66 results about "Goal graph" patented technology

The invention relates to a semantic query method and device based on measurement knowledge, computer equipment and a storage medium. The method comprises the following steps: acquiring a query question inputted by a user; repeating and transferring the query question to generate a synonymous question set; the synonymous question set comprises a plurality of synonymous questions matched with the semantics of the query question; based on a pre-established question template library, respectively generating target question templates corresponding to all synonymous questions in the synonymous question set, and determining target query statements respectively matched with all the target question templates according to keywords in all the synonymous questions; and based on a pre-established measurement knowledge graph, performing graph query by utilizing the target query statement to obtain a target graph element matched with the target query statement, and taking the target graph element as an answer to the query question. By adopting the method, user semantics can be accurately understood, and mixed retrieval of knowledge and documents is realized.

The invention relates to a big data technology, and discloses a knowledge graph-based text comparison method, which comprises the following steps: obtaining a training text, identifying a target entity and a target relationship in the training text, generating a graph by taking the target entity as a node and the target relationship as an edge, and taking the graph as an initial graph; marking a target entity and a target relationship of an initial graph, and clustering nodes of the initial graph according to the marked target entity and target relationship to obtain a target graph; obtainingto-be-compared texts, inputting the to-be-compared texts into the target atlas, and counting the coverage rate of entities and relationships extracted from each to-be-compared text on core informationin the target atlas; and if the coverage rate exceeds a preset threshold, judging that the to-be-compared text is a similar text. The invention also relates to a blockchain technology, and the to-be-compared text is stored in the blockchain. According to the invention, the text comparison accuracy and efficiency are improved in an atlas comparison mode.

Embodiments of the invention provide a data processing method, device and equipment and a medium, and the method relates to an artificial intelligence technology, can be applied to the field of natural language processing, and comprises the steps of obtaining a target text and a standard text, and generating a target entity sub-graph corresponding to the target text and a standard entity sub-graphcorresponding to the standard text according to a knowledge graph, wherein a first entity in the target entity subgraph and a second entity in the standard entity subgraph belong to entities in the knowledge graph; according to the first entity and the second entity, generating a target graph structure feature corresponding to the target entity sub-graph and a standard graph structure feature corresponding to the standard entity sub-graph; and determining graph similarity between the target entity sub-graph and the standard entity sub-graph according to the target graph structure features andthe standard graph structure features, wherein the graph similarity is used for indicating the association degree between the target text and the standard text. By adopting the embodiment of the invention, the matching accuracy between the target text and the standard text can be improved.

The embodiment of the invention discloses a method, system and device for determining an atlas for information recommendation. The method comprises the following steps: acquiring a plurality of nodesfor constructing a target graph; the nodes at least comprising word nodes and knowledge point nodes; if the node is a word node, taking the vector representation of the word corresponding to the nodeas the vector representation of the node; if the node is a knowledge point node, determining vector representation corresponding to the knowledge point node based on vector representation of words related to the knowledge point node; for any two nodes, determining an edge weight between the two nodes based on the types of the two nodes, and taking the edge weight as an association relationship between the two nodes; and performing at least one round of graph aggregation iteration based on the vector representation of the nodes and the association relationship between the nodes so as to updatethe vector representation of the nodes in the graph.

The invention provides a graphic resource conversion method and device, electronic equipment and a storage medium. The method comprises the following steps: when receiving a drawing end instruction ofan OpenGL or OpenGL ES graph input by a user, obtaining a user state set of all graph resource operations for drawing the OpenGL or OpenGL ES graph; and mapping the user state set to a correspondinghardware device or initializing the user state set to a virtual memory to simulate the corresponding hardware device to perform conversion between an OpenGL or OpenGL ES graphic resource interface anda corresponding target graphic resource interface. That is to say, on the basis of not changing the original OpenGL or OpenGL ES upper-layer code architecture, the original OpenGL or OpenGL ES upper-layer code architecture is not changed, when the drawing ending instruction of the OpenGL or OpenGL ES graph is received, the corresponding target graph resource interface is determined according to all the obtained graph resource operations of drawing the graph, so that the conversion of the graph resources is realized, and the workload and the research and development cost of graph special effect rendering research and development personnel are reduced.

