10 results about "Graph sampling" patented technology

The application discloses a digital quantum computing-based computing power network DDoS detection method and system, and relates to the technical field of network space safety management and control.The application comprises the following steps: collecting real-time network flow data in a jurisdictional area through a dispersed detection point, constructing a graph neural network DDoS detection algorithm based on quantum random walk sampling, and performing quantum random walk to obtain quantum probability distribution of each node; performing quantum probability weighted non-replacement sampling on neighbor nodes of each target node to obtain a sampled neighbor set; performing message passing on the sampled neighbor set through a graph sampling aggregation network; uploading local model parameters to a safety management center through a federated learning architecture, and outputting a DDoS attack detection result.The application realizes DDoS flow feature extraction based on a graph structure, and utilizes a neighbor sampling mechanism guided by quantum random walk to complete real-time identification and detection of DDoS attacks.

The present disclosure provides a data analysis method, device, electronic equipment, storage medium and program product, the method comprising: obtaining input data; according to the input data, using graph sampling and aggregation model, data matching is carried out in knowledge graph, according to the matching result, vector representation conversion and text representation conversion are carried out, the vector representation and the text representation are spliced to obtain intermediate data; determining whether the intermediate data conforms to the set rule; in response to the intermediate data conforming to the set rule, determining the calculation rule of the analysis result in the knowledge graph according to the intermediate data, determining the analysis result according to the calculation rule and the intermediate data, outputting the analysis result.

The application discloses a zero sample graph learning method based on a large language model, comprising: neighborhood subgraph sampling on to-be-processed graph structure data to generate graph query text; based on the graph query text, a structured prompt template containing multi-stage reasoning instructions is constructed, and the prompt template instructs the large language model to sequentially perform topological structure analysis, semantic attribute interpretation, multi-candidate answer enumeration and deep reevaluation before generating a final answer; a graph reasoning training data set is constructed; the basic large language model is fine-tuned by full parameters by using the graph reasoning training data set; the large language model is optimized by using a reinforcement learning algorithm based on group relative advantage; for a new graph task to be reasoned, the new graph task is input into the optimized large language model, and a final prediction answer containing a reasoning process is directly output. The application discards the dependence of a graph neural network, and only uses the text reasoning capability of the large language model to complete a graph task, so that the deployment complexity and the calculation cost are greatly reduced.

This invention relates to the field of lithium-ion battery state monitoring and health management technology, and proposes a battery health state estimation method based on an improved graph neural network and a hybrid PINN. The method includes constructing a hybrid graph structure containing time edges and similarity edges based on weighted multidimensional health features and time series information, and inputting it into an improved graph sampling aggregation network. High-dimensional spatiotemporal features of each battery charge-discharge cycle node are extracted and embedded through multi-layer graph convolution operations. A hybrid physical prior model is constructed and combined with a residual correction module to form a physical constraint dynamic equation. The high-dimensional spatiotemporal feature embeddings are input into a prediction network to obtain a preliminary prediction of the battery health state. A loss weight annealing strategy is used to dynamically weight the data-driven loss and the physical constraint loss, and the improved graph sampling aggregation network, prediction network, hybrid physical prior model, and residual correction module are collaboratively trained to finally output the estimated battery health state.

The application discloses a kind of based on low rank contrast learning and reconstruction graph anomaly detection method, comprising: 1) obtain graph data, and generate low rank graph data by SVD singular value decomposition dimension reduction, using restart random walk algorithm to carry out subgraph sampling, obtain original view and low rank view;2) on original view and low rank view, construct contrast pair and carry out contrast learning, obtain contrast learning loss;3) low rank attribute reconstruction is carried out on original view and low rank view, and the final reconstruction loss of original view and low rank view is obtained;4) the graph neural network model is trained in combination with contrast learning loss and reconstruction loss;5) according to the trained graph neural network model, the abnormality of node in the graph to be measured is judged, and the potential abnormal node is determined.The application generates low rank view by low rank approximation to node attribute and topological structure, effectively filters the interference of abnormal node and noise on the basis of retaining the original structure of graph.

