11 results about "Cluster graph" patented technology

Computer security improvements relating to fraud detection and data correlations through large-scale graph clustering of graph transformations and embeddings are disclosed. A service provider may utilize a framework having computing operations for detecting fraud and other malicious or suspicious activities by groups of accounts and fraudsters. In this regard, the service provider may transform relationship graphs of account networks and relationships between accounts and account data captured in the nodes and edges of such graphs. The service provider may merge nodes that edges connecting to other nodes of a certain type of account data, while other types of account data and nodes may not be merged. Edges may also be merged and weighted, and the resulting transformed graph may undergo graph embedding to generate vectors that may be clustered using an AI clustering algorithm. The clusters may then be used for AI model training and inferencing.

The invention discloses an unknown working condition equipment state anomaly detection method based on a graph neural network, and belongs to the field of mechanical equipment fault diagnosis. The method comprises the following steps: respectively preprocessing normal state data and abnormal state data of equipment with unknown working conditions, obtaining low-frequency data of different layers in each state, and determining an analysis layer; performing segmentation processing on data corresponding to the analysis layers in the two states; extracting features of each segment processing data from multiple angles; carrying out segmented processing on the data in each state to obtain a multi-modal feature node set, and generating a working condition graph feature set by adopting a feature centroid hierarchical clustering graph construction method; and obtaining a trained message passing graph neural network model by using the working condition graph feature set. According to the method, on the basis of constructing the working condition graph feature set, the anomaly detection of the equipment with the unknown working condition is effectively realized according to the constructed message passing graph neural network model.

The present disclosure relates to an approximate nearest neighbor search method and an approximate nearest neighbor search system. According to the embodiment, the approximate nearest neighbor search method manages graph index information for defining an inter-cluster graph. The approximate nearest neighbor search method searches for a vector closest to a query from vectors belonging to a search start cluster having a reference position closest to the query among a plurality of clusters. The approximate nearest neighbor search method selects one or more search target clusters close to the search start cluster while advancing along the inter-cluster graph, and searches for a vector closest to the query from vectors belonging to each of the one or more search target clusters. Thus, the approximate nearest neighbor search method capable of reducing the amount of data required to be rewritten accompanying update of the graph index and capable of obtaining sufficient search accuracy is provided.

The invention relates to the technical field of knowledge graph construction and information retrieval sorting, in particular to a technical requirement matching graph construction method based on a graph neural network, which comprises the following steps: reading technical requirement and technical supply literatures, extracting term entities and generating candidate pairs according to character string similarity and semantic similarity; constructing a candidate synonym cluster graph according to the candidate pairs, writing the candidate synonym cluster graph into a heterogeneous demand matching graph, and inputting the candidate synonym cluster graph into a Bayesian graph neural network to obtain node embedding and node and edge uncertainty parameters; weighting and aggregating the adjacency information based on the edge uncertainty and applying consistency constraint update in the cluster; and calculating a matching sorting score, writing a demand-supply matching edge according to a threshold value and Top-K, recording a confidence coefficient and an interpretation field, and generating and storing an atlas version. According to the method, the demand-supply matching accuracy is improved under the uncertainty constraint, and the mismatching rate is reduced.

According to one embodiment, an approximate nearest neighbor search method manages graph-based index information for defining an inter-cluster graph. The approximate nearest neighbor search method searches for a vector closest to a query vector from vectors belonging to a search start cluster that is closest to the query vector among a plurality of clusters. The approximate nearest neighbor search method selects one or more search target clusters close to the search start cluster while traversing the inter-cluster graph, and searches for a vector closest to the query vector from vectors belonging to each of the one or more search target clusters.

