136 results about "Label propagation" patented technology

The invention discloses a tensor depth semi-supervised learning method for high-dimensional small sample data classification. The tensor depth semi-supervised learning method comprises the steps of preprocessing original high-dimensional small sample data; constructing a deep neural network comprising a feature extraction module and a classifier module; constructing a second-order similarity matrix and a third-order similarity tensor based on the low-dimensional embedding representation obtained by pre-training; combining the second-order similarity matrix and the third-order similarity tensor to construct an objective function containing multi-order smooth constraints; then, taking the low-dimensional embedded representation obtained by pre-training as input, performing iterative optimization on the target function by adopting a gradient descent algorithm through a label propagation network formed by a full connection layer, and generating a pseudo label; and inputting the original high-dimensional small sample data, the low-dimensional embedded features and the pseudo labels into the deep neural network, iteratively updating the network in a semi-supervised mode until convergence, and outputting a final prediction result. According to the method, more accurate label propagation is realized, and the semi-supervised classification precision is improved.

The invention relates to a real-time power grid topology analysis method based on a graph neural network, and the method comprises the steps: firstly, carrying out the electrical topology analysis at a substation level through constructing an optimized power system physical connection model, carrying out the electrical topology analysis in combination with a label propagation algorithm (LPA), precisely recognizing a calculation region, optimizing the division of the calculation region through employing the graph neural network (GNN), and enhancing the topology adaptability, mistaken division is reduced; and the robustness of equipment state change is improved. Besides, according to the method, the real-time performance, the accuracy and the intelligent level of power grid topology analysis are further improved by predicting the influence of the state change of the circuit breaker and the disconnecting switch on the power grid topology and training a GNN model and reinforcement learning (RL) optimization region division strategy through historical data. And finally, bus-branch connection is optimized through depth-first search (DFS), the topology integrity is ensured, and the efficiency of electrical island analysis, power supply area division and fault recovery is remarkably improved. The real-time performance, the accuracy and the intelligent level of power grid topology analysis are effectively improved.

The invention discloses a key sensor short-time abnormal distribution drift detection method in a unit start-stop process, and belongs to the technical field of gas turbine power plant financial supervision and artificial intelligence, and the method comprises the steps: synchronously triggering multi-channel signal collection through a main clock, and achieving noise suppression and data pre-screening through the combination of first-order difference and threshold filtering; constructing a nonlinear weighted feature matrix, and fusing a time attenuation coefficient and a shafting acceleration factor to enhance the transient feature expression capability; generating a sensor association graph based on double-threshold determination of weighted Pearson's correlation coefficients and mutual information, and dividing stable subgroups by using an incremental label propagation algorithm; designing a double-layer Cluster-GCN model, aggregating subgroup internal characteristics in the first layer, introducing a fuel valve position-acceleration comparison gating mechanism in the second layer to correct a global edge weight, and generating a node embedding vector sensitive to working condition change; gaussian kernel density estimation and an instantaneous deviation index of embedding similarity are fused, and a historical sliding mean value and subgroup connectivity analysis are combined, so that sensor faults and working condition abrupt changes are distinguished.

The invention relates to the technical field of intelligent education management, in particular to a self-adaptive learning progress informatization teaching test system, which comprises the following contents: a knowledge node construction module, a learning state identification module, a test task generation module, a path scheduling adjustment module and a feedback data backtracking module. According to the method, refined numbering management of knowledge points is realized by constructing a directed edge numbering set, a dependency direction is set in combination with a label propagation algorithm, the semantic expression ability of a node relationship is enhanced, mastering weights and stability coefficients are matched based on answering behaviors, a state weight sequence is formed, and the stability of classification and recognition is improved; cognitive ability coding and time-consuming median value linkage state weight are introduced, questions are screened, a priority queue is constructed, task pushing precision is improved, numbering and sorting weight are fused to construct a path chain, dependency intensity is calculated to expand path branches, and individual suitability and task rhythm coordination ability of path scheduling are enhanced.

