42 results about "Dual graph" patented technology

The invention discloses an emotion pressure recognition method and system based on an action form fusion graph neural network, and belongs to the field of image processing and machine learning. A double-graph data structure is constructed, wherein graph data with human body key points as nodes and graph data with image frames as nodes are processed through T-GCN and PCSN respectively. The T-GCN model fuses a GCN layer and a Mama encoder, the cohesion and coupling ability of emotion category characterization is enhanced through a graph partitioning strategy, and the spatial-temporal characteristic relation of human body actions is effectively captured. The PCSN adopts a three-branch parallel structure including one-dimensional global average pooling, 3 * 3 convolution and 5 * 5 convolution, efficient extraction of non-homogeneous features of the human body, the face and the hand is achieved, and the long and short distance dependence and local cross-channel interaction relation of the global features is established. According to the system, through combination of transfer learning and small sample learning, a public data set is utilized to initialize a network, and secondary training is performed on a small sample data set of campus emotion pressure, so that the recognition precision is remarkably improved.

The invention discloses a three-dimensional physical field real-time prediction method and system based on geometric deep learning and physical constraint, and relates to the technical field of computer-aided engineering and artificial intelligence. The method comprises the following steps: directly extracting native boundary representation data (B-Rep) of a three-dimensional model from a computer aided design system; constructing a heterogeneous dual graph taking a parameterized curved surface as a graph node, skipping finite element grid division, and aggregating local and global topological features by using a graph neural network; in combination with a physical information driving mechanism, a partial differential equation (PDE) residual error is introduced as a loss function for constraint training, and generalization prediction of a novel geometric structure is realized; and finally, the physical field state quantity is predicted through direct regression and is rendered in real time. An incremental reasoning mechanism based on a local topology subgraph is adopted, millisecond-level physical field real-time feedback under design modification is achieved, and the method is suitable for scheme rapid screening and trend prediction in the initial stage of design.

The invention discloses a logical reasoning method and device based on knowledge enhancement and capsule network collaboration and a medium. The method comprises the steps that a public knowledge local database is constructed, and a vectorization database and a graph network database are deployed locally; performing preliminary retrieval according to the logical reasoning text, and expanding a retrieval range based on a graph network; inputting the logic text, the problem and the related background knowledge into a large language model to generate a logic reasoning link, and integrating all contents to obtain a logic reasoning text after knowledge enhancement; constructing a semantic graph and a connection graph according to the logical reasoning text after knowledge enhancement; the semantic graph and the connection graph are respectively imported into a capsule network, and a dynamic routing algorithm is applied to promote low-level capsules to be progressive to high-level capsules; respectively executing an average fusion operation on the plurality of high-level capsules in the double images to extract global features of the images; global features of the double graphs are integrated through a fusion strategy, final knowledge text features are formed, and final options are obtained.

Disclosed is a graph convolution auto-encoder based method for computing road network similarity. The method includes: creating a dual graph of a road network, and giving road network space feature information to nodes of the dual graph from three aspects of global, local and connection characteristics on the basis of a relation principle between an entire structure and parts of the structure, such that a quantitative expression of a road network graph structure is obtained; aggregating and updating node feature information and structure information of a road network graph by the graph convolution auto-encoder, and forming a deep understanding of the road network, such that a coded expression of node information of the road network is obtained; and mapping a complex high-dimensional feature space to an easy-to-measure low-dimensional feature space through an average pooling operation, so as to obtain a set of feature vectors, and computing the similarity.

The present invention provides a sentiment prediction method and system based on an interactive dual graph convolutional network, comprising: obtaining a text to be predicted and converting it into a plurality of word vector sequences; extracting context information of the plurality of word vector sequences to obtain a hidden state vector; based on the plurality of word vector sequences, using a syntactic graph convolutional network to obtain a syntactic graph; based on the hidden state vector, using a semantic graph convolutional network to obtain a semantic graph; based on the syntactic graph and the semantic graph, interactively learning syntactic information and semantic information to obtain a syntactic graph and a semantic graph after interactive learning; based on the syntactic graph and the semantic graph after interactive learning, predicting the sentiment probability distribution of the text to be predicted. The accuracy and stability of the judgment of sentiment polarity are improved.

