48 results about "Partial graph" patented technology

The invention discloses a construction method, system and equipment of a power dispatching knowledge question-answering system and a storage medium. The construction method comprises the steps of obtaining a power dispatching semantic document needing to be processed by the power dispatching knowledge question-answering system; sequentially carrying out character-based segmentation, proposition conversion and proposition combination on the power dispatching semantic document on the basis of the large language model and the related cue words to obtain a plurality of text blocks; based on the large language model and the related prompt words, identifying and extracting entities related to power dispatching and relationships among the entities from each text block; constructing a local graph for each text block on the basis of the large language model and the related prompt words, the entities extracted from each text block and the relationship among the entities; traversing each text block, and combining all the local graphs into a global graph; and on the basis of the large language model and the related prompt words, according to the question type queried by the user, a reply text is correspondingly generated by matching a minimum local graph which is most related to the global graph in the global graph.

Methods and server systems for generating task-agnostic representations for nodes in bipartite graph are described herein. Method performed by server system includes accessing bipartite graph including first set of nodes and second set of nodes. Herein, set of edges exist between first and second set of nodes. Method includes performing for each node of first and second set of nodes: identifying a natural neighbor node, the natural neighbor node being a two-hop neighbor node from the each node, Then, generating temporary representation for one-hop neighbor node based on set of features corresponding to the one-hop neighbor node Then, generating temporary neighbor node based on temporary representation for the one-hop neighbor node. Then, generating augmented neighborhood based on the natural node and the temporary neighbor node, and then determining via machine learning model, task-agnostic representation for the each node based on augmented neighborhood.

Provided are a method of generating a partial area of an image by using a generative model and an electronic device for performing the method. The method of generating a partial area of an image by using a generative model includes obtaining an image comprising information of the partial area, obtaining an intermediate generated image by inputting the image into a first generative model, the intermediate generated image comprising first image information corresponding to the partial area, and obtaining a final generated image comprising second image information by inputting the image and the intermediate generated image to a second generative model, the second image information being at least partially different from the first image information.

During pretraining, a computer generates three untrained machine learning models that are a token sequence encoder, a token predictor, and a decoder that infers a frequency distribution of graph traversal paths. A sequence of lexical tokens is generated that represents a lexical text in a training corpus. A graph is generated that represents the lexical text. In the graph, multiple traversal paths are selected that collectively represent a sliding subsequence of the sequence of lexical tokens. From the subsequence, the token sequence encoder infers an encoded sequence that represents the subsequence of the sequence of lexical tokens. The decoder and token predictor accept the encoded sequence as input for respective inferencing for which respective training losses are measured. Both training losses are combined into a combined loss that is used to increase the accuracy of the three machine learning models by, for example, backpropagation of the combined loss.

The invention discloses a redundant space robot inverse kinematics solving method based on a graph neural network, and relates to the technical field of robot motion control and artificial intelligence crossing. A distance geometric graph is constructed to represent the configuration of the mechanical arm, an inverse kinematics problem is converted into a completion problem of a partial graph, joint configuration is sampled, and data pairs of a complete graph and the partial graph are stored as a data set; training based on an isotropic graph neural network and a conditional variation auto-encoder, and training a model based on a loss function of an evidence lower bound; and in the reasoning process, constructing a partial graph, inputting the partial graph into the trained prior network, outputting hidden variables meeting Gaussian mixture distribution, extracting sampling points, and generating a reconstructed complete graph to obtain joint angle information. The mechanical arm structure is represented through the distance geometric diagram, the inverse kinematics problem is converted into the complementation problem of partial diagrams, probability distribution of a solution space is learned through a conditional variation auto-encoder frame, multi-solution generation of different mechanical arm configurations is supported, and the solving precision and efficiency are high.

Provided are methods for hierarchical multi-object tracker for auto-labeling. Some methods include generating tracklets based on detections in sensor data. A weighted track graph is generated based on the tracklets, and the weight graph is converted to a bipartite graph. The bipartite graph is solved to determine at least one best path cover corresponding to respective observed objects, and the detections in the sensor data are labeled with a track identifier corresponding to the track representing the best path cover of a respective observed object. Systems and computer program products are also provided.

