1763 results about "Feature engineering" patented technology

The invention provides a construction method of a comprehensive intelligent early warning system for a traumatic patient, and relates to the technical field of medical artificial intelligence, and the method comprises the steps: carrying out the processing of multi-modal data through a feature engineering framework, and extracting multi-scale time sequence features and correlation features; carrying out abnormal state identification and complication risk prediction by adopting a deep learning prediction framework, and carrying out feature fusion through an attention mechanism; constructing a medical knowledge graph to obtain vector representation of domain rule knowledge; and performing integrated verification through a bidirectional mapping mechanism to generate a prediction result. According to the invention, accurate early warning of disease development of the trauma patient can be realized, the early warning accuracy and interpretability are improved, and effective support is provided for clinical decision making.

The invention discloses a power distribution equipment state monitoring system and monitoring method based on the Internet of Things technology, and relates to the technical field of power distribution equipment monitoring, the system comprises the following components: a sound acquisition module, a data transmission module, a data processing center and an early warning display module; by combining the Internet of Things technology, the expert system and the feature engineering technology, high-precision acquisition and analysis of operation sound signals of the power distribution equipment are realized, and by constructing the fault voiceprint feature library, the system can quickly recognize and match equipment fault features, so that early warning is given out at the initial stage of the fault, and the fault early warning efficiency is improved. In addition, due to the application of the cross-equipment associated fault prediction model and the fault propagation prediction model, the system can predict the propagation conditions of cascading faults and system-level faults, more comprehensive fault information is provided for operation and maintenance personnel, prevention measures can be taken in advance, and the fault monitoring accuracy and timeliness are improved. The influence of faults on a power distribution system is reduced.

The invention relates to the field of financial science and technology, and discloses a financial risk dynamic assessment system and method based on artificial intelligence. The system comprises a multi-source heterogeneous data acquisition module which acquires transaction data, public opinion texts and association maps in real time; the adaptive feature engineering module dynamically screens key risk factors; the dynamic risk map construction module calculates a risk conduction coefficient through a map neural network; the multi-modal AI analysis engine cooperatively runs a time sequence prediction model, a text mining model and a graph calculation model; a risk conduction simulator quantifies a systematic risk path. The problems of data splitting processing, model static solidification and correlation risk quantification deficiency in the prior art are solved, the false alarm rate is reduced to 12%, the response speed reaches 90 seconds, the prediction deviation is reduced to 22%, and an interpretable supervision report is generated.

The invention relates to the technical field of distributed resource management and optimization, in particular to a distributed resource life cycle evaluation and dynamic updating method, which comprises the following steps: data acquisition: collecting multi-modal data of distributed resources, including resource state data, use behavior data, environment data and historical maintenance data; feature extraction: carrying out feature engineering processing on the multi-modal data, and extracting key indexes such as a resource health state, a degradation rate and environmental sensitivity; building a life cycle evaluation model, building the model by using the time sequence data of the resources based on a multi-task learning framework, and predicting the health state and the residual life of the resources; and optimizing a dynamic updating strategy, and monitoring and dynamically adjusting in real time. The method provided by the invention overcomes the problems of insufficient life cycle dynamics and rigid updating strategy in a traditional method, has the characteristics of high efficiency, intelligence and accuracy, and is suitable for intelligent management and optimization of new energy equipment, industrial assets and other distributed resources.

The invention relates to the technical field of power equipment operation and maintenance management, in particular to a power equipment asset health management and predictive maintenance service system which comprises a data acquisition and integration module, a feature engineering module, a health assessment and prediction engine maintenance decision and early warning module and a service interface module. The data acquisition and integration module acquires equipment operation parameters through multiple types of sensors, and associates pre-stored equipment asset information to generate an equipment comprehensive data stream; the feature engineering module cleans and standardizes the equipment comprehensive data stream, and constructs a space-time correlation feature matrix; the health assessment and prediction engine comprises a health state assessment unit and a fault prediction unit, the health state assessment unit outputs a health index HI by using a gradient boosting decision tree, and the fault prediction unit outputs a fault probability and a remaining service life RUL in a future preset time period; and the maintenance decision and early warning module generates a grading early warning signal and a maintenance strategy scheme. The intelligent level of operation and maintenance of power equipment is improved, reliable operation of the equipment is guaranteed, and the operation and maintenance cost is reduced.