The invention discloses a semi-supervised multi-modal entity alignment method, which relates to the technical field of knowledge maps, and is characterized by comprising the following steps: S1, symbol definition of a multi-modal entity alignment task; s2, constructing a semi-supervised multi-modal entity alignment model; s21, the multi-modal knowledge feature embedding module extracts heterogeneous features through a heterogeneous encoder; s22, a cross-modal fusion module uses a cross attention mechanism to model complementarity and correlation between modals, and joint representation is generated; and S23, a pseudo label generation and momentum contrast learning module screens high-confidence pseudo labels based on graph label propagation, and enhances contrast learning stability in combination with a momentum queue. The technical problem to be solved by the invention is to provide a semi-supervised multi-modal entity alignment method. Multi-modal entity alignment aims to identify and connect information representing the same entity in different multi-modal knowledge maps.

The present application provides a data processing method and a data processing device. The method comprises: propagating a label of a starting point of an event to a label of an end point of the event. A label of a node can indicate historical state information of a target path which has been detected in log data and uses the node as an end point, so that by means of label propagation, an abnormal path having an abnormal historical state is found, and the abnormal path is output in a local streaming provenance graph mode. According to the method, a complete streaming provenance graph is not required to be constructed, the occupation of computing resources and memories can be reduced, abnormal behaviors (for example, abnormal paths) can be detected in real time, and abnormal paths can be output so as to trace abnormal behaviors.

Some embodiments can include methods and related systems to project coarse representations of natural language interactions into fine-grained representations using contrastive learning projections. Some embodiments can maximize a first set of distances between dissimilar points and anchor points in the fine-grained representations, and minimize a second set of distances between similar points and the anchor points in the fine-grained representations. Some embodiments can then propagate labels from labeled projections to unlabeled projections based on a similarity metric.

The invention relates to the technical field of data processing, and discloses a fault analysis method and system based on a label propagation algorithm. The method comprises the following steps: acquiring operation state data through a monitoring equipment network, extracting the data to obtain a system topology data set, performing label propagation fault analysis on the system topology data set to obtain node fault information, and performing fault influence weight analysis on each node based on the node fault information to obtain a maintenance priority, and inputting the influence weight data into the graph neural network for coping strategy analysis to obtain a target processing strategy. According to the invention, the efficiency of fault propagation analysis and the accuracy of decision making are improved.

The technology is generally directed to determining whether candidate digital components violate a policy and using the determination to propagate policy labels. Candidate digital components may be filtered such that only a subset of the candidate digital components is provided to a machine learning model for further policy review. The machine learning model may provide a confidence score associated with the policy violation prediction. The policy violation prediction may be “violates policy” or “does not violate policy.” A label corresponding to the policy violation prediction may be associated with the digital component. The confidence score may be used when determining whether to use the policy violation prediction to propagate labels to other digital components. The labels may be propagated using a seed based enforcement system or a neighborhood based propagation system.

The invention discloses a multi-source semi-supervised incremental working condition identification method and system for a rod-pumped well, and relates to the technical field of working condition identification of rod-pumped wells. The method is characterized by comprising the following steps: step 1, respectively storing a sample library of an actually measured ground indicator diagram and an actually measured electric indicator diagram; 2, respectively constructing a graph neural network teacher model for two data sources, namely an actually measured ground indicator diagram and an actually measured electric indicator diagram; 3, dynamically fusing the prediction probability of each teacher model; 4, multi-source data distillation learning is carried out; and 5, performing semi-supervised working condition identification by using a label propagation algorithm improved by a logistic regression classifier. According to the multi-source semi-supervised class increment working condition identification method and system for the rod-pumped well, a multi-source fusion technology based on an attention mechanism, class increment learning and semi-supervised learning are simultaneously applied to class increment working condition identification of the rod-pumped well, and a small number of multi-source marking working condition samples are fully utilized; and more efficient, robust and practical rod-pumped well working condition identification is realized by combining a large number of multi-source unknown working condition samples.

