226 results about "Connected component" patented technology

The invention discloses a load transfer path regulation and control method and system based on a maintenance topology rule base, and relates to the technical field, and the method comprises the following steps: constructing a graph model, obtaining a load node of a shutdown device in the graph model, and obtaining a load path switching node based on a connected component analysis method; correcting the graph model to obtain a power grid topological graph of load path switching nodes, and generating a load path switching scheme based on a shortest path algorithm; a pre-switching adjustment strategy is set, and a load transfer action instruction is generated and executed step by step based on a load path switching scheme; carrying out local control on load transfer path adjustment based on a load transfer action instruction and a distributed control technology; the optimal load switching path is identified through connected component analysis and the shortest path algorithm, and the load transfer path of the maintenance equipment is controlled and switched according to the load transfer action instruction in combination with the distributed control technology, so that the stability, the flexibility, the response speed and the regulation and control precision of load path regulation and control are improved.

The invention provides a layout file geometric data processing method, a computer device and a storage medium. The method comprises the steps that a layout file of a three-dimensional chip is obtained, polygonal entities and layer information are extracted, the polygonal entities are distributed to corresponding layer containers, and an independent R tree index is created for each layer; performing connectivity analysis on the polygonal entity, and returning a connected component set and performance analysis statistical information; when an independent R-tree index is created for each layer, data of all polygonal entities of a single layer is obtained, a minimum boundary rectangle is generated for each polygonal entity, R-tree indexes are constructed for different layers in parallel by adopting a plurality of threads, whether the number of node entries of the R-tree indexes exceeds a splitting threshold value or not is judged, and if yes, splitting processing is carried out on nodes; and verifying the consistency of the created R tree index and the original data. The computer device and the storage medium can realize the method. The geometric data processing efficiency of the layout file can be improved.

The invention discloses a rapid local repair method for a self-intersecting triangular mesh. According to the method, local processing and rational number calculation are combined, aiming at an input low-quality triangular mesh, firstly, the mesh quality is optimized through a preprocessing step, intersection areas are positioned, then the mesh is partitioned based on octree division and connected component analysis, and the intersection areas and non-intersection areas are separated. In each intersection area, a shape-preserving boundary three-dimensional grid optimization method based on rational numbers is adopted to ensure the robustness of intersection calculation, and surface grids are extracted after successful conversion into floating-point number representation. And finally, seamlessly splicing the repaired local grid and the non-intersecting grid, and improving the overall grid quality through an edge re-gridding method based on curvature self-adaption. According to the method, the non-intersecting high-quality grid can be quickly generated, the method is suitable for downstream applications such as finite element analysis, meanwhile, the calculation overhead is remarkably reduced, and the algorithm robustness is improved.

The invention discloses a handwritten element automatic segmentation and extraction method for a complex layout, relates to the technical field of handwritten element automatic segmentation and extraction, and aims to solve the technical problem that the recognition and separation precision of handwritten contents in a mixed image-text layout is insufficient. S201, a dynamic threshold segmentation algorithm is carried out; s202, context sensing connected domain analysis is carried out; s203, judging whether the elements are handwritten elements or not; s204, if the judgment result is yes, the handwriting region candidate is reserved; and S205, if not, filtering and eliminating. According to the method, the dynamic threshold segmentation algorithm and the context sensing connected domain analysis technology are cooperated, the segmentation threshold can be adaptively adjusted according to the pixel mean value and the standard deviation of the image local window through dynamic threshold segmentation, and the context sensing connected domain analysis is combined with the context information of the document to perform semantic analysis on the connected domain. The problem that the recognition and separation precision of the handwritten content in the mixed image-text layout is insufficient is solved.

The invention provides a method for eliminating metal artifacts in a cone beam CT (computed tomography) projection domain, which comprises the following steps of: converting a current frame projection image IC into a binarization image IL and an edge detection image IG, marking connected domains in the IL and the IG, and deleting non-metal artifact area connected domains, so that binarization and edge detection results can be mutually verified; the accuracy of metal artifact area detection is improved; obtaining an extended bounding rectangle Ri, ext of each connected domain in the IM, and effectively eliminating metal artifacts according to the extended bounding rectangles Ri, ext; by segmenting the metal artifact area in the projection domain image, the resolution of the image is protected, and the artifact elimination effect is improved.