The invention discloses an ACM data analysis method and a data monitoring system, and belongs to the technical field of aircraft maintenance, and the method comprises the steps: constructing an ACM data set, setting a feature engineering processing method, carrying out coupling feature extraction through setting a dynamic window and calculating a dynamic correlation coefficient, dividing working conditions, eliminating fluctuation interference, and generating a structured time series data set; the method comprises the steps of obtaining ACM reference data of aircrafts of the same model, setting a reference fault judgment method, judging latest data in a structured time sequence data set, screening abnormal parameters, judging whether the ACM breaks down or not by combining an actual temperature adjusting effect, reducing single-parameter misjudgment, setting a coupling fault positioning method, diagnosing the faulty ACM, and distinguishing true faults and false anomalies. Meanwhile, a prediction scheduling method is set, fault prediction, health state prediction and service life evaluation are carried out on the fault-free ACM, the probability of sudden faults is reduced, and non-planned flight stopping is reduced.

The invention relates to the technical field of power equipment state monitoring, in particular to a power equipment operation state evaluation and prediction method based on big data, which comprises a multi-source data acquisition module, a feature engineering processing module, an intelligent evaluation and prediction module and a decision support output module. By setting a multi-source sensing end, when the operation state of the power equipment is evaluated, the definiteness of state evaluation of different types of equipment is ensured by formulating multi-modal data fusion standard parameters and setting different state sensing weights for different types of equipment; and meanwhile, real-time state sensing is performed by fusing electrical parameters, mechanical vibration, thermal distribution and environmental stress data, so that whether a sensing blind area problem caused by a single data dimension occurs in an equipment evaluation process or not can be detected in real time, the comprehensiveness and accuracy of equipment operation state evaluation are ensured, and state sensing fragmentation errors are further reduced.

The invention relates to the technical field of network security, in particular to a network security situation awareness and early warning method based on big data analysis, and the method comprises the following steps: collecting multi-modal security data, and carrying out the noise reduction and normalization processing; constructing a high-dimensional security feature vector by using feature engineering; establishing an anomaly detection model based on physical constraints and a deep residual network; a self-adaptive loss optimization strategy training model is adopted, so that the detection accuracy is improved; through cross-domain transfer learning, model adaptability is optimized, and unknown attacks can be detected; future attack trends are analyzed in combination with historical data, and defense strategies are dynamically adjusted. Through combination of deep learning and big data analysis, the accuracy, real-time performance and adaptive capability of network security situation awareness are improved, unknown attacks and variant attacks can be effectively detected, the false alarm rate is reduced, the security protection capability is enhanced, and the method is suitable for a security defense system in a complex network environment.

The invention relates to an intelligent delivery decision-making method and system based on multi-dimensional index association, and the method comprises the following steps: S1, collecting user, advertisement and context multi-dimensional data, and carrying out the preprocessing of the data to generate standardized features; s2, performing fusion calculation on the multi-dimensional standardized features, extracting key features, and constructing and generating a user-advertisement-context joint feature set; s3, constructing a multi-task prediction model, and training according to a user-advertisement-context joint feature set; s4, according to a prediction result and real-time features of the trained multi-task prediction model, rapidly matching an optimal advertisement for a given user in a real-time bidding process; and S5, performing causal analysis according to the exposure / click log of the optimal advertisement, verifying the real effect of the advertisement, correcting the index, and feeding back to the feature engineering in the S2 and the model training step in the S3 according to the corrected index. According to the invention, the advertisement putting efficiency and effect are effectively improved.

The invention relates to a bank marketing model construction method and system based on machine learning, and the method comprises the following steps: constructing a customer multi-dimensional feature engineering system which is used for integrating customer multi-dimensional features, and extracting customer behavior period features through employing a time sequence feature coding technology; meanwhile, a graph neural network is adopted to construct customer social influence features; constructing a dynamic customer value analysis model integrated with XGBoost and establishing a dynamic attenuation function of customer life cycle value; establishing a marketing response prediction rate model of a hybrid model architecture combining LightGBM and Transform, and embedding an adversarial training sample generation mechanism; a marketing strategy generation model is constructed, the marketing strategy generation model is based on a multi-objective optimization function considering the marketing response rate, the marketing cost and the customer satisfaction, and a marketing strategy is generated through a marketing path planning algorithm of Monte Carlo tree search and the multi-objective optimization function.

