38 results about "Citation network" patented technology

The invention discloses a graph neural network link prediction method based on multi-dimensional similarity, and aims to improve the accuracy and generalization ability of missing link prediction in a complex network. The method is suitable for social networks, citation networks, recommendation systems and other actual scenes with isomerism, sparsity and dynamic evolution characteristics. In order to solve the problem that a traditional method only depends on local adjacency information or single topological similarity and is difficult to capture a high-order structure relation and multi-dimensional feature association, a unified measurement system fusing structure similarity, attribute similarity and path similarity is constructed, and potential association between nodes is deeply mined. By introducing a self-adaptive feature weighting mechanism, the model can dynamically adjust the multi-dimensional similarity fusion weight according to network features, and the expression and distinguishing capability of the node relationship is enhanced. On the basis, the deep representation learning advantage of the graph neural network is combined, a model structure with the selective feature fusion capability is designed, and precise modeling of a complex link generation mechanism is achieved. The method has good expandability and interpretability, and prediction deviation caused by network heterogeneity can be effectively relieved. Experimental results show that the method is obviously superior to the existing mainstream method on a plurality of real network data sets, and has high theoretical value and wide application prospect.

The invention discloses an academic community discovery and analysis method driven by a citation network, and the method comprises the steps: constructing the citation network, constructing an adjacent matrix A and a node attribute matrix X according to the citation network, and extracting a core sub-network information matrix S based on a k-core algorithm; constructing a dual-channel sparse graph attention auto-encoder, respectively taking (X, A) and (S, A) as input of the two channels to learn low-dimensional embedding of the two channels, and obtaining joint embedding Z through a dynamic weighted fusion strategy; reconstructing adjacent matrix information by adopting an inner product decoder, reconstructing node attribute characteristics and core sub-network information, and calculating reconstruction loss; and inputting the joint embedded Z into a self-supervised clustering module, performing joint optimization on the information embedding and reconstruction module and the self-supervised clustering module, and finally outputting a group division result of the papers / authors. According to the method, complementary fusion of attributes and a core structure is realized, robustness in noise and sparse scenes is enhanced, and discriminability and stability of group division are improved.

The invention relates to the technical field of literature management, in particular to a scientific research literature management system and method based on core literature identification and frontier prediction, and the system comprises a data collection and preprocessing module, a core literature identification module, a frontier literature supplement module, a trend analysis and prediction module and an error processing and adaptive engine. And the data acquisition and preprocessing module is used for realizing automatic acquisition, cleaning and standardization of literature data. By combining citation network structure analysis and frontier semantic modeling, the scientific research literature management system with high accuracy, interpretability and perspectiveness is constructed, the literature screening efficiency is improved, an intelligent, visual and predictive scientific research auxiliary tool is provided for scientific research personnel, and the scientific research literature screening efficiency is improved. The method can be widely applied to scientific research activities such as topic selection design, review writing and research trend judgment.

According to the citation network node intra-class mixing classification method based on the node class centrality, class center sampling, intra-class mixing, neighbor selection, edge screening and adaptive loss are not isolated, an efficient cooperative enhancement chain is formed, class center nodes are screened out through construction of a multi-stage class center system, the nodes of the class centers are fused, and therefore the classification efficiency of the citation network nodes is improved. After fusion, connection is not performed on source nodes (namely parent nodes) but high-quality nodes screened out through integrated prediction consistency, then dynamic edge screening (node degrees and semantic similarity) is performed on the high-quality nodes, and through organic combination of noise suppression and structure optimization, the accuracy and generalization of citation network node classification are effectively improved; the method has wide use value and application prospect in the field of image processing.

