121 results about "AdaBoost" patented technology

The invention relates to the technical field of fault prediction, and provides a fault prediction method for a multi-modal cross-attention enhancement graph neural network, and the method comprises the steps: collecting the data of equipment; performing adaptive enhancement and normalization processing on the image data, performing sliding window segmentation, standardization and noise suppression on a time sequence numerical signal, and performing semantic vectorization coding on a maintenance log text; extracting low-dimensional spatial features of image data by using the pruned lightweight convolutional neural network, connecting time sequence features of modeling time sequence numerical signals in series, extracting context semantic expressions of maintenance log texts, integrating the features into multi-modal data, alternately taking each modal feature as Query and the other modal features as Key and Value, and obtaining multi-modal data; calculating attention weight and performing weighted fusion; constructing a modal node weighted graph, and performing inter-node feature propagation through a multi-layer graph attention network; and a residual service life regression prediction module and a degradation level classification module are deployed in parallel, and fault early warning is completed through multi-task joint optimization.

The invention discloses a wind resource assessment report generation method based on a large model technology. The method comprises the following steps: processing multi-source data, and constructing a domain knowledge base and a fine tuning database; field adaptive RAG enhancement is carried out, professional literatures, historical cases and industry specifications in a field knowledge base are retrieved by adopting a retrieval enhancement generation technology, and wind resource assessment contents meeting technical standards are generated through a multi-modal fusion word vector technology; performing large model fine tuning, and optimizing the generative large model through a gradient-free optimization algorithm Wind-DFO on the basis of a fine tuning database by adopting a field self-adaptive fine tuning strategy; and automatically generating a report, arranging and matching multiple templates through an AI workflow, embedding a data visualization chart, executing verification of a grammar layer, a logic layer and a compliance layer, and outputting a standardized wind resource assessment report. The accuracy, specialty and efficiency of report generation are remarkably improved, and the problems that a traditional method depends on artificial experience, the data utilization efficiency is low, and standardization is insufficient are solved.

The invention relates to a water quality prediction method and system based on gating residual enhancement and feature fusion, and belongs to the technical field of water environment intelligent analysis and deep learning. Taking each water quality index as a node of the graph, and constructing two complementary variable relation graph structures by utilizing a Pearson's correlation coefficient and mutual information; respectively inputting the two graph structures into a graph convolutional network, extracting deep dependency features among indexes, and splicing and fusing the deep dependency features. A multi-head attention mechanism is used as a trunk to extract global time dependence, a GRU network is introduced to extract local time sequence features, GRU output is used as an adjustable residual term to be injected into the attention trunk through a residual gating mechanism, self-adaptive enhancement of local dynamic features is achieved, and finally a self-adaptive fusion mechanism is introduced to generate comprehensive representation. According to the method, the complex dependency relationship between the water quality indexes and the time dynamic evolution process can be modeled in a collaborative manner, the response capability to key local change and sudden change events is remarkably enhanced, and the accuracy and robustness of water quality prediction are improved.

The invention discloses a multiband high-voltage power supply control system and a normalization control and protection method thereof, and relates to the technical field of power supply control, and the method comprises the steps: collecting multi-mode signals of S, C and Ku band high-voltage power supply systems and a cooling system; an SDAE deep network and an integrated learning AdaBoost framework are combined to construct a fault diagnosis model, and a fault type and confidence are obtained according to signal features; when a fault occurs, high-voltage output of a corresponding power supply unit is cut off and reported through an isolation interface, and a deep reinforcement learning agent is used for carrying out protection action intelligent decision making; a digital twinborn model of a power supply unit is constructed, an improved grey wolf optimizer is used for multi-task collaborative optimization, optimized system parameters are acquired and issued to a PLC for execution, and waveband output stability is ensured. According to the invention, high reliability, rapid response and intelligent operation and maintenance of the multi-band high-voltage power supply system are realized through deep integration of multi-source signal acquisition, intelligent fault diagnosis, adaptive protection decision and digital twinning optimization.