The invention belongs to the technical field of pipeline safety assessment, and discloses a multi-dimensional information interconnection and autonomous evolution collaborative pipeline full-state safety assessment method. And capturing a high-order relationship of data through double hypergraph reasoning of the instance-level hypergraph and the modal-level hypergraph to realize efficient interconnection. According to the method, mode-level and instance-level hypergraph information features are extracted through hypergraph information propagation, high-order correlation is mined through double-graph information aggregation, cross-mode and cross-instance consistency information and exclusive information are output after feature recombination, multi-dimensional data deep fusion is promoted, and high-quality data support is provided for follow-up pipeline full-state safety assessment. A two-stage autonomous evolution mechanism of intra-class progressive calibration and inter-class knowledge migration is respectively adapted to slight fluctuation and significant change scenes of the deep sea environment: precise adaptation of environment perturbation is realized through dual-branch feature extraction and dynamic weight adjustment in a domain; model parameter dynamic optimization is completed between domains through spatial-temporal feature clustering and cross-domain knowledge migration, and dynamic environment self-adaption can be achieved without manual intervention.

The invention relates to the technical field of digital mechanical design, and particularly provides a two-dimensional multi-communication surface domain construction method, device and equipment and a medium, and the two-dimensional multi-communication surface domain construction method comprises the steps: obtaining a geometric figure file of a to-be-analyzed target aero-engine; thirdly, constructing an undirected graph to be processed based on geometric feature data in the geometric graph file, and performing triangulation processing on a first endpoint set in the undirected graph to be processed to obtain a triangulation graph; finally, constructing a dual graph of the triangulation graph, and determining a multi-connected surface domain information set according to a plurality of connected components in the dual graph; according to the invention, the recognition accuracy and efficiency of the two-dimensional multi-connected surface domain can be improved.

The invention provides a graph structure data processing method based on double graph neural network knowledge distillation, and relates to the technical field of graph structure data processing, and the method comprises the steps: inputting a graph structure data training set into a teacher model and a student model, and obtaining the knowledge distillation loss of an output layer; obtaining layer-by-layer knowledge distillation loss by utilizing an attention-based self-adaptive layer-by-layer knowledge alignment mechanism; utilizing an attention-based adaptive interlayer knowledge transfer mechanism to obtain interlayer knowledge distillation loss; and constructing a mixed loss function based on the knowledge distillation loss of the output layer, the layer-by-layer knowledge distillation loss and the interlayer knowledge distillation loss, training the student model to obtain a trained student model, processing the graph structure data set to obtain a graph structure data processing result, and storing the graph structure data processing result. And graph structure data processing based on double graph neural network knowledge distillation is completed. According to the method, the problems of high calculation cost, high memory occupation and low accuracy of graph neural network processing graph structure data are solved.

The invention discloses a space-time dual graph representation-based staying hot spot sequence inference method, which comprises the following steps of: constructing a space-time staying hot spot transfer relation graph based on a waybill track and staying hot spot data, and modeling a relation between a staying hot spot and a driving path; constructing a dual graph coding method based on a graph convolution variational auto-encoder model, and introducing an attention mechanism to jointly learn a space-time dynamic relationship between a staying hot spot and a driving path; performing embedding generation on the query request by using a denoising diffusion model, and capturing correlation between a historical transportation route and a current query; on the basis of a decoder of a recurrent neural network, a mask mechanism is introduced, an unreasonable staying hotspot sequence is effectively pruned, and the inference precision and efficiency are improved; performing model optimization by adopting multi-stage joint loss, and performing training by using an Adam optimizer; and deducing a staying hotspot sequence conforming to the driver behavior mode based on the historical track and the current query request. The method has wide application value.

The present invention discloses a method for predicting the popularity of event propagation based on a graph neural network. For each event text in an event propagation data sample, the feature vector of each user in the social network in the propagation of the event text is determined, and the temporal feature cascade graph corresponding to the event text is determined. A dual graph neural network is used to obtain the temporal user feature sequence of the event text based on the user feature vector and the temporal feature cascade graph. An event propagation popularity prediction model including a temporal convolutional neural network and a summation and pooling module is constructed. The event propagation popularity prediction model is trained using the temporal user feature sequence and popularity value of the event text in the event propagation data sample. The popularity value of the event currently propagating in the social network is predicted using the event propagation popularity prediction model. The present invention combines a graph neural network and a temporal convolutional neural network to improve the performance of event propagation popularity prediction.