The invention relates to the technical field of coal mine safety, in particular to a coal mine water disaster prediction system based on a data analysis and machine learning technology, which comprises a multi-source data acquisition module, a dynamic data preprocessing module, a multi-modal feature engineering module, an integrated prediction model construction module and a prediction optimization control module, the multi-source data acquisition module fuses geological and hydrological data, micro-seismic data and equipment working condition data, the dynamic data preprocessing module constructs a noise feature library and realizes noise elimination and data standardization, and the multi-modal feature engineering module extracts dynamic causal feature vectors of a water diversion coefficient change rate and a micro-seismic energy release rate based on convergence cross mapping; the integrated prediction model construction module fuses and outputs a water disaster risk probability value through a meta-learner; and the prediction optimization control module triggers a sampling rate adjustment and disaster response linkage mechanism according to the risk probability value. The method has the advantages of high reliability, high adaptability and timely response, and is suitable for real-time prediction of water disasters in a complex coal mine environment.

The invention relates to a spinel multi-objective reverse design method based on machine learning and a Bayesian optimization algorithm, electronic equipment and a storage medium, and the design method comprises the steps: firstly extracting related data of a spinel material from a database, and constructing a balanced data set through preprocessing; feature engineering is carried out, a comprehensive feature set is constructed, and key features are reserved; then training a multi-target prediction model through hyper-parameter optimization by using a multi-task gradient elevator model; and finally, integrating to a Bayesian reverse design framework, expanding a design space through a specific encoder, and combining a Gaussian process proxy function and an expected hyper-volume improvement criterion to screen candidate materials meeting conditions and verify performance, thereby completing reverse design optimization. Compared with the prior art, the intelligent and efficient spinel novel multi-target reverse design method can be used for solving the problem of data scarcity, and development of high-performance spinel solar cell materials is accelerated.

The invention discloses an interpretable machine learning genome prediction method and device, belongs to the technical field of combination of biological breeding, biological information and machine learning, and utilizes an advanced machine learning algorithm to perform parameter optimization in combination with biological prior information. Through processing of multi-source data (genome, transcriptome and epigenetic data), dynamic feature engineering (PCA and PHATE dimensionality reduction) and organic combination of various machine learning models, and an automatic parameter adjustment framework based on a grid search and sparrow search algorithm, genome prediction precision and calculation efficiency are significantly improved; meanwhile, the interpretability of the model is realized based on the SHAP value, the SNP site contribution is quantified, a reference is provided for precise breeding, and the method is suitable for animal and plant molecular breeding and medical genetic analysis, and can accelerate genetic analysis of high-value characters, assist precise breeding decision and disease risk prediction, and promote leap-forward development from experience breeding to intelligent breeding.

The invention discloses a fire risk accurate prediction method and system based on a multi-source data fusion knowledge graph, and belongs to the technical field of machine learning, and the method comprises the following steps: accessing a multi-source heterogeneous data set, integrating sensor data, geographic information, historical data and external data, and obtaining a multi-source heterogeneous data set; a full-size forest three-dimensional model is constructed by means of FDS and SolidWorks, combustion simulation is carried out, environmental parameters are set carefully to ensure that the result is accurate, and a foundation is laid for construction of a multi-source heterogeneous data set; the method comprises the steps of data acquisition, data preprocessing, noise data cleaning, space-time alignment and feature engineering, multi-source heterogeneous data acquisition and preprocessing are carried out, and forest fire related data covering structured, semi-structured and non-structured types are acquired from a multi-source heterogeneous data set. The accuracy and timeliness of fire early warning are remarkably improved, effective fusion of forest fire multi-source heterogeneous data can be achieved, and transparency and traceability in the data fusion process are ensured.

The invention discloses an employment information matching method and system based on data analysis, and particularly relates to the field of employment matching, and the method comprises the steps: collecting structured and unstructured data, and carrying out the semantic feature extraction through employing a BERT model and BiLSTM-CRF; in the preprocessing stage, entity standardization is realized through a knowledge graph, and a job seeker portrait and post model including a skill matrix and an occupational development trajectory is constructed; in the feature engineering stage, extracting four core features of skill matching degree, salary expectation integrating degree, commuting tolerance and occupational development goodness of fit; the salary integrating degree is quantitatively evaluated through a bidirectional tolerance model, a random forest model with time decay is used for dynamic weight, feature weight is generated based on historical successful cases, and a real-time feedback mechanism is introduced to adjust a weight coefficient; finally, the matching degree function fuses the weighted features and the industry trend factors, and the model is continuously optimized through a three-level updating mechanism.

