20 results about "Concept drift" patented technology

Approaches herein relate to model decay of an anomaly detector due to concept drift. Herein are machine learning techniques for dynamically self-tuning an anomaly score threshold. In an embodiment in a production environment, a computer receives an item in a stream of items. A machine learning (ML) model hosted by the computer infers by calculation an anomaly score for the item. Whether the item is anomalous or not is decided based on the anomaly score and an adaptive anomaly threshold that dynamically fluctuates. A moving standard deviation of anomaly scores is adjusted based on a moving average of anomaly scores. The moving average of anomaly scores is then adjusted based on the anomaly score. The adaptive anomaly threshold is then adjusted based on the moving average of anomaly scores and the moving standard deviation of anomaly scores.

This invention discloses a method and system for identifying encrypted traffic based on spatiotemporal features and semantic alignment. The method first extracts the spatial and temporal feature sequences of the network flow, and uses a byte-pair encoding algorithm to convert the spatial packet length into discrete symbols. Then, the discrete symbols and temporal features are mapped to a high-dimensional space and fused together. A global spatiotemporal feature vector is extracted through a network using a concatenated one-dimensional convolution and multi-head self-attention mechanism. Next, the text semantic bullseye matrix of fine-grained behaviors of various known applications is obtained offline from a large language model. Finally, the similarity between the spatiotemporal features and the text bullseye is calculated, and a multi-instance learning max-pooling mechanism is introduced for dynamic routing. Based on this, a contrastive learning loss function optimization model is constructed or cross-modal inference is performed. This invention completely overcomes the conceptual drift problem caused by changes in encrypted features, achieving extremely high generalization accuracy and feature interpretability across generations.

The application discloses a stream data self-adaptive classification method and system based on artificial intelligence, relates to the technical field of artificial intelligence and machine learning, and comprises the following steps: acquiring stream input data and a classification model of a current time step; using the model to obtain a relative position feature representing a decision boundary and to calculate an instantaneous gradient vector; updating the feature to a feature sequence, determining a target update resistance threshold based on the distribution discrete degree of the feature in the time sequence dimension; attenuating a historical accumulated gradient vector and superimposing the instantaneous gradient vector to obtain a target accumulated gradient vector; then judging whether the length of the vector is greater than the resistance threshold; if not, keeping the model parameters unchanged and retaining the accumulated gradient to the next time step; if yes, updating the classification model parameters based on the difference and resetting the target accumulated gradient vector; and the application effectively removes transient random interference and real concept drift, and breaks the noise resistance and sensitivity bottleneck.

The application discloses a cloud-edge collaborative and federated learning-based electroencephalogram prediction model self-evolution system and method. The system comprises an edge device and a cloud server cluster: the edge device collects physiological signals of a user and runs a first machine learning model, and uploads desensitized data of a marked event asynchronously; the cloud server performs continuous wavelet transform on received one-dimensional electroencephalogram signals to generate two-dimensional time-frequency images, trains a second deep learning model by using the images, generates updated weights, and completes silent updating by issuing the updated weights to the edge device. The application solves the model concept drift problem through a cloud-edge collaborative architecture, realizes continuous evolution of a prediction model, improves feature extraction depth and generalization ability through time-frequency conversion and a multi-specialist sub-network architecture, and effectively protects user privacy through a data desensitization and asynchronous uploading mechanism.

The present application provides an electroencephalogram sound stimulation evaluation prediction and adaptive output method and system, which is based on an individual-group bidirectional migration collaborative mechanism of shared feature space and distribution alignment constraint to fuse individual specificity and group commonality knowledge, forming a mechanism to overcome the individual differences of electroencephalogram; the method also uses an adaptive decision fusion mechanism based on prediction uncertainty evaluation to ensure output stability when the prediction model reliability fluctuates, and a model dynamic online updating mechanism based on concept drift detection to adapt the prediction model to the long-term changes of the user state, forming a mechanism to improve accuracy and robustness; the present application can effectively overcome the individual differences of electroencephalogram, realize high-precision system prediction and output, and has robustness.

The application discloses an unknown threat identification method based on adaptive snapshot integration, which is applied to instant fine classification of network encrypted traffic and can identify unknown threats caused by concept drift. The method comprises an encrypted traffic preprocessing and feature extraction module, an encrypted traffic time sequence feature neural network classification module, a new category traffic discrimination module, a snapshot integration module and a transfer learning module. The method can cope with increasing unknown abnormal traffic, give unknown abnormal traffic clustering results for experts to mark, effectively solve the concept drift and category imbalance problem, and thus guarantee the reliability of abnormal traffic detection.

The application discloses a kind of prediction and abnormality detection algorithm and application for time series data, belong to time series data abnormality detection technical field, comprising: the original time series data of input is preprocessed, and the standardized sample segment is generated;Multi-scale feature fusion time series prediction model is constructed and trained;Using the trained time series prediction model, the standardized sample segment is multi-step forward prediction, and the predicted sequence is obtained;Based on the predicted sequence and the corresponding actual observation sequence, dynamic residual threshold is calculated, and real-time abnormality detection and marking are carried out according to the threshold.The application solves the problem that the existing complex space-time correlation feature is not sufficient, cannot dynamically adapt to data change and model cross-scene migration and online learning ability is weak.The application fully captures complex nonlinear space-time correlation features, improves the adaptability of abnormality detection to data nonstationarity and concept drift, realizes online self-adaptation and threshold drift tracking, and improves the practicability and long-term robustness of the algorithm.