The invention relates to a structure-semantic double-graph collaborative SAR image quality evaluation method, which comprises the following steps of separating an SAR image, and constructing a double-channel quality measurement set for independent modeling; indexes are obtained, correlation calculation is carried out, an index map is constructed, and each node corresponds to one index; on the basis of the index map, the dependency relationship between indexes is calculated from the structure dimension and the semantic dimension through self-supervised learning, the dependency relationship of the two dimensions is integrated, and an image level score based on the integration result is output; and constructing a measurement index shared with system analysis and a measurement index special for information retrieval, and carrying out quality measurement evaluation: after extracting a structure sub-graph, integrating an IR special index which is not contained in SAR prior into a global graph. The method is superior to a reference model in the aspects of recognition accuracy, recall rate, precision and efficiency, and a solution with high universality and good interpretability is provided for cross-modal image quality evaluation.

The present invention relates to a small-sample bearing fault diagnosis method based on a dual-graph network. The method involves selecting a test sample and a training sample of bearing faults, preprocessing them, collecting data points, and constructing a metadata set. A convolutional neural network is then used to extract features from the metadata set. The extracted features and the annotation information of the training samples are then input into the dual-graph network to determine the fault type of the test sample. Compared with existing technologies, this method offers advantages such as high accuracy and wide applicability.

The present invention belongs to the field of sentiment analysis, and specifically relates to an aspect-level sentiment analysis method based on a dual graph convolutional network, including: obtaining the context and aspects of the text to be analyzed, converting them into word vector embedding representations as inputs; using a bidirectional long short-term memory network to extract features from the word vector embedding representations of the context and aspects to obtain the hidden state representations of the context and aspects; after obtaining the hidden state of the context, performing position encoding on it and then using it as the initial input of the syntactic graph convolutional network to obtain syntactic features; at the same time, combining guiding vectors to encode the hidden states of the context and aspects to obtain an interaction matrix; using it as the initial input of the semantic graph convolutional network to obtain semantic features; connecting the syntactic features and semantic features as the final features to predict the sentiment polarity. The aspect-level sentiment analysis method provided by the present invention can improve the accuracy of aspect-level sentiment analysis from both semantic and syntactic aspects.

The invention discloses an overpass identification method under the support of a graph attention network. According to the method, road data of an open street map (OSM) is utilized to carry out an experiment, and the method comprises the following steps: firstly, carrying out data set extraction on an obtained road network of a city center through a point density clustering method to obtain a road data set needing to be identified; secondly, modeling a road network into a dual graph, and representing related nodes in the graph by combining local features and global features of the road; and finally, carrying out dichotomy in a supervised learning mode by using a graph attention network to realize the recognition of the overpass. Experimental results show that various classification indexes, such as the accuracy rate, the recall rate and the F1 value, all exceed 91%, the method is superior in the aspect of identifying complex and atypical overpasses, and in addition, the model is good in generalization ability on different city data sets and high in adaptability.

The invention discloses an automatic parallel method based on a dual graph Mangbar network and strategy gradient optimization, and the method comprises the steps: firstly obtaining a public AI model data set, carrying out the operator fusion of each calculation graph G, and obtaining a feature matrix X; secondly, constructing a double TMAN comprising a TMAN branch and a decoupling graph neural network branch, and obtaining feature representations XM and XD from the feature matrix X in the two branches; xM and XD are averaged, the averaged XM and XD are input into an LSTM network for feature fusion, a feature representation # imgabs0 # of the double Titman-Bar network is obtained, finally the feature representation # imgabs1 # is input into a reinforcement learning iteration solving module, and an optimal parallel strategy is obtained through continuous iteration and optimization of an intermediate reward value. According to the method, the graph embedding expression capability is enhanced, and the problems of inaccuracy and stability caused by overlarge new and old strategy change difference of a traditional strategy gradient algorithm in the equipment placement problem are effectively solved.