Methods, apparatuses, or computer program products disclosed herein provide for receiving an API object via a communication channel, applying a machine learning model to (i) the API object and (ii) one or more graph embedding structures for a portion of graph data to generate one or more predictive inferences related to the API object, and initiating a resolution action related to the API object based at least in part on the one or more predictive inferences.

According to the method for training the target model based on reinforcement learning, the target model is used for executing tampering detection on an input image, and the method comprises the steps that a training sample is obtained, the training sample comprises a target image and boundary information of a plurality of truth value boxes, and the truth value boxes are borders of a part of images marked in the target image and comprising tampering content; and inputting the target image into the target model, and outputting boundary information of the plurality of prediction frames. And calculating the overall overlap ratio of the plurality of prediction frames and the plurality of true value frames. Determining a first reward score based on a preset piecewise function according to a numerical range of the overall overlap ratio; the function corresponding to each numerical range of the piecewise function is a constant function, and the value of the corresponding constant function is increased along with the improvement of the overall overlap ratio. And based on a reinforcement learning algorithm, according to the first reward score, updating the target model.

Disclosed herein are various approaches for visualizing a graph-organized file system (GOFS) using a graphical user interface. A GOFS may represent a graph comprising a plurality of nodes and one or more edges representing one or more relationships between the plurality of nodes. A user interface comprising a representation of at least a portion of the graph may be rendered in a display accessible to one or more computing devices. A file system command for the GOFS may be received via the user interface, and the user interface may be modified based at least in part on executing the file system command.

Conventional techniques for explaining graph machine learning models are problematic, for example, in that when there are a plurality of graph patterns that contribute to a specific prediction, it is not possible to comprehensively present these graph patterns. This information output program causes a computer to perform processing for: identifying, for each of a plurality of sets of graph data corresponding to at least any one label that corresponds to a prediction result of a trained graph machine learning model, one or more nodes, the contribution of which to the prediction result of the set of graph data satisfies a prescribed condition; identifying, in each of one or more groups obtained by classifying the identified one or more nodes, a frequent graph pattern from partial graph data including the identified one or more nodes; and outputting information indicating the identified frequent graph pattern, as explanatory information for the trained graph machine learning model. This allows for improved explanation of the graph machine learning model.

A method of compiling an artificial neural network includes partitioning a graph representing an artificial neural network into partial graphs, determining a partial partitioning space which has to be intensively searched for in a total partitioning space and then generating node information about nodes associated with the partial partitioning space, in a case which defines, as the total partitioning space, a set including the number of all cases corresponding to a partitioning method capable of being used in a process of partitioning the graph into the partial graphs, partitioning the graph into the partial graphs by using an optimal partitioning method selected by configuring and searching for the partial partitioning space, based on the node information, and generating artificial neural network intermediate representations, based on the partial graphs, and arranging the artificial neural network in different computing hardware resources based on the artificial neural network intermediate representations.

An information processing device includes at least one hardware processor. The hardware processor is configured to divide an entire graph indicating a relationship between a plurality of elements into a plurality of partial graphs. The hardware processor is configured to set an objective function for learning a representation vector of a partial graph for each of the plurality of partial graphs. The hardware processor is configured to calculate n representation vectors by learning to optimize the objective function using each of n (n is an integer of 1 or more) setting values for each of the plurality of partial graphs.

The disclosed technology is generally directed to graph queries with reduced latencies. In one example of the technology, there is a cross-tenancy collaboration between two different tenancies: a first tenancy that is homed in a first geographical region and a second tenancy that is homed in a second geographical region. In the first geographical region, a first set of graph data is stored. The first set of the graph data is associated with the first tenancy. A portion of the first set of the graph data to be copied from the first geographical region to the second geographical region is determined. In response to determining the portion of the first set of the graph data, a copy of the portion of the first set of the graph data is stored in the second geographical region.