This invention belongs to the field of data mining and machine learning, specifically a data stream concept drift learning method and apparatus that integrates adaptive sample selection. It includes: S1: Standardizing and relabeling the streaming data, and calculating corresponding weights based on the number of samples in each category; S2: Real-time monitoring of changes in the distribution of the streaming data and determining the type of data drift; S3: Constructing a neural network model for feature learning and classification prediction; S4: Dynamically adjusting the selection threshold according to the data drift type to filter samples and extracting high-confidence samples to expand the training set; S5: Using the expanded and optimized final training sample set, continuously training and updating the neural network model based on a dynamic class-weighted loss function, and using the weights calculated in S1, applying a weighted penalty mechanism to impose a greater penalty on misclassification of minority class samples during training.

The application discloses a kind of light-weight federated learning threat detection methods under industrial control scene, each industrial control node local acquisition multi-source heterogeneous data, after pre-processing, light-weight feature extraction and dimension compression are carried out, Laplace noise is introduced to realize differential privacy protection, each node trains and carries out model compression simplified convolutional neural network, reduce communication cost by gradient sparsification and accumulation mechanism;Three-layer federated learning architecture is constructed, adaptive weight calculation method is designed, parameter alignment and knowledge distillation are used to realize heterogeneous model fusion, introduce Byzantine fault-tolerant algorithm to filter outlier gradient, use model difference coding and two-level cache architecture to reduce model distribution overhead, trigger incremental learning by sliding window monitoring concept drift, combined with elastic weight, consolidate and keep old task accuracy, establish decentralized threat intelligence sharing and multi-node collaborative response mechanism;The application systematically solves the key technical problems of federated learning threat detection in resource-constrained industrial control environment.

The application relates to a power grid load intelligent prediction scheduling method, device, equipment and medium. The method comprises the following steps: performing short-time Fourier transform on historical load data of a power grid to obtain a frequency spectrum feature vector; based on the frequency spectrum feature vector and current context information, a routing attention weight is calculated, and an adaptive learning rate multiplier and a forgetting gate threshold are generated based on concept drift significance; based on a minimum loss function, a prediction model is trained through a training sample, the adaptive learning rate multiplier and the forgetting gate threshold, so that an adaptive prediction model is obtained; historical time series data and future condition data are input into the adaptive prediction model, so that a final load point prediction and a prediction uncertainty interval are obtained; based on the final load point prediction, the prediction uncertainty interval and the routing attention weight, a scheduling optimization model is updated to generate unit combination and output planning of a target future period. The method can improve the stability and accuracy of load prediction in a variable environment.

The application discloses a kind of based on depth condition generation replay's continuous learning soft measurement method, comprising: the historical time series data of industrial process is collected, historical dataset is constructed, to obtain preprocessed dataset;According to StreamKM++ streaming clustering algorithm, the preprocessed dataset is clustered, obtains C cluster;For each cluster, introduce the working condition identification c j Of one-hot coding, build working condition dataset;Using working condition dataset, the prediction model is trained, and the trained prediction model is obtained;Using working condition dataset, the depth condition generation model is trained, and the trained generation model is obtained;Set data buffer, for receiving the preprocessed data sample in online data stream, each data sample includes process variable;Real-time monitoring data buffer, judge whether the data sample stored in data buffer meets condition A or meets condition B;When any condition is met, trigger adaptive mechanism, realize quality variable prediction under continuous learning.The method effectively solves the problem that existing soft measurement model is difficult to overcome concept drift and catastrophic forgetting simultaneously in dynamic industrial environment, improves the adaptive ability and long-term prediction accuracy of model.

This invention relates to the field of power grid information security technology, specifically a method, system, device, and storage medium for detecting malicious software in the power grid Internet of Things (IoT) based on active learning. The method involves acquiring application samples from power grid IoT nodes, extracting static features, dynamic features, and power grid context information to form a multi-dimensional feature vector, and organizing these into data blocks according to timestamps. Classification uncertainty scores are calculated from an unlabeled sample pool, a detector committee is constructed to calculate consensus entropy, and the sample with the most information content is selected by combining the two scores and submitted for expert annotation. A random forest classifier is trained to build a detection model. The F1 score of the current data block is evaluated; annotation stops when a preset threshold is reached and is applied to the next data block. Model performance changes are monitored, and when performance degradation is detected, batch retraining, rolling back historical configurations, or incremental updates are performed based on the evolution of the threat environment. The method reduces annotation costs through sample selection and addresses the conceptual drift problem of the power grid threat environment through an adaptive update strategy.