The invention relates to the field of digital circuit experiment teaching, in particular to a digital circuit experiment platform and method applying a multi-modal large model and a medium, and the method comprises the steps: inputting experiment task description, analyzing and extracting structured semantic information, and forming task representation; retrieving a circuit function block from the electronic component knowledge base, constructing a context enhancement cue word, guiding a multi-modal large language model to generate a Verilog HDL code, and outputting the Verilog HDL code after grammar check and function verification; a Yosys tool is used for carrying out logic synthesis on the codes to generate a standard JSON netlist, and then the standard JSON netlist is converted into an SVG-format circuit diagram through a Netlistsvg tool; and an electronic component knowledge base updating mechanism is constructed to realize knowledge cyclic evolution and adaptive enhancement, so that the intelligent level and practical training efficiency of circuit experiment teaching are remarkably improved.

The invention provides a multi-modal sentiment analysis method and system based on main modal two-stage guidance, and relates to the technical field of sentiment analysis. Inputting the multi-modal data into a multi-modal sentiment analysis model, and extracting language, visual and acoustic features from the multi-modal data through a feature extraction module; semantically decoupling the multi-modal features into modal invariant features and modal unique features through a feature space distribution alignment module, and realizing feature distribution alignment dominated by language modals through alignment reconstruction constraints; performing self-attention modeling on the modal invariant feature through an attention enhancement module to obtain a first enhanced feature, and adaptively enhancing the visual and acoustic unique features through a cross-modal attention mechanism by taking the language unique feature as a dominant feature to obtain a second enhanced feature; the first enhanced feature and the second enhanced feature are fused through the emotion prediction module, an emotion intensity prediction result is obtained through regression prediction, and the accuracy and robustness of emotion analysis in a complex scene are improved.

The embodiment of the invention discloses an authority hierarchical control method based on dynamic desensitization and real-time monitoring and an operation and maintenance bastion host system.According to the embodiment of the invention, by integrating a database firewall and a dual-mode desensitization engine and combining authority hierarchical control and real-time semantic analysis, the data security and operation compliance in an operation and maintenance scene are remarkably improved, and the operation and maintenance security is improved. The dynamic desensitization rewrites a query statement in real time according to a user role, and limits exposure of original data; static desensitization is performed to pre-generate an isolated copy, so that direct access to a production library is reduced; based on semantic analysis and a rule engine, the response time is shortened to be within 1 second; the static desensitization library supports direct use of development and testing, and the permission application process is reduced; a rule base is dynamically updated through an Attention-GRU-Adaboost model, and the adaptability to a novel attack mode is improved.

The invention belongs to the technical field of remote sensing information processing, and particularly relates to a water chlorophyll a concentration inversion-oriented remote sensing time-space-spectrum fusion method, which realizes improvement of spatial resolution of a chlorophyll a concentration inversion sensitive wave band by fusing complementary information of different sensors on time-space-spectrum resolution. The method comprises the following steps of: establishing a water body chlorophyll a concentration inversion-oriented MSI and OLCI space-time spectrum fusion deep learning network, embedding a time sequence dynamic adjustment module, and establishing a water body chlorophyll a concentration inversion-oriented MSI and OLCI space-time spectrum fusion deep learning network for water body chlorophyll a concentration inversion. According to the method, the network can intelligently combine time and space features to generate a more accurate prediction image, an Adaboost machine learning joint inversion model is constructed based on time-space-spectrum fusion data and corresponding limited ground station data, and high-precision remote sensing inversion of the concentration of chlorophyll a is realized.