The invention discloses a progress management system and method for electric power engineering, and belongs to the field of electric power construction engineering, and the system comprises a data collection module which is used for obtaining real-time sensor data, construction log data and external data of a construction site; the feature engineering module is used for integrating the multi-source data of the data acquisition module based on a spatial-temporal feature fusion engine and constructing an enhanced feature matrix; the model processing module is used for outputting a progress deviation and an equipment fault probability based on the PhaseAware LSTM network; key features are selected according to the construction stage, structured prediction is carried out based on a random forest, and a progress deviation rate prediction value and a risk factor evaluation result are output; and the dynamic weight fusion module is used for dynamically distributing model weights based on the prediction results of the random forest and the LSTM, the real-time equipment state and the environment parameters, and generating a fused progress prediction value. According to the invention, high-precision progress prediction and risk early warning can be output.

The invention provides a multi-modal education evaluation system and method based on super-automation and federal cognitive calculation, and the system integrates multi-source heterogeneous data collection, a federal cognitive calculation engine, an automatic evaluation workflow engine and a privacy enhanced data processing architecture. And comprehensive acquisition, efficient processing, accurate evaluation and safety protection of education data are realized. Through the LSTM-Bayesian hybrid model of dynamic parameter adjustment, intelligent feature engineering, interpretability analysis, reinforcement learning strategy optimization and other technologies, the system can generate personalized learning path planning and an adaptive teaching intervention scheme, and the teaching effect and learning efficiency are improved. And meanwhile, the security and privacy of the education data are ensured by adopting privacy protection technologies such as differential privacy and homomorphic encryption.

The invention discloses a transformer current rising test data analysis method based on deep learning, and relates to the technical field of power transformation equipment, and the method comprises the following steps: S1, data collection and preprocessing; s2, performing feature engineering; s3, dividing a data set; s4, model selection and architecture design; s5, model training; s6, performing model verification and hyper-parameter tuning; s7, testing and evaluating the model; s8, performing anomaly detection and adaptive learning; s9, result interpretation and model interpretability; and S10, continuously monitoring and updating the model. According to the transformer current rising test data analysis method based on deep learning, based on deep learning, in combination with technologies of feature engineering, model selection and architecture design, anomaly detection and adaptive learning and the like, the accuracy and robustness of a transformer current rising test are improved through comprehensive data analysis; the generalization ability of the model for unseen data can be improved, and the model can adapt to environmental changes in real time.

The invention relates to the technical field of intelligent power grid and household energy management, and provides a household ultra-short-term load prediction method, which comprises the following steps of: performing preprocessing and characteristic engineering processing on user power consumption data acquired by an intelligent electric meter; user type clusters are obtained through clustering analysis, and a standard user power consumption mode corresponding to each cluster is determined; constructing a deep learning prediction model based on the mode, and generating a model parameter matrix sequence and a timestamp; generating an ultra-short-term load prediction value by using the parameter matrix and historical data, and forming a prediction load curve according to a timestamp; and finally, the prediction curve and the management suggestion are sent to the household energy management terminal. According to the method, accurate prediction is realized through data cleaning, user grouping, pattern matching and deep learning modeling, and a visual result and an energy-saving suggestion are output. According to the invention, the household energy management efficiency and the power utilization economy can be improved.

The invention relates to the technical field of medical emergency monitoring, in particular to an ICU emergency response system which comprises a preliminary risk assessment module, an emergency recognition module, a treatment scheme optimization module, a vital sign monitoring module, an emergency response coordination module, a disease evolution prediction module, a resource allocation management module and a medical decision support module. According to the method, feature engineering and logistic regression analysis are combined with medical history and real-time vital signs of a patient, emergency medical events are recognized by applying pattern recognition and natural language processing, a treatment scheme is optimized by using a support vector machine and a decision tree, personalized treatment suggestions are provided, and the time sequence and a biometric method are used for finely monitoring the vital signs; health risks are early warned, resources are reasonably allocated in emergency response through a resource scheduling algorithm and a priority queue, illness state prediction is assisted through machine learning and probability statistics, resource utilization is improved through linear programming and a resource optimization strategy, and waste is reduced.

