74 results about "Goal graph" patented technology

The invention relates to the technical field of attribute graph collection and release, in particular to an attribute graph collection and release method, system and device based on local differential privacy and a medium. Receiving disturbed data from each client; based on all disturbed data, estimating community division of the original graph structure and triangular counting of each node; obtaining a target graph structure based on community division and triangular counting; and on the basis of the target graph structure and the disturbed data, node attributes are optimized, so that node attribute distribution and community division are kept consistent, and a final publishable target attribute graph is obtained. The method has the advantages that strict requirements of local differential privacy are met on the privacy protection level, and multi-dimensional features such as a community structure, triangular counting and node attribute homogeneity are reserved in the published attribute graph at the same time; and the practical value of the synthetic data in applications such as downstream graph analysis, community discovery and personalized service is greatly improved.

The embodiment of the invention discloses a knowledge graph construction method and device, a storage medium and a terminal. Extracting a plurality of to-be-linked entities in the current text and to-be-linked relationships among the to-be-linked entities; matching each to-be-linked entity with each target entity in the target knowledge graph, and determining the to-be-linked entities meeting a first matching condition as to-be-updated entities; matching each to-be-linked relationship with a target relationship between target entities in the target knowledge graph, and determining the to-be-linked relationship meeting a second matching condition as a to-be-updated relationship; and updating the entity to be updated and all relation triples of the relation to be updated to the target knowledge graph. Through the active matching mechanism based on the existing knowledge of the target map, entities and relationships which exist in the current text and conform to the current semantic specification, structural constraint and knowledge rule of the target knowledge map can be effectively screened out, and the perception and adaptability to the dynamic change of the knowledge rule are remarkably enhanced.

Provided in the present application is a method for fusing operators in a computational graph, which method is applied to an AI compiling process. The method comprises: acquiring a target graph, wherein the target graph comprises a plurality of nodes and at least one edge, and the nodes are associated with operators in a computational graph; determining computation types of two nodes connected to a first edge, wherein computation logic of two operators corresponding to the two nodes both comprise a loop statement; and on the basis of a first computation type and a second computation type, fusing the loop statement of one operator into the loop statement of the other operator, so as to obtain a fused operator which is obtained by means of fusing the two operators. In the solution provided in the present application, it is not necessary to compress all loop statements of operators into one dimension and recalculate indexes for the operators, instead, two operators can be fused by means of computation types of the two operators, so that a high-performance fused operator can be obtained.

The application discloses a trigger node detection method and device, equipment and a storage medium, and relates to the technical field of graph backdoor detection. The method comprises the following steps: performing node vector learning on graph data through a target graph neural network to obtain a target node vector corresponding to the graph data; performing clustering screening on the target node vector through a target clustering algorithm to determine an abnormal node in the graph data; performing structural disturbance on the abnormal node, calculating a target drift score of the abnormal node after the structural disturbance; generating a discrimination threshold based on the target drift score, and screening a trigger node in the graph data from the abnormal node according to the discrimination threshold. Through the cooperative mechanism of the representation learning to establish the discrimination basis, the clustering screening to narrow the search space, the structural disturbance to expose the stability difference, and the statistical modeling to automatically make decisions, the technical problem that it is difficult to accurately identify the hidden trigger node in the graph data is solved, and the stability and reliability of the detection process are improved.

The invention relates to a layout generation method and device, equipment, a storage medium and a program product. The layout generation method comprises the following steps: acquiring a target graph and target layout precision; determining a numerical value effective standard according to the target layout precision; and based on the numerical value effective standard and the geometric information of the target graph, generating a periodic arrangement graph of the target graph, and obtaining a target layout. According to the method and the device, the periodic arrangement graph with the target layout precision can be generated, so that advanced resolution enhancement technologies such as reverse photoetching technology correction and the like can be conveniently implemented on the full-chip layout.

The invention discloses a similar resource identification method and device, equipment, a medium and a program product, and relates to the technical field of computers.The method comprises the steps that target graph data corresponding to a resource recommendation platform is obtained, and the target graph data comprises nodes, edges between the nodes and weights of the edges; the types of the nodes comprise resource nodes, label nodes and resource acquisition object nodes, and resource acquisition objects comprise objects of which resources are acquired on the resource recommendation platform; walking in the target graph data based on the meta-path in the target graph data to obtain a node pair; processing node pairs in the target graph data to obtain features of the nodes; and determining the similarity among the resources in the resource recommendation platform based on the characteristics of the resource nodes to obtain similar resources. The similar resources determined by the method not only can be matched in the aspect of content, but also can be matched in the aspect of resource acquisition objects, so that the recognition accuracy of the similar resources can be improved.