The invention provides an interest point recommendation method and device based on an association mode and heterogeneous double graphs and a storage medium. The method comprises the steps that a user information set, an interest point information set, an interest point category information set and a user sign-in time information set are acquired; constructing an association mode according to the user information set, the interest point information set, the interest point category information set and the user sign-in time information set; respectively constructing a first heterogeneous graph and a second heterogeneous graph according to the association mode and the set; according to the association mode, based on vector embedding, respectively determining a first decomposition graph of the first heterogeneous graph and a second decomposition graph of the second heterogeneous graph; based on an information entropy weighting method, determining a first information entropy and a first weight corresponding to the first heterogeneous graph, and determining a second information entropy and a second weight corresponding to the second heterogeneous graph; and according to the first information entropy, the first weight, the second information entropy and the second weight, determining a recommendation score of each interest point. According to the method, the interest point recommendation accuracy can be improved.

The embodiment of the invention provides a maximum segmentation solving method based on primal dual graph neural network learning optimization and related equipment, and the method comprises the steps: firstly, obtaining an image maximum segmentation model which comprises an adjacent objective function and a one-hot vector parameter; then, simplex relaxation conversion is carried out on one-hot vector parameters in the image maximum segmentation model, a relaxation continuous optimization model is obtained, and the relaxation continuous optimization model comprises continuous parameters; thirdly, performing iterative solution on the relaxation continuous optimization model based on an adjacent objective function, continuous parameters and a dual hybrid gradient neural network to obtain a relaxation feasible solution; and finally, sampling is carried out based on the probability distribution of the relaxation feasible solution, a target feasible solution of the image maximum segmentation model is obtained, the target feasible solution is used for segmenting image data corresponding to the image maximum segmentation model into multiple pieces of subset image data with the maximum total weight, and the solving efficiency of the maximum segmentation model is greatly improved.

This invention relates to the field of software engineering technology and discloses a method and system for generating code annotations based on a dual graph neural network. The method includes: acquiring source code and natural language annotations as source code, preprocessing the source code, and constructing training data based on the preprocessed source code and natural language annotations; constructing a code processing model, training the code processing model using the training data, and obtaining a trained code processing model. The code processing model includes a dual graph module, an encoder, an aggregator, and a decoder. The dual graph module parses the preprocessed source code to obtain an abstract syntax tree (AST), and constructs a syntactic dependency graph and a semantic dependency graph based on the AST; the encoder obtains a first encoding representation based on the syntactic dependency graph and a second encoding representation based on the semantic dependency graph; the aggregator obtains an aggregate graph representation based on the first and second encoding representations; the decoder generates natural language annotations based on the first, second, and aggregate graph representations; and inputting the code to be annotated into the trained code processing model to obtain natural language annotations. This invention can more effectively encode code structure, improve the accuracy of annotation generation, and enhance the generalization ability of the code processing model.

The present invention discloses a knowledge tracing modeling method and system based on a dual graph neural network, mainly related to the fields of intelligent education and educational big data mining. It includes a question-answering interaction node: based on the question information, adding the possible answering situation of the student to this question (i.e., answering correctly or wrongly), and fusing it into the student's question-answering interaction, which serves as the node for constructing a graph; a concept association graph: constructing a hypergraph between the question-answering interaction nodes, and using a hypergraph convolutional network to obtain the representation of each question-answering interaction node, which incorporates the association information between the questions and knowledge concepts; a directed transfer graph: constructing a directed graph between the question-answering interaction nodes, and using a directed graph neural network to obtain the representation of each question-answering interaction node, which incorporates the transfer information between the question-answering interaction nodes. The beneficial effects of the present invention are as follows: it can improve the quality of teaching work and achieve personalized teaching.

The invention relates to the technical field of data analysis, and provides a dynamic hierarchical rendering and context awareness-based report header management method, which comprises the following steps of: acquiring financial index historical data, identifying a supervision period type, processing time sequence data through a supervision period embedding layer and a three-layer attention mechanism of a hierarchical time sequence encoder, and performing dynamic hierarchical rendering and context awareness; outputting a time sequence weight feature vector; constructing a main graph and a constraint graph by using a dual graph convolutional network, propagating information through a constraint perception message transfer function, adjusting a graph topological structure according to a constraint default degree, and outputting an index relation weight matrix; inputting the time sequence weight feature vector and the index relation weight matrix into a neural symbol fusion network to obtain a final display weight value; and sorting and layering the financial indexes by adopting a dynamic layering strategy based on the weight values, and outputting a layered rendered report header. According to the method, the accuracy and adaptability of business index importance weight prediction are improved, and intelligent header layout optimization is realized through a dynamic layering strategy.