The invention discloses an individual tree segmentation method based on machine learning, and particularly relates to the field of individual tree segmentation. The method comprises the following steps: respectively acquiring forest point cloud data through a ground scanner and an unmanned aerial vehicle, registering the forest point cloud data into a complete data set, preprocessing the point cloud data, extracting geometric, reflective and spatial distribution multi-dimensional features, and fusing the geometric, reflective and spatial distribution multi-dimensional features into a comprehensive feature vector; training a model by using a machine learning method based on the labeled data, taking the feature vector as input, and outputting whether the point belongs to a tree or not; predicting a point category by using the trained model, performing individual tree instance segmentation by using a connected component clustering and graph segmentation method through CRF post-processing optimization, constructing a 3D model and calculating key parameters; and finally, performing post-processing on a preliminary segmentation result, filtering noise by using connected region analysis, filling the deficiency by using a three-dimensional hole, optimizing a boundary based on graph segmentation, and optimizing a block seam by using an ICP (Inductively Coupled Plasma) algorithm.

The present invention relates to a method for analyzing the connectivity of communication nodes based on a knowledge graph, and relates to the field of communication network analysis. The present invention manages communication nodes and the relationships between them through a graph database, and dynamically screens the node relationships in combination with time attributes and communication types. The specific steps include: first, obtaining all nodes and relationships that meet the specified time conditions, and grouping them by communication type; then, constructing a graph for each communication type and applying a breadth-first search algorithm to identify connected components; finally, processing the relationships between nodes based on the attributes of the communication type, and identifying the set of interconnected nodes under each communication type. The present invention aims to efficiently analyze the connectivity between nodes in a communication network. The present invention can efficiently process large-scale network topologies, is flexible, and is particularly suitable for dynamic and real-time changing communication network environments. It has broad application value, especially in communication network modeling and analysis.

Embodiments of the present disclosure relate to the field of deep learning, and provide a model evaluation method and apparatus, a device, a program, and a medium. The method comprises: acquiring a test image, the test image comprising a foreground area and a background area; inputting the test image into a target classification model, to obtain a target classification result, the target classification result at least comprising target feature information and target attribute information; inputting the test image into an attribution analysis model, to acquire an attribution graph corresponding to the test image; using the test image as a reference, analyzing a connected component in the attribution graph, and determining a type of the connected component, the type of the connected component being a foreground type or a background type; on the basis of the type of the connected component, determining whether the target classification model is a qualified target classification model, and on the basis of the type of the connected component, determining whether the target classification result is a trusted result.

The invention relates to the technical field of artificial intelligence, in particular to a question and answer method and system based on LLM fusion knowledge graph and retrieval enhancement generation. The entities which are connected with the known entities and do not appear in the local knowledge graph are marked as related entities through the graph structure connection relation, a new local knowledge graph is formed, descending sorting is carried out according to the edges and the weights in the connected components, when the weights are the same, the lexicographical order of the entity names is used as a second sorting key, and the second sorting key is used as a third sorting key; and after sorting is completed, according to the sorting sequence, until the accumulated number of the documents reaches a preset number, combining the finally obtained individual documents with the questions, and inputting the combined documents and the questions into a large language model to generate a final answer. According to the method, the accuracy and interpretability of questions and answers can be effectively improved, the illusion problem of a large language model is solved, and reliable knowledge service support is provided for a complex decision-making scene.

The invention provides a node clustering method based on communication network connectivity analysis, and belongs to the technical field of network analysis. The method comprises the following steps: constructing a graph model according to input nodes and a connection relationship thereof, wherein the construction of a graph supports a single network or multi-network relationship; traversing each node in the graph by using a depth-first search algorithm, recording an access path, and classifying the nodes with a communication relationship into the same communication component; and outputting a set of all connected components. According to the method, when the graph is constructed, topology analysis of various network conditions in the undirected graph is supported by dynamically judging the nodes and the neighbor relation of the nodes. The method has the advantages of low calculation complexity and high expansibility, is suitable for the fields of network communication, equipment connectivity check, complex command and control system information transmission modeling and the like, and provides an efficient and accurate solution for connectivity analysis.