This invention relates to the field of computer complex network optimization technology, and discloses a method for mining key nodes in a network based on a discount strategy and an improved discrete crow search algorithm. The method includes: first, preprocessing the citation network to convert it into an adjacency matrix, and then reversing the network to obtain a reverse network; then using the LRDiscount algorithm to initially screen the nodes in the reverse network to obtain a candidate node set. C Next, the candidate node set is optimized according to the local optimization process of the improved discrete crow search algorithm. C Optimization is performed; finally, the optimal set is selected from the optimized node set, and the node influence is evaluated to obtain the final result. k Key seed nodes. Compared with existing technologies, this invention combines the influence discount strategy of network nodes with an improved discrete crow search algorithm. It spreads influence by updating node positions in the process of mimicking crow search, and finds key nodes by the marginal gain generated by individual crows walking in the citation network.

The invention discloses a dynamic network link prediction method based on node importance and edge feature learning, and aims to improve prediction precision and time-dependent modeling capability of missing links in a complex dynamic network. According to the method, the influence of node centrality and attribute characteristics on network evolution is comprehensively considered by constructing time-aware node importance measurement; meanwhile, multi-dimensional feature modeling is carried out on the edges, the features comprise topological structures, node similarity and time evolution features, different features are fused through a self-adaptive weighting mechanism, and the expression capacity of the node relation is improved. On the basis, deep dynamic embedding of node representation is realized by combining a graph neural network and a time sequence modeling technology, so that an evolution rule of a node structure along with time change is captured. The method is suitable for practical scenes with remarkable dynamic evolution characteristics, such as social networks, citation networks and recommendation systems, and has good expandability and interpretability. Experimental results show that the method is superior to an existing link prediction method on various dynamic network data sets, and has remarkable advantages in the aspects of prediction accuracy, time sensitivity and generalization ability.

The invention discloses a community discovery method of a graph neural network based on multi-view information fusion, and belongs to the technical field of data mining. The method comprises the following steps: preprocessing data, performing PCA dimension reduction on an attribute matrix, and normalizing an adjacent matrix; inputting the correlation matrix combination into an automatic encoder and a graph attention automatic encoder to obtain a new matrix representation and fusing the new matrix representation into a final node representation matrix; then back-propagating the optimization model by using various loss functions; and finally, community division is realized by using a k-means clustering algorithm. According to the method, the structure and attribute information of the original data are fully utilized, multi-view information is effectively fused, the accuracy of community discovery is improved, and the method has great significance in the fields of research on citation networks, recommendation systems and the like.

The application provides a keyword reverse propagation algorithm based on a citation network structure, and comprises the following steps: a spring charge model is established, force-directed layout processing is performed, and a force-directed layout graph is established; a keyword propagation model is established by using a reverse propagation algorithm, and a keyword weight change contrast curve is obtained; a citation network model is constructed by using the force-directed layout graph; iterative calculation is performed on the force-directed layout graph until the energy state in the force-directed layout graph reaches a minimum value; while the citation network is iteratively calculated, the keyword weight in the citation network model is adjusted, and a converged citation network layout graph is calculated. The application has the beneficial effects that the entire network is taken as a main body, keywords owned by cited documents are selected at a certain probability and are propagated backward along the network to the citing documents, the weight of the keywords is increased while the text clustering idea is retained, and clear visual data effects are obtained through force-directed layout.

The invention discloses an educational academic literature tracing method and system based on retrieval enhancement generation. The method comprises the following steps: performing fine-grained analysis on the multi-source literature, constructing a document object containing fields such as a title, an abstract, a methodology, an experimental result and a conclusion, and establishing a field-level index and a citation network feature score; identifying an academic intention queried by a user by utilizing a large model, dynamically loading a weight mapping table according to the academic intention, and performing weighted rearrangement on multiple paths of retrieval results to obtain candidate core literatures; generating a traceability text with an explicit label based on the candidate literature; and executing reference consistency verification by using the natural language inference model, and executing illusion correction according to a verification result. According to the method, through structured field analysis and dynamic rearrangement of intention driving, the problems of semantic fragmentation and reference fictition when a general RAG is used for processing complex academic literatures are solved, and the academic traceability preciseness and accuracy are remarkably improved.