The invention provides a diffusion-driven channel adaptive point cloud semantic communication method, which belongs to the technical field of wireless communication, and comprises the following steps: obtaining a training point cloud data set, constructing a point cloud feature extraction network based on a hypergraph convolutional neural network as a semantic encoder, and constructing a channel adaptive enhancement module as a channel decoder, a channel adaptive recovery module is constructed at a receiving end as a channel decoder, a diffusion reconstruction network is constructed as a semantic decoder, end-to-end joint training is performed on the point cloud feature extraction network, the channel adaptive enhancement module, the channel adaptive recovery module and the diffusion reconstruction network, the diffusion reconstruction network predicts original point cloud distribution, and the point cloud feature extraction network and the channel adaptive enhancement module are subjected to end-to-end joint training. And a loss function is constructed based on the chamfering distance between the predicted point cloud distribution and the original point cloud. In the communication process, the reconstructed semantic features are input into the diffusion reconstruction network to reconstruct an original point cloud structure. The high-order semantic features of the point cloud can be effectively extracted so as to improve the adaptive capacity of the method to the incomplete point cloud.

The invention relates to the technical field of data processing, and provides an adaptive enhancement staged graph representation learning method based on quotation information, which adopts a data enhancement method and comprises a topological structure level adaptive enhancement method, which comprises the following steps: calculating the centrality of an edge based on a node centrality measurement function, generating a first sampling probability through a truncation probability, and generating a second sampling probability through a truncation probability; taking the first sampling probability as an edge deletion probability, and reserving the topological structure based on the edge deletion probability; the node attribute level adaptive enhancement method comprises the following steps: respectively calculating a corresponding first weight and a corresponding second weight based on discrete node features and continuous node features; and generating a second sampling probability through the truncation probability, taking the second sampling probability as a feature shielding probability, and retaining the feature dimension based on the feature shielding probability. According to the method, topological structure level adaptive enhancement and node attribute level adaptive enhancement are introduced on the basis of the GRLWPT to produce the comparison graph, so that the accuracy in a node classification task and the robustness of an algorithm are improved.

The invention discloses an oil-based drilling fluid performance parameter prediction method, and relates to the technical field of oil-gas field development. According to the method, firstly, multiple training sets are obtained, each training set comprises a drilling fluid formula and temperature which serve as input and drilling fluid performance parameters which serve as output, then the training sets are used for training an Adaboost-BP prediction model, and the trained model can be used for prediction; the Adaboost-BP prediction model takes a three-layer BP neural network as a sub-model, and meanwhile, a feature enhancement-fusion module is arranged on a hidden layer of the sub-model. According to the method, multiple key indexes of the oil-based drilling fluid can be predicted at a time, and compared with a traditional method, the prediction efficiency is improved, and the application range is widened.

The invention discloses a fine-grained feature matching vehicle re-identification method for a license plate shielding scene, and the method comprises a vehicle detection stage based on illumination perception and adaptive prediction, and a fine-grained Transform feature matching stage based on implicit semantic prototype perception. Comprising an illumination sensing module and an adaptive prediction module. The illumination sensing module is used for realizing image adaptive enhancement under different illumination conditions; the adaptive prediction module suppresses a redundant prediction frame through a self-attention weight mechanism; in the fine-grained Transform feature matching stage based on implicit semantic prototype perception, an implicit semantic prototype learning module and a fine-grained Transform matching module are included; the implicit semantic prototype learning module unsupervised decouples vehicle structural components through a group of learnable semantic prototypes to generate a soft semantic distribution diagram; and the fine-grained Transform matching module is used for introducing semantic affinity bias in cross attention. According to the method, the accuracy and stability of vehicle detection and identity matching in a complex environment can be improved.

The invention provides a sintering furnace temperature control method and system based on a BP neural network prediction model, and the method comprises the steps: constructing an initial model of a BP neural network based on Adaboost, and training a prediction model through test data and the initial model; the test data comprises the sintering furnace temperature and power of the test sintering target; and on the basis of the prediction model, according to the sintering temperature curve of the target needing to be sintered, the heating power needed by the sintering furnace is predicted and adjusted in real time. According to the sintering furnace temperature control method and system based on the BP neural network prediction model, the Adaboost-based BP neural network is trained by using the test data to obtain the prediction model, and the heating power required by the sintering furnace is predicted according to the sintering temperature curve of the required sintering target and is adjusted in real time; the heating process of the sintering furnace is more timely and more linear, the anti-interference capability is higher, further, the product stability of sintered products is improved, and the defective rate of the products is reduced.