The invention discloses a subway power distribution system fault prediction and operation and maintenance method based on big data analysis. The method comprises the steps of S1, data preprocessing; s2, constructing a topological graph of the power distribution network; s3, extracting node space embedding based on multi-head GAT; s4, generating time embedding through bidirectional LSTM and time attention; s5, fusing spatio-temporal features across spatio-temporal attention; s6, only using normal samples to train an auto-encoder to learn a reconstruction function; s7, adaptively generating a threshold value in the sliding window by using the GMM, and mapping a reconstruction error into a risk score; and S8, when the risk score exceeds a dynamic threshold value, automatically dividing a suspected fault area according to a connected component, and issuing early warning information including a risk grade, the suspected fault area and a disposal suggestion. According to the method, prospective prediction of the fault risk of the subway power distribution system can be realized, so that operation and maintenance personnel can take preventive measures in advance, and efficient and stable operation of the subway power distribution system is ensured.

The invention relates to the technical field of process control, in particular to a radiation environment laboratory full-process traceable system and a processing method.According to the radiation environment laboratory full-process traceable system and processing method.By executing timestamp sequence extraction, attribute difference screening and path structure decomposition operation on detector records and shielding cover logs, causal, time sequence and role attachment relation edges between nodes are established; and classifying attribute values to construct a unified mapping set, converting the multi-source heterogeneous data into a flow chart structure with relevance, executing node embedding operation through a graph attention network algorithm, and performing adjacent node feature weighted aggregation and edge weight screening processing based on an embedding result. And calling a Tarjan strong connected component algorithm to analyze a node branch structure, identifying a heterogeneous sub-graph in a flow path by branch index difference, executing priority ranking and task insertion actions in combination with the number of available tokens and lead plate thickness grade parameters, and generating a dynamic scheduling sequence under a multi-task coexistence condition in a control path.

The invention relates to the technical field of data cleaning, in particular to an automatic heterogeneous data cleaning method and system based on a configurable rule engine. The method comprises the following steps: acquiring a heterogeneous data source, uniformly converting a data mode and an instance into a multi-dimensional heterogeneous fact graph, calculating an execution weight for each conflict rule according to the authority of the data source and the priority of the rule when a write operation conflict is detected, segmenting data partitions by utilizing the betweenness centrality of a connected component and a node, the method comprises the following steps of: generating a plurality of data partitions, forming rule subsets corresponding to the data partitions, creating isolated Drools session instances to perform parallel cleaning, generating traceability logs in the parallel cleaning process, aggregating the traceability logs after all the data partitions are cleaned, and re-evaluating and updating the authority of each data source to solve rule conflicts in the next cleaning period. According to the scheme, the writing conflict can be precisely processed, the safety of parallel cleaning is improved, the processing period is shortened, and a continuously optimized processing closed loop is formed.

The invention belongs to the technical field of robot path planning, and particularly discloses a robot path planning method based on large language model guidance, and the method comprises the steps: discretizing an environment space, and building a configuration space of a robot and an obstacle; calculating a collision area in real time and segmenting a free space into connected components; generating a prompt text; calling a large language model to analyze the text and outputting a recommended obstacle list; constructing a path tree; generating a new node; generating candidate paths based on new node backtracking, and allowing node poses to shift in a preset range through a tolerance verification mechanism; and when the target area is connected with the connected component, adding the path into the solution set library, and selecting an optimal solution according to a weighted cost function of a minimum path length and a total obstacle moving distance. The search strategy is optimized by using the semantic understanding ability of the large language model, the efficiency and adaptability of path planning in a dynamic environment are remarkably improved, and the method is suitable for scenes such as warehouse logistics and disaster rescue.

The invention discloses an Internet of Things distributed monitoring data synchronization method based on port machinery equipment state, which comprises the following steps: taking a fault sign as a node, and if the co-occurrence frequency between two nodes is greater than a preset value, constructing an undirected edge; constructing a fault group according to each connected component; acquiring image data through a plurality of information acquisition terminals, and analyzing whether a fault sign exists or not; obtaining residual fault signs in the corresponding fault group, generating a to-be-detected task, and broadcasting the to-be-detected task in the information acquisition terminal group; the information acquisition terminal calculates the spatial distance between the information acquisition terminal and each to-be-detected task, and the information acquisition terminal corresponding to the minimum value is used as a task execution terminal to confirm residual fault signs; summarizing residual fault sign confirmation conditions, generating a fault confidence coefficient, and forming a recheck message; according to the method, isolated alarm is converted into group early warning, the fault advanced sensing capability is remarkably improved, and the calculation amount of a data center is reduced through co-occurrence relation mining and group division of fault signs.