The application provides a core set calculation method for a graph structure, relates to the field of graph structure, and constructs a citation network graph and generates an adjacency vector of each node, calculates a DOPH signature of each adjacency vector, and then performs clustering division based on the DOPH signature, calculates by using a GA error, and accelerates by using a clustering-based method, and meanwhile, the application combines a reverse reachable set of the node, selects the node to form a core set, so that the application constructs the core set capable of representing the information of the whole graph structure based on the propagation characteristics, local structure similarity and global role information of the nodes in the graph. Further, the framework introduces a graph adaptive sampling strategy and an adjustable covering mechanism, can dynamically balance the calculation efficiency and the representation accuracy according to the task requirement, and thus realizes the automatic balance between the effect and the cost.

The invention relates to the technical field of literature clustering, in particular to a literature clustering method based on a citation network and large language model analysis, which comprises the following steps of: obtaining and preprocessing literatures; clustering is carried out on the reference literature questions; constructing a clustering quality evaluation mechanism; screening highly cited literatures and cited literatures; carrying out abstract analysis and panoramic scanning; and generating a structured review and visualization. According to the method, a large language model is used for carrying out clustering analysis on reference literature topics, finding out mainstream clusters, ensuring comprehensiveness and systematicness of the review content, screening out highly-introduced literatures from the mainstream clusters, ensuring high quality and authority of the review content, analyzing the abstract of the literatures by using the large language model, extracting important topics, and improving the accuracy of the review content. The accuracy and depth of the review content are ensured, and the comprehensiveness, accuracy, systematicness and efficiency of literature review can be remarkably improved.

Embodiments of the present application provide a text analysis method and device, electronic equipment and storage medium, and relate to the technical field of data mining. The method comprises: constructing a text citation network corresponding to a set of texts to be analyzed based on the citation relationship between each text in the set of texts to be analyzed in a target field; selecting a plurality of candidate paths from the text citation network; performing at least one clustering operation on the plurality of candidate paths until a preset ending condition is met, and at least two clustering centers obtained when the preset ending condition is met are taken as knowledge evolution paths corresponding to at least two subfields in the target field respectively. Through analysis of the set of texts to be analyzed in the target field, embodiments of the present application obtain the development context corresponding to each subfield in the target field, and the analysis result is more comprehensive; the text semantic information and network structure information of the candidate paths are considered, the information utilization is more comprehensive, and the analysis result is more accurate.

The invention provides a graph structure-oriented core set calculation method, and relates to the field of graph structures, and the method comprises the steps: constructing a citation network graph, generating an adjacent vector of each node, calculating a DOPH signature of each adjacent vector, carrying out the clustering division based on the DOPH signatures, carrying out the calculation through a GA error, and carrying out the acceleration through a clustering-based method. And meanwhile, a core set is formed by combining a reverse reachable set of the nodes and the selected nodes, so that the core set capable of representing total graph structure information is constructed on the basis of propagation characteristics, local structure similarity and global role information of the nodes in the graph. Furthermore, a graph self-adaptive sampling strategy and an adjustable coverage mechanism are introduced into the framework, the calculation efficiency and the representation precision can be dynamically balanced according to task requirements, and therefore automatic balance between the effect and the cost is achieved.

The application relates to the technical field of document management, in particular to a scientific research document management system and method based on core document identification and front prediction, which comprises a data acquisition and preprocessing module, a core document identification module, a front document supplement module, a trend analysis and prediction module and an error processing and adaptive engine; the data acquisition and preprocessing module is used for realizing automatic acquisition, cleaning and standardization of document data. The application combines citation network structure analysis and front semantic modeling to construct a scientific research document management system with high accuracy, interpretability and foresight, which not only improves the document screening efficiency, but also provides an intelligent, visual and predictive scientific research auxiliary tool for scientific researchers, and can be widely applied to scientific research activities such as topic design, review writing and research trend judgment.