The application provides a longitudinal federated graph learning method and device satisfying differential privacy, which comprises the following steps: sending a learning request to a service party and other parties participating in longitudinal federated graph learning except a local party, obtaining graph structure coding information based on target conjecture graph structure information and an updated community set to generate disturbed graph structure coding information satisfying differential privacy; obtaining target shared graph structure information satisfying differential privacy based on the disturbed graph structure coding information and initial shared graph structure information to share with other parties; receiving target shared graph structure information from other parties, determining global graph structure information based on the target shared graph structure information and target conjecture graph structure information to reconstruct a global graph structure; and performing distributed training on a preset global graph model based on the global graph structure and local partial graph data by sending intermediate results to the service party to obtain a trained global graph model.

The compression device (101) is configured to include: a matrix acquisition unit (1) that sequentially acquires a partial feature matrix for each of a plurality of partial images into which an image is segmented; and a first global matrix calculation unit (3) that performs singular value decomposition on the first partial feature matrix acquired by the matrix acquisition unit (1), i.e., the first partial feature matrix, and calculates a first global singular value matrix containing the singular values ​​of the first partial feature matrix as the first global singular value matrix, and a first global right singular matrix containing the right singular vectors corresponding to the singular values ​​of the first partial feature matrix as the first global right singular matrix. In addition, the compression device (101) includes: an object matrix calculation unit (4) that calculates a matrix that is the object matrix of the bth singular value decomposition, which includes the bth partial feature matrix obtained by the matrix acquisition unit (1) (b is an integer of 2 or more), the (b-1)th global singular value matrix, and the (b-1)th global right singular matrix; and a second global matrix calculation unit (5) that performs singular value decomposition on the object matrix of the bth object matrix calculated by the object matrix calculation unit (4), calculates the singular value matrix of the object matrix of the bth object matrix that includes the singular values ​​of the object matrix of the bth object matrix as the global singular value matrix of the bth object matrix, and calculates the right singular matrix of the object matrix of the bth object matrix that includes the right singular vector corresponding to the singular value of the object matrix of the bth object matrix as the global right singular matrix of the bth object matrix.

1. Name of the design product: Main body of the graphical user interface for displaying medical information of an electronic device. 2. Use of the design product: For an electronic device, and the graphical user interface is used for displaying information. 3. Design key points of the design product: Lies in the partial interface content of the graphical user interface. 4. Picture or photo that best shows the design key points: Front view. 5. The electronic device has a conventional design, and other views of this design are omitted. 6. Use of the graphical user interface: The graphical user interface of this design is used for displaying medical information related to drug administration, and the claimed partial is for the main body of the graphical user interface. 7. Other circumstances that need to be explained: Other explanations: The solid line parts shown in the drawings are the parts claimed for this design product; the dashed line parts shown in the drawings are the parts not claimed for this design product.

This invention discloses a malware detection method based on adaptive node-edge joint masking. First, a function call graph of an Android application is constructed, and the structural and semantic features of nodes and edges are extracted. Then, a masking strategy is adaptively determined based on the relative importance of nodes and edges in the graph structure, and joint masking is applied to nodes and edges. On this basis, a graph neural network model is trained, enabling the model to learn stable and discriminative representations even when some graph structures or features are damaged. Finally, the trained model is used to detect malware in Android applications. This invention demonstrates effectiveness in improving the robustness and engineering practicality of Android malware detection models.

1. Name of the design product: Main body of the graphical user interface for displaying medical information of an electronic device. 2. Use of the design product: It is used for an electronic device, and the graphical user interface is used to display information. 3. Design key points of the design product: Lies in the partial interface content of the graphical user interface. 4. Picture or photo that best shows the design key points: Front view. 5. The electronic device has a conventional design, and other views of this design are omitted. 6. Use of the graphical user interface: The graphical user interface of this design is used to display medical information related to treatment plans, and the part claimed is for the main body of the graphical user interface. 7. Other situations that need to be explained: Other explanations: The solid-line parts shown in the drawings are the parts claimed for this design product; the dashed-line parts shown in the drawings are the parts not claimed for this design product.