The invention discloses a CAE (Computer Aided Engineering) workflow control subsystem and method based on cloud computing, and belongs to the technical field of crossing of computer simulation and cloud computing, and the subsystem comprises a workflow configuration analysis module which is used for converting a CAE workflow configuration file possibly containing cyclic dependence into a directed acyclic graph state machine through strong connectivity component analysis; the workflow state machine operation module is used for dynamically deriving task groups which can be executed in parallel in the next stage in the state machine according to the current state; and the workflow scheduling module is used for submitting the tasks to a cloud solving platform in parallel and realizing fault recovery through state persistence. Through deep fusion of a graph theory method and a cloud computing architecture, automatic scheduling, efficient parallel execution and reliable fault tolerance of the CAE workflow are realized, and the computing resource utilization rate and the system reliability are remarkably improved.

A method for decoding a mesh includes receiving a bitstream including coded information of the mesh that includes a first group of connected components that has a first connectivity. The method includes determining at least one portion of the first connectivity. The at least one portion of the first connectivity is shared by at least one region of each connected component in the first group. The method includes for each connected component in the first group, determining attribute values of vertices in the at least one region of the respective connected component.

The invention relates to the technical field of old-age nursing task automatic generation and distribution, and discloses an old-age nursing task automatic generation and distribution method. The overall process comprises the steps of collecting basic data of the old people and nursing personnel, defining original variables, performing standardization processing on the data, and calculating feature distances between the old people; then adaptively determining distance scale parameters, constructing a similarity matrix and extracting connected components, and realizing demand clustering of the elderly; and on the basis, a greedy strategy is adopted to select the least nursing personnel to cover the service demand, tasks are accurately distributed according to the capability proportion, and a result is output. According to the method, a whole-process closed loop from data acquisition to task allocation is realized, and the method has an end-to-end automation capability. Through standardized modeling, similarity calculation, graph theory clustering and a greedy optimization algorithm, the scheme realizes intelligent nursing management in a resource limited environment.

The invention discloses an orbit foreign matter detection method and system, and relates to the technical field of orbit detection.The method comprises the steps that an unknown foreign matter model is built through Gaussian distribution and a convex hull algorithm, and a known foreign matter model is built in combination with prior data; extracting a flat area of the ballast bed, projecting the foreign body model into a depth map and generating a shadow, and superposing to obtain a synthetic image with a mark; training a segmentation network by using the synthetic image and a real image, and obtaining a potential foreign matter mask through thermodynamic diagram binaryzation, connected domain analysis and size screening during reasoning; and inherent facility false alarms are eliminated through a secondary classification network, a real foreign matter detection result is finally output, alarm is triggered according to a detected threshold value, and efficient and accurate detection is realized. According to the method, on the premise that real foreign matter samples are scarce and ballast bed scenes are complex, efficient, accurate and real-time ballastless track foreign matter detection is achieved, meanwhile, the false alarm rate is reduced, and the generalization ability of the model to unknown foreign matter is improved.

The invention provides an online dynamic water quality fingerprint rapid acquisition and preprocessing device and method. The method comprises the steps that intelligent flow path selection is achieved through graph theory modeling, a water quality monitoring system is modeled into a directed weighted graph, bilateral connected component decomposition is carried out to recognize system vulnerabilities, and a redundant flow path is configured to improve the fault-tolerant capability; adopting an optimal transmission theory to optimize dilution control, modeling a dilution problem as an optimal transmission problem of spectral distribution, and calculating an optimal dilution ratio through a linear space super-gradient algorithm; a matrix flipping graph search algorithm is applied to accelerate spectrum calculation, a spectrum data matrix is abstracted into a flipping graph model, and an optimal matrix flipping operation sequence is found through heuristic search. According to the method, the efficiency, precision and robustness of water quality monitoring are remarkably improved, the monitoring efficiency is improved by 50%, the measurement error is reduced by 70%, and the calculation speed is improved by 5-10 times.