The embodiment of the invention provides a federal learning-based model parameter updating method, device and equipment, and the method comprises the steps: receiving a model parameter updating instruction which is issued by a federated learning server and aims at a target graph neural network model, wherein the model parameter updating instruction carries a first sharing parameter, and the target graph neural network model is a common model of a plurality of federated learning clients; based on the first shared parameter, a locally stored first independent parameter and map data constructed by local user private data, training the target map neural network model to obtain a model parameter of the trained target map neural network model; and sending the second sharing parameter to the federated learning server, so that the federated learning server updates the first sharing parameter of the target graph neural network model based on the second sharing parameter sent by a plurality of federated learning clients.

Embodiments of the invention disclose a model optimization method and device, computer equipment and a storage medium. The method comprises the steps of obtaining target map data; performing semi-supervised learning on the first model by adopting each node feature and target label information in the target graph data to obtain a second model; calling a second model to carry out label prediction on each label-free node to obtain a prediction label of each label-free node and the confidence coefficient of each prediction label; on the basis of the confidence of each prediction label, selecting one or more difficult samples from the N non-label nodes, wherein the difficult samples refer to the non-label nodes corresponding to the prediction labels with the confidence meeting a preset condition; and performing model optimization on the second model by adopting one or more difficult samples to obtain the target model, so that the performance of the graph processing model can be improved.

The invention relates to the field of artificial intelligence, and provides a word sense disambiguation method and device based on a graph expansion structure, equipment and a medium, which can extract candidate nodes in an initial graph according to a created window, realize the expansion of the graph, and then improve the connectivity. The weight of each edge is calculated according to the text similarity between the two candidate nodes corresponding to each edge and the word meaning similarity between the two candidate nodes corresponding to each edge, and the importance of each candidate node is determined according to the weight of each edge, so that high semantic and emotion information is explored and captured, and the word meaning disambiguation accuracy is improved; and according to the importance degree of each candidate node, interference removal processing is performed on the candidate map to obtain a target map, so that the word sense disambiguation efficiency is improved through interference removal processing, center measurement is carried out on the target map to obtain a target word sense, and the improvement of the word sense disambiguation effect is realized. In addition, the invention also relates to a block chain technology, and the target map can be stored in a block chain node.

The invention provides a method for quickly drawing a layout. The method comprises the following steps: setting an auxiliary layer in the layout; a plurality of reference patterns are laid in the auxiliary pattern layer, and the intervals of the adjacent reference patterns are equal; the reference graph is a preset regular graph; when a graph is drawn on the target graph layer, automatically acquiring the vertex position of the input graph and adjusting the position to enable the graph to accord with a preset graph rule of the target graph layer; the graph rule of the target graph layer is set based on the reference graph. According to the layout drawing method and the layout drawing device, the drop points which do not conform to the graphic rule of the target layer can be adjusted by setting the auxiliary layer and combining the graphic rule of the preset target layer, layout drawing is visually assisted, then rapid layout drawing is achieved, and the drawing accuracy and the working efficiency are greatly improved. The invention further provides a system for rapidly drawing the layout, and the system has corresponding advantages due to the fact that the method can be executed for drawing.

The invention discloses a Faster R-CNN-based graph model construction method, and the method specifically comprises the steps: 1, transmitting a target image into a trained Faster R-CNN-based target detection network model, and outputting a detection frame corresponding to each target in the target image; 2, screening the target detection frames according to a set threshold value, and removing redundant target detection frames; 3, distributing a unique label to the target detection frame; 4, dividing targets of the image into primary targets and secondary targets, and then constructing a target tree for the secondary targets; 5, determining the relative position relation between the two objects; and 6, constructing a graph model of the image according to the target tree and the position relationship between the targets. According to the Faster R-CNN-based graph model construction method provided by the invention, the established graph model can effectively represent the spatial layout and semantic relation of each target in the target image.

