42 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.

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 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 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.

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 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.

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.

The invention discloses a primitive variable association method and device, equipment, a medium and a product, and relates to the field of SCADA development, and the method comprises the steps: obtaining a first variable name, a preset variable name template and a preset step value associated with a target primitive from a configuration file of the target primitive in response to the generation of the target primitive, the target primitive is a primitive newly generated when a user performs copying operation on the to-be-copied primitive; determining an initial sequence number according to the first variable name; determining a target variable name according to a preset variable name template, the initial sequence number and a preset step value; and updating the first variable name in the configuration file of the target primitive according to the target variable name. The variable association efficiency of the copied primitives can be improved.

The invention discloses an enterprise intelligent knowledge base generation method based on a large language model, and the method specifically comprises the steps: S1, carrying out the cleaning, word segmentation and format unification processing of text, table and log data of an enterprise system, and inputting a result into an improved Mistral model; s2, setting a semantic gating unit in the model, introducing an enterprise knowledge embedding matrix, performing dynamic screening and field alignment on context semantic features, and generating a semantic vector with enterprise semantic features; s3, constructing a semantic relation graph based on the semantic vector and generating an enterprise semantic structure graph; s4, reading a target graph of a historical version or a heterogeneous system, inputting the enterprise semantic structure graph as a source graph into the unbalanced Gromov-Wasserstein alignment model, and completing semantic fusion through non-conservation regular constraint and semantic distance weighting; and S5, converting the fused semantic graph into standardized knowledge entries, and writing the standardized knowledge entries into an enterprise knowledge base to realize knowledge updating and semantic unification. According to the method, the enterprise knowledge automatic construction capability is improved, and cross-system fusion and continuous evolution are supported.

The application discloses a kind of three-dimensional building model and the linkage method, device, equipment and medium of two-dimensional drawing, the method includes: obtaining the three-dimensional model file of building, and the drawing file of building, the three-dimensional model file and drawing file are sent to backend equipment, the backend equipment is used to establish the binding relationship between model view in the three-dimensional model file and at least one two-dimensional drawing, the model view and at least one two-dimensional drawing are non-homologous graph model or partial homologous graph model;Receive the binding relationship, and according to the view interface of binding relationship display target two-dimensional drawing and model view, receive the click operation of user on view interface;In response to the click operation, determine the target component in the model view, or target graph element on target two-dimensional drawing, and show target component or target graph element, the present method realizes the linkage between non-homologous graph model, partial homologous graph model and two-dimensional drawing and three-dimensional model, satisfies joint examination demand.

The invention discloses a data accurate recall method, device and system based on a large model and an atlas, and belongs to the field of large language models. After the large model receives user input, obtaining a keyword list and an input vector input by the user; determining a first node in a target map based on the keyword list, and determining a second node in the target map based on an input vector; determining a preset number of target nodes in the first node and the second node; searching related nodes in the target map based on the target node; and taking the data of the related node as the context. According to the scheme, the nodes related to the user input in the target graph are determined through the keyword mode and the vector mode, then the data in the nodes are recalled to serve as the context, it is guaranteed that the recalled data are related to the user input, omission is avoided, and the accurate context is provided for the large model so that the large model can be output accurately.

The invention discloses a method, device and equipment for uniformly querying different types of graph databases based on SQL, and a medium, and relates to the technical field of graph databases. The method comprises the following steps: receiving an SQL query request; responding to the SQL query request, and adapting to a target graph database; the target graph database comprises a first class graph database with a native query language of Gremlin and a second class graph database with a native query language of SPARQL; analyzing the SQL query request into an intermediate representation, and converting the intermediate representation into a query plan of a native query language corresponding to the target graph database type based on a predefined conversion rule; the converted Gremlin query plan and / or the converted SPARQL query plan are / is distributed to the corresponding target graph database to be executed; and receiving a query result from the target graph database, integrating the query result, converting the query result into a unified structured data format, and outputting and / or visually displaying the query result in a preset format. According to the method, the multi-source graph data query efficiency and convenience of different types of graph databases are improved.