This invention provides a short text clustering and fuzzy recognition algorithm for large-scale online subgraph sampling, comprising the following steps: Step S1, extraction and preprocessing of training samples; Step S2, construction of the neural network; Step S3, overall clustering prediction; Step S4, fuzzy sample recognition; Step S5, retraining of the neural network. This invention combines short text clustering with a large language model, which not only improves clustering accuracy but also enables the handling of clustering tasks with different themes and classification requirements, significantly reducing the manual cost of data annotation. Furthermore, this invention can annotate fuzzy samples for classification, using K-nearest neighbors combined with minimum spanning trees to assist subgraph sampling in the selection scheme. This utilizes sparse structure to reduce computational costs and exposes the fluctuations of boundary samples through spectral clustering, providing a more comprehensive perspective for fuzzy sample selection and improving the accuracy and interpretability of the clustering results.

The present invention belongs to the field in which a semantic web and deep learning are combined. The present invention relates to a heterogeneous ontology matching method and system based on BERT and graph contrastive learning. In the present invention, a semantic feature extraction module extracts internal triple information of an ontology to construct a corpus; the corpus is input into a BERT model for parameter fine-tuning, and the fine-tuned BERT model is used to generate a semantic feature vector of an entity; and then, a graph contrastive learning module executes graph sampling on the basis of a topological structure of an ontology graph, so as to generate two views. Training is implemented by selecting positive samples and negative samples and setting a loss function, so as to generate a comprehensive entity feature vector; and finally, a similarity calculation module is used to calculate final similarity scores of different entity pairs. The present invention can effectively use a topological structure of an ontology graph to extract structural features, so as to overcome the problem of traditional structural features being incapable of fully expressing complex structural relationships between entities, thereby improving the accuracy of matching.

The application discloses an abnormality detection method based on low-rank contrast and reconstruction, comprising the following steps: 1) performing SVD dimension reduction on original graph data to generate a low-rank view, performing subgraph sampling on the original view and the low-rank view, and obtaining original and low-rank subgraphs; 2) constructing positive and negative sample pairs on the two views respectively, and performing contrast learning; 3) performing reconstruction learning on the two views respectively; 4) integrating contrast learning and reconstruction learning to train a model; and 5) using the trained model to perform abnormality discrimination on nodes. The application proposes a graph abnormality detection method based on low-rank contrast learning and reconstruction, low-rank approximation is performed on node attributes and topological structures to generate a low-rank view, and on the basis of retaining the original structure of the graph, the interference of abnormal nodes and noises is effectively filtered.

The application discloses a financial fraud detection method and system based on hypergraph neural network dynamic neighborhood modeling, and the method comprises the following steps: constructing a hypergraph of a target network; for a target node in the hypergraph, a local subgraph is obtained through subgraph sampling, and the abnormal probability of the target node is estimated based on the feature comparison between the target node and the local subgraph; according to the abnormal probability, the high-order neighborhood information of the target node is aggregated from a benign perspective and a fraud perspective respectively, and the aggregation results of the two perspectives are fused to generate the final embedding representation of the target node; and whether the target node is a fraud node is identified based on the final embedding representation. The application estimates the abnormal probability based on the consistency of the node-hypergraph subgraph features, adaptively groups and aggregates the high-order neighborhood information from the benign perspective and the fraud perspective, separates the mixed signals caused by structural camouflage, strengthens the rare features of a small number of fraud nodes, and alleviates the influence of class imbalance.

The application belongs to the technical field of database benchmark test, and discloses a data generation method and system for multi-model database query performance evaluation. A graph sampling algorithm based on probability propagation is used to extract a seed data set that retains topological features from a large-scale academic network to construct a probability distribution model. In the generation process, a unified logical entity object is constructed based on statistical characteristics, and four kinds of modal data, i.e. relational, document, graph structure and vector, are synchronously analyzed and mapped to ensure strong consistency of cross-model semantics. A specific domain statistical language model and deep semantic coding are introduced to realize semantic alignment of unstructured text and high-dimensional vectors. Through a closed-loop time sequence evolution mechanism, incremental features are fed back to the probability model in real time to drive the next time step generation. The application effectively solves the problems of existing generated data, such as loss of real data features, weak cross-model consistency and lack of time sequence causality, and provides a high-fidelity and scalable test benchmark for multi-model database performance evaluation.