The invention provides a method and a device for identifying an abnormal account in a game, electronic equipment and a storage medium, and relates to the technical field of games. The method comprises the steps of obtaining a sample data set, wherein the sample data set comprises game logs of at least one game virtual object under a target game within a preset time period; according to the game log of each game virtual object and a pre-established knowledge graph architecture, constructing a target graph, wherein the target graph is used for representing information of the game virtual objects; based on the target map, determining a target abnormal virtual object and an abnormal account corresponding to the target abnormal virtual object; according to the game log of the target abnormal virtual object and the data of the abnormal account corresponding to the target abnormal virtual object, training a target recognition model, wherein the target recognition model is used for recognizing whether the game account corresponding to the to-be-recognized virtual object is the abnormal account or not. According to the method, the accuracy and efficiency of abnormal account identification can be improved.

The invention discloses a method for processing an auxiliary graph by adopting a visual editing graph database. The method comprises the following steps: S1, establishing a target graph database; the target graph database comprises a plurality of target graphs, and each target graph comprises a main graph and an auxiliary graph; s2, defining the size of a graph search range; s3, defining a limiting condition of graph matching; the limiting condition comprises an anchor point of the main graph and a line width size range of the auxiliary graph; s4, performing graph scanning on the whole test layout, finding out a matched graph meeting the limiting condition, marking the matched graph, and outputting the matched graph and marked layout data; and S5, determining at least one auxiliary graph according to the layout data of the matched graph.

The invention relates to a computer device for creating a knowledge graph, which is used for acquiring a knowledge graph creation instruction sent by a target user, carrying out identity verificationon the target user according to a user identity character field in the knowledge graph creation instruction, acquiring target graph data and target schema if the identity verification is passed, performing longitudinal fusion on the target map data and the target schema to obtain an initial knowledge map of the vertical field, then obtaining an associated knowledge map according to the initial knowledge map and a preset knowledge map database, and finally performing transverse fusion on the initial knowledge map and the associated knowledge map to obtain a final knowledge map. The finally obtained knowledge graph not only contains the knowledge graph of the target field, but also expands transversely and contains the associated knowledge graph, so that the situation that the finally obtained knowledge graph is relatively limited and cannot meet the actual requirements can be avoided.

The invention discloses a comment data quality analysis method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining target comment data to be subjected to quality analysis; analyzing the comment contents and the comment phrases to obtain a comment theme corresponding to the target comment data, and obtaining an association relationship set among the comment theme, the comment contents and the comment phrases; generating an initial graph structure based on the comment contents, the comment phrases, the comment themes and the association relationship set, and converting the comment contents, the comment themes and the comment phrases in the initial graph structure into corresponding initial embedded matrixes to obtain a target graph structure; and inputting the target graph structure into a pre-trained graph attention model to obtain a quality analysis result of the target comment data. According to the method, the graph structure is generated by establishing the relation among the theme, the content and the word group, so that the comments are completely covered, meanwhile, feature analysis is performed on the graph structure based on the graph attention model, and the accuracy of comment quality analysis is improved.

The invention relates to the technical field of image processing, and discloses a method and a system for realizing high-speed preview of a graph. The method comprises the steps of: drawing an initialgraph through employing a Canvas plug-in according to an instruction inputted by a user; obtaining a first coordinate corresponding to the initial graph; converting the first coordinate into a secondcoordinate corresponding to an OpenGL (Open Graphics Library); drawing a target graph according to the second coordinate; and outputting the target graph for a user to preview. Visibly, the fine graph is drawn based on the Canvas plug-in, and then the OpenGL is adopted to efficiently move and output the graph, so that the operated graph can be displayed at a high speed for the user to preview after the user operates the graph, and the use experience of the user is improved.