The invention provides an image foreign matter detection method capable of reducing false detection probability. The method comprises the following steps: searching a difference region between a to-be-detected image and a standard image; binarizing the image according to the difference region to obtain a binarized abnormal image; inputting a to-be-detected image into the false detection model, and marking false detection points and non-false detection points; binarizing the image according to the false detection points to obtain a binarized false detection image; searching a connected domain Ai and a connected domain Bj in the two binarized images respectively, wherein the connected domains are recorded as the connected domain Ai and the connected domain Bj; if the consistency of a certain connected domain Ai and any connected domain Bj meets the requirement, deleting the connected domain Ai; marking the connected domain Ai which is not deleted in the to-be-detected image as a foreign matter region; according to the method, a deep learning model classification method and an image processing method are fused, the robustness of the foreign matter detection method is enhanced, suspected areas are screened through fusion of the two methods, and the false detection rate of foreign matter detection is effectively reduced; the anti-interference capability is stronger, and the foreign matter area positioning is more accurate.

The invention discloses a fault propagation path determination method and device, a storage medium and electronic equipment, and relates to the field of Internet of Things. The method comprises the following steps: acquiring a target data set; a service calling graph is constructed according to the target data set, then strong connectivity vectors in the service calling graph are determined, and the service calling graph is used for representing a topological structure and a dependency relationship of service interaction in the distributed system; the strong connectivity vector is used for representing a connectivity component of which the bidirectional calling frequency is greater than a preset frequency and / or the data interaction strength is greater than a preset strength in the service calling graph; performing neighborhood feature aggregation on the service call graph to obtain a time sequence feature matrix; and determining a fault propagation path of the distributed system according to the strong connectivity vector and the time sequence characteristic matrix. According to the method and the device, the technical problem of poor fault propagation path prediction accuracy caused by lack of quantification of dependency relationship and topological association between services in fault propagation prediction in the prior art is solved.

The invention discloses an unmanned aerial vehicle landslide image clustering method and device for emergency monitoring, and belongs to the technical field of landslide monitoring. The method comprises the following steps: acquiring an original image shot by a camera mounted on an unmanned aerial vehicle; extracting multi-modal features of the landslide instance from the original image, wherein the multi-modal features comprise a spatial position feature, a global semantic embedding feature and a local geometric matching feature; fusing the multi-modal features by using a neural network model based on an attention mechanism to generate an instance feature vector; on the basis of the spatial position features, the local geometric matching features and the instance feature vectors, through an iteration process including a feedback mechanism, a graph structure representing the incidence relation between the landslide instances is constructed; and connected components in the graph structure are extracted, and each connected component is determined as a landslide instance cluster. According to the invention, different image instances belonging to the same landslide can be accurately associated, and the error rate of cross-frame target matching under a complex terrain is reduced.

The invention relates to the field of computer vision, in particular to a road defect self-adaptive detection method and system. The method comprises the following steps: acquiring an original road surface image, and generating a plurality of feature views by using the original road surface image; based on the feature view, performing reasoning by using a plurality of pre-constructed defect detection models to obtain an initial detection frame and a corresponding initial confidence coefficient; constructing a detection frame topological association graph by using the initial detection frame and the initial confidence coefficient, and obtaining a connected component of a potential defect target based on the detection frame topological association graph; calculating a fusion defect position and a fusion confidence coefficient based on the connected component; and carrying out adaptive updating on the defect detection model by utilizing the fusion defect position and the fusion confidence coefficient. The problems of insufficient robustness and long-term effectiveness of model identification caused by insufficient environmental adaptability, easy attenuation of model performance due to data drift and single decision-making mechanism in road defect detection in the prior art are solved.