The invention discloses a micro spring washer manufacturing process optimization method using a collaborative filtering algorithm, and the method comprises the following steps: S1, collecting and preprocessing historical manufacturing data, and constructing a tensor structure comprising manufacturing batches, process parameters and product quality indexes; s2, converting the tensor structure into a scoring matrix, and predicting an initial process parameter combination of a target batch by adopting a collaborative filtering algorithm; s3, constructing a weighted graph, introducing a label propagation network to complement scores, and determining a recommendation parameter combination; s4, constructing a multi-objective optimization model with size consistency, residual stress balance and unit energy consumption as objectives based on the recommended combination; s5, solving by adopting an improved cat swarm optimization algorithm, and outputting an optimal solution; and S6, applying the optimal solution to the manufacturing process, collecting quality result feedback, updating the scoring matrix and the graph model, and realizing a manufacturing optimization closed loop. According to the method, the tag propagation network and the improved cat swarm optimization algorithm are fused, and the manufacturing process of the miniature spring washer is optimized.

The invention discloses a small sample point cloud semantic segmentation method, computer equipment and a storage medium, and relates to the technical field of three-dimensional computer vision, the small sample point cloud semantic segmentation method mainly comprises the following steps: according to a support set point cloud and a query set point cloud, using an embedded network to obtain support set features and query set features, using a feature correlation matching module to obtain enhanced support set features and enhanced query set features; according to the enhanced support set features, obtaining a support prototype by using a similarity perception prototype number constraint method and a multi-prototype generation method; according to the enhanced query set features and the support prototype, utilizing a prototype correction module to obtain a corrected support prototype; and according to the enhanced query set features and the corrected support prototype, obtaining a prediction mask by using a KNN graph construction and label propagation method. By implementing the small sample point cloud semantic segmentation method, the computer equipment and the storage medium provided by the invention, the small sample point cloud semantic segmentation precision can be improved.

The invention discloses a bacterial colony image time sequence classification tracking method based on dynamic time warping and label propagation, and solves the problems of inconsistent classification and accurate segmentation of bacterial colonies with different sizes caused by the change of bacterial colony morphology along with time. The method comprises the following steps: acquiring a bacterial colony image feature sequence and constructing a bacterial colony feature distance matrix; calculating an accumulated distance matrix based on a dynamic time warping algorithm, and calculating accumulated distance values point by point through a recursion formula; through a path backtracking algorithm, finding a time point matching path which minimizes an accumulated distance value between bacterial colonies, and obtaining an optimal time alignment relationship between feature sequences of different bacterial colonies; constructing a similarity matrix, and calculating a similarity value between bacterial colonies; and a classification corresponding relation between time points is established by adopting a cross-time-point target association algorithm, and the bacterial colony classification label at the first time point is propagated to the subsequent time point, so that the consistency of the time sequence classification labels is ensured.

The invention provides an automatic user label construction method and system based on multi-source heterogeneous data, and relates to the technical field of data mining, and the method comprises the steps: obtaining multi-source behavior data, carrying out the feature fusion through a bidirectional attention mechanism, and carrying out the clustering center dynamic adjustment based on time sequence drift. And constructing a multi-level label structure tree by using a label propagation algorithm considering node time sequence evolution characteristics. According to the method, heterogeneous data source information can be effectively integrated, user behavior changes can be adaptively captured, the tag accuracy and timeliness are improved, and support is provided for precise marketing and personalized recommendation.

Systems, methods, and computer program products may (i) obtain a graph including a plurality of edges and a plurality of nodes for the plurality of edges, each labeled node of a subset of labeled nodes being associated with a label, and each unlabeled node of a subset of unlabeled nodes not being associated with a label; (ii) train, using the graph and the label for each labeled node, a graph neural network (GNN), wherein training the GNN generates a prediction for each node; (iii) generate, from the subset of unlabeled nodes, a candidate pool of candidate nodes; (iv) generate, using a label propagation algorithm, a predicted label for each candidate node; (v) select a candidate node of the candidate pool of candidate nodes that is associated with a greatest hybrid entropy reduction for the graph; and (vi) provide the selected candidate node for labeling.