The invention relates to a two-dimensional code image classification method based on double-domain contrast learning and sample adaptive enhancement, and belongs to the field of semi-supervised image classification. According to the method, a double-domain contrast learning module (Freq-MOCO) is designed. The module carries out comparative learning in parallel in a feature domain and a frequency domain, the feature domain learning mainly focuses on spatial features of images, and the frequency domain learning focuses on spectrum features and global structure information. Besides, a sample adaptive enhancement module (SAA) is also designed, and the learning effect of the samples is further improved by identifying the simple samples and performing more diversified enhancement on the simple samples. The SAA module selects a simple sample by using historical loss information, and applies a richer enhancement strategy to the simple sample, so as to ensure that the sample which cannot effectively promote model learning originally can generate positive influence on model training through diversified enhancement modes. The algorithm provided by the invention has better performance than several recent algorithms.

The invention discloses a credit scoring model modeling method based on transfer learning, and the method comprises the steps: a data collection stage: dividing a sample into a source domain and a target domain, and dividing the sample of the target domain into a training set and a test set; in the data preprocessing stage, special values and abnormal values are removed, initial weights are given to samples, linearization based on the evidence weight (WOE) is carried out on variables, and then variables suitable for model entering are screened according to the distinguishing capacity of the variables for good and bad samples and correlation between the variables; in the model iteration stage, based on the improved migration adaptive enhancement algorithm (TrAdaBoost.R2) aiming at the regression problem as a basic framework, a generalized linear model is adopted as a reference model, and repeated iteration is carried out on the weight and the model; in the iteration stopping stage, whether iteration is stopped or not is judged based on the model loss function and the expression trend of the model loss function on the test set. According to the method, credit scoring model modeling based on small samples is realized, and the speed of model iteration is greatly improved.

The invention relates to a prediction modeling method of a multi-source migration adaptive enhancement network, which comprises the following steps of: source domain modeling: after samples of a multi-source domain and a target domain are respectively subjected to deep migration learning based on confrontation, extracting consistency information of the multi-source domain, and inputting the information into a domain discriminator to distinguish whether data is from the source domain or the target domain; inputting the source domain features into a nonlinear regression device to complete a source domain prediction task; simultaneously training an adversarial-based deep transfer learning network, a domain discriminator and a nonlinear regression device based on a domain discrimination error and a regression prediction error, and stopping training when the domain discriminator cannot correctly divide received data into source domain features or target domain features and the nonlinear regression device can predict source domain data; and target domain prediction: performing prediction by using the prediction network trained by the source domain and inputting new information of the target domain, performing transfer learning on data of each source domain, constructing a multi-source transfer prediction model, and better performing accurate prediction by using low-value density data.

The invention relates to a method for rapidly predicting particle rotation of a cyclone based on data driving, which comprises the following steps of: carrying out CFD numerical simulation through an Euler-Lagrange coupling model, combining PIV (particle image velocimetry) measurement and high-speed camera experiment data, and dynamically fusing multi-source data by adopting Kalman filtering to construct a mixed data set; in the feature engineering stage, thousand-dimensional flow field data are compressed to 50-dimensional through PCA dimension reduction and an auto-encoder, and key physical quantities such as centrifugal acceleration, shear stress and vorticity are weighted and fused. A multi-model collaborative prediction system (BP / XGBoost / CATBoost / RF / AdaBoost / SVM) is innovatively constructed, and algorithm advantage complementation is realized through dynamic weight fusion (error reciprocal distribution + abnormal weight drop). Classified hyper-parameter optimization (Bayesian optimization tree model depth / learning rate, grid search SVM kernel parameters) is adopted, TensorRT quantization (FP16) and ONNX conversion are combined, and the inference speed of embedded deployment reaches 48 ms. And the prediction result drives the PID controller to accurately adjust the inlet flow in real time. And through data-driven modeling and interpretability analysis, an efficient solution is provided for cyclone optimization control.