The invention relates to the technical field of computer vision, in particular to a domain adaptation target detection method and system based on partial graph matching and electronic equipment, and the method comprises the following steps: respectively obtaining a marked source domain image and an unmarked target domain image; training a target detector through the source domain and target domain image features extracted by the shared feature extractor; comprising a feature extractor module, a graph neural network feature fusion module and a partial graph matching module. According to the method, the universe diagram fusing the category information of the source domain and the target domain is constructed, and joint reasoning is performed through the multilayer graph convolutional network, so that finer cross-domain feature interaction is realized. The problem that generalization is reduced due to the fact that isolated reasoning of an existing method lacks domain invariant feature learning is solved, the distribution alignment effect of different domains is enhanced through universe diagram joint reasoning, and therefore generalization of target detection in practical application is improved.

The present invention discloses a real-time anime avatar driving method, belonging to the field of image processing technology. The method comprises: obtaining a real-time user image; performing a 3DMM model solution on the real-time user image to obtain a target expression vector and a target head posture vector; semantically mapping the target expression vector to generate an expression change partial graph; and identically mapping the target head posture vector to the expression change partial graph to generate a three-dimensional reconstructed image, thereby driving the avatar. The present invention also discloses a real-time anime avatar driving system. The present invention can mass-produce high-quality datasets for anime avatar driving. Generating datasets using this method can implement a data-driven anime character avatar driving method. The present invention can also achieve lightweight mobile avatar driving.

This invention provides a method for putting a base station into a low-power consumption state. [Solution] The method includes the steps of receiving a measurement report transmitted wirelessly from a user device (UE), and creating a three-part graph in response to the measurement report, which includes a first set, a second set, and a third set of nodes. The first set of nodes represents a plurality of cells, and the third set of nodes represents a plurality of UEs that receive coverage from the plurality of cells. The method also includes the step of identifying cell coverage for the plurality of UEs based on the three-part graph using a set of active cells from the plurality of cells.

There is provided a data generation apparatus including a display control unit that displays, on a screen, an image and borders of a plurality of partial images generated by dividing the image into a plurality of pieces while the image and the borders are superimposed together, an input unit that receives input of a label to be given to each of the plurality of partial images, and a generation unit that generates learning data for causing a learning model to learn by associating each of the plurality of partial images with the label given to the corresponding partial image of the plurality of partial images.

The application discloses a kind of based on multilayer perceptron's graph classification model construction method and graph classification method, the former includes: the classification task of required application scene is acquired to several graph data and constitutes training set;At least part of graph data of training set has class label;Using training set, selected graph neural network is trained, and the graph neural network that training is completed is used as teacher network and saves the classification result corresponding to graph neural network;Selected multilayer perceptron is used as student model, based on training set, teacher network and corresponding classification result, student model is trained using the method of knowledge distillation, and the student model that training is completed is used as graph classification model for the remaining graph data classification of required application scene.The graph classification model of the application combines the respective advantages of multilayer perceptron and graph neural network, without the dependency of graph in reasoning process, ensure higher accuracy while can greatly reduce model calculation complexity, improve reasoning speed, can be used for time limited engineering deployment.

The application discloses a kind of fusion fault and feature industrial pump knowledge graph construction method.The method comprises: first, after analyzing the characteristics of unstructured data, to the data after pre-processing, ontology construction and knowledge extraction are carried out, and industrial pump fault graph is created using neo4j graph database.Then on the basis of structured data analysis, through system mechanism, experience knowledge and feature extraction, the entity and attribute extraction of feature graph is completed;Then the related features are classified by machine learning and deep learning algorithm, to provide relationship extraction method for the creation of feature graph, and create industrial pump feature graph.Finally, the fault graph and feature graph are fused by graph fusion method, and a unified knowledge graph is formed.Two partial graphs are used as search engine, and then fault report is generated.This comprehensive diagnostic capability greatly improves the efficiency and accuracy of fault solving, and can automatically generate detailed fault diagnosis report.