The invention provides a large-model intelligent label synthesis and data automatic labeling integration method and system, and belongs to the technical field of label synthesis and data labeling, and the method comprises the steps: carrying out the semantic embedding and robust clustering of text data, and obtaining a stable cluster set; when new data is introduced, semantic consistency alignment of cross-round clustering results is realized through a confusion matrix matching strategy, and label drift is inhibited; maintaining an editable hierarchical label directed acyclic graph to support label system evolution; driving a large language model to generate a high-quality and interpretable cluster-level semantic tag based on the representative sample; carrying out automatic annotation and confidence evaluation by using large model context learning for clustering non-attribution or low-confidence samples; and propagating the cluster-level labels to the instances, and combining the cluster-level labels with an automatic labeling result to construct a full-process traceable label management mechanism. According to the method, the efficiency, quality and consistency of text labeling are improved, and powerful support is provided for large model training and intelligent data management.

The invention provides a cross-individual human body behavior recognition method based on self-training and active inquiry, and the method comprises the steps: obtaining a source domain data set with a label and a target domain data set without a label; processing acceleration data in the source domain data set with the label and the target domain data set without the label; dividing the target domain data into a label-free training set and a test set in proportion; establishing a feature extractor based on a dual-channel convolutional network, and extracting features of time and space dimensions from the input two-dimensional acceleration data at the same time; a cross-individual adaptation algorithm based on a confidence threshold value, sparse query and label propagation is adopted, a model is trained on a non-label training set on a target domain, and the adaptation problem caused by cross-individual data distribution difference is relieved. According to the method, the behavior recognition accuracy of the model in a cross-individual scene can be improved, the development cost and the user burden are reduced, and a more intelligent and adaptive solution is provided for application of wearable equipment such as exoskeleton robots.

A cross-shard collaborative consensus method for drone clusters based on a reputation mechanism belongs to the technical field of drone cluster collaboration. The present invention solves the problems of heavy storage burden, high communication overhead, limited scalability and poor fault tolerance in existing systems. By combining state sharding technology and a multi-dimensional reputation evaluation mechanism, and realizing dynamic optimization allocation of tasks based on a task collaboration network and a label propagation mechanism, the system can adaptively adjust the sharding structure according to real-time load conditions, and the sharding strategy based on task correlation can reduce the communication overhead of cross-shard collaboration. The two-stage cross-shard transaction mechanism designed by the method of the present invention combines multiple guarantees such as lock-up period, multiple signatures and proof of failure. Through a lightweight state synchronization mechanism and the PBFT consensus protocol, it not only ensures the consistency and reliability of the data, but also improves the scalability and fault tolerance of the system. The method of the present invention can be applied to the field of drone cluster collaboration.

Described is a system for detecting and classifying new patterns of objects and images for applications where labeled data is scarce. In operation, the system trains a neural network with unlabeled images and extracts features with the neural network from both the unlabeled images and a set of labeled images to generate a feature space. Labels are propagated in the feature space using nearest neighbors, allowing for modeling of a per-class simplified distribution. An object in a new test image can then be classified using reconstruction error based on the per-class simplified distributions.

The invention discloses a knowledge graph fusion method, device and equipment based on label propagation. The method comprises the following steps: acquiring a label propagation command, wherein the command comprises a knowledge graph list and a result output path; respectively executing a label propagation algorithm on each knowledge graph in the knowledge graph list, and determining initial label value distribution of each knowledge graph; determining an equivalent entity set among different knowledge maps; based on an initial label value and a local topological structure of each equivalent entity in the equivalent entity set in the knowledge graph, fusing the initial label value and the topological structure to obtain a fused entity, a fused label value and a fused topological structure; and according to the fusion entity, the fusion label value and the fusion topological structure, fusing the at least two knowledge maps in the knowledge map list to obtain a fusion result, and storing the fusion result in a result output path. According to the embodiment of the invention, cross-graph complex semantic calculation and conjoint analysis are supported.