The present invention discloses a railway accident type prediction method based on KNN and AdaBoost. Specifically, the method involves calculating the sparsity of attributes in a railway accident history data set and deleting some attribute columns based on a sparsity threshold; encoding character data in the railway accident data; using the KNN algorithm to fill missing values ​​in the railway accident data; normalizing the railway accident data and randomly dividing the normalized data into a training set and a test set; constructing a railway accident type prediction classifier using the AdaBoost method, and testing the classifier performance on the test set. The method disclosed in the present invention effectively preprocesses the railway accident data and uses the ensemble learning method AdaBoost to alleviate the class imbalance problem of the original data, thereby improving the performance of accident type prediction.

The application discloses a train axle temperature anomaly recognition method based on a generative adversarial network and ensemble learning, which comprises the following steps: collecting operation data in actual operation of an urban rail train, obtaining a two-class data set with unbalanced categories after preprocessing, and dividing the data set into a training set and a test set; training a constructor and a discriminator of the generative adversarial network by using abnormal data samples in the training set, and realizing automatic network parameter adjustment by using a Bayesian optimization algorithm; synthesizing abnormal samples by using the trained generative adversarial network model, and jointly constructing a training set with balanced categories with the original training set; filtering and screening noise samples by using a cross-committee filtering technology; constructing an axle temperature anomaly recognition classifier by using an AdaBoost method, training the ensemble learning model by using the training set, and inputting the test set to obtain a test result. The application solves the problems of missing of the axle temperature abnormal samples of the urban rail train and data imbalance, and improves the accuracy and correctness of the axle temperature anomaly recognition.

The invention discloses a breeding performance prediction system based on an intelligent sheep breeding platform, and belongs to the technical field of animal husbandry informatization. The intelligent breeding platform is designed, standardized collection, storage and intelligent management of sheep full-life-cycle data are achieved, and a solid data foundation is laid for follow-up research; secondly, innovatively combining ensemble learning (AdaBoost, GBRT and the like), machine learning (SVR, KNN and the like) and a sorting learning algorithm, and constructing a multi-level breeding sheep breeding performance prediction model system; particularly, a subjective and objective combination weighting method based on AHP-PCA is provided, and the prediction precision of the model is remarkably improved through feature reconstruction; in addition, an Achimedes optimization algorithm (AOA) is introduced into the field of breeding prediction for the first time, and adaptive search of hyper-parameters is realized by using a physical simulation mechanism of the AOA, so that the accuracy, efficiency and robustness of the model are remarkably improved.

This invention provides a landslide susceptibility assessment method based on categorical feature enhancement, belonging to the field of landslide prediction. The method includes: preprocessing multi-class data of the landslide disaster research area, deriving the original values ​​of evaluation factors corresponding to landslide points to obtain an original dataset; training a categorical feature enhancement algorithm and performing grid search to obtain a categorical feature enhancement algorithm with optimal parameters; using an adaptive enhancement model as a meta-learner, and using the categorical feature enhancement algorithm with optimal parameters as a base learner for adaptive enhancement ensemble modeling to obtain an ensemble model; substituting the training set into the ensemble model for training simulation, and importing grid points into the trained ensemble model for landslide susceptibility assessment, outputting a landslide susceptibility prediction map. This invention solves the problems of low adaptability of existing machine learning models to complex data and low accuracy in susceptibility assessment.