The application provides an event graph construction reasoning method and device based on sentence similarity. The method comprises the following steps: extracting a cause-effect relationship and event description from an original text, and constructing an initial event graph; calculating the similarity between nodes, i.e. event descriptions, in the initial event graph, merging events with a cause-effect relationship and a similarity greater than a set threshold into an event cluster to obtain an event cluster graph; inputting an event description into the event cluster graph, determining an event cluster in which an event with the greatest similarity to the event description is located, returning a partial event cluster graph having a direct cause-effect relationship with the event cluster, and calculating a related cause-effect event probability. The application merges events into event clusters based on similarity calculation, replaces events as nodes in a network structure, simplifies the network structure, and improves the efficiency of finding causes and results.

The application discloses a news event prediction method based on heterogeneous evolution event clustering, comprising the following steps: generating event representation based on the preliminary updated entity representation and relationship representation in the constructed entity graph, regarding the event as a node, regarding the heterogeneous relationship between events as an edge, and constructing an event graph; obtaining event clusters by fuzzy clustering and constructing an event cluster graph; optimizing the event cluster representation according to the distance and similarity between event clusters on the event cluster graph by using a self-supervised optimization algorithm; capturing the implicit correlation between event clusters by using an implicit relationship encoder, and then updating the representation of the event cluster, the representation of the event, the entity and the relationship representation in sequence after sparsification and information aggregation; and predicting by a convolution-based news event model. The application effectively models the pair correlation, high-order correlation and multi-step time sequence evolution between events, and has important application value in international situation analysis, social governance and intelligent decision support.

The invention provides an information security risk detection method and system based on data feature analysis, and the method comprises the steps: obtaining traffic data of each node of a network, extracting communication protocol state transition and load information entropy features, and constructing a node feature vector through combining port and protocol information; clustering the nodes by adopting a density peak clustering algorithm to obtain a plurality of initial clusters; an initial cluster is regarded as a super node, a communication stability coefficient is determined according to communication flow jitter and periodicity between the super nodes, a cluster graph is constructed, and node feature vector dispersion in the super nodes is calculated to serve as an internal stability index; calculating super-node structure centrality based on the cluster graph, fusing the node feature vector and the subordinate super-node structure centrality to obtain a node context risk value, and aggregating node risk values in the super-nodes to generate a cluster risk value; and determining a global risk baseline according to statistical distribution of all cluster risk values, adjusting the baseline in combination with a super-node internal stability index to obtain a threshold value, and determining that the cluster is a high-risk cluster if the cluster risk value exceeds the threshold value.

The application discloses a kind of automatic driving multi-vehicle coordination control method and system based on robust QMIX, belong to vehicle networking and automatic driving field, including: by cluster graph representation module, the local graph structure of description in cluster vehicle interaction and the global graph structure of inter-cluster interaction, to represent the interaction relationship inside and outside vehicle cluster;Through the noise perception mechanism of robust strategy learning module, dynamically evaluate the environmental disturbance intensity, adopt the weighted QMIX framework to adjust the value function weight, and combine the robust loss function to optimize strategy;Through cross-cluster reward coordination module, according to the reward distribution difference between clusters, dynamically reduce the reward value of high-reward cluster to balance global optimization;Through central dispatching system, cooperative decision-making instruction is distributed to each automatic driving vehicle for execution.The application can realize long-term stable strategy optimization in complex traffic system.

The present application relates to the technical field of knowledge graph construction and information retrieval sorting, and particularly relates to a technical requirement matching graph construction method based on a graph neural network, comprising: reading technical requirement and technical supply literature, extracting term entities and generating candidate pairs according to string similarity and semantic similarity; constructing a candidate synonym cluster graph according to the candidate pairs and writing into a heterogeneous requirement matching graph, inputting a Bayesian graph neural network to obtain node embedding and node and edge uncertainty parameters; weighting and aggregating adjacent information based on edge uncertainty and updating within the cluster by applying consistency constraints; calculating a matching sorting score, writing requirement-supply matching edges according to a threshold and Top-K, recording confidence and explanation fields, and generating and storing a graph version. The present application improves requirement-supply matching accuracy under uncertainty constraints and reduces the mis-matching rate.