The application provides a local consistency guided sparse label enhancement method, which is suitable for road drivable area detection and belongs to the technical field of images. The method aims to solve the problem that the existing deep learning model depends on a large amount of pixel-level label data. Firstly, the input image is sparsely labeled, and context enhancement features are constructed according to local and global image representations to establish the similarity relationship between superpixel nodes. Then, a label propagation model is constructed based on a graph convolution network to propagate sparse labels to unlabeled areas to generate pseudo labels. In the application, a local consistency guided weak supervision training strategy is adopted, and a joint loss function is designed to cooperatively supervise the labeled areas and the unlabeled areas, thereby improving the reliability of the pseudo labels and the overall segmentation accuracy. Experimental results show that the application can be applied to various road drivable area detection tasks, and the obtained high-quality pixel-level pseudo labels can be used for subsequent full-supervised model training.

The application belongs to the technical field of brain image analysis, and discloses a brain image data classification model establishment method based on a near neighbor propagation bias label learning, which comprises the following steps: S1, acquiring a training data set and corresponding original labels, solving correlation coefficients between samples and degrees of centrality of the samples, and generating a typical sample set and a category center set according to the correlation coefficients and the degrees of centrality; S2, determining candidate labels of training samples, and constructing a candidate label set; S3, performing label propagation by using a K+N near neighbor sample graph through the training data set, and establishing a classification model. The application can improve the accuracy and precision of the classification model.

The invention relates to the technical field of power system stability control, and provides a new energy black-start partition optimization method considering unconventional risks, which comprises the following steps: simulating unconventional risks possibly encountered by a power system by adopting Monte Carlo sampling; extracting the output characteristics of wind power under the unconventional risk by adopting variational mode decomposition, and performing output prediction in combination with a long-short-term memory neural network; a power system recovery partition is divided based on an LPA algorithm, and the LPA algorithm is improved by considering a partition size balance principle, so that the partition area is more balanced, and the tag oscillation effect is reduced. According to the method, the black-start partition optimization model fusing new energy output uncertainty modeling and unconventional risk scene generation is designed, and the partition scheme is cooperatively solved by adopting the improved label propagation algorithm, so that the robustness and the recovery efficiency of the black-start partition are effectively improved; and rapid and stable power supply of a power system under complex disturbance can be realized.

The application relates to an individual brain mapping method and device based on a brain mapping fusion model. The method comprises the following steps: receiving at least two groups of subject data for training of a brain mapping fusion model, extracting data features of the subject data, and pre-processing the subject data to obtain an adjacency matrix; inputting the data features and the adjacency matrix into an initial brain mapping fusion model based on a graph convolution model and a label propagation model, obtaining brain mapping prediction values output by the initial brain mapping fusion model, training the initial brain mapping fusion model based on the graph convolution and the label propagation algorithm according to the brain mapping prediction values, and obtaining a trained brain mapping fusion model; and inputting to-be-detected data into the trained brain mapping fusion model to obtain an individual brain map. The method can combine the graph convolution algorithm and the label propagation algorithm to process the subject data, and improve the drawing speed and precision of the individual brain map.

This invention discloses a microblog group identification method based on community discovery, comprising the following steps: S1, data collection and cleaning; S2, feature extraction and representation; S3, establishing a classification model; S4, community tagging and influence analysis. In this invention, an optimized Dynamic Topic Model (DTM) is used to mine specific groups within the microblog community. Microblog posts from the past year are selected as the research object, and the similarity of topics in posts from different authors is used as the weight of links between authors, mapping the microblog network into a directed weighted network. Community discovery is performed using the Label Propagation Algorithm (LPA), identifying the inherent community structure within the social relationship network. This invention conducts in-depth analysis of user relationships within the microblog network, and based on identification methods for user-generated content characteristics, user association characteristics, and environmental characteristics, it mines potential topics to identify users with similar interests and active user groups in specific fields.