The invention provides a data updating method and device, a storage medium and computer equipment, and the method comprises the steps: determining a target hierarchy to which target vector data corresponding to a data updating operation belongs from each constructed layer of graph structure; the highest N layers of graph structures in all the layers of graph structures are stored in a memory table, and all the layers of graph structures except the highest N layers are stored in an SSTable of a disk in a layered mode; determining neighbor graph nodes of a target graph node corresponding to the target vector data under each hierarchy from graph nodes included in the graph structure of the target hierarchy and graph nodes included in graph structures of all hierarchies below the target hierarchy, and storing the neighbor graph nodes in a memory table; under the condition that the flash opportunity is triggered, target graph nodes corresponding to each data updating operation stored in the memory table and neighbor graph nodes of the target graph nodes under each level are written into an SSTable in a disk; the SSTable of each layer in the disk is merged and updated, and a new SSTable is obtained; the updated graph structure is stored in the new SSTable.

The invention relates to the field of graph storage, and provides a dynamic graph storage method, device and equipment, a medium and a computer program product, and the method comprises the following steps: obtaining insertion graph elements; the insertion graph elements comprise a first insertion element and a second insertion element; storing the first insertion element in a first storage part of an empty unit to obtain a first unit under the condition that the empty unit exists in the mapping bucket of the first insertion element; under the condition that the small slot of the second storage part of the first unit is full, storing the first table pointer into the large slot of the second storage part of the first unit, and determining a target hash table pointed by the first table pointer; storing the second insertion element and the target graph element into a target hash table; the target map element is a map element stored in a small slot of a second storage portion of the first cell. The data storage structure provided by the invention can be efficiently adjusted according to the dynamic change of the graph data, so that the query efficiency and access speed of the graph data are improved.

The invention discloses a secondary equipment graph description method and system based on template reuse. The method comprises the following steps: defining basic primitives and a description method thereof; constructing a secondary equipment graph description template library, wherein the template library comprises a graph frame, a symbol template and an equipment graph template; performing template instantiation based on the template library, generating a target graphic element of the secondary equipment, and associating the graphic element with a physical loop model; assembling the instantiated target graphic elements into a secondary equipment loop drawing; and storing the symbol template, the equipment graph template, the picture frame template and the picture album file according to a directory structure of the GIM model. According to the method, the design efficiency can be greatly improved, repeated drawing is reduced, the consistency of similar graphs in different designers and projects is ensured, cross-link collaboration is supported, and mistakes and omissions of manual association are avoided; in addition, a standardized graph description mode is provided, data management and sharing are facilitated, and the increasing digital requirements of power transmission and transformation projects are met.

The invention discloses an isomorphic sub-graph query optimization method and device, equipment and a medium, and the method comprises the steps: S1, obtaining a query graph, a target graph, a first path set, a second path set, a first query sub-graph and a first target sub-graph, S2, obtaining a query vertex and a target vertex, S3, enabling the query vertex and the first query sub-graph to form a first expansion sub-graph, s4, determining a query path from the first path set, determining a target path from the second path set, and embedding representation to obtain a query path vector and a target path vector, S5, inputting a target model to obtain a prediction result, and S6, if a preset condition is not met, returning to execute S3 until the preset condition is met, and if the preset condition is not met, returning to execute S3 until the preset condition is met. And S2, taking the first extended sub-graph as a first query sub-graph and the second extended sub-graph as a first target sub-graph, and returning to execute S2 until the query graph is matched, so as to obtain a query result corresponding to the second extended sub-graph. The query efficiency is improved, and the accuracy of the result is ensured at the same time.

This specification provides a training method, training system, and storage medium for a graph neural network. The training method for the graph neural network includes: the training system determining a target graphics processor (GPU) corresponding to a sampling task based on the label of the starting vertex of the sampling task; wherein the root queue of the target GPU includes at least one root vertex, the label of which is the same as the label of the starting vertex; the at least one root vertex includes hot vertices; the feature data of the hot vertices is cached in the local cache of the target GPU; and the sampling probability of the hot vertices satisfies a preset condition. Furthermore, the training system can utilize the target GPU to execute the sampling task based on the feature data of the hot vertices in the local cache to train the graph neural network.