This invention provides a method and system for crack recognition in ground-penetrating radar (GPR) images based on frequency-domain enhanced YOLOv11. The method comprises the following steps: S1, constructing a GPR B-scan image dataset containing road cracks and dividing it into training and validation sets; S2, constructing a PFAE-YOLOv11 feature extraction model, which embeds a pyramid frequency attention extraction module into the YOLOv11 backbone network; S3, training the PFAE-YOLOv11 feature extraction model using the training and validation sets to optimize network parameters; S4, inputting the GPR image to be identified into the trained model and outputting initial detection bounding boxes for the cracks; S5, constructing a dual graph convolutional inference module, using the initial detection bounding boxes output in step S4 as graph nodes, and using a graph convolutional network to infer the topological relationships of the cracks, outputting corrected continuous crack paths. This invention significantly improves the accuracy, completeness, and anti-interference capability of crack detection in GPR images.

The invention discloses a multi-port inverter topology derivation method based on an even graph, and the method comprises the steps: constructing a mapping rule based on the even graph, mapping components in a multi-port inverter into edges in the even graph, and mapping circuit nodes, a DC source and AC ports in the multi-port inverter into points in the even graph; then, basic circuit constraints are converted into graph constraints based on a mapping rule of the even graph, so that the minimum degree of each point is obtained; determining the degree of each point in combination with the handshake theorem, and further deriving an even graph meeting the graph constraint; in addition, topology type and more source expansion can be carried out on the even graph, so that diversified effective even graphs are obtained; and finally, the diversified effective even graph is converted into a topological graph of the multi-port inverter.

The invention provides a grid parameterization method and device, equipment, a storage medium and a program product. The method comprises the steps of obtaining a first target grid; the first target grid is a topological structure to be parameterized; the first target grid comprises a plurality of patches; segmenting the first target grid based on the dual graph to obtain a second target grid; determining whether the second target grid meets a preset condition or not; the preset condition is used for indicating whether the second target grid still needs to be subjected to secondary segmentation; if the second target grid meets the preset condition, determining the torsion resistance of the second target grid, and determining a third target grid based on the torsion resistance of the second target grid; adopting a preset parameterization algorithm to carry out parameterization mapping on the third target grid so as to obtain initial parameterization coordinates corresponding to the third target grid; and arranging the initial parameterized coordinates corresponding to the third target grid in a preset parameterized space to obtain target parameterized coordinates corresponding to the third target grid.

The present application relates to the technical field of computer-aided design, in particular to a distribution box thermal fault prediction system based on a mechanism model, which comprises a model voxelization processing module, used for calling a three-dimensional model of a distribution box containing busbars and circuit breaker components, performing spatial discretization on the three-dimensional model of the distribution box, establishing thermal conduction connection edges between adjacent voxel units, and generating a voxelized dual graph.In the present application, the number of non-empty grids is counted and the streamline fractal dimension is calculated by covering different scale space grids, so that the geometric distribution characteristics of the flow field are converted into quantifiable complexity indicators, and then the flow field dimension attenuation coefficient distribution is generated in combination with the reference dimension value under the standard operating condition, thereby realizing quantitative identification of the dust deposition state of the air inlet.The thermal fault prediction is extended from a single temperature criterion to the structure coupling and flow evolution level, the forward-looking of thermal anomaly identification is improved, and the calculation burden caused by the model size is reduced.

The present invention relates to a perspective-level text sentiment classification system based on a dual graph convolutional neural network, including a text preprocessing module for performing feature extraction on perspective-level text; a text semantic information acquisition module for capturing bidirectional semantic dependency relationships of the text; an attention encoding module for capturing the global internal correlation of the text word sequence and generating a text semantic relationship graph; a related semantic graph convolutional neural network module that applies GCN to the text semantic graph to model the sentence structure; a text syntactic information acquisition module for capturing text information based on dependency syntax; a dependency syntax graph convolutional neural network module that directly applies GCN to the sentence dependency tree to model the sentence structure; a bidirectional mapping module for exchanging relevant features between semantic GCN and syntactic GCN information; and an emotion category output module that uses a classification function to obtain the final sentiment classification result.