The invention discloses a wind driven generator anomaly detection method and system based on SCADA periodic data. The method comprises the steps of obtaining operation data collected by an SCADA system of a wind driven generator in actual operation; according to the method, a normal data set is constructed besides the abnormal data of SCADA alarm, and the abnormal data collected by an SCADA system comprises a periodic type, a stable type and an irregular fluctuation type; performing preliminary labeling on three types of data in the abnormal data; performing data pattern recognition on the obtained data by using a neural network model to recognize periodic data; performing feature engineering processing on the data of which the output result is periodic, and extracting corresponding data features; enhancing the features in a mode of calculating abnormal scores by using an isolated forest; and performing anomaly classification on the feature vectors formed in the time window by using a machine learning model, and detecting abnormal data in the periodic data. According to the method, the accuracy of abnormal data detection of the wind driven generator can be improved.

The invention discloses a water ecological environment decision response intelligent interaction system based on AI natural language processing, and the system carries out the data collection and preprocessing, and forms a training set. In combination with the training set, data annotation and feature engineering are carried out, and AI model training including data segmentation, a training method and transfer learning is further carried out; on the basis, continuously collecting monitoring data, and inputting the monitoring data into the trained AI model for real-time prediction; data analysis and decision support are carried out; and once an abnormal trend is detected, an early warning mechanism is triggered. Through an AI large model technology in the vertical field, big data and an artificial intelligence algorithm are utilized to simulate and improve intelligence, convenience and precision of water ecological environment supervision, through combination of an AI large model and an intelligent voice interaction technology, based on analysis and processing capability of the AI large model, deep analysis is performed on water ecological environment data, and a water ecological environment monitoring result is obtained. And managers are helped to quickly make scientific decisions.

The invention discloses a fault determination method and device for a micro-service system, a product and electronic equipment. Relates to the technical field of artificial intelligence. The method comprises the following steps: determining an abnormal event flow according to abnormal monitoring information; an abnormal event causal graph is determined based on an abnormal event flow, and then a fault point, a fault chain and a fault classification are determined by utilizing an intelligent agent driven by a pre-training model and combining the event causal graph and a fault mode standard. According to the method, anomaly detection, fault classification and root cause positioning of the micro-service system are realized, and closed-loop diagnosis from anomaly discovery to root cause positioning is realized; secondly, performing depth feature engineering and semantic abstraction on the refined data from the perspective of events and causal relationships, fusing system behaviors and dependency relationships dispersed in different modal data into a unified event causal graph through a graph modeling technology, and providing comprehensive and high-dimensional input for fault reasoning of an intelligent agent; and the accuracy of micro-service fault determination is improved.

The invention belongs to the technical field of high-performance composite materials, and discloses a carbon fiber reinforced thermoplastic composite material performance database, a construction method and application thereof, and the method comprises the following steps: S1, database structure construction; s2, experimental sample collection and data standardization; s3, feature engineering and variable reduction; s4, training a machine learning model; s5, constructing and verifying an adaptive model; and S6, data expansion and feedback optimization. According to the method, material performance prediction and formula parameter reverse design under target performance are realized through systematic acquisition and normalization processing of three types of data of material components, preparation process and performance characterization and building of a nonlinear mapping model among a material structure, a process and performance through a machine learning method. The database can be used for intelligently recommending a high-performance composite material combination scheme, is suitable for rapid screening and customized development of various thermoplastic composite materials, effectively reduces the research and development cost and development cycle, and improves the material design efficiency.

The invention relates to the technical field of network flow detection, in particular to a real-time network flow anomaly detection method based on deep learning, and the system comprises the following steps: S1, carrying out the real-time collection and preprocessing of multi-modal data; s2, performing dynamic feature engineering and sliding window statistics; s3, carrying out online adaptive threshold initialization; s4, multi-modal deep learning model reasoning is carried out; s5, updating the adaptive threshold in real time; s6, abnormal decision making and confidence coefficient calibration; s7, generating interpretability analysis; and S8, performing real-time feedback and online learning. According to the scheme, the capability of detecting hidden and complex attacks is remarkably improved through multi-modal data fusion and dynamic feature engineering, network traffic, system logs, user behavior data and external threat intelligence are synchronously collected, and traffic statistical features, time sequence change features, frequency domain features and distribution features are extracted in real time by using a sliding window mechanism.