The application is suitable for the field of model explanation, and relates to a rule mining method and device for recommending model explanation, equipment and medium. For any user-item pair in graph data, a corresponding neighborhood graph and a connected subgraph are determined, a candidate subgraph is determined from the connected subgraph, a target subgraph is determined from the candidate subgraph according to a graph evaluation score, a target graph pattern is extracted from the target subgraph, for any variable in a pattern path of the target graph pattern, a target predicate is determined from all predicates corresponding to the variable, a candidate premise condition is formed by the variable and the target predicate, a candidate explanation rule is obtained according to the target graph pattern and a candidate premise condition set corresponding to all pattern paths in the target graph pattern, and a candidate explanation rule satisfying a preset condition is determined as a target explanation rule from all candidate explanation rules. The target explanation rule reflecting the prediction principle of the recommendation model is mined from the graph data as the global explanation of the recommendation model, and the effectiveness of the explanation is improved.

The invention relates to the technical field of data processing, in particular to a knowledge graph construction method and system for scientific and technological achievement management, and the method comprises the steps: obtaining an initial knowledge graph of each category of scientific and technological achievements, and according to the similarity between word vectors and structural feature vectors of a target entity and all entities in a reference graph, obtaining a knowledge graph of each category of scientific and technological achievements; obtaining a plurality of candidate entities of the target entity in the reference map, and screening out a plurality of to-be-aligned entities from all the candidate entities according to the difference between the attribute value sequence of the target entity and the predicted attribute value sequences of all the candidate entities, and according to the repetition condition of the target entity and each neighbor node in the to-be-aligned entity in the reference map, performing entity alignment between the target map and the reference map to obtain a fused knowledge map. According to the method, the accuracy of entity alignment between the knowledge maps constructed by different types of scientific and technological achievement data is improved.

The application provides a graph data processing method, system, device and medium, comprising processing a plurality of to-be-processed graph data in a training data set to obtain node features and edge features; generating a node feature matrix and a resistance variation array according to the node features and the edge features; generating first transition features according to a graph neural network, the node feature matrix and the resistance variation array; inputting the first transition features into one or more graph convolution layers in the graph neural network for weighted calculation to output second transition features; inputting the second transition features into a readout network previously constructed in the graph neural network to generate result features; adjusting weight parameters of the graph neural network according to the result features and a Hamiltonian loss function, realizing training of the graph neural network to obtain a target neural network; and generating target result features according to node features, edge features and the target graph neural network of target graph data. The graph data operation time is reduced, and the processing speed is accelerated.

Embodiments of the present application disclose a method, related device and equipment for entity recognition applied to natural language processing, which are used to improve the accuracy of entity recognition. The method of the embodiments of the present application comprises: obtaining a text to be recognized, obtaining corresponding syntactic relationship features and semantic features of each word to be recognized according to the text to be recognized, the syntactic relationship features comprising at least one of syntactic relationship features, part-of-speech combination relationship features and semantic dependency relationship features, obtaining corresponding fusion features of each word to be recognized according to the corresponding syntactic relationship features and semantic features of each word to be recognized, generating a basic graph network according to the fusion features of each word to be recognized and the fusion features of sample words, clustering the basic graph network according to a weight value to obtain a target graph network, the target graph network comprising a class set, and determining target entities belonging to an entity category in at least two words to be recognized according to the target graph network.

The invention discloses a trigger node detection method and device, equipment and a storage medium, and relates to the technical field of graph backdoor detection, and the method comprises the steps: carrying out the node vector learning of graph data through a target graph neural network, and obtaining a target node vector corresponding to the graph data; performing clustering screening on the target node vector through a target clustering algorithm, and determining abnormal nodes in the graph data; performing structural disturbance on the abnormal node, and calculating a target drift score of the abnormal node subjected to structural disturbance; and generating a distinguishing threshold value based on the target drift score, and screening trigger nodes in the graph data from the abnormal nodes according to the distinguishing threshold value. The technical problem that hidden trigger nodes in graph data are difficult to accurately recognize is solved through a collaborative mechanism of establishing a distinguishing basis through representation learning, reducing a search space through clustering screening, exposing stability difference through structural disturbance and performing statistical modeling automatic decision making, and the stability and reliability of the detection process are improved.