The application provides an open vocabulary segmentation method and system for multi-modal model representation optimization, and belongs to the technical field of computer vision. Image data to be segmented is acquired; a pre-trained multi-modal model is used to process the acquired image to obtain a segmentation result. The application better optimizes visual-text representation in a multi-modal task, effectively aligns the same visual-text representation space, proposes a mask-sensitive loss to constrain the classification score and mask quality to be consistent in the parameter fine-tuning process, thereby giving the visual encoder local perception ability and improving the effect of the model in the fine-grained downstream task, introduces the original pre-training feature as a representation compensation to ensure the zero-shot ability of the pre-training visual-language model in the optimization process, and interacts the text representation and the visual representation, so that the text representation can be adaptively enhanced for different input images, and the alignment property of the visual-text in the open vocabulary segmentation can be effectively improved.

The invention relates to the technical field of large language models, in particular to a gearbox degradation trend prediction method of multi-head memory LLM under unsteady excitation, which comprises the following steps: performing feature extraction based on a vibration signal to obtain a time-frequency domain feature set; screening out a plurality of degradation sensitive features from the time-frequency domain feature set; performing feature fusion on each degradation sensitive feature to obtain a fused degradation feature; inputting the fused degradation features into a trained multi-head memory large language model, and outputting a degradation trend predicted value; the multi-head memory large language model adopts a multi-head memory attention mechanism to enhance the model feature extraction capability; a dynamic enhancement factor is generated based on the decoding features through an adaptive enhancement normalization layer, and the normalization strength is adjusted in real time to obtain enhanced normalization features; and inputting the enhanced normalized features into a large model detection head to obtain a degradation trend prediction value. According to the method, the gear box degradation trend prediction precision and efficiency can be improved.

The invention discloses a wind and light output prediction method based on particle swarm optimization and LSTM-Adaboost integration. The invention relates to the technical field of new energy power system prediction, and particularly solves the problems that in traditional wind and light output prediction, LSTM hyper-parameters depend on manual adjustment, the generalization ability of a single model is insufficient, and Adaboost integration weight distribution is solidified. LSTM hyper-parameters (a learning rate, a hidden layer node number and a regularization coefficient) are automatically optimized by adopting a particle swarm optimization (PSO), and a training set mean square error (MSE) is taken as a fitness function, so that the problem of low manual parameter adjustment efficiency is solved; a plurality of optimized LSTM models are dynamically integrated based on an Adaboost framework, sample weights are adjusted through an error threshold value (0.01), sub-model weights are distributed according to an exponential function, and the adaptability to time sequence fluctuation is improved; and constructing an LSTM network structure containing a sequence folding layer, and preventing overfitting in combination with a Dropout layer. The whole process is optimized through multi-algorithm collaborative optimization, and the precision of short-term power prediction of the wind-solar power station and the model stability are remarkably improved.

This invention discloses an intelligent management method based on real-time speech recognition and transcription, relating to the field of artificial intelligence technology. The method includes the following steps: Step S1, multimodal audio perception and environmental adaptive enhancement; Step S2, acoustic feature extraction and real-time transcription mapping; Step S3, semantic error correction compensation based on dynamic context weighting; Step S4, structured element extraction and logical association reconstruction; Step S5, intelligent management closed-loop decision-making and task distribution; Step S6, multi-source information backtracking and index construction; Step S7, intelligent management efficiency evaluation. This application can solve the problems of limited recognition accuracy and missing semantic logic under complex sound fields. By improving transcription accuracy through multimodal perception and dynamic semantic compensation, it achieves automated connection from speech recording to structured management decisions, significantly improving office management efficiency.

The present invention discloses a method for predicting the internal leakage level of a valve based on an acoustic emission signal, which solves the problems in the prior art of being unable to automatically extract valve internal leakage features, as well as the problems of low modeling efficiency and low prediction accuracy. The method comprises: first, collecting the acoustic emission signals of the valve under different internal leakage rates, and performing bandpass filtering preprocessing on the original signals. Then, wavelet scattering transform is used to extract features of the valve internal leakage acoustic emission signal, the second-order scattering coefficient is converted into a two-dimensional feature matrix by averaging in the time dimension, and the ReliefF algorithm is used to extract the optimal scattering coefficient feature. The optimal feature subset and pressure are used as inputs of the classification model, and the AdaBoost.M1 method is used for classification modeling. Finally, the trained AdaBoost.M1 model is used to predict the internal leakage level of the unknown valve internal leakage acoustic emission signal. The present invention realizes the automatic extraction of valve internal leakage features and improves the efficiency and prediction accuracy of valve internal leakage acoustic emission signal modeling.