A data-centric system for analyzing agricultural crops, consisting of: a data acquisition module configured to capture images of agricultural fields using cameras, unmanned aerial vehicles (UAVs) or sensors, with the sensors collecting data on soil moisture, temperature, light, humidity and pH; a data preprocessing module configured to: resize the acquired images to a standardized dimension suitable for input to a deep learning model; apply noise reduction using a Gaussian filter; improve image contrast through histogram equalization; and perform image magnification through rotation, reflection, and scaling transformations; a feature engineering module configured to extract the following features: color features, which include color histograms, mean, and standard deviation of color channels; texture features using Gray-Level Co-occurrence Matrix (GLCM) properties, which include contrast, dissimilarity, homogeneity, energy, angular moment (ASM), and correlation; shape features, which include contour area, perimeter, aspect ratio, and roundness; and other features, which include the green pixel ratio and edge density; a classification module configured to: implement deep learning-based classification models selected from the group consisting of Support Vector Machine (SVM), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), ResNet18, Random Forest (RF), SegNet, VGGNet, Naive Bayes (NBG), Decision Tree (DT), K-Nearest Neighbors (KNN), and DeepLab; detecting and classifying weed species in the images of agricultural fields; and diagnosing plant diseases based on the features extracted from the images of agricultural fields; an output module comprises a user interface configured to display the classification and recognition results; and a recommendation module configured to suggest treatment solutions for diagnosed plant diseases through the output module's user interface.

The invention relates to an offshore wind power prediction method, and aims to improve the accuracy and reliability of prediction. The method comprises the following steps: (1) a data preprocessing stage: detecting an abnormal value in data by using a DBSCAN clustering algorithm, reconstructing the abnormal value by using a KNN interpolation method, detecting time sequence abnormity through an LSTM automatic encoder, and performing regression reconstruction by using LSTM to ensure the retention of time sequence features; (2) a feature engineering stage: screening out key features through correlation analysis, generating a label column through K-means clustering and wind direction classification, and extracting features such as wind direction change rate, time periodicity and wind speed interaction; and (3) a model construction stage: constructing a composite model in combination with multi-scale convolution (Inception), a bidirectional long short-term memory neural network (BiLSTM) and a multi-head self-attention mechanism, extracting local features through a convolution layer, capturing a time dependency relationship through a bidirectional LSTM layer, enhancing the attention of key features by using the multi-head self-attention mechanism, and finally realizing high-precision wind power prediction.

The invention provides an intelligent comprehensive system and method for steel production process parameter optimization, and the system comprises a data configuration module which is used for collecting quality-related data in a steel production process; the influence factor analysis module is used for processing data related to quality by using a feature engineering technology and identifying key variables; the quality index prediction module is used for constructing a quality prediction model by using a machine learning algorithm and key variables; the process parameter optimization module is used for constructing a process parameter optimization model based on the prediction result and the quality index control target, and analyzing and recommending an optimal process parameter control range by utilizing an intelligent algorithm; and the model monitoring optimization module is used for evaluating and optimizing the operation effects of the quality prediction model and the process parameter optimization model in real time. According to the method, the whole-process intelligent management from data configuration and key factor identification to quality prediction, process parameter optimization and model dynamic monitoring is realized, a closed-loop optimization mechanism is formed, and the production efficiency and the product quality are effectively improved.

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 underground cavern surrounding rock displacement prediction, in particular to a high-stress large underground cavern group surrounding rock displacement prediction method. According to the technical scheme, the method comprises the following steps that data collection and arrangement are carried out, and various types of sensors are arranged at different parts of a high-stress large underground cavern group to collect data; the method comprises the following steps: performing preliminary screening, cleaning and normalization processing on collected data, performing feature engineering and data enhancement work, including time-frequency domain feature extraction, wavelet transform-based data decomposition and reconstruction and a data enhancement strategy, and constructing a hybrid neural network model fusing a convolutional neural network and a gating circulation unit. Through multi-source accurate data acquisition and processing, depth feature engineering, hybrid neural network construction training and scientific evaluation and early warning, the accuracy, reliability and timeliness of high-stress large underground cavern group surrounding rock displacement prediction are remarkably improved, powerful support is provided for engineering safety guarantee, and risks and losses are effectively reduced.