The present application belongs to the technical field of pipeline safety assessment, and discloses a pipeline full-state safety assessment method based on multi-dimensional information interconnection and autonomous evolution coordination. The high-order relationship of data is captured through dual hypergraph reasoning of instance-level hypergraph and modal-level hypergraph, and efficient interconnection is realized. The modal-level and instance-level hypergraph information features are extracted through hypergraph information propagation, the high-order correlation is mined through dual graph information aggregation, and the cross-modal and cross-instance consistent information and exclusive information are output after feature reorganization, which promotes the deep fusion of multi-dimensional data and provides high-quality data support for subsequent pipeline full-state safety assessment. The two-level autonomous evolution mechanism of intra-class gradual calibration and inter-class knowledge transfer is respectively adapted to the scenes of slight fluctuation and significant change of deep sea environment: within the domain, the dual-branch feature extraction and dynamic weight adjustment are realized to accurately adapt to the environmental perturbation; between the domains, the spatiotemporal feature clustering and cross-domain knowledge transfer are completed to realize the dynamic optimization of model parameters without manual intervention, and the dynamic environment self-adaptation is realized.

This paper discloses a reference image segmentation method based on cross-modal dual graph alignment, belonging to the field of multimodal image segmentation. This method innovatively proposes a "part-unity-whole" paradigm, mapping the extracted visual and textual features to a unified latent representation structure before performing cross-modal fusion. This facilitates the explicit alignment information extracted by the model, effectively enhancing the final segmentation effect.

The present application belongs to the technical field of defect detection, and discloses a kind of defect detection method, device, equipment and storage medium, comprising: mesh product image is identified to mesh, and the identified mesh is used as node to build directed graph;The dual of directed graph is calculated, and the dual graph is obtained;With the edge in dual graph as reference, set the region of interest, segment product image, obtain edge image set;Each image in edge image set is scored by the classification model obtained by pre-training, and the scoring result is pulled back to the dual graph, to obtain weighted directed graph;According to weighted directed graph, defect classification is carried out.The present application indirectly locates the edge of mesh in mesh product image through dual graph, generates edge image set, scores each edge image in edge image set through classification model, obtains weighted directed graph, and then classifies defects through weighted directed graph, to ensure that mesh product can be automatically detected for defects, and the robustness and accuracy of mesh product defect detection are improved.

A recommendation system based on double graph representation learning pre-training model, comprising: a data entry module, a meta feature extraction module, a graph construction module and an intelligent recommendation module, wherein: the data entry module enters the model data and dataset data of the external data source and outputs to the meta feature extraction module after parsing; the meta feature extraction module extracts and aggregates the meta feature vectors of the model and the dataset; the graph construction module constructs the double graph representation of the model graph and the dataset graph based on the meta feature vectors, and calculates the architecture feature similarity between the models and analyzes the label weight relationship between the datasets; the intelligent recommendation module uses a deep recommendation model based on residual graph convolution and multilayer perceptron to predict the regression accuracy of the dataset based on the double graph representation and the corresponding meta feature vectors, and then obtains the result list recommended by the model. Through meta feature extraction of the model and the dataset, and double graph representation learning based on the similarity relationship, the present application can effectively capture the complex relationship between the dataset and the model, thereby realizing efficient and accurate model recommendation.

The invention provides a graph structure-based traditional block property unit spatial relationship expression and topology construction method and system, and the method comprises the steps: firstly obtaining a property unit set in a block range, calculating the mass center of each property unit, constructing a mass center point set, and then constructing an adjacency relationship between the property units through a graph structure, the original graph is adjacent to the original graph, and a space unit defined by the boundary of the property unit is identified through plane embedding; then, establishing a dual graph by taking a space unit as a node, and completely expressing a connected network of a medium space in the block; through cooperative representation of an original adjacent graph and a dual graph, spatial organization characteristics of a traditional block can be systematically and accurately described, and a unified data basis and an analysis framework are provided for applications such as city design, spatial form analysis and fire evacuation.