The invention provides a local quotation recommendation method and system based on a quotation statement heterogeneous network, and relates to the technical field of information recommendation, and the method comprises the steps: carrying out the data preprocessing and quotation relation analysis of a quotation statement sentence in a paper according to a preset measurement index and a preset semantic feature of local quotation recommendation, and obtaining a quotation statement statement; constructing a citation statement heterogeneous network; and for the citation statement heterogeneous network, performing node low-dimensional embedded learning, acquiring a citation relation path instance based on reinforcement learning, generating a citation relation meta-path diagram, performing citation recommendation and generating a recommended literature list. The technical problem of poor paper recommendation effect caused by lack of citation context information in a citation embedding network in the prior art is solved, and the technical effect of improving the citation recommendation accuracy and recommendation quality is achieved by constructing a citation statement heterogeneous network and accurately identifying the deep semantic relevance between citations.

The application discloses a citation network article classification and recommendation method based on a graph integrated neural network, which comprises the following steps: performing structure enhancement on an original citation network, performing feature enhancement on initial features of the original citation network, and obtaining sub-citation networks and new features respectively; training base classifiers based on the sub-citation networks and the new features and performing deep integration, performing integration when data flow passes through each layer of base classifiers, taking an integration result as an input of a next layer, adjusting the base classifiers in training based on neighbor information, and obtaining a trained graph integrated neural network model; inputting an article to be classified of a citation network into the trained graph integrated neural network model, obtaining a probability that the article is predicted to correspond to a category, and classifying and sorting the article based on the obtained probability. The base classifiers are trained based on the sub-citation networks and the new features and deep integration is performed, so that the close neighbor information between the base classifiers influences each other, and the classification performance of the article and the effectiveness of recommendation are improved.

This invention discloses a community detection method, system, device, and medium based on a graph dual autoencoder, relating to the field of community detection technology. The method includes inputting a given citation network into a graph dual autoencoder to obtain graph structure representation information and graph attribute representation information; fusing the graph structure representation information and graph attribute representation information to obtain fused graph representation information; and using a clustering method to divide the fused graph representation information into communities to obtain the community detection result. This invention improves the accuracy of community division in citation networks.

The application relates to the technical field of citation network node classification, and provides a citation network node classification method and system based on graph contrast learning, which comprises the following steps: obtaining two enhanced views of citation network graph data by using data enhancement, and obtaining enhanced view node embedding representation by using an encoder; performing node clustering based on original graph data by using a K-means clustering algorithm, setting a pseudo label based on a clustering result, and sharing the same pseudo label by similar nodes; obtaining probability representation of a node sample as a positive example relative to an anchor point by using a PU learning probability estimator; calculating a node negative example tendency score; fusing the original view negative example tendency score and the enhanced view cosine similarity to construct a node negative example measurement index; training a model to obtain optimized node embedding representation; and obtaining a node classification result according to the embedding representation. The application fully utilizes PU learning, makes the graph contrast learning obtain more discriminative representation, and improves the citation network node classification performance of the graph contrast learning.

The application relates to the technical field of natural language processing, and particularly discloses a paper classification method for a citation network, a device and a medium, the method comprising the following steps: graph data preprocessing of the citation network, node centroid topology enhancement for the majority class and the minority class, and multi-period centroid node information fusion for the minority class. The method combines the node centroid topology enhancement and the multi-period centroid node information fusion mechanism, improves the classification performance of the graph neural network for the minority class nodes on the unbalanced graph, and improves the classification accuracy of different types of papers in the citation network.

The application provides a geoscience hotspot extraction and visualization method and system based on literature, comprising the following steps: step 1, constructing a literature citation network according to geoscience journal literature; step 2, clustering the geoscience journal literature based on the citation network; step 3, extracting hot keywords based on text statistics by adopting a theme construction method; step 4, extracting hot keywords based on text semantic information by adopting text embedding representation clustering; step 5, fusing and screening the extracted keywords, and obtaining geoscience research hot keywords in combination with paper clustering; and step 6, constructing a hot core paper set and a citation network thereof, and performing visual display. The application constructs a geoscience field hotspot mining and visualization scheme, can comprehensively utilize text statistics and semantic information to mine research hotspots compared with existing methods, can reveal the research focus and front direction of the current field, and helps researchers better understand the discipline development trend and grasp the front dynamic.