The invention relates to the technical field of computer graphic processing, in particular to an intraoral scanning interactive segmentation method based on self-adaptive curvature, which comprises the following steps: importing a three-dimensional model into a system, calculating the curvature value of each vertex by the system by adopting a self-adaptive curvature analysis method, and identifying and extracting a gingival margin line part; correcting an inaccurate part through an interactive interface to ensure the continuity and accuracy of the gingival margin line; gradually expanding adjacent vertexes and patches which conform to a curvature threshold based on the seed points, and extracting a complete gingival margin line; accurate control on the form of the gingival margin line is realized through a self-adaptive curve fitting morphological processing method; the system uses a connected component detection algorithm to identify and segment the independent dental crown area, and each connected component is classified into an independent dental crown or gingival area to realize segmentation. According to the method, curvature analysis and a small amount of manual interaction are combined, so that the method can adapt to diversified tooth forms and maintain relatively high segmentation precision.

A portable electronic system receives a set of one or more canonical maps and determines the sparse map based at least in part upon one or more anchors pertaining to the physical environment. The sparse map is localized to at least one canonical map in the set of one or more canonical maps, and a new canonical map is created at least by merging sparse map data of the sparse map into the at least one canonical map. The set of one or more canonical maps may be determined from a universe of canonical maps comprising a plurality of canonical maps by applying a hierarchical filtering scheme to the universe. The sparse map may be localized to the at least one canonical map at least by splitting the sparse map into a plurality of connected components and by one or more merger operations.

The application relates to a key node identification method, device, equipment and medium of an electric power coupling network. A power station and a power-on relay in an electric power system are taken as an application node and a transition node of a physical layer network respectively, a logical node is constructed by the application node, a logical layer network of a structure of an undirected and weightless graph representing communication capability is built, the electric power system is modeled into a physical-logical coupling network, a logical edge centrality score in the logical layer network is calculated by using a hybrid centrality measurement, a logical edge criticality list is arranged in descending order according to the scores, a target logical edge is selected according to the sequence, corresponding transition nodes in the physical layer network are determined, a plurality of shortest paths between the two are calculated, path nodes are taken as candidate nodes to be removed, the candidate nodes and corresponding logical edges are removed, a change of a maximum connected component of the logical layer network is taken as a damage rate, and when the damage rate reaches a preset value, the removed nodes are key nodes. The method can effectively and quickly identify key nodes of an electric power network.

This invention provides a drawing processing method and system based on scene text recognition. It identifies all graphic and non-graphic elements within the global scope of a drawing. Based on the shape features of the graphic elements, it divides the drawing into several sets of non-graphic elements. Based on the connected components of all non-graphic elements within each set, it generates several text strings corresponding to those sets and performs fuzzy classification to identify the text results of the non-graphic element sets. Based on the spatial distribution information of the graphic and non-graphic elements on the drawing, it preprocesses the text results and overlays them onto the corresponding areas of the drawing, distinguishing between non-graphic and graphic elements. It also performs connectivity recognition on the non-graphic elements, initially labeling the text strings within them to obtain their corresponding text results. This achieves synchronous association recognition of graphics and text within the drawing, improving the efficiency and accuracy of drawing editing.

This invention discloses a method for generating network game optimization strategies based on a hybrid node and edge strategy. The method includes: acquiring the network topology, determining the strategy sets of the attacker and defender, and constructing a basic model of the network game; calculating the attack and defense costs of nodes and edges in the network based on the network topology and network metrics, and determining the cost constraints of the attacker and defender; considering the hybrid attack and defense strategies of nodes and edges, obtaining the strategy sets of the attacker and defender; using the maximum connected component size index to represent network performance, calculating the payoffs of the attacker and defender under each strategy profile, and obtaining the payoff matrix of the network game model; and converting the basic model of the network game into a linear programming problem for solution, obtaining the hybrid strategy Nash equilibrium solution of the attacker and defender.

An example operation may include at least one of determining, by a transformer encoder trained on annotated image-text data, first latents for a first dataset stored in a memory, and second latents for a second dataset stored in the memory, generating a similarity matrix based on comparisons between the first latents and the second latents, constructing a graph comprising nodes corresponding to the first latents and edges based on pairwise similarity exceeding a threshold, identifying connected components in the graph and selecting, from each component, at least one latent having a highest score from a classifier trained to approximate divergence between the first dataset and the second dataset, forming a reduced dataset comprising the at least one latent, providing the reduced dataset to a model training module, and training an image classifier using the reduced dataset and the second dataset.