The present application relates to a kind of multi-loop cable group electromagnetic loss intelligent calculation method and device, belong to power cable operation technical field, method includes: with finite element method to establish the cable group electromagnetic field model including multi-loop, current sample is randomly generated and corresponding cable core and metal sleeve loss are calculated, form current-loss sample set;GWO-RBF-Adaboost Intelligent Prediction Model is constructed, the center point of radial basis function neural network RBF, width and output weight are globally optimized by grey wolf optimization algorithm GWO, and the RBF neural network is used as the base learner of Adaboost, and current-loss sample set is used to train to obtain current-loss mapping relationship model;The current data of multi-loop cable group to be evaluated is input into the GWO-RBF-Adaboost model trained, and the cable core loss and metal sleeve loss of each loop are predicted.The present application realizes the convenient calculation of multi-loop cable group electromagnetic loss by current, and significantly improves the calculation precision of electromagnetic loss.

The invention relates to the technical field of bearing fault diagnosis, and discloses a bearing degradation starting point detection method based on an auto-encoder and an AOMM, and the method comprises the steps: collecting a real-time vibration signal of a bearing; obtaining a characteristic sequence of the real-time vibration signal by using an auto-encoder; obtaining a symbolized feature sequence of the real-time vibration signal according to an optimal symbol number obtained by pre-training; obtaining a plurality of sliding windows according to an optimal window size obtained by pre-training; an AOMM method is applied to adaptively adjust the Markov order based on the symbol distribution entropy and the polynomial regression model, and a state stationary probability matrix is obtained; and inputting the state stationary probability matrix and the label data into a pre-trained adaptive enhancement classifier for prediction, and outputting a predicted degradation starting point. According to the method, the degradation starting point is identified more accurately, and the problems that the feature extraction of the degradation starting point is not comprehensive and is greatly influenced by noise, and the detection of the degradation starting point depends on the signal amplitude and neglects the dynamic behavior of the signal are solved.

The invention discloses an adaptive enhanced dynamic graph contrast learning multivariate time sequence classification method, which is oriented to a multivariate time sequence classification task under the condition of few labels, and comprises the following steps: 1) an adaptive enhanced strategy; 2) dynamic graph comparison learning; and 3) carrying out two-stage combined training. According to the method, in a preprocessing stage, trend-periodic decomposition and statistical significance test based on random permutation are combined to judge the strength of time sequence dependence, and an enhanced recommendation strategy matched with data characteristics is generated; and dynamic graph comparison characterization learning and a two-stage training mechanism are introduced, so that the classification performance and the model stability are improved while unlabeled data are fully utilized.

The application discloses a knowledge reasoning path selection and evaluation method, system, device and medium based on reinforcement learning, belongs to the technical field of path selection and evaluation, and comprises the following steps: representing a knowledge graph as a graph structure, adopting a deep reinforcement learning framework; generating node embedding vectors by using graph contrast learning and an adaptive enhancement mechanism; constructing a generation network and a discrimination network to obtain a candidate reasoning path; constructing a multi-objective reward function which fuses a topological connectivity reward and a semantic consistency reward, and performing reinforcement learning; calculating dynamic propagation weights of nodes in a reasoning process by using an information propagation model, and integrating the dynamic propagation weights into node feature representation; and adopting a deep reinforcement learning method to perform end-to-end training on an agent, and outputting a reasoning path and a path evaluation score. The application is suitable for multiple actual reasoning scenes, and provides a technical path for deep knowledge discovery and intelligent decision-making of a large-scale knowledge graph.