This invention relates to the field of power grid engineering cost management and industrial data analysis technology, specifically a power grid technical upgrade pricing system based on industrial data analysis. The system includes: an industrial data acquisition module, which synchronously acquires project type, timestamp, BIM structure data, IoT device status time-series data, and financial text data; a data modality alignment module, which performs cross-modal feature alignment and joint representation; a concept drift perception module, which monitors changes in feature distribution and quantifies the decay of pricing rules; a topology reconfiguration decision module, which, in conjunction with audit compliance logic, determines whether to generate a pricing topology reconfiguration instruction; a dynamic compensation generation module, which generates pricing compensation parameters and calculation logic paths and updates the pricing topology structure; an adaptive evolution module, which evaluates the interpretability index of dynamic compensation and identifies the model evolution state; and a pricing execution and output module, which outputs the final pricing result and cost list. This invention achieves dynamic, adaptive, and auditable pricing calculation for power grid technical upgrade projects.

The application discloses a test-time adaptive fine ash content prediction method for latent space concept drift evaluation, and belongs to the technical field of computers. The application aims to improve the generalization ability and robustness of an artificial intelligence model under non-stationary conditions of heavy medium coal preparation. The application constructs a sample-offset sample pair modeling mechanism driven by time shift, designs a double-input latent space representation network with LSTNet as the backbone, and realizes direct estimation of the dynamic offset of fine ash content based on the difference between the representations of two time points. The application fuses target offset loss and latent space reconstruction constraints to construct a composite loss function, thereby reducing the excessive dependence of the model on a single data distribution by enhancing the stability of the representation space structure. The test-time adaptive strategy proposed by the application can evaluate and compensate for concept drift under new conditions without relying on large-scale retraining, thereby improving the accuracy, stability and reliability of ash content prediction under unknown or extreme conditions.

This invention discloses a rate-distortion optimization pruning method and system for dynamic anomaly detection in the Internet of Things (IoT). It utilizes a sliding window to extract real-time time-series samples and proposes a distribution difference quantification method based on the Kolmogorov-Smirnov test. By calculating the statistical distance between the current data and the historical baseline distribution, it identifies concept drift in real time and automatically triggers pruning and reconfiguration signals, ensuring the continuous effectiveness of the detection system in dynamic environments. In the strategy optimization stage, rate-distortion theory is introduced, and a rate-distortion objective function integrating model computational overhead, feature fidelity loss, and gradient sensitivity is constructed. The optimal pruning rate under the current distribution is obtained through optimization calculation, achieving a precise mathematical trade-off between model size and detection performance. A channel-level structured pruning algorithm is adopted to remove redundant feature channels according to the optimal pruning rate, generating a lightweight anomaly detection model with a more compact physical structure. This invention not only reduces the inference latency and memory consumption at the edge of the model but also improves the adaptability and robustness of the detection system to dynamically changing environments, possessing high engineering practical value.

The present application relates to the technical field of sewage biological treatment, in particular to a method, a control system and an evaluation system for online adaptive updating of precise aeration control of short-cut nitrification, and a storage medium. The present application introduces a concept drift detection module and incremental learning fine-tuning, so that a deep learning time series prediction model can learn complex and nonlinear process dynamics to realize automatic correction of the model, provide aeration quantity prediction with higher efficiency and higher prediction accuracy maintenance than traditional PID or redeployment of deep learning time series prediction model, and greatly enhance the adaptability and stability of the aeration system in long-term operation.

The application discloses a dynamic working condition precise control method for gallium enrichment and impurity removal process, which comprises the following steps: firstly, an initial Gaussian prediction model is constructed based on historical working condition data, which is used for model predictive control and working condition monitoring; when the working condition is monitored to be switched, data is collected for model updating; in the transition stage, model mismatch causes conceptual drift of the prediction result, and the model predictive control performance is reduced; in order to reduce the control fluctuation in the transition period, the input of the regulation and control variable is tightly constrained according to the prediction uncertainty estimation; after a small amount of samples are collected, the model updating module obtains a drift matrix through a conceptual drift correction method, and generates a new working condition data set with pseudo labels in combination with the original sample set; subsequently, the model is reconstructed based on the new data set, and the working condition is monitored again; the model predictive controller adaptively relaxes the input constraint boundary of the regulation and control variable, and ensures precise control. The application can ensure the stability and control precision of the gallium enrichment and impurity removal process under the condition that the working condition frequently changes.

This invention discloses an online distributed parameter optimization method and system for intelligent modeling of complex systems, relating to the field of electronic digital data processing technology. The method includes: on the edge side, an adaptive recursive ridge regression algorithm is used to recursively update the weights of the output layer of the feedforward neural network in real time to quickly track data flow dynamics; when the edge side detects a continuous decline in performance, node pruning, selection, and random configuration of node growth based on the optimal dataset are triggered; when concept drift is detected, the edge side uploads data and model status, and the cloud side performs anti-forgetting deep optimization on the feature extraction module, and then downloads the optimized parameters for collaborative reconstruction and deployment. This invention solves the problems of insufficient adaptability to dynamic operating conditions, low computational resource efficiency, and susceptibility to knowledge forgetting in existing technologies, achieving an optimal balance between model accuracy, adaptation speed, and resource consumption, and is particularly suitable for online modeling of complex dynamic systems such as intelligent control of high-speed trains.