The application provides a large model intelligent label synthesis and data automatic labeling integrated method and system, and belongs to the technical field of label synthesis and data labeling. The method comprises the following steps: performing semantic embedding and robust clustering on text data to obtain a stable cluster set; when new data is introduced, the semantic consistency alignment of cross-round clustering results is realized through a confusion matrix matching strategy to suppress label drift; an editable hierarchical label directed acyclic graph is maintained to support label system evolution; a large language model is driven based on representative samples to generate high-quality and interpretable cluster-level semantic labels; for samples that are not attributed or have low confidence in clustering, automatic labeling and confidence evaluation are performed through context learning on the large model; the cluster-level labels are propagated to instances and combined with the automatic labeling results to construct a full-process traceable label management mechanism. The application improves the efficiency, quality and consistency of text labeling, and provides strong support for large model training and intelligent data management.

The present application is applicable to the field of point cloud semantic segmentation technology, and provides a small sample point cloud semantic segmentation method, network, storage medium and processor. The small sample point cloud semantic segmentation method uses label propagation to extract pseudo-prototype features that are adapted to the query set data, thereby obtaining prototype features that are adapted to the query set data, and performs feature calibration by extracting the relationship between the prototype and the query set data. Prototype expansion effectively utilizes the distribution information of the query set data and the prototype information of the support set. This further improves the adaptability of the prototype to the query set data. Therefore, the present invention can obtain prototype features that are adapted to the query set, achieve effective segmentation of the point cloud scene, and reduce the impact of misjudgment results on the expanded prototype.

The application discloses a semi-supervised high-resolution remote sensing image change detection method based on label expansion, comprising the following steps: setting an input data set; constructing an encoder-decoder change detection model; constraining the consistency of the prediction results between weak enhancement and strong enhancement in the construction of the encoder-decoder change detection model; expanding pseudo labels through a position interaction graph; optimizing data through supervised loss and unsupervised loss; extracting features of the input data set through an encoder to obtain differential features; and obtaining a change detection probability graph through decoding of the differential features by a decoder. The application proposes a consistency regularization framework of one weak and two strong, and constrains the consistency of the prediction results between weak enhancement and strong enhancement and between the two strong enhancements. The position interaction graph is introduced, the global-local relationship between pixels is utilized, and the internal consistency of pseudo labels is mined, so that the model precision is improved.

The invention discloses a data processing method, electronic equipment, a storage medium and a computer program product, and relates to the technical field of large model technology and data query. The method comprises the following steps: acquiring seed data; pre-labeling the seed data in a label propagation mode to obtain labeled data; performing data quality inspection on the labeled data to obtain training data; and training the initial intention classification model by adopting the training data to obtain a target intention classification model. The technical problems that the training cost of a model with a tool selection function is high, the efficiency is low, and the tool selection accuracy and the query accuracy of the model obtained through training are poor in the prior art are solved.

The invention discloses a power grid partitioning method based on partial differential morphology and label propagation, and the method comprises the steps: abstracting a power network into a weighted graph, and based on a selection strategy of electrical centrality, namely selecting k nodes with the maximum electrical centrality as seed nodes, obtaining a seed node set, and distributing a unique label for each seed; morphological diffusion and label propagation are combined in a power grid partition, and outward diffusion propagation is carried out from a seed node set; label propagation and morphological diffusion run in parallel to dynamically adjust label attribution of nodes, and each node is endowed with a final label after multi-round iteration when the cost of all the nodes does not change any more, so that division of the power grid is completed. According to the method, efficient partition control and management of the power grid can be effectively achieved, accurate identification and reasonable division of the topological structure of the power grid are achieved, and scientific support is provided for planning and management of a power system.