The application provides a citation network node classification method and system fusing GCN and multiple classifiers, wherein the classification method comprises the following steps: regarding the whole citation network as a non-directional graph G comprising node attributes and topological structures; calculating an adjacency matrix and a feature matrix of the non-directional graph G; initializing an edge weight matrix of the non-directional graph G, and calculating the edge weight of the non-directional graph G according to the feature matrix; converging the calculated edge weight to the nodes at both ends of the edge, updating the feature matrix; filtering and amplifying the features in the updated feature matrix; inputting the adjacency matrix and the updated feature matrix into n classifiers respectively for prediction and fusing the prediction results to obtain the final classification result. The classification method comprehensively considers the effective semantic information in the network, can obtain more accurate and stable classification effect through the prediction of multiple classifiers and the fusion by using fuzzy integration.

The application discloses a literature classification method and system based on a twin graph neural network and a cluster structure, and the method comprises the following steps: detecting a cluster structure in a citation network by using a clustering algorithm to obtain cluster structure information; adaptively modulating the weight of the connection between clusters; propagating the features of the citation network and the original citation network after the weight modulation through a twin graph neural network structure to obtain neighbor node information and obtain two different feature representations of the literature nodes; inputting the features with the cluster information after the feature propagation and the original features into a feature fusion module for feature fusion; and inputting the fused features into a linear multi-classifier to obtain a final classification result. The application effectively improves the classification accuracy by retaining the cluster structure in the citation network.

The application discloses an expert influence maximization method based on graph convolution and DBSCAN algorithm, and relates to the field of influence maximization research under a citation network. First, each expert is regarded as a node, and a citation network is constructed according to the citation relationship between the experts, a graph convolution neural network is used to extract features of the citation network, and a feature representation of each expert node is obtained; then, a matrix is clustered by using a DBSCAN algorithm, different communities are obtained, and a spectral clustering method is used to divide the expert nodes into different clustering clusters, and each clustering cluster represents an expert group with high influence; finally, the expert nodes are sorted according to influence scores, and thus a list of experts with the most influence is obtained. Compared with the prior art, the method provided in the application can better identify experts with high influence in the citation network, and is a relatively excellent influence maximization algorithm.

The invention discloses a graph self-encoding mask strategy optimization system and method for a link prediction task. The system comprises a mask generation module, a self-adaptive mask strategy module and a graph self-encoding module, the mask generation module is used for calculating an importance score of a reference edge connecting two literatures in the original literature reference network; the self-adaptive mask strategy module is used for dynamically adjusting a mask strategy according to the importance score and generating a mask edge set; and the graph self-encoding module is used for performing mask processing on the original literature reference network according to the mask edge set to obtain a masked graph structure, performing node representation learning and link prediction on the masked graph structure, and optimizing model parameters by using a loss function.

A method and device for quantifying and distributing author contribution based on an academic network, the method comprising: S1: writing a network crawler program and collecting paper data, citation relationship data between papers, and author data of the papers; S2: constructing a citation network of a paper p0 for which author contribution score points need to be calculated, the nodes of the network being scientific papers and the edges being citation relationships between the papers; the network structure being divided into two layers, the first layer being a reference literature layer of the paper p0, and the second layer being citations of the reference literature layer, including the paper p0 and other citations; S3: calculating the contribution score of each author in the paper p0 in each paper in the citation layer, and constructing an author contribution matrix A of the paper p0; S4: calculating the number of times that the paper p0 and each paper in the citation layer including the paper p0 jointly cite the papers in the reference literature layer, and constructing a common citation intensity matrix S; and S5: multiplying the contribution matrix and the common citation intensity matrix to obtain the final contribution score C of the authors of the paper p0.