The invention provides a drawing operation method and device, equipment and a storage medium. Relates to the technical field of computers, in particular to the technical fields of drawing operation, graphic interaction and the like. According to the specific implementation scheme, a target drawing is displayed, the target drawing contains multiple existing primitives stacked in the depth direction, and the multiple existing primitives are in a visual state; in response to a selected operation executed on the target drawing, performing penetration processing on the target drawing in the depth direction based on the operation position of the selected operation on the screen and the operation frequency of the selected operation to obtain a target primitive selected by the selected operation; wherein each selection operation corresponds to one target primitive; and displaying the target primitive in a selected state.

The application discloses a kind of graph data query statement determination method, device, equipment and medium, it is related to computer technical field, including: obtaining graph data query information, and determine whether the graph data query information is legal;If the graph data query information is legal, then based on the graph data query information from local preset graph data query statement library filtering out graph data query statement;Obtain statement query configuration information, and based on the statement query configuration information from the graph data query statement determines out to be configured graph data query statement, and according to the statement query configuration information to the to be configured graph data query statement is configured, to obtain target graph data query statement.Through the above technical scheme of the application, the efficiency of graph data query statement determination can be improved, the diversity of business requirements is increased, and the security of graph data query statement is improved.

An inductive link prediction method based on subgraph and path comparative representation learning is characterized in that an overall knowledge graph comprises a plurality of structured triples et = (s, rT, o), surrounding subgraphs containing target nodes are extracted, isolated nodes and a complete neighbor relation are reserved, and node features of complete semantic information between neighbor nodes are obtained. And extracting a topological relation path between the head entity s and the tail entity o from the knowledge graph. Local structures and relation semantics are obtained through node-level relation coding, sub-graph-level aggregation perception message passing and an attention mechanism. And carrying out modeling on paths of adjacent relations of the sub-graphs to obtain features in the sub-graphs. A topological structure of a target map is associated with path representation, marginal-based loss is incorporated into distance scores of a positive path sample and a negative path sample, the positive path sample and the negative path sample which need to be distinguished are compared and learned through semantic information conveyed by a relation path, and a loss function is optimized through joint training.

This invention discloses a graph storage method for mixed query loads of transactional and analytical queries, belonging to the field of graph data storage. The method includes: storing graph data in a row-oriented storage structure before reaching the maximum capacity allocated in the LSM tree memory; when the written graph data reaches the maximum capacity, allocating new empty memory in the LSM tree memory to store the new graph data in a row-oriented storage structure, and converting the graph data in the old memory that has reached the maximum capacity into a column-oriented storage structure and migrating it to the LSM tree's external storage; in response to receiving mixed query concurrency requests, transactional query requests preferentially retrieve the first target graph data from the row-oriented storage structure of the LSM tree memory, while analytical query requests preferentially retrieve the second target graph data from the column-oriented storage structure of the LSM tree's external storage. This solution can reduce the response latency and computational resource consumption when handling mixed transactional / analytic queries.

The embodiment of the application provides a kind of based on multi-dimensional feature constraint's net body intelligent multi-model calling method and product, it is related to artificial intelligence technical field.The method comprises: obtaining directed graph structure;Wherein, directed graph structure includes multiple graph nodes and the node feature and the edge feature corresponding to each graph node;According to user task request, generate task request feature;According to task request feature and the multiple graph nodes in directed graph structure and the node feature and the edge feature corresponding to each graph node, one or more graph nodes in directed graph structure is determined as target graph node;According to target graph node, determine task processing path;Wherein, task processing path is used to call the model corresponding to target graph node according to the model calling order corresponding to task processing path when processing user task request;Solved the problem that the model called in prior art scheme exists poor matching, improves data processing efficiency and resource utilization.

The invention discloses a subgraph editing distance calculation method based on a graph neural network, and relates to the field of graph calculation and artificial intelligence, and the method comprises the following steps: obtaining a query graph and a target graph; generating node-level and edge-level representations for the query graph and the target graph through a unified graph isomorphism encoder to capture the influence of node and edge specific editing operation on graph topology; inputting the target graph into a self-adaptive graph mask module, generating mask scores of nodes and edges through a gating attention mechanism in combination with query graph representation, shielding irrelevant parts and dynamically balancing graph scale differences; and performing multi-head mask processing on the target map based on the mask score to generate a plurality of candidate substructures. According to the method, asymmetry can be effectively processed, fine-grained structure differences are captured, calculation precision and efficiency are improved, and the method is suitable for scenes such as drug discovery, social network analysis and recommendation systems.