An image processing device including a processor or circuit configured to: acquire an input image; divide the input image into a plurality of partial images to obtain a partial image sequence; convert the partial image sequence into a token sequence by respectively converting each of the partial images includes in the partial image sequence into a token having a fixed-dimensional vector; obtain an encoded representation sequence based on an attention map indicating a degree of association between tokens and the token sequence; obtain a feature vector from the encoded representation sequence; and adjust at least parameters of the feature vector to reduce an attention loss value. The attention loss value corresponds to an error between a target value of the degree of association between the partial images and a value indicated by the attention map.

This invention belongs to the field of tunnel defect detection technology and provides a method for identifying tunnel lining defects based on a lightweight semantic segmentation model. The method includes: acquiring multiple partial images of the tunnel lining; stitching the multiple partial images together to obtain an unfolded image of the tunnel lining; inputting the unfolded image of the tunnel lining into a defect segmentation model; wherein the defect segmentation model includes a lightweight encoder and a U-Net style decoder; and post-processing the probability map output by the defect segmentation model to obtain the defect identification result. The technical solution of this invention, while balancing recognition accuracy and computational complexity, particularly improves the ability to identify linear defects such as fine cracks, and features low computational complexity and ease of edge deployment.

The present invention discloses a defense method, system, terminal and storage medium for backdoor attacks based on motif-based graph networks, belonging to the field of network security technology. By obtaining a target graph neural network model and a graph training set; randomly extracting a part of the graph data from the graph training set as a graph data subset; calculating the motif distribution in each class of graph data in the graph training set, selecting the trigger motif for each class of graph data, and embedding the trigger motif into the graph data of other classes in the graph data subset to form an enhanced graph data set; using the original graph in the graph data subset and the enhanced graph from the original graph as a pair of positive sample pairs to train the graph encoder; using the trained graph encoder to extract embedding features from real-time graph data, and using the embedding features as the input of the target graph neural network model to obtain an output result. This method can directly destroy the trigger structure inserted by the attacker in the graph, causing it to be unable to obtain the pre-specified result, and effectively resist backdoor attacks.

The invention discloses an industrial pump knowledge graph construction method fusing faults and features. The method comprises the steps that firstly, after characteristics of unstructured data are analyzed, ontology construction and knowledge extraction are conducted on preprocessed data, and an industrial pump fault map is created through a neo4j map database; then, on the basis of structured data analysis, entity and attribute extraction of the feature map is completed through a system mechanism, experience knowledge and feature extraction; and then fault classification is carried out on related features by utilizing a machine learning and deep learning algorithm, a relation extraction method is provided for creation of a feature map, and the industrial pump feature map is created. And finally, fusing the fault atlas and the characteristic atlas through an atlas fusion method to form a unified knowledge atlas. And generating a fault report by taking the two partial maps as a search engine. The comprehensive diagnosis capability greatly improves the fault solving efficiency and accuracy, and a detailed fault diagnosis report can be automatically generated.

A synthesis and distribution device 30 includes an encoding unit 32 for selecting a plurality of different partial images from a single image on the basis of a common identifier of the plurality of partial images and synthesizing the plurality of partial images, and transmits data of the synthesized plurality of partial images to another synthesis and distribution device including a decoding unit 36 for decoding an image using the data of the synthesized plurality of partial images.

The application discloses a kind of socialized recommendation method, device and medium based on user multi-intention, wherein method includes: obtaining data set, constructs graph structure data;Build the recommendation model containing two parts graph convolution network, for modeling user commodity interaction relationship and user social relationship in turn;Intention space mapping;Interaction intention decoupling learning;Self-adapting denoising;User social multi-influence learning;Unsupervised learning;Combination obtained final commodity feature vector, final user feature vector and unsupervised learning to train and learn recommendation model;The user and commodity feature vector that recommendation model finally learns are scored and predicted, and the recommended commodity order is obtained.The application fully mines the multi-intention influence in user commodity interaction, and the multi-influence of user social relationship, learns more fine-grained user representation and commodity representation, and obtains more accurate recommendation result.The application can be widely applied in the technical field of recommendation system.