The invention discloses a stable graph structure learning method and device, and relates to the field of machine learning, and the method comprises the steps: obtaining a graph structure implied witha biased relation in each environment through a data-driven mapping method according to a plurality of given biased sampling environments; obtaining the probability that each point in the graph structure is associated with a symbiotic data sample according to the graph structure of each environment and a multi-environment data generation mechanism; initializing a target graph structure, randomly sampling a symbiotic data sample in a plurality of environments, setting conditions for the symbiotic data sample, respectively obtaining a generation probability in each biased environment and a generation probability under an implicit relationship of the target graph structure, and taking the generation probability of the target graph structure as a mean value of the generation probability of each environment; and carrying out loop iteration until a convergence condition is satisfied so as to obtain a stable graph structure. According to the method, estimation deviation of parameters in a graph structure is reduced, and stable performance is kept in a complex and changeable test environment.

The method is suitable for the technical field of data display, and provides a component relation graph generation method and device, and the method comprises the steps: obtaining a graph generation instruction, carrying out the semantic analysis of a front-end system according to the reference component information, which is contained in the graph generation instruction and is used for generatinga component relation graph, so as to obtain all components, which have an association relation with a reference component, from the front-end system; then arranging the reference component and all the components having the association relationship with the reference component on the basis of a target map template, so as to generate a corresponding component relationship map according to the target map template, wherein the target map template is determined through a selection rule preset by the front-end system. According to the method, developers can determine the overall architecture and functional boundary of the component more clearly, and testers can evaluate the change difference and risk boundary of the component more accurately.

The embodiment of the invention discloses a graph drawing method and device. The graph drawing method and device are used for solving the burr problem of graphs and improving the visual effect of the graphs. The method includes the steps that a target graph is drawn on a control, a transparent background layer is drawn on the control and located on the next layer of the target graph, a non-border window is drawn on the control, the background of the non-border window is a bit map of the position overlapped with the background layer, and the non-border window is located on the former layer of the target graph. Due to the fact that the background of the non-border window is the same as the transparent background layer of the target graph, when the target graph is covered with the non-border window, burrs of the target graph can be covered, and the visual effect of the graph can be improved.

The invention relates to the field of microelectronic device modeling, and provides a graph screening method and device for a device modeling tool, a server and a storage medium, and the method comprises the steps: firstly obtaining a graph screening rule set comprising a plurality of pre-configured graph screening rules; secondly, screening out a target graph set from the original graph set according to one graph screening rule in the graph screening rule set; and finally, grouping and sequencing the target graph set according to a pre-configured graph sequencing rule. Therefore, tree structure nodes of an original graph set can be traversed through different screening statements, keyword query containing original graph storage names is carried out, and a target graph set to be called is rapidly and accurately selected; and grouping and sorting are performed the target graph set according to the judgment statement and the sorting statement with the preset target graph parameter thresholds, thereby effectively improving the efficiency and accuracy of graph data analysis in device modeling.

The invention discloses a graph generation method and device, and the specific implementation scheme is as follows: in response to a received graph generation request, receiving information which is input by a user and corresponds to the graph generation request and an instruction which is sent by the user and corresponds to the graph generation request; in response to a received graph generation instruction sent by a user, based on received first information input by the user, determining graph information corresponding to the first information, and generating a first graph corresponding to the graph information; in response to a received product acquisition instruction sent by the user, acquiring target product information corresponding to second information input by the user; based on the matching result of the target product information and the first graph, generating a target graph corresponding to the matching result, wherein the target graph is used for representing the specific position of the target product in the first graph. According to the scheme, the method for quickly and simply determining whether the furniture required by the user is matched with the house type or not is realized.

The invention provides a graph erasing control method and device and a processor. The method comprises the following steps: acquiring attribute information of a graph in a first area; performing logical operation on at least part of attribute information to obtain a target attribute combination; determining at least part of the area on the interface as a second area; according to the target attribute combination, the target graph in the second area is deleted, and the target graph is a graph conforming to the target attribute combination. In the scheme, as the attribute information is subjected to logical operation to obtain the target attribute combination, when the graph is erased, only the graph of which the attribute information conforms to the target attribute combination can be erased, that is, only the target graph is erased without mistakenly erasing other graphs on the interface, so that the specified graph can be accurately erased, and the user experience is improved. Therefore, the problem that the specified graph cannot be accurately erased in the prior art is solved, so that when a user erases the specified graph, the user does not need to carefully erase the graph, and the user experience effect is good.