screening, sufficient excavation attitude, tunneling and vibration data, the model structure is simplified, precision and calculation efficiency are considered, and the method is suitable for field deployment; the attitude deviation can be predicted 6 minutes ahead of time, an operator is assisted to adjust parameters, deviation accumulation is reduced, and construction safety is guaranteed.

The invention discloses an eSIM equipment intelligent network selection method based on environment perception and an AI strategy, and the method comprises the steps: collecting and preprocessing multi-source environment data, and generating a multi-mode original feature vector; constructing a three-dimensional situation tensor, generating a causal structure diagram, clustering to obtain a situation identifier, and embedding a situation; constructing a situation feature table, improving TabNet to perform feature selection, and outputting a high-dimensional situation representation vector; based on the situation characterization and the capability characteristics, performing chain type prediction on the performance and generating an anti-factual income score; constructing short-time domain and long-time domain preferences, generating a comprehensive preference value after fusion, and determining a target connection object; and an eSIM strategy configuration instruction is generated, intelligent network selection switching is carried out, and model parameters are incrementally updated. According to the method, active high-stability intelligent network selection of the eSIM equipment in a complex scene is realized through fusion of multi-source environment perception, causal inference and an AI intelligent strategy.

The invention relates to a lightweight neural network model implementation method and system for small target detection in a complex aerial photography scene, and belongs to the technical field of computer vision and unmanned aerial vehicle target detection. In order to solve the problem of low detection precision caused by small target size, complex background, easy feature submerging and the like in an aerial image of an existing unmanned aerial vehicle, the method comprises the following steps: constructing a multi-scale adaptive hierarchical feature enhancement module MSAHFE, and combining multi-scale pooling and differential edge enhancement to improve feature sensitivity; constructing a lightweight feature selection module LAFS based on an attention mechanism, and screening high-correlation features by using a space and frequency double-domain attention mechanism; a lightweight detection head LWDeect is constructed, and shared packet convolution and self-calibration convolution are utilized to reduce the calculation complexity. The method has the advantages of being high in detection precision, small in parameter quantity, high in reasoning speed and the like, and is suitable for complex aerial photography and other application scenes needing real-time small target detection.

The invention discloses a deep learning-based rock hardness intelligent identification model and method, a DF (data fusion)-improved CNN (Convolutional Neural Network) model provided by the invention still keeps 97.92% stable accuracy under continuous cutting and different working conditions, and the problems of tedious artificial feature extraction engineering and weak model generalization in traditional rock hardness identification are solved. And the problems of insufficient characterization capability and weak model generalization performance of a traditional method are solved. Different from a feature screening process dominated by expert experience in a traditional mode, the method provided by the invention realizes feature adaptive extraction through a multi-channel convolutional neural network, carries out overlapped sampling data enhancement on an original vibration signal, constructs a time-frequency entropy multi-domain fusion graph through short-time Fourier transform, and obtains a time-frequency entropy multi-domain fusion graph; experimental verification shows that the classification accuracy of the multi-channel structure is greatly improved compared with that of a single-channel model, and time-frequency entropy multi-domain fusion is more accurate than that of a single-domain recognition model.

The invention discloses an air conditioner energy consumption adaptive management system and method based on dynamic feature selection, and relates to the technical field of air conditioner energy consumption management, and the method comprises the steps: building a system energy consumption digital twin model as a theoretical optimal energy consumption baseline; operating parameters are collected in real time, and key parameter subsets are screened through working condition recognition and feature importance dynamic evaluation; inputting the key parameters into the model to obtain theoretical energy consumption, and comparing the theoretical energy consumption with a measured value to generate an energy consumption deviation rate; smooth processing is carried out on the deviation ratio sequence, recognition is carried out in combination with a dynamic threshold value and various anomaly detection algorithms, and grading early warning is triggered; the system comprises four core modules, namely a digital twinborn model construction module, a key parameter dynamic screening module, an energy consumption deviation calculation module and a grading early warning triggering module. The method can adapt to different working conditions, accurately capture energy consumption abnormities, and effectively improve the intelligent level and accuracy of energy efficiency management of the air conditioning system.

The invention discloses an anti-fact generation method for processing class imbalance based on a real sample. The method comprises the following steps: preprocessing input data; performing causal feature selection by adopting a causal discovery algorithm; calculating causal feature tendency scores, and performing matching; carrying out anti-fact generation, forming a synthesized minority class set, and integrating the synthesized minority class set with original data to obtain an enhanced data set; and performing data cleaning on the enhanced data set to obtain a balanced data set. According to the method, a data set is effectively balanced by generating a high-quality and close-to-reality anti-fact sample, so that the performance of a downstream classifier on key indexes is remarkably improved; the feature values of the real instances are combined to ensure that the generated samples are located in a reasonable area of data distribution, so that the credibility and availability of the enhanced data are improved; the generated anti-fact sample is located in a boundary region between the majority class and the minority class, the decision region of the minority class is effectively expanded, and the unique post-cleaning avoids the influence of noise accumulation on model training.

The invention discloses a COPD-FE risk prediction method based on disease and symptom combination, and is applied to the technical field of chronic obstructive pulmonary disease risk prediction. Comprising the following steps: acquiring chronic obstructive pulmonary frequent acute exacerbation influence factor data of a patient; the influence factors are screened through LASSO regression and an improved Boruta algorithm respectively; the LASSO independent influence factors and the Boruta independent influence factors are combined in different modes, a Logistic regression model and an XGBoost model are trained, and a plurality of COPD-FE risk prediction models are obtained; and evaluating the performance of all the COPD-FE risk prediction models, and selecting the COPD-FE risk prediction model meeting the requirement to predict the COPD-FE risk. According to the method, clinical data of patients are collected, a risk prediction model is constructed in combination with a feature selection method and machine learning, and an optimal model is screened out through comprehensive evaluation.