The invention provides a code completion method, electronic equipment, a storage medium and a program product. The code completion method comprises the following steps: in response to a code completion request, determining a target code entity corresponding to a cursor position in a code editing interface; target graph nodes corresponding to the target code entities are recognized from the dependency graph, graph nodes in the dependency graph are used for representing the code entities, and edges are used for representing dependency relations between the code entities; cutting out adjacent sub-graphs related to target graph nodes from the dependency graph; according to the code snippets corresponding to the graph nodes in the adjacent sub-graphs and the code context of the cursor position, constructing cue words, taking the cue words as input of a large language model, and outputting codes to complement the text by the large language model; and displaying the code complementation text in the code editing interface.

The present application is applicable to the technical field of big data mining, and particularly relates to a cross-dataset graph association analysis method and apparatus, and a medium. The method comprises: determining matching pairs in external graph data and target graph data; acquiring a first path of any matching pair between a first vertex and a second vertex in the external graph data, and calculating a first ranking score representing the semantic importance of the first path in the external graph data; acquiring a second path in the target graph data that uses the first vertex as a starting point and has a secondary intersection with the first path, and calculating a second ranking score representing the semantic importance of the second path in the target graph data; and filtering the external graph data on the basis of the first ranking score and the second ranking score to obtain filtered external graph data, and performing association rule mining on the basis of the filtered external graph data and the target graph data to obtain a rule mining result. While reducing noise and errors, the present application expands the scope of rule discovery for target graph data, thereby improving the accuracy of graph association analysis.

The specification provides an optimization method, device, storage medium and equipment of a graph computing execution plan. In the method, an optimization rule is obtained; attribute information of a target graph operator in an initial graph computing execution plan is detected, if the attribute information of the target graph operator is detected to match the optimization rule, the target graph operator is optimized based on the optimization rule to obtain an optimized graph operator, and attribute information of the optimized graph operator and attribute information of other graph operators associated with the optimized graph operator in the initial graph computing execution plan are updated; and an optimized graph computing execution plan is determined according to each optimized graph operator. The scheme realizes effective optimization of the graph computing execution plan, and further guarantees performance improvement of the optimized graph computing execution plan.

The embodiment of the invention provides a knowledge graph creation method and device, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the steps of triggering a knowledge graph creation task process in response to a knowledge graph creation request sent by a user, and executing the following steps according to the knowledge graph creation task process: obtaining multiple pieces of entity data in a to-be-processed document and target relationship information among the multiple pieces of entity data; inputting the first prompt word, the multiple pieces of entity data and target relationship information among the multiple pieces of entity data into a first large language model to obtain a graph database import statement corresponding to the target graph database; and storing the graph database import statement into a target graph database to create a target knowledge graph based on the target graph database. The scheme is automatically carried out in the whole process, manual participation is not needed, cost is low, and efficiency is high.

The application discloses a knowledge graph abstract determination method and device, comprising: determining an initial graph abstract of a current version of a knowledge graph and a first candidate triple corresponding to the initial graph abstract; obtaining a user portrait of a target user; determining first operation information corresponding to the first candidate triple according to the initial graph abstract and the user portrait; determining a target graph abstract of the current version of the knowledge graph according to the initial graph abstract and the first operation information; predicting in combination with the initial graph abstract and the user portrait to determine the first operation information; and operating the initial graph abstract according to the first operation information to obtain the target graph abstract, so that the target graph abstract can reflect key information in the knowledge graph and can also take into account the interests and demands of the user.

The invention discloses an extensible and comprehensive graph converter graph representation learning method, system and device and a storage medium, and relates to the technical field of machine learning. The method comprises the steps of obtaining target graph data, determining corresponding node features, edge features and an adjacent matrix according to the target graph data, calculating a node embedding matrix and an edge embedding matrix of a graph, and generating an initial graph structure; based on the initial graph structure, transmitting an adjacent matrix into a graph coarsening module, generating a graph hierarchical structure by using a graph coarsening algorithm, and calculating an absolute position coding matrix and a relative position coding matrix of each graph layer; inputting each coding matrix into a comprehensive position coding module for merging to obtain a comprehensive position code; and inputting the comprehensive position code and the node embedding matrix into a focused graph linear attention module, calculating focused linear attention, and outputting final node representation. The efficiency and expression ability of graph representation learning can be improved.