The application discloses a kind of construction methods and devices of high-speed rail technology evolution graph.The construction method includes: obtaining patent data set related to high-speed rail technology and classifying according to technical field, obtain multiple technical subsets;Based on PatentsBERTa model and cosine similarity calculation formula, obtain multiple similarity data sets;Obtain the similarity threshold of each technical subset, and based on the similarity threshold, obtain multiple candidate patent groups corresponding to each technical subset respectively;Based on the candidate patent group corresponding to each technical subset, build the time evolution graph and citation network graph corresponding to each technical subset, and convert into network data using graph projection, construct multiple evolution knowledge graphs;Obtain the target technology of pre-set, and based on the evolution knowledge graph corresponding to the technical subset of target technology, construct the evolution subgraph of target technology.The construction method provided by the application can identify the evolution path of each sub-technology in high-speed rail technology.

The invention relates to the technical field of natural language processing, and particularly discloses a paper classification method and device of a citation network and a medium, and the method comprises the following steps: graph data preprocessing of the citation network, node centroid topology enhancement aiming at majority classes and minority classes, and multi-cycle centroid node information fusion aiming at the minority classes. According to the method, node centroid topology enhancement and a multi-cycle centroid node information fusion mechanism are combined, so that the classification performance of the graph neural network for minority class nodes on the unbalanced graph is improved, and the classification accuracy of different classes of papers in the citation network is improved.

The invention discloses a social network node classification method and system based on comparative learning robust dynamic graph representation. Relates to the technical field of social network node classification. According to the technical scheme, a time sub-graph is generated through neighbor sampling, a noise recognition function is used for eliminating noise edges to generate a de-noising enhancement sub-graph, and meanwhile structure and time noise are introduced to generate a noise-adding enhancement sub-graph; fusing node features and time information by means of a time embedding encoder sharing parameters to obtain node embedding of the original sub-graph and the de-noising enhancement sub-graph and the de-noising enhancement sub-graph; the model is optimized through noise enhancement contrast learning and time contrast learning, so that the node representation adapts to a complex noise environment and captures a dynamic evolution law, and finally the node representation is used for downstream tasks such as node classification of citation network diagram data. According to the method, the de-noising and noise-adding enhancement sub-graphs are constructed, and a contrast learning framework is combined, so that the problem of noise interference in a dynamic graph is solved, the discrimination and robustness of node representation are improved, and the social network node classification performance is improved.

The invention discloses a citation network node classification method and system based on a hidden equidistant manifold. The invention provides a node classification algorithm for a citation network structure. The method comprises the following steps of: firstly, maximizing mutual information between paired sub-graph views related to a literature citation relationship through comparative learning by adopting a path mask strategy so as to fully capture structural characteristics of a citation network; meanwhile, calculating the matching degree between the degree prediction of the paper node and the degree of the original node in the mask quotation graph so as to ensure the structural consistency; and obtaining a potential space coordinate keeping the equidistant constraint through equidistant learning. The method can effectively improve the classification accuracy and robustness in the citation network node classification task, not only solves the node classification problem of high-dimensional complex data in the citation network, but also can retain the manifold structure information of the hidden space of the citation network.

The application discloses a kind of reference intention classification methods based on dynamic heterogeneous graph fusion network.Method includes: dynamically extracting reference sentence and its related context, combine chapter information to form text T;Using SciBERT pre-training model, the feature vector of text T is extracted;Complex relationship between nodes such as paper, chapter and author is expressed by constructing heterogeneous graph;Node features are extracted by dynamic heterogeneous graph network, and the node feature vector of heterogeneous graph is generated;The text feature vector of text T is fused with node feature vector, to form comprehensive features;Finally, the reference intention is predicted using classifier, and the model is optimized by loss function.The application extracts distinguishing semantic features from the internal structure of the paper and the cross-document relationship, enabling high-precision reference intention recognition in complex citation networks, and is particularly suitable for reference intention classification tasks in academic literature.