The invention discloses a test data generation method and device based on an atlas and electronic equipment, the method is applied to the field of testing, and the method comprises the steps that atlas configuration information input by a target object is received, the graph configuration information at least comprises a plurality of relationship types, weight information of the plurality of relationship types, an entity creation mode and a target database type; generating a plurality of entities according to the entity creation mode; determining a relationship among the plurality of entities based on the plurality of relationship types and the weight information to obtain a target map; and generating a structured query language script according to the target database type and the target map, and executing the structured query language script through the target database to generate test data. By means of the method and device, the problem that in the related technology, when a large amount of test data is adopted for testing the atlas platform, the script needs to be manually input or repeatedly edited to generate the large amount of test data, and consequently the test efficiency is low is solved.

This invention discloses a method, apparatus, device, storage, and product for identifying abnormal objects. The method includes: generating an interaction dataset reflecting the interactive behaviors between different operation objects based on acquired operational behavior data generated by different operation objects on a target platform; constructing a target graph structure based on the interaction dataset; wherein the target graph structure reflects the interactive relationships between different operation objects, and includes at least two graph nodes, each corresponding to an operation object; determining abnormal nodes in the target graph structure, and identifying the operation object corresponding to the abnormal node as an abnormal object on the target platform. The technical solution of this invention can identify abnormal objects by comprehensively considering the mutual influence between various operation objects, which is beneficial to improving the accuracy of abnormal object identification.

The present invention discloses a backdoor-free model node injection attack method in a graph neural network, comprising: obtaining the original data set of the target graph neural network, pre-training an intermediary model based on the original data set; constructing a specific structure trigger generator model, and generating a trigger node to bind to the target node to obtain a poisoned data set; training a specific structure trigger generator model based on the poisoned data set and the intermediary model to obtain a general trigger generator model; constructing and training several graph neural network test models with different structures; obtaining a poisoned test data set based on the general trigger generator and the test data set; predicting the poisoned test data set using several graph neural network test models with different structures, and evaluating the attack performance based on the prediction results. The present invention solves the problems of existing backdoor attack methods that rely on the construction of backdoor models and complex node selection algorithms, thereby improving the concealment and practical operability of the attack methods.

A method of identifying a webpage, a device, and a medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of deep learning, knowledge graph and other technologies. The method of identifying the webpage includes: acquiring structural data of a target webpage, a first association relationship between the target webpage and a historical webpage, and historical graph data for the historical webpage; determining target graph data for the target webpage and the historical webpage based on the structural data of the target webpage, the first association relationship and the historical graph data; determining a similarity between the target webpage and the historical webpage based on the target graph data; and determining a category of the target webpage based on a category of the historical webpage and the similarity.

This invention discloses an automated migration method and system for graph database metadata, belonging to the field of graph database data migration technology. The method includes: acquiring metadata from a source graph database, including structural definitions of vertex and edge types; performing full sampling analysis on vertex and edge data in the source graph database to construct a distribution mapping relationship from vertices to types and a connection mapping relationship from edges to vertex types; generating graph structure definition statements for the target graph database based on the metadata, distribution mapping relationship, and connection mapping relationship, combined with a preset migration strategy; and sending the graph structure definition statements to the target graph database for execution to complete graph structure modeling. This application can meet the migration needs between different versions of graph databases and ensure data consistency and integrity, thus having broad application prospects.

The application relates to a cell type acquisition method and system, comprising the following steps: obtaining a cell node relationship graph according to a training cell of a sample table; performing structure conversion processing on the cell node relationship graph to obtain a cell tree structure; training an initial graph attention network according to the cell tree structure to obtain a target graph attention network; fine-tuning parameters of an initial large language model according to the target graph attention network and a preset soft prompt vector template to obtain a target large language model; and inputting a target table of a to-be-recognized cell type into the target large language model to obtain a cell type of each target cell of the target table. The application can improve the accuracy of cell type prediction in a complex table.

The invention provides a mouse event response method and device, equipment, a medium and a computer program product, and the method comprises the steps: determining a rectangular bounding box of each graph based on the position information of each graph in a canvas region; based on coordinate information of a mouse in the canvas area and the rectangular bounding box of each graph, determining the rectangular bounding box where the mouse is located; under the condition that a plurality of rectangular surrounding frames where the mouse is located exist, determining a mark attribute of a graphic element at the position where the mouse is located; responding to a mouse event corresponding to the target graph; the target graph is determined based on the mark attribute of the graph element. Compared with the prior art, the method has no limitation requirement on the graph in the canvas, and does not need to create excessive DIV elements, so that computer resources are saved, and the mouse event